Modeling evidential grids using semantic context information for dynamic scene perception

摘要

Uncertainty about urban environments stems not only from imprecise pose estimation and noisy information in images but also from the lack of semantic information. This article presents an approach to improve the perception capability of intelligent vehicles in complex urban environments. The new method uses the meta-knowledge extracted from semantic context images associated with depth information to model occupancy grids from stereo vision. It uses the evidential formalism of the Dempster–Shafer theory to manage uncertainties involved in grid discretization, partial observation of the environment and also dynamic elements present in the scene. Real experiments carried out in a challenging urban environment using the KITTI benchmark are reported, from which meaningful evaluations compared to the standard evidential grid are done to show that the proposed method is able to better handle semantic, dynamic and uncertainty aspects in the environment representation.