A robust cost function for stereo matching of road scenes

• We compare different cost functions for stereo matching of road scenes.
• We propose a new non-parametric cost function: DIFFCensus.
• The lowest error rate is given by the proposed function.

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, normalised 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 dataset1 with both global and local stereo matching algorithms.