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 .
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)(2) the claimed invention was described in a patent issued under section 151, or in an application for patent published or deemed published under section 122(b), in which the patent or application, as the case may be, names another inventor and was effectively filed before the effective filing date of the claimed invention.
Claims 1-4, 6, 8-12, 14, 16 are rejected under 35 U.S.C. 102(a)(2) as being anticipated by Nouranian et al. (US 2024/0161262).
Regarding claim 1, Nouranian teaches a method for object detection comprising:
downsampling a set of 3D features, wherein the set of 3D features are generated based on an obtained 3D point cloud (see para. 0048, Nouranian discusses downsampling lidar 3D point cloud data);
pooling the downsampled set of 3D features based on Atrous Spatial Pyramid Pooling (ASPP) to generate a pooled set of 3D features (see para. 0053-0054, Nouranian discusses performing a pooling function using Atrous Spatial Pyramid Pooling (ASPP));
upsampling the pooled set of 3D features to generate a upsampled pooled set of 3D features (see para. 0053-0054, Nouranian discusses upsampling the pooled features based on ASPP);
predicting bounding boxes based on the upsampled pooled set of 3D features (see figure 5, para. 0053-0054, Nouranian discusses image segmentation prediction based on upsampled pooled features using ASPP); and
outputting the predicted bounding boxes (see figure 5, para. 0054, Nouranian discusses segmentation label boxes).
Regarding claim 2, Nouranian teaches wherein pooling the downsampled set of 3D features based on ASPP comprises convolving the set of 3D features using a pyramid structure (see para. 0130, Nouranian discusses atrous convolution modules have different dilation rates using a pyramid structure).
Regarding claim 3, Nouranian teaches wherein the pyramid structure convolves the set of 3D features at multiple dilation rates to generate sets of convolved 3D features (see para. 0130, Nouranian discusses atrous convolution modules have different dilation rates using a pyramid structure).
Regarding claim 4, Nouranian teaches wherein pooling the downsampled set of 3D features based on ASPP further comprises: concatenating the sets of convolved 3D features to generate a concatenated set of convolved 3D features; and convolving the concatenated set of convolved 3D features (see para. 0130, Nouranian discusses atrous convolution modules have different dilation rates).
Regarding claim 6, Nouranian teaches wherein the 3D point cloud comprises a lidar point cloud (see para. 0048, Nouranian discusses downsampling lidar 3D point clouds).
Regarding claim 8, Nouranian teaches further comprising applying channel attention and spatial attention to the set of 3D features (see figure 13A, para. 0130, Nouranian discusses applying pyramid scales (channel attention) and spatial convolution).
Claim 9 is rejected as applied to claim 1 as pertaining to a corresponding apparatus with memory and processor.
Claim 10 is rejected as applied to claim 2 as pertaining to a corresponding apparatus with memory and processor.
Claim 11 is rejected as applied to claim 3 as pertaining to a corresponding apparatus with memory and processor.
Claim 12 is rejected as applied to claim 4 as pertaining to a corresponding apparatus with memory and processor.
Claim 14 is rejected as applied to claim 6 as pertaining to a corresponding apparatus with memory and processor.
Claim 16 is rejected as applied to claim 8 as pertaining to a corresponding apparatus with memory and processor.
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.
Claims 5, 13 are rejected under 35 U.S.C. 103 as being unpatentable over Nouranian et al. (US 2024/0161262) in view of Liu et al. (US 2022/0215558).
Regarding claim 5, Nouranian does not expressly disclose wherein downsampling the set of 3D features comprises: determining an average value for a portion of the set of 3D features; and downsampling the set of 3D features based on the average value for the portion of the set of 3D features. However, Liu teaches wherein downsampling the set of 3D features comprises: determining an average value for a portion of the set of 3D features; and downsampling the set of 3D features based on the average value for the portion of the set of 3D features (see para. 0110, Liu discusses an average pooling operation, a kernel size such as 2×2, to downsample a feature map).
Motivation to combine may be gleaned from the prior art considered. It would have been obvious before the effective filing date of the claimed invention to one of ordinary skill in the art to modify the invention of Nouranian with Liu to derive at the invention of claim 5. The result would have been expected, routine, and predictable in order to perform object feature detection.
The determination of obviousness is predicated upon the following: One skilled in the art would have been motivated to modify Nouranian in this manner in order to improve object feature detection by downsampling image data to reduce computational costs by reducing spatial dimension and there reducing parameter numbers. Furthermore, the prior art collectively includes each element claimed (though not all in the same reference), and one of ordinary skill in the art could have combined the elements in this manner explained using known engineering design, interface and/or programming techniques, without changing a fundamental operating principle of Nouranian, while the teaching of Liu continues to perform the same function as originally taught prior to being combined, in order to produce the repeatable and predictable result of receiving image data, downsampling the image data to improve the network by decreasing spatial dimensions that need to be processed. The Nouranian and Liu systems perform object feature detection, therefore one of ordinary skill in the art would have reasonable expectation of success in the combination. It is for at least the aforementioned reasons that the examiner has reached a conclusion of obviousness with respect to the claim in question.
Claim 13 is rejected as applied to claim 5 as pertaining to a corresponding apparatus with memory and processor.
Claims 7, 15 are rejected under 35 U.S.C. 103 as being unpatentable over Nouranian et al. (US 2024/0161262) in view of Jeong et al. (US 2023/0072682).
Regarding claim 7, Nouranian does not expressly disclose wherein the set of 3D features are generated by: discretizing the 3D point cloud into an evenly spaced grid; representing points in a cell of the grid as a pillar; and generating a feature based on the pillar.
However, Jeong teaches wherein the set of 3D features are generated by: discretizing the 3D point cloud into an evenly spaced grid; representing points in a cell of the grid as a pillar; and generating a feature based on the pillar (see figure 4, figure 5, para. 0089, Jeong discusses generating a plurality of grid pillars by dividing three-dimensional point cloud, LiDAR sensor data and generating feature maps).
Motivation to combine may be gleaned from the prior art considered. It would have been obvious before the effective filing date of the claimed invention to one of ordinary skill in the art to modify the invention of Nouranian with Jeong to derive at the invention of claim 7. The result would have been expected, routine, and predictable in order to perform object feature detection.
The determination of obviousness is predicated upon the following: One skilled in the art would have been motivated to modify Nouranian in this manner in order to improve object feature detection of 3D image data from LiDAR using a CNN by performing a well-known pillarization technique that transforms unstructured, sparse 3D point clouds into a structured representation to improve computational speed. Point clouds are sparse, meaning most of the 3D space is empty. A pillar grid divides the space into cells, and only stacks points vertically within those cells, avoiding the need to process thousands of empty voxels, thereby improving performance. Furthermore, the prior art collectively includes each element claimed (though not all in the same reference), and one of ordinary skill in the art could have combined the elements in this manner explained using known engineering design, interface and/or programming techniques, without changing a fundamental operating principle of Nouranian, while the teaching of Jeong continues to perform the same function as originally taught prior to being combined, in order to produce the repeatable and predictable result of performing the pillarization technique that transforms unstructured, sparse 3D point clouds into a structured data that improves a Convolutional Neural Network. The Nouranian and Jeong systems perform object feature detection, therefore one of ordinary skill in the art would have reasonable expectation of success in the combination. It is for at least the aforementioned reasons that the examiner has reached a conclusion of obviousness with respect to the claim in question.
Claim 15 is rejected as applied to claim 7 as pertaining to a corresponding apparatus with memory and processor.
Conclusion
The prior art made of record and not relied upon is considered pertinent to applicant's disclosure.
Zou et al. (US 2022/0058429)
Oblak et al. (US 2022/0180131)
Kushnarev et al. (US 2025/0029240)
Zhou et al. “AFPNet: A 3D fully convolutional neural network with atrous-convolution feature pyramid for brain tumor segmentation via MRI images.”
Contact Information
Any inquiry concerning this communication or earlier communications from the examiner should be directed to KENNY A CESE whose telephone number is (571) 270-1896. The examiner can normally be reached on Monday – Friday, 9am – 4pm.
If attempts to reach the primary examiner by telephone are unsuccessful, the examiner’s supervisor, Gregory Morse can be reached on (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 an application may be obtained from the Patent Application Information Retrieval (PAIR) system. Status information for published applications may be obtained from either Private PAIR or Public PAIR. Status information for unpublished applications is available through Private PAIR only. For more information about the PAIR system, see http://pair-direct.uspto.gov. Should you have questions on access to the Private PAIR system, contact the Electronic Business Center (EBC) at 866-217-9197 (toll-free). If you would like assistance from a USPTO Customer Service Representative or access to the automated information system, call 800-786-9199 (IN USA OR CANADA) or 571-272-1000.
/Kenny A Cese/
Primary Examiner, Art Unit 2663