DETAILED ACTION
The present application, filed on or after March 16, 2013, is being examined under the first inventor to file provisions of the AIA .
Priority
This application claims benefit of foreign priority under 35 U.S.C. 119(a)-(d) of Application No. JP2024-051852, filed in Japan on 03/27/2024.
Information Disclosure Statement
The information disclosure statement (IDS) submitted on 03/25/2025 was considered by the examiner.
Specification
The disclosure is objected to because it contains an embedded hyperlink and/or other form of browser-executable code in Par. [0070] of the specification, Reference: Alan D. Thompson, 'Inside language models (from GPT-4 to Nova) https://lifearchitect.ai/models/ (February 25, 2025). Applicant is required to delete the embedded hyperlink and/or other form of browser-executable code; references to websites should be limited to the top-level domain name without any prefix such as http:// or other browser-executable code. See MPEP § 608.01.
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.
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 1-2 and 17-20 are rejected under 35 U.S.C. 103 as being unpatentable over Sawai (U.S. Patent Pub No. 2019/0147598 A1, hereafter referred as Sawai) in view of Jin et al. (NPL: Unsupervised Hard Example Mining from Videos for Improved Object Detection, hereafter referred as Jin).
Regarding Claim 1:
Sawai teaches an information processing apparatus comprising: at least one memory storing instructions; and at least one processor that, upon execution of the stored instructions (Sawai: Par. [0020]; The image processing apparatus 101 is, in one example, a general-purpose computer, and its hardware arrangement includes, for example, a storage unit 102, a control unit 103, a function unit 104, an input unit 105, an output unit 106, and an interface (I/F) 107.), causes the information processing apparatus to: detect an object in a captured image (Sawai: Par. [0033]; The head detection unit 204 determines whether a human head is included in the input image obtained from the image obtainment unit 201, and obtains, when a head is included, the position and the size (the vertical and horizontal sizes of the region including the head) of the head in the image.); and generate an image acquired by superimposing (Sawai: Par. [0038]; The combining unit 209 generates and outputs a combined image by combining the silhouette image generated by the occluding image generation unit 208 with the background image obtained by the background image obtainment unit 202 by executing a blending.), on a predetermined background image (Sawai: Par. [0031]; The background image obtainment unit 202 obtains a background image of a state in which a foreground object such as a person is absent in the same image capturing region as the image obtained by the image obtainment unit 201. The background image may be an image captured in a state in which a foreground object is absent or an image generated from a plurality of images based on image processing or learning. For example, the background image can be prepared beforehand as an image captured before the activation of the monitoring system.), a predetermined object image that corresponds to the type of the object, based on a result of the estimation (Sawai: Par. [0032]; The foreground extraction unit 203 extracts a foreground region by comparing the input image obtained by the image obtainment unit 201 and the background image obtained by the background image obtainment unit 202. The foreground extraction unit 203 can generate, for example, a mask image in which the foreground region is set as “1” and the background image is set as “0”, Par. [0037]; In the mask image in which the shadow portion has been removed by the shadow removal unit 207, the occluding image generation unit 208 generates a silhouette image of the region set with a value “1”, which indicates the foreground, by filling the region with arbitrary RGB values or adding a texture to the region.).
Sawai fails to teach track the object in a chronologically captured image, based on a result of the detection of the object; estimate, from the captured image, a region in which detection of the object in the captured image is difficult for the detection unit per type of the object, based on the result of the detection of the object and a result of the tracking of the object.
Jin, like Sawai, is directed to image processing techniques for object detection. Jin does teach track the object in a chronologically captured image, based on a result of the detection of the object (Jin: p. 322; Given a sequence of video frames, the face of the actor is consistently detected except at frame f. Such isolated “off-flickers” can be harvested in an unsupervised fashion to form a set of hard positives, We generate tracklets using the method from [26] and show results incorporating hard positives on pedestrian and face detection in the experiments section.); estimate, from the captured image, a region in which detection of the object in the captured image is difficult for the detection unit per type of the object, based on the result of the detection of the object and a result of the tracking of the object (Jin: p. 322; The idea is to look for “off-flickers” of a detector in a video tracklet – given a series of detections of an object in a video, such as a face, we can search for single frames that have no detections but are surrounded by detections on either side. Of course, these could be caused by short-duration occlusions, for example, but a large percentages of these “off-flickers” are hard positives, as in Fig. 3.).
It would have been obvious to one of ordinary skill in the art before the effective filing date of the claimed invention to modify Sawai to utilize the tracking technique, as taught by Jin, to arrive at the claimed invention discussed above. Such a modification is the result of combining prior art elements according to known methods for improvement to yield predictable results. As taught by Jin, the proposed modification helps to fine-tune a detector leading to improved performance (Jin: p. 318).
In regards to Claim 2, Sawai as modified by Jin further teaches the information processing apparatus according to Claim 1, wherein the at least one processor, upon execution of the stored instructions, further causes the information processing apparatus to estimate the region from a region in the captured image that is defined such that the object is present (Jin: p. 322; The idea is to look for “off-flickers” of a detector in a video tracklet – given a series of detections of an object in a video, such as a face, we can search for single frames that have no detections but are surrounded by detections on either side. Of course, these could be caused by short-duration occlusions, for example, but a large percentages of these “off-flickers” are hard positives, as in Fig. 3.).
In regards to Claim 17, Sawai as modified by Jin further teaches the information processing apparatus according to Claim 1, wherein the at least one processor, upon execution of the stored instructions, further causes the information processing apparatus to, in a case where an object cannot be tracked, based on the result of detection of the object, estimate, as the region in which the detection of the object is difficult, a region that corresponds to the object that cannot be tracked (Jin: p. 322; The idea is to look for “off-flickers” of a detector in a video tracklet – given a series of detections of an object in a video, such as a face, we can search for single frames that have no detections but are surrounded by detections on either side. Of course, these could be caused by short-duration occlusions, for example, but a large percentages of these “off-flickers” are hard positives, as in Fig. 3.).
In regards to Claim 18, Sawai as modified by Jin further teaches the information processing apparatus according to Claim 17, wherein the at least one processor, upon execution of the stored instructions, further causes the information processing apparatus to estimate, as the region in which the detection of the object is difficult, a region that corresponds to the object that is tracked before the object cannot be tracked (Jin: p. 322; The idea is to look for “off-flickers” of a detector in a video tracklet – given a series of detections of an object in a video, such as a face, we can search for single frames that have no detections but are surrounded by detections on either side. Of course, these could be caused by short-duration occlusions, for example, but a large percentages of these “off-flickers” are hard positives, as in Fig. 3.).
Regarding Claim 19:
Sawai as modified by Jin further teaches an information processing method comprising (Sawai: Par. [0020]; The image processing apparatus 101 is, in one example, a general-purpose computer, and its hardware arrangement includes, for example, a storage unit 102, a control unit 103, a function unit 104, an input unit 105, an output unit 106, and an interface (I/F) 107.): a detection step of detecting an object in a captured image (Sawai: Par. [0033]; The head detection unit 204 determines whether a human head is included in the input image obtained from the image obtainment unit 201, and obtains, when a head is included, the position and the size (the vertical and horizontal sizes of the region including the head) of the head in the image.); a tracking step of tracking the object in a chronologically captured image, based on a result of detection of the object at the detection step (Jin: p. 322; Given a sequence of video frames, the face of the actor is consistently detected except at frame f. Such isolated “off-flickers” can be harvested in an unsupervised fashion to form a set of hard positives, We generate tracklets using the method from [26] and show results incorporating hard positives on pedestrian and face detection in the experiments section.); an estimation step of estimating, from the captured image, a region in which detection of the object in the captured image is difficult at the detection step per type of the object, based on the result of detection of the object at the detection step and a result of tracking of the object at the tracking step (Jin: p. 322; The idea is to look for “off-flickers” of a detector in a video tracklet – given a series of detections of an object in a video, such as a face, we can search for single frames that have no detections but are surrounded by detections on either side. Of course, these could be caused by short-duration occlusions, for example, but a large percentages of these “off-flickers” are hard positives, as in Fig. 3.); and a generation step of generating an image acquired by superimposing (Sawai: Par. [0038]; The combining unit 209 generates and outputs a combined image by combining the silhouette image generated by the occluding image generation unit 208 with the background image obtained by the background image obtainment unit 202 by executing a blending.), on a predetermined background image (Sawai: Par. [0031]; The background image obtainment unit 202 obtains a background image of a state in which a foreground object such as a person is absent in the same image capturing region as the image obtained by the image obtainment unit 201. The background image may be an image captured in a state in which a foreground object is absent or an image generated from a plurality of images based on image processing or learning. For example, the background image can be prepared beforehand as an image captured before the activation of the monitoring system.), a predetermined object image that corresponds to the type of the object, based on a result of estimation at the estimation step (Sawai: Par. [0032]; The foreground extraction unit 203 extracts a foreground region by comparing the input image obtained by the image obtainment unit 201 and the background image obtained by the background image obtainment unit 202. The foreground extraction unit 203 can generate, for example, a mask image in which the foreground region is set as “1” and the background image is set as “0”, Par. [0037]; In the mask image in which the shadow portion has been removed by the shadow removal unit 207, the occluding image generation unit 208 generates a silhouette image of the region set with a value “1”, which indicates the foreground, by filling the region with arbitrary RGB values or adding a texture to the region.).
Regarding Claim 20:
Sawai as modified by Jin further teaches a non-transitory computer-readable medium storing computer-executable instructions for causing a computer to execute a method comprising (Sawai: Par. [0020]; The image processing apparatus 101 is, in one example, a general-purpose computer, and its hardware arrangement includes, for example, a storage unit 102, a control unit 103, a function unit 104, an input unit 105, an output unit 106, and an interface (I/F) 107.): a detection step of detecting an object in a captured image (Sawai: Par. [0033]; The head detection unit 204 determines whether a human head is included in the input image obtained from the image obtainment unit 201, and obtains, when a head is included, the position and the size (the vertical and horizontal sizes of the region including the head) of the head in the image.); a tracking step of tracking the object in a chronologically captured image, based on a result of detection of the object at the detection step (Jin: p. 322; Given a sequence of video frames, the face of the actor is consistently detected except at frame f. Such isolated “off-flickers” can be harvested in an unsupervised fashion to form a set of hard positives, We generate tracklets using the method from [26] and show results incorporating hard positives on pedestrian and face detection in the experiments section.); an estimation step of estimating, from the captured image, a region in which detection of the object in the captured image is difficult at the detection step per type of the object, based on the result of detection of the object at the detection step and a result of tracking of the object at the tracking step (Jin: p. 322; The idea is to look for “off-flickers” of a detector in a video tracklet – given a series of detections of an object in a video, such as a face, we can search for single frames that have no detections but are surrounded by detections on either side. Of course, these could be caused by short-duration occlusions, for example, but a large percentages of these “off-flickers” are hard positives, as in Fig. 3.); and a generation step of generating an image acquired by superimposing (Sawai: Par. [0038]; The combining unit 209 generates and outputs a combined image by combining the silhouette image generated by the occluding image generation unit 208 with the background image obtained by the background image obtainment unit 202 by executing a blending.), on a predetermined background image (Sawai: Par. [0031]; The background image obtainment unit 202 obtains a background image of a state in which a foreground object such as a person is absent in the same image capturing region as the image obtained by the image obtainment unit 201. The background image may be an image captured in a state in which a foreground object is absent or an image generated from a plurality of images based on image processing or learning. For example, the background image can be prepared beforehand as an image captured before the activation of the monitoring system.), a predetermined object image that corresponds to the type of the object, based on a result of estimation at the estimation step (Sawai: Par. [0032]; The foreground extraction unit 203 extracts a foreground region by comparing the input image obtained by the image obtainment unit 201 and the background image obtained by the background image obtainment unit 202. The foreground extraction unit 203 can generate, for example, a mask image in which the foreground region is set as “1” and the background image is set as “0”, Par. [0037]; In the mask image in which the shadow portion has been removed by the shadow removal unit 207, the occluding image generation unit 208 generates a silhouette image of the region set with a value “1”, which indicates the foreground, by filling the region with arbitrary RGB values or adding a texture to the region.).
Claims 3-9 are rejected under 35 U.S.C. 103 as being unpatentable over Sawai (U.S. Patent Pub No. 2019/0147598 A1, hereafter referred as Sawai) in view of Jin et al. (NPL: Unsupervised Hard Example Mining from Videos for Improved Object Detection, hereafter referred as Jin) and Hassbring et al. (U.S. Patent Pub No. 2023/0108667 A1, hereafter referred as Hassbring).
In regards to Claim 3, Sawai as modified by Jin fails to further teach the information processing apparatus according to Claim 1, wherein the at least one processor, upon execution of the stored instructions, further causes the information processing apparatus to acquire an estimation accuracy of the region in which the detection of the object is difficult per type of the object and determine the region in which the detection of the object is difficult, based on the estimation accuracy.
Hassbring, like Sawai, is directed to image processing techniques for object detection. Hassbring does teach wherein the at least one processor, upon execution of the stored instructions, further causes the information processing apparatus to acquire an estimation accuracy of the region in which the detection of the object is difficult per type of the object and determine the region in which the detection of the object is difficult, based on the estimation accuracy (Hassbring: Par. [0026]; The object detection algorithm 114 may be configured or trained to detect objects in need of masking, such as human faces, keypads, vehicle license plates etc. The object detection algorithm's 114 detection score D(i) for an image region i may be a confidence level or a probability, which is interpreted as the likelihood that an object of the detected type is present in the image region. Alternatively, the detection score can refer to a scale [0,1] in arbitrary units, the endpoints of which may conceptually carry labels such as ‘no suggestion that an object is present’ (0) and ‘highest certainty that an object is present’ (1). The detection score is provided as a value table or map, which associates each image region with a detection score value.)
It would have been obvious to one of ordinary skill in the art before the effective filing date of the claimed invention to modify Sawai to utilize the detection reliabitlity score, as taught by Hassbring, to arrive at the claimed invention discussed above. Such a modification is the result of combining prior art elements according to known methods for improvement to yield predictable results. As taught by Hassbring, the proposed modification allows for masking even in lower visibility situations (Hassbring: Par. [0003-0004]).
In regards to Claim 4, Sawai as modified by Jin and Hassbring further teaches the information processing apparatus according to Claim 3, wherein the at least one processor, upon execution of the stored instructions, further causes the information processing apparatus to adjust an estimation accuracy of a second region to an estimation accuracy higher than that of a first region that corresponds to the object in the captured image that is detected, based on the result of detection of the object and the result of tracking of the object, the second region being a region in which the object is not detected and corresponding to the object that is tracked (Hassbring: Par. [0026]; The object detection algorithm 114 may be configured or trained to detect objects in need of masking, such as human faces, keypads, vehicle license plates etc. The object detection algorithm's 114 detection score D(i) for an image region i may be a confidence level or a probability, which can be interpreted as the likelihood that an object of the detected type is present in the image region. Alternatively, the detection score can refer to a scale [0,1] in arbitrary units, the endpoints of which may conceptually carry labels such as ‘no suggestion that an object is present’ (0) and ‘highest certainty that an object is present’ (1). The detection score is provided as a value table or map, which associates each image region with a detection score value.).
In regards to Claim 5, Sawai as modified by Jin and Hassbring further teaches the information processing apparatus according to Claim 4, wherein the at least one processor, upon execution of the stored instructions, further causes the information processing apparatus to adjust an estimation accuracy of a third region to be higher than that of the second region, the third region being a region in which the object is not detected and the object is not tracked (Hassbring: Par. [0026]; The object detection algorithm 114 may be configured or trained to detect objects in need of masking, such as human faces, keypads, vehicle license plates etc. The object detection algorithm's 114 detection score D(i) for an image region i may be a confidence level or a probability, which can be interpreted as the likelihood that an object of the detected type is present in the image region. Alternatively, the detection score can refer to a scale [0,1] in arbitrary units, the endpoints of which may conceptually carry labels such as ‘no suggestion that an object is present’ (0) and ‘highest certainty that an object is present’ (1). The detection score is provided as a value table or map, which associates each image region with a detection score value.).
In regards to Claim 6, Sawai as modified by Jin and Hassbring further teaches the information processing apparatus according to Claim 3, wherein the at least one processor, upon execution of the stored instructions, further causes the information processing apparatus to generate the image acquired by superimposing, on the predetermined background image, the predetermined object image preferentially in a region the estimation accuracy of which is high (Hassbring: Par. [0026]; The masking function 116 may, for example, perform a thresholding operation such than the privacy mask is applied to image regions for which the detection score is greater than or equal to a masking threshold).
In regards to Claim 7, Sawai as modified by Jin and Hassbring teaches the information processing apparatus according to Claim 1, wherein the at least one processor, upon execution of the stored instructions, further causes the information processing apparatus to estimate the region in which the detection of the object is difficult, based on at least reliability of the detection or reliability of the tracking (Hassbring: Par. [0026]; The object detection algorithm 114 may be configured or trained to detect objects in need of masking, such as human faces, keypads, vehicle license plates etc. The object detection algorithm's 114 detection score D(i) for an image region i may be a confidence level or a probability, which can be interpreted as the likelihood that an object of the detected type is present in the image region. Alternatively, the detection score can refer to a scale [0,1] in arbitrary units, the endpoints of which may conceptually carry labels such as ‘no suggestion that an object is present’ (0) and ‘highest certainty that an object is present’ (1). The detection score is provided as a value table or map, which associates each image region with a detection score value.).
In regards to Claim 8, Sawai as modified by Jin and Hassbring further teaches the information processing apparatus according to Claim 7, wherein the at least one processor, upon execution of the stored instructions, further causes the information processing apparatus to estimate, as the region in which the detection of the object is difficult, a region in which at least the reliability of the detection or the reliability of the tracking is less than a predetermined reliability threshold (Hassbring: Par. [0026]; The object detection algorithm 114 may be configured or trained to detect objects in need of masking, such as human faces, keypads, vehicle license plates etc. The object detection algorithm's 114 detection score D(i) for an image region i may be a confidence level or a probability, which can be interpreted as the likelihood that an object of the detected type is present in the image region. Alternatively, the detection score can refer to a scale [0,1] in arbitrary units, the endpoints of which may conceptually carry labels such as ‘no suggestion that an object is present’ (0) and ‘highest certainty that an object is present’ (1). The detection score is provided as a value table or map, which associates each image region with a detection score value, The masking function 116 may, for example, perform a thresholding operation such than the privacy mask is applied to image regions for which the detection score is greater than or equal to a masking threshold).
In regards to Claim 9, Sawai as modified by Jin and Hassbring further teaches the information processing apparatus according to Claim 1, wherein the at least one processor, upon execution of the stored instructions, further causes the information processing apparatus to set, as the region in which the detection of the object is difficult, a region in the captured image that is set by a user (Hassbring: Par. [0055]; With respect to Event 1, the value of the threshold β≥0 can be set by trial and error. More precisely, the video camera 120 when configured with different candidate values β.sub.1, β.sub.2, . . . can be exposed to rapid luminance variations, during which an operator monitors whether any unwanted unmasking of faces, keypads, license plates etc. occurs.).
Claims 10-16 are rejected under 35 U.S.C. 103 as being unpatentable over Sawai (U.S. Patent Pub No. 2019/0147598 A1, hereafter referred as Sawai) in view of Jin et al. (NPL: Unsupervised Hard Example Mining from Videos for Improved Object Detection, hereafter referred as Jin), Hassbring et al. (U.S. Patent Pub No. 2023/0108667 A1, hereafter referred as Hassbring), and Cobb et al. (U.S. Patent Pub No. 2011/0052003 A1, hereafter referred as Cobb).
In regards to Claim 10, Sawai as modified by Jin fails to further teach the information processing apparatus according to Claim 1, wherein the at least one processor, upon execution of the stored instructions, further causes the information processing apparatus to estimate the region in which the detection of the object is difficult based on an amount of movement of the object that is tracked.
Cobb, like Sawai, is directed to image processing techniques for object detection. Cobb in combination with Hassbring does teach to estimate the region in which the detection of the object is difficult based on an amount of movement of the object that is tracked (Cobb: Par. [0060]; The consistent motion flow field component 330 receives the detected foreground patches and the motion flow field and produces the consistent motion flow field. A detected foreground patch is determined to be reliable (not spurious) by the merge/split component 325 when a consistent flow field is observed for the detected foreground patch over a predetermined number of sequential frames. Detected foreground patches and feature vectors that are not reliable are removed by the consistent motion flow field component 330. In some embodiments the predetermined number of sequential frames is three. The motion flow field component 330 outputs the consistent motion flow field to the tracker component 210 as part of the FG/BG image data 335; Hassbring: Par. [0026]; The object detection algorithm's 114 detection score D(i) for an image region i may be a confidence level or a probability, which can be interpreted as the likelihood that an object of the detected type is present in the image region. The detection score is provided as a value table or map, which associates each image region with a detection score value).
It would have been obvious to one of ordinary skill in the art before the effective filing date of the claimed invention to modify Sawai to utilize the motion estimation, as taught by Cobb, to arrive at the claimed invention discussed above. Such a modification is the result of combining prior art elements according to known methods for improvement to yield predictable results. As taught by Cobb, the proposed modification allows the surveillance system to correctly detect and track foreground objects (Cobb: Par. [0005]).
The reasons for combining the references with Hassbring are the same as those discussed above in conjunction with Claim 3 mutatis mutandis.
In regards to Claim 11, Sawai as modified by Jin, Hassbring, and Cobb further teaches the information processing apparatus according to Claim 10, wherein the at least one processor, upon execution of the stored instructions, further causes the information processing apparatus to estimate, as the region in which the detection of the object is difficult, a region in which the amount of movement of the object is more than a predetermined amount of movement (Cobb: Par. [0060]; The consistent motion flow field component 330 receives the detected foreground patches and the motion flow field and produces the consistent motion flow field. A detected foreground patch is determined to be reliable (not spurious) by the merge/split component 325 when a consistent flow field is observed for the detected foreground patch over a predetermined number of sequential frames. Detected foreground patches and feature vectors that are not reliable are removed by the consistent motion flow field component 330. In some embodiments the predetermined number of sequential frames is three. The motion flow field component 330 outputs the consistent motion flow field to the tracker component 210 as part of the FG/BG image data 335.).
In regards to Claim 12, Sawai as modified by Jin, Hassbring, and Cobb further teaches the information processing apparatus according to Claim 1, wherein the at least one processor, upon execution of the stored instructions, further causes the information processing apparatus to estimate the region in which the detection of the object is difficult, based on a first aspect ratio of a region that corresponds to the object and that is chronologically earlier and a second aspect ratio of a region that corresponds to the object and that is chronologically later (Cobb: Par. [0074]; The patch management component 525 determines if the size of the foreground patch corresponding to the existing track 640 is similar to the size of the detected foreground patch 645, and, if so, the detected foreground patch 645 is associated with the existing track 640. The size may be considered to be similar when the area of the detected foreground patch 645 is within 60% to 120% of the area of the foreground patch corresponding to the existing track 640. When the size is not similar, the patch management component 525 instructs the covariance matcher component 520 to compute the covariance matrix for the detected foreground patch 645 and determine whether or not the detected foreground patch 645 is associated with the existing track 645.).
In regards to Claim 13, Sawai as modified by Jin, Hassbring, and Cobb further teaches the information processing apparatus according to Claim 12, wherein the at least one processor, upon execution of the stored instructions, further causes the information processing apparatus to estimate the region in which the detection of the object is difficult based on a change amount of the second aspect ratio with respect to the first aspect ratio (Cobb: Par. [0074]; The patch management component 525 determines if the size of the foreground patch corresponding to the existing track 640 is similar to the size of the detected foreground patch 645, and, if so, the detected foreground patch 645 is associated with the existing track 640. The size may be considered to be similar when the area of the detected foreground patch 645 is within 60% to 120% of the area of the foreground patch corresponding to the existing track 640. When the size is not similar, the patch management component 525 instructs the covariance matcher component 520 to compute the covariance matrix for the detected foreground patch 645 and determine whether or not the detected foreground patch 645 is associated with the existing track 645.).
In regards to Claim 14, Sawai as modified by Jin, Hassbring, and Cobb further teaches the information processing apparatus according to Claim 13, wherein the at least one processor, upon execution of the stored instructions, further causes the information processing apparatus to calculate, as the change amount, a value acquired by dividing the first aspect ratio by the second aspect ratio and estimate, as the region in which the detection of the object is difficult, a region in which the change amount is more than a predetermined change amount threshold (Cobb: Par. [0074]; The patch management component 525 determines if the size of the foreground patch corresponding to the existing track 640 is similar to the size of the detected foreground patch 645, and, if so, the detected foreground patch 645 is associated with the existing track 640. The size may be considered to be similar when the area of the detected foreground patch 645 is within 60% to 120% of the area of the foreground patch corresponding to the existing track 640. When the size is not similar, the patch management component 525 instructs the covariance matcher component 520 to compute the covariance matrix for the detected foreground patch 645 and determine whether or not the detected foreground patch 645 is associated with the existing track 645.).
In regards to Claim 15, Sawai as modified by Jin, Hassbring, and Cobb further teaches the information processing apparatus according to Claim 1, wherein the at least one processor, upon execution of the stored instructions, further causes the information processing apparatus to estimate the region in which the detection of the object is difficult based on a size of a region that corresponds to the object that is tracked (Cobb: Par. [0074]; The patch management component 525 determines if the size of the foreground patch corresponding to the existing track 640 is similar to the size of the detected foreground patch 645, and, if so, the detected foreground patch 645 is associated with the existing track 640. The size may be considered to be similar when the area of the detected foreground patch 645 is within 60% to 120% of the area of the foreground patch corresponding to the existing track 640. When the size is not similar, the patch management component 525 instructs the covariance matcher component 520 to compute the covariance matrix for the detected foreground patch 645 and determine whether or not the detected foreground patch 645 is associated with the existing track 645.).
In regards to Claim 16, Sawai as modified by Jin, Hassbring, and Cobb further teaches the information processing apparatus according to Claim 15, wherein the at least one processor, upon execution of the stored instructions, further causes the information processing apparatus to estimate, as the region in which the detection of the object is difficult, a region the size of which is more than a predetermined size threshold (Cobb: Par. [0074]; The patch management component 525 determines if the size of the foreground patch corresponding to the existing track 640 is similar to the size of the detected foreground patch 645, and, if so, the detected foreground patch 645 is associated with the existing track 640. The size may be considered to be similar when the area of the detected foreground patch 645 is within 60% to 120% of the area of the foreground patch corresponding to the existing track 640. When the size is not similar, the patch management component 525 instructs the covariance matcher component 520 to compute the covariance matrix for the detected foreground patch 645 and determine whether or not the detected foreground patch 645 is associated with the existing track 645.).
Pertinent Art
The prior art made of record and not relied upon is considered pertinent to applicant's disclosure.
Tripathi et al. (U.S. Patent Pub No. 10,909,349 B1) teaches a way to make training images for object detection by using 3D models instead of only real photos.
Conclusion
Any inquiry concerning this communication or earlier communications from the examiner should be directed to RENAE BITOR whose telephone number is (703)756-5563. The examiner can normally be reached Monday to Friday: 8:00 - 5:30 but off the 1st Friday of the biweek.
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, GREG MORSE can be reached on (571)272-3838. 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.
/RENAE A BITOR/Examiner, Art Unit 2663
/GREGORY A MORSE/Supervisory Patent Examiner, Art Unit 2698
Prosecution Insights