Automatic Video Surveillance Using Statistical Analysis of Temporal Posture Sequences

Purpose: The problem of automatic recognition of human activities is among the most important and challenging open areas of research in Computer Vision due to the wide range of possible applications such as surveillance, advanced human-computer interactions, monitoring, etc. This paper presents statistical computer vision approaches to automatically recognize human activities. Methodology/Approach: The human activity recognition process is performed in three steps: first of all human blobs are segmented by motion analysis; then the human body posture is estimated and finally, for each activity to be recognized, a temporal model of the detected posture series is generated by Discrete Hidden Markov Models (DHMM). Findings: The system was tested on image sequences acquired in a real archaeological site while some people simulated both legal and illegal actions. Four kinds of activities were automatically classified with a high percentage of correct detections. Research limitations/implications The proposed approach provides efficient solutions to some of the most common problems in the human activity recognition research field: high detailed image requirement, sequence alignment and intensive user interaction in the training phase. The main constraint of this framework is that the posture estimation approach is not completely view independent; Practical implications: Time performance tests were very encouraging for the use of the proposed method in real time surveillance applications; the Originality/value of paper: The proposed framework can work with low cost cameras with large view focal lenses; it does not need any a priori knowledge of the scene and no intensive user interaction bis required in the early training phase;