Research Area: Machine Learning
Human motion recognition is one of the most important branches of human-centered research activities. In recent years, motion recognition based on RGB-D data has attracted much attention. Along with the development in artificial intelligence, deep learning techniques have gained remarkable success in computer vision. In particular, convolutional neural networks (CNN) have achieved great success for image-based tasks, and recurrent neural networks (RNN) are renowned for sequence-based problems. Specifically, deep learning methods based on the CNN and RNN architectures have been adopted for motion recognition using RGB-D data. In this paper, a detailed overview of recent advances in RGB-D-based motion recognition is presented. The reviewed methods are broadly categorized into four groups, depending on the modality adopted for recognition: RGB-based, depth-based, skeleton-based and RGB+D-based. As a survey focused on the application of deep learning to RGB-D-based motion recognition, we explicitly discuss the advantages and limitations of existing techniques. Particularly, we highlighted the methods of encoding spatial-temporal-structural information inherent in video sequence, and discuss potential directions for future research.
Keywords:
Rgb-D
Human Motion Recognition
Deep Learning
convolutional neural networks
Machine Learning
Author(s) Name: Pichao Wang, Wanqing Li, Philip Ogunbona, Jun Wan, Sergio Escalera
Journal name: Computer Vision and Image Understanding
Conferrence name:
Publisher name: Elsevier
DOI: 10.1016/j.cviu.2018.04.007
Volume Information: Volume 171, June 2018, Pages 118-139
