Tracking system based on binocular camera shooting

Abstract

The invention relates to a full automatic target detecting and tracking system in the computer vision field, wherein, an input module is responsible for collecting digital images shot by a binocular camera to be taken as system input, the obtained digital images are input into a feature extraction module and feature analysis is carried out to one image to obtain a plurality of characteristic points to be taken as the subsequently processed images. By matching the characteristic points of two images, the parallax of the two images is calculated, and by combining the pre-informed external and internal parameters of the camera, the lower coordinate of a camera coordinate system of the characteristic points can be calculated; furthermore, by the relationship between a world coordinate system and the camera coordinate system, the coordinate of the world coordinate system of the characteristic points can be known. A clustering module clusters the characteristic points into an aggregation for expressing target position, while a trajectory analysis module estimates the target position on a time sequence to obtain the motion trajectory of the target. The invention can effectively and steadily detect the targets in a designated area, track the targets and calculate the motion trajectories of the targets.

Description

technical field [0001] The invention relates to a tracking system in the technical field of image recognition, in particular to a tracking system based on binocular photography. Background technique [0002] With the popularity of digital cameras, digital images have played an increasingly important role in production and life. Especially in surveillance and security, digital images play an important role in target recognition and target tracking. However, due to changes in the lighting conditions and viewing angles of the monitoring scene, the accuracy of monitoring is affected, which limits the application of fully automatic tracking based on image technology. Surveillance scenes in real life vary greatly, and factors such as the influence of ambient light, camera angle, target occlusion, and shadows vary greatly between different scenes. Even in some outdoor scenes, these conditions vary from moment to moment. Surveillance systems based on a single camera are often ver...

AI Technical Summary

Problems solved by technology

[0004] The disadvantage of the above system is that although the system can detect and track multiple human targets, the algorithm requires more cameras (12 pairs of stereo cameras in the text), resulting in higher hardware costs

At the same time, the algorithm has no way to calculate the speed and direction of the target. At the same time, it can only detect and track the human body but not any object, such as the detection and tracking of cars on the road.

Images