Camera target handover method and handover system

Abstract

The invention discloses a camera target handover method, which is applied to a monitoring area at least comprising two cameras, and comprises the following steps: generating a homography matrix between the two cameras according to a projective relationship between view images in the two cameras; mutually mapping the target objects shot by the two cameras to the opposite cameras by using the homography matrix, and respectively matching the target objects in the two cameras with the mapping objects to generate respective one-way matching matrixes; combining the one-way matching matrixes of the two cameras to obtain a two-way matching matrix, so as to obtain a corresponding relation between the target objects in the two cameras according to element values in the two-way matching matrix; and finding the known tracking target in the original camera in the target camera by using the corresponding relation so as to carry out handover. The technical scheme provided by the invention improves the accuracy of target handover, is easy to implement, and has good performance when being applied to a multi-target handover scene.

Description

technical field [0001] The invention relates to the field of video surveillance, in particular to a camera target handover method and a handover system. Background technique [0002] In recent years, with the continuous development of smart cities, intelligent transportation and other fields, single cameras suffer from the defects of large blind spots and small perception field of view when performing monitoring tasks, which limits the development of related monitoring technologies. Therefore, multi-camera tracking technology has emerged as the times require. pregnancy. In the actual road scene, the multi-camera tracking technology can realize the continuous tracking of suspicious targets in a large scene, and can assist the monitoring personnel to better analyze the target movement trajectory. Among them, target handover tracking is one of the very important links in multi-camera tracking. It aims to identify the same target between cameras through computer vision, image p...

AI Technical Summary

Problems solved by technology

Among them, when the algorithm based on target feature matching is used, because the same target has problems such as viewing angle and brightness changes between different cameras, the intra-class difference of the target is large, resulting in slightly poor matching robustness; the method based on the visual field boundary is more dependent on The accuracy of the position of the line of sight boundary and the error generated when establishing the line of sight line equation will be passed on to the determination of the subsequent handover tracking timing and the result of target handover tracking; in the case of a large number of targets and a more complex scene, it is likely to cause Target handover and tracking errors; the algorithm based on camera coordinate calibration maps the monitoring target and the camera to the same coordinate system to achieve target tracking from various angles, which is relatively difficult in terms of information acquisition and computational complexity, and real-time Poor, more difficult to implement

Images