Human action recognition has gained popularity because of its wide applicability, such as in patient monitoring systems, surveillance systems, and a wide diversity of systems that contain interactions between people and electrical devices, including human computer interfaces. The proposed method includes sequential stages of object segmentation, feature extraction, action detection and then action recognition. Effective results of human actions using different features of unconstrained videos was a challenging task due to camera motion, cluttered background, occlusions, complexity of human movements, and variety of same actions performed by distinct subjects. Thus, the proposed method overcomes such problems by using the fusion of features concept for the development of a powerful human action descriptor. This descriptor is modified to create a visual word vocabulary (or codebook) which yields a Bag-of-Words representation. The True Positive Rate (TPR) and False Positive Rate (FPR) measures gave a true indication about the proposed HAR system. The computed Accuracy (Ar) and the Error (misclassification) Rate (Er) reveal the effectiveness of the system with the used dataset.
Merging linear discriminant analysis with Bag of Words model for human action recognition
