# US 12,597,115 B2 · Systems and techniques for vehicle inspection and condition analysis

> Agents: this data is available as JSON from the patentgrep API and MCP server — see https://patentgrep.com/llms.txt

- Number: US 12,597,115 B2
- Document ID: US12597115B2
- Status: Granted
- Kind: B2
- Application number: 19/294,071
- Filed: 2025-08-07
- Published: 2026-03-05
- Granted: 2026-04-07
- Earliest claimed: 2024-08-30
- Assignees: ACV Auctions Inc.
- Applicants: ACV Auctions Inc.
- Inventors: Mark Brighton; Margaret Donnelly; Livio Forte, III; William Giegerich; Frank Pollina; Philip Schneider; Prajwal Shubhodaya Shetty; Justas Birgiolas; Stephen Christopher Hull; Akhil Kanna Devarashetti
- Web page: https://patentgrep.com/patent/US12597115B2

## CPC

- G06T 7/0004: {Industrial image inspection}
- G01N 21/8851: {Scan or image signal processing specially adapted therefor, e.g. for scan signal adjustment, for detecting different kinds of defects, for compensating for structures, markings, edges (G01N21/8806 and G01N21/93 - G01N21/95692 take precedence; optical measurement of dimensions G01B11/00; optical scanning G02B26/10; image transformation G06T3/00; computerised image enhancement G06T5/00; image processing per se for flaw detection G06T7/0002)}
- G06T 3/4038: Image mosaicing, e.g. composing plane images from plane sub-images
- G06T 7/0002: {Inspection of images, e.g. flaw detection}
- G06T 7/0008: {checking presence/absence}
- G06T 7/70: Determining position or orientation of objects or cameras (camera calibration G06T7/80)
- G06V 10/12: Details of acquisition arrangements; Constructional details thereof
- G06V 10/147: Details of sensors, e.g. sensor lenses (fingerprint or palmprint sensors G06V40/13; vascular sensors G06V40/145; eye sensors G06V40/19)
- G06V 10/70: using pattern recognition or machine learning (optical pattern recognition or electronic computations therefor G06V10/88)
- G06V 10/751: {Comparing pixel values or logical combinations thereof, or feature values having positional relevance, e.g. template matching}
- G07C 5/0808: {Diagnosing performance data (testing of vehicles G01M17/00; testing of electrical installation on vehicles G01R31/005)}
- H04N 23/90: Arrangement of cameras or camera modules, e.g. multiple cameras in TV studios or sports stadiums
- G06T 2200/04: involving 3D image data
- G06T 2200/08: involving all processing steps from image acquisition to 3D model generation
- G06T 2207/10012: Stereo images
- G06T 2207/10048: Infrared image
- G06T 2207/20081: Training; Learning
- G06T 2207/20084: Artificial neural networks [ANN]
- G06T 2207/30136: Metal
- G06T 2207/30164: Workpiece; Machine component
- G06T 2207/30248: Vehicle exterior or interior
- G06T 2207/30252: Vehicle exterior; Vicinity of vehicle
- G06V 2201/08: Detecting or categorising vehicles
- G06T: IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G01N: INVESTIGATING OR ANALYSING MATERIALS BY DETERMINING THEIR CHEMICAL OR PHYSICAL PROPERTIES (measuring or testing apparatus or processes other than immunoassay, involving enzymes or microorganisms C12M, C12Q)
- G06V: IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G07C: TIME OR ATTENDANCE REGISTERS; REGISTERING OR INDICATING THE WORKING OF MACHINES; GENERATING RANDOM NUMBERS; VOTING OR LOTTERY APPARATUS; ARRANGEMENTS, SYSTEMS OR APPARATUS FOR CHECKING NOT PROVIDED FOR ELSEWHERE
- H04N: PICTORIAL COMMUNICATION, e.g. TELEVISION

## Abstract

Systems and techniques for inspecting vehicles, such as cars or trucks. Some embodiments provide a method for inspecting a vehicle using a vehicle inspection system. The vehicle inspection system may include a vehicle exterior inspection system having a plurality of exterior sensor arrays, the plurality of exterior sensor arrays including respective sets of sensors oriented in different directions. The vehicle inspection system may include a vehicle undercarriage inspection system having an undercarriage sensor array including cameras configured to capture images at different angles, and a sensor configured to output vehicle position/motion data. In some embodiments, the method includes: moving the vehicle and/or vehicle inspection system; triggering capture, by the exterior sensor arrays and undercarriage sensor array, of sensor data about the vehicle; capturing the sensor data; stopping capture of the sensor data; stopping movement of the vehicle and/or vehicle inspection system; and generating a vehicle condition report.

## Claims

### Claim 1

A system for vehicle inspection, the system comprising:
a vehicle exterior inspection system, comprising:
a first support member, comprising:
a first set of cameras configured to image an exterior of a vehicle, the first set of cameras comprising:
a first camera oriented to capture images of the vehicle as the vehicle approaches the first support member;
a second camera oriented to capture images of the vehicle as the vehicle is alongside the first support member; and
a third camera oriented to capture images of the vehicle as the vehicle moves past the first support member;
a second support member, comprising:
a second set of cameras configured to image at least one wheel and/or tire of the vehicle; and
a wheel light source configured to illuminate the at least one wheel and/or tire of the vehicle; and
an undercarriage imaging device, comprising:
a third set of cameras configured to image an undercarriage of the vehicle, the third set of cameras including a first, second, and third camera oriented to capture images at different angles relative to the undercarriage of the vehicle; and
an undercarriage light source configured to illuminate the undercarriage of the vehicle; and
a processor configured to:
receive image data from the first set of cameras, the second set of cameras, and the third set of cameras; and
process the image data using at least one trained machine learning model to determine one or more defects of the vehicle.

### Claim 2 (depends on 1)

The system of claim 1, wherein the at least one trained machine learning model comprises:
a vehicle exterior machine learning model trained on images of vehicle exteriors;
a wheel and tire machine learning model trained on images of wheels and/or tires; and
an undercarriage machine learning model trained on images of vehicle undercarriages.

### Claim 3 (depends on 1)

The system of claim 1, wherein the first support member further comprises a vehicle exterior light source configured to illuminate the exterior of the vehicle, and/or wherein the first support member further comprises an infrared camera.

### Claim 4 (depends on 1)

The system of claim 1, wherein the processor is configured to perform:
identifying, from the image data, an image containing personally identifiable information (PII);
identifying a region of the image containing the PII; and
distorting the region of the image containing the PII.

### Claim 5 (depends on 1)

The system of claim 1, wherein;
the first support member further comprises a time of flight sensor, and
the processor is configured to trigger capture of the image data based on an output of the time of flight sensor.

### Claim 6 (depends on 1)

The system of claim 1, 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.

### Claim 7 (depends on 1)

The system of claim 1, wherein the processor is further configured to:
generate, using photogrammetry, neural radiance fields or Gaussian splatting, a 3D model of at least a portion of the vehicle using the image data; and
generate a visualization of the 3D model.

### Claim 8 (depends on 1)

The system of claim 1, wherein the image data comprises a plurality of images, wherein the processor is further configured to perform:
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, the identifying comprising:
determining a degree of matching between the pose of the vehicle in images of the plurality of images and vehicle poses of a reference set of vehicle poses; and for each vehicle pose of the reference set of vehicle poses, identifying an image in the plurality of images having at least a threshold degree of matching and including the identified image in the subset of the plurality of images; and
processing the subset of the plurality of images using at least one trained machine learning model to determine one or more defects of the vehicle.

### Claim 9

A system for vehicle inspection, the system comprising:
a vehicle exterior inspection system, comprising:
a first support member, comprising:
a first set of cameras configured to image an exterior of a vehicle;
a second support member, comprising:
a second set of cameras configured to image at least one wheel and/or tire of the vehicle; and
a wheel light source configured to illuminate the at least one wheel and/or tire of the vehicle; and
a set of microphones configured to capture audio of the vehicle; and
a processor configured to:
receive image data from the first set of cameras and the second set of cameras;
receive audio data from the set of microphones; and
process at the image data and the audio data using at least one trained machine learning model to determine one or more defects of the vehicle.

### Claim 10 (depends on 9)

The system of claim 9, wherein the set of microphones comprises a plurality of microphones configured to capture audio from different portions of the vehicle.

### Claim 11 (depends on 9)

The system of claim 9, wherein the at least one trained machine learning model comprises:
a vehicle exterior machine learning model trained on images of vehicle exteriors; and
a wheel and tire machine learning model trained on images of wheels and/or tires.

### Claim 12 (depends on 9)

The system of claim 9, wherein the at least one trained machine learning model is configured to output:
the one or more defects of the vehicle; and
one or more likelihoods that the one or more defects of the vehicle are present.

### Claim 13 (depends on 9)

The system of claim 9, wherein the vehicle exterior inspection system comprises an undercarriage imaging device, comprising:
a third set of cameras configured to image an undercarriage of the vehicle, the third set of cameras including a first, second, and third camera oriented to capture images at different angles relative to the undercarriage of the vehicle; and
an undercarriage light source configured to illuminate the undercarriage of the vehicle,
wherein the processor is further configured to receive image data from the third set of cameras.

### Claim 14 (depends on 13)

The system of claim 13, wherein the processor is configured to generate a composite image of the undercarriage of the vehicle by combining images captured by the third set of cameras based on speed of the vehicle.

### Claim 15 (depends on 13)

The system of claim 13, wherein the at least one trained machine learning model comprises an undercarriage machine learning model trained on images of vehicle undercarriages.

### Claim 16

A system for vehicle inspection, the system comprising:
a vehicle exterior inspection system, comprising:
a first support member, comprising:
a first set of cameras configured to image at least one wheel and/or tire of a vehicle; and
a wheel light source configured to illuminate the at least one wheel and/or tire of the vehicle;
an undercarriage imaging device, comprising:
a second set of cameras configured to image an undercarriage of the vehicle, the second set of cameras including a first, second, and third camera oriented to capture images at different angles relative to the undercarriage of the vehicle;
an undercarriage light source configured to illuminate the undercarriage of the vehicle; and
at least one microphone; and
at least one sensor configured to collect alignment data of the vehicle relative to the vehicle exterior inspection system; and
a processor configured to:
receive alignment data from the at least one sensor;
trigger, based on the alignment data, capture of images by the first set of cameras and the second set of cameras;
receive image data from the first set of cameras and the second set of cameras;
process the image data using at least one trained machine learning model to determine one or more defects of the vehicle;
receive audio data from the at least one microphone; and
process the audio data using the at least one trained machine learning model to determine the one or more defects of the vehicle.

### Claim 17 (depends on 16)

The system of claim 16, wherein the at least one sensor comprises a ranging sensor.

### Claim 18 (depends on 16)

The system of claim 16, wherein the undercarriage light source comprises a plurality of individual light sources configured to illuminate at different angles relative to the undercarriage of the vehicle, wherein the undercarriage light source comprises constant current light emitting diodes.

### Claim 19 (depends on 16)

The system of claim 16, wherein:
the vehicle exterior inspection system further comprises:
a second support member, comprising:
a third set of cameras configured to image an exterior of a vehicle, and the processor is further configured to receive image data from the third set of cameras.

### Claim 20 (depends on 16)

The system of claim 16, wherein:
the at least one microphone is a plurality of microphones, and
the plurality of microphones are distributed along a width of the undercarriage imaging device.