Methods and datasets on semantic segmentation: A review

doi:10.1016/j.neucom.2018.03.037

IMR OpenIR

	Methods and datasets on semantic segmentation: A review
	Yu, Hongshan 1,2; Yang, Zhengeng 1; Tan, Lei 1,3; Wang, Yaonan 1; Sun, Wei 1; Sun, Mingui 4; Tang, Yandong 5
通讯作者	Yu, Hongshan(yuhongshancn@hotmail.com)
	2018-08-23
发表期刊	NEUROCOMPUTING
ISSN	0925-2312
卷号	304 页码:82-103
摘要	Semantic segmentation, also called scene labeling, refers to the process of assigning a semantic label (e.g. car, people, and road) to each pixel of an image. It is an essential data processing step for robots and other unmanned systems to understand the surrounding scene. Despite decades of efforts, semantic segmentation is still a very challenging task due to large variations in natural scenes. In this paper, we provide a systematic review of recent advances in this field. In particular, three categories of methods are reviewed and compared, including those based on hand-engineered features, learned features and weakly supervised learning. In addition, we describe a number of popular datasets aiming for facilitating the development of new segmentation algorithms. In order to demonstrate the advantages and disadvantages of different semantic segmentation models, we conduct a series of comparisons between them. Deep discussions about the comparisons are also provided. Finally, this review is concluded by discussing future directions and challenges in this important field of research. (c) 2018 Elsevier B.V. All rights reserved.
关键词	Semantic segmentation Convolutional neural network Markov random fields Weakly supervised method 3D point clouds labeling
资助者	National Natural Science Foundation of China ; National Key Technology Support Program ; National Key Scientific Instrument and Equipment Development Project of China ; Hunan Key Laboratory of Intelligent Robot Technology in Electronic Manufacturing ; Science and Technology Plan Project of Shenzhen City ; Key Project of Science and Technology Plan of Guangdong Province ; Open foundation of State Key Laboratory of Robotics of China ; National Institutes of Health of the United States
DOI	10.1016/j.neucom.2018.03.037
收录类别	SCI
语种	英语
资助项目	National Natural Science Foundation of China[61573135] ; National Key Technology Support Program[2015BAF11B01] ; National Key Scientific Instrument and Equipment Development Project of China[2013YQ140517] ; Hunan Key Laboratory of Intelligent Robot Technology in Electronic Manufacturing[2018001] ; Science and Technology Plan Project of Shenzhen City[JCYJ20170306141557198] ; Key Project of Science and Technology Plan of Guangdong Province[2013B011301014] ; Open foundation of State Key Laboratory of Robotics of China[2013O09] ; National Institutes of Health of the United States[R01CA165255] ; National Institutes of Health of the United States[R21CA172864]
WOS研究方向	Computer Science
WOS类目	Computer Science, Artificial Intelligence
WOS记录号	WOS:000432492800006
出版者	ELSEVIER SCIENCE BV
引用统计	被引频次：145[WOS] [WOS记录] [WOS相关记录]
文献类型	期刊论文
条目标识符	http://ir.imr.ac.cn/handle/321006/128471
专题	中国科学院金属研究所
通讯作者	Yu, Hongshan
作者单位	1.Hunan Univ, Coll Elect & Informat Engn, Natl Engn Lab Robot Visual Percept & Control Tech, Changsha, Hunan, Peoples R China 2.Hunan Univ, Shenzhen Res Inst, Shenzhen 518057, Guangdong, Peoples R China 3.Carnegie Mellon Univ, Robot Inst, Pittsburgh, PA 15213 USA 4.Univ Pittsburgh, Lab Computat Neurosci, Pittsburgh, PA USA 5.Chinese Acad Sci, Shenyang Inst Automat, Shenyang, Liaoning, Peoples R China
推荐引用方式 GB/T 7714	Yu, Hongshan,Yang, Zhengeng,Tan, Lei,et al. Methods and datasets on semantic segmentation: A review[J]. NEUROCOMPUTING,2018,304:82-103.
APA	Yu, Hongshan.,Yang, Zhengeng.,Tan, Lei.,Wang, Yaonan.,Sun, Wei.,...&Tang, Yandong.(2018).Methods and datasets on semantic segmentation: A review.NEUROCOMPUTING,304,82-103.
MLA	Yu, Hongshan,et al."Methods and datasets on semantic segmentation: A review".NEUROCOMPUTING 304(2018):82-103.