The current surveillance systems must identify the continuous human behaviors to detect various events from video streams. To enhance the performance of event recognition, in this chapter, we propose a distributed low-cost smart cameras system, together with a machine learning technique to detect abnormal events through analyzing the sequential behaviors of a group of people. Our system mainly includes a simple but efficient strategy to organize the behavior sequence, a new indirect encoding scheme to represent a group of people with relatively few features, and a multi-camera collaboration strategy to perform collective decision making for event recognition. Experiments have been conducted and the results confirm the reliability and stability of the proposed system in event recognition.

The current surveillance systems must identify the continuous human behaviors to detect various events from video streams. To enhance the performance of event recognition, in this chapter, we propose a distributed low-cost smart cameras system, together with a machine learning technique to detect abnormal events through analyzing the sequential behaviors of a group of people. Our system mainly includes a simple but efficient strategy to organize the behavior sequence, a new indirect encoding scheme to represent a group of people with relatively few features, and a multi-camera collaboration strategy to perform collective decision making for event recognition. Experiments have been conducted and the results confirm the reliability and stability of the proposed system in event recognition.