File Download
  Links for fulltext
     (May Require Subscription)
Supplementary

Article: Effective moving cast shadow detection for monocular color traffic image sequences

TitleEffective moving cast shadow detection for monocular color traffic image sequences
Authors
KeywordsImage segmentation
Image sequence analysis
Intelligent transportation systems
Shadow detection
Visual traffic surveillance
Issue Date2002
PublisherS P I E - International Society for Optical Engineering. The Journal's web site is located at http://www.spie.org/oe
Citation
Optical Engineering, 2002, v. 41 n. 6, p. 1425-1440 How to Cite?
AbstractFor an accurate scene analysis using monocular color traffic image sequences, a robust segmentation of moving vehicles from the stationary background is generally required. However, the presence of moving cast shadow may lead to an inaccurate vehicle segmentation, and as a result, may lead to further erroneous scene analysis. We propose an effective method for the detection of moving cast shadow. By observing the characteristics of cast shadow in the luminance, chrominance, gradient density, and geometry domains, a combined probability map, called a shadow confidence score (SCS), is obtained. From the edge map of the input image, each edge pixel is examined to determine whether it belongs to the vehicle region based on its neighboring SCCs. The cast shadow is identified as those regions with high SCSs, which are outside the convex hull of the selected vehicle edge pixels. The proposed method is tested on 100 vehicle images taken under different lighting conditions (sunny and cloudy), viewing angles (roadside and overhead), vehicle sizes (small, medium, and large), and colors (similar to the road and not). The results indicate that an average error rate of around 14% is obtained while the lowest error rate is around 3% for large vehicles.
Persistent Identifierhttp://hdl.handle.net/10722/42919
ISSN
2023 Impact Factor: 1.1
2023 SCImago Journal Rankings: 0.331
ISI Accession Number ID
References

 

DC FieldValueLanguage
dc.contributor.authorFung, GSKen_HK
dc.contributor.authorYung, NHCen_HK
dc.contributor.authorPang, GKHen_HK
dc.contributor.authorLai, AHSen_HK
dc.date.accessioned2007-03-23T04:34:43Z-
dc.date.available2007-03-23T04:34:43Z-
dc.date.issued2002en_HK
dc.identifier.citationOptical Engineering, 2002, v. 41 n. 6, p. 1425-1440en_HK
dc.identifier.issn0091-3286en_HK
dc.identifier.urihttp://hdl.handle.net/10722/42919-
dc.description.abstractFor an accurate scene analysis using monocular color traffic image sequences, a robust segmentation of moving vehicles from the stationary background is generally required. However, the presence of moving cast shadow may lead to an inaccurate vehicle segmentation, and as a result, may lead to further erroneous scene analysis. We propose an effective method for the detection of moving cast shadow. By observing the characteristics of cast shadow in the luminance, chrominance, gradient density, and geometry domains, a combined probability map, called a shadow confidence score (SCS), is obtained. From the edge map of the input image, each edge pixel is examined to determine whether it belongs to the vehicle region based on its neighboring SCCs. The cast shadow is identified as those regions with high SCSs, which are outside the convex hull of the selected vehicle edge pixels. The proposed method is tested on 100 vehicle images taken under different lighting conditions (sunny and cloudy), viewing angles (roadside and overhead), vehicle sizes (small, medium, and large), and colors (similar to the road and not). The results indicate that an average error rate of around 14% is obtained while the lowest error rate is around 3% for large vehicles.en_HK
dc.format.extent1774447 bytes-
dc.format.extent28160 bytes-
dc.format.extent961133 bytes-
dc.format.extent5183 bytes-
dc.format.mimetypeapplication/pdf-
dc.format.mimetypeapplication/msword-
dc.format.mimetypeapplication/pdf-
dc.format.mimetypetext/plain-
dc.languageengen_HK
dc.publisherS P I E - International Society for Optical Engineering. The Journal's web site is located at http://www.spie.org/oeen_HK
dc.relation.ispartofOptical Engineeringen_HK
dc.rightsCopyright 2002 Society of Photo‑Optical Instrumentation Engineers (SPIE). One print or electronic copy may be made for personal use only. Systematic reproduction and distribution, duplication of any material in this publication for a fee or for commercial purposes, and modification of the contents of the publication are prohibited. This article is available online at https://doi.org/10.1117/1.1473638-
dc.subjectImage segmentationen_HK
dc.subjectImage sequence analysisen_HK
dc.subjectIntelligent transportation systemsen_HK
dc.subjectShadow detectionen_HK
dc.subjectVisual traffic surveillanceen_HK
dc.titleEffective moving cast shadow detection for monocular color traffic image sequencesen_HK
dc.typeArticleen_HK
dc.identifier.openurlhttp://library.hku.hk:4550/resserv?sid=HKU:IR&issn=0091-3286&volume=41&issue=6&spage=1425&epage=1440&date=2002&atitle=Effective+moving+cast+shadow+detection+for+monocular+color+traffic+image+sequencesen_HK
dc.identifier.emailYung, NHC:nyung@eee.hku.hken_HK
dc.identifier.emailPang, GKH:gpang@eee.hku.hken_HK
dc.identifier.authorityYung, NHC=rp00226en_HK
dc.identifier.authorityPang, GKH=rp00162en_HK
dc.description.naturepublished_or_final_versionen_HK
dc.identifier.doi10.1117/1.1473638en_HK
dc.identifier.scopuseid_2-s2.0-0036612357en_HK
dc.identifier.hkuros81154-
dc.relation.referenceshttp://www.scopus.com/mlt/select.url?eid=2-s2.0-0036612357&selection=ref&src=s&origin=recordpageen_HK
dc.identifier.volume41en_HK
dc.identifier.issue6en_HK
dc.identifier.spage1425en_HK
dc.identifier.epage1440en_HK
dc.identifier.isiWOS:000176176600038-
dc.publisher.placeUnited Statesen_HK
dc.identifier.scopusauthoridFung, GSK=7004213392en_HK
dc.identifier.scopusauthoridYung, NHC=7003473369en_HK
dc.identifier.scopusauthoridPang, GKH=7103393283en_HK
dc.identifier.scopusauthoridLai, AHS=7102225794en_HK
dc.identifier.issnl0091-3286-

Export via OAI-PMH Interface in XML Formats


OR


Export to Other Non-XML Formats