1. ScholarBank@NUS
  2. 1. Staff
  3. Staff Publications
Please use this identifier to cite or link to this item: https://doi.org/10.1016/S0031-3203(02)00126-7
DC FieldValue
dc.titlePedestrian registration in static images with unconstrained background
dc.contributor.authorFan, L.
dc.contributor.authorSung, K.-K.
dc.contributor.authorNg, T.-K.
dc.date.accessioned2013-07-04T07:31:50Z
dc.date.available2013-07-04T07:31:50Z
dc.date.issued2002
dc.identifier.citationFan, L., Sung, K.-K., Ng, T.-K. (2002). Pedestrian registration in static images with unconstrained background. Pattern Recognition 36 (4) : 1019-1029. ScholarBank@NUS Repository. https://doi.org/10.1016/S0031-3203(02)00126-7
dc.identifier.issn00313203
dc.identifier.urihttp://scholarbank.nus.edu.sg/handle/10635/39006
dc.description.abstractThis paper introduces a human body contour registration method for static pedestrian images with unconstrained backgrounds. By using a statistical compound model to impose structural and textural constraints on valid pedestrian appearances, the matching process is robust to image clutter. Experimental results show that the proposed method register pedestrian contours in complex backgrounds effectively. © 2002 Pattern Recognition Society. Published by Elsevier Science Ltd. All rights reserved.
dc.description.urihttp://libproxy1.nus.edu.sg/login?url=http://dx.doi.org/10.1016/S0031-3203(02)00126-7
dc.sourceScopus
dc.subjectFeature extraction
dc.subjectHuman body registration
dc.subjectImage matching
dc.subjectSimilarity measure
dc.subjectStatistical modeling
dc.typeArticle
dc.contributor.departmentCOMPUTER SCIENCE
dc.description.doi10.1016/S0031-3203(02)00126-7
dc.description.sourcetitlePattern Recognition
dc.description.volume36
dc.description.issue4
dc.description.page1019-1029
dc.description.codenPTNRA
dc.identifier.isiut000180577600015
Appears in Collections:Staff Publications

Show simple item record
Files in This Item:
There are no files associated with this item.

Google ScholarTM

Check

Altmetric


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