25 October 2016 Vision-based posture recognition using an ensemble classifier and a vote filter
Author Affiliations +
Proceedings Volume 10157, Infrared Technology and Applications, and Robot Sensing and Advanced Control; 101571J (2016) https://doi.org/10.1117/12.2246542
Event: International Symposium on Optoelectronic Technology and Application 2016, 2016, Beijing, China
Abstract
Posture recognition is a very important Human-Robot Interaction (HRI) way. To segment effective posture from an image, we propose an improved region grow algorithm which combining with the Single Gauss Color Model. The experiment shows that the improved region grow algorithm can get the complete and accurate posture than traditional Single Gauss Model and region grow algorithm, and it can eliminate the similar region from the background at the same time. In the posture recognition part, and in order to improve the recognition rate, we propose a CNN ensemble classifier, and in order to reduce the misjudgments during a continuous gesture control, a vote filter is proposed and applied to the sequence of recognition results. Comparing with CNN classifier, the CNN ensemble classifier we proposed can yield a 96.27% recognition rate, which is better than that of CNN classifier, and the proposed vote filter can improve the recognition result and reduce the misjudgments during the consecutive gesture switch.
© (2016) COPYRIGHT Society of Photo-Optical Instrumentation Engineers (SPIE). Downloading of the abstract is permitted for personal use only.
Peng Ji, Peng Ji, Changcheng Wu, Changcheng Wu, Xiaonong Xu, Xiaonong Xu, Aiguo Song, Aiguo Song, Huijun Li, Huijun Li, } "Vision-based posture recognition using an ensemble classifier and a vote filter", Proc. SPIE 10157, Infrared Technology and Applications, and Robot Sensing and Advanced Control, 101571J (25 October 2016); doi: 10.1117/12.2246542; https://doi.org/10.1117/12.2246542
PROCEEDINGS
6 PAGES


SHARE
RELATED CONTENT

Hybrid image recognition architecture
Proceedings of SPIE (June 07 2002)
Image compensation for camera and lighting variability
Proceedings of SPIE (December 18 1996)
Optical pattern recognition
Proceedings of SPIE (November 16 1992)

Back to Top