Motion-detection-based human body abnormal behavior detection method

Abstract

The invention relates to a motion-detection-based human body abnormal behavior detection method for scene detection of a fixed camera. Motion detection is carried out by using a way of combination of a background subtraction method and a motion historical image, a motion foreground is extracted and background updating is carried out by sing a mask obtained by using a frame difference method, and post processing operation is carried out and a foreground of a human body is filtered; with a method based on context information matching between video frames, and human bodies in a previous frame and a current frame are matched; with combination of an originally-set abnormal condition, system decision is carried out by using geometrical features of a rectangular frame and a center of mass, whether the human body in motion has an abnormal behavior is determined, and an invasion direction is determined; and then counting of the abnormal people and human body track marking after abnormal behaviors are carried out, thereby achieving an objective of a video analysis. According to the invention, the algorithm complexity is low and the portability is high; and the real-time performance is good and the detection rate accuracy is improved.

Description

technical field [0001] The invention relates to a method for detecting abnormal human behavior based on motion detection, which is used in security monitoring fields such as power stations and prisons, as well as video digital image analysis and understanding. It belongs to the field of computer vision and artificial intelligence technology. Background technique [0002] Intelligent video monitoring technology is an important application field of computer vision, mainly used in banks, airports and other occasions with high security requirements. The collected video data can automatically judge whether there is an abnormal behavior, whether it is necessary to call the police, and notify the relevant personnel. This method greatly reduces labor costs and ensures the safety of the monitoring site. [0003] Abnormal behavior detection is generally divided into two categories, one is based on motion detection and target tracking. Due to the complexity and diversity of the enviro...

AI Technical Summary

Problems solved by technology

[0003] Abnormal behavior detection is generally divided into two categories, one is based on motion detection and target tracking. Due to the complexity and diversity of the environment, there is currently no algorithm that can be applied to various environments. Many current researches are also based on When focusing on improving the accuracy and robustness of the detection and tracking algorithm, the time-consuming of the algorithm will often increase. Therefore, it is necessary to improve and select the existing algorithm based on the characteristics of intelligent surveillance video.

The other is a detection method based on statistical thinking, using machine learning methods to establish a database of abnormal behaviors, so as to match videos and judge whether abnormal behaviors occur. The disadvantage of this method is that due to the diversity of abnormal behaviors, the detection results The accuracy depends largely on the quantity and quality of samples

In addition, the training and learning process takes a lot of time, and it is difficult to meet the requirements in practical applications.

Images