Real-Time Continuous Action Detection And Recognition Using Depth Images And Inertial Signals
Keywords
Action recognition from continuous data streams; Real-time continuous action detection; Simultaenous utilization of depth images and inertial signals for action recognition
Abstract
This paper presents an approach to detect and recognize actions of interest in real-time from a continuous stream of data that are captured simultaneously from a Kinect depth camera and a wearable inertial sensor. Actions of interest are considered to appear continuously and in a random order among actions of non-interest. Skeleton depth images are first used to separate actions of interest from actions of non-interest based on pause and motion segments. Inertial signals from a wearable inertial sensor are then used to improve the recognition outcome. A dataset consisting of simultaneous depth and inertial data for the smart TV actions of interest occurring continuously and in a random order among actions of non-interest is studied and made publicly available. The results obtained indicate the effectiveness of the developed approach in coping with actions that are performed realistically in a continuous manner.
Publication Date
8-3-2017
Publication Title
IEEE International Symposium on Industrial Electronics
Number of Pages
1342-1347
Document Type
Article; Proceedings Paper
Personal Identifier
scopus
DOI Link
https://doi.org/10.1109/ISIE.2017.8001440
Copyright Status
Unknown
Socpus ID
85029902727 (Scopus)
Source API URL
https://api.elsevier.com/content/abstract/scopus_id/85029902727
STARS Citation
Dawar, Neha; Chen, Chen; Jafari, Roozbeh; and Kehtarnavaz, Nasser, "Real-Time Continuous Action Detection And Recognition Using Depth Images And Inertial Signals" (2017). Scopus Export 2015-2019. 6970.
https://stars.library.ucf.edu/scopus2015/6970