CROSS-LENS MULTI-TARGET TRACKING METHOD AND APPARATUS BASED ON SPACE-TIME CONSTRAINTS

摘要

A cross-lens multi-target tracking method and apparatus based on space-time constraints. The method comprises: performing image preprocessing on different color spaces so that the images are consistent in color temperature and tone to obtain photographing information of a plurality of photographing devices (S101); establishing a correspondence of 2D points by means of the projection matrix of the photographing devices to obtain geometric information among the plurality of photographing devices, wherein the projection matrix is a projection matrix about the 3D world (S102); and performing human body feature matching among the plurality of cameras according to the photographing information and the geometric information to obtain the pictures and the real-time tracking result of each photographing device using the appearance and spatial-temporal features of the tracking target (S103). By combining the current multi-target tracking algorithm with the multi-camera processing method and using the attitude and posture matrix of the camera network, the method can achieve multi-camera-based multi-target object tracking, improving the robustness of object tracking, reducing the tracking error, and increasing the tracking accuracy.