# US 12,002,269 B2 · Vehicle feature acquisition method and device > Agents: this data is available as JSON from the patentgrep API and MCP server — see https://patentgrep.com/llms.txt - Number: US 12,002,269 B2 - Document ID: US12002269B2 - Status: Granted - Kind: B2 - Application number: 17/280,191 - Filed: 2019-04-26 - Published: 2022-01-06 - Granted: 2024-06-04 - Earliest claimed: 2018-09-27 - Assignees: Neusoft Reach Automotive Technology (Shenyang) Company - Applicants: Neusoft Reach Automotive Technology (Shenyang) Company - Inventors: Huan Tian; Jun Hu; Shuai Cheng - Web page: https://patentgrep.com/patent/US12002269B2 ## CPC - G06V 20/58: Recognition of moving objects or obstacles, e.g. vehicles or pedestrians; Recognition of traffic objects, e.g. traffic signs, traffic lights or roads - G06T 7/73: using feature-based methods - G06V 10/764: using classification, e.g. of video objects - G06T 2207/30252: Vehicle exterior; Vicinity of vehicle - G06V 10/422: for representing the structure of the pattern or shape of an object therefor - G06V 10/82: using neural networks - G06V 20/584: {of vehicle lights or traffic lights} - G06V 2201/08: Detecting or categorising vehicles - G06V: IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING - G06T: IMAGE DATA PROCESSING OR GENERATION, IN GENERAL ## Abstract A method and a device for acquiring a vehicle feature are provided. In the method, a to-be-processed image including a vehicle is acquired. A feature element of the vehicle is then recognized from the to-be-processed image, where the feature element may be a side element and an element of a vehicle end, and the vehicle-end may be a head of the vehicle or a rear of the vehicle. Based on a position of the side element in the to-be-processed image and a position of the element of the vehicle end in the to-be-processed image, a side region of the vehicle and an end region of the vehicle are determined. ## Claims ### Claim 1 A method for acquiring a vehicle feature, comprising: acquiring a to-be-processed image comprising a vehicle; recognizing a feature element of the vehicle from the to-be-processed image, wherein the feature element comprises a side element and an element of a vehicle end, and the vehicle end comprises a head of the vehicle or a rear of the vehicle, the side element comprises one or more of a wheel, a side window, a rearview mirror, and a door; determining, in the to-be-processed image, a side region of the vehicle and an end region of the vehicle, based on a location where the side element is in the to-be-processed image and a location where the element of the vehicle end is in the to-be-processed image; and acquiring a side region feature based on the side region, and an end region feature based on the end region, wherein the side region feature comprises a location where a vertex of the side region is in the to-be-processed image, a location where a center point of the side region is in the to-be-processed image, or a location where a midpoint of an edge of the side region is in the to-be-processed image; and determining a relative position of the vehicle to an image capturing device, based on the end region feature, the side region feature and a shooting parameter of the to-be-processed image. ### Claim 2 (depends on 1) The method according to claim 1, wherein the determining, in the to-be-processed image, a side region of the vehicle and an end region of the vehicle, based on a location where the side element is in the to-be-processed image and a location where the element of the vehicle end is in the to-be-processed image, comprises: determining, in the to-be-processed image, a vehicle region where the vehicle locates; determining a boundary between the side region and the end region, based on the location of the element that is of the vehicle end and is close to the side element in the to-be-processed image and the location of the side element that is close to the element of the vehicle end in the to-be-processed image; and determining, in the vehicle region, the side region and the end region, based on the boundary, the location of the side element in the to-be-processed image, and the location of the element of the vehicle end in the to-be-processed image. ### Claim 3 (depends on 1) The method according to claim 1, wherein the recognizing a feature element of the vehicle from the to-be-processed image comprises: recognizing the vehicle region where the vehicle locates in the to-be-processed image; clipping the vehicle region from the to-be-processed image to generate a vehicle image; and recognizing the feature element of the vehicle from the vehicle image. ### Claim 4 (depends on 1) The method according to claim 1, wherein the image capturing device is a device that photographs the vehicle to obtain the to-be-processed image. ### Claim 5 (depends on 4) The method according to claim 4, wherein the determining a relative position of the vehicle to an image capturing device, based on the end region feature, the side region feature and a shooting parameter of the to-be-processed image, comprises: determining, one of the end region and the side region, that faces toward the image capturing device, as a target region; and determining the relative position of the vehicle to the image capturing device, based on a region feature of the target region and the shooting parameter of the to-be-processed image. ### Claim 6 (depends on 4) The method according to claim 4, wherein the determining a relative position of the vehicle to an image capturing device, based on the end region feature, the side region feature and a shooting parameter of the to-be-processed image, comprises: determining the relative position of the vehicle to the image capturing device, based on a boundary between the end region and the side region, and the shooting parameter of the to-be-processed image. ### Claim 7 (depends on 1) The method according to claim 1, wherein the end region feature comprises a location where a vertex of the end region is in the to-be-processed image, a location where a center point of the end region is in the to-be-processed image, or a location where a midpoint of an edge of the end region is in the to-be-processed image. ### Claim 8 (depends on 1) The method according to claim 1, wherein the element of the head of the vehicle comprises one or more of a front light, a front window, a bumper and a front license plate, and the element of the rear of the vehicle comprises one or more of a rear light, a rear window, and a rear license plate. ### Claim 9 A device for acquiring a vehicle feature, comprising: an image acquisition unit configured to acquire a to-be-processed image comprising a vehicle; an image recognition unit configured to recognize a feature element of the vehicle from the to-be-processed image, wherein the feature element comprises a side element and an element of a vehicle end, and the vehicle end comprises a head of the vehicle or a rear of the vehicle, the side element comprises one or more of a wheel, a side window, a rearview mirror, and a door; a region determination unit configured to determine, in the to-be-processed image, a side region of the vehicle and an end region of the vehicle, based on a location where the side element is in the to-be-processed image and a location where the element of the vehicle end is in the to-be-processed image; and a feature acquisition unit, configured to acquire a side region feature based on the side region, and acquire an end region feature based on the end region, wherein the side region feature comprises a location where a vertex of the side region is in the to-be-processed image, a location where a center point of the side region is in the to-be-processed image, or a location where a midpoint of an edge of the side region is in the to-be-processed image; and a relative position determination unit, configured to determine a relative position of the vehicle to an image capturing device, based on the end region feature, the side region feature and a shooting parameter of the to-be-processed image. ### Claim 10 (depends on 9) The device according to claim 9, wherein the region determination unit comprises: a vehicle region determination unit configured to determine, in the to-be-processed image, a vehicle region where the vehicle locates; a boundary determination unit configured to determine a boundary between the side region and the end region, based on the location of the element that is of the vehicle end and is close to the side element in the to-be-processed image and the location of the side element that is close to the element of the vehicle end in the to-be-processed image; and a region determination subunit configured to determine, in the vehicle region, the side region and the end region, based on the boundary, the location where the side element is in the to-be-processed image, and the location where the element of the vehicle end is in the to-be-processed image. ### Claim 11 (depends on 9) The device according to claim 9, wherein the image capturing device is a device that photographs the vehicle to obtain the to-be-processed image. ### Claim 12 (depends on 11) The device according to claim 11, wherein the relative position determination unit comprises: a target region determination unit configured to determine, one of the end region and the side region, that faces toward the image capturing device, as a target region; and a relative position determination subunit configured to determine the relative position of the vehicle to the image capturing device, based on a region feature of the target region and the shooting parameter of the to-be-processed image. ### Claim 13 (depends on 11) The device according to claim 11, wherein the relative position determination unit is configured to determine the relative position of the vehicle to the image capturing device, based on a boundary between the end region and the side region, and the shooting parameter of the to-be-processed image. ### Claim 14 (depends on 9) The device according to claim 9, wherein the end region feature comprises a location where a vertex of the end region is in the to-be-processed image, a location where a center point of the end region is in the to-be-processed image, or a location where a midpoint of an edge of the end region is in the to-be-processed image. ### Claim 15 (depends on 9) The device according to claim 9, wherein the image recognition unit comprises: a vehicle region recognition unit configured to recognize the vehicle region where the vehicle locates in the to-be-processed image; an vehicle image acquisition unit configured to clip the vehicle region from the to-be-processed image to generate a vehicle image; and a feature element recognition unit configured to recognize the feature element of the vehicle from the vehicle image. ### Claim 16 (depends on 9) The device according to claim 9, wherein the element of the head of the vehicle comprises one or more of a front light, a front window, a bumper and a front license plate, and the feature element of the rear of the vehicle comprises one or more of a rear light, a rear window, and a rear license plate.