US 10,475,208 B1Granted

Vehicle analysis platform

AssigneeCapital One Services, LLC

InventorsMark Morrison, Prasad Pathapati

Life of this patent

Estimating the term…

Loading patent…

Abstract

A vehicle analysis platform may cause one or more image capture devices to capture a plurality of images. The vehicle analysis platform may cause one or more sensors to provide measurement data associated with one or more operational characteristics of a vehicle. The vehicle analysis platform may determine, based on the plurality of images, one or more features of the vehicle and obtain, based on the one or more features, reference information associated with the vehicle. The vehicle analysis platform may analyze the vehicle based on the plurality of images and the reference information to determine an image score associated with the vehicle. The vehicle analysis platform may analyze the vehicle based on the measurement data and the reference information to determine an operational score associated with the vehicle. The vehicle analysis platform perform an action associated with the vehicle based on the image score and the operational score.

Claims20

Dependent claims

A method, comprising:

detecting, by a device, that a vehicle is in an inspection bay,
wherein the vehicle is running in the inspection bay;
causing, by the device and based on detecting that the vehicle is in the inspection bay, an image capture device of the inspection bay to capture a plurality of images of the vehicle,
wherein the plurality of images are captured from a plurality of different angles based on dimensions of the vehicle;
determining, by the device and from an image analysis of the plurality of images, one or more features of the vehicle;
obtaining, by the device and based on the one or more features, reference information associated with the vehicle;
comparing the reference information with the plurality of images to detect variances;
determining, using a first machine learning model and based on the detected variances, a first score associated with the vehicle,
wherein the first score is representative of a visual condition of the vehicle;
receiving, by the device and from one or more sensors, measurement data associated with the vehicle;
determining, by the device and using a second machine learning model, based on the measurement data and the reference information, a second score associated with the vehicle,
wherein the second score is representative of an operational condition of the vehicle;
determining, by the device and using a third machine learning model, a vehicle condition score for the vehicle based on the first score and the second score,
wherein the vehicle condition score is representative of an overall condition of the vehicle, and
wherein the third machine learning model is trained based on historical information associated with determining a condition of a plurality of vehicles based on a plurality of first scores and a plurality of second scores;
and
performing, by the device, an action associated with the vehicle based on the vehicle condition score.

14 more elements

A device, comprising:

a memory;
and
one or more processors operatively coupled to the memory, the memory and the one or more processors configured to:
receive, from an image capture device, a plurality of images of a vehicle;
identify, from the plurality of images, reference information associated with the vehicle;
determine, based on the reference information and using a first machine learning model, a first score associated with the vehicle based on a visual condition of the vehicle,
wherein the visual condition is represented in the plurality of images;
receive, from one or more sensors, measurement data associated with the vehicle;
determine, based on the reference information and using a second machine learning model, a second score associated with the vehicle based on an operational condition of the vehicle,
wherein the operational condition of the vehicle is represented in the measurement data;
determine, using a third machine learning model, a vehicle condition score for the vehicle based on the first score and the second score,
wherein the vehicle condition score is representative of an overall condition of the vehicle;
and
perform an action associated with the vehicle based on the vehicle condition score.

11 more elements

A system configured to analyze a vehicle, the system comprising:

one or more image capture devices configured to capture a plurality of images of the vehicle;
one or more sensors configured to detect one or more operational characteristics of the vehicle;
and
one or more control devices configured to:
cause the one or more image capture devices to capture the plurality of images;
cause the one or more sensors to provide measurement data associated with the one or more operational characteristics;
determine, based on the plurality of images, one or more features of the vehicle;
obtain, based on the one or more features, reference information associated with the vehicle;
analyze, using a machine learning model, the vehicle based on the plurality of images and the reference information to determine an image score associated with the vehicle;
analyze, using the machine learning model, the vehicle based on the measurement data and the reference information to determine an operational score associated with the vehicle;
determine, using the machine learning model, a vehicle condition score associated with the vehicle based on the image score and the operational score,
wherein the machine learning model is trained based on the one or more features, the reference information, and historical data associated with a plurality of vehicle condition scores for a plurality of vehicles;
and
perform an action associated with the vehicle based on the vehicle condition score.

11 more elements

Dependencies are inferred from the claim text.