中国科学院机构知识库网格
Chinese Academy of Sciences Institutional Repositories Grid
首页 机构 成果 学者
  
  1. CAS IR Grid
  2. 计算技术研究所
  3. 中国科学院计算技术研究所
  4. 中国科学院计算技术研究所期刊论文
  5. 英文
Weighted Large Margin Nearest Center Distance-Based Human Depth Recovery With Limited Bandwidth Consumption

文献类型：期刊论文

作者Huang, Meiyu2; Xiang, Xueshuang2; Chen, Yiqiang1,3; Fan, Da2
刊名IEEE TRANSACTIONS ON IMAGE PROCESSING
出版日期2018-12-01
卷号27期号:12页码:5728-5743
关键词Tele-immersive interaction occlusion handling depth recovery distance learning
ISSN号1057-7149
DOI10.1109/TIP.2018.2855414
英文摘要This paper proposes a weighted large margin nearest center (WLMNC) distance-based human depth recovery method for tele-immersive video interaction systems with limited bandwidth consumption. In the remote stage, the proposed method highly compresses the depth data of the remote human into skeletal block structures by learning the WLMNC distance, which is equivalent to downsampling the human depth map at 64x the sampling rate. In the local stage, the method first recovers a rough human depth map based on a WLMNC distance augmented clustering approach and then obtains a fine depth map based on a rough depth-guided autoregressive model to preserve the depth discontinuities and suppress texture copy artifacts. The proposed WLMNC distance is learned by the large margin clustering problem with a weighted hinge loss to balance the clustering accuracy and depth recovery accuracy and is verified to be able to preserve depth discontinuities between skeletal block structures with occlusion. A theoretical analysis is conducted to verify the effectiveness of using the weighted hinge loss. Furthermore, a novel data set containing various types of human postures with self-occlusion is built to benchmark the human depth recovery methods. The quantitative comparison with the state-of-the-art depth recovery methods on the introduced benchmark data set demonstrates the effectiveness of the proposed method for human depth recovery with such a high upsampling rate.
资助项目National Natural Science Foundation of China[61702520] ; National Natural Science Foundation of China[61773383] ; National Natural Science Foundation of China[61572471] ; National Key Research and Development Program of China[2017YFC0803401] ; Beijing Municipal Science and Technology Commission[Z171100000117017] ; Innovation Foundation of Qian Xuesen Laboratory of Space Technology
WOS研究方向Computer Science ; Engineering
语种英语
WOS记录号WOS:000444019600001
出版者IEEE-INST ELECTRICAL ELECTRONICS ENGINEERS INC
源URL[http://119.78.100.204/handle/2XEOYT63/4945]  
专题中国科学院计算技术研究所期刊论文_英文
通讯作者Xiang, Xueshuang
作者单位1.Chinese Acad Sci, Beijing Key Lab Mobile Comp & Pervas Device, Inst Comp Technol, Beijing 100190, Peoples R China
2.China Acad Space Technol, Qian Xuesen Lab Space Technol, Beijing 100094, Peoples R China
3.Univ Chinese Acad Sci, Sch Comp & Control Engn, Beijing 100049, Peoples R China
推荐引用方式
GB/T 7714		 Huang, Meiyu,Xiang, Xueshuang,Chen, Yiqiang,et al. Weighted Large Margin Nearest Center Distance-Based Human Depth Recovery With Limited Bandwidth Consumption[J]. IEEE TRANSACTIONS ON IMAGE PROCESSING,2018,27(12):5728-5743.
APA Huang, Meiyu,Xiang, Xueshuang,Chen, Yiqiang,&Fan, Da.(2018).Weighted Large Margin Nearest Center Distance-Based Human Depth Recovery With Limited Bandwidth Consumption.IEEE TRANSACTIONS ON IMAGE PROCESSING,27(12),5728-5743.
MLA Huang, Meiyu,et al."Weighted Large Margin Nearest Center Distance-Based Human Depth Recovery With Limited Bandwidth Consumption".IEEE TRANSACTIONS ON IMAGE PROCESSING 27.12(2018):5728-5743.

入库方式： OAI收割

来源：计算技术研究所

浏览0
下载0
收藏0
其他版本

除非特别说明，本系统中所有内容都受版权保护，并保留所有权利。