Traffic Sign Detection from Video: A Fast Approach with Tracking
Wang Dongdong; Hou Xinwen; Liu Cheng-Lin
2015-12
会议名称3rd Asian Conference on Pattern Recognition
会议录名称Asian Conference on Pattern Recognition
会议日期2015-12-3-2015-12-6
会议地点马来西亚吉隆坡
摘要
This paper proposes a fast approach for traffic sign detection from video. First, we modify the image-based detector HHVCas to improve its accuracy and speed, then apply it to video-based detection with further acceleration by tracking. For the image-based detector, by optimizing the parameters in the cascade using an unsupervised approach, we achieve performance comparable to the state-of-the-art while keeping the speed advantage. Parallelizing some steps in the HHVCas detector leads to 1:5x speedup and 20fps detection. In video, the detector achieves 2.8x speedup and performs 35 fps by tracking every other frame. It also obtains significant precision increase by 5~8% at high recall when exploiting temporal coherence of results in multiple frames.
 
关键词Traffic Sign Detection Tracking
学科领域模式识别与智能系统
收录类别EI
文献类型会议论文
条目标识符http://ir.ia.ac.cn/handle/173211/11767
专题模式识别国家重点实验室_模式分析与学习
通讯作者Wang Dongdong
作者单位中科院自动化研究所
推荐引用方式
GB/T 7714
Wang Dongdong,Hou Xinwen,Liu Cheng-Lin. Traffic Sign Detection from Video: A Fast Approach with Tracking[C],2015.
条目包含的文件 下载所有文件
文件名称/大小 文献类型 版本类型 开放类型 使用许可
Traffic Sign Detecti(406KB)会议论文 开放获取CC BY-NC-SA浏览 下载
个性服务
推荐该条目
保存到收藏夹
查看访问统计
导出为Endnote文件
谷歌学术
谷歌学术中相似的文章
[Wang Dongdong]的文章
[Hou Xinwen]的文章
[Liu Cheng-Lin]的文章
百度学术
百度学术中相似的文章
[Wang Dongdong]的文章
[Hou Xinwen]的文章
[Liu Cheng-Lin]的文章
必应学术
必应学术中相似的文章
[Wang Dongdong]的文章
[Hou Xinwen]的文章
[Liu Cheng-Lin]的文章
相关权益政策
暂无数据
收藏/分享
文件名: Traffic Sign Detection from Video-A Fast Approach with Tracking.pdf
格式: Adobe PDF
所有评论 (0)
暂无评论
 

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。