Color transformation for improved traffic sign detection

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

Onderzoeksoutput: Bijdrage aan congresPoster

137 Downloads (Pure)

Samenvatting

This paper considers large scale traffic sign detection on a dataset consisting of high-resolution street-level panoramic photographs. Traffic signs are automatically detected and classified with a set of state-of-the-art algorithms. We introduce a color transformation to extend a Histogram of Oriented Gradients (HOG) based detection algorithm to further improve the performance. This transformation uses a specific set of reference colors that aligns with traffic sign characteristics, and measures the distance of each pixel to these reference colors. This results in an improved consistency on the gradients at the outer edge of the traffic sign. In an experiment with 33, 400 panoramic images, the number of misdetections decreased by 53.6% and 51.4% for red/blue circular signs, and by 19.6% and 28.4% for yellow speed bump signs, measured at a realistic detector operating point.
Originele taal-2Engels
Pagina's461-464
DOI's
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

Congres

Congres19th IEEE International Conference on Image Processing (ICIP 2012)
Verkorte titelICIP 2012
LandVerenigde Staten van Amerika
StadLake Buena Vista, FL
Periode30/09/123/10/12
AnderIEEE International Conference on Image Processing (ICIP)

Bibliografische nota

Proceedings of the 19th International Conference on Image Processing (ICIP) 2012, 30 September - 3 October 2012, Orlando, Florida

Vingerafdruk Duik in de onderzoeksthema's van 'Color transformation for improved traffic sign detection'. Samen vormen ze een unieke vingerafdruk.

Citeer dit