Rough road surface driving assisted equipment and method for rough road driving assisting

Abstract

The invention provides rough road surface driving assisted equipment, which comprises: a road surface information acquisition device with a binocular camera system, wherein the binocular camera system is adopted to shoot the road surface ahead a vehicle so as to acquire the ahead road surface video information; and a rough road surface judgment device, wherein the ahead road surface video information acquired by the road surface information acquisition device is converted into a parallax image, a moving window is adopted to divide the parallax image into a series of sub-parallax images, the divided sub-parallax images are converted into various sub-V parallax images according to the V parallax image generation criterion, line segment fitting is performed on various sub-V parallax images to obtain road surface mapping line segments, and whether the ahead road surface is the rough road surface is judged according to the total number of the endpoints of the road surface mapping line segments in various sub-V parallax images.

Description

technical field [0001] The invention relates to an auxiliary device for driving on uneven roads and a method for assisting driving on uneven roads, which can use the images captured by two cameras installed on the vehicle to judge and detect the uneven road ahead, and realize the slope type road / pit type The classification of the road surface automatically judges whether there are potential safety hazards. Background technique [0002] Unmanned vehicles usually have cognitive driving environment and automatic driving functions. Among them, the feasible road area detection is an important part of the cognitive driving environment function. The data information collected by the camera equipment in the road surface information collection instrument is far more accurate and reliable than the data information collected by the ranging sensor, and its image information covers a larger area. [0003] Road surface detection based on camera information usually uses simple two-dimens...

AI Technical Summary

Problems solved by technology

[0007] However, the traditional V parallax algorithm has limitations. Although this method can detect the road ahead, it cannot quantitatively judge whether the road is uneven or not, and it cannot judge the slope / pit, and it cannot combine the actual parameters of the car body to judge the front. Is there a hidden danger in the slope / pit?

Images