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 .
Priority
Receipt is acknowledged of certified copies of papers submitted under 35 U.S.C. 119(a)-(d), which papers have been placed of record in the file.
Information Disclosure Statement
The information disclosure statements (IDS) submitted on 03/19/2026 and 04/20/2026 are being considered by the examiner.
Response to Amendment
Applicant’s remarks filed 04/09/2026 regarding the specification objection, the claim objections, and the 112(a) and 112(b) rejections submitted in the non-final office action dated 01/12/2026 are persuasive due to the amendments and thus the specification objection, the claim objections, and the 112(a) and 112(b) rejections are withdrawn.
Response to Arguments
Applicant’s arguments, see remarks, filed 04/09/2026, with respect to claims 1-6 regarding the prior art rejection under 35 U.S.C. 102, have been considered, but are moot because the arguments do not apply to the current reference, or combinations of references being used in the current rejection. The Office would like to bring to Applicant’s attention that claims 3, and 5 that were once pointed as allowable subject matter are now rejected on prior art based on the amendment submitted on 04/09/2026.
Remarks
Claim 5 incudes the phrase “if” when reciting a conditional statement. In view of the broadest reasonable interpretation of the claims, MPEP 2111, these limitations may be interpreted in the sense that the limitations occur when the conditional statement occurs, but also introduces the possibility that the conditional statement may not occur. If the condition for performing a conditional statement is not satisfied, the functionality recited by the statement need not be carried out in order for the claimed functionality to be performed. Since the claim fails to recite any specific limitations regarding the possibility that the conditional statement may not occur, the broadest reasonable interpretation of the claim allows for the possibility wherein no functionality is achieved when the conditional statement is not achieved.
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 1-3 are rejected under 35 U.S.C. 103 as being unpatentable over YOSHIMURA et al. (US 20230342951 A1), hereinafter referenced as YOSHIMURA, in view of HAO et al. (US 20220270366 A1), hereinafter referenced as HAO, and further in view of YU et al. (US 20170039457 A1), hereinafter referenced as YU.
Regarding claim 1, YOSHIMURA explicitly teaches an object detection device (Fig. 1. Paragraph [0032]-YOSHIMURA discloses the object tracking apparatus 1 includes an image acquisition section 11, a detection section 12, a decision section 13, and an identification section 14.), which performs object detection processing to detect an area where a target object is present in images captured by a camera (Fig. 1. Paragraph [0032]-YOSHIMURA discloses the detection section 12 detects an object region including an object from the image, and calculates an evaluation value related to the object region (wherein the image is captured by a camera).), the object detection device comprising:
a memory (Fig. 15, #C2 called memory. Paragraph [0163]-YOSHIMURA the computer C includes at least one processor C1 and at least one memory C2. The memory C2 stores a program P for causing the computer C to function as the object tracking apparatuses 1 and 1A. In the computer C, the processor C1 reads the program P from the memory C2 and executes the program P, so that the functions of the object tracking apparatuses 1 and 1A are realized.) configured to store a bounding box indicating the area where the target object is present (Fig. 3. Paragraph [0045]-YOSHIMURA discloses the storage section 120 stores tracking target information 21 (wherein tracking target information includes a bounding box indicating an area where a target is).), the bounding box being output to a comparison image of the images (Fig. 5, illustrates bounding boxes output on a comparison image (wherein image frame #f1 is a comparison image). Paragraph [0055]-YOSHIMURA discloses the detection section 12A detects, from the frame f1, an object region d1 including an object obj1 and an object region d2 including an object obj2.); and
a processor (Fig. 15, #C1 called a processor. Paragraph [0164]-YOSHIMURA discloses as the processor C1, for example, it is possible to use a central processing unit (CPU), a graphic processing unit (GPU), a digital signal processor (DSP), a micro processing unit (MPU), a floating point number processing unit (FPU), a physics processing unit (PPU), a microcontroller, or a combination of these.) configured to execute program codes or commands stored in the memory (Fig. 15. Paragraph [0163]-YOSHIMURA discloses the computer C includes at least one processor C1 and at least one memory C2. The memory C2 stores a program P for causing the computer C to function as the object tracking apparatuses 1 and 1A. In the computer C, the processor C1 reads the program P from the memory C2 and executes the program P, so that the functions of the object tracking apparatuses 1 and 1A are realized.), in order to:
acquire a detection target image of the images (Fig. 5, illustrates a detection target image (wherein image frame #f2 is the detection target image). Paragraph [0032]-YOSHIMURA discloses the image acquisition section 11 acquires an image from an image sequence.), the detection target image being captured at a time after the comparison image is captured (Fig. 5. Paragraph [0046]- YOSHIMURA discloses the moving image F is a moving image in which a plurality of objects are captured, and is a sequence of a plurality of frames f1, f2, f3, and so forth. The frames f1, f2, f3, and so forth are arranged in order of a captured time. Further in paragraph [0047]-YOSHIMURA discloses f1, f2, and f3 are each also referred to as an identifier of the frame. A frame which is to be subjected to a process is also referred to as a target frame. A frame closer to the beginning (frame f1) of the moving image F than the target frame is referred to as “a frame before the target frame”, “a past frame of the target frame”, and the like (wherein the target frame is the detection target image and wherein the frame #f1 is the comparison image).);
provide a plurality of rectangular frames each indicating a candidate for the area where the target object is present in the detection target image (Fig. 5, illustrates a plurality of rectangular frames indicating target locations. Paragraph [0072]-YOSHIMURA discloses as illustrated in FIG. 5, the detection section 12A detects, from the frame f2, an object region d3 including an object obj3, an object region d4 including an object obj4, an object region d5 including an object obj5, and an object region d6 including an object obj6 (wherein the object regions are rectangular frames).);
perform calculation processing to calculate a similarity score that is an index indicating a degree of similarity between the bounding box in the comparison image and the rectangular frame in the detection target image (Fig. 9. Paragraph [0081]-YOSHIMURA discloses the identification section 14A calculates total similarity for the corresponding high evaluation object region and the corresponding tracking target (wherein the bounding box is the high evaluation object region and wherein the rectangular frame is the tracking target). Further in paragraph [0084]-YOSHIMURA discloses FIG. 9 is a diagram for describing a specific example of a similarity matrix related to a high evaluation object region. As illustrated in FIG. 9, the similarity matrix is a matrix of two rows and two columns in which total similarities of respective combinations of the high evaluation object regions d1 and d2 in the frame f2 and the tracking targets ID1 and ID2 registered in the tracking target information 21 are used as elements (wherein the values in the matrix represent the degree of similarity).);
YOSHIMURA fails to explicitly teach perform addition processing to increase a confidence score of a rectangular frame, out of the plurality of rectangular frames, having the similarity score that satisfies a predetermined condition.
However, HAO explicitly teaches perform addition processing to increase a confidence score of a rectangular frame, out of the plurality of rectangular frames, having the similarity score that satisfies a predetermined condition (Figs. 1 and 4. Paragraph [0046]-HAO discloses similarity detector 309 detects paired object patches in frames 303, 304 based on a detected similarity between the paired objects (wherein paired object patches are frames satisfying a predetermined similarity score condition). Further in paragraph [0046]-HAO discloses enhancement module 312 can modify the prediction result within feature map 308 for frame 304 using the prediction result for the similar patch in frame 303 (as stored in history max score cache 311) as discussed herein. For example, if the similar patch in frame 303 has a higher confidence score, the prediction result for the patch in frame 304 is modified to the higher confidence score and classification (wherein the patch is a rectangular frame and wherein increasing a confidence score of a rectangular frame is modifying to a higher confidence score).);
Therefore, it would have been obvious to one of ordinary skill in the art before the effective filing date of the claimed invention was made to combine the teachings of YOSHIMURA of an object detection device, which performs object detection processing to detect an area where a target object is present in images captured by a camera, the object detection device comprising: a memory configured to store a bounding box indicating the area where the target object is present, the bounding box being output to a comparison image of the images; and a processor configured to execute program codes or commands stored in the memory, in order to: acquire a detection target image of the images, the detection target image being captured at a time after the comparison image is captured; provide a plurality of rectangular frames each indicating a candidate for the area where the target object is present in the detection target image; perform calculation processing to calculate a similarity score that is an index indicating a degree of similarity between the bounding box in the comparison image and the rectangular frame in the detection target image with the teachings of HAO of perform addition processing to increase a confidence score of a rectangular frame, out of the plurality of rectangular frames, having the similarity score that satisfies a predetermined condition.
Wherein having YOSHIMURA’s object detection apparatus having perform addition processing to increase a confidence score of a rectangular frame, out of the plurality of rectangular frames, having the similarity score that satisfies a predetermined condition.
The motivation behind the modification would have been to obtain an object detection apparatus that enhances the accuracy in detecting objects in images. Since both YOSHIMURA and HAO relate to object detection, wherein YOSHIMURA is to provide a technique for further improving accuracy in tracking a tracking target in an image sequence, while HAO is using still image object recognition on each frame and similarity detection between frames for improved object recognition. Please see YOSHIMURA et al. (US 20230342951 A1), Paragraph [0010], and HAO et al. (US 20220270366 A1), Paragraph [0020].
YOSHIMURA in view of HAO fail to explicitly teach perform deletion processing to delete a rectangular frame, out of the plurality of rectangular frames, having the confidence score less than a confidence score threshold after the addition processing; and output a rectangular frame remaining after the deletion processing as the bounding box for the comparison image.
However, YU explicitly teaches perform deletion processing to delete a rectangular frame, out of the plurality of rectangular frames, having the confidence score less than a confidence score threshold after the addition processing (Fig. 4. Paragraph [0045]-YU discloses in post-classification, the first plurality of bounding boxes identified from the multi-crop evaluation is further classified to refine the results. In other words, another classifier is applied to the results to raise the confidence that each bounding box contains a business storefront location. Further in paragraph [0051]-YU discloses the second plurality of bounding boxes 440 may be filtered by removing bounding boxes having confidence scores below a set threshold.); and
output a rectangular frame remaining after the deletion processing as the bounding box for the comparison image (Figs. 4 and 6. Paragraph [0051]-YU discloses the filtered bounding boxes may then be associated with the evaluated image and stored in storage system 150 for later use (wherein a filtered bounding box is a rectangular frame remaining and wherein associating with the image and storing in the storage system is outputting).).
Therefore, it would have been obvious to one of ordinary skill in the art before the effective filing date of the claimed invention was made to combine the teachings of YOSHIMURA in view of HAO of an object detection device, which performs object detection processing to detect an area where a target object is present in images captured by a camera, the object detection device comprising: a memory configured to store a bounding box indicating the area where the target object is present, the bounding box being output to a comparison image of the images; and a processor configured to execute program codes or commands stored in the memory, in order to: acquire a detection target image of the images, the detection target image being captured at a time after the comparison image is captured; provide a plurality of rectangular frames each indicating a candidate for the area where the target object is present in the detection target image; perform calculation processing to calculate a similarity score that is an index indicating a degree of similarity between the bounding box in the comparison image and the rectangular frame in the detection target image with the teachings of YU of perform deletion processing to delete a rectangular frame, out of the plurality of rectangular frames, having the confidence score less than a confidence score threshold after the addition processing; and output a rectangular frame remaining after the deletion processing as the bounding box for the comparison image.
Wherein having YOSHIMURA’s object detection apparatus having perform deletion processing to delete a rectangular frame, out of the plurality of rectangular frames, having the confidence score less than a confidence score threshold after the addition processing; and output a rectangular frame remaining after the deletion processing as the bounding box for the comparison image.
The motivation behind the modification would have been to obtain an object detection apparatus that enhances the accuracy in detecting objects in images. Since both YOSHIMURA and YU relate to object detection, wherein YOSHIMURA is to provide a technique for further improving accuracy in tracking a tracking target in an image sequence, while YU has the advantage that it integrates the proposal generation and post-processing using a single network to predict a large number of proposals and confidences at the same time. Please see YOSHIMURA et al. (US 20230342951 A1), Paragraph [0010], and YU et al. (US 20170039457 A1), Paragraph [0023].
Regarding claim 2, YOSHIMURA in view of HAO and further in view of YU explicitly teach the object detection device according to claim 1,
YOSHIMURA further explicitly teaches wherein the processor(Fig. 9. Paragraph [0081]-YOSHIMURA discloses the identification section 14A calculates total similarity for the corresponding high evaluation object region and the corresponding tracking target. Further in paragraph [0084]-YOSHIMURA discloses FIG. 9 is a diagram for describing a specific example of a similarity matrix related to a high evaluation object region. As illustrated in FIG. 9, the similarity matrix is a matrix of two rows and two columns in which total similarities of respective combinations of the high evaluation object regions d1 and d2 in the frame f2 and the tracking targets ID1 and ID2 registered in the tracking target information 21 are used as elements (wherein the values in the matrix represent the degree of similarity).):
a position score that is the index indicating the degree of similarity between a position of the bounding box in the comparison image and a position of the rectangular frame in the detection target image (Fig. 3. Paragraph [0048]-YOSHIMURA discloses the plurality of types of similarity referred to by the identification section 14A include positional similarity in addition to appearance similarity. The positional similarity is similarity that is based on a position of an object region in a frame in which the object region has been detected and on a position of a tracking target region that is associated with a tracking target. Further in paragraph [0156]-YOSHIMURA discloses the similarity based on a position in a three-dimensional space is calculated as similarity between a position of the object region and a position of the tracking target region in the three-dimensional space. For example, the positions of the respective regions in the three-dimensional space can be inferred based on frames included in the moving image F. For example, even in a case where positions of two object regions are close to each other in a two-dimensional frame, the two object regions may be far apart from each other in a three-dimensional space. By using the similarity based on the position in the three-dimensional space, it is possible to further accurately calculate the total similarity.);
an area score that is the index indicating the degree of similarity between an area of the bounding box in the comparison image and an area of the rectangular frame in the detection target image (Figs. 3 and 7. Paragraph [0048]-YOSHIMURA discloses the positional similarity is similarity that is based on a position of an object region in a frame in which the object region has been detected and on a position of a tracking target region that is associated with a tracking target. For example, the tracking target region is a region including a tracking target in at least any of frames before a target frame (i.e., a frame in which the object region has been detected). The positional similarity can be intersection over union (IoU) between the object region and the tracking target region (wherein calculating positional similarity with intersection over union is calculating an area score).)
an aspect ratio score that is the index indicating the degree of similarity between an aspect ratio of the bounding box in the comparison image and an aspect ratio of the rectangular frame in the detection target image (Fig. 3. Paragraph [0151]-YOSHIMURA discloses the second example embodiment can also be altered to include other types of similarity in addition to appearance similarity and IoU as the plurality of types of similarity. For example, specific examples of such other types of similarity include similarity that is based on a moving speed, a feature point, a size, or a position in a three-dimensional space of each of an object region and a tracking target region, and the like. Further in paragraph [0155]-YOSHIMURA discloses the similarity based on a size is similarity based on a size of the object region and on a size of the tracking target region (wherein size is the aspect ratio score as the aspect ratio is a ratio between width and height and size includes a measure of length and width).).
Regarding claim 3, YOSHIMURA in view of HAO and further in view of YU and further in view of TAMURA explicitly teach the object detection device according to claim 2,
YOSHIMURA further explicitly teaches wherein the processor uses a product of the position score (Fig. 7. Paragraph [0081]-YOSHIMURA discloses in step S27-4 of FIG. 7, the identification section 14A calculates total similarity for the corresponding high evaluation object region and the corresponding tracking target. In this example, the total similarity is a weighted average of appearance similarity and IoU (wherein the IoU is a position score and wherein the weighted average calculation involves the use of using the products of the different scores).), the aspect ratio score (Fig. 3. Paragraph [0151]-YOSHIMURA discloses the second example embodiment can also be altered to include other types of similarity in addition to appearance similarity and IoU as the plurality of types of similarity. For example, specific examples of such other types of similarity include similarity that is based on a moving speed, a feature point, a size, or a position in a three-dimensional space of each of an object region and a tracking target region, and the like. Further in paragraph [0155]-YOSHIMURA discloses the similarity based on a size is similarity based on a size of the object region and on a size of the tracking target region (wherein size is the aspect ratio score as the aspect ratio is a ratio between width and height and size includes a measure of length and width), and the area score for the similarity score (Figs. 3 and 7. Paragraph [0081]-YOSHIMURA discloses in step S27-4 of FIG. 7, the identification section 14A calculates total similarity for the corresponding high evaluation object region and the corresponding tracking target. In this example, the total similarity is a weighted average of appearance similarity and IoU (wherein the IoU is an area score and wherein the weighted average calculation involves the use of using the products of the different scores). Further in paragraph [0048]-YOSHIMURA discloses the positional similarity is similarity that is based on a position of an object region in a frame in which the object region has been detected and on a position of a tracking target region that is associated with a tracking target. For example, the tracking target region is a region including a tracking target in at least any of frames before a target frame (i.e., a frame in which the object region has been detected). The positional similarity can be intersection over union (IoU) between the object region and the tracking target region (wherein calculating positional similarity with intersection over union is calculating an area score).)).
Claim 5 is rejected under 35 U.S.C. 103 as being unpatentable over YOSHIMURA et al. (US 20230342951 A1), hereinafter referenced as YOSHIMURA, in view of HAO et al. (US 20220270366 A1), hereinafter referenced as HAO, and further in view of YU et al. (US 20170039457 A1), hereinafter referenced as YU, and further in view of and LIM et al. (US 20240193803 A1), hereinafter referenced as LIM, and further in view of OTAKE et al. (US 20230126046 A1), hereinafter referenced as OTAKE.
Regarding claim 5, YOSHIMURA in view of HAO and further in view of YU explicitly teach the object detection device according to claim 1,
YOSHIMURA further explicitly teaches wherein the processor performs (Fig. 15. Paragraph [0163]-YOSHIMURA discloses the computer C includes at least one processor C1 and at least one memory C2. The memory C2 stores a program P for causing the computer C to function as the object tracking apparatuses 1 and 1A. In the computer C, the processor C1 reads the program P from the memory C2 and executes the program P, so that the functions of the object tracking apparatuses 1 and 1A are realized.):
YOSHIMURA in view of HAO and further in view of YU fail to explicitly teach Non-Maximum Suppression (NMS) processing to the plurality of rectangular frames to calculate an overlap ratio by dividing an area of intersection of two of the rectangular frames overlapping each other by an area of union of the two of the rectangular frames, and calculates the similarity score between the bounding box output to the comparison image and the rectangular frames remaining after the NMS processing as the calculation processing.
However, LIM explicitly teaches Non-Maximum Suppression (NMS) processing to the plurality of rectangular frames to calculate an overlap ratio by dividing an area of intersection of two of the rectangular frames overlapping each other by an area of union of the two of the rectangular frames (Fig. 7, illustrates calculating the overlap ratio. Paragraph [0104]-LIM discloses referring to FIG. 7, the overlapping degree between the first bounding box Bbox 1 and the second bounding box Bbox 2 may be obtained using an Intersection over Union (IoU) method.), and
calculates the similarity score between the bounding box output to the comparison image and the rectangular frames remaining after the NMS processing as the calculation processing (Fig. 3. Paragraph [0078]-LIM discloses in S330, the processor 20 may calculate a three-dimensional overlapping degree by reflecting the depth deviation to the two-dimensional overlapping degree (wherein an overlapping degree is the similarity score). Further in paragraph [0134]-LIM discloses each NMS procedure may include procedures S310 to S340 illustrated in FIG. 3. Further in paragraph [0135]-LIM discloses the processor 20 may perform the NMS on the bounding boxes of the second group left by the NMS result of the first group (wherein performing NMS of the second group includes calculating a similarity score, as in S330, and wherein the bounding boxes of the second group left by the NMS result of the first group are the rectangular frames remaining after the NMS processing).).
Therefore, it would have been obvious to one of ordinary skill in the art before the effective filing date of the claimed invention was made to combine the teachings of YOSHIMURA in view of HAO and further in view of YU of an object detection device, which performs object detection processing to detect an area where a target object is present in images captured by a camera, the object detection device comprising: a memory configured to store a bounding box indicating the area where the target object is present, the bounding box being output to a comparison image of the images; and a processor configured to execute program codes or commands stored in the memory, in order to: acquire a detection target image of the images, the detection target image being captured at a time after the comparison image is captured; provide a plurality of rectangular frames each indicating a candidate for the area where the target object is present in the detection target image; perform calculation processing to calculate a similarity score that is an index indicating a degree of similarity between the bounding box in the comparison image and the rectangular frame in the detection target image with the teachings of LIM of Non-Maximum Suppression (NMS) processing to the plurality of rectangular frames to calculate an overlap ratio by dividing an area of intersection of two of the rectangular frames overlapping each other by an area of union of the two of the rectangular frames, and calculates the similarity score between the bounding box output to the comparison image and the rectangular frames remaining after the NMS processing as the calculation processing.
Wherein having YOSHIMURA’s object detection apparatus having Non-Maximum Suppression (NMS) processing to the plurality of rectangular frames to calculate an overlap ratio by dividing an area of intersection of two of the rectangular frames overlapping each other by an area of union of the two of the rectangular frames, and calculates the similarity score between the bounding box output to the comparison image and the rectangular frames remaining after the NMS processing as the calculation processing.
The motivation behind the modification would have been to obtain an object detection apparatus that enhances the accuracy in detecting objects in images. Since both YOSHIMURA and LIM relate to object detection, wherein YOSHIMURA is to provide a technique for further improving accuracy in tracking a tracking target in an image sequence, while LIM provide an object detection apparatus and an object detection method capable of selecting an object with high accuracy while reducing the amount of computation in the object selection process. Please see YOSHIMURA et al. (US 20230342951 A1), Paragraph [0010], and LIM et al. (US 20240193803 A1), Paragraph [0010].
YOSHIMURA in view of HAO and further in view of YU and further in view of LIM fail to explicitly teach delete one of the two of the rectangular frames having the confidence score lower than the other of the two of the rectangular frames if the overlap ratio exceeds an overlap ratio threshold.
However, OTAKE explicitly teaches delete one of the two of the rectangular frames having the confidence score lower than the other of the two of the rectangular frames (Fig. 3. Paragraph [0028]-OTAKE discloses for each overlap-detected group, the representative area determination unit 204 detects a candidate area corresponding to a detection result with the highest confidence score among detection results included in the overlap-detected group, and determines the detected candidate area as the representative area of the overlap-detected group. Further in paragraph [0030]-OTAKE discloses for each overlap-detected group output by the overlap determination unit 203, the result correction unit 206 deletes detection results other than the detection result corresponding to the representative area determined by the representative area determination unit 204 (wherein the detection results other than the detection result corresponding to the area determined by unit #204 are the frames having the lower confidence score).) if the overlap ratio exceeds an overlap ratio threshold (Fig. 3. Paragraph [0027]-OTAKE discloses the overlap determination unit 203 selects a combination of two arbitrary candidate areas from all detection results obtained by the object detection unit 202 and calculates the overlap ratio between the two candidate areas in the selected combination on a combination-by-combination basis for all combinations. The overlap determination unit 203 determines that there is an overlap if there is a combination of candidate areas for which the calculated overlap ratio is equal to or greater than a threshold value (wherein the threshold value is an overlap ratio threshold).), and
Therefore, it would have been obvious to one of ordinary skill in the art before the effective filing date of the claimed invention was made to combine the teachings of YOSHIMURA in view of HAO and further in view of YU and further in view of LIM of an object detection device, which performs object detection processing to detect an area where a target object is present in images captured by a camera, the object detection device comprising: a memory configured to store a bounding box indicating the area where the target object is present, the bounding box being output to a comparison image of the images; and a processor configured to execute program codes or commands stored in the memory, in order to: acquire a detection target image of the images, the detection target image being captured at a time after the comparison image is captured; provide a plurality of rectangular frames each indicating a candidate for the area where the target object is present in the detection target image; perform calculation processing to calculate a similarity score that is an index indicating a degree of similarity between the bounding box in the comparison image and the rectangular frame in the detection target image with the teachings of OTAKE of delete one of the two of the rectangular frames having the confidence score lower than the other of the two of the rectangular frames if the overlap ratio exceeds an overlap ratio threshold.
Wherein having YOSHIMURA’s object detection apparatus having delete one of the two of the rectangular frames having the confidence score lower than the other of the two of the rectangular frames if the overlap ratio exceeds an overlap ratio threshold.
The motivation behind the modification would have been to obtain an object detection apparatus that enhances the accuracy in detecting objects in images. Since both YOSHIMURA and OTAKE relate to object detection, wherein YOSHIMURA is to provide a technique for further improving accuracy in tracking a tracking target in an image sequence, while OTAKE can provide an improvement in the detection accuracy by using not only the class probability of the object in the representative area but also the class probability of the object in the candidate area overlapping the representative area. Please see YOSHIMURA et al. (US 20230342951 A1), Paragraph [0010], and OTAKE et al. (US 20230126046 A1), Paragraph [0029].
Allowable Subject Matter
Claims 4 and 6, along with their dependent claims, are therefrom objected to as being dependent upon rejected base claim, claim 1, respectively but would be allowable if rewritten in independent form including all of the limitations of the base claims and any intervening claims.
The following is a statement of reasons for the indication of allowable subject matter:
Regarding Claim 4, the prior arts fail to explicitly teach, the processor adjusts importance of the aspect ratio score based on the motion of the vehicle, as claimed in claim 4.
Regarding claim 6, the prior arts fail to explicitly teach, a series of low confidence is a state in which the rectangular frames having the similarity score that satisfies the predetermined condition is the low-confidence rectangular frame, and the one of the rectangular frames to be output as the bounding box to the comparison image used for calculating the similarity score between the rectangular frame having the similarity score that satisfies the predetermined condition and the one of the rectangular frames to be output as the bounding box is the low-confidence rectangular frame, the processor reduces an increase amount of the confidence score in the addition processing depending on the number of consecutive counts, as claimed in claim 6.
Conclusion
Listed below are the prior arts made of record and not relied upon but are considered pertinent to applicant’s disclosure.
SAKATA (US 20240144631 A1) - An object detection device for detecting a predetermined object from an image includes a first detector that detects one or more candidate areas including the predetermined object from the image, a determiner that determines a target area from the one or more candidate areas detected by the first detector, a second detector that detects the predetermined object in the target area with a detection algorithm different from a detection algorithm used by the first detector, and a storage that stores detection information indicating a detection result obtained by the second detector for the target area. The determiner determines the target area from the one or more candidate areas based on the detection information about a frame being at least one frame preceding a current frame…Abstract, Fig. 4.
SUGIO et al. (US 20240071028 A1) - An information processing apparatus includes a detector that detects a movable object in a frame image of a video, a calculator that calculates a confidence of the detected movable object being a predetermined object, and a detection range determiner that determines a detection range for a first movable object detected in a first frame based on a confidence of the first movable object calculated with a range circumscribing the first movable object and on a confidence of the first movable object in the first frame calculated with a detection range for a second movable object detected in a second frame preceding the first frame and records the determined detection range into a recorder…Abstract, Fig. 5A-C.
Applicant's amendment necessitated the new ground(s) of rejection presented in this Office action. Accordingly, THIS ACTION IS MADE FINAL. See MPEP § 706.07(a). 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 ETHAN N WOLFSON whose telephone number is (571)272-1898. The examiner can normally be reached Monday - Friday 8:00 am - 5:00 pm.
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.
/ETHAN N WOLFSON/Examiner, Art Unit 2673
/CHINEYERE WILLS-BURNS/Supervisory Patent Examiner, Art Unit 2673
Prosecution Insights