Method and device for evaluating barrier detection result of driverless vehicle

Abstract

The invention discloses a method and device for evaluating a barrier detection result of a driverless vehicle. The method in one embodiment comprises steps of: acquiring an image, sensed by the driverless vehicle, of a barrier and a real image of the barrier, and solving a minimum circumscribed rectangle to obtain the sensed area and the real area of the barrier; computing the coincidence rate of the sensed area and the real area according to the area of the intersected area of the sensed area and the real area and the area of the united area of the sensed area and the real area; computing the distance between the central point of the sensed area and the central point of the real area according to the position of the central point of the sensed area and the position of the central point of the real area; computing the figure similarity of the sensed area and the real area according to the area and the length-width ratio of the sensed area and the real area; and computing the matching degree of the sensed area and the real area on the basis of the coincidence rate, the distance between the central points, and the figure similarity. The method accurately evaluates the barrier detection result.

Description

technical field [0001] The present application relates to the field of computer technology, in particular to obstacle detection technology, and in particular to a method and device for evaluating obstacle detection results for unmanned vehicles. Background technique [0002] With the development of multiple disciplines such as computer, cybernetics, artificial intelligence and bionics, driverless vehicle technology has developed by leaps and bounds. Unmanned vehicles use on-board sensors to perceive the surrounding environment of the vehicle, and control the steering and speed of the vehicle based on the road, vehicle position and obstacle information obtained from the perception, so that the vehicle can drive safely and reliably on the road. [0003] Existing evaluation methods for obstacle detection results for unmanned vehicles are usually based on the ratio of the intersection area and union area of ​​the unmanned vehicle's perception of obstacles to the obstacle's real ...

AI Technical Summary

Problems solved by technology

[0003] Existing evaluation methods for obstacle detection results for unmanned vehicles are usually based on the ratio of the intersection area and union area of ​​the unmanned vehicle's perception of obstacles to the obstacle's real area and the union area. The matching degree between the perceived area and the real area. However, in the process of driving an unmanned vehicle, it often faces a large number of different types of obstacles. The existing evaluation methods for obstacle detection results consider too few factors, and Unable to accurately evaluate obstacle detection results

Images