中国科学院机构知识库网格
Chinese Academy of Sciences Institutional Repositories Grid
Shadow Detection and Removal from Solo Natural Image Based on Retinex Theory

文献类型:会议论文

作者Sun J(孙静); Du YK(杜英魁); Tang YD(唐延东)
出版日期2008
会议名称1st International Conference Intelligent Robotics and Applications
会议日期October 15-17, 2008
会议地点Wuhan, China
关键词Shadow detection Shadow removal Retinex Theory Machine Vision
页码660-668
中文摘要Shadows are physical phenomena observed in most natural scenes. They can cause many problems in computer vision performance. The paper addresses the problem of shadow detection and removal from solo image of natural scenes. Our method is based on Retinex theory which is an image enhancement and illumination compensation model of the lightness and color perception of human vision. The approach proposed here does not use any special prior knowledge and assumptions. The shadow extraction algorithm originates from a simple idea that the human-vision-based Retinex has the natural ability to enhance the shadow region of an image no matter it is penumbrae or umbrae. The penumbrae and umbrae regions will be highlighted if we compare the Retinex-enhanced images with original images. Then through adding smooth light forcibly to shadow edges and introducing shadow edge masks, we reduce the effects of shadow edges in the Retinex enhancement processing. Experiment results validate the approach.
收录类别EI ; CPCI(ISTP)
产权排序1
会议主办者Huazhong Univ Sci & Technol, Natl Nat Sci Fdn China, HUST, Sch Mech Sci & Engn, State Key Lab Digital Mfg Equipment & Technol, State Key Lab Robot, State Key Lab Mech Syst & Vibrat
会议录INTELLIGENT ROBOTICS AND APPLICATIONS, PT I, PROCEEDINGS
会议录出版者SPRINGER-VERLAG
会议录出版地BERLIN
语种英语
ISSN号0302-9743
ISBN号978-3-540-88516-0
WOS记录号WOS:000261049200071
源URL[http://ir.sia.cn/handle/173321/8873]  
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
Sun J,Du YK,Tang YD. Shadow Detection and Removal from Solo Natural Image Based on Retinex Theory[C]. 见:1st International Conference Intelligent Robotics and Applications. Wuhan, China. October 15-17, 2008.

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。