File Download
  Links for fulltext
     (May Require Subscription)
Supplementary

Conference Paper: Improved multi-level pedestrian behavior prediction based on matching with classified motion patterns

TitleImproved multi-level pedestrian behavior prediction based on matching with classified motion patterns
Authors
KeywordsDynamically changing environment
Motion patterns
Multi-level behavior prediction
Similarity matching
Issue Date2009
PublisherIEEE.
Citation
The 12th IEEE International Conference on Intelligent Transportation Systems (ITSC 2009), St. Louis, MO., 3-7 October 2009. In Proceedings of the 12th ITSC, 2009, p. 249-254 How to Cite?
AbstractThis paper proposes an improved multi-level pedestrian behavior prediction method based on our previous research work on learning pedestrian motion patterns and predicting pedestrian long-term behaviors as their motion instances are being observed. The improvement mainly focuses on the similarity matching criteria between the trajectory and the clustered MP whose main advantages are that (1) a reasonable similarity range of MP is automatically calculated instead of manually set; (2) the distance feature and the changing angle feature are considered together for similarity matching while only the distance feature is considered before. The improved method has been implemented and a study of how the new prediction method performs in real world scenario is conducted. The results show that it works well in real DCE and the prediction is consistent with the actual behavior. © 2009 IEEE.
Persistent Identifierhttp://hdl.handle.net/10722/126065
ISBN
References

 

DC FieldValueLanguage
dc.contributor.authorChen, Zen_HK
dc.contributor.authorYung, NHCen_HK
dc.date.accessioned2010-10-31T12:07:54Z-
dc.date.available2010-10-31T12:07:54Z-
dc.date.issued2009en_HK
dc.identifier.citationThe 12th IEEE International Conference on Intelligent Transportation Systems (ITSC 2009), St. Louis, MO., 3-7 October 2009. In Proceedings of the 12th ITSC, 2009, p. 249-254en_HK
dc.identifier.isbn978-1-4244-5519-5-
dc.identifier.urihttp://hdl.handle.net/10722/126065-
dc.description.abstractThis paper proposes an improved multi-level pedestrian behavior prediction method based on our previous research work on learning pedestrian motion patterns and predicting pedestrian long-term behaviors as their motion instances are being observed. The improvement mainly focuses on the similarity matching criteria between the trajectory and the clustered MP whose main advantages are that (1) a reasonable similarity range of MP is automatically calculated instead of manually set; (2) the distance feature and the changing angle feature are considered together for similarity matching while only the distance feature is considered before. The improved method has been implemented and a study of how the new prediction method performs in real world scenario is conducted. The results show that it works well in real DCE and the prediction is consistent with the actual behavior. © 2009 IEEE.en_HK
dc.languageengen_HK
dc.publisherIEEE.en_HK
dc.relation.ispartofProceedings of the 12th IEEE International Conference on Intelligent Transportation Systems, ITSC 2009en_HK
dc.rightsInternational Conference on Intelligent Transportation. Copyright © IEEE.-
dc.rightsCreative Commons: Attribution 3.0 Hong Kong License-
dc.rights©2009 IEEE. Personal use of this material is permitted. However, permission to reprint/republish this material for advertising or promotional purposes or for creating new collective works for resale or redistribution to servers or lists, or to reuse any copyrighted component of this work in other works must be obtained from the IEEE.-
dc.subjectDynamically changing environmenten_HK
dc.subjectMotion patternsen_HK
dc.subjectMulti-level behavior predictionen_HK
dc.subjectSimilarity matchingen_HK
dc.titleImproved multi-level pedestrian behavior prediction based on matching with classified motion patternsen_HK
dc.typeConference_Paperen_HK
dc.identifier.openurlhttp://library.hku.hk:4550/resserv?sid=HKU:IR&issn=978-1-4244-5519-5&volume=&spage=1&epage=6&date=2009&atitle=Improved+multi-level+pedestrian+behavior+prediction+based+on+matching+with+classified+motion+patterns-
dc.identifier.emailYung, NHC:nyung@eee.hku.hken_HK
dc.identifier.authorityYung, NHC=rp00226en_HK
dc.description.naturepublished_or_final_version-
dc.identifier.doi10.1109/ITSC.2009.5309849en_HK
dc.identifier.scopuseid_2-s2.0-72449190645en_HK
dc.identifier.hkuros176245en_HK
dc.relation.referenceshttp://www.scopus.com/mlt/select.url?eid=2-s2.0-72449190645&selection=ref&src=s&origin=recordpageen_HK
dc.identifier.spage249en_HK
dc.identifier.epage254en_HK
dc.description.otherThe 12th IEEE International Conference on Intelligent Transportation Systems (ITSC 2009), St. Louis, MO., 3-7 October 2009. In Proceedings of the 12th ITSC, 2009, p. 249-254-
dc.identifier.scopusauthoridChen, Z=35277857300en_HK
dc.identifier.scopusauthoridYung, NHC=7003473369en_HK

Export via OAI-PMH Interface in XML Formats


OR


Export to Other Non-XML Formats