Pedestrian three-dimensional detection tracking method and system based on top view angle

Abstract

The invention discloses a pedestrian three-dimensional detection tracking method and system based on a top visual angle. The method comprises the following steps: performing stereo correction and stereo matching processing on left and right images acquired by a binocular camera; filling holes and converting to obtain a height map; modeling the height map to obtain a two-dimensional height foreground map; projecting and converting into a two-dimensional plane point cloud projection drawing under a top view angle, and detecting to obtain a three-dimensional coordinate point of the head of the pedestrian; mapping the three-dimensional coordinate points of the heads of the pedestrians back to the two-dimensional image coordinate system, and positioning a bounding box of each pedestrian; and performing inter-frame pedestrian matching tracking by combining the three-dimensional coordinate point of the pedestrian head and the positioned pedestrian bounding box. According to the invention, the problem of missing detection caused by shielding among pedestrians can be effectively overcome, and the recall rate of pedestrian detection is improved. The pedestrian three-dimensional detection tracking method and system based on the top view angle can be widely applied to the field of pedestrian detection.

Description

technical field [0001] The invention relates to the field of video image processing, in particular to a method and system for three-dimensional detection and tracking of pedestrians based on a top view. Background technique [0002] As a hot research direction of computer vision, pedestrian detection is widely used in our daily life. The pedestrian detection problem can be divided into pedestrian detection from a top view and pedestrian detection from an oblique view according to the position and viewing angle of the camera. At present, most of the mainstream pedestrian detection algorithms are researched on the more flexible oblique angle of view pedestrian detection, and the disadvantage of this angle of view is that the occlusion and adhesion between pedestrians are serious, and it is easy to miss detection. Pedestrian detection based on the top view is also a pedestrian detection task. A special application scenario, but few people have done research on this aspect at p...

AI Technical Summary

Problems solved by technology

At present, most of the mainstream pedestrian detection algorithms are researched on the more flexible oblique angle of view pedestrian detection, and the disadvantage of this angle of view is that the occlusion and adhesion between pedestrians are serious, and it is easy to miss detection. Pedestrian detection based on the top view is also a pedestrian detection task. A special application scenario, but few people have done research on this aspect

Images