标题:Estimation of Kinect depth confidence through self-training
作者:Song, Xibin; Zhong, Fan; Wang, Yanke; Qin, Xueying
通讯作者:Zhong, F
作者机构:[Song, Xibin; Zhong, Fan; Wang, Yanke; Qin, Xueying] Shandong Univ, Sch Comp Sci & Technol, Jinan 250100, Peoples R China.; [Qin, Xueying] Shandong 更多
会议名称:31st CGI conference
会议日期:JUN 10-13, 2014
来源:VISUAL COMPUTER
出版年:2014
卷:30
期:6-8
页码:855-865
DOI:10.1007/s00371-014-0965-y
关键词:Depth map; Kinect; Confidence prediction; RGB-D; Learning
摘要:All depth data captured by Kinect devices are noisy, and sometimes even lost or shifted, especially around the edges of the depth. In this paper, we propose an approach to generate a per-pixel confidence measurement for each depth map captured by Kinect devices in indoor environments through supervised learning. Several distinguishing features from both the color images and depth maps are selected to train depth map estimators using Random Forest regressor. Using this estimator, we can predict a confidence map of any depth map captured by Kinect devices. Usage of other devices, such as an industrial laser scanner, is unnecessary, making the implementation more convenient. The experiments demonstrate precise confidence prediction of the depth.
收录类别:CPCI-S;EI;SCOPUS;SCIE
WOS核心被引频次:8
Scopus被引频次:11
资源类型:会议论文;期刊论文
原文链接:https://www.scopus.com/inward/record.uri?eid=2-s2.0-84902189578&doi=10.1007%2fs00371-014-0965-y&partnerID=40&md5=212a9925a3fdbf985696abde6bf8e308
TOP