Multi-camera personnel positioning, tracking and displaying method based on human skeleton detection

Abstract

The invention discloses a multi-camera personnel positioning tracking display method based on human skeleton detection. The method comprises the steps: calibrating a plurality of cameras in a target region, obtaining an internal parameter and an external parameter of each camera, and storing the internal parameters and the external parameters; calculating the foreground of two frames of images acquired by each camera before and after to obtain a foreground change value, and when the foreground change value of each camera is greater than a preset foreground threshold, determining that the cameras are synchronous; identifying a target person image acquired by the camera through the mathematical model and extracting human skeleton points after determining that the camera is synchronized, mapping the human skeleton points through internal parameters and external parameters of the camera to obtain space rays, and matching the space rays through a matching algorithm; after matching is completed, according to the position of each target person in the world coordinate system, the space average coordinates of the points are calculated respectively, the space average coordinates serve as tracking points, a target is tracked through a tracking method, and the obtained matched target person is displayed.

Description

technical field [0001] The invention relates to the technical field of image processing, in particular to a multi-camera personnel positioning tracking display method based on human skeleton detection. Background technique [0002] Due to the limited field of view of the monocular camera and inaccurate monocular positioning, in the actual target positioning and tracking system, more multi-camera systems are used. The multi-camera system can help solve occlusions and moving targets under sudden changes in ambient light. However, it also introduces new problems, mainly including: time synchronization between multiple cameras and matching between multiple targets. The main idea of ​​traditional multi-camera target positioning and tracking is: calibrate the internal and external parameters of the camera, and then use traditional methods to extract targets, such as background modeling, frame difference, etc., and then register and fuse the data to obtain objects belonging to the ...

AI Technical Summary

Problems solved by technology

[0004] The present invention provides a multi-camera personnel positioning and tracking display method based on human skeleton detection. By mapping the detected human body posture points to the space according to the internal parameters of the camera, the rays corresponding to the points are obtained, and the closest distance between two straight lines in space is obtained. The value is used as the cost matrix, combined with the matching algorithm to calculate the matching result, and then the result is positioned and tracked to solve the technical problems of poor detection effect and robustness in the traditional method of target detection, thereby improving the target detection effect and increasing the robustness. In order to improve the effect of multi-camera tracking

Images