Contrast invariant features for human detection in far infrared images

e-Archivo Repository

Show simple item record

dc.contributor.author Olmeda Reino, Daniel
dc.contributor.author Escalera Hueso, Arturo de la
dc.contributor.author Armingol Moreno, José María
dc.date.accessioned 2013-09-17T10:08:50Z
dc.date.available 2013-09-17T10:08:50Z
dc.date.issued 2012
dc.identifier.bibliographicCitation 2012 IEEE Intelligent Vehicles Symposium (IV), Pp. 117-122
dc.identifier.isbn 978-1-4673-2119-8 (print)
dc.identifier.isbn 978-1-4673-2118-1 (online)
dc.identifier.issn 1931-0587
dc.identifier.uri http://hdl.handle.net/10016/17553
dc.description Proceeding of: 2012 IEEE Intelligent Vehicles Symposium (IV), Alcalá de Henares, Spain, June 3-7, 2012
dc.description.abstract In this paper a new contrast invariant descriptor for human detection in long-wave infrared images is proposed. It exploits local information histogram of orientations of phase coherence. Contrast in infrared images depends on the temperature of the object and the background, which makes gradient based descriptors less robust, especially in daylight conditions. The objective is to obtain a scale, brightness and contrast invariant descriptor that can successfully detect pedestrians in images taken with a cheap, temperature-sensitive, uncooled microbolometer. The descriptor, packed into grids is feed to a Support Vector Machine classifier. The algorithm has been tested in night and day sequences and its performance is compared with a day only descriptor: the histogram of oriented features (HOG).
dc.description.sponsorship This work was supported by the Spanish Government through the Cicyt projects FEDORA (GRANT TRA2010- 20225-C03-01) and VIDAS-Driver (GRANT TRA2010- 21371-C03-02), and the Comunidad de Madrid through the project SEGVAUTO (S2009/DPI-1509).
dc.format.mimetype application/pdf
dc.language.iso eng
dc.publisher IEEE
dc.rights © 2012 IEEE
dc.subject.other Bolometers
dc.subject.other Infrared images
dc.subject.other Object detection
dc.subject.other Pattern classification
dc.subject.other Pedestrian detection
dc.subject.other Support vector machines
dc.title Contrast invariant features for human detection in far infrared images
dc.type conferenceObject
dc.description.status Publicado
dc.relation.publisherversion http://dx.doi.org/10.1109/IVS.2012.6232242
dc.identifier.doi 10.1109/IVS.2012.6232242
dc.rights.accessRights openAccess
dc.relation.projectID Comunidad de Madrid. S2009/DPI-1509/SEGVAUTO
dc.type.version acceptedVersion
dc.relation.eventdate 2012-06-03
dc.relation.eventplace Alcalá de Henares
dc.relation.eventtitle 2012 IEEE Intelligent Vehicles Symposium (IV)
dc.identifier.publicationfirstpage 117
dc.identifier.publicationlastpage 122
dc.identifier.publicationtitle 2012 IEEE Intelligent Vehicles Symposium (IV)
dc.identifier.uxxi CC/0000014610
 Find Full text

Files in this item

*Click on file's image for preview. (Embargoed files's preview is not supported)


This item appears in the following Collection(s)

Show simple item record