Integrating Entropy Skeleton Motion Maps and Convolutional Neural Networks for Human Action Recognition

Nour El-Din El-Madany, Yifeng He, Ling Guan

Abstract: This paper presents an effective method to represent the information of skeleton sequences as images, referred to skeleton motion maps (SMM) and employ convolutional neural networks to recognize the human actions. The proposed approach employs Entropy SMM which captures the temporal evolution of action leading to more effective and discriminative representation. In order to verify the effectiveness of the proposed method, several experiments were conducted on UTD Multimodal Human Action Dataset (UTD-MHAD), Kinect Action Recognition Dataset (KARD), and Multimodal Action Database (MAD) datasets. The Experimental results show the superiority of the proposed method over the existing work.