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 .
Claim Rejections - 35 USC § 103
In the event the determination of the status of the application as subject to AIA 35 U.S.C. 102 and 103 (or as subject to pre-AIA 35 U.S.C. 102 and 103) is incorrect, any correction of the statutory basis (i.e., changing from AIA to pre-AIA ) for the rejection will not be considered a new ground of rejection if the prior art relied upon, and the rationale supporting the rejection, would be the same under either status.
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.
Claims 21 and 29 are rejected under 35 U.S.C. 103 as being unpatentable over Venetianer et al. (US 2007/0122000) in view of Wang et al. (US 2007/0076957) (hereinafter, Wang ‘957), and further in view of Kim et al. (US 2010/0202663) (hereinafter, Kim ‘663) and Wu et al. (US 2021/0329193).
Regarding claims 21 and 29, Venetianer discloses a method and a computing device comprising a memory or a computer-readable medium and at least one processor coupled with the memory (paragraph 23, lines 1-2: “A "computer system" may refer to a system having a computer, where the computer may include a computer-readable medium embodying software to operate the computer”; paragraph 21, lines 3-4: “a computer having a single processor”), the at least one processor configured to perform the method comprising:
identifying pixels indicative of motion based on a frame of pixels (paragraph 29, lines 1-2: “Motion detection may detect pixels that change between frames … and may label the pixels as motion pixels.”).
Venetianer fails to disclose selecting a region of interest within the frame of pixels based on the pixels indicative of motion.
However, in an analogous art, Wang ‘957 discloses selecting a region of interest within a frame of pixels based on pixels indicative of motion (paragraph 41, lines 1-4: “a motion-based ROI detection technique that uses motion information … to perform ... detection that efficiently extracts … ROIs”). It would have been obvious to one of ordinary skill in the art before the effective filing date of the claimed invention to modify the method in Venetianer by incorporating this feature taught in Wang ‘957 for the purpose of reducing computational load and improving detection accuracy by ignoring static background pixels.
The combination of Venetianer and Wang ‘957 fails to disclose the region of interest being a subset of the frame of pixels and including the pixels indicative of motion.
However, in an analogous art, Kim ‘663 discloses a region of interest being a subset of a frame of pixels and including pixels indicative of motion (paragraph 37, lines 4-5: “The ROI can be the received motion region itself, or an enlarged version of the motion region obtained by including neighboring pixels.”). It would have been obvious to one of ordinary skill in the art before the effective filing date of the claimed invention to modify the method in Venetianer and Wang ‘957 by incorporating this feature taught in Kim ‘663 for the purpose of isolating dynamic content with a smaller subset of pixels and enabling more efficient processing and accurate detection of relevant events.
The combination of Venetianer, Wang ‘957 and Kim ‘663 fails to disclose after selecting the region of interest, issuing an alarm.
However, in an analogous art, Wu discloses disclose after selecting the region of interest, issuing an alarm (paragraph 113, lines 2-3: “The image sensor device 1700 is capable of … providing one or more regions of interest (ROIs) … determining an alarm schedule of ROIs”). It would have been obvious to one of ordinary skill in the art before the effective filing date of the claimed invention to modify the method in Venetianer, Wang ‘957 and Kim ‘663 by incorporating this feature taught in Wu for the purpose of promptly notifying a user of a detected event within a relevant region and enabling a timely response to the detected event.
Claim 22 is rejected under 35 U.S.C. 103 as being unpatentable over Venetianer et al. (US 2007/0122000) in view of Wang ‘957, and further in view of Kim ‘663, Wu et al. (US 2021/0329193), Pedeville et al. (US 2020/0251031) and Vitek et al. (US 2022/0147751).
Regarding claim 22, the combination of Venetianer, Wang ‘957, Kim ‘663 and Wu fails to disclose that the region of interest is a first region of interest having a first quantity of pixels.
However, in an analogous art, Pedeville discloses that a region of interest is a first region of interest having a first quantity of pixels (paragraph 16, line 6: “a region of interest (“ROI”) in the image may contain only a small number of imaging device pixels”). It would have been obvious to one of ordinary skill in the art before the effective filing date of the claimed invention to modify the method in Venetianer, Wang ‘957, Kim ‘663 and Wu by incorporating this feature taught in Pedeville for the purpose of quantifying the size of the region of interest and enabling more controlled and consistent processing.
The combination of Venetianer, Wang ‘957, Kim ‘663, Wu and Pedeville fails to disclose selecting a second region of interest, the second region of interest having a second quantity of pixels that is less than the first quantity; identifying a first object based on pixels in the first region of interest; and after identifying the first object, identifying a second object based on pixels in the second region of interest.
However, in an analogous art, Vitek discloses selecting a second region of interest, the second region of interest (corresponding to a downscaled ROI) having a second quantity of pixels that is less than a first quantity (corresponding to a reduced image) (paragraph 19, lines 1-5: “The merged ROIs are downscaled … object detectors … operate on the downscaled ROIs to output accurate detections … by operating on a reduced image … cropped images based on the generated ROIs”; paragraph 37, lines 4-5: “a total number of pixels of the cropped images is less than a number of pixels of the image.”); identifying a first object based on pixels in a first region of interest; and after identifying the first object, identifying a second object based on pixels in the second region of interest (paragraph 39, line 5: “an object detection network 140 to detect the objects in the cropped images.”). It would have been obvious to one of ordinary skill in the art before the effective filing date of the claimed invention to modify the method in Venetianer, Wang ‘957, Kim ‘663, Wu and Pedeville by incorporating this feature taught in Vitek for the purpose of improving detection accuracy and efficiency through staged processing of regions of interest.
Claim 23 is rejected under 35 U.S.C. 103 as being unpatentable over Venetianer et al. (US 2007/0122000) in view of Wang ‘957, and further in view of Kim ‘663, Wu et al. (US 2021/0329193), Vitek et al. (US 2022/0147751) and Badr et al. (US 2020/0265229).
Regarding claim 23, the combination of Venetianer, Wang ‘957, Kim ‘663 and Wu fails to disclose that the frame of pixels is a first frame of pixels; the subset of the frame of pixels is a first subset of the first frame of pixels; the region of interest is a first region of interest; and the method further comprises: selecting a second region of interest within the first frame of pixels, the second region of interest being a second subset of the first frame of pixels.
However, Vitek discloses that the frame of pixels is a first frame of pixels (paragraph 4, lines 2-4: the system receives an image comprising a first frame of pixels); the subset of the frame of pixels is a first subset of the first frame of pixels (paragraph 19, line 4: “operate on a subset of the entire image”; the subset of the image corresponds to a first subset of the first frame of pixels); the region of interest is a first region of interest (paragraph 17, line 9: “generate ROIs”; an ROI corresponds to a first region of interest); and the method further comprises:
selecting a second region of interest within the first frame of pixels, the second region of interest being a second subset of the first frame of pixels (paragraph 62, line 7: “cropped images of the initial image that correspond to identified ROIs”; the plurality of ROIs includes a second ROI selected within the image which corresponds to the second region of interest being a second subset of the first frame of pixels). It would have been obvious to one of ordinary skill in the art before the effective filing date of the claimed invention to modify the method in Venetianer, Wang ‘957, Kim ‘663 and Wu by incorporating this feature taught in Vitek for the purpose of enabling targeted processing of relevant image data while reducing computational complexity and improving efficiency.
The combination of Venetianer, Wang ‘957, Kim ‘663, Wu and Vitek fails to disclose identifying, in the second region of interest, an object that was identified previously within a second frame of pixels.
However, in an analogous art, Badr discloses identifying, in a second region of interest, an object that was identified previously within a second frame of pixels (paragraph 5, lines 17-20: “determining a first visual characteristic of a first set of pixels represented in the first image and associated with the object; receiving a second image representing one or more objects … and determining a location of the object in the second image based upon the first visual characteristic”). It would have been obvious to one of ordinary skill in the art before the effective filing date of the claimed invention to modify the method in Venetianer, Wang ‘957, Kim ‘663, Wu and Vitek by incorporating this feature taught in Badr for the purpose of maintaining continuity of object recognition across frames, thereby improving tracking accuracy and reducing redundant processing.
Claims 24 and 28 are rejected under 35 U.S.C. 103 as being unpatentable over Venetianer et al. (US 2007/0122000) in view of Wang ‘957, and further in view of Kim ‘663, Wu et al. (US 2021/0329193), and Vitek et al. (US 2022/0147751).
Regarding claim 24, the combination of Venetianer, Wang ‘957, Kim ‘663 and Wu fails to disclose that the region of interest is a first region of interest; and the method further comprises: selecting a second region of interest within the frame of pixels; merging the first region of interest and the second region of interest to generate a merged region; and identifying an object based on the merged region.
However, Vitek discloses that a region of interest is a first region of interest (paragraph 17, line 9: “generate ROIs”; an ROI corresponds to a first region of interest); and the method further comprises: selecting a second region of interest within the frame of pixels (paragraph 62, line 7: “cropped images of the initial image that correspond to identified ROIs”; the plurality of ROIs includes a second ROI selected within the image which corresponds to selecting a second region of interest within the frame of pixels); merging the first region of interest and the second region of interest to generate a merged region (paragraph 62, lines 6-7: “Overlapping ROIs may then be merged to generate one or more crops”); and identifying an object based on the merged region (paragraph 68, lines 3-4: “generate one or more cropped images (e.g., merged ROIs) … for object detection”). It would have been obvious to one of ordinary skill in the art before the effective filing date of the claimed invention to modify the method in Venetianer, Wang ‘957, Kim ‘663 and Wu by incorporating this feature taught in Vitek for the purpose of combining multiple relevant regions into a unified analysis area, thereby improving the accuracy of detecting the object.
Regarding claim 28, the combination of Venetianer, Wang ‘957, Kim ‘663 and Wu fails to disclose scaling the region of interest to comply with an object detection model; and after scaling the region of interest, applying the object detection model to identify an object within the region of interest.
However, Vitek discloses scaling a region of interest (corresponding to downscaled ROIs) to comply with an object detection model (paragraph 19, lines 1-5: “The merged ROIs are downscaled … object detectors … operate on the downscaled ROIs to output accurate detections … by operating on a reduced image … cropped images based on the generated ROIs”; paragraph 37, lines 4-5: “a total number of pixels of the cropped images is less than a number of pixels of the image.”); and after scaling the region of interest, applying the object detection model to identify an object within the region of interest (paragraph 39, line 5: “an object detection network 140 to detect the objects in the cropped images.”). It would have been obvious to one of ordinary skill in the art before the effective filing date of the claimed invention to modify the method in Venetianer, Wang ‘957, Kim ‘663 and Wu by incorporating this feature taught in Vitek for the purpose of ensuring compatibility with the detection model while enabling accurate object identification within the region of interest.
Claim 25 is rejected under 35 U.S.C. 103 as being unpatentable over Venetianer et al. (US 2007/0122000) in view of Wang ‘957, and further in view of Kim ‘663, Wu et al. (US 2021/0329193), Vitek et al. (US 2022/0147751) and Wang et al. (US 2019/0318171) (hereinafter, Wang ‘171).
Regarding claim 25, the combination of Venetianer, Wang ‘957, Kim ‘663 and Wu fails to disclose that the region of interest is a first region of interest; and the method further comprises: selecting a second region of interest within the frame of pixels; merging the first region of interest and the second region of interest to generate a merged region; and identifying an object based on the merged region.
However, Vitek discloses that a region of interest is a first region of interest (paragraph 17, line 9: “generate ROIs”; an ROI corresponds to a first region of interest); and the method further comprises: selecting a second region of interest within the frame of pixels (paragraph 62, line 7: “cropped images of the initial image that correspond to identified ROIs”; the plurality of ROIs includes a second ROI selected within the image which corresponds to selecting a second region of interest within the frame of pixels); merging the first region of interest and the second region of interest to generate a merged region (paragraph 62, lines 6-7: “Overlapping ROIs may then be merged to generate one or more crops”); and identifying an object based on the merged region (paragraph 68, lines 3-4: “generate one or more cropped images (e.g., merged ROIs) … for object detection”). It would have been obvious to one of ordinary skill in the art before the effective filing date of the claimed invention to modify the method in Venetianer, Wang ‘957, Kim ‘663 and Wu by incorporating this feature taught in Vitek for the purpose of combining multiple relevant regions into a unified analysis area, thereby improving the accuracy of detecting the object.
The combination of Venetianer, Wang ‘957, Kim ‘663, Wu and Vitek fails to disclose issuing the alarm in response to the merged region including both the object and the pixels indicative of motion.
However, in an analogous art, Wang ‘171 discloses issuing the alarm (corresponding to a notification) in response to a merged region (corresponding to a scene within a field of view) including both an object and pixels indicative of motion (paragraph 101, line 1: “The motion may be detected by determining a change in pixels between sequential frames”; paragraph 109, lines 4-5: “The motion event may be detected in a portion of a plurality of portions of the scene within the field of view. The scene within the field of view may be partitioned in to different regions of interest”; paragraph 113, lines 2-3: “The camera system may provide a notification to the user/user device based on a detection that a person is walking”). It would have been obvious to one of ordinary skill in the art before the effective filing date of the claimed invention to modify the method in Venetianer, Wang ‘957, Kim ‘663, Wu and Vitek by incorporating this feature taught in Wu ‘171 for the purpose of triggering alerts only when both object presence and motion are detected, thereby reducing false alarms and improving relevance of notifications.
Claim 26 is rejected under 35 U.S.C. 103 as being unpatentable over Venetianer et al. (US 2007/0122000) in view of Wang ‘957, and further in view of Kim ‘663, Wu et al. (US 2021/0329193), Pedeville et al. (US 2020/0251031), Vitek et al. (US 2022/0147751) and Kim et al. (US 2025/0110550) (hereinafter, Kim ‘550).
Regarding claim 26, the combination of Venetianer, Wang ‘957, Kim ‘663 and Wu fails to disclose that the region of interest is a first region of interest having a first quantity of pixels.
However, Pedeville discloses that a region of interest is a first region of interest having a first quantity of pixels (paragraph 16, line 6: “a region of interest (“ROI”) in the image may contain only a small number of imaging device pixels”). It would have been obvious to one of ordinary skill in the art before the effective filing date of the claimed invention to modify the method in Venetianer, Wang ‘957, Kim ‘663 and Wu by incorporating this feature taught in Pedeville for the purpose of quantifying the size of the region of interest and enabling more controlled and consistent processing.
The combination of Venetianer, Wang ‘957, Kim ‘663, Wu and Pedeville fails to disclose selecting a second region of interest, the second region of interest having a second quantity of pixels; and after making a determination, merging the first region of interest and the second region of interest.
However, Vitek discloses selecting a second region of interest, the second region of interest (corresponding to a downscaled ROI) having a second quantity of pixels (paragraph 19, lines 1-5: “The merged ROIs are downscaled … object detectors … operate on the downscaled ROIs to output accurate detections … by operating on a reduced image … cropped images based on the generated ROIs”; paragraph 37, lines 4-5: “a total number of pixels of the cropped images is less than a number of pixels of the image.”); and after making a determination (corresponding to object characteristics), merging the first region of interest and the second region of interest (paragraph 62, lines 4-7: “Object characteristics … are determined from the object scale heatmap … Overlapping ROIs may then be merged to generate one or more crops.”). It would have been obvious to one of ordinary skill in the art before the effective filing date of the claimed invention to modify the method in Venetianer, Wang ‘957, Kim ‘663, Wu and Pedeville by incorporating this feature taught in Vitek for the purpose of adaptively combining relevant regions based on analysis results, thereby improving processing efficiency and detection reliability.
The combination of Venetianer, Wang ‘957, Kim ‘663, Wu, Pedeville and Vitek fails to disclose making a determination that the second quantity is equal to or greater than a threshold percentage of the first quantity.
However, in an analogous art, Kim ‘550 discloses making a determination that a second quantity (corresponding to a threshold amount) is equal to or greater than a threshold percentage of a first quantity (paragraph 43, lines 1-3: “an operation to determine whether a threshold amount … from the sampled pixels … is used … For example, if a threshold number (e.g., 50% or more, 75% or more) of sampled pixels is used to present the virtual object”). It would have been obvious to one of ordinary skill in the art before the effective filing date of the claimed invention to modify the method in Venetianer, Wang ‘957, Kim ‘663, Wu, Pedeville and Vitek by incorporating this feature taught in Kim ‘550 for the purpose of evaluating whether a condition is sufficiently satisfied relative to a baseline, thereby enabling consistent decision-making based on thresholds.
Claim 27 is rejected under 35 U.S.C. 103 as being unpatentable over Venetianer et al. (US 2007/0122000) in view of Wang ‘957, and further in view of Kim ‘663, Wu et al. (US 2021/0329193), Pedeville et al. (US 2020/0251031), Vitek et al. (US 2022/0147751), Roehrig et al. (US 6,263,092), He et al. (US 2019/0180452) and Yu et al. (US 2020/0394458).
Regarding claim 27, the combination of Venetianer, Wang ‘957, Kim ‘663 and Wu fails to disclose that the region of interest is a first region of interest having a first quantity of pixels.
However, Pedeville discloses that a region of interest is a first region of interest having a first quantity of pixels (paragraph 16, line 6: “a region of interest (“ROI”) in the image may contain only a small number of imaging device pixels”). It would have been obvious to one of ordinary skill in the art before the effective filing date of the claimed invention to modify the method in Venetianer, Wang ‘957, Kim ‘663 and Wu by incorporating this feature taught in Pedeville for the purpose of quantifying the size of the region of interest and enabling more controlled and consistent processing.
The combination of Venetianer, Wang ‘957, Kim ‘663, Wu and Pedeville fails to disclose selecting a second region of interest, the second region of interest having a second quantity of pixels; and after making a determination, merging the first region of interest and the second region of interest.
However, Vitek discloses selecting a second region of interest, the second region of interest (corresponding to a downscaled ROI) having a second quantity of pixels (paragraph 19, lines 1-5: “The merged ROIs are downscaled … object detectors … operate on the downscaled ROIs to output accurate detections … by operating on a reduced image … cropped images based on the generated ROIs”; paragraph 37, lines 4-5: “a total number of pixels of the cropped images is less than a number of pixels of the image.”) and after making a determination (corresponding to object characteristics), merging the first region of interest and the second region of interest (paragraph 62, lines 4-7: “Object characteristics … are determined from the object scale heatmap … Overlapping ROIs may then be merged to generate one or more crops.”). It would have been obvious to one of ordinary skill in the art before the effective filing date of the claimed invention to modify the method in Venetianer, Wang ‘957, Kim ‘663, Wu and Pedeville by incorporating this feature taught in Vitek for the purpose of adaptively combining relevant regions based on analysis results, thereby improving processing efficiency and detection reliability.
The combination of Venetianer, Wang ‘957, Kim ‘663, Wu, Pedeville and Vitek fails to disclose determining an intersecting quantity of pixels in an intersection between the first region of interest and the second region of interest.
However, in an analogous art, Roehrig discloses determining an intersecting quantity of pixels in an intersection between a first region of interest and a second region of interest (claim 1, lines 2-4: “determining a region of potential intersection for each of a plurality of image pixels … accumulating said regions of potential intersection to produce a cumulative array”). It would have been obvious to one of ordinary skill in the art before the effective filing date of the claimed invention to modify the method in Venetianer, Wang ‘957, Kim ‘663, Wu, Pedeville and Vitek by incorporating this feature taught in Roehrig for the purpose of quantifying an overlap between regions and enabling the assessment of similarity or relevance for further processing decisions.
The combination of Venetianer, Wang ‘957, Kim ‘663, Wu, Pedeville, Vitek and Roehrig fails to disclose determining a minimum quantity of pixels that is a smaller of the first quantity and the second quantity.
However, in an analogous art, He discloses determining a minimum quantity of pixels that is a smaller of a first quantity and a second quantity (corresponding to multiple frames) (paragraph 40, lines 2-3: “the threshold pixel value … for the current frame is a minimum value of the m previous frames of the current frame image”). It would have been obvious to one of ordinary skill in the art before the effective filing date of the claimed invention to modify the method in Venetianer, Wang ‘957, Kim ‘663, Wu, Pedeville, Vitek and Roehrig by incorporating this feature taught in He for the purpose of normalizing comparisons using the smaller region and enabling fair and consistent evaluation between regions of different sizes.
The combination of Venetianer, Wang ‘957, Kim ‘663, Wu, Pedeville, Vitek, Roehrig and He fails to disclose making a determination that the intersecting quantity of pixels is greater than a threshold percentage of the minimum quantity of pixels.
However, in an analogous art, Yu discloses making a determination that an intersecting quantity of pixels is greater than a threshold percentage of a minimum quantity of pixels (paragraph 45, line 6: an intersection over union (“IoU”) between region r and region r*′.sup.k(c) is larger than 0.5”; the intersection corresponds to an intersecting quantity of pixels. 0.5 corresponds to a threshold percentage, 50%). It would have been obvious to one of ordinary skill in the art before the effective filing date of the claimed invention to modify the method in Venetianer, Wang ‘957, Kim ‘663, Wu, Pedeville, Vitek, Roehrig and He by incorporating this feature taught in Yu for the purpose of determining whether the overlap is sufficiently significant relative to the smaller region and enabling reliable threshold-based matching or association.
Claim 30 is rejected under 35 U.S.C. 103 as being unpatentable over Venetianer et al. (US 2007/0122000) in view of Wang ‘957, and further in view of Kim ‘663, Wu et al. (US 2021/0329193) and Choi et al. (US 2010/0277607).
Regarding claim 30, the combination of Venetianer, Wang ‘957, Kim ‘663 and Wu fails to disclose that selecting the region of interest comprises setting boundaries of the region of interest that encompass the pixels indicative of motion.
However, in an analogous art, Choi discloses that selecting a region of interest comprises setting boundaries of the region of interest that encompass pixels indicative of motion (paragraph 33, lines 3-4: “Motion detection unit 22 identifies a region-of-interest (ROI) within a frame based on motion image signals”).
Claim 33 is rejected under 35 U.S.C. 103 as being unpatentable over Venetianer et al. (US 2007/0122000) in view of Wang et al. (US 2007/0076957) (hereinafter, Wang ‘957), and further in view of Kim ‘663, Wu et al. (US 2021/0329193) and Pedeville (US 2020/0251031).
Regarding claim 33, the combination of Venetianer, Wang ‘957, Kim ‘663 and Wu fails to disclose that the region of interest is a square.
However, Pedeville discloses that the region of interest is a square (paragraph 47, line 9: “the ROI 570 can have any suitable shape (e.g., square…)”). It would have been obvious to one of ordinary skill in the art before the effective filing date of the claimed invention to modify the method in Venetianer, Wang ‘957, Kim ‘663 and Wu by incorporating this feature taught in Pedeville for the purpose of simplifying processing and resizing while maintaining consistent aspect ratios for the model.
Claims 34 and 35 are rejected under 35 U.S.C. 103 as being unpatentable over Venetianer et al. (US 2007/0122000) in view of Wang ‘957, and further in view of Kim ‘663, Wu et al. (US 2021/0329193) and Sun et al. (US 2017/0206431).
Regarding claim 34, Venetianer, Wang ‘957, Kim ‘663 and Wu fails to disclose selecting the region of interest comprises establishing a size of the region of interest to be equal to or greater than a size of input upon which an object detection model is configured to operate.
However, in an analogous art, Sun discloses selecting the region of interest comprises establishing a size of the region of interest to be equal to or greater than a size of input upon which an object detection model is configured to operate (paragraph 68, lines 1-2: “adjust and/or resize the input image in order to make the objects in the image easier to detect”). It would have been obvious to one of ordinary skill in the art before the effective filing date of the claimed invention to modify the method in Venetianer, Wang ‘957, Kim ‘663 and Wu by incorporating this feature taught in Sun for the purpose of ensuring the ROI can be properly processed by the model, thereby enabling accurate detection and avoiding loss of critical features.
Regarding claim 35, Venetianer, Wang ‘957, Kim ‘663 and Wu fails to disclose selecting the region of interest comprises establishing a size of the region of interest to be equal to or greater than a size of input upon which an object detection model is configured to operate; and the at least one processor is further configured to identify an object in the region of interest using the object detection model.
However, Sun discloses selecting the region of interest comprises establishing a size of the region of interest to be equal to or greater than a size of input upon which an object detection model is configured to operate (paragraph 68, lines 1-2: “adjust and/or resize the input image in order to make the objects in the image easier to detect”); and the at least one processor is further configured to identify an object in the region of interest using the object detection model (paragraph 116, lines 1-2: “training a model to detect and classify objects in an image.”). It would have been obvious to one of ordinary skill in the art before the effective filing date of the claimed invention to modify the method in Venetianer, Wang ‘957, Kim ‘663 and Wu by incorporating this feature taught in Sun for the purpose of determining what object is present in the selected region, thereby enabling accurate detection, classification and subsequent decision-making.
Claim 36 is rejected under 35 U.S.C. 103 as being unpatentable over Venetianer et al. (US 2007/0122000) in view of Wang ‘957, and further in view of Kim ‘663, Wu et al. (US 2021/0329193) and Jha et al. (US 2022/0051020).
Regarding claim 36, the combination of Venetianer, Wang ‘957, Kim ‘663 and Wu fails to disclose that selecting the region of interest comprises translating a boundary of the region of interest from a first position in which a portion of the boundary resides outside the frame of pixels to a second position in which the portion of the boundary is inside or upon an edge of the frame of pixels.
However, in an analogous art, Jha discloses that selecting a region of interest comprises translating a boundary of the region of interest from a first position in which a portion of the boundary resides outside a frame of pixels (corresponding to a bounding box outside an object of interest) to a second position in which the portion of the boundary is inside or upon an edge of the frame of pixels (paragraph 162, lines 2-3: “a region which is included in the input first image frame … and is bounded by the bounding box coordinates”; paragraph 164, lines 6-7: “The extracted object detection result may include bounding box coordinates for the object of interest”; paragraph 79, lines 2-3: “select a bounding box … around the object of interest … in the input first image frame”). It would have been obvious to one of ordinary skill in the art before the effective filing date of the claimed invention to modify the method in Venetianer, Wang ‘957, Kim ‘663 and Wu by incorporating this feature taught in Jha for the purpose of ensuring the region stays within the image so it can be properly processed without error or missing data.
Claims 37 and 40 are rejected under 35 U.S.C. 103 as being unpatentable over Venetianer et al. (US 2007/0122000) in view of Wang ‘957, and further in view of Kim ‘663, Vitek et al. (US 2022/0147751) and Fancella (US 2007/0046462).
Regarding claim 37, Venetianer discloses a method comprising:
identifying, in a frame of pixels, pixels indicative of motion (paragraph 29, lines 1-2: “Motion detection may detect pixels that change between frames … and may label the pixels as motion pixels.”).
Venetianer fails to disclose selecting a region of interest that includes the pixels indicative of motion.
However, Wang ‘957 discloses selecting a region of interest that includes pixels indicative of motion (paragraph 41, lines 1-4: “a motion-based ROI detection technique that uses motion information … to perform ... detection that efficiently extracts … ROIs”). It would have been obvious to one of ordinary skill in the art before the effective filing date of the claimed invention to modify the method in Venetianer by incorporating this feature taught in Wang ‘957 for the purpose of reducing computational load and improving detection accuracy by ignoring static background pixels.
The combination of Venetianer and Wang ‘957 fails to disclose the region of interest being a subset of the frame of pixels and including the pixels indicative of motion; and modifying the region of interest to include pixels that were not identified as indicative of motion, thereby generating a modified region of interest, wherein the modified region of interest includes the object and pixels indicative of motion.
However, in an analogous art, Kim ‘663 discloses a region of interest being a subset of a frame of pixels and including pixels indicative of motion (paragraph 37, lines 4-5: “The ROI can be the received motion region itself, or an enlarged version of the motion region obtained by including neighboring pixels.”); and modifying the region of interest to include pixels that were not identified as indicative of motion, thereby generating a modified region of interest, wherein the modified region of interest includes the object and pixels indicative of motion (paragraph 38, lines 5-7: “the radius of the ROI can increase as a function of the number of frames between the detected motion and the current frame for which an ROI is being determined.”). It would have been obvious to one of ordinary skill in the art before the effective filing date of the claimed invention to modify the method in Venetianer and Wang ‘957 by incorporating this feature taught in Kim ‘663 for the purpose of isolating dynamic content with a smaller subset of pixels and enabling more efficient processing and accurate detection of relevant events.
The combination of Venetianer, Wang ‘957 and Kim ‘663 fails to disclose identifying an object based on pixels within the modified region of interest.
However, Vitek discloses identifying an object based on pixels within a modified region of interest (paragraph 18, lines 5-6: “a first heatmap indicating a probability that pixels of the image corresponds to a center of an object”; paragraph 19, lines 4-5: “applying an object detection network 140 to each of the cropped images”; paragraph 39, lines 1-2: “applying an object detection network 140 to each of the cropped images”). It would have been obvious to one of ordinary skill in the art before the effective filing date of the claimed invention to modify the method in Venetianer, Wang ‘957 and Kim ‘663 by incorporating this feature taught in Vitek for the purpose of focusing computation on a refined region of interest, thereby improving detection accuracy while reducing processing overhead and noise.
The combination of Venetianer, Wang ‘957, Kim ‘663 and Vitek fails to disclose after generating the modified region of interest, issuing an alarm.
However, in an analogous art, Fancella discloses after generating a modified region of interest (corresponding to a detected motion), issuing an alarm. (claim 1, lines 4-5: “communicating an electronic notification in response to detected motion”). It would have been obvious to one of ordinary skill in the art before the effective filing date of the claimed invention to modify the method in Venetianer, Wang ‘957, Kim ‘663 and Vitek by incorporating this feature taught in Fancella for the purpose of triggering a timely response based on detected activity in the refined region, improving system responsiveness and event detection accuracy.
Regarding claim 40, Vitek further disclose that modifying the region of interest comprises scaling the region of interest (corresponding to downscaled ROIs) to comply with a dimension upon which an object detection model is configured to operate (paragraph 19, lines 1-5: “The merged ROIs are downscaled … object detectors … operate on the downscaled ROIs to output accurate detections … by operating on a reduced image … cropped images based on the generated ROIs”; paragraph 37, lines 4-5: “a total number of pixels of the cropped images is less than a number of pixels of the image.”); and identifying the object comprises applying the object detection model to the modified region of interest (paragraph 39, line 5: “an object detection network 140 to detect the objects in the cropped images.”). It would have been obvious to one of ordinary skill in the art before the effective filing date of the claimed invention to modify the method in Venetianer, Wang ‘957, Kim ‘663, Vitek and Fancella by incorporating this feature further taught in Vitek for the purpose of ensuring compatibility with the detection model while enabling accurate object identification within the region of interest.
Claim 38 is rejected under 35 U.S.C. 103 as being unpatentable over Venetianer et al. (US 2007/0122000) in view of Wang ‘957, and further in view of Kim ‘663, Vitek et al. (US 2022/0147751), Fancella (US 2007/0046462) and Jha et al. (US 2022/0051020).
Regarding claim 38, the combination of Venetianer, Wang ‘957, Kim ‘663, Vitek and Fancella fails to disclose modifying the region of interest comprises translating a boundary of the region of interest from a first position in which a portion of the boundary resides outside the frame of pixels to a second position in which the portion of the boundary is inside or upon an edge of the frame of pixels.
However, Jha discloses modifying the region of interest comprises translating a boundary of the region of interest from a first position in which a portion of the boundary resides outside the frame of pixels (corresponding to a bounding box outside the object of interest) to a second position in which the portion of the boundary is inside or upon an edge of the frame of pixels (paragraph 162, lines 2-3: “a region which is included in the input first image frame … and is bounded by the bounding box coordinates”; paragraph 164, lines 6-7: “The extracted object detection result may include bounding box coordinates for the object of interest”; paragraph 79, lines 2-3: “select a bounding box … around the object of interest … in the input first image frame”). It would have been obvious to one of ordinary skill in the art before the effective filing date of the claimed invention to modify the method in Venetianer, Wang ‘957, Kim ‘663, Vitek and Fancella by incorporating this feature taught in Jha for the purpose of ensuring the region stays within the image so it can be properly processed without error or missing data.
Claim 39 is rejected under 35 U.S.C. 103 as being unpatentable over Venetianer et al. (US 2007/0122000) in view of Wang ‘957, and further in view of Kim ‘663, Vitek et al. (US 2022/0147751), Fancella (US 2007/0046462) and Glickman et al. (US 2010/0045423).
Regarding claim 39 the combination of Venetianer, Wang ‘957, Kim ‘663, Vitek and Fancella fails to disclose that the modified region of interest has a size that is less than or equal to a size of the frame of pixels.
However, in an analogous art, Glickman discloses that a modified region of interest has a size that is less than or equal to a size of a frame of pixels (paragraph 89, lines 2-3: “A position of a bounding box within the image is then determined. The ROI is inside the bounding box”). It would have been obvious to one of ordinary skill in the art before the effective filing date of the claimed invention to modify the method in Venetianer, Wang ‘957, Kim ‘663, Vitek and Fancella by incorporating this feature taught in Jha for the purpose of ensuring the region can be processed within image bounds, thereby avoiding errors and maintaining valid pixel data for analysis.
Allowable Subject Matter
Claims 31 and 32 are objected to as being dependent upon a rejected base claim, but would be allowable if rewritten in independent form including all of the limitations of the base claim and any intervening claims.
The following is a statement of reasons for the indication of allowable subject matter: the prior art fails to disclose the recited combination of elements, including identifying a first length of a boundary of the pixels indicative of motion; calculating a second length that is equal to the first length multiplied by a factor; and setting a boundary of the region of interest to have a length equal to the second length, as in claims 31; identifying a first length of a first boundary of the pixels indicative of motion; making a determination that the first length is greater than a second length of a second boundary of the pixels indicative of motion; and after making the determination, calculating a dimension that is equal to the first length multiplied by a factor; and setting a boundary of the region of interest to have a length equal to the dimension, as in claim 32.
Conclusion
The prior art made of record and not relied upon is considered pertinent to applicant's disclosure.
Watson (US 10,074,183) discloses selecting pixels within a region of interest that is determined based on movement of the imaging element at the time the image is generated.
Any inquiry concerning this communication or earlier communications from the examiner should be directed to SAM BHATTACHARYA whose telephone number is (571)272-7917. The examiner can normally be reached weekdays, 9-5:30.
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, Matthew D. Anderson can be reached at (571) 272-4177. 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.
/SAM BHATTACHARYA/Primary Examiner, Art Unit 2646
Prosecution Insights