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 .
Drawings
The drawings were received on 11/27/2024. These drawings are accepted.
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 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 and 8 are rejected under 35 U.S.C. 103 as being unpatentable over Sato et al. (US20070248244, hereinafter “Sato”) and in view of Suja et al (NPL “Fusion Based Object Detection”, hereinafter “Suja”)
Claim 1. (Currently Amended) Sato teaches An object detection device that detects an object from an image included in a moving image, ([0047] “moving object which has been detected five times over a plurality of frames of the inputted image” ) the object detection device comprising: a memory; ([0038] “image storage unit 20 can be implemented via an electronic medium, such as an HDD (Hard Disk Drive) or a RAM (Random Access Memory),”) and at least one processor ( [0036] “ and object processing unit 30”) coupled to the memory, ([0036] “transmits the inputted image data to the image storage unit 20”) the at least one processor being configured to:
acquire the image from the moving image; ([0036] “The image input unit 10 receives an input of image data transmitted thereto from a video camera”)
set a number of surfaces for dividing the image into a plurality of surfaces using a difference between consecutive images; ([0115] “When determining that the average size and average movement of each object … are small, the block shape determination processing unit 100 sets the size of each of the plurality of equal-sized block areas to a small one. In contrast, when determining that the average size and average movement of each object …are large, the block shape determination processing unit 100 sets the size of each of the plurality of equal-sized block areas to a large one” It is understood by the examiner that when Sato et al sets the block areas to large or small, it is essentially setting the number of surfaces to divide the image into. Sato et al does this based on the average size and movement of each object over a plurality of frames which is understood to be the same as the claimed using a difference between consecutive images because taking an average of movements across frames involves using a difference between consecutive images.)
allocate a frequency of detecting the object for each of the divided surfaces; ([0068] “settings are made so that the lower limit of the specific staying time is set to 10 seconds, and therefore only an object which has been staying for "10 seconds or longer" in a rectangular area defined by on-screen two points (Xs, Ys) and (Xe, Ye) at the upper left and lower right corners thereof, as shown by a dotted line of FIG. 8, can be detected.” The staying time of 10 seconds is understood to be the same as the claimed frequency of detecting the object because the detecting only occurs when the object is staying in the frame for 10 seconds or longer which is the frequency)
divide the image into a plurality of surfaces ([0111] “the block shape determination processing unit 100 sets the size of each of the plurality of equal-sized block areas into which the image screen is divided by the object processing unit 30”) depending on the set number of surfaces ([0115] “When determining that the average size and average movement of each object … are small, the block shape determination processing unit 100 sets the size of each of the plurality of equal-sized block areas to a small one…the size of each of the plurality of equal-sized block areas can be adjusted dynamically.” ) and detect an object from the surfaces ([0071] “Block areas which can include the specific segment completely are defined as a target area to be detected…”) in accordance with the allocated frequency; ([0068] “therefore only an object which has been staying for "10 seconds or longer" in a rectangular area … can be detected.”)
Sato does not explicitly teach reduce the image to an entire surface indicating the entire image and detect an object from the entire surface; and combine respective detection results detected from the surfaces and the entire surface to detect an object from the image.
Suja teaches reduce the image to an entire surface indicating the entire image and detect an object from the entire surface; (pg1PDF “object detection…The global method uses chain code based global description, which derives an image representation from the edge image and it captures global information from the input edge image.” Deriving an image representation global information from the input image is understood to be the same as the claimed detect an object from the entire surface.) and combine respective detection results (Abstract “Fusion based object detection method presented herein combines local and global features for object detection.”) detected from the surfaces (pg1PDF “Small image patches are then extracted around the interest points obtained. Essential parts for describing the object are identified”) and the entire surface to detect an object from the image. (pg2PDF “classifier can be improved by fusing the information received from the local and global feature based methods.”)
It would have been obvious to persons of ordinary skill in the art before the effective filing date of the claimed invention to modify Sato to have detect an object at the global and local patch level and combine both detections as taught by Suja to arrive at the claimed invention discussed above. The motivation for the proposed modification would have been because (Suja et al “The algorithm is tested on a set of real-world images … and found to yield very good results with no false alarm within the data base that was used for testing”)
Claim 8. (Currently Amended) The method herein has been executed and performed by the system of claim 1 and is likewise rejected
Claim 2 is rejected under 35 U.S.C. 103 as being unpatentable over Sato et al. (US20070248244, hereinafter “Sato”) and in view of Suja et al (NPL “Fusion Based Object Detection”, hereinafter “Suja”) and in view of Diggins et al (US 20170178295, hereinafter “Diggins”)
Claim 2. (Currently Amended) Sato and Suja teach The object detection device according to claim 1, wherein the at least one processor is further configured to:
Sato teaches estimate a vector indicating movement of an object from the image; ([0048] “the traveling path of the extracted object is drawn by connecting the representative points of the block areas, in which the above-mentioned moving object has been detected, in order.” Fig. 4b)
PNG
media_image1.png
524
350
media_image1.png
Greyscale
and generate a predicted image in which a current position of the object has been predicted using the vector, (Fig. 4b is an image generated which shows the current position of the object predicted using the vector)
Sato and Suja does not explicitly teach wherein, in a case in which a sum of absolute difference values calculated using the predicted image and the acquired image satisfies a predetermined condition, the at least one processor resets the number of surfaces to a number of surfaces corresponding to the predetermined condition.
Diggins teaches wherein, in a case in which a sum of absolute difference values calculated ([0084] “may perform sum-of-absolute difference (SAD) calculations to determine the difference in pixel values between a subset of pixels in the second input frame that encompasses the candidate matching pixel,”) using the predicted image and the acquired image ([0086] “between the regions of the first and second input frame over the pixel range of the calculation”) satisfies a predetermined condition, the at least one processor resets the number of surfaces to a number of surfaces corresponding to the predetermined condition. ([0086] “The pixel selector module 114 may be configured to select as the candidate matching pixel the pixel with the best associated SAD value. The ‘best’ SAD value for the candidate matching pixels may be the lowest value (corresponding to the best overall match between the regions of the first and second input frame over the pixel range of the calculation).” The best SAD value is understood to be the same as the claimed predetermined condition. Diggins et al pixel selector selects pixels with the best associated SAD value which is understood by the examiner to be the same as the claimed resets the number of surfaces corresponding to the predetermined condition. When pixels are selected that increases the number of surfaces)
It would have been obvious to persons of ordinary skill in the art before the effective filing date of the claimed invention to modify the proposed combination of Sato and Suja to have a sum of absolute difference using pixels in the first and second input frames satisfy a SAD value which resets the number of pixels as taught by Diggins to arrive at the claimed invention discussed above. The motivation for the proposed modification would have been because it (Diggins et al [0072] “may reduce the false-positive rate of artefact detection.”)
Allowable Subject Matter
Claims 3-7 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.
Sato et al US20070248244 discloses a moving object detection and setting the amount of blocks to form from an object based on the motion differential between frames but does not render obvious the claimed combination as a whole.
Suja et al NPL “Fusion Based Object Detection” discloses global object detection and local object detection and combines both detections to output a final detection but does not render obvious the claimed combination as a whole.
Diggins et al US20170178295 discloses sum of absolute difference between pixel values from the first and second frames and sets the amount of pixel range to be detected but does not render obvious the claimed combination as a whole.
Honjo et al US20180308242 discloses generating predetermined size blocks for detection of an object and a predetermined time elapsing before training is considered complete for the machine learning model but does not render obvious the claimed combination as a whole.
Hoten et al US20230401898 discloses calculating a difference of average luminance within the frame and determines it is correctly detected when the average luminance is lower than a threshold and if it is incorrect then the rate of detection may be lowered
Conclusion
The prior art made of record and not relied upon is considered pertinent to applicant’s disclosure:
Ogura et al US20220254290 teaches motion detection across frames utilizing luminance comparison between macroblocks of the image
Any inquiry concerning this communication or earlier communications from the examiner should be directed to OWAIS MEMON whose telephone number is (571)272-2168. The examiner can normally be reached M-F (7:00am - 4:00pm) CST.
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.
/OWAIS I MEMON/Examiner, Art Unit 2663
Prosecution Insights