Perimeter Intrusion Detection Based On Intelligent Video Analysis

Monitoring system has become one of the most important means for perimeter intrusion prevention. But most of existing monitoring systems are passive surveillance. In this paper, we propose a method to implement active perimeter intrusion detection by identifying human targets in video images captured by monitoring system. In order to enhance the robustness of detecting postures of human targets, this paper introduces Fourier Descriptor ( FD) and Histogram of Oriented Gradients ( HOG) to realize an effective detection of human bodies with multiple postures captured by fixed cameras. The experiment results confirm that the proposed algorithm has higher recognition rate for detecting human targets with walking, climbing, and jumping postures, and sufficiently meets the requirements of perimeter intrusion detection.