Probabilistic depth map fusion of Kinect and stereo in real-time

Yong Duan*, Mingtao Pei, Yucheng Wang

*Corresponding author for this work

Research output: Chapter in Book/Report/Conference proceedingConference contributionpeer-review

6 Citations (Scopus)

Abstract

This paper proposes a probabilistic framework for real-time depth map fusion of Kinect and stereo. By modeling the depth imaging process as a random experiment, we turn the depth map fusion into a problem of probability density function (pdf) estimation, and the problem can be further decoupled into four parts: fusion space, influence term, visibility term and confidence term. Strategies for each part of the framework are presented to perform real-time fusion of Kinect and stereo. Experimental results demonstrate the effectiveness of the method.

Original languageEnglish
Title of host publication2012 IEEE International Conference on Robotics and Biomimetics, ROBIO 2012 - Conference Digest
Pages2317-2322
Number of pages6
DOIs
Publication statusPublished - 2012
Event2012 IEEE International Conference on Robotics and Biomimetics, ROBIO 2012 - Guangzhou, China
Duration: 11 Dec 201214 Dec 2012

Publication series

Name2012 IEEE International Conference on Robotics and Biomimetics, ROBIO 2012 - Conference Digest

Conference

Conference2012 IEEE International Conference on Robotics and Biomimetics, ROBIO 2012
Country/TerritoryChina
CityGuangzhou
Period11/12/1214/12/12

Fingerprint

Dive into the research topics of 'Probabilistic depth map fusion of Kinect and stereo in real-time'. Together they form a unique fingerprint.

Cite this