A robust cost function for stereo matching of road scenes

Alina Miron (1) , Samia Ainouz (2) , Alexandrina Rogozan (3) , Abdelaziz Bensrhair (3)

1 CEDIN - Centre de droit international de Nanterre
2 INSA Rouen Normandie - Institut national des sciences appliquées Rouen Normandie
3 LITIS - Laboratoire d'Informatique, de Traitement de l'Information et des Systèmes

In this paper different matching cost functions used for stereo matching are evaluated in the context of intelligent vehicles applications. Classical costs are considered, like: sum of squared differences, normalized cross correlation or census transform that were already evaluated in previous studies, together with some recent functions that try to enhance the discriminative power of Census Transform (CT). These are evaluated with two different stereo matching algorithms: a global method based on graph cuts and a fast local one based on cross aggregation regions. Furthermore we propose a new cost function that combines the CT and alternatively a variant of CT called Cross-Comparison Census (CCC), with the mean sum of relative pixel intensity differences (DIFFCensus). Among all the tested cost functions, under the same constraints, the proposed DIFFCensus produces the lower error rate on the KITTI road scenes dataset 1 with both global and local stereo matching algorithms.

Mots clés: stereo vision; census transform; cross comparison census; graph cuts; matching cost comparison; road scenes

Domaines: Vision par ordinateur et reconnaissance de formes [cs.CV]

Alina Miron, Samia Ainouz, Alexandrina Rogozan, Abdelaziz Bensrhair. A robust cost function for stereo matching of road scenes. Pattern Recognition Letters, 2019, ⟨10.1016/j.patrec.2013.11.009⟩. ⟨hal-02114542⟩