Automatic detection of cracks in road images

Key words : Image processing, detection, segmentation, wavelet decomposition, Markov random field, cracks, roads

Abstract : Every year, the French Public Works Research Laboratory is involved in the evaluation of the quality of the roads in order to planify reparations. The criteria taken into account for the evaluation are: roadholding adhesion, quality of micro-texture and macro-texture, damages of the road. This work concerns deterioration detection and more specifically, crack detection. Before research work about automatic detection, the areas of deteriorations were manually detected. This task is dangerous for the employers (the vehicule used for this work has to drive slowly), tedious (evaluation of all the roads is very long), non-reproducible (the evaluation of the crack is different from a person to another) and not efficient (as this task is hard, the probability of errors is high).
Our contributions in this research context are

Method based on Markovian modelling ;

Multiscale watershed algorithm ;

Method based on multiple images ;

Points of Interest based method.

Publications

Sylvie Chambon. " Detection of Points of Interest for Geodesic Contours: Application on Road Images for Crack Detection ". In International Joint Conference on Computer Vision Theory and Applications, VISAPP, Vilamoura, Portugal, march 2011.

Sylvie Chambon, Christian Gourraud, Jean-Marc Moliard, Philippe Nicolle. " Road crack extraction with adapted filtering and Markov model-based segmentation ", In International Joint Conference on Computer Vision Theory and Applications, VISAPP, Angers, France, may 2010.

Nicolas Coudray, Argyro Karathanou, Nicolas Coudray, Sylvie Chambon. " Multi-resolution approach for fine structure extraction - Application and validation on road images ", In International Joint Conference on Computer Vision Theory and Applications, VISAPP, Angers, France, may 2010.

Sylvie Chambon. " Detection of road cracks with multiple images ", In International Joint Conference on Computer Vision Theory and Applications, VISAPP, Angers, France , may 2010.

Sylvie Chambon, Peggy Subirats, Jean Dumoulin. " Introduction of a wavelet transform based on 2D matched filter in a Markov Random Field for fine structure extraction: Application on road crack detection ", In IS&T/SPIE Electronic Imaging - Image Processing: Machine Vision Applications II, San José, États-Unis, january 2009.

Home

	Sylvie Chambon. " Detection of Points of Interest for Geodesic Contours: Application on Road Images for Crack Detection ". In International Joint Conference on Computer Vision Theory and Applications, VISAPP, Vilamoura, Portugal, march 2011.
	Sylvie Chambon, Christian Gourraud, Jean-Marc Moliard, Philippe Nicolle. " Road crack extraction with adapted filtering and Markov model-based segmentation ", In International Joint Conference on Computer Vision Theory and Applications, VISAPP, Angers, France, may 2010.
	Nicolas Coudray, Argyro Karathanou, Nicolas Coudray, Sylvie Chambon. " Multi-resolution approach for fine structure extraction - Application and validation on road images ", In International Joint Conference on Computer Vision Theory and Applications, VISAPP, Angers, France, may 2010.
	Sylvie Chambon. " Detection of road cracks with multiple images ", In International Joint Conference on Computer Vision Theory and Applications, VISAPP, Angers, France , may 2010.
	Sylvie Chambon, Peggy Subirats, Jean Dumoulin. " Introduction of a wavelet transform based on 2D matched filter in a Markov Random Field for fine structure extraction: Application on road crack detection ", In IS&T/SPIE Electronic Imaging - Image Processing: Machine Vision Applications II, San José, États-Unis, january 2009.