3D Pose Estimation by Directly Matching Polyhedral Models to Gray Value Gradients

This contribution addresses the problem of pose estimation and tracking of vehicles in image sequences from traffic scenes recorded by a stationary camera. In a new algorithm, the vehicle pose is estimated by directly 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 successfully tracked vehicles that were partially occluded by textured objects, e.g., foliage, where a previous approach based on edge segment extraction 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 presented.

[1]  Hans-Hellmut Nagel,et al.  A vision of vision and language' comprises action: an example from road traffic , 1994 .

[2]  Anil K. Jain,et al.  Contour extraction of moving objects in complex outdoor scenes , 1995, International Journal of Computer Vision.

[3]  M Kilger.  HEAVY TRAFFIC MONITORING IN REAL-TIME , 1993 .

[4]  Mubarak Shah,et al.  Motion-based recognition a survey , 1995, Image Vis. Comput..

[5]  Olof Henricsson,et al.  The Role of Key-Points in Finding Contours , 1994, ECCV.

[6]  Xu Zhang.  Computation of Vehicle Trajectories Using a Neural Network , 1993, BMVC.

[7]  D. Charnley,et al.  Attentive Visual Tracking , 1993, BMVC.

[8]  Jitendra Malik,et al.  Robust Multiple Car Tracking with Occlusion Reasoning , 1994, ECCV.

[9]  Andrew Blake,et al.  A framework for spatiotemporal control in the tracking of visual contours , 1993, International Journal of Computer Vision.

[10]  Michael Otte.  Extraktion von linienförmigen Merkmalen und Ermittlung des optischen Flusses mit seinen Ableitungen aus Voll- und Halbbildfolgen , 1994, DISKI.

[11]  Takeo Kanade,et al.  Region segmentation: Signal vs semantics , 1980 .

[12]  M. Kilger,et al.  A shadow handler in a video-based real-time traffic monitoring system , 1992, [1992] Proceedings IEEE Workshop on Applications of Computer Vision.

[13]  Donald B. Gennery,et al.  Visual tracking of known three-dimensional objects , 1992, International Journal of Computer Vision.

[14]  Dieter Koller.  Detektion, Verfolgung und Klassifikation bewegter Objekte in monokularen Bildfolgen am Beispiel von Straßenverkehrsszenen , 1992, DISKI.

[15]  Olivier Faugeras,et al.  Three D-Dynamic Scene Analysis: A Stereo Based Approach , 1992 .

[16]  Demetri Terzopoulos,et al.  Snakes: Active contour models , 2004, International Journal of Computer Vision.

[17]  Rachid Deriche,et al.  Tracking line segments , 1990, Image Vis. Comput..

[18]  Takeo Kanade,et al.  Visual Tracking of High DOF Articulated Structures: an Application to Human Hand Tracking , 1994, ECCV.

[19]  Y. Bar-Shalom.  Tracking and data association , 1988 .

[20]  Hans-Hellmut Nagel,et al.  Estimation of Optical Flow Based on Higher-Order Spatiotemporal Derivatives in Interlaced and Non-Interlaced Image Sequences , 1995, Artif. Intell..

[21]  Berthold K. P. Horn.  Robot vision , 1986, MIT electrical engineering and computer science series.

[22]  William Grimson,et al.  Object recognition by computer - the role of geometric constraints , 1991 .

[23]  Geoffrey D. Sullivan,et al.  Pose refinement of active models using forces in 3D , 1994, ECCV.

[24]  Olivier Faugeras,et al.  3D Dynamic Scene Analysis , 1992 .

[25]  Tieniu Tan,et al.  Fast Vehicle Localisation and Recognition Without Line Extraction and Matching , 1994, BMVC.

[26]  Arthur Gelb,et al.  Applied Optimal Estimation , 1974 .

[27]  Li Du,et al.  Quantitative analysis of the viewpoint consistency constraint in model-based vision , 1993, 1993 (4th) International Conference on Computer Vision.

[28]  Hans-Hellmut Nagel,et al.  Association of Motion Verbs with Vehicle Movements Extracted from Dense Optical Flow Fields , 1994, ECCV.

[29]  Allen R. Hanson,et al.  Robust methods for estimating pose and a sensitivity analysis , 1994 .

[30]  David G. Lowe,et al.  Robust model-based motion tracking through the integration of search and estimation , 1992, International Journal of Computer Vision.

[31]  Hans-Hellmut Nagel,et al.  Model-based object tracking in monocular image sequences of road traffic scenes , 1993, International Journal of Computer 11263on.

[32]  Hans-Hellmut Nagel,et al.  3D pose estimation by fitting image gradients directly to polyhedral models , 1995, Proceedings of IEEE International Conference on Computer Vision.

[33]  Tieniu Tan,et al.  Pose Determination and Recognition of Vehicles in Traffic Scenes , 1994, ECCV.

[34]  V. von Holt.  Tracking and classification of overtaking vehicles on Autobahnen , 1994 .