3D POSE ESTIMATION BY DIRECTLY MATCHING POLYHEDRAL MODELS TO GRAY VALUE GRADIENTS

This contribution addresses the problem of pose estimation and trackin g of vehicles in image sequences from traffic scenes recorded by a sta tionary camera. In a new algorithm, the vehicle pose is estimated by d irectly matching polyhedral vehicle models to image gradients without an edge segment extraction process. The new approach is significantly more robust than approaches that rely on feature extraction since the new approach exploits more information from the image data. We success fully tracked vehicles that were partially occluded by textured object s, e.g., foliage, where a previous approach based on edge segment extr action failed. Moreover, the new pose estimation approach is also used to determine the orientation and position of the road relative to the camera by matching an intersection model directly to image gradients. Results from various experiments with real world traffic scenes are p resented.