Hierarchical human activity recognition system based on R-transform and nonlinear kernel discriminant features

A framework for a video based hierarchical human activity recognition (HAR) system is presented based on efficient feature extraction and dimension reduction techniques R-transform and kernel discriminant analysis (KDA). The hierarchical HAR system is proposed to group similar activities and further improve the recognition rate. A first level system uses R-transform to extract symmetric, scale and translation invariant shape features from the silhouette sequences and KDA is applied on the R-transformed features to increase discrimination among different classes of activities based on their nonlinear representations from different view angles. A second level system is applied selectively to the recognised activities from the first level system to increase further discrimination for the activities with high similarity in postures. The system is validated with a recognition rate of 97.3% for the KTH dataset and 99.1% for the Weizmann dataset. The improved recognition rate for the hierarchical HAR system compared to state of the art on the KTH and Weizmann datasets demonstrates the effectiveness of the proposed system.