A Saliency-Based Cascade Method for Fast Traffic Sign Detection

doi:10.1109/IVS.2015.7225683

CORC > 自动化研究所 > 中国科学院自动化研究所 > 模式识别国家重点实验室 > 模式分析与学习团队

	A Saliency-Based Cascade Method for Fast Traffic Sign Detection
	Wang Dongdong1 ; Yue Shigang 2; Xu Jiawei 2; Hou Xinwen1 ; Liu Cheng-Lin1
	2015-06
会议日期	2015-6-28-2015-7-1
会议地点	韩国首尔
关键词	Traffic Sign Detection Cascade Neighbor Scale Awareness
DOI	10.1109/IVS.2015.7225683
页码	180 - 185
英文摘要	We propose a cascade method for fast and accurate traffic sign detection. The main feature of the method is that mid-level saliency test is used to efficiently and reliably eliminate background windows. Fast feature extraction is adopted in the subsequent stages for rejecting more negatives. Combining with neighbor scales awareness in window search, the proposed method runs at 3~5 fps for high resolution (1360×800) images, 2~7 times as fast as most state-of-the-art methods. Compared with them, the proposed method yields competitive performance on prohibitory signs while sacrifices performance moderately on danger and mandatory signs.
会议录	2015 IEEE Intelligent Vehicles Symposium (IV)
学科主题	模式识别与智能系统
语种	英语
内容类型	会议论文
源URL	[http://ir.ia.ac.cn/handle/173211/11750]
专题	自动化研究所_模式识别国家重点实验室_模式分析与学习团队
通讯作者	Wang Dongdong
作者单位	1.中科院自动化研究所 2.英国林肯大学
推荐引用方式 GB/T 7714	Wang Dongdong,Yue Shigang,Xu Jiawei,et al. A Saliency-Based Cascade Method for Fast Traffic Sign Detection[C]. 见:. 韩国首尔. 2015-6-28-2015-7-1.