RGB-D joint modelling with scene geometric information for indoor semantic segmentation
文献类型:期刊论文
作者 | Liu, Hong; Wu, Wenshan; Wang, Xiangdong; Qian, Yueliang |
刊名 | MULTIMEDIA TOOLS AND APPLICATIONS
![]() |
出版日期 | 2018-09-01 |
卷号 | 77期号:17页码:22475-22488 |
关键词 | RGB-D Gravity direction Semantic segmentation CRF |
ISSN号 | 1380-7501 |
DOI | 10.1007/s11042-018-6056-8 |
英文摘要 | This paper focuses on the problem of RGB-D semantic segmentation for indoor scenes. We introduce a novel gravity direction detection method based on vertical lines fitting combined 2D vision information and 3D geometric information to improve the original HHA depth encoding. Then to fuse two-stream networks of deep convolutional networks from RGB and depth encoding, we propose a joint modelling method by learning a weighted summing layer to fuse the prediction results. Finally, to refine the pixel-wise score maps, we adopt fully-connected CRF as a post-processing and propose a pairwise potential function combined normal kernel to explore geometric information. Experimental results show our proposed approach achieves state-of-the-art performance of RGB-D semantic segmentation on public dataset. |
资助项目 | Beijing Natural Science Foundation[4142051] |
WOS研究方向 | Computer Science ; Engineering |
语种 | 英语 |
WOS记录号 | WOS:000441364500039 |
出版者 | SPRINGER |
源URL | [http://119.78.100.204/handle/2XEOYT63/5093] ![]() |
专题 | 中国科学院计算技术研究所期刊论文_英文 |
通讯作者 | Liu, Hong |
作者单位 | Chinese Acad Sci, Inst Comp Technol, Beijing Key Lab Mobile Comp & Pervas Device, Beijing 100190, Peoples R China |
推荐引用方式 GB/T 7714 | Liu, Hong,Wu, Wenshan,Wang, Xiangdong,et al. RGB-D joint modelling with scene geometric information for indoor semantic segmentation[J]. MULTIMEDIA TOOLS AND APPLICATIONS,2018,77(17):22475-22488. |
APA | Liu, Hong,Wu, Wenshan,Wang, Xiangdong,&Qian, Yueliang.(2018).RGB-D joint modelling with scene geometric information for indoor semantic segmentation.MULTIMEDIA TOOLS AND APPLICATIONS,77(17),22475-22488. |
MLA | Liu, Hong,et al."RGB-D joint modelling with scene geometric information for indoor semantic segmentation".MULTIMEDIA TOOLS AND APPLICATIONS 77.17(2018):22475-22488. |
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。