基于颜色和标志边缘特征的交通标志检测

基金项目: 国家重点基础研究发展计划资助项目(2006CB705500)，国家自然科学基金资助项目(40571134)

详细信息

Traffic Sign Detection Based on Color and Boundary Feature

¹State Key Laboratory for Information Engineering in Surveying,Mapping and Remote Sensing, Wuhan University,129 Luoyu Road,Wuhan 430079,China;²Traffic Research Center,Wuhan University,129 Luoyu Road,Wuhan 430079,China

Funds: 国家重点基础研究发展计划资助项目(2006CB705500)，国家自然科学基金资助项目(40571134)

摘要: 首先利用禁令标志明显的红色边界和白色区域分别并行地提取可能的交通标志颜色,然后对其两者融合,其目的是减少漏检率;融合后的影像通过Canny算子提取其边界,再根据边界的圆形度参数判断是否为圆形区域。实验结果显示,本算法能够很好地检测和定位禁令标志。
- 交通标志 /
- 检测 /
- Canny算子 /
- 定位
Abstract: This paper mainly presents an off-line traffic sign detection approach.Because their color and shapes feature are very different from natural environments,the algorithm described in this paper takes advantage of these features.It has two main parts.The first one uses the feature of red boundary and white region to segment the image,and then fuse their segmentation image.The second one uses Canny operator to analysis the boundary shape and locate the traffic signs.Some results from natural scenes are shown.
- traffic sign /
- detection /
- canny operator /
- image segmentation