Human activity recognition for video surveillance using sequences of postures

The Human activities recognition has become a research area of great interest as it has many potential applications; including automated surveillance, sign language interpretation and human-computer interfaces. In recent years, an extensive research has been conducted in this field. This paper presents a part of a novel a Human posture recognition system for video surveillance using one static camera. The training and testing stages were implemented using four different classifiers which are K Means, Fuzzy C Means, Multilayer Perceptron Self-Organizing Maps and Feedforward Neural networks. The accuracy recognition of used classifiers is calculated. The results indicate that Self-Organizing Maps shows the highest recognition rate. Moreover, results show that supervised learning classifiers tend to perform better than unsupervised classifiers for the case of human posture recognition. Furthermore, for each individual classifier, the recognition rate has been found to be proportional to the number of training postures. Performance comparisons between the proposed system and existing similar systems were also shown.