RGB-D-based human motion recognition with deep learning: A survey
RGB-D-based human motion recognition with deep learning: A survey
复制标题
基于 RGB-D 的深度学习人体运动识别：一项调查
DOI：
10.1016/j.cviu.2018.04.007
复制
发表时间：
2018-06-01
影响因子：
4.5
通讯作者：
Escalera, Sergio
中科院分区：
文献类型：
--
作者：
Wang, Pichao;Li, Wanqing;Escalera, Sergio
人体运动识别是以人为中心的研究活动中最重要的分支之一。近年来，基于RGB-D数据的运动识别引起了人们的广泛关注。沿着人工智能的发展，深度学习技术在计算机视觉领域取得了巨大的成功。特别是，卷积神经网络（CNN）在基于图像的任务方面取得了巨大成功，而递归神经网络（RNN）则以基于序列的问题而闻名。具体而言，基于CNN和RNN架构的深度学习方法已被用于使用RGB-D数据的运动识别。本文详细介绍了基于RGB-D的运动识别的最新进展。综述的方法大致分为四组，这取决于识别所采用的模式：基于RGB的，基于深度的，基于RGB+ D的。作为一项专注于深度学习在基于RGB-D的运动识别中的应用的调查，我们明确讨论了现有技术的优点和局限性。重点介绍了视频序列中时空结构信息的编码方法，并讨论了未来的研究方向。
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.