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 .
Claim Objections
It appears that claims 5 and 6 are duplicate claims; which appear identical to each other. Applicant should amend or cancel at least one of the claims.
Appropriate amendment or cancellation is required.
Claim Interpretation
During patent examination, pending claims must be “given their broadest reasonable interpretation consistent with the specification.” MPEP 2111; See also, MPEP 2173.02. Limitations appearing in the specification but not recited in the claim are not read into the claim. In re Prater, 415 F.2d 1393, 1404-05, 162 USPQ 541, 550-551 (CCPA 1969). See also, In re Zletz, 893 F.2d 319, 321-22, 13 USPQ2d 1320, 1322 (Fed. Cir. 1989) (“During patent examination the pending claims must be interpreted as broadly as their terms reasonably allow”). The reason is simply that during patent prosecution when claims can be amended, ambiguities should be recognized, scope and breadth of language explored, and clarification imposed. An essential purpose of patent examination is to fashion claims that are precise, clear, correct, and unambiguous. Only in this way can uncertainties of claim scope be removed, as much as possible, during the administrative process.
The Examiner respectfully requests of the Applicant in preparing responses, to consider fully the entirety of the reference(s) as potentially teaching all or part of the claimed invention. It is noted, REFERENCES ARE RELEVANT AS PRIOR ART FOR ALL THEY CONTAIN.
Claim Rejections - 35 USC § 102
The following is a quotation of the appropriate paragraphs of 35 U.S.C. 102 that form the basis for the rejections under this section made in this Office action:
A person shall be entitled to a patent unless –
(a)(1) the claimed invention was patented, described in a printed publication, or in public use, on sale, or otherwise available to the public before the effective filing date of the claimed invention.
Claim(s) 1-11 are rejected under 35 U.S.C. 102(a)(1) as being anticipated by “Labels Are Not Perfect: Inferring Spatial Uncertainty in Object Detection”, by Di Feng, et al. published, December 18, 2020, (hereinafter Feng).
With regard to claim 1, Feng discloses:
1. A computer-implemented method for training a birds-eye-view (BEV) object detection model (see, abstract: “we incorporate the proposed label of uncertainty in a loss function to train a probabilistic object detector to improve its detection accuracy”; the method works on birds-eye-view (BEV) images, see, Figs. 1, 5, and 7) the method comprising:
inputting a training sample into the model, wherein:
the training sample includes a BEV image including a plurality of pixels, and a plurality of target confidence values, and
each pixel of the plurality of pixels is associated with a target confidence value of the plurality of target confidence values (see, p.3, left col., 2nd par.: “applies the label uncertainty in training and evaluating object detection networks”, bridging par. On p.4-5: “spatial uncertainty distribution […] LiDAR Bird’s Eye View (BEV) space; bridging par. On p.12-13 “Training a Probabilistic Object Detector”; p.13 left col., first par. “input sample”).
receiving as output from the model a plurality of predicted confidence values, wherein each predicted confidence value is associated with a pixel of the plurality of pixels (see, p.13, left col., first par. “Given an input sample of LiDAR point cloud […] predicted by the network output layers”); and
adjusting a parameter set of the model according to a loss, wherein the loss is based on the plurality of predicted confidence values and the plurality of target confidence values (see, bridging par. On p.12-13 “Kullback-Leibler Divergence (KLD) loss, p. 13, last sentence before eq. 20 “To train ProbPIXOR, we minimize the KLD between p and q […]”; adjusting the parameters is inherent to the training).
With regard to claim 2, Feng discloses:
2. The method of claim 1 wherein:
a target confidence value of the plurality of target confidence values indicates an uncertainty value corresponding to the pixel of the plurality of pixels associated with the target confidence value (see, as above, (see, p.3, left col., 2nd par.: “applies the label uncertainty in training and evaluating object detection networks”, bridging par. On p.4-5: “spatial uncertainty distribution […] LiDAR Bird’s Eye View (BEV) space; bridging par. On p.12-13 “Training a Probabilistic Object Detector”; p.13 left col., first par. “input sample”); and
the plurality of target confidence values indicates a distribution of uncertainty values associated with the plurality of pixels (see, a “spatial uncertainty distribution”, in for example, bridging par. On p. 4-5 and p.6, right col. first paragraph).
With regard to claim 3, Feng discloses:
3. The method of claim 2 wherein a shape of the distribution of uncertainty values depends on at least one of a distance, position, rotation, size, or class of an object within the BEV image (see, Figure 5, illustrates the influence of noise and distance on the spatial uncertainty distribution. See, Fig. 7, the influence of rotation is visible in fig. 7}.
With regard to claim 4, Feng discloses:
4. The method of claim 1 wherein adjusting the parameter set of the model includes:
determining a subset of the plurality of predicted confidence values,
wherein the loss is based on the subset of the plurality of predicted confidence values and a corresponding subset of the plurality of target confidence values (see, Fig. 1, illustrating all obtained data. p.6, right col., first par. “transform this label uncertainty distribution into a spatial uncertainty distribution of BBoxes”). Selecting the BBox based on label information, sensor information or object detection score would be a first design choice for the skilled person).
With regard to claim 5, Feng discloses:
5. The method of claim 4 wherein determining the subset of the plurality of predicted confidence values includes selecting the subset of the plurality of predicted confidence values based on label information associated with a subset of the plurality of pixels corresponding to the subset of the plurality of predicted confidence values (see, Fig. 1, illustrating all obtained data. p.6, right col., first par. “transform this label uncertainty distribution into a spatial uncertainty distribution of BBoxes”). Selecting the BBox based on label information, sensor information or object detection score would be a first design choice for the skilled person).
With regard to claim 6, Feng discloses:
6. The method of claim 4 wherein determining the subset of the plurality of predicted confidence values includes selecting the subset of the plurality of predicted confidence values based on sensor information associated with a subset of the plurality of pixels corresponding to the subset of the plurality of predicted confidence values (see, Fig. 1, illustrating all obtained data. p.6, right col., first par. “transform this label uncertainty distribution into a spatial uncertainty distribution of BBoxes”). Selecting the BBox based on label information, sensor information or object detection score would be a first design choice for the skilled person).
With regard to claim 7, Feng discloses:
7. The method of claim 4 wherein determining the subset of the plurality of predicted confidence values includes:
selecting the subset of the plurality of predicted confidence values based on a plurality of object detection scores,
wherein each object detection score of the plurality of object detection scores is associated with a pixel of a subset of the plurality of pixels corresponding to the subset of the plurality of predicted confidence values (see, Fig. 1, illustrating all obtained data. p.6, right col., first par. “transform this label uncertainty distribution into a spatial uncertainty distribution of BBoxes”). Selecting the BBox based on label information, sensor information or object detection score would be a first design choice for the skilled person).
With regard to claim 8, Feng discloses:
8. The method of claim 1 wherein:
the training sample includes a plurality of target value sets;
each pixel of the plurality of pixels is associated with a target value set of the plurality of target value sets;
the output of the model includes a plurality of predicted value sets; and
adjusting the parameter set of the model is based on a loss between the plurality of predicted value sets and the plurality of target value sets (see, Fig. 1, illustrating all obtained data. p.6, right col., first par. “transform this label uncertainty distribution into a spatial uncertainty distribution of BBoxes”). Selecting the BBox based on label information, sensor information or object detection score would be a first design choice for the skilled person).
With regard to claim 9, Feng discloses:
9. The method of claim 1 wherein at least one of:
each pixel of the plurality of pixels is associated with an angle value and a distance value within the BEV image; or
each pixel of the plurality of pixels is associated with first cartesian coordinate and a second cartesian coordinate (see, Fig. 1, illustrating all obtained data. p.6, right col., first par. “transform this label uncertainty distribution into a spatial uncertainty distribution of BBoxes”). Selecting the BBox based on label information, sensor information or object detection score would be a first design choice for the skilled person).
With regard to claim 10, Feng discloses:
10. A computer-implemented method for BEV object detection, the method comprising:
the method of claim 1 (see, as above claim 1);
obtaining a new BEV image including a plurality of pixels;
inputting the new BEV image into the model;
receiving, from the model, an output including at least a plurality of predicted confidence values; and
detecting an object within the new BEV image using the output of the model (see, p.13-14, Section B, Fig. 13, Experimental results, we observe consistent recall improvements in both networks when modeling uncertainties, indicating better detection performance. Both networks show the largest recall gain at 0-8 threshold, because the majority of detections lie at IoU values around 0.6-0.8).
With regard to claim 11, Feng discloses:
11. The method of claim 10 wherein:
the output of the model includes a plurality of predicted value sets; and
detecting the object within the BEV image includes applying the plurality of predicted confidence values on the plurality of predicted value sets (see, p. 13-14, Section B, Experimental Results when using the trained network (“on detecting ‘Car’ objects”).
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.
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.
This application currently names joint inventors. In considering patentability of the claims the examiner presumes that the subject matter of the various claims was commonly owned as of the effective filing date of the claimed invention(s) absent any evidence to the contrary. Applicant is advised of the obligation under 37 CFR 1.56 to point out the inventor and effective filing dates of each claim that was not commonly owned as of the effective filing date of the later invention in order for the examiner to consider the applicability of 35 U.S.C. 102(b)(2)(C) for any potential 35 U.S.C. 102(a)(2) prior art against the later invention.
Claim(s) 12-16 are rejected under 35 U.S.C. 103 as being unpatentable over Feng in view of U.S. Patent Application No. 2021/0150720 A1 to Kumar et al. (hereinafter Kumar).
With regard to claim 12, Feng discloses:
12. An apparatus comprising:
[memory storing instructions]; and
[at least one processor configured to execute the instructions], wherein the instructions include:
inputting a training sample into a birds-eye-view (BEV) object detection model, wherein:
the training sample includes a BEV image including a plurality of pixels, and a plurality of target confidence values, and
each pixel of the plurality of pixels is associated with a target confidence value of the plurality of target confidence values (see, p.3, left col., 2nd par.: “applies the label uncertainty in training and evaluating object detection networks”, bridging par. On p.4-5: “spatial uncertainty distribution […] LiDAR Bird’s Eye View (BEV) space; bridging par. On p.12-13 “Training a Probabilistic Object Detector”; p.13 left col., first par. “input sample”),
receiving as output from the model] at least a plurality of predicted confidence values, wherein each predicted confidence value is associated with a pixel of the plurality of pixels (see, p.13, left col., first par. “Given an input sample of LiDAR point cloud […] predicted by the network output layers”), and
adjusting a parameter set of the model according to a loss, wherein the loss is based at least on the plurality of predicted confidence values and the plurality of target confidence values (see, bridging par. On p.12-13 “Kullback-Leibler Divergence (KLD) loss, p. 13, last sentence before eq. 20 “To train ProbPIXOR, we minimize the KLD between p and q […]”; adjusting the parameters is inherent to the training).
(see as above, claim 1, directed to a method claim, and since the invention lies in further processing data for the machine-learning model training sample into a birds-eye-view (BEV). Such a method cannot be carried out by generic data processing means, and is focused to include inputting a training sample).
Kumar discloses:
memory storing instructions (see, detailed description, including, Raw and/or processed sensor data may be stored in a sensor data memory 344 storage medium, para. 0042); and
at least one processor configured to execute the instructions, (see, detailed description, including, processor configured to interpret the returned electromagnetic waves and determine locational properties of targets. Examples of the RADAR sensors 324 as described herein may include, but are not limited to, at least one of Infineon RASIC™ RTN7735PL transmitter and RRN7745PL/46PL, para. 0036).
It would have been obvious to one having ordinary skill at the time the invention was filed, and having the teachings of Feng with Kumar before her, to be motivated to combine the features from Kumar, with Feng, including, memory storing instructions (see, detailed description, including, Raw and/or processed sensor data may be stored in a sensor data memory 344 storage medium, para. 0042); and
at least one processor configured to execute the instructions, (see, detailed description, including, processor configured to interpret the returned electromagnetic waves and determine locational properties of targets. Examples of the RADAR sensors 324 as described herein may include, but are not limited to, at least one of Infineon RASIC™ RTN7735PL transmitter and RRN7745PL/46PL, para. 0036).
Therefore, a rationale to support a conclusion that a claim would have been obvious is that all the claimed elements were known in the prior art and one skilled in the art could have combined the elements as claimed by known methods with no change in their respective functions, and the combination would have yielded nothing more than predictable results to one of ordinary skill in the art1.
With regard to claim 13, claim 13 (an apparatus claim) recites substantially similar limitations to claim 10 (a method claim) and is therefore rejected using the same art and rationale set forth above.
With regard to claim 14, claim 14 (an apparatus claim) recites substantially similar limitations to claims 11 and 13 (both a method claim) with a vehicle, see, claim 11, and “car”, is therefore rejected using the same art and rationale set forth above.
15. A vehicle comprising the apparatus of claim 12.
With regard to claim 15, claim 15 (an apparatus claim) recites substantially similar limitations to claims 11 and 13 (both a method claim) with a vehicle, see, claim 11, and “car”, is therefore rejected using the same art and rationale set forth above.
With regard to claim 16, claim 16 (a non-transitory computer-readable medium claim) recites substantially similar limitations to claims 1 and 11 (both a method claim) with a vehicle, see, claim 11, and “car”, is therefore rejected using the same art and rationale set forth above.
A sampling of the prior art made of record and not relied upon and considered
pertinent to Applicants’ disclosure includes: U.S. Patent Application Publication No. 2023/0410530A1 to Taghavi et al. that discusses: Devices, systems, methods, and media are disclosed for performing an object detection task comprising: obtaining a semantic segmentation map representing a real-world space, the semantic segmentation map including an array of elements that each represent a respective location in the real-world space and are assigned a respective element classification label; clustering groups of the elements based on the assigned respective element classification labels to identify at least a first cluster of elements that have each been assigned the same respective element classification label; generating, based on a location of the first cluster within the semantic segmentation map, at least one anchor that defines a respective probable object location of a first dynamic object; and generating, based on the semantic segmentation map and the at least one anchor, a respective bounding box and object instance classification label for the first dynamic object.
Conclusion
Any inquiry concerning this communication or earlier communications from the examiner should be directed to WILLIAM D. TITCOMB whose telephone number is (571)270-5190. The examiner can normally be reached 9:30 AM - 6:30 PM (M-F).
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, Stephen C. Hong can be reached at 571-272-4124. 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.
WILLIAM D. TITCOMB
Primary Examiner
Art Unit 2178
/WILLIAM D TITCOMB/Primary Examiner, Art Unit 2178 12-23-2025
1 1 KSR International Co. v. Teleflex Inc., 127 S.Ct. 1727, 82 U.S.P.Q.2d 1385 (2007).