Target tracking method and related device

Abstract

The invention discloses a target tracking method and a related device. The target tracking method and the related device are used for achieving real-time tracking and processing of a target. The target tracking method comprises the steps of according to a position of the target in a video monitoring image of a previous frame, using a motion predicting model built for the target for predicting positions of the target in a video monitoring image of a current frame, obtaining predicted positions of the target, conducting target detecting in an image area where the predicted positions are distributed according to a detecting model built for the target, obtaining detected positions of the target, conducting target tracking in the image area where the predicted positions are distributed according to a tracking model built for the target, obtaining tracked positions of the target, conducting weight fusion on the detected positions and the tracked positions according to an image position overlapping ratio, obtaining the tracked positions of the target in the video monitoring image of the current frame, adjusting an intelligent video monitoring device according to the tracked positions of the target in the video monitoring image of the current frame, and achieving tracking of the target.

Description

technical field [0001] The invention relates to the field of intelligent video monitoring, in particular to a target tracking method and a related device. Background technique [0002] Intelligent video surveillance is a method of actively monitoring targets. Through video analysis technology, intelligent monitoring of scenes can be realized without manual intervention, and it is more and more favored by the market. [0003] In the prior art, intelligent video surveillance uses video analysis technology to analyze and process the field of view image monitored by the camera in real time. Once an emergency occurs, the target (such as pedestrians, vehicles) can be locked and actively alarmed, and the control equipment can be adjusted. The camera direction, angle of view, and focal length continuously track the target, so as to achieve intelligent tracking of the target. In the prior art, after the target is locked, due to the uncertainty of the target position, the commonly us...

AI Technical Summary

Problems solved by technology

In the prior art, after the target is locked, due to the uncertainty of the target position, the commonly used target tracking method is to search the entire image within the video monitoring range of the camera to find the target, which is blind. High-definition, the computational complexity of this method will become greater, resulting in a greater delay, so the existing target tracking method is difficult to achieve real-time tracking

Moreover, since the target in the monitoring image is the projection of the three-dimensional target object on the two-dimensional plane in the real world, the real target has a changeable shape and is easily blocked. When the target is blocked or the shape changes too fast, the tracked target will Lost, resulting in insufficient robustness of the target tracking method

Images