An Integrated Traffic and Pedestrian Model-Based Vision System

The paper describes a novel integrated vision system in which two autonomous visual modules are combined to interpret a dynamic scene. The first module employs a 3D model-based scheme to track rigid objects such as vehicles. The second module uses a 2D deformable model to track non-rigid objects such as people. The principal contribution is a novel method for handling occlusion between objects within the context of this hybrid tracking system. The practical aim of the work is to derive a scene description that is sufficiently rich to be used in a range of surveillance tasks. The paper describes each of the modules in outline before detailing the method of integration and the handling of occlusion in particular. Experimental results are presented to illustrate the performance of the system in a dynamic outdoor scene involving cars and people.

[1]  David C. Hogg,et al.  Learning Flexible Models from Image Sequences , 1994, ECCV.

[2]  Geoff Sullivan.  Model-based vision for traffic scenes using the ground-plane constraint , 1995 .

[3]  Lee S Baumann,et al.  Proceedings of the Image Understanding Workshop, Held at Los Angeles, California November 7-8, 1979 , 1979 .

[4]  Hans-Hellmut Nagel,et al.  From image sequences towards conceptual descriptions , 1988, Image Vis. Comput..

[5]  G. Sullivan,et al.  MODEL-BASED VISION FOR ROAD TRAFFIC UNDERSTANDING , 1993 .

[6]  Tieniu Tan,et al.  Linear Algorithms for Object Pose Estimation , 1992, BMVC.

[7]  K.D. Baker,et al.  Efficient image gradient-based object localisation and recognition , 1996, Proceedings CVPR IEEE Computer Society Conference on Computer Vision and Pattern Recognition.

[8]  Tieniu Tan,et al.  Recognizing objects on the ground-plane , 1994, Image Vis. Comput..

[9]  Shaogang Gong,et al.  Visual Surveillance in a Dynamic and Uncertain World , 1995, Artif. Intell..

[10]  A. Jacobson,et al.  Morphometric tools for landmark data , 1993 .

[11]  Timothy F. Cootes,et al.  Building and using flexible models incorporating grey-level information , 1993, 1993 (4th) International Conference on Computer Vision.

[12]  Karl Rohr,et al.  Incremental recognition of pedestrians from image sequences , 1993, Proceedings of IEEE Conference on Computer Vision and Pattern Recognition.

[13]  Tieniu Tan,et al.  Recognising Objects on the Ground-plane , 1993, BMVC.

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

[15]  Adam Baumberg.  Hierarchical shape fitting using an iterated linear filter , 1998, Image Vis. Comput..

[16]  G. D. Sullivan,et al.  Natural and artificial low-level seeing systems - Visual interpretation of known objects in constrained scenes , 1992 .

[17]  David C. Hogg,et al.  An Adaptive Eigenshape Model , 1995, BMVC.

[18]  Nigel J. B. McFarlane,et al.  Segmentation and tracking of piglets in images , 1995, Machine Vision and Applications.

[19]  Geoffrey D. Sullivan,et al.  A Filter for Visual Tracking Based on a Stochastic Model for Driver Behaviour , 1996, ECCV.

[20]  David C. Hogg.  Model-based vision: a program to see a walking person , 1983, Image Vis. Comput..

[21]  Larry S. Davis,et al.  3-D model-based tracking of humans in action: a multi-view approach , 1996, Proceedings CVPR IEEE Computer Society Conference on Computer Vision and Pattern Recognition.

[22]  Geoffrey D. Sullivan,et al.  Model-based vehicle detection and classification using orthographic approximations , 1997, Image Vis. Comput..

[23]  David C. Hogg,et al.  An efficient method for contour tracking using active shape models , 1994, Proceedings of 1994 IEEE Workshop on Motion of Non-rigid and Articulated Objects.