Skip to main content

Research Repository

Advanced Search

Improved Depth Recovery In Consumer Depth Cameras via Disparity Space Fusion within Cross-spectral Stereo

Payen de La Garanderie, G.; Breckon, T.P.

Improved Depth Recovery In Consumer Depth Cameras via Disparity Space Fusion within Cross-spectral Stereo Thumbnail


Authors

G. Payen de La Garanderie



Contributors

Michel Valstar
Editor

Andrew French
Editor

Tony Pridmore
Editor

Abstract

We address the issue of improving depth coverage in consumer depth cameras based on the combined use of cross-spectral stereo and near infra-red structured light sensing. Specifically we show that fusion of disparity over these modalities, within the disparity space image, prior to disparity optimization facilitates the recovery of scene depth information in regions where structured light sensing fails. We show that this joint approach, leveraging disparity information from both structured light and cross-spectral sensing, facilitates the joint recovery of global scene depth comprising both texture-less object depth, where conventional stereo otherwise fails, and highly reflective object depth, where structured light (and similar) active sensing commonly fails. The proposed solution is illustrated using dense gradient feature matching and shown to outperform prior approaches that use late-stage fused cross-spectral stereo depth as a facet of improved sensing for consumer depth cameras.

Citation

Payen de La Garanderie, G., & Breckon, T. (2014). Improved Depth Recovery In Consumer Depth Cameras via Disparity Space Fusion within Cross-spectral Stereo. In M. Valstar, A. French, & T. Pridmore (Eds.), Proceedings of the British Machine Vision Conference (417.1-417.12). https://doi.org/10.5244/C.28.110

Conference Name Proceedings of the British Machine Vision Conference
Publication Date Sep 1, 2014
Deposit Date Dec 9, 2014
Publicly Available Date Feb 4, 2015
Pages 417.1-417.12
Book Title Proceedings of the British Machine Vision Conference.
DOI https://doi.org/10.5244/C.28.110
Keywords rgb-d, consumer depth camera, kinect, depth improvment, disparity space image, multimodal stereo, multi-modal, infrared colour stereo, depth map improvement, hole filling, structured light, disparity filling, disparity improvement, infrared stereo vision
Public URL https://durham-repository.worktribe.com/output/1154173
Publisher URL https://web.archive.org/web/20220706011347/https://www.bmva.org/bmvc/2014/papers/paper107/index.html
Related Public URLs https://breckon.org/toby/publications/papers/pdlg14depth.pdf

Files





You might also like



Downloadable Citations