Semi-transparent vision for driving assistance
Koichiro Suzuki, Naoki Hashimoto
Proceedings of the 11th ACM SIGGRAPH International Conference on Virtual-Reality Continuum and its Applications in Industry, 2012, pp. 99--102.
Abstract: A lack of recognition with blind spots of driver's view is one of causes of traffic accidents. In this research, we propose a visual assistance system that can assist the driver's vision obstructed by the preceding large vehicle by making the blind spots semi-transparent. Under the use of this system, each vehicle should be equipped with in-vehicle stereo camera which captures forward. And in-vehicle camera images are shared with inter-vehicle communication to supplement other vehicle driver's vision. The assistance images for drivers are generated from shared preceding vehicle camera images and reconstructed by cutting the blind spot region and positioning with estimated relation using computer vision techniques. In this paper, we describe the methods of estimation of the relative positions and generation of the assistance images. Further, we indicate the prototype implementation of proposed system and the assistance presentation result of it.
@inproceedings{10.1145-2407516.2407547,
author = {Koichiro Suzuki and Naoki Hashimoto},
title = {Semi-transparent vision for driving assistance},
booktitle = {Proceedings of the 11th ACM SIGGRAPH International Conference on Virtual-Reality Continuum and its Applications in Industry},
pages = {99--102},
year = {2012},
}
Return to the search page.
graphbib: Powered by "bibsql" and "SQLite3."