A human body recognition and tracking method for security system

Abstract

The invention discloses a human body identification and tracking method applied to a security system. The method comprises the steps that a video input device acquires the image information of each frame of a video; a processing unit detects a human body target according to the information of each frame of the video; the processing unit carries out face detection according to the human body targetdetection result; the processing unit carries out feature extraction on a detected face area to acquire a face feature vector; the processing unit matches face feature data and a face feature in a database, and assigns an ID to the detected human body target according to the matching result, and at the same time assigns the ID to the human body target corresponding to the face; and the processingunit compares the ID of the detected human body target in each frame and connects the positions of human body targets with the same ID in different frames to form the movement trajectory of the humanbody target corresponding to the ID. According to the method provided by the invention, real-time face detection and identification can be realized, and target lost or failed tracking can be prevented.

Description

technical field [0001] The invention relates to the field of safety management, in particular to a human body identification and tracking method used in a security system. Background technique [0002] The detection, recognition and tracking technology of human body and human face target has been developed very rapidly in recent years. Although face recognition technology is relatively mature, each existing face recognition algorithm has its limitations. For example, it is difficult for traditional face feature extraction methods to extract face features accurately and automatically. A large amount of training data is required, and it is difficult to cope with real-time face detection and recognition in terms of speed. In terms of object tracking, most of the biometric tracking devices currently on the market still have many problems. For traditional target tracking, if there are too many changes in the characteristics of the human target, such as a person suddenly turning...

AI Technical Summary

Problems solved by technology

For traditional target tracking, if there are too many changes in the characteristics of the human target, such as a person suddenly turning around or taking off his coat, traditional target tracking is easy to lose the target

In addition, when tracking targets that have been detected in different frames, when the targets overlap, or the trajectories of pedestrians cross, etc., the tracking will also fail.

Images