Event-based Timestamp Image Encoding Network for Human Action Recognition and Anticipation
This work addresses human action understanding for applications like robotics or surveillance by leveraging event cameras, though it appears incremental as it builds on existing encoding and network methods.
The paper tackles human action recognition and anticipation using event camera data by proposing a timestamp image encoding 2D network and a future timestamp image generator, achieving performance comparable to RGB-based benchmarks on real-world action recognition and state-of-the-art results on gesture recognition, with the generator improving prediction accuracy for incomplete actions.
Event camera is an asynchronous, high frequency vision sensor with low power consumption, which is suitable for human action understanding task. It is vital to encode the spatial-temporal information of event data properly and use standard computer vision tool to learn from the data. In this work, we propose a timestamp image encoding 2D network, which takes the encoded spatial-temporal images with polarity information of the event data as input and output the action label. In addition, we propose a future timestamp image generator to generate futureaction information to aid the model to anticipate the human action when the action is not completed. Experiment results show that our method can achieve the same level of performance as those RGB-based benchmarks on real world action recognition,and also achieve the state of the art (SOTA) result on gesture recognition. Our future timestamp image generating model can effectively improve the prediction accuracy when the action is not completed. We also provide insight discussion on the importance of motion and appearance information in action recognition and anticipation.