Method and system for identifying obstacles

Abstract

The invention discloses an obstacle identification method, the method comprising: acquiring a first depth image of the surrounding environment in a driving route; performing cutting processing on the first depth image to obtain a second depth image corresponding to the driving lane; based on Perform ground fitting on the second depth image, determine the ground straight line, and remove the ground part according to the ground straight line to obtain a third depth image without the ground part; perform cluster analysis on the third depth image to obtain multiple Obstacle cluster point set, and determine the position information of each obstacle. Correspondingly, the invention also discloses an obstacle recognition system. Through the present invention, obstacles can be monitored in real time, and obstacles can be better avoided.

Description

technical field

[0001] The invention relates to the technical field of computer vision, in particular to an obstacle recognition method and system. Background technique

[0002] With the development of science and technology, robots or express unmanned vehicles are more and more widely used. Obstacle recognition and avoidance has become an important embodiment of robot intelligence. With the continuous development of various robots, the requirements for obstacle avoidance are also increasing. The real environment is often complex and changes in real time. It is necessary to be able to accurately identify obstacles and obtain the distance between them and the robot. The patent application number is 201510891318, which is based on the Kinect sensor depth map and the uncertainty map construction method of the robot's working environment. It adopts the technical solution of pre-stored ground for ground detection. When encountering slopes, etc., the ground cannot be detected no...

Images