ReHAR: Robust and Efficient Human Activity Recognition
This work addresses the challenge of efficient and accurate human activity recognition for applications in video analysis, though it appears incremental as it builds on existing methods like optical flow and LSTMs.
The paper tackles the problem of predicting both single-person and group activities in videos by proposing ReHAR, a robust and efficient human activity recognition scheme, which achieves higher accuracy with an order of magnitude shorter computation time compared to state-of-the-art methods on datasets like NCAA Basketball and UCFSports Action.
Designing a scheme that can achieve a good performance in predicting single person activities and group activities is a challenging task. In this paper, we propose a novel robust and efficient human activity recognition scheme called ReHAR, which can be used to handle single person activities and group activities prediction. First, we generate an optical flow image for each video frame. Then, both video frames and their corresponding optical flow images are fed into a Single Frame Representation Model to generate representations. Finally, an LSTM is used to pre- dict the final activities based on the generated representations. The whole model is trained end-to-end to allow meaningful representations to be generated for the final activity recognition. We evaluate ReHAR using two well-known datasets: the NCAA Basketball Dataset and the UCFSports Action Dataset. The experimental results show that the pro- posed ReHAR achieves a higher activity recognition accuracy with an order of magnitude shorter computation time compared to the state-of-the-art methods.