激光与光电子学进展, 2019, 56 (23): 231009, 网络出版: 2019-11-27   

复杂光照条件下的交通标志检测与识别 下载: 1009次

Traffic Sign Detection and Recognition Under Complicated Lighting Conditions
作者单位
重庆交通大学交通运输学院, 重庆 400074
摘要
针对现有主流检测算法在低光照或光照条件强烈变化情况下对交通标志检测精度不足、漏检现象严重的问题,提出一种改进后的基于图像关键点统计变换(MCT)特征的Adaboost集成算法,以降低样本图像对光照变化的敏感性,通过对图像关键点进行提取并建立弱分类器,增强噪声和部分遮挡情况下算法的抗干扰能力,同时采用多尺度特征融合算法实现交通标志的分类识别。选用德国交通标志数据集(GTSDB、GTSRB)和自建数据集对所提算法性能进行验证,结果表明,在三类数据集中本文算法均具有最佳检测率与识别率,对于低光照条件下的交通标志图像,本文算法的检测精确率为94.96%,在复杂光照环境下具有较好的稳健性。
Abstract
Herein, we investigate solutions to address various problems, including the low detection precision and leak detection of the traffic signs, associated with the major detection algorithms under conditions of low illumination or intense variation of lighting. We propose an improved integrated Adaboost algorithm based on multicomponent transformation of the characteristics of key points of image to reduce the sensitivity of a sample image to illumination variation. The proposed algorithm extracts the key points of image and builds a weak classifier to reinforce the anti-disturbance ability of the algorithm under conditions of noise and partial obscurity. Meanwhile, the multi-scale feature fusion algorithm is used to classify and recognize the traffic signs. Furthermore, the German traffic sign datasets (the GTSDB and GTSRB datasets, respectively) and the self-built dataset are used to verify the performance of the proposed algorithm. The results denote that the proposed algorithm exhibits the highest detection and recognition rates when compared to other existing algorithms based on these three datasets. For the images of traffic signs under low illumination, the detection accuracy of proposed algorithm is 94.96%, indicating good robustness in complicated lighting environments.

屈治华, 邵毅明, 邓天民, 朱杰, 宋晓华. 复杂光照条件下的交通标志检测与识别[J]. 激光与光电子学进展, 2019, 56(23): 231009. Zhihua Qu, Yiming Shao, Tianmin Deng, Jie Zhu, Xiaohua Song. Traffic Sign Detection and Recognition Under Complicated Lighting Conditions[J]. Laser & Optoelectronics Progress, 2019, 56(23): 231009.

本文已被 5 篇论文引用
被引统计数据来源于中国光学期刊网
引用该论文: TXT   |   EndNote

相关论文

加载中...

关于本站 Cookie 的使用提示

中国光学期刊网使用基于 cookie 的技术来更好地为您提供各项服务,点击此处了解我们的隐私策略。 如您需继续使用本网站,请您授权我们使用本地 cookie 来保存部分信息。
全站搜索
您最值得信赖的光电行业旗舰网络服务平台!