SIA OpenIR  > 工业控制网络与系统研究室
Methods and datasets on semantic segmentation: A review
Yu HS(余洪山)1,2; Yang, Zhengeng1; Tan, Lei1,3; Wang YN(王耀南)1; Sun, Wei1; Sun, Mingui4; Tang YD(唐延东)5
作者部门工业控制网络与系统研究室
关键词Semantic segmentation Convolutional neural network Markov random fields Weakly supervised method 3D point clouds labeling
发表期刊NEUROCOMPUTING
ISSN0925-2312
2018
卷号304页码:82-103
收录类别SCI ; EI
EI收录号20182105222020
WOS记录号WOS:000432492800006
产权排序5
资助机构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
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.
语种英语
WOS类目Computer Science, Artificial Intelligence
关键词[WOS]MARKOV RANDOM-FIELDS ; IMAGE SEGMENTATION ; OBJECT RECOGNITION ; ENERGY MINIMIZATION ; POINT CLOUDS ; FEATURES ; VISION ; CONTEXT ; MODEL ; ALGORITHMS
WOS研究方向Computer Science
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]
引用统计
文献类型期刊论文
条目标识符http://ir.sia.cn/handle/173321/21902
专题工业控制网络与系统研究室
通讯作者Yu HS(余洪山)
作者单位1.National Engineering Laboratory for Robot Visual Perception and Control Technology, College of Electrical and Information Engineering, Hunan University, Changsha, China;
2.Shenzhen Research Institute of Hunan University, Shenzhen, Guangdong 518057, China;
3.Robotics Institute, Carnegie Mellon University, Pittsburgh, PA, USA;
4.Laboratory for Computational Neuroscience, University of Pittsburgh, Pittsburgh, USA;
5.Shenyang Institute of Automation, Chinese Academy of Sciences, Shenyang, China
推荐引用方式
GB/T 7714
Yu HS,Yang, Zhengeng,Tan, Lei,et al. Methods and datasets on semantic segmentation: A review[J]. NEUROCOMPUTING,2018,304:82-103.
APA Yu HS.,Yang, Zhengeng.,Tan, Lei.,Wang YN.,Sun, Wei.,...&Tang YD.(2018).Methods and datasets on semantic segmentation: A review.NEUROCOMPUTING,304,82-103.
MLA Yu HS,et al."Methods and datasets on semantic segmentation: A review".NEUROCOMPUTING 304(2018):82-103.
条目包含的文件 下载所有文件
文件名称/大小 文献类型 版本类型 开放类型 使用许可
Methods and datasets(2926KB)期刊论文出版稿开放获取CC BY-NC-SA浏览 下载
个性服务
推荐该条目
保存到收藏夹
查看访问统计
导出为Endnote文件
谷歌学术
谷歌学术中相似的文章
[Yu HS(余洪山)]的文章
[Yang, Zhengeng]的文章
[Tan, Lei]的文章
百度学术
百度学术中相似的文章
[Yu HS(余洪山)]的文章
[Yang, Zhengeng]的文章
[Tan, Lei]的文章
必应学术
必应学术中相似的文章
[Yu HS(余洪山)]的文章
[Yang, Zhengeng]的文章
[Tan, Lei]的文章
相关权益政策
暂无数据
收藏/分享
文件名: Methods and datasets on semantic segmentation.pdf
格式: Adobe PDF
所有评论 (0)
暂无评论
 

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。