摘要
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.
源语言 | 英语 |
---|---|
主期刊名 | 2012 IEEE International Conference on Robotics and Biomimetics, ROBIO 2012 - Conference Digest |
页 | 2317-2322 |
页数 | 6 |
DOI | |
出版状态 | 已出版 - 2012 |
活动 | 2012 IEEE International Conference on Robotics and Biomimetics, ROBIO 2012 - Guangzhou, 中国 期限: 11 12月 2012 → 14 12月 2012 |
出版系列
姓名 | 2012 IEEE International Conference on Robotics and Biomimetics, ROBIO 2012 - Conference Digest |
---|
会议
会议 | 2012 IEEE International Conference on Robotics and Biomimetics, ROBIO 2012 |
---|---|
国家/地区 | 中国 |
市 | Guangzhou |
时期 | 11/12/12 → 14/12/12 |
指纹
探究 'Probabilistic depth map fusion of Kinect and stereo in real-time' 的科研主题。它们共同构成独一无二的指纹。引用此
Duan, Y., Pei, M., & Wang, Y. (2012). Probabilistic depth map fusion of Kinect and stereo in real-time. 在 2012 IEEE International Conference on Robotics and Biomimetics, ROBIO 2012 - Conference Digest (页码 2317-2322). 文章 6491315 (2012 IEEE International Conference on Robotics and Biomimetics, ROBIO 2012 - Conference Digest). https://doi.org/10.1109/ROBIO.2012.6491315