Method and device for evaluating target detection algorithm based on unmanned vehicle

Abstract

The embodiment of the invention discloses a method and device for evaluating a target detection algorithm based on an unmanned vehicle. The unmanned vehicle is provided with a camera, a vehicle body signal sensor, a laser radar and a millimeter-wave radar. The method comprises the steps that: continuous images collected by the camera, vehicle body signals collected by the vehicle body signal sensor, radar data corresponding to the laser radar and millimeter-wave radar data corresponding to the millimeter-wave radar in the driving process of the unmanned vehicle are acquired; the continuous images and the vehicle body signals are input into the target detection algorithm, so that a prediction position and a prediction speed of each prediction target are obtained; a true value position and atrue value speed of each true value target around the unmanned vehicle at each sampling moment are calculated according to the radar data and the millimeter wave radar data; and an evaluation resultof the target detection algorithm is calculated according to the prediction position and the prediction speed of each prediction target and the truth value position and the truth value speed of each truth value target. According to the method and device of the embodiment of the invention, the evaluation precision of the target detection algorithm can be improved.

Description

technical field [0001] The present invention relates to the technical field of intelligent driving, in particular to a method and device for an evaluation target detection algorithm based on an unmanned vehicle. Background technique [0002] During the driving process of the unmanned vehicle, it needs to detect the targets that appear on the road, such as other vehicles, pedestrians, bicycles, etc., so as to avoid accidents such as collisions and ensure the safety of its driving. Specifically, a camera can be installed on the vehicle, and the image of the surrounding environment during the driving of the vehicle can be collected through the camera, and the target detection algorithm can perform target detection on the image captured by the camera to obtain the coordinate information of each target. [0003] The detection accuracy of the target detection algorithm will affect the accuracy of the target detection results. When evaluating the detection accuracy of the target d...

AI Technical Summary

Problems solved by technology

However, due to the difference between the target to be tested and the real target around the vehicle, the obtained true position of the target cannot objectively describe the complex situation in the real scene, that is, the accuracy of the obtained target’s true position Poor, resulting in poor accuracy of the evaluation results of the target detection algorithm

Images