Human Actions Tracking and Recognition Based on Body Parts Detection via Artificial Neural Network

Human body action recognition has drawn a good deal of interest in the community of computer vision, owing to its wide range of applications. Recently, the video / image sequence base action recognition techniques are believed to be ideal for its efficiency and lower cost compared to other techniques such as the ambient sensor and the wearable sensor. However, given to a large amount of variation in human pose and image quality, reliable detection of human action is still a very challenging job for scientists. In this document, we used linear discriminant analysis for the generation of features from the body parts detected. The primary goal of this study is to combine linear discriminant analysis with an artificial neural network for precise human action detection and recognition. Our proposed mechanism detects complicated human actions in two state-of-the-art datasets, i.e. KTH-dataset and Weizmann Human Action. We obtained multidimensional features from twelve body parts, which are estimated from body models. These multidimensional characteristics are used as inputs for the artificial neural network. To access the efficiency of our suggested method, we compared the outcomes with other state-of-the-art classifiers. Experimental results show that our proposed technique is reliable and applicable in health exercise systems, smart surveillance, e-learning, abnormal behavioral detection, protection for child abuse, care of the elderly people, virtual reality, intelligent image retrieval and human computer interaction.