Multi-person abnormal behavior detection method based on security monitoring video data

Abstract

The invention provides a multi-person abnormal behavior detection method based on security monitoring video data. According to the method, a standard AV output signal of a monitoring camera is acquired; pedestrian characteristics are extracted, and coarse detectors, coarse pedestrian ROIs and precise ROIs are respectively acquired; pedestrian behavior tracking is carried out, a particle filtering method is employed to respectively surround each tracking target of a video into a rectangular frame, a multi-order autoregression process mathematics model is established for state transferring of each tracking target, and a state transferring model for describing actual motion situations of motion targets is acquired; under the particle filtering framework, a particle filtering human body tracking method integrated with color and shape characteristics is acquired; abnormal-pedestrian classification is carried out, and optical flow characteristics of the precise ROIs are calculated; each frame of gray-scale image in the monitoring video flow is set to be a Markov random field ; characteristics of pedestrians determined to have abnormal traffic behaviors in video monitoring scenes are extracted, a continuous hidden Markov model is established, and the abnormal behaviors are identified.

Description

technical field [0001] The invention relates to a multi-person abnormal behavior detection method based on security monitoring video data, which belongs to the field of 3S integration application. Background technique [0002] Perception and recognition of human behavior in complex environments is one of the hot and difficult topics in intelligent video surveillance research. Its task is to use cameras to perform real-time monitoring and scene interpretation of continuous and transient objects in a specific environment, and to understand and predict context-related objects. Behaviors and events, and interact with observed objects based on information obtained from sensors, are of great value in applications such as detection, monitoring, management, and command in public facilities, commercial, transportation, and military scenarios. The ever-increasing social security requirements have created the need to monitor many environments, making the research and application of vid...

AI Technical Summary

Problems solved by technology

Therefore, the software system based on the visual perception network intelligent environment needs to solve three key interrelated technical problems: one is the multi-camera control model for multi-scale behavior information perception; the other is multi-cue fusion technology for behavior detection and tracking; It is a context-based method for analysis and interpretation of actions and activities, but there is currently no good solution

Images