中国科学院机构知识库网格
Chinese Academy of Sciences Institutional Repositories Grid
Finding passable regions for robots from a single still image

文献类型:期刊论文

作者Tian JD(田建东); Dong W(董威); Tang YD(唐延东)
刊名International Journal of Robotics & Automation
出版日期2009
卷号24期号:3页码:228-234
关键词Monocular vision MILN depth cues passable regions
ISSN号0826-8185
产权排序1
中文摘要Vision-guided obstacle avoidance, especially in unstructured environments, is a challenging issue in robotics. The paper proposes a biological inspired method to find passable regions based on the estimation of relative depth in a single still colour image. In the method, Multiple-layer In-place Learning Network (MILN) is applied to learn the passable regions in images, choosing several depth-related features extracted from the images as inputs. The method proposed here does not need any special prior knowledge or assumptions. We test our method on practical images of different scenes. Experimental results validate our method.
WOS标题词Science & Technology ; Technology
类目[WOS]Automation & Control Systems ; Robotics
研究领域[WOS]Automation & Control Systems ; Robotics
关键词[WOS]DEPTH
收录类别SCI ; EI
语种英语
WOS记录号WOS:000268644300009
公开日期2012-05-29
源URL[http://ir.sia.cn/handle/173321/7353]  
专题沈阳自动化研究所_机器人学研究室
推荐引用方式
GB/T 7714
Tian JD,Dong W,Tang YD. Finding passable regions for robots from a single still image[J]. International Journal of Robotics & Automation,2009,24(3):228-234.
APA Tian JD,Dong W,&Tang YD.(2009).Finding passable regions for robots from a single still image.International Journal of Robotics & Automation,24(3),228-234.
MLA Tian JD,et al."Finding passable regions for robots from a single still image".International Journal of Robotics & Automation 24.3(2009):228-234.

入库方式: OAI收割

来源:沈阳自动化研究所

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。