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 .
All amendments to the claims as filed on 4/27/2026 have been entered and action follows:
Response to Arguments
Applicant’s arguments with respect to claim(s) have been considered but are moot because the new ground of rejection does not rely on any reference applied in the prior rejection of record for any teaching or matter specifically challenged in the argument.
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, 5, 7, 11-13, 15 and 17 are rejected under 35 U.S.C. 103 as being unpatentable over Adaptive object detection using adjacency and zoom prediction, by Lu et al. in view of Tseng (US 8,810,599).
With respect to claim 1, Lu discloses A method of inferencing performed by a computer vision system, comprising: receiving an input image, (see section 3.1, wherein … starting from the entire image…);
mapping a plurality of grid cells to the input image so that each grid cell of the plurality of grid cells includes a respective portion of the input image, (see figure 1 right hand side under Our AZ-Net, the entire image has square i.e. mapping plurality of grids);
performing an inferencing operation on the portion of the input image included in a first grid cell of the plurality of grid cells, using an object detection model, (see section 3.1, wherein, our object detection algorithm “object detection model” …For any region “a first grid” encountered in the search procedure, the algorithm extracts features from this region to compute the zoom indicator and the adjacency predictions…; also page 3, right hand column, figure 4, … while the neighboring squares are used to detect objects that fall in the gaps between anchor regions generated in the search process);
detecting an object of interest [at an edge] of the first grid cell that partially overlaps a second grid cell of the plurality of grid cells based on a result of the inferencing operation performed on the first grid cell, (see page 4, left hand column, wherein …The role of adjacency prediction is to detect one or multiple objects that overlap with the anchor region sufficiently by providing tight bounding boxes…); and
performing the inferencing operation on a second grid cell of the plurality of grid cells using the object detection model in response to detecting the object of interest, (see section 3.1, wherein … Our object detection algorithm consists of two steps. In step 1, a set of class-independent region proposals are generated using Adaptive Search with AZ-Net [independent region proposals are read as “plurality of grid cells”] (see Algorithm 1). In step 2, an object detector evaluates each region [this is read as determining the objects in plurality of grid cells] proposed in step 1 to provide class-wise detections …the current region “a first grid” is divided into sub-regions in the manner shown in Figure 2. These sub-regions [are read as “a second grid” or third or fourth grids…] is then recursively processed in the same manner as its parent region…), as claimed.
Lu fails to explicitly disclose detecting an object of interest at an edge of the first grid cell that partially overlaps a second grid cell of the plurality of grid cells, (emphasis added), as claimed.
Tseng teaches detecting an object of interest at an edge of the first grid cell that partially overlaps a second grid cell of the plurality of grid cells, (emphasis added, see col. 5, lines 31-44, wherein …For example, the algorithm may analyze each pixel within the image 112 to determine if a characteristic point is present by detecting the similarities between a patch of pixels centered on the pixel being analyzed and nearby, partially overlapping patches of pixels [patches of pixels are read as the “grids”]. If the pixel is in a region of uniform intensity, then the nearby patches will be similar. If the pixel is on an edge [edge is read as the edge of the patch], then nearby patches in a direction perpendicular [the patches in a direction perpendicular is read as multiple grids] to the edge will appear quite different, whereas nearby patches in a direction parallel to the edge will appear similar. The pixel can be identified as a corner characteristic point if the analysis detects pixel variation in all directions), as claimed.
It would have been obvious to one ordinary skilled in the art at the effective date of invention to combine the two references as they are analogous because they are solving similar problem of object detection using image analysis. Teaching of Tseng to detect a pixel “object” on an edge of the overlapping patches can be incorporated into the Lu system as suggested in figure 4 of Lu detect objects that fall in the gaps, for suggestion, and modifying the system yields identifying data in an image, see Abstract of Tseng, for motivation.
With respect to claim 2, Lu and Tseng further discloses assigning a respective priority value to each of the plurality of grid cells, the inferencing operation being performed on the portion of the input image included in the first grid cell based on the priority value assigned to the first grid cell; and updating the priority value assigned to the first grid cell based on the result of the inferencing operation performed on the portion of the input image included in the first grid cell, (see figure 1, right hand side under Our AZ-Net, where the 3 grid is further divided and section 3.1, wherein … The adjacency predictions with confidence scores above a threshold are included in the set of output region proposals. If the zoom indicator is above a threshold, this indicates that the current region is likely to contain small objects…), as claimed.
With respect to claim 3, Lu and Tseng further discloses wherein the result of the inferencing operation indicates a confidence level associated with detecting the object of interest, (see section 3.1, wherein …If the zoom indicator is above a threshold [threshold is read as confidence level], this indicates that the current region is likely to contain small objects…), as claimed.
With respect to claim 5, Lu and Tseng further discloses updating the priority value assigned to the second grid cell based on the result of the inferencing operation performed on the portion of the input image included in the first grid cell, (section 3.1, wherein … If the zoom indicator is above a threshold, this indicates that the current region is likely to contain small objects. To detect these embedded small objects, the current region is divided into sub-regions in the manner shown in Figure 2. Each of these sub-regions is then recursively processed in the same manner as its parent region, until either its area or its zoom indicator is too small. Figure 1 illustrates this procedure…“updating the priority value assigned to the second grid cell based on the result of the inferencing operation”), as claimed.
With respect to claim 7, Lu and Tseng further discloses wherein the inferencing operation is performed on the portion of the input image included in the second grid cell based on the updated priority value assigned to the second grid cell, (see section 3.1, wherein … We consider a recursive search strategy, starting from the entire image as the root region. For any region encountered in the search procedure, the algorithm extracts features from this region to compute the zoom indicator and the adjacency predictions. The adjacency predictions with confidence scores above a threshold are included in the set of output region proposals. If the zoom indicator is above a threshold, this indicates that the current region is likely to contain small objects… Each of these sub-regions is then recursively processed in the same manner as its parent region, until either its area or its zoom indicator is too small. Figure 1 illustrates this procedure…), as claimed.
With respect to claim 11, Lu and Tseng further discloses refraining from performing the inferencing operation on the portion of the input image included in a third grid cell of the plurality of grid cells based on the priority value assigned to the third grid cell; and incrementing the priority value assigned to the third grid cell, (see figure 2, right side Our AZ-Net where only the third grid is further divided i.e. the other grids 1, 2 and 4 are “refrained[ing] from performing the inferencing operation”), as claimed.
Claims 12, 13, 15 and 17 are rejected for the same reasons as set forth in the rejections of claims 1, 2, 5 and 7, because claims 12, 13, 15 and 17 are claiming subject matter of similar scope as claimed in claims 1, 2, 5, and 7 respectively.
Claims 8-10 and 18-20 are rejected under 35 U.S.C. 103 as being unpatentable over Adaptive object detection using adjacency and zoom prediction, by Lu et al. in view of Tseng (US 8,810,599) as applied to claim 1 above, and further in view of Faster R-CNN: Towards Real-Time Object Detection with Region Proposal Networks, by Ren et al.
With respect to claim 8, Lu and Tseng discloses all the limitation as claimed and as rejected in claim 1 above. However, Lu and Tseng fail to explicitly disclose comparing the result of the inferencing operation performed on the portion of the input image included in the first grid cell with a result of the inferencing operation performed on the portion of the input image included in the second grid cell; and outputting one of the results based at least in part on the comparison, as claimed.
Ren teaches comparing the result of the inferencing operation performed on the portion of the input image included in the first grid cell with a result of the inferencing operation performed on the portion of the input image included in the second grid cell; and outputting one of the results based at least in part on the comparison, (see page 7, left hand column, wherein … RPN proposals highly overlap with each other. To reduce redundancy, we adopt non-maximum suppression (NMS) on the proposal regions based on their cls scores [this is read as comparing the proposals i.e. grids; and redundancy is read as outputting one of the results] …), as claimed.
It would have been obvious to one ordinary skilled in the art at the effective date of invention to combine the two references as they are analogous because they are solving similar problem of object detection using image analysis. Teaching of Ren to use the similarity of proposals i.e. the comparison of grids can be incorporated in to Lu and Tseng’s system as suggested (see page 3 of Lu, left hand side column, wherein … Our work is most related to the recent work by Ren et al. [22], which uses a set of heuristically designed 2400 overlapping anchor regions…), for suggestion, and modifying the system yields a more accurate object detection system, for motivation.
With respect to claim 9, combination of Lu, Tseng and Ren further discloses wherein the outputting of one of the results comprises: detecting one or more redundancies based on comparing the result of the inferencing operation performed on the portion of the input image included in the first grid cell with the result of the inferencing operation performed on the portion of the input image included in the second grid cell, the one or more redundancies representing inferences associated with the result of the inferencing operation performed on the portion of the input image included in the first grid cell; and filtering the one or more redundancies from the output, (see page 7 left hand side column, wherein … RPN proposals highly overlap with each other. To reduce redundancy, we adopt non-maximum suppression (NMS) on the proposal regions based on their cls scores. We fix the IoU threshold for NMS at 0.7, which leaves us about 2000 proposal regions per image. As we will show, NMS does not harm the ultimate detection accuracy, but substantially reduces the number of proposals…), as claimed.
With respect to claim 10, combination of Lu, Tseng and Ren further discloses wherein the outputting of one of the results comprises: identifying one or more duplicate detections based on comparing the result of the inferencing operation performed on the portion of the input image included in the first grid cell with the result of the inferencing operation performed on the portion of the input image included in the second grid cell, the one or more duplicate detections representing inferences associated with the result of the inferencing operation performed on the portion of the input image included in the first grid cell that overlap inferences associated with the result of the inferencing operation performed on the portion of the input image included in the second grid cell; and filtering the one or more duplicate detections from the output, (see page 7 left hand side column, wherein … RPN proposals highly overlap with each other. To reduce redundancy, we adopt non-maximum suppression (NMS) on the proposal regions based on their cls scores. We fix the IoU threshold for NMS at 0.7, which leaves us about 2000 proposal regions per image. As we will show, NMS does not harm the ultimate detection accuracy, but substantially reduces the number of proposals…), as claimed.
Claims 18-20 are rejected for the same reasons as set forth in the rejections of claim 8-10, because claims 18-20 are claiming subject matter of similar scope as claimed in claims 8-10.
Allowable Subject Matter
Claims 4 and 14 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.
Conclusion
THIS ACTION IS MADE FINAL. Applicant is reminded of the extension of time policy as set forth in 37 CFR 1.136(a).
A shortened statutory period for reply to this final action is set to expire THREE MONTHS from the mailing date of this action. In the event a first reply is filed within TWO MONTHS of the mailing date of this final action and the advisory action is not mailed until after the end of the THREE-MONTH shortened statutory period, then the shortened statutory period will expire on the date the advisory action is mailed, and any nonprovisional extension fee (37 CFR 1.17(a)) pursuant to 37 CFR 1.136(a) will be calculated from the mailing date of the advisory action. In no event, however, will the statutory period for reply expire later than SIX MONTHS from the mailing date of this final action.
Any inquiry concerning this communication or earlier communications from the examiner should be directed to VIKKRAM BALI whose telephone number is (571)272-7415. The examiner can normally be reached Monday-Friday 7:00AM-3:00PM.
Examiner interviews are available via telephone, in-person, and video conferencing using a USPTO supplied web-based collaboration tool. To schedule an interview, applicant is encouraged to use the USPTO Automated Interview Request (AIR) at http://www.uspto.gov/interviewpractice.
If attempts to reach the examiner by telephone are unsuccessful, the examiner’s supervisor, Gregory Morse can be reached at 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.
/VIKKRAM BALI/ Primary Examiner, Art Unit 2663
Prosecution Insights