NaviView: bird's-eye view for highway drivers using roadside cameras

AHS (Automated Highway System) will increase the traffic potential of highways because it enables drivers to shorten the distance between cars. On the other hand, AHS may make the drivers uncomfortable because it presents them with a reduced field of vision of the car ahead and may induce anxiety over the reliability of the control system. In order to improve the comfort of drivers under the control of AHS it is necessary to recover the driver's field of vision. We propose the NaviView system for this purpose. In AHS, the entire traffic load on the highway is visually monitored by many roadside video cameras. NaviView utilizes these video images for the recovery of the driver's visual field. It enables the driver to observe the behavior of other cars by means of a virtual view from a point just above his car. The virtual view presented to the driver is generated by combining the video images of the fixed roadside cameras. The proposed algorithm was tested by using a miniature highway model and a real road scene.

[1]  Richard Szeliski,et al.  Video mosaics for virtual environments , 1996, IEEE Computer Graphics and Applications.

[2]  Steven M. Seitz,et al.  View morphing , 1996, SIGGRAPH.

[3]  Shenchang Eric Chen,et al.  QuickTime VR: an image-based approach to virtual environment navigation , 1995, SIGGRAPH.

[4]  Takeo Kanade,et al.  Virtual worlds using computer vision , 1998, Proceedings 1998 IEEE and ATR Workshop on Computer Vision for Virtual Reality Based Human Communications.

[5]  Jitendra Malik,et al.  Modeling and Rendering Architecture from Photographs: A hybrid geometry- and image-based approach , 1996, SIGGRAPH.

[6]  Yuichi Ohta,et al.  3D image display with motion parallax by camera matrix stereo , 1996, Proceedings of the Third IEEE International Conference on Multimedia Computing and Systems.