Kinect depth image enhancement with adaptive joint multi-lateral discrete filters

Abstract

One of the major problems of Kinect depth image is the existence of noise and holes. Thus, it is necessary to enhance depth images for post processing. In this paper, we propose an adaptive joint bilateral/trilateral filter, considering both the depth image and the aligned colour image, to refine the depth edges and remove the noise. Specifically, the pixels around the common boundary of depth edges and colour edges are taken as unreliable pixels due to the perturbations around the depth edges, then a support region and kernel-width adaptive joint bilateral filter considering the colour edge is applied to refine the marked unreliable pixels and the depth edges. For the depth pixels except unreliable pixels, we apply a kernel-width adaptive joint trilateral filter to remove the noise. Experimental results show that our approach outperforms the compared methods in terms of finer depth edges and noise removal.

Keywords:

• Kinect depth
• joint bilateral/trilateral filter
• adaptive support regions
• edge refinement
• denoising

AMS Subject Classification:

• 68U10

Acknowledgements

The authors thank the anonymous referees for their constructive suggestions. The authors would like to thank Prof. Ming-Ting Sun at University of Washington for his valuable discussions. Xizhou Lin would like to acknowledge the fellowship of Postgraduates-oversea Study Program for Building High-Level Universities from the China Scholarship Council.

Notes

No potential conflict of interest was reported by the authors.

Additional information

Funding

This work was supported by the National Natural Science Foundation of China [grant number 61571377], [grant number 61471308].