Intelligent human posture recognition in video sequences

• Main Authors: Khalifa, Othman Omran, Htike Ali, Kyaw Kyaw, Lai, Weng Kai
• Format: Conference or Workshop Item
• Language: English
• Published: 2010
• Subjects: TK7800 Electronics. Computer engineering. Computer hardware. Photoelectronic devices
• Online Access: http://irep.iium.edu.my/23110/1/p90.pdf; http://irep.iium.edu.my/23110/; http://www.iium.edu.my/irie/10/

Human posture recognition is gaining increasing attention in the field of computer vision due to its promising applications in the areas of personal health care, environmental awareness, human-computerinteraction and surveillance systems. Human posture recognition in video sequences is a challenging task which is part of the more general problem of video sequence interpretation. In this project, an intelligent human posture recognition system using a single static camera is proposed. The project consists of two stages: the first stage is training and evaluation and the second is deployment. In the first stage, the system is trained and evaluated using a dataset of human postures to ‘teach’ the system to classify human postures for any future inputs. When the training and evaluation process is deemed satisfactory as measured by recognition rates, the trained system is then deployed to recognize human postures in any input video sequence. In the training stage, to obtain the human posture datasets, video sequences have been recorded and preprocessed to extract human silhouettes. The training and testing were performed using four different classifiers which are Multilayer Perceptron Feedforward Neural networks, SelfOrganizing Maps, Fuzzy C Means and K Means. The recognition rates (accuracies) of those classifiers were then compared and results indicate that MLP gives the highest. Performance comparisons between the proposed systems and existing systems were also carried out.