RGB-D joint modelling with scene geometric information for indoor semantic segmentation

doi:10.1007/s11042-018-6056-8

CORC > 计算技术研究所 > 中国科学院计算技术研究所 > 中国科学院计算技术研究所期刊论文 > 英文

	RGB-D joint modelling with scene geometric information for indoor semantic segmentation
	Liu, Hong; Wu, Wenshan; Wang, Xiangdong; Qian, Yueliang
刊名	MULTIMEDIA TOOLS AND APPLICATIONS
	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
出版者	SPRINGER
WOS记录号	WOS:000441364500039
内容类型	期刊论文
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.