Traffic Signs Color Detection and Segmentation in Poor Light Conditions

Document identifier: oai:dalea.du.se:1025
Keyword: Engineering and Technology, Civil Engineering, Transport Systems and Logistics, Teknik och teknologier, Samhällsbyggnadsteknik, Transportteknik och logistik, Color segmentation, Color constancy, Histogram equalization, Color detection, Road signs, Outdoor images.
Publication year: 2005
Abstract:

This paper presents a new algorithm for color detection and segmentation of road signs in poor light conditions. The images were taken by a digital camera mounted in a car. The RGB channels of the digital images were enhanced separately by histogram equalization, and then a color constancy algorithm was applied to extract the true colors of the sign. The resultant image was then converted into HSV color space, and segmented to extract the colors of the road signs. The method was tested on outdoor images in different poor light conditions such as fog and snow, and they show high robustness. This project is part of the research taking place at Dalarna University - Sweden in the field of the Intelligent Transport Systems (ITS).

Authors

Hasan Fleyeh

Högskolan Dalarna; Datateknik
Other publications >>

Documents attached

Click on thumbnail to read

Record metadata

Click to view metadata

	
    header: 
        identifier: oai:dalea.du.se:1025
        datestamp: 2021-04-15T14:04:07Z
        setSpec: SwePub-du
    metadata: 
        mods: 
            @attributes: 
                version: 3.7
            recordInfo: 
                recordContentSource: du
                recordCreationDate: 2005-05-02
            identifier: http://urn.kb.se/resolve?urn=urn:nbn:se:du-1025
            titleInfo: 
                @attributes: 
                    lang: eng
                title: Traffic Signs Color Detection and Segmentation in Poor Light Conditions
            abstract: 
This paper presents a new algorithm for color detection and segmentation of road signs in poor light conditions. The images were taken by a digital camera mounted in a car. The RGB channels of the digital images were enhanced separately by histogram equalization and then a color constancy algorithm was applied to extract the true colors of the sign. The resultant image was then converted into HSV color space and segmented to extract the colors of the road signs. The method was tested on outdoor images in different poor light conditions such as fog and snow and they show high robustness. This project is part of the research taking place at Dalarna University - Sweden in the field of the Intelligent Transport Systems (ITS).

            subject: 
                    @attributes: 
                        lang: eng
                        authority: uka.se
                    topic: 
                        Engineering and Technology
                        Civil Engineering
                        Transport Systems and Logistics
                    @attributes: 
                        lang: swe
                        authority: uka.se
                    topic: 
                        Teknik och teknologier
                        Samhällsbyggnadsteknik
                        Transportteknik och logistik
                    @attributes: 
                        lang: eng
                    topic: Color segmentation
                    @attributes: 
                        lang: eng
                    topic: color constancy
                    @attributes: 
                        lang: eng
                    topic: histogram equalization
                    @attributes: 
                        lang: eng
                    topic: color detection
                    @attributes: 
                        lang: eng
                    topic: road signs
                    @attributes: 
                        lang: eng
                    topic: outdoor images.
            language: 
                languageTerm: eng
            genre: 
                conference/other
                ref
            note: 
                Published
                1
            name: 
                @attributes: 
                    type: personal
                    authority: du
                namePart: 
                    Fleyeh
                    Hasan
                role: 
                    roleTerm: aut
                affiliation: 
                    Högskolan Dalarna
                    Datateknik
                nameIdentifier: 
                    hfl
                    0000-0002-1429-2345
            originInfo: 
                dateIssued: 2005
                place: 
                    placeTerm: Tsukuba Science City
            relatedItem: 
                @attributes: 
                    type: host
                titleInfo: 
                    title: Machine Vision Applications (MVA2005)
            location: 
                url: http://du.diva-portal.org/smash/get/diva2:521402/FULLTEXT01.pdf
            accessCondition: gratis
            physicalDescription: 
                form: electronic
            typeOfResource: text