A multi-camera data fusion method based on a spatial coordinate system

Abstract

The invention discloses a multi-camera data fusion method based on a spatial coordinate system, comprising the following steps: constructing a training data set according to the target to be extracted, and completing the training of the target detection and identification model; extracting the category of the target and the position information of the target in the 2D image coordinate system fromthe video data collected by each camera, and establishing the coordinate mapping relationship between the 2D image coordinate system and the 3D space coordinate system; for video stream data collectedby cameras in multiple scenes, carrying out target detection and target recognition to extract the category information of targets in each frame and the position information of targets in two-dimensional image coordinate system; mapping the position information of the target in the two-dimensional image coordinate system to the coordinates of the target in the three-dimensional space coordinate system; according to the distance information between each target in the current time node and each target in the previous time node, obtaining the motion trajectory data of the target in the three-dimensional space coordinate system.

Description

technical field [0001] The invention relates to the field of video image processing, in particular to a monitoring data fusion method collected by multiple cameras in continuous multiple monitoring scenes under a spatial coordinate system. Background technique [0002] In recent years, with the popularity of network cameras used for security, intelligent video surveillance technology has rapidly become a current research hotspot. Video data is a record of what happened in the surveillance scene, which contains various information. In view of the fact that the background is fixed in most video surveillance data, what users are really interested in in video surveillance data are the objects appearing in them and their running trajectories. [0003] At present, most of the video surveillance data is stored separately according to the number of the camera, and then analyzed and processed by intelligent video surveillance technology. Target detection, target recognition and tar...

AI Technical Summary

Problems solved by technology

However, the disadvantages of this method are: 1. The traditional target tracking technology is limited to the two-dimensional image space, and cannot reflect the position change information of the target in space; 2. When the target moves across the scene, the traditional target tracking technology needs to The target in the current scene is compared with the targets in multiple subsequent scenes, and the moving direction of the target is judged based on this. It is not possible to continuously track the target in multiple scenes.

Images