Multi-target detection and tracking method for speed dome camera control strategy

Abstract

The invention discloses a multi-target detection and tracking method for a speed dome camera control strategy. The method mainly comprises the following steps: preprocessing acquired bolt video image data, removing surplus frames of image, carrying out foreground point detection on the [2, N] frame of image, updating a background model, carrying out communicated region analysis, computing target characteristics, computing and comparing similarity of targets in adjacent frames, carrying out multi-characteristic similarity fusion, carrying out optimal matching, finding out targets, updating states and updating target characteristics. The method has the advantages of improving the accuracy of target tracking, dealing with separation and integration events very well and finding out target IDs related to the events; in addition, the similarity accuracy can be effectively improved so that the precision in the matching process is improved, the matching accuracy is enhanced greatly and the mismatching rate is lowered greatly; the IDs of targets after integration and separation can be found again accurately; the algorithm real-time property is high, the operation efficiency is very high, the required memory is less, and therefore, the method can be implemented in a front-end embedded environment.

Description

technical field [0001] The invention relates to the field of intelligent video monitoring, in particular to a multi-target detection and tracking method used in the dome camera control strategy. Background technique [0002] With the improvement of computer vision technology, computer processing ability, and the increase of public safety precautions, intelligent video surveillance technology has developed rapidly. Intelligent video surveillance mainly uses machine vision technology to actively process, analyze and understand the interested targets in the video scene, and detect, track and identify the targets in the scene without human intervention, so as to achieve automatic discovery, automatic Tracking and automated alerting purposes. [0003] Collaborative monitoring technology of gun camera and dome camera is one of the main development directions of intelligent video surveillance technology. This technology automatically analyzes the image sequence obtained by the hi...

AI Technical Summary

Problems solved by technology

[0004] The traditional single bolt or single dome passive monitoring technology can no longer meet the growing monitoring needs. The existing technology mainly has the following defects:

[0005] 1) For large scenes and high-complexity camera video, when the multi-target detection and tracking algorithm is processed, the accuracy and precision of target tracking are relatively low, resulting in low control accuracy of the dome camera, making it impossible for the target to be in the center of the dome camera ;

[0006] 2) When the active target is partially or completely covered, it is difficult to recover the target ID. When multiple targets are merged and separated from each other, the target ID cannot be recovered;

[0007] 3) The complexity of the multi-target detection and tracking algorithm is high, which cannot meet the requirements of real-time control of the dome camera

[0009] 1) The monitoring scene is large, the target is far away from the gun, and the amount of target information is very small;

[0010] 2) The scene is very complex (people, motor vehicles, non-motor vehicles, etc.), it is impossible to establish a unified model, and the movement of the moving target is random;

[0011] 3) The system requires real-time processing, which is limited by the performance of the front-end processor. On the premise of meeting the real-time requirements, algorithms with relatively high algorithm complexity cannot be used

Images