H. Kollnig et Hm. Nagel, 3D POSE ESTIMATION BY DIRECTLY MATCHING POLYHEDRAL MODELS TO GRAY VALUE GRADIENTS, International journal of computer vision, 23(3), 1997, pp. 283-302
Citations number
36
Categorie Soggetti
Computer Sciences, Special Topics","Computer Science Artificial Intelligence
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.