RGB-D sensing based human action and interaction analysis: A survey. (October 2019)

• Record Type: Journal Article
• Authors: Liu, Bangli; Cai, Haibin; Ju, Zhaojie; Liu, Honghai
• Is Part Of: Pattern recognition. Volume 94(2019:Oct.)
• Page Start: 1
• Page End: 12
• Publication Date: 2019-10
• Subjects: Survey -- RGB-D sensing -- Action recognition -- Interaction recognition -- Deep learning; Pattern perception -- Periodicals; Perception des structures -- Périodiques; Patroonherkenning; 006.4
• DOI: 10.1016/j.patcog.2019.05.020
• Languages: English
• ISSNs: 0031-3203

Abstract

Highlights: A thorough overview of human action and interaction recognition using RGB-D sensors is presented. A comprehensive analysis of both hand-crafted and deep learning based methods is conducted. The challenges of human activity recognition using RGB-D data and existing solutions are discussed. Abstract: Human activity recognition has been actively studied in the last three decades. Compared to human action performed by a single person, human interaction is more complex due to the involvement of more subjects and the interdependence between them. Recently, motivated by the remarkable success of deep learning techniques, many learning-based feature representations have been developed for activity recognition. This paper provides a comprehensive review of human action and interaction recognition methods, covering both hand-crafted features and learning-based features, with a special focus on data captured by RGB-D sensors. Furthermore, this review reveals practical challenges in human activity analysis along with their promising solutions and potential future directions.