Kinect-like depth denoising
- 1 May 2012
- conference paper
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- No. 02714302,p. 512-515
Abstract
Accuracy and stability of Kinect-like depth data is limited by its generating principle. In order to serve further applications with high quality depth, the preprocessing on depth data is essential. In this paper, we analyze the characteristics of the Kinect-like depth data by examing its generation principle and propose a spatial-temporal denoising algorithm taking into account its special properties. Both the intra-frame spatial correlation and the inter-frame temporal correlation are exploited to fill the depth hole and suppress the depth noise. Moreover, a divisive normalization approach is proposed to assist the noise filtering process. The 3D rendering results of the processed depth demonstrates that the lost depth is recovered in some hole regions and the noise is suppressed with depth features preserved.Keywords
This publication has 8 references indexed in Scilit:
- ACCURACY ANALYSIS OF KINECT DEPTH DATAThe International Archives of the Photogrammetry, Remote Sensing and Spatial Information Sciences, 2012
- Spatio-temporal consistency in video disparity estimation2011
- A gentle introduction to bilateral filtering and its applications2007
- A Non-Local Algorithm for Image Denoising2005
- Bilateral mesh denoising2003
- A stereo matching algorithm with an adaptive window: theory and experiment2002
- Dense Disparity Map Estimation Respecting Image Discontinuities: A PDE and Scale-Space Based ApproachJournal of Visual Communication and Image Representation, 2002
- Nonlinear total variation based noise removal algorithmsPhysica D: Nonlinear Phenomena, 1992