DETAILED ACTION
Notice of Pre-AIA or AIA Status
The present application, filed on or after March 16, 2013, is being examined under the first inventor to file provisions of the AIA .
Response to Remark(s)
Applicant's amendment filed July 14th, 2026 have been fully entered and considered. Regarding the arguments to the previous prior art rejections, the examiner respectfully finds the arguments to be non-persuasive, see response to remarks section below. Accordingly, this action is made final.
Status of Claims
Claims 1-20 are pending, claims 8-10 have been amended. Claims 1-20 remains rejected.
Response to Argument(s)
Regarding the Applicants’ argument on the prior art rejections:
In pages 6-11 of the Applicants’ remarks, filed on July 14th, 2026, the Applicants argue that the proposed Sabol does not teach or suggest the features of the claims:
Corresponding claims 1, 2, 5, 8 and 9:
“individual frame of the video to determine multiple locations of a candidate object in that individual frame;
vision processor…configured to process the thermal image to obtain multiple candidate locations of the drogue in the thermal image”
As the Applicants state that the proposed Sabol does not teach or suggest these features, therefore the claims 1, 2, 5, 8 and 9 as stated above, now should be allowed, therefore, the dependent claims 3-4, 6-7, 10-20 are allowed based on dependency.
In support of the above argument, the Applicants state that Sabol describes a tracking algorithm that processes detected candidate objects in motion across video frames producing a time and spatial history for each, and the Office Action, mailed on June 22nd, 2026, mapped the spatial history of an object over the multiple frames to the candidate locations of claim 1. While Sabol processes a candidate object over multiple frames to detect a spatial history of the candidate object over the multiple frames, Sabol does not teach the features of the claims as shown above, which is different to what Sabol describes.
Moreover, although Sabol describes tracking a lighted drogue, Sabol only describes using visible light imagery, not thermal imagery to cover the claimed features as discussed above.
Examiner’s reply:
The examiner respectfully disagrees with the Applicants’ argument. Importantly, the proposed Sabol teaches, in Par. [0033] of “pixel clusters that represent individual objects in motion…for each candidate object in motion, the pixels are differenced in the video frames sequentially by subtracting an adaptive temporal background, the subtraction at least removing clutter from the differenced frame…resulting in candidate objects in motion appearing as the only pixel cluster” which indicates within each single image frame of the video frames, such as disclosed in Par. [0029] of “a difference in pixel counts for each bat in the current video frame is calculated for comparison, and if multiple bats, each identified as one of the pixel clusters, are found within the search radius…potential bats being viewed only for a single video frame”, wherein, pixel clusters of different objects/bats being identified within the each single image frame of the video frames, and being tracked across multiple image frames of the video frames. Therefore, the claimed limitation of “individual frame of the video to determine multiple locations of a candidate object in that individual frame” falls within this teaching of Sabol, wherein the individual clusters represent different objects identified within the single image frame, is analogous to the recited “multiple locations of a candidate object”. The examiner recognizes the Applicants uses a different language to the claim, instead of multiple locations of a drogue, the Applicants uses “multiple locations of a candidate object” to refer the object to the drogue for the purpose of making this argument. Therefore, the examiner respectfully recognizes and reminds the Applicants that the claims are construed based on BRI (broadest reasonable interpretation) in light of the specification, wherein when the claim recites multiple locations of a drogue/a candidate object, it can be understood that object to be obtained locations of being a drogue, that indicates there are multiple locations of a drogue within a single image, not necessary only one single drogue being shown multiple locations instantaneously, based on BRI scope of the claim, it can be understood a candidate object/a drogue indicating a name of an object type, such as an object of bat, an object of drogue, here the reference Sabol teaches an object of bat. Nevertheless, the proposed Sabol still teaches that multiple clusters within a single image can be identified to represent multiple instances of objects, however, potential clusters that are identified to be potentially representing the same tracked object/bat, and then the processing continues to find the best match to be the tracked object/track within the same single image frame, such as disclosed in Par. [0029] of “each identified as one of the pixel clusters, are found within the search radius, a search radius that is closest the predicted location and closest in size to an individual tracked pixel cluster is selected as a best fit”. Furthermore, Sabol teaches the object of being processed can also be of a drogue, Par. [0064] discloses “employ algorithms using a visible light imagery to track vehicles at an intersection and to track lighted drogues progressing through a hydraulics model” indicating the object to be tracked can be a drogue associated with a vehicle.
Regarding the Applicants’ argument to the limitation of “vision processor…configured to process the thermal image to obtain multiple candidate locations of the drogue in the thermal image”, the examiner respectfully disagrees with the Applicants’ argument. The examiner finds Sabol to teach the claimed limitation, in Par. [0037] of “video-rate thermal imagery” and Par. [0064] of “visible, IR or the UV light spectra…using visible light imagery to track”, therefore, the visible IR imagery is also IR that is a thermal imagery.
Therefore, the prior art rejections remain, claims 1-20 are still rejected using the proposed prior art Sabol and the corresponding prior arts in 102 and 103 rejections as set forth below.
Claim Rejections - 35 USC § 102
The following is a quotation of the appropriate paragraphs of 35 U.S.C. 102 that form the basis for the rejections under this section made in this Office action:
A person shall be entitled to a patent unless –
(a)(1) the claimed invention was patented, described in a printed publication, or in public use, on sale, or otherwise available to the public before the effective filing date of the claimed invention.
(a)(2) the claimed invention was described in a patent issued under section 151, or in an application for patent published or deemed published under section 122(b), in which the patent or application, as the case may be, names another inventor and was effectively filed before the effective filing date of the claimed invention.
Claims 1-2, 5, 8, 11-12, 15 and 17-18 are rejected under 35 U.S.C. 102(a)(1) as being anticipated by Bruce M. Sabol et. al. (“US 2011/0081043 A1” hereinafter as “Sabol”).
Regarding claim 1, Sabol teaches a device comprising (Title and Abstract): a thermal imaging sensor configured to generate a thermal image (Par. [0018] discloses “detect, track and count moving objects digitally captured with video-based thermal imagery. A camera with IR lens…” indicating the use of a thermal imaging sensor to generate thermal image to track object) depicting a drogue attached to a vehicle (Par. [0064] discloses “employ algorithms using a visible light imagery to track vehicles at an intersection and to track lighted drogues progressing through an hydraulics model” indicating the object to be tracked can be a drogue associated with a vehicle); a vision processor coupled to the thermal imaging sensor (Par. [0038] discloses “thermal imagery is digitally recorded and in select embodiments of the present invention transferred to a suitable processor” indicating a vision processor coupled with the imager, is analogous to the vision processor as claimed), wherein the vision processor is configured to process the thermal image to obtain multiple candidate locations (Par. [0034] discloses “a Tracking Algorithm processes detected candidate objects in motion across video frames producing a time and spatial history for each” indicating candidate objects with spatial history [analogous for candidate locations] for each frame) of the drogue in the thermal image (Par. [0064] discloses “employ algorithms using a visible light imagery to track vehicles at an intersection and to track lighted drogues progressing through an hydraulics model” indicating the object to be tracked can be a drogue detected in the thermal video frame) and one or more scores associated with each of the candidate locations (Par. [0033] discloses “candidate objects in motion having at least one characteristic of their signature in a range that is approximately equal to the range of a characteristic in the signature of an established temporal background behind the object in motion” indicating a characteristic signature generated for each candidate object in a range that is measurable, therefore, is analogous to one or more scores associated with each of the candidate locations as claimed); and a second processor configured to process the candidate locations and the one or more scores associated with each of the candidate locations to generate a tracked position of the drogue (Par. [0033] discloses “the specially configured computer processes the capture images by employing algorithms, a first algorithm applies so that for each candidate object in motion…to predict a next position of a candidate object in motion, and each algorithm is iterated for successive video frames to generate an output of individual tracks of each candidate object in motion” indicating using a specially configured computer [second processor as claimed] to process the candidate locations and their signatures to obtain output of individual tracks of the object [tracked position of the drogue]).
Regarding claim 2, Sabol teaches the device of claim 1, wherein the vision processor is configured to generate a first set of the candidate locations (Par. [0027] discloses “a tracking algorithm establishes a four lists: a Pixel Cluster List loaded for each selected video frame; a Potential List; a Tracking List; and a Target List” indicating a set of candidate locations) based on a first image processing operation (Any of the four lists indicated is analogous to the first set of the candidate locations, moreover, Par. [0027] discloses “in addition to the above lists, the method implements four processes” any of which is analogous to the first processing operation and its associated list to be analogous to the first set of the candidate locations) and a second set of the candidate locations based on a second image processing operation (Any of the four lists, that was not selected as the first set, indicated is analogous to the second set of the candidate locations, moreover, Par. [0027] discloses “in addition to the above lists, the method implements four processes” any of which, that was not selected as the first processing operation, is analogous to the second processing operation and its associated list to be analogous to the first set of the candidate locations) that is distinct from the first image processing operation (Par. [0027] discloses “a tracking algorithm establishes a four lists: a Pixel Cluster List loaded for each selected video frame; a Potential List; a Tracking List; and a Target List… in addition to the above lists, the method implements four processes” indicating the four distinct processes, therefore, the fist and the second selected processes accordingly would be distinct from each other).
Regarding claim 5, Sabol teaches the device of claim 1, wherein the vision processor is configured to perform thermal thresholding on the thermal image to identify pixels having intensity values that satisfy a thermal threshold (Par. [0037] discloses “present invention, un-calibrated video-rate thermal imagery…was captured…frames were then differenced with an adaptive temporal background to remove stationary clutter, and thresholded to select only pixels at the tail ends of the statistical distribution of differenced pixels” indicating a thresholding on thermal image based on pixel to identify certain pixels meeting the threshold [thresholding on thermal image according to pixels being analogous to thermal thresholding as claimed and the threshold is analogous to a thermal threshold as claimed]; furthermore, Par. [0022] discloses “temporal filtering process…the location and value of difference pixels meeting a user-specified threshold are save to a detected pixel report for subsequent processing…the value for each pixel…is determined by taking the mode of the histogram of pixel values for each location” indicating the threshold, as discussed, is based on pixel values meeting a threshold of a histogram of pixel values [analogous to intensity values as claimed]).
Regarding claim 8, Sabol teaches the device of claim 1, wherein the second processor is configured to provide information associated with the tracked position of the drogue to the vision processor (Par. [0038] discloses “thermal imagery is digitally recorded and in select embodiments of the present invention transferred to a suitable processor” indicating a vision processor coupled with the imager, is analogous to the vision processor as claimed, the selected embodiments being transferred to a suitable processor indicating that the information associated with the tracked position of the drogue, as being one of the embodiments as discussed, being provided to the vision processor as claimed), wherein the information associated with the tracked position includes at least one of an updated range to the drogue or an updated range to the vehicle (“or” indicates a selection, only one of the options is the instant scope of the claim, the examiner selects “updated range to the drogue”, wherein Sabol’s Par. [0038] discloses “thermal imagery is digitally recorded and in select embodiments …transferred to a suitable processor”, moreover, Par. [0043] discloses “the threshold value is chosen to eliminate all or almost all background…For bats imaged from a considered distance…it is desirable to set the threshold low to achieve as many pixels on target as possible, while still remaining above background noise. For bats imaged at a close range, e.g., less than 50-100 yards, it is preferable to set a high threshold so that only the body of the bat, and not its wings, are evident in the resultant image” wherein, the thermal imagery thermally and digitally recorded is analogous to the recited information associated with the tracked position, moreover, the resultant image/the digitally recorded thermal image being chosen a threshold range value to capture the object and eliminate noise, therefore, the chosen threshold for a range of imaging is analogous to the recited updated range).
Regarding claim 11, Sabol teaches a method comprising (Title and Abstract): receiving, at a vision processor of a device, a thermal image (Par. [0018] discloses “detect, track and count moving objects digitally captured with video-based thermal imagery. A camera with IR lens…” indicating the use of a thermal imaging sensor to generate thermal image to track object) depicting a drogue attached to a vehicle (Par. [0064] discloses “employ algorithms using a visible light imagery to track vehicles at an intersection and to track lighted drogues progressing through an hydraulics model” indicating the object to be tracked can be a drogue associated with a vehicle); processing, at the vision processor, (Par. [0038] discloses “thermal imagery is digitally recorded and in select embodiments of the present invention transferred to a suitable processor” indicating a vision processor coupled with the imager, is analogous to the vision processor as claimed) , the thermal image to obtain multiple candidate locations (Par. [0034] discloses “a Tracking Algorithm processes detected candidate objects in motion across video frames producing a time and spatial history for each” indicating candidate objects with spatial history [analogous for candidate locations] for each frame) of the drogue in the thermal image (Par. [0064] discloses “employ algorithms using a visible light imagery to track vehicles at an intersection and to track lighted drogues progressing through an hydraulics model” indicating the object to be tracked can be a drogue detected in the thermal video frame) and one or more scores associated with each of the candidate locations (Par. [0033] discloses “candidate objects in motion having at least one characteristic of their signature in a range that is approximately equal to the range of a characteristic in the signature of an established temporal background behind the object in motion” indicating a characteristic signature generated for each candidate object in a range that is measurable, therefore, is analogous to one or more scores associated with each of the candidate locations as claimed); and processing, at a second processor of the device, the candidate locations and the one or more scores associated with each of the candidate locations to generate a tracked position of the drogue (Par. [0033] discloses “the specially configured computer processes the capture images by employing algorithms, a first algorithm applies so that for each candidate object in motion…to predict a next position of a candidate object in motion, and each algorithm is iterated for successive video frames to generate an output of individual tracks of each candidate object in motion” indicating using a specially configured computer [second processor as claimed] to process the candidate locations and their signatures to obtain output of individual tracks of the object [tracked position of the drogue]).
Regarding claim 12, Sabol teaches the method of claim 11, wherein processing the thermal image to obtain multiple candidate locations (Par. [0027] discloses “a tracking algorithm establishes a four lists: a Pixel Cluster List loaded for each selected video frame; a Potential List; a Tracking List; and a Target List” indicating a set of candidate locations) includes generating, at the vision processor, a first set of the candidate locations based on a first image processing operation (Any of the four lists indicated is analogous to the first set of the candidate locations, moreover, Par. [0027] discloses “in addition to the above lists, the method implements four processes” any of which is analogous to the first processing operation and its associated list to be analogous to the first set of the candidate locations) and a second set of the candidate locations based on a second image processing operation (Any of the four lists, that was not selected as the first set, indicated is analogous to the second set of the candidate locations, moreover, Par. [0027] discloses “in addition to the above lists, the method implements four processes” any of which, that was not selected as the first processing operation, is analogous to the second processing operation and its associated list to be analogous to the first set of the candidate locations) that is distinct from the first image processing operation (Par. [0027] discloses “a tracking algorithm establishes a four lists: a Pixel Cluster List loaded for each selected video frame; a Potential List; a Tracking List; and a Target List… in addition to the above lists, the method implements four processes” indicating the four distinct processes, therefore, the fist and the second selected processes accordingly would be distinct from each other).
Regarding claim 15, Sabol teaches the method of claim 11, further comprising performing, at the vision processor, thermal thresholding on the thermal image to identify pixels having intensity values that satisfy a thermal threshold (Par. [0037] discloses “present invention, un-calibrated video-rate thermal imagery…was captured…frames were then differenced with an adaptive temporal background to remove stationary clutter, and thresholded to select only pixels at the tail ends of the statistical distribution of differenced pixels” indicating a thresholding on thermal image based on pixel to identify certain pixels meeting the threshold [thresholding on thermal image according to pixels being analogous to thermal thresholding as claimed and the threshold is analogous to a thermal threshold as claimed]; furthermore, Par. [0022] discloses “temporal filtering process…the location and value of difference pixels meeting a user-specified threshold are save to a detected pixel report for subsequent processing…the value for each pixel…is determined by taking the mode of the histogram of pixel values for each location” indicating the threshold, as discussed, is based on pixel values meeting a threshold of a histogram of pixel values [analogous to intensity values as claimed]).
Regarding claim 17, Sabol teaches a non-transitory, computer readable medium storing instructions that, when executed by one or more processors that include a vision processor and a second processor, cause the one or more processors to perform operations comprising (Title and Abstract and Par. [0024] discloses “embodiments of the present invention, a method for tracking bats employs one or more specially configured computers incorporating computer readable storage media containing…software” indicating the use of a computer which is known to have a processor executing instruction program stored in the storage media for processing the instructions of the invention): receiving, at the vision processor, a thermal image (Par. [0018] discloses “detect, track and count moving objects digitally captured with video-based thermal imagery. A camera with IR lens…” indicating the use of a thermal imaging sensor to generate thermal image to track object) depicting a drogue attached to a vehicle (Par. [0064] discloses “employ algorithms using a visible light imagery to track vehicles at an intersection and to track lighted drogues progressing through an hydraulics model” indicating the object to be tracked can be a drogue associated with a vehicle); processing, at the vision processor, the thermal image (Par. [0038] discloses “thermal imagery is digitally recorded and in select embodiments of the present invention transferred to a suitable processor” indicating a vision processor coupled with the imager, is analogous to the vision processor as claimed) to obtain multiple candidate locations (Par. [0034] discloses “a Tracking Algorithm processes detected candidate objects in motion across video frames producing a time and spatial history for each” indicating candidate objects with spatial history [analogous for candidate locations] for each frame) of the drogue in the thermal image (Par. [0064] discloses “employ algorithms using a visible light imagery to track vehicles at an intersection and to track lighted drogues progressing through an hydraulics model” indicating the object to be tracked can be a drogue detected in the thermal video frame) and one or more scores associated with each of the candidate locations (Par. [0033] discloses “candidate objects in motion having at least one characteristic of their signature in a range that is approximately equal to the range of a characteristic in the signature of an established temporal background behind the object in motion” indicating a characteristic signature generated for each candidate object in a range that is measurable, therefore, is analogous to one or more scores associated with each of the candidate locations as claimed); and processing, at the second processor, the candidate locations and the one or more scores associated with each of the candidate locations to generate a tracked position of the drogue (Par. [0033] discloses “the specially configured computer processes the capture images by employing algorithms, a first algorithm applies so that for each candidate object in motion…to predict a next position of a candidate object in motion, and each algorithm is iterated for successive video frames to generate an output of individual tracks of each candidate object in motion” indicating using a specially configured computer [second processor as claimed] to process the candidate locations and their signatures to obtain output of individual tracks of the object [tracked position of the drogue]).
Regarding claim 18, Sabol teaches the non-transitory, computer readable medium of claim 17, wherein the operations further include generating, at the vision processor, a first set of the candidate locations (Par. [0027] discloses “a tracking algorithm establishes a four lists: a Pixel Cluster List loaded for each selected video frame; a Potential List; a Tracking List; and a Target List” indicating a set of candidate locations) based on a first image processing operation (Any of the four lists indicated is analogous to the first set of the candidate locations, moreover, Par. [0027] discloses “in addition to the above lists, the method implements four processes” any of which is analogous to the first processing operation and its associated list to be analogous to the first set of the candidate locations) and a second set of the candidate locations based on a second image processing operation (Any of the four lists, that was not selected as the first set, indicated is analogous to the second set of the candidate locations, moreover, Par. [0027] discloses “in addition to the above lists, the method implements four processes” any of which, that was not selected as the first processing operation, is analogous to the second processing operation and its associated list to be analogous to the first set of the candidate locations) that is distinct from the first image processing operation (Par. [0027] discloses “a tracking algorithm establishes a four lists: a Pixel Cluster List loaded for each selected video frame; a Potential List; a Tracking List; and a Target List… in addition to the above lists, the method implements four processes” indicating the four distinct processes, therefore, the fist and the second selected processes accordingly would be distinct from each other).
Claim Rejections - 35 USC § 103
The following is a quotation of 35 U.S.C. 103 which forms the basis for all obviousness rejections set forth in this Office action:
A patent for a claimed invention may not be obtained, notwithstanding that the claimed invention is not identically disclosed as set forth in section 102, if the differences between the claimed invention and the prior art are such that the claimed invention as a whole would have been obvious before the effective filing date of the claimed invention to a person having ordinary skill in the art to which the claimed invention pertains. Patentability shall not be negated by the manner in which the invention was made.
The factual inquiries for establishing a background for determining obviousness under 35 U.S.C. 103 are summarized as follows:
1. Determining the scope and contents of the prior art.
2. Ascertaining the differences between the prior art and the claims at issue.
3. Resolving the level of ordinary skill in the pertinent art.
4. Considering objective evidence present in the application indicating obviousness or nonobviousness.
Claims 3-4, 13-14 and 19-20 are rejected under 35 U.S.C. 103 as being unpatentable over Bruce M. Sabol et. al. (“US 2011/0081043 A1” hereinafter as “Sabol”) in view of Walter Clark et. al. (“US 2004/0071346 A1” hereinafter as “Clark”).
Regarding claim 3, Sabol teaches the device of claim 2, Sabol wherein the first image processing operation includes (Any of the four lists indicated is analogous to the first set of the candidate locations, moreover, Par. [0027] discloses “in addition to the above lists, the method implements four processes” any of which is analogous to the first processing operation and its associated list to be analogous to the first set of the candidate locations; wherein Par. [0027] discloses “four processes:…clearing unmatched bats from the Potential List, creating new candidate objects for each pixel cluster remaining in the Pixel Cluster List and placing all unmatched bats in the current video frame on a potential list for input into a next process for a next video frame, and adding candidate bats to the Potential List” which is analogous to the first processing operation as claimed).
However, Sabol does not explicitly teach the first image processing operation includes at least one of a gradient-based circle detection of an outer edge of a drogue basket, a gradient-based spoke detection of inner spokes of the drogue basket, or a transform-based template matching detection of the drogue basket.
In the same field of object detection and tracking (Title and Abstract, Clark), Clark teaches the first image processing operation includes at least one of a gradient-based circle detection of an outer edge of a drogue basket, a gradient-based spoke detection of inner spokes of the drogue basket, or a transform-based template matching detection of the drogue basket (“at least one of….or” indicating a selection, therefore, only one of the options is required to be the instant scope of the claim, the examiner selects “a transform-based template matching detection of the drogue basket” which is disclosed in Clark’s Par. [0098]”, which discloses “such as frequency domain Fourier Transform are performed…in order to accomplish template matching” indicating a transform-based template matching detection of the object to track the object through images [analogous to the process of Sabol as discussed above]. Therefore, it would have been obvious to one or ordinary skill of the art at the time the invention was made to have the first process of tracking of objects through images through matching of object to a criteria to be modified to be based on a transform-based template matching detection as taught by Clark. Thus in order to have a method that can process template matching process without drawback when a certain condition is not met such as a function of the Sobel-chaincode is not cyclical, therefore, it is more effective and robust to use transform-based templating matching through Fourier Transform, see Clark’s Par. [0098]).
Therefore, it would have been obvious to one of ordinary skill in the art before the effective filing data of the claimed invention was made to combine the teachings of Sabol of a device with a first and second processing algorithms to process the images. Moreover, Sabol’s first processing algorithm can be modified to includes at least one of a gradient-based circle detection of an outer edge of a drogue basket, a gradient-based spoke detection of inner spokes of the drogue basket, or a transform-based template matching detection of the drogue basket as taught in Clark.
Such a modification is the result of combing prior art elements, wherein both Sabol and Clark share the same endeavor of object detection and tracking through template matching. The motivation for the proposed modification would have been to have a first processing algorithm can be modified to includes at least one of a gradient-based circle detection of an outer edge of a drogue basket, a gradient-based spoke detection of inner spokes of the drogue basket, or a transform-based template matching detection of the drogue basket in order to have a method that can process template matching process without drawback when a certain condition is not met such as a function of the Sobel-chaincode is not cyclical, therefore, it is more effectively and robust to use transform-based templating matching through Fourier Transform, (see Clark’s Par. [0098]).
Regarding claim 4, Sabol in view of Clark teaches the device of claim 3, Sabol teaches wherein the second image processing operation includes another of (Any of the four lists indicated is analogous to the first set of the candidate locations, moreover, Par. [0027] discloses “in addition to the above lists, the method implements four processes” any of which is analogous to the second processing operation and its associated list to be analogous to the first set of the candidate locations; wherein Par. [0027] discloses “and Identifying Completed Tracks, that accepts an input from the Potential List, and identifies any bats on the Tracking List that have not had any recent track updates and, based on processing rules, discards bats without recent track updates or moves bats without recent track updates to the Target List, such that the tracking algorithm processes detected bats across the video frames, producing a time and spatial history for each” which is analogous to the second processing operation as claimed, which includes identifying tracked locations of the object to be tracked).
However, Sabol does not explicitly teach the second image processing operation includes another of the gradient-based circle detection of the outer edge of the drogue basket, the gradient-based spoke detection of the inner spokes of the drogue basket, or the transform-based template matching detection of the drogue basket.
In the same field of object detection and tracking (Title and Abstract, Clark), Clark explicitly teaches the second image processing operation includes another of the gradient-based circle detection of the outer edge of the drogue basket, the gradient-based spoke detection of the inner spokes of the drogue basket, or the transform-based template matching detection of the drogue basket (“at least one of….or” indicating a selection, therefore, only one of the options is required to be the instant scope of the claim, the examiner selects “a transform-based template matching detection of the drogue basket” which is disclosed in Clark’s Par. [0098]”, which discloses “such as frequency domain Fourier Transform are performed…in order to accomplish template matching” indicating a transform-based template matching detection of the object to track the object through images [analogous to the process of Sabol as discussed above]; therefore, Sabol’s process, as stated above, that is based on first identifying tracked locations of the object to be tracked, can be modified to be performed a step of template matching based on Fourier Transform to identify the tracked locations, since the processes of Sobel are distinct, but sharing the same component of tracked locations, and Clark teaches such tracking can be done through Fourier Transform template matching, Clark’s teaching can be applied to both processed still be distinct but share same component. Therefore, it would have been obvious to one or ordinary skill of the art at the time the invention was made to have the second process of tracking of objects through images through matching of object to a criteria to be modified to be based on a transform-based template matching detection as taught by Clark. Thus in order to have a method that can process template matching process without drawback when a certain condition is not met such as a function of the Sobel-chaincode is not cyclical, therefore, it is more effective and robust to use transform-based templating matching through Fourier Transform, see Clark’s Par. [0098]).
Therefore, it would have been obvious to one of ordinary skill in the art before the effective filing data of the claimed invention was made to combine the teachings of Sabol of a device with a first and second processing algorithms to process the images. Moreover, Sabol’s second processing algorithm can be modified to includes at least one of a gradient-based circle detection of an outer edge of a drogue basket, a gradient-based spoke detection of inner spokes of the drogue basket, or a transform-based template matching detection of the drogue basket as taught in Clark.
Such a modification is the result of combing prior art elements, wherein both Sabol and Clark share the same endeavor of object detection and tracking through template matching. The motivation for the proposed modification would have been have a second processing algorithm can be modified to includes at least one of a gradient-based circle detection of an outer edge of a drogue basket, a gradient-based spoke detection of inner spokes of the drogue basket, or a transform-based template matching detection of the drogue basket in order to have a method that can process template matching process without drawback when a certain condition is not met such as a function of the Sobel-chaincode is not cyclical, therefore, it is more effectively and robust to use transform-based templating matching through Fourier Transform, (see Clark’s Par. [0098]).
Regarding claim 13, Sabol teaches the method of claim 12, wherein the first image processing operation includes (Any of the four lists indicated is analogous to the first set of the candidate locations, moreover, Par. [0027] discloses “in addition to the above lists, the method implements four processes” any of which is analogous to the first processing operation and its associated list to be analogous to the first set of the candidate locations; wherein Par. [0027] discloses “four processes:…clearing unmatched bats from the Potential List, creating new candidate objects for each pixel cluster remaining in the Pixel Cluster List and placing all unmatched bats in the current video frame on a potential list for input into a next process for a next video frame, and adding candidate bats to the Potential List” which is analogous to the first processing operation as claimed).
However, Sabol does not explicitly teach the first image processing operation includes at least one of a gradient-based circle detection of an outer edge of a drogue basket, a gradient-based spoke detection of inner spokes of the drogue basket, or a transform-based template matching detection of the drogue basket.
In the same field of object detection and tracking (Title and Abstract, Clark), Clark explicitly teaches the first image processing operation includes at least one of a gradient-based circle detection of an outer edge of a drogue basket, a gradient-based spoke detection of inner spokes of the drogue basket, or a transform-based template matching detection of the drogue basket (“at least one of….or” indicating a selection, therefore, only one of the options is required to be the instant scope of the claim, the examiner selects “a transform-based template matching detection of the drogue basket” which is disclosed in Clark’s Par. [0098]”, which discloses “such as frequency domain Fourier Transform are performed…in order to accomplish template matching” indicating a transform-based template matching detection of the object to track the object through images [analogous to the process of Sabol as discussed above]. Therefore, it would have been obvious to one or ordinary skill of the art at the time the invention was made to have the first process of tracking of objects through images through matching of object to a criteria to be modified to be based on a transform-based template matching detection as taught by Clark. Thus in order to have a method that can process template matching process without drawback when a certain condition is not met such as a function of the Sobel-chaincode is not cyclical, therefore, it is more effective and robust to use transform-based templating matching through Fourier Transform, see Clark’s Par. [0098]).
Therefore, it would have been obvious to one of ordinary skill in the art before the effective filing data of the claimed invention was made to combine the teachings of Sabol of a device with a first and second processing algorithms to process the images. Moreover, Sabol’s first processing algorithm can be modified to includes at least one of a gradient-based circle detection of an outer edge of a drogue basket, a gradient-based spoke detection of inner spokes of the drogue basket, or a transform-based template matching detection of the drogue basket as taught in Clark.
Such a modification is the result of combing prior art elements, wherein both Sabol and Clark share the same endeavor of object detection and tracking through template matching. The motivation for the proposed modification would have been to have a first processing algorithm can be modified to includes at least one of a gradient-based circle detection of an outer edge of a drogue basket, a gradient-based spoke detection of inner spokes of the drogue basket, or a transform-based template matching detection of the drogue basket in order to have a method that can process template matching process without drawback when a certain condition is not met such as a function of the Sobel-chaincode is not cyclical, therefore, it is more effectively and robust to use transform-based templating matching through Fourier Transform, (see Clark’s Par. [0098]).
Regarding claim 14, Sabol in view of Clark explicitly teaches the method of claim 13, Sabol teaches wherein the second image processing operation includes another of (Any of the four lists indicated is analogous to the first set of the candidate locations, moreover, Par. [0027] discloses “in addition to the above lists, the method implements four processes” any of which is analogous to the second processing operation and its associated list to be analogous to the first set of the candidate locations; wherein Par. [0027] discloses “and Identifying Completed Tracks, that accepts an input from the Potential List, and identifies any bats on the Tracking List that have not had any recent track updates and, based on processing rules, discards bats without recent track updates or moves bats without recent track updates to the Target List, such that the tracking algorithm processes detected bats across the video frames, producing a time and spatial history for each” which is analogous to the second processing operation as claimed, which includes identifying tracked locations of the object to be tracked).
However, Sabol does not explicitly teach the second image processing operation includes another of the gradient-based circle detection of the outer edge of the drogue basket, the gradient-based spoke detection of the inner spokes of the drogue basket, or the transform-based template matching detection of the drogue basket.
In the same field of object detection and tracking (Title and Abstract, Clark), Clark explicitly teaches the second image processing operation includes another of the gradient-based circle detection of the outer edge of the drogue basket, the gradient-based spoke detection of the inner spokes of the drogue basket, or the transform-based template matching detection of the drogue basket (“at least one of….or” indicating a selection, therefore, only one of the options is required to be the instant scope of the claim, the examiner selects “a transform-based template matching detection of the drogue basket” which is disclosed in Clark’s Par. [0098]”, which discloses “such as frequency domain Fourier Transform are performed…in order to accomplish template matching” indicating a transform-based template matching detection of the object to track the object through images [analogous to the process of Sabol as discussed above]; therefore, Sabol’s process, as stated above, that is based on first identifying tracked locations of the object to be tracked, can be modified to be performed a step of template matching based on Fourier Transform to identify the tracked locations, since the processes of Sobel are distinct, but sharing the same component of tracked locations, and Clark teaches such tracking can be done through Fourier Transform template matching, Clark’s teaching can be applied to both processed still be distinct but share same component. Therefore, it would have been obvious to one or ordinary skill of the art at the time the invention was made to have the second process of tracking of objects through images through matching of object to a criteria to be modified to be based on a transform-based template matching detection as taught by Clark. Thus in order to have a method that can process template matching process without drawback when a certain condition is not met such as a function of the Sobel-chaincode is not cyclical, therefore, it is more effective and robust to use transform-based templating matching through Fourier Transform, see Clark’s Par. [0098]).
Therefore, it would have been obvious to one of ordinary skill in the art before the effective filing data of the claimed invention was made to combine the teachings of Sabol of a device with a first and second processing algorithms to process the images. Moreover, Sabol’s second processing algorithm can be modified to includes at least one of a gradient-based circle detection of an outer edge of a drogue basket, a gradient-based spoke detection of inner spokes of the drogue basket, or a transform-based template matching detection of the drogue basket as taught in Clark.
Such a modification is the result of combing prior art elements, wherein both Sabol and Clark share the same endeavor of object detection and tracking through template matching. The motivation for the proposed modification would have been have a second processing algorithm can be modified to includes at least one of a gradient-based circle detection of an outer edge of a drogue basket, a gradient-based spoke detection of inner spokes of the drogue basket, or a transform-based template matching detection of the drogue basket in order to have a method that can process template matching process without drawback when a certain condition is not met such as a function of the Sobel-chaincode is not cyclical, therefore, it is more effectively and robust to use transform-based templating matching through Fourier Transform, (see Clark’s Par. [0098]).
Regarding claim 19, Sabol explicitly teaches the non-transitory, computer readable medium of claim 18, Sabol further teaches wherein the first image processing operation includes (Any of the four lists indicated is analogous to the first set of the candidate locations, moreover, Par. [0027] discloses “in addition to the above lists, the method implements four processes” any of which is analogous to the first processing operation and its associated list to be analogous to the first set of the candidate locations; wherein Par. [0027] discloses “four processes:…clearing unmatched bats from the Potential List, creating new candidate objects for each pixel cluster remaining in the Pixel Cluster List and placing all unmatched bats in the current video frame on a potential list for input into a next process for a next video frame, and adding candidate bats to the Potential List” which is analogous to the first processing operation as claimed).
However, Sabol does not explicitly teach the first image processing operation includes at least one of a gradient-based circle detection of an outer edge of a drogue basket, a gradient-based spoke detection of inner spokes of the drogue basket, or a transform-based template matching detection of the drogue basket.
In the same field of object detection and tracking (Title and Abstract, Clark), Clark explicitly teaches the first image processing operation includes at least one of a gradient-based circle detection of an outer edge of a drogue basket, a gradient-based spoke detection of inner spokes of the drogue basket, or a transform-based template matching detection of the drogue basket (“at least one of….or” indicating a selection, therefore, only one of the options is required to be the instant scope of the claim, the examiner selects “a transform-based template matching detection of the drogue basket” which is disclosed in Clark’s Par. [0098]”, which discloses “such as frequency domain Fourier Transform are performed…in order to accomplish template matching” indicating a transform-based template matching detection of the object to track the object through images [analogous to the process of Sabol as discussed above]. Therefore, it would have been obvious to one or ordinary skill of the art at the time the invention was made to have the first process of tracking of objects through images through matching of object to a criteria to be modified to be based on a transform-based template matching detection as taught by Clark. Thus in order to have a method that can process template matching process without drawback when a certain condition is not met such as a function of the Sobel-chaincode is not cyclical, therefore, it is more effective and robust to use transform-based templating matching through Fourier Transform, see Clark’s Par. [0098]).
Therefore, it would have been obvious to one of ordinary skill in the art before the effective filing data of the claimed invention was made to combine the teachings of Sabol of a device with a first and second processing algorithms to process the images. Moreover, Sabol’s first processing algorithm can be modified to includes at least one of a gradient-based circle detection of an outer edge of a drogue basket, a gradient-based spoke detection of inner spokes of the drogue basket, or a transform-based template matching detection of the drogue basket as taught in Clark.
Such a modification is the result of combing prior art elements, wherein both Sabol and Clark share the same endeavor of object detection and tracking through template matching. The motivation for the proposed modification would have been to have a first processing algorithm can be modified to includes at least one of a gradient-based circle detection of an outer edge of a drogue basket, a gradient-based spoke detection of inner spokes of the drogue basket, or a transform-based template matching detection of the drogue basket in order to have a method that can process template matching process without drawback when a certain condition is not met such as a function of the Sobel-chaincode is not cyclical, therefore, it is more effectively and robust to use transform-based templating matching through Fourier Transform, (see Clark’s Par. [0098]).
Regarding claim 20, Sabol in view of Clark explicitly teaches the non-transitory, computer readable medium of claim 19, Sabol further teaches wherein the second image processing operation includes another of (Any of the four lists indicated is analogous to the first set of the candidate locations, moreover, Par. [0027] discloses “in addition to the above lists, the method implements four processes” any of which is analogous to the second processing operation and its associated list to be analogous to the first set of the candidate locations; wherein Par. [0027] discloses “and Identifying Completed Tracks, that accepts an input from the Potential List, and identifies any bats on the Tracking List that have not had any recent track updates and, based on processing rules, discards bats without recent track updates or moves bats without recent track updates to the Target List, such that the tracking algorithm processes detected bats across the video frames, producing a time and spatial history for each” which is analogous to the second processing operation as claimed, which includes identifying tracked locations of the object to be tracked).
However, Sabol does not explicitly teach the second image processing operation includes another of the gradient-based circle detection of the outer edge of the drogue basket, the gradient-based spoke detection of the inner spokes of the drogue basket, or the transform-based template matching detection of the drogue basket.
In the same field of object detection and tracking (Title and Abstract, Clark), Clark explicitly teaches the second image processing operation includes another of the gradient-based circle detection of the outer edge of the drogue basket, the gradient-based spoke detection of the inner spokes of the drogue basket, or the transform-based template matching detection of the drogue basket (“at least one of….or” indicating a selection, therefore, only one of the options is required to be the instant scope of the claim, the examiner selects “a transform-based template matching detection of the drogue basket” which is disclosed in Clark’s Par. [0098]”, which discloses “such as frequency domain Fourier Transform are performed…in order to accomplish template matching” indicating a transform-based template matching detection of the object to track the object through images [analogous to the process of Sabol as discussed above]; therefore, Sabol’s process, as stated above, that is based on first identifying tracked locations of the object to be tracked, can be modified to be performed a step of template matching based on Fourier Transform to identify the tracked locations, since the processes of Sobel are distinct, but sharing the same component of tracked locations, and Clark teaches such tracking can be done through Fourier Transform template matching, Clark’s teaching can be applied to both processed still be distinct but share same component. Therefore, it would have been obvious to one or ordinary skill of the art at the time the invention was made to have the second process of tracking of objects through images through matching of object to a criteria to be modified to be based on a transform-based template matching detection as taught by Clark. Thus in order to have a method that can process template matching process without drawback when a certain condition is not met such as a function of the Sobel-chaincode is not cyclical, therefore, it is more effective and robust to use transform-based templating matching through Fourier Transform, see Clark’s Par. [0098]).
Therefore, it would have been obvious to one of ordinary skill in the art before the effective filing data of the claimed invention was made to combine the teachings of Sabol of a device with a first and second processing algorithms to process the images. Moreover, Sabol’s second processing algorithm can be modified to includes at least one of a gradient-based circle detection of an outer edge of a drogue basket, a gradient-based spoke detection of inner spokes of the drogue basket, or a transform-based template matching detection of the drogue basket as taught in Clark.
Such a modification is the result of combing prior art elements, wherein both Sabol and Clark share the same endeavor of object detection and tracking through template matching. The motivation for the proposed modification would have been have a second processing algorithm can be modified to includes at least one of a gradient-based circle detection of an outer edge of a drogue basket, a gradient-based spoke detection of inner spokes of the drogue basket, or a transform-based template matching detection of the drogue basket in order to have a method that can process template matching process without drawback when a certain condition is not met such as a function of the Sobel-chaincode is not cyclical, therefore, it is more effectively and robust to use transform-based templating matching through Fourier Transform, (see Clark’s Par. [0098]).
Claims 6 and 16 are rejected under 35 U.S.C. 103 as being unpatentable over Bruce M. Sabol et. al. (“US 2011/0081043 A1” hereinafter as “Sabol”) in view of Koba Natroshvili et. al. (“US 8,391,612 B2” hereinafter as “Natroshvili”).
Regarding claim 6, Sabol explicitly teaches the device of claim 1, wherein the vision processor is configured to perform (Par. [0038] discloses “thermal imagery is digitally recorded and in select embodiments of the present invention transferred to a suitable processor” indicating a vision processor coupled with the imager, is analogous to the vision processor as claimed, which is to detect and track object).
However, Sabol does not explicitly teach perform edge thresholding of an intensity gradient image that is based on the thermal image to detect edges associated with gradient magnitudes that satisfy an edge threshold.
In the same field of image processing for object detection (Natroshvili, Title and Abstract), Natroshvili discloses perform edge thresholding of an intensity gradient image (Col. 2, lines 7-12, discloses “all pixels in the gradient image having an intensity higher than the upper threshold are considered real edges in the image” indicating an edge thresholding of an intensity gradient image as claimed) that is based on the thermal image to detect edges (Col. 2, lines 7-12, discloses “all pixels in the gradient image having an intensity higher than the upper threshold are considered real edges in the image” indicating an edge thresholding of an intensity gradient image as claimed to detect edges, moreover, the image here can be understood to be any type of image such as thermal image which was already mapped to Sabol being performed the edge thresholding to detect edges of an object) associated with gradient magnitudes that satisfy an edge threshold (Col. 4, lines 10-20, discloses, “an edge detection operator….used to determine the edge gradient and direction…a search is performed to determine if the gradient magnitude is a local maximum in the gradient direction” indicating that the gradient magnitudes that satisfy an edge threshold as claimed. Therefore, it would have been obvious to one or ordinary skill of the art at the time the invention was made to have to perform object detection to be modified to be through edge detection by performing edge thresholding such as taught by Natroshvili. Thus in order to have a method that can perform object detection effectively through an edge detection process to achieve a good localizing by marking edge point, see Natroshvili’s Col. 1, lines 35-47).
Therefore, it would have been obvious to one of ordinary skill in the art before the effective filing data of the claimed invention was made to combine the teachings of Sabol of a device with a vision processor to perform object detection. Moreover, Sabol’s object detection can be modified to be through performing of an edge thresholding in an intensity gradient image to detect edged through gradient magnitude being compared to satisfy an edge threshold as taught in Natroshvili.
Such a modification is the result of combing prior art elements, wherein both Sabol and Natroshvili share the same endeavor of object detection. The motivation for the proposed modification would have been to have vision processor is configured to perform edge thresholding of an intensity gradient image that is based on the thermal image to detect edges associated with gradient magnitudes that satisfy an edge threshold in order to have a method that can perform object detection effectively through an edge detection process to achieve a good localizing by marking edge point, (see Natroshvili’s Col. 1, lines 35-47).
Regarding claim 16, Sabol explicitly teaches the method of claim 11, Sabol further comprising performing, at the vision processor (Par. [0038] discloses “thermal imagery is digitally recorded and in select embodiments of the present invention transferred to a suitable processor” indicating a vision processor coupled with the imager, is analogous to the vision processor as claimed, which is to detect and track object).
However, Sabol does not explicitly teach perform edge thresholding of an intensity gradient image that is based on the thermal image to detect edges associated with gradient magnitudes that satisfy an edge threshold.
In the same field of image processing for object detection (Natroshvili, Title and Abstract), Natroshvili discloses perform edge thresholding of an intensity gradient image (Col. 2, lines 7-12, discloses “all pixels in the gradient image having an intensity higher than the upper threshold are considered real edges in the image” indicating an edge thresholding of an intensity gradient image as claimed) that is based on the thermal image to detect edges (Col. 2, lines 7-12, discloses “all pixels in the gradient image having an intensity higher than the upper threshold are considered real edges in the image” indicating an edge thresholding of an intensity gradient image as claimed to detect edges, moreover, the image here can be understood to be any type of image such as thermal image which was already mapped to Sabol being performed the edge thresholding to detect edges of an object) associated with gradient magnitudes that satisfy an edge threshold (Col. 4, lines 10-20, discloses, “an edge detection operator….used to determine the edge gradient and direction…a search is performed to determine if the gradient magnitude is a local maximum in the gradient direction” indicating that the gradient magnitudes that satisfy an edge threshold as claimed. Therefore, it would have been obvious to one or ordinary skill of the art at the time the invention was made to have to perform object detection to be modified to be through edge detection by performing edge thresholding such as taught by Natroshvili. Thus in order to have a method that can perform object detection effectively through an edge detection process to achieve a good localizing by marking edge point, see Natroshvili’s Col. 1, lines 35-47).
Therefore, it would have been obvious to one of ordinary skill in the art before the effective filing data of the claimed invention was made to combine the teachings of Sabol of a device with a vision processor to perform object detection. Moreover, Sabol’s object detection can be modified to be through performing of an edge thresholding in an intensity gradient image to detect edged through gradient magnitude being compared to satisfy an edge threshold as taught in Natroshvili.
Such a modification is the result of combing prior art elements, wherein both Sabol and Natroshvili share the same endeavor of object detection. The motivation for the proposed modification would have been to have vision processor is configured to perform edge thresholding of an intensity gradient image that is based on the thermal image to detect edges associated with gradient magnitudes that satisfy an edge threshold in order to have a method that can perform object detection effectively through an edge detection process to achieve a good localizing by marking edge point, (see Natroshvili’s Col. 1, lines 35-47).
Claim 7 is rejected under 35 U.S.C. 103 as being unpatentable over Bruce M. Sabol et. al. (“US 2011/0081043 A1” hereinafter as “Sabol”) in view of Reza Rassool (“US 2022/0207916 A1” hereinafter as “Rassool”).
Regarding claim 7, Sabol explicitly teaches the device of claim 1, wherein at least one of the one or more scores associated with each of the candidate locations (Par. [0033] discloses “candidate objects in motion having at least one characteristic of their signature in a range that is approximately equal to the range of a characteristic in the signature of an established temporal background behind the object in motion” indicating a characteristic signature generated for each candidate object in a range that is measurable, therefore, is analogous to one or more scores associated with each of the candidate locations as claimed).
However, Sabol does not explicitly teach wherein at least one of the one or more scores associated with each of the candidate locations corresponds to a confidence value for a candidate location.
In the same field of determining candidate object through motion signature (Abstract, Rassool), Rassool discloses wherein at least one of the one or more scores associated with each of the candidate locations corresponds to a confidence value for a candidate location (Par. [0026] discloses “generate identification information representing a set of candidate identities of persons associated with one of the stored biometric signatures for which the biometric motion signature satisfies the criterion for similarity. The identification information may include a record, such as confidence score, indicating a degree of similarity of the corresponding stored biometric signature to the biometric motion signature” indicating the motion signature [analogous to Sabol’s characteristic motion signature to identify objects] is used to be compared between a stored one and the detected one to identify similar or the same object, which is based on confidence value for the candidate identity [analogous to candidate location as claimed and Sabol’s candidate location, since the target of the similarity determination is a candidate result/identity/location/object information]; Therefore, it would have been obvious to one or ordinary skill of the art at the time the invention was made to have to perform object detection using one or more scores associated with the candidate locations which can be modified to be based on confidence scores associated with the candidate locations taught by Rassool. Thus in order to have such method to recognize and identify object, constantly moving in images, more accurately, see Par. [0003] of Rassool).
Therefore, it would have been obvious to one of ordinary skill in the art before the effective filing data of the claimed invention was made to combine the teachings of Sabol of a device with one of the one or more scores associated with each of the candidate locations. Moreover, Sabol’s device can be modified to be based on the at least one of the one or more scores associated with each of the candidate locations corresponds to a confidence value for a candidate location as taught in Rassool.
Such a modification is the result of combing prior art elements, wherein both Sabol and Rassool share the same endeavor of object detection through motion signatures. The motivation for the proposed modification would have been to have a device wherein at least one of the one or more scores associated with each of the candidate locations corresponds to a confidence value for a candidate location in order to have method to recognize and identify object, constantly moving in images, more accurately, (see Par. [0003] of Rassool).
Claim 9 is rejected under 35 U.S.C. 103 as being unpatentable over Bruce M. Sabol et. al. (“US 2011/0081043 A1” hereinafter as “Sabol”) in view of Ruey-Yuan Han et. al. (“US 2006/0120590 A1” hereinafter as “Han”).
Regarding claim 9, Sabol teaches the device of claim 1, wherein the vision processor is configured to process the thermal image (Par. [0038] discloses “thermal imagery is digitally recorded and in select embodiments of the present invention transferred to a suitable processor” indicating a vision processor coupled with the imager, is analogous to the vision processor as claimed, which is to detect and track object).
However, Sabol does not explicitly teach generate an accumulation map indicating, for each pixel of a plurality of pixels in the thermal image, how many extended edge unit vectors terminate proximate to the pixel or at least partially in the pixel; and identify a predetermined number of largest peaks in the accumulation map as the one or more candidate locations.
Han teaches generate an accumulation map indicating, for each pixel of a plurality of pixels in the thermal image, how many extended edge unit vectors terminate proximate to the pixel or at least partially in the pixel (“or” indicates a selection, only one of the options is the instant scope of the claim, Han’s Par. [0142] discloses “in performing Hough Transform, the accumulation of correlation counts in matching up the edge points between input image and reference model can be handled individually for each of the six edge direction…Hough planes are summed up pixel by pixel…the correlation counts from each pair of Hough planes are multiplied together at the corresponding pixel locations” wherein, the accumulation of correlation counts is analogous to the recited “indicating how many extended edge unit vectors terminate proximate to the pixel” since the correlation is represented as vector form, Par. [0030] discloses “the correlation method called WDCP (Weighted Direction Cross Product)”, Par. [0027] discloses “extract edged from the input IR images…use the WDCP…Hough correlation method of the invention on the extracted edge points” and Par. [0031] discloses “frame-to-frame correlation between pre-stored reference model(s) and input images using the edge information defined within or near the target area” indicates proximate to the pixel); and identify a predetermined number of largest peaks in the accumulation map as the one or more candidate locations (Par. [0034] discloses “aim-point is selected by first finding the highest peak on the Hough correlation surface within the AOIs and then performing centroid detection around the detected peak to finalize the location of the aim-point”).
Therefore, it would have been obvious to one or ordinary skill in the art before the effective filing date of the claimed invention was made to combine the teachings of Sabol of a device, wherein the vision processor is configured to process the thermal image, with the teachings of Han of having wherein to generate an accumulation map indicating, for each pixel of a plurality of pixels in the thermal image, how many extended edge unit vectors terminate proximate to the pixel or at least partially in the pixel; and identify a predetermined number of largest peaks in the accumulation map as the one or more candidate locations.
Wherein having Sabol’s device of having wherein to generate an accumulation map indicating, for each pixel of a plurality of pixels in the thermal image, how many extended edge unit vectors terminate proximate to the pixel or at least partially in the pixel; and identify a predetermined number of largest peaks in the accumulation map as the one or more candidate locations.
The motivation behind the modification would have been to improve object detection by detecting changes in every frames permitting reprocessing with different parameters any number of times to enable efficient object localization, and further to improve target object identification in images by using pre-stored reference to be matched with an input image by using Correlation determination allowing accurate detection and minimizing probability of errors. Since both Sabol and Han both perform target object detection based on pixel clustering. Wherein Sabol’s system improves object detection by detecting changes in every frames permitting reprocessing with different parameters any number of times to enable efficient object localization, (see Sabol’s Par [0016]) and Han’s system improves target object identification in images by using pre-stored reference to be matched with an input image by using Correlation determination allowing accurate detection and minimizing probability of errors, (see Han’s Par. [0026]).
Claim 10 is rejected under 35 U.S.C. 103 as being unpatentable over Bruce M. Sabol et. al. (“US 2011/0081043 A1” hereinafter as “Sabol”) in view of Ruey-Yuan Han et. al. (“US 2006/0120590 A1” hereinafter as “Han”) and Takeo Kimura et. al. (“US 4,504,847” hereinafter as “Kimura”).
Regarding claim 10, Sabol in view of Han teaches the device of claim 9.
However, Sabol in view of Han does not explicitly teach wherein the vision processor is configured to: determine an edge normal unit vector for each edge pixel; and generate the extended edge unit vectors by extending, for each edge normal unit vector, a vector in both directions perpendicular to the edge normal unit vector by an amount proportional to an expected size of the drogue basket.
Kimura teaches wherein the vision processor is configured to: determine an edge normal unit vector for each edge pixel (Col 11, lines 43-51, disclose “a unit normal vector is calculated for each pixel of the range image”); and generate the extended edge unit vectors by extending (Col. 3, lines 31-40, disclose “calculating normal vectors based on the input range image, forming an edge map for the range image based on the calculated normal vectors, detecting non-closed edges by scanning the formed edge map, performing a shaping operation which deletes or extends the detected non-closed edges”), for each edge normal unit vector (Col 11, lines 43-51, disclose “a unit normal vector is calculated for each pixel of the range image”; Col. 3, lines 31-40, disclose “calculating normal vectors based on the input range image, forming an edge map for the range image based on the calculated normal vectors” wherein, the extending is performed on the edges in the edge map formed by normal vectors indicating the extending is for each edge normal vector), a vector in both directions perpendicular to the edge normal unit vector (Col. 8, lines 39-58, disclose “vertices at each point in which edge lines in two directions are connected in the form of a T on the edge-line map are found” wherein, the edge-line map contain normal unit vectors, hence, each point is a normal unit vector point, the edge lines in two directions are analogous to a vector in both directions as claimed, T shape indicates perpendicularity) by an amount proportional to an expected size of the drogue basket (Col. 8, lines 39-58, disclose “vertices at each point in which edge lines in two directions are connected in the form of a T on the edge-line map are found, and the distance values for these vertices are corrected using the following expressions as shown in Fig. 6(b)” wherein, the distance values indicating an amount, moreover, the equation for when xA/=xB indicates an disproportionality, while other instances of zC would be in a proportionality; and the reconfigured object is analogous to the recited drogue basket).
Therefore, it would have been obvious to one or ordinary skill in the art before the effective filing date of the claimed invention was made to combine the teachings of Sabol in view of Han of a device, wherein the vision processor is configured to process the thermal image, with the teachings of Kimura of having wherein the vision processor is configured to: determine an edge normal unit vector for each edge pixel; and generate the extended edge unit vectors by extending, for each edge normal unit vector, a vector in both directions perpendicular to the edge normal unit vector by an amount proportional to an expected size of the drogue basket.
Wherein having Sabol’s device of having wherein the vision processor is configured to: determine an edge normal unit vector for each edge pixel; and generate the extended edge unit vectors by extending, for each edge normal unit vector, a vector in both directions perpendicular to the edge normal unit vector by an amount proportional to an expected size of the drogue basket.
The motivation behind the modification would have been to improve object detection by detecting changes in every frames permitting reprocessing with different parameters any number of times to enable efficient object localization, and further to improve object approximation utilizing polygon analysis of patches of the object image data enabling improved accuracy for an object having a complicated shape. Since both Sabol and Kimura both perform object approximation using vector analysis. Wherein Sabol’s system improves object detection by detecting changes in every frames permitting reprocessing with different parameters any number of times to enable efficient object localization, (see Sabol’s Par [0016]) and Kimura’s system improves object approximation utilizing polygon analysis of patches of the object image data enabling improved accuracy for an object having a complicated shape, (see Kimura’s Par. [0026]).
Pertinent Prior Art(s)
The prior art made of record and not relied upon is considered pertinent to applicant's disclosure:
MAGRI, Luca et. al., “US 2014/0161359 A1”, discloses detecting a straight line in a digital image comprising a plurality of pixels comprising the steps: detecting an edge in the digital image, generating a first straight line which passes through a first pixel of the detected edge, generating a second straight line which passes through a second pixel of the detected edge, which is different from the first pixel, determining at least two intersections with a boundary of the digital image for each generated straight line, determining a set of two parameter values for each generated straight line based on the respective determined at least two intersections, wherein the set of two parameter values uniquely determines the respective generated straight line, and detecting the straight line in the digital image based on the determined sets of two parameter values.
OLSON, Edwin et. al., “US 2018/0210087 A1”, discloses presenting both computational and physical challenges in terms of matching, storage, and retrieval. Most of the environments where vehicles operate in contain frequent and distinct vertical structure sufficient for 2D localization, while state-of-the-art IMUs can be used to recover roll and pitch. This disclosure introduces a fast method for constructing 2D maps summarizing the vertical structure in the environment and demonstrate that it can be used to localize accurately in vehicular and other applications.
Conclusion
THIS ACTION IS MADE FINAL. Applicant is reminded of the extension of time policy as set forth in 37 CFR 1.136(a).
A shortened statutory period for reply to this final action is set to expire THREE MONTHS from the mailing date of this action. In the event a first reply is filed within TWO MONTHS of the mailing date of this final action and the advisory action is not mailed until after the end of the THREE-MONTH shortened statutory period, then the shortened statutory period will expire on the date the advisory action is mailed, and any nonprovisional extension fee (37 CFR 1.17(a)) pursuant to 37 CFR 1.136(a) will be calculated from the mailing date of the advisory action. In no event, however, will the statutory period for reply expire later than SIX MONTHS from the mailing date of this final action.
Any inquiry concerning this communication or earlier communications from the examiner should be directed to PHUONG HAU CAI whose telephone number is (571)272-9424. The examiner can normally be reached M-F 8:30 am - 5:00pm.
Examiner interviews are available via telephone, in-person, and video conferencing using a USPTO supplied web-based collaboration tool. To schedule an interview, applicant is encouraged to use the USPTO Automated Interview Request (AIR) at http://www.uspto.gov/interviewpractice.
If attempts to reach the examiner by telephone are unsuccessful, the examiner’s supervisor, Chineyere Wills-Burns can be reached at (571) 272-9752. The fax phone number for the organization where this application or proceeding is assigned is 571-273-8300.
Information regarding the status of published or unpublished applications may be obtained from Patent Center. Unpublished application information in Patent Center is available to registered users. To file and manage patent submissions in Patent Center, visit: https://patentcenter.uspto.gov. Visit https://www.uspto.gov/patents/apply/patent-center for more information about Patent Center and https://www.uspto.gov/patents/docx for information about filing in DOCX format. For additional questions, contact the Electronic Business Center (EBC) at 866-217-9197 (toll-free). If you would like assistance from a USPTO Customer Service Representative, call 800-786-9199 (IN USA OR CANADA) or 571-272-1000.
/PHUONG HAU CAI/Examiner, Art Unit 2673
/CHINEYERE WILLS-BURNS/Supervisory Patent Examiner, Art Unit 2673
Prosecution Insights