SIA OpenIR  > 机器人学研究室
New spectrum ratio properties and features for shadow detection
Tian JD(田建东); Qi XJ(齐虓隽); Qu LQ(屈靓琼); Tang YD(唐延东)
Department机器人学研究室
Source PublicationPattern Recognition
ISSN0031-3203
2016
Volume51Issue:3Pages:85–96
Indexed BySCI ; EI
EI Accession number20155201737836
WOS IDWOS:000367633400007
Contribution Rank1
Funding OrganizationNatural Science Foundation of China under Grants 61102116 and 61473280.
KeywordSpectrum Ratio Properties Shadow Features Skylight Spd Daylight Spd Shadow Detection
AbstractSuccessfully detecting shadows in still images is challenging yet has wide applications. Shadow properties and features are very important for shadow detection and processing. The aim of this work is to find some new physical properties of shadows and use them as shadow features to design an effective shadow detection method for outdoor color images. We observe that although the spectral power distribution (SPD) of daylight and that of skylight are quite different, in each channel, the spectrum ratio of the point-wise product of daylight SPD with sRGB color matching functions (CMFs) to the point-wise product of skylight SPD with sRGB CMFs roughly approximates a constant. This further leads to that the ratios of linear sRGB pixel values of surfaces illuminated by daylight (in non-shadow regions) to those illuminated by skylight (in shadow regions) equal to a constant in each channel. Following this observation, we calculated the spectrum ratios under various Sun angles and further found out four new shadow properties. With these properties as shadow features, we developed a simple shadow detection method to quickly locate shadows in single still images. In our method, we classify an edge as a shadow or non-shadow edge by verifying whether the pixel values on both sides of the Canny edges satisfy the three shadow verification criteria derived from the shadow properties. Extensive experiments and comparison show that our method outperforms state-of-the-art shadow detection methods.
Language英语
WOS HeadingsScience & Technology ; Technology
WOS SubjectComputer Science, Artificial Intelligence ; Engineering, Electrical & Electronic
WOS KeywordCAST SHADOWS ; MODEL ; REMOVAL ; CALIBRATION ; SURFACE ; IMAGES
WOS Research AreaComputer Science ; Engineering
Citation statistics
Document Type期刊论文
Identifierhttp://ir.sia.cn/handle/173321/17439
Collection机器人学研究室
Corresponding AuthorTian JD(田建东)
Affiliation1.State Key Laboratory of Robotics, Shenyang Institute of Automation, Chinese Academy of Sciences, Shenyang, Liaoning Province, China
2.University of Chinese Academy of Sciences, Beijing, China
3.Department of Computer Science, Utah State University, Logan, UT, United States
Recommended Citation
GB/T 7714
Tian JD,Qi XJ,Qu LQ,et al. New spectrum ratio properties and features for shadow detection[J]. Pattern Recognition,2016,51(3):85–96.
APA Tian JD,Qi XJ,Qu LQ,&Tang YD.(2016).New spectrum ratio properties and features for shadow detection.Pattern Recognition,51(3),85–96.
MLA Tian JD,et al."New spectrum ratio properties and features for shadow detection".Pattern Recognition 51.3(2016):85–96.
Files in This Item: Download All
File Name/Size DocType Version Access License
New spectrum ratio p(7205KB)期刊论文作者接受稿开放获取ODC PDDLView Download
Related Services
Recommend this item
Bookmark
Usage statistics
Export to Endnote
Google Scholar
Similar articles in Google Scholar
[Tian JD(田建东)]'s Articles
[Qi XJ(齐虓隽)]'s Articles
[Qu LQ(屈靓琼)]'s Articles
Baidu academic
Similar articles in Baidu academic
[Tian JD(田建东)]'s Articles
[Qi XJ(齐虓隽)]'s Articles
[Qu LQ(屈靓琼)]'s Articles
Bing Scholar
Similar articles in Bing Scholar
[Tian JD(田建东)]'s Articles
[Qi XJ(齐虓隽)]'s Articles
[Qu LQ(屈靓琼)]'s Articles
Terms of Use
No data!
Social Bookmark/Share
File name: New spectrum ratio properties and features for shadow detection.pdf
Format: Adobe PDF
All comments (0)
No comment.
 

Items in the repository are protected by copyright, with all rights reserved, unless otherwise indicated.