Vehicle identification method, device and vehicle

Abstract

Provided are a vehicle identification method and device, and a vehicle. The vehicle identification method comprises: acquiring a first image and a second image (S11), wherein the first image is a color image or luminosity image, and the second image is a depth image; identifying a target vehicle in the second image, and determining a target vehicle area in the second image (S12); mapping the target vehicle area to the first image according to a mapping relationship between the first image and the second image so as to generate a car lamp identification area in the first image (S13); identifying a turn signal lamp at the rear end of the target vehicle in the car lamp identification area (S14); and obtaining travel information of the target vehicle according to an identified status of the turn signal lamp of the target vehicle (S15). The invention can better identify a target vehicle that is about to change lanes, and improve an intelligence level of the vehicle.

Description

technical field [0001] The invention relates to the technical field of vehicles, in particular to a vehicle identification method, a device and a vehicle. Background technique [0002] With the continuous development of science and technology, people's travel is becoming more and more convenient. Various cars, electric vehicles, etc. have become an indispensable means of transportation in people's lives. However, although these means of transportation facilitate people's travel, traffic safety accidents do occur frequently. In order to improve the safety of the vehicle, ranging sensors can be installed on the vehicle to sense multiple target vehicles in front of the vehicle to reduce collisions. accident rate. [0003] Currently, a stereo camera can be used as a ranging sensor, or a single ordinary camera can be used with a millimeter-wave radar or lidar as a ranging sensor to increase the accuracy of the measurement. [0004] However, the ranging algorithm using a stereo ...

AI Technical Summary

Problems solved by technology

[0004] However, the ranging algorithm using a stereo camera is relatively complicated, which may lead to an increase in power consumption of the computer chip, and the method of using a single ordinary camera with millimeter-wave radar or lidar requires a large installation space in the car, and the cost is high

Moreover, since the above-mentioned ranging sensor mainly detects changes in the distance of the target vehicle, and when there is no change or little change in the distance of the target vehicle, for example, in the initial stage of lane change, etc., the above-mentioned ranging sensor may not be able to detect , so that no corresponding measures can be taken

Images