Intelligent video monitoring system

Abstract

The invention provides an intelligent video monitoring system. The intelligent video monitoring system comprises a plurality of cameras for acquiring video streams in a monitoring space range in real time, a video microprocessor for processing the video streams of the plurality of cameras, and a monitoring center connected with the video microprocessor through a wireless network, the video microprocessor comprises a video data acquisition module, a video data preprocessing module, a video data feature extraction module, an anomaly detection model establishment module and an anomaly judgment module. According to the invention, the video data feature extraction module carries out modeling on a motion change trend between continuous frames through multi-example division and by adopting a time sequence, so that the problem of different perceptions of motion speeds at different visual angles is solved, and the anomaly detection model establishment module carries out modeling on a feature space through a non-parametric model based on clustering. The problem that training data category labels are not clear is solved, the model is updated online during modeling and detection, and the problem that abnormal event definition is fuzzy is solved.

Description

technical field [0001] The invention belongs to the technical field of video monitoring, and in particular relates to an intelligent video monitoring system. Background technique [0002] Video surveillance is an important part of the security system. Traditional surveillance systems include front-end cameras, transmission cables, and video surveillance platforms. Cameras can be divided into network digital cameras and analog cameras, which can be used as front-end video image signal collection. It is intuitive, accurate, timely and informative, and is widely used in many occasions. Existing video surveillance systems calmly deal with various event detection in complex environments and scenes by combining image processing technology and artificial intelligence technology. Significance, and make corresponding distinctions to find out the corresponding abnormal motion events and alert the management personnel. Therefore, for the abnormal event detection algorithm, in additio...

AI Technical Summary

Problems solved by technology

[0008]Through the above technical solution, the video data feature extraction module divides multiple examples and uses time series to model the motion trend between consecutive frames, solving the problem of different viewing angles. For the problem of different perception of motion speed, the anomaly detection model building module uses a cluster-based non-parametric model to model the feature space, which solves the problem of unclear training data category labels

Images