24 March 2017 Accurate per-pixel hand detection from a single depth image
Author Affiliations +
Optical Engineering, 56(3), 033107 (2017). doi:10.1117/1.OE.56.3.033107
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, Zhijiang Zhang, Haiwei Zhang, 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
Submission: Received 26 November 2016; Accepted 9 March 2017


RGB color model


Image segmentation

Motion models

Optical engineering

Human-computer interaction


Temporally consistent segmentation of point clouds
Proceedings of SPIE (June 03 2014)
Illumination-invariant hand gesture recognition
Proceedings of SPIE (September 09 2015)
Face tracking based on grey prediction
Proceedings of SPIE (November 15 2007)
Motion based situation recognition in group meetings
Proceedings of SPIE (January 28 2010)

Back to Top