Obstacle detection method and equipment

Abstract

The invention discloses an obstacle detection method and equipment. The method comprises the steps that an image sequence from image acquisition equipment is received through a first processor; a first image in the image sequence is sent to a second processor through the first processor, and a child thread operated by the second processor is invoked so as to detect a plurality of obstacles in thefirst image; detection results of detection from the second processor are received through the first processor; a plurality of tracking devices used for tracking at least part of the plurality of obstacles in the image sequence are initialized through the first processor according to the detection results; and at least part of the obstacles in the image sequence are tracked by means of the plurality of tracking devices through the first processor.

Description

technical field [0001] The present invention relates to the field of image recognition for vehicle driving, in particular, to a method and device for detecting obstacles. Background technique [0002] The driving assistance system can assist the driver in highway and urban environment driving, and is of great significance in solving traffic jams and driving safely. Obstacle collision warning is the core function of the driving assistance system. At present, scholars at home and abroad have proposed many algorithms for detecting obstacles in front of vehicles. Commonly used sensors include monocular cameras, binocular cameras, laser radars, and millimeter-wave radars. The detection scheme based on the monocular camera is mature in technology, but it is greatly affected by the environment; the detection scheme based on the binocular camera has high ranging accuracy, but the calculation amount is large, and it is also greatly affected by the environment; the detection scheme b...

AI Technical Summary

Problems solved by technology

[0007] Embodiments of the present invention provide a method and device for detecting obstacles, to at least solve the problem that the detection scheme of traditional monocular or binocular cameras is greatly affected by the environment, the cost of the detection scheme of laser radar is high, and environmental details cannot be obtained; based on The detection scheme of millimeter wave radar returns a small amount of data and technical problems of low accuracy

Images