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 .
Continued Examination Under 37 CFR 1.114
A request for continued examination under 37 CFR 1.114, including the fee set forth in 37 CFR 1.17(e), was filed in this application after final rejection. Since this application is eligible for continued examination under 37 CFR 1.114, and the fee set forth in 37 CFR 1.17(e) has been timely paid, the finality of the previous Office action has been withdrawn pursuant to 37 CFR 1.114. Applicant's submission filed on 6/2/26 has been entered.
Priority
The applicant’s claim to priority of PRO 63/689,539 on 8/30/24 is acknowledged.
Information Disclosure Statement
The applicant filed an IDS on 6/2/26. It has been annotated and considered.
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.
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) 21-24, 27-28, 31-34 and 36-41 are rejected under 35 U.S.C. 103 as being unpatentable over Hever et al. (US 20210090242 hereinafter Hever) in view of Hever et al. (US 20240404041 hereinafter ‘041) and further in view of Gilbert et al. (US 20200402219 hereinafter Gilbert).
Regarding claim 21 (and similarly 32 and 37), Hever teaches a method for analyzing condition of a vehicle from images of the vehicle collected by a vehicle inspection system (See at least: Fig. 1A), the vehicle inspection system comprising a plurality of sensor arrays comprising first, second and third sensor arrays comprising respective first, second, and third sets of cameras (See at least: Fig. 2A), the method comprising:
using at least one computer hardware processor to perform (See at least: Fig. 1B):
obtaining a plurality of images using the vehicle inspection system, the plurality of images including first, second, and third sets of images captured, respectively, by the first, second, and third sets of cameras (See at least: Fig. 2A, top, middle and bottom cameras respectively);
identifying a subset of the plurality of images for subsequent processing to identify whether the vehicle has one or more defects, wherein the identifying is performed based on a pose of the vehicle in images of the plurality of images (See at least: [0129] The 3D mesh and/or the 3D model with virtual views can be used for identifying anomalies on the vehicle, including any anomaly which can be indicative of potential damages and deterioration, such as, e.g., cracking, scrapes, bulges, cuts, snags, punctures, foreign objects, or other damage resulting from daily use, etc. Due to removal of light reflection in the 3D mesh and/or 3D model, anomalies which could not be discovered before, can now be revealed. In addition, exact positions of the anomalies on the vehicle can be located. Repeated anomalies, such as, e.g., same scratches detected from different images, can be identified and eliminated, thereby rendering better detection results.”);
but fails to teach processing the subset of the plurality of images, using at least one trained machine learning (ML) model, to determine whether the vehicle has the one or more defects; and
generating a vehicle condition report based on results of the processing, the vehicle condition report including an indication of the one or more defects in the plurality of images.
However, ‘041 teaches processing the subset of the plurality of images, using at least one trained machine learning (ML) model, to determine whether the vehicle has the one or more defects (See at least: [0046] via “The remote server can host powerful one or more processors that run code and optionally machine learning models to analyze the imaging data and detect defects on the vehicle's exterior.”); and
generating a vehicle condition report based on results of the processing, the vehicle condition report including an indication of the one or more defects in the plurality of images (See at least: Fig. 2; [0035] via “The onboard processors can immediately process the captured imaging data, identifying defects and generating comprehensive inspection reports, allowing for quick decision-making and maintenance planning.”).
Therefore, it would have been obvious to one of ordinary skill in the art at the time of the invention to modify Hever in view of ‘041 to teach processing the subset of the plurality of images, using at least one trained machine learning (ML) model, to determine whether the vehicle has the one or more defects; and generating a vehicle condition report based on results of the processing, the vehicle condition report including an indication of the one or more defects in the plurality of images so the system for vehicle inspection to learn to identify defects on its own using past and current defect images and data and to generate a report for review by a user to make informed decisions and take corrective actions as needed.
Modified Hever further fails to teach the following limitation, but Gilbert teaches determining poses of the vehicle in images of the plurality of images; after determining the poses, 430 of the illustrated example of FIG. 4 analyzes inspection images represented in the captured image data 422. In some examples, the inspection image analyzer 430 determines a vehicle condition, vehicle part condition, wear metric, usage metric and/or other analysis metric corresponding to a vehicle and/or vehicle part based on analysis of an inspection image. For example, the inspection image analyzer 430 can compare inspection images with reference inspection images to identify differences and make inferences about a vehicle condition, vehicle part condition, etc. For example, if an inspection image is captured corresponding to a side view of a vehicle, the inspection image analyzer 430 can compare the current inspection image with a reference image from the same perspective. In such an example, if a central portion of the vehicle has a substantially different shading or texture, the inspection image analyzer 430 may attempt to determine if the difference corresponds to damage by comparing the inspection image with reference images of known damaged vehicles.”; [0108]; [0169]).
Therefore, it would have been obvious to one of ordinary skill in the art at the time of the invention to take modified Hever in view of Gilbert to teach determining poses of the vehicle in images of the plurality of images; after determining the poses, comparing the poses with reference poses of a reference set of vehicle poses to determine a degree of pose matching between a particular reference pose and a particular pose of the vehicle in a particular image so that the generated image can be compared to an accurate reference image of the inspected vehicle to accurately perform an inspection to identify any defects or discrepancies with the vehicle condition.
Regarding claim 22 (and similarly 33 and 38), Hever teaches wherein the obtaining comprises controlling the plurality of sensor arrays of the vehicle inspection system to capture the plurality of images of the vehicle (See at least: Fig. 1B; [0055] The system 100 illustrated in FIG. 1A is a computer-based vehicle inspection system for automatically inspecting a vehicle. System 100 comprises a computerized system 101 for 3D vehicle model reconstruction and vehicle inspection, and a set of image acquisition devices 130 (also termed herein as imaging devices). System 101 can be configured to obtain, from the set of imaging devices 130, a plurality of sets of images capturing/acquiring a plurality of segments of surface of a vehicle. The set of imaging devices 130 can be operatively connected to system 101 and the captured images can be transmitted to system 101 via wired or wireless communication.).
Regarding claim 23 (and similarly 34 and 39), Hever teaches wherein the controlling comprises:
controlling the first set of cameras to capture images of one or more wheels of the vehicle (See at least: Fig. 2A, bottom camera(s));
controlling the second set of cameras to capture images of a first side of the vehicle (See at least: Fig. 2A, cameras in the middle of the support structure); and
controlling the third set of cameras to capture images of a roof of the vehicle (See at least: Fig. 2A, top most cameras).
Regarding claim 24, Hever teaches generating a 3D model of the vehicle using at least some of the plurality of images; generating a visualization of the 3D model; and providing access to the visualization to one or more users (See at least: Figs. 7-12).
Regarding claim 27 (and similarly 36 and 40), Hever teaches wherein the one or more defects include: scratches to an exterior of the vehicle, cracked windows, mirrors, or windshields, chipped paint, dents to the exterior of the vehicle, misaligned body panels, missing vehicle parts, non-standard replacement parts, non-standard paint, aftermarket vehicle accessories, rust/corrosion on the vehicle, damaged wheels, damaged tires, bald tires, tire sidewall bubbles, broken tire valves, wheel misalignment, mismatched tires, brake rotor discoloration, brake rotor damage, brake rotor wear, and/or suspension modifications (See at least: [0129] The 3D mesh and/or the 3D model with virtual views can be used for identifying anomalies on the vehicle, including any anomaly which can be indicative of potential damages and deterioration, such as, e.g., cracking, scrapes, bulges, cuts, snags, punctures, foreign objects, or other damage resulting from daily use, etc.”).
Regarding claim 28, Hever teaches wherein the vehicle inspection system further comprises a vehicle undercarriage inspection system; and the plurality of images includes a fourth set of images of an undercarriage of the vehicle captured by the vehicle undercarriage inspection system (See at least: “[0071] In some cases, the inspection system 100 can further comprise an undercarriage inspection unit (not shown separately) embedded underground, e.g., between the two poles. The undercarriage inspection unit can comprise one or more imaging devices configured to capture one or more images of the undercarriage of the vehicle when the vehicle passes by.”).
Regarding claim 31, Hever teaches wherein the set of vehicle poses includes poses associated with the cameras of the first, second and third sets of cameras (See at least: Fig. 2A; [0129] The 3D mesh and/or the 3D model with virtual views can be used for identifying anomalies on the vehicle, including any anomaly which can be indicative of potential damages and deterioration, such as, e.g., cracking, scrapes, bulges, cuts, snags, punctures, foreign objects, or other damage resulting from daily use, etc.”).
Regarding claim 41, Hever fails to teach the following limitation, but ‘041 teaches
wherein determining the poses of the vehicle in the images of the plurality of images comprises: segmenting the vehicle out from the images (See at least: [0071] Optionally, the defect detection is limited only to pixels containing the vehicle (100) by setting to zero all pixels of the input image where the segmentation predicted class “0” (background) or by calculating a bounding rectangle for all pixels predicted as “1” (vehicle), cropping this portion of the input image, and providing only the crop to the defect detection algorithm. Relevant pixels may be determined across frames according to motion sensing of the vehicle (100) using techniques such as odometry or simultaneous localization and mapping (SLAM). Relevant pixels may be determined across frames according to motion sensing of the vehicle (100) combined with the known 3D model of the vehicle (100).).
Therefore, it would have been obvious to one of ordinary skill in the art at the time of the invention to modify Hever in view of ‘041 to teach wherein determining the poses of the vehicle in the images of the plurality of images comprises: segmenting the vehicle out from the images so that the method for analyzing the condition of a vehicle can be limited only to the vehicle and not use any computing resources on non-vehicle objects in the mirror.
Claims 25 and 35 are rejected under 35 U.S.C. 103 as being unpatentable over Hever in view of ‘041 and further in view of Rasheed et al. (US 12159467 hereinafter Rasheed).
Regarding claim 25, Hever fails to teach the following limitation, but Rasheed teaches wherein the 3D model is generated using photogrammetry, neural radiance fields, or Gaussian splatting (See at least: Col. 34 lines 37-42 via “The 3D reconstruction module 100 may be responsible for generating 3D point clouds, surfaces, and models from the pre-processed (raw) sensor data 85, using various computer vision and photogrammetry techniques, such as stereo matching, point cloud registration, and surface reconstruction, for example.”).
Therefore, it would have been obvious to one of ordinary skill in the art at the time of the invention to take modified Hever in view of Rasheed to teach wherein the 3D model is generated using photogrammetry, neural radiance fields, or Gaussian splatting so that a 3D model of a vehicle can be created to inspect the vehicle and find defects.
Regarding claim 35, modified Hever teaches generating, using photogrammetry, neural radiance fields or Gaussian splatting, a 3D model of the vehicle using at least some of the plurality of images;
generating a visualization of the 3D model; and
providing access to the visualization to one or more users (Refer at least to claim 24 and 25 for reasoning and rationale.)
Claim 26 is rejected under 35 U.S.C. 103 as being unpatentable over Hever in view of ‘041 and further in view of Gaidon et al. (US 20250272788 hereinafter Gaidon).
Regarding claim 26, modified Hever teaches wherein the vehicle condition report includes the image (refer at least to claim 21 for reasoning and rationale)
but fails to teach the following limitation, but Gaidon teaches identifying, from among the plurality of images, an image containing personally identifiable information (PID); identifying a region of the image containing the PII; and distorting the region of the image containing the PII, (See at least: [0018] via “Thus, the representation of the scene derived by the depth model does not convey details of faces, license plates, or other PII. Instead, the depth map functions to obscure the PII while still providing a depiction of the scene from the original image.”).
Therefore, it would have been obvious to one of ordinary skill in the art at the time of the invention to take modified Hever in view of Gaidon to teach identifying, from among the plurality of images, an image containing personally identifiable information (PID); identifying a region of the image containing the PII; and distorting the region of the image containing the PII, wherein the vehicle condition report includes the image so that vehicle owners can safeguard their personal information when having their vehicles inspected.
Response to Arguments
Applicant's arguments filed 6/2/26 have been fully considered but they are not persuasive.The Applicant contends that:
“The Office Action alleges (p. 10) that 107 of Gilbert teaches the subject matter of previously-cancelled claim 29, aspects of which have been integrated into the independent claims. But the cited portion of Gilbert merely states that "if an inspection image is captured corresponding to a [given perspective], the inspection image analyzer can compare the current inspection image with a reference image [of the same type of car] from the same perspective" (Gilbert, 107, see 100). Gilbert is silent on how to assess whether the inspection image and the reference image are from the same perspective. Accordingly, Gilbert simply does not disclose "determining poses of the vehicle in images" and "after determining the poses, comparing the poses with reference poses...to determine a degree of matching between a particular reference pose and a particular pose" as recited in the amended claims.”
The Examiner respectfully disagrees. [0107] of Gilbert teaches “For example, if an inspection image is captured corresponding to a side view of a vehicle, the inspection image analyzer 430 can compare the current inspection image with a reference image from the same perspective.” The Examiner contends “compare the current inspection image with a reference image from the same perspective” teaches determining poses of the vehicle and comparing them to a similar reference pose. Therefore, the Examiner maintains that Hever in view of Gilbert teaches the amended limitations.
Allowable Subject Matter
Claim 30 is 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
Any inquiry concerning this communication or earlier communications from the examiner should be directed to Harry Oh whose telephone number is (571)270-5912. The examiner can normally be reached on Monday-Thursday, 9:00-3:00.
If attempts to reach the examiner by telephone are unsuccessful, the examiner’s supervisor, Abby Lin can be reached on (571) 270-3976. 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.
/HARRY Y OH/Primary Examiner, Art Unit 3657
Prosecution Insights