A Vision-Based Hierarchical Framework for Autonomous Front-Vehicle Taillights Detection and Signal Recognition | |
Cui, Zhiyong ; Yang, Shao-Wen ; Tsai, Hsin-Mu | |
2015 | |
英文摘要 | Automatically recognizing rear light signals of front vehicles can significantly improve driving safety by automatic alarm and taking actions proactively to prevent rear-end collisions and accidents. Much previous research only focuses on detecting brake signals at night. In this paper, we present the design and implementation of a robust hierarchical framework for detecting taillights of vehicles and estimating alert signals (turning and braking) in the daytime. The framework contains three-layers of processes, (i) detecting the vehicles in image; (ii) extracting taillight candidates using a clustering technique; and (iii) estimating rear-light signal states. The three-layer structure of the vision-based framework can effectively filter out noises in the image background and select correct pairs of taillights. Comparing to existing work addressing nighttime detection, the proposed method is capable of recognizing taillight signals under different illumination circumstances. The experiment results show our framework outperforms the state-of-the-art luminance-based method in different weather conditions during the daytime.; EI; CPCI-S(ISTP); 1201210546@pku.edu.cn; shao-wen.yang@intel.com; hsinmu@csie.ntu.edu.tw; 931-937; 2015-October |
语种 | 英语 |
出处 | 2015 IEEE 18TH INTERNATIONAL CONFERENCE ON INTELLIGENT TRANSPORTATION SYSTEMS |
DOI标识 | 10.1109/ITSC.2015.156 |
内容类型 | 其他 |
源URL | [http://ir.pku.edu.cn/handle/20.500.11897/436525] |
专题 | 软件与微电子学院 |
推荐引用方式 GB/T 7714 | Cui, Zhiyong,Yang, Shao-Wen,Tsai, Hsin-Mu. A Vision-Based Hierarchical Framework for Autonomous Front-Vehicle Taillights Detection and Signal Recognition. 2015-01-01. |
个性服务 |
查看访问统计 |
相关权益政策 |
暂无数据 |
收藏/分享 |
除非特别说明,本系统中所有内容都受版权保护,并保留所有权利。
修改评论