AFE-CNN: 3D Skeleton-based Action Recognition with Action Feature Enhancement
This work addresses the problem of efficient and accurate action recognition from 3D skeleton data for applications in surveillance and human-computer interaction, representing an incremental improvement over prior methods.
The paper tackles the limitations of existing 3D skeleton-based action recognition methods by introducing AFE-CNN, which enhances action features from multiple perspectives to improve robustness and accuracy on challenging actions, while using a lightweight CNN to reduce computational burden, achieving outstanding performance on benchmark datasets like NTU RGB+D and UTKinect-Action3D.
Existing 3D skeleton-based action recognition approaches reach impressive performance by encoding handcrafted action features to image format and decoding by CNNs. However, such methods are limited in two ways: a) the handcrafted action features are difficult to handle challenging actions, and b) they generally require complex CNN models to improve action recognition accuracy, which usually occur heavy computational burden. To overcome these limitations, we introduce a novel AFE-CNN, which devotes to enhance the features of 3D skeleton-based actions to adapt to challenging actions. We propose feature enhance modules from key joint, bone vector, key frame and temporal perspectives, thus the AFE-CNN is more robust to camera views and body sizes variation, and significantly improve the recognition accuracy on challenging actions. Moreover, our AFE-CNN adopts a light-weight CNN model to decode images with action feature enhanced, which ensures a much lower computational burden than the state-of-the-art methods. We evaluate the AFE-CNN on three benchmark skeleton-based action datasets: NTU RGB+D, NTU RGB+D 120, and UTKinect-Action3D, with extensive experimental results demonstrate our outstanding performance of AFE-CNN.