Event detection in video using motion analysis

Digital video is being used widely in a variety of applications such as entertainment, surveillance and security. Large amount of video in surveillance and security requires systems capable of processing video to automatically detect and recognize events to alleviate the load on humans and enable preventive actions when events are detected. The main objective of this work is the analysis of computer vision techniques and algorithms to perform automatic detection of specific events in video sequences. This paper presents a surveillance system based on motion analysis and introduces the idea of event probability zones. Advantages, limitations, capabilities and possible solution alternatives are also discussed. The result is a system capable of detecting events of objects moving in opposing direction in a predefined context or running in the scene; the results showed precision greater than 50% and recall greater than 80%.