24 March 2017 Accurate per-pixel hand detection from a single depth image
Author Affiliations +
Abstract
Per-pixel hand detection plays an important role in many human–computer interaction applications while accurate and robust hand detection remains a challenging task due to the large appearance variance of hands in images. We introduce a per-pixel hand detection system using one single depth image. We propose a circle sampling depth-context feature for hand regions representation, and a multilayered hand detection model is built for hand regions detection. Finally, a postprocessing step based on spatial constraints is applied to refine the detection results and further improve the detection accuracy. We evaluate the accuracy of our method on a public dataset and investigate the effect of key parameters in our system. The results of the qualitative and quantitative evaluation reveal that the proposed method performs well on per-pixel hand detection tasks. Furthermore, an additional experiment on hand parts segmentation proves that the depth-context feature has a generalization power for more complex multiclass classification tasks.
© 2017 Society of Photo-Optical Instrumentation Engineers (SPIE)
Zhao Zhang, Zhao Zhang, Zhijiang Zhang, Zhijiang Zhang, Haiwei Zhang, Haiwei Zhang, Dan Zeng, Dan Zeng, } "Accurate per-pixel hand detection from a single depth image," Optical Engineering 56(3), 033107 (24 March 2017). https://doi.org/10.1117/1.OE.56.3.033107 . Submission: Received: 26 November 2016; Accepted: 9 March 2017
Received: 26 November 2016; Accepted: 9 March 2017; Published: 24 March 2017
JOURNAL ARTICLE
11 PAGES


SHARE
RELATED CONTENT

Stable and real time hand gesture recognition based on RGB...
Proceedings of SPIE (December 18 2013)
Temporally consistent segmentation of point clouds
Proceedings of SPIE (June 02 2014)
Scene-based scalable video summarization
Proceedings of SPIE (November 25 2003)

Back to Top