论文信息 - Multi-texture modeling of 3D traffic scenes

Multi-texture modeling of 3D traffic scenes

We present a system for 3D reconstruction of traffic scenes. Traffic surveillance is a challenging scenario for 3D reconstruction in cases, where only a small number of views is available that do not contain much overlap. We address the possibilities and restrictions for modeling such scenarios with only a few cameras and introduce a compositor that allows rendering of the semi automatically generated 3D scenes. Some of the occurring problems concern camera images, which might show a common background area, but can still differ drastically in lighting effects. For foreground objects nearly no common visual information might be available, as angles between cameras may exceed even 90/spl deg/.

[1] John B. Shoven,et al. I , Edinburgh Medical and Surgical Journal.

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

[3] Olaf Munkelt,et al. Adaptive Background Estimation and Foreground Detection using Kalman-Filtering , 1995 .

[4] Marc Levoy,et al. Light field rendering , 1996, SIGGRAPH.

[5] Tieniu Tan,et al. An Integrated Traffic and Pedestrian Model-Based Vision System , 1997, BMVC.

[6] Hironobu Fujiyoshi,et al. A System for Video Surveillance and Monitoring CMU VSAM Final Report , 1999 .

[7] Takeo Kanade,et al. A System for Video Surveillance and Monitoring , 2000 .

[8] Oliver Schreer,et al. 3D analysis and image-based rendering for immersive TV applications , 2002, Signal Process. Image Commun..

[9] Philip H. S. Torr,et al. The Development and Comparison of Robust Methods for Estimating the Fundamental Matrix , 1997, International Journal of Computer Vision.

[10] Steven M. Seitz,et al. Photorealistic Scene Reconstruction by Voxel Coloring , 1997, International Journal of Computer Vision.

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