Knowledge Commons of Institute of Automation,CAS
A real-time semantic visual SLAM approach with points and objects | |
Guan, Peiyu1,2![]() ![]() ![]() ![]() ![]() | |
发表期刊 | INTERNATIONAL JOURNAL OF ADVANCED ROBOTIC SYSTEMS
![]() |
ISSN | 1729-8814 |
2020 | |
卷号 | 17期号:1页码:1-10 |
摘要 | Visual simultaneously localization and mapping (SLAM) is important for self-localization and environment perception of service robots, where semantic SLAM can provide a more accurate localization result and a map with abundant semantic information. In this article, we propose a real-time PO-SLAM approach with the combination of both point and object measurements. With point-point association in ORB-SLAM2, we also consider point-object association based on object segmentation and object-object association, where the object segmentation is employed by combining object detection with depth histogram. Also, besides the constraint of feature points belonging to an object, a semantic constraint of relative position invariance among objects is introduced. Accordingly, two semantic loss functions with point and object information are designed and added to the bundle adjustment optimization. The effectiveness of the proposed approach is verified by experiments. |
关键词 | Semantic SLAM data association object segmentation semantic constraint |
DOI | 10.1177/1729881420905443 |
收录类别 | SCI |
语种 | 英语 |
资助项目 | Beijing Advanced Innovation Center for Intelligent Robots and Systems[2018IRS21] ; Key Research and Development Program of Shandong Province[2017CXGC0925] ; National Natural Science Foundation of China[61633020] ; National Natural Science Foundation of China[61836015] ; National Natural Science Foundation of China[61633017] ; National Natural Science Foundation of China[61633017] ; National Natural Science Foundation of China[61836015] ; National Natural Science Foundation of China[61633020] ; Key Research and Development Program of Shandong Province[2017CXGC0925] ; Beijing Advanced Innovation Center for Intelligent Robots and Systems[2018IRS21] |
WOS研究方向 | Robotics |
WOS类目 | Robotics |
WOS记录号 | WOS:000515812100001 |
出版者 | SAGE PUBLICATIONS INC |
引用统计 | |
文献类型 | 期刊论文 |
条目标识符 | http://ir.ia.ac.cn/handle/173211/38425 |
专题 | 复杂系统认知与决策实验室_先进机器人 |
通讯作者 | Cao, Zhiqiang |
作者单位 | 1.Chinese Acad Sci, Inst Automat, State Key Lab Management & Control Complex Syst, Beijing, Peoples R China 2.Univ Chinese Acad Sci, Beijing, Peoples R China 3.Shandong Univ Sci & Technol, Coll Elect Engn & Automat, Qingdao, Peoples R China 4.Peking Univ, Dept Mech & Engn Sci, Beijing Innovat Ctr Engn Sci & Adv Technol, Coll Engn, Beijing, Peoples R China |
第一作者单位 | 中国科学院自动化研究所 |
通讯作者单位 | 中国科学院自动化研究所 |
推荐引用方式 GB/T 7714 | Guan, Peiyu,Cao, Zhiqiang,Chen, Erkui,et al. A real-time semantic visual SLAM approach with points and objects[J]. INTERNATIONAL JOURNAL OF ADVANCED ROBOTIC SYSTEMS,2020,17(1):1-10. |
APA | Guan, Peiyu,Cao, Zhiqiang,Chen, Erkui,Liang, Shuang,Tan, Min,&Yu, Junzhi.(2020).A real-time semantic visual SLAM approach with points and objects.INTERNATIONAL JOURNAL OF ADVANCED ROBOTIC SYSTEMS,17(1),1-10. |
MLA | Guan, Peiyu,et al."A real-time semantic visual SLAM approach with points and objects".INTERNATIONAL JOURNAL OF ADVANCED ROBOTIC SYSTEMS 17.1(2020):1-10. |
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 | ||
1729881420905443.pdf(1980KB) | 期刊论文 | 作者接受稿 | 开放获取 | CC BY-NC-SA | 浏览 下载 |
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。
修改评论