Robust classification of traffic signs using multi-view cues

L. Hazelhoff, I.M. Creusen, P.H.N. With, de

Onderzoeksoutput: Hoofdstuk in Boek/Rapport/CongresprocedureConferentiebijdrageAcademicpeer review

7 Citaten (Scopus)


Traffic sign inventories are created for road safety and maintenance based on street-level panoramic images. Due to the large capturing interval, large viewpoint deviations between the different capturings occur. These viewpoint variations complicate the classification procedure, which aims at the selection of the correct sign type, out of a high number of nearly similar sign types, typically resulting in misclassifications. This paper describes a novel approach for incorporating viewpoint information to the classification procedure, where the sign orientation is estimated based on dense matching. Afterwards, each sample is corrected to a frontal viewpoint, which is then classified. Finally, the sign type is obtained by weighted voting. Large-scale experiments including 2, 224 traffic signs show that this approach reduces the misclassification rate by about 33% compared to the single-view case.
Originele taal-2Engels
TitelProceedings of the 19th International Conference on Image Processing (ICIP) 2012, 30 September - 3 October 2012, Orlando, Florida
Plaats van productiePiscataway
UitgeverijInstitute of Electrical and Electronics Engineers
ISBN van geprinte versie978-1-4673-2532-5
StatusGepubliceerd - 2012
Evenement19th IEEE International Conference on Image Processing (ICIP 2012) - Lake Buena Vista, FL, Verenigde Staten van Amerika
Duur: 30 sep. 20123 okt. 2012
Congresnummer: 19


Congres19th IEEE International Conference on Image Processing (ICIP 2012)
Verkorte titelICIP 2012
Land/RegioVerenigde Staten van Amerika
StadLake Buena Vista, FL
AnderIEEE International Conference on Image Processing (ICIP)


Duik in de onderzoeksthema's van 'Robust classification of traffic signs using multi-view cues'. Samen vormen ze een unieke vingerafdruk.

Citeer dit