Vehicle obstacle avoidance method and electronic equipment based on binocular vision and deep learning

Abstract

The invention discloses a vehicle obstacle avoidance method based on binocular vision and deep learning: obtain the RGB image in front of the vehicle; obtain the depth information map in front of the vehicle; predict and obtain the drivable area segmentation result; information fusion optimizes the drivable area; The depth information of the drivable area is used to generate the main view of depth obstacles; the distribution of obstacles in the three-dimensional space in front of the car is obtained, and the bird's-eye view obstacle scatter diagram is obtained accordingly; the bird's-eye view obstacle scatter diagram is density clustered to remove noise; The bird's-eye view obstacle scatter map performs Euclidean distance transformation and sets an adaptive threshold, and divides the front map into safe driving areas and dangerous areas; constructs a map for path planning through the bird's-eye view safe driving area map and field angle boundary information; uses dynamic The window method combines the map used for path planning to plan the obstacle avoidance path; calculate the expected speed and expected angle according to the obstacle avoidance path trajectory and send it to the control system. The invention also provides corresponding electronic equipment.

Description

technical field [0001] The invention belongs to the technical field of computer vision, and more specifically relates to a vehicle obstacle avoidance method based on binocular vision and deep learning. Background technique [0002] Navigation is one of the most important basic functions in the autonomous driving decision-making system, and it is also an important bridge between environmental perception and vehicle control. It determines how the vehicle uses environmental information to make scientific judgments with the goal of safely reaching the destination. . More specifically, navigation can be divided into global navigation and local navigation. [0003] The mainstream method of global navigation is to obtain location information based on GPS and other positioning satellites, and use the global path planning algorithm to comprehensively consider road conditions, path length and other conditions to comprehensively plan the road from the starting point to the ending poin...

AI Technical Summary

Problems solved by technology

[0007] The existing obstacle recognition technology based on the binocular camera has the following problems: the traditional ground filtering algorithm is usually complicated and the effect is not good, the generalization is poor, and it cannot cope with the ups and downs of the road, and the ground is misidentified as an obstacle, which will cause the vehicle to run unstable state

If only obstacles are extracted from the field of view of the camera and the ground level, a lot of detection information on low obstacles will be lost, and the semantic information of the generated obstacle avoidance map will be weak; errors in the distance measurement of the depth camera will lead to inaccurate judgments on the position of the edge of the obstacle. Easy to be disturbed by noise, direct use will lead to mislocation of obstacles, etc.

Images