Human action recognition on depth dataset

Human action recognition is a hot research topic; however, the change in shapes, the high variability of appearances, dynamitic background, potential occlusions in different actions and the image limit of 2D sensor make it more difficult. To solve these problems, we pay more attention to the depth channel and the fusion of different features. Thus, we firstly extract different features for depth image sequence, and then, multi-feature mapping and dictionary learning model (MMDLM) is proposed to deeply discover the relationship between these different features, where two dictionaries and a feature mapping function are simultaneously learned. What is more, these dictionaries can fully characterize the structure information of different features, while the feature mapping function is a regularization term, which can reveal the intrinsic relationship between these two features. Large-scale experiments on two public depth datasets, MSRAction3D and DHA, show that the performances of these different depth features have a big difference, but they are complementary. Further, the features fusion by MMDLM is very efficient and effective on both datasets, which is comparable to the state-of-the-art methods.