A new minimal path selection algorithm for automatic crack detection on pavement images

Rabih Amhaz (1, 2) , Sylvie Chambon (3, 4) , Jérôme Idier (5) , Vincent Baltazart (2)

1 IRIT-VORTEX - Visual Objects from Reality To Expression
2 UNAM - PRES Université Nantes Angers Le Mans
3 IRIT-REVA - Real Expression Artificial Life
4 Toulouse INP - Institut National Polytechnique (Toulouse)
5 IRCCyN - Institut de Recherche en Communications et en Cybernétique de Nantes

This paper proposes a new algorithm for crack detection based on the selection of minimal paths. It takes account of both photometric and geometric characteristics and requires few information a priori. It is validated on synthetic and real images.

Mots clés: Minimal path; Dijkstra; Edge detection; Pavement Photometry; Non destructive control; Algorithm; Crack detection

Domaines: Traitement des images [eess.IV]

Rabih Amhaz, Sylvie Chambon, Jérôme Idier, Vincent Baltazart. A new minimal path selection algorithm for automatic crack detection on pavement images. IEEE International Conference on Image Processing (ICIP 2014), Oct 2014, Paris, France. pp.788-792, ⟨10.1109/ICIP.2014.7025158⟩. ⟨hal-01387817⟩