Obstacle detection in road scene based on motion analysis

Cédric Demonceaux (1, 2) , A. Potelle (2) , D. Kachi (2)

1 LAMFA - Laboratoire Amiénois de Mathématique Fondamentale et Appliquée
2 CREA - Centre de Robotique, d'Electrotechnique et d'Automatique

This paper deals with the problem of obstacle detec- tion in traffic applications. The proposed device allows a driver to receive the current road and vehicle environment information. The perception of the environment is performed through a fast pro- cessing of image sequences acquired from a single camera mounted on a vehicle. This approach is based on frame motion analysis. The road motion is first computed through a fast and robust wavelets analysis. Finally, we detect the areas that have a different motion thanks to a Bayesian modelization. Results shown in this paper prove that the proposed method permits the detection of any ob- stacle on all type of road in various image conditions.

Mots clés: Motion estimation; road detection; obstacle detection

Domaines: Robotique [cs.RO]

Cédric Demonceaux, A. Potelle, D. Kachi. Obstacle detection in road scene based on motion analysis. IEEE Transactions on Vehicular Technology, 2004, 53 (6), pp.1649-1656. ⟨hal-01205581⟩