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 .
Response to Arguments
Applicant’s arguments have been considered. See Davydov (“Supervised Object-Specific Distance Estimation from Monocular Images for Autonomous Driving”) which teaches the amendments.
Regarding claim 3 and 11-12, new 103 rejection are written below.
Claim Rejections - 35 USC § 103
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.
Claim(s) 1-2, 4-7 and 9-10 are rejected under 35 U.S.C. 103 as being unpatentable over Vajgl (“Dist-YOLO: Fast Object Detection with Distance Estimation”) in view of Davydov (“Supervised Object-Specific Distance Estimation from Monocular Images for Autonomous Driving”).
Regarding claim 1 Vajgl teaches a detection circuit, comprising: a neural network module, configured to receive an image to generate an output tensor (section 2.1),
wherein the output tensor comprises position information of a specific object and distance adjustment information (section 2.2); and
Davydov teaches wherein the distance adjustment information is a dimensionless scaling factor (equation 3, dimensionless scaling factors applied to bounding box dimensions (1 + x2) and (1+x3).
a calculation circuit, coupled to the neural network module, configured to calculate an initial distance between an image capture device and the specific object according to the position information of the specific object and generate an estimated distance according to the initial distance and the distance adjustment information (see section 2.2, paragraph starting with “Decoding block: This….” And “x2 and x3 serve as correction terms to the bounding box dimensions”. Also see equation 3 which teaches dimensionless scaling factor).
It would have been obvious prior to the effective filing date of the invention to one of ordinary skill in the art to include in Vajgl the decoding method as taught by Davydov. The reason is to allow the system to train more efficiently and uses a specific structure.
Regarding claim 2, Vajgl teaches the specific object is a person, the output tensor comprises the position information of the person and the distance adjustment information (section 3, shows a person and section 2.2 teaches updating the prediction vector); and
the calculation circuit calculates the initial distance between the image capture device and the specific object according to the position information, default width and default height of the person (see table 1 in section 3.1 of Franke).
Regarding claim 4, Vajgl teaches all the features of claim 4 except different poses in section 3 and 2.2. Franke teaches different poses in section 4.1 (various rotations)
Regarding claim 5, Vaigl teaches wherein the training parameter comprises another distance adjustment information calculated according to a real distance between the image capture device and the person and real position information of the person, wherein the another distance adjustment information serves as a training target in the training phase of the neural network module (section 2.2-2.3 and section 3, updating vector by minimizing a loss function. This uses ground truths which are the real position information).
Regarding claims 6-7 and 9-10, see the rejection of claims 1-2 and 4-5.
Claim(s) 3 and 8 are rejected under 35 U.S.C. 103 as being unpatentable over Vajgl (“Dist-YOLO: Fast Object Detection with Distance Estimation”) in view of Davydov (“Supervised Object-Specific Distance Estimation from Monocular Images for Autonomous Driving”) in further view of Bertoni (“MonoLoco: Monocular 3D Pedestrian Localization and Uncertainty Estimation”).
Regarding claim 3, Bertoni teaches wherein the calculation circuit multiplies the distance adjustment information by the initial distance to generate the estimated distance (see section 3 which states: From the triangle similarity relation of human heights and distances, dh-mean/hmean = dgt/hgt, where hgt and dgt are the the ground-truth human height and distance, hmean is the assumed mean height of a person and dh-mean the estimated distance under the hmean assumption).
It would have been obvious prior to the effective filing date of the invention to one of ordinary skill in the art to include in Vajgl and Davydov the ability to have multiplication scaling as taught by Bertoni. The reason is to allow the system to use ground truths.
Regarding claim 8, see the rejection of claim 3.
Claim(s) 11 and 12 are rejected under 35 U.S.C. 103 as being unpatentable over Vajgl (“Dist-YOLO: Fast Object Detection with Distance Estimation”) in view of Davydov (“Supervised Object-Specific Distance Estimation from Monocular Images for Autonomous Driving”) in further view of Zhu (“Learning Object-Specific Distance From a Monocular Image”).
Regarding claim 11, Zhu teaches the another distance adjustment information is a ratio of the real distance to an initial training distance calculated according to the real position information (see section 5, evaluation metrics, “threshold: % of di s.t.max(di/d∗ i,d∗ i/di)=δ<threshold” and also see section 5, compared approaches, which teaches “ we compute the width and height ….”).
It would have been obvious prior to the effective filing date of the invention to one of ordinary skill in the art to include in Vajgl and Davydov the ability to have specific ratios as taught by Zhu. The reason is to allow the system to use initial estimate should be scaled to match reality.
Regarding claim 12, see section 5, evaluation metrics of Zhu teaches ground truth distance and predicted distance and threshold % as explained in rejection of claim 11.
Conclusion
Any inquiry concerning this communication or earlier communications from the examiner should be directed to HADI AKHAVANNIK whose telephone number is (571)272-8622. The examiner can normally be reached 9 AM - 5 PM Monday to Friday.
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, Henok Shiferaw can be reached at (571) 272-4637. 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.
/HADI AKHAVANNIK/Primary Examiner, Art Unit 2676