激光与光电子学进展, 2018, 55 (9): 091006, 网络出版: 2018-09-08
一种基于HDR技术的交通标志牌检测和识别方法 下载: 739次
A Method of Traffic Sign Detection and Recognition Based on HDR Technology
图像处理 高动态范围 交通标志牌 检测 识别 逆色调映射 多曝光融合 image processing high dynamic range traffic signs detection recognition inverse tone mapping multi-exposure fusion
摘要
现有基于低动态范围(LDR)图像的识别方法在良好的曝光环境下, 能取得较为理想的结果, 但其容易受照明条件的限制以及天气状况的影响, 稳健性不强。为此, 提出一种基于高动态范围(HDR)技术的识别方法。通过改进的逆色调映射算法, 对相机捕获的不同曝光的LDR图像进行自适应亮度范围拉伸, 分别生成明暗两幅子图像, 再采用多曝光融合算法对子图像进行融合, 生成一幅HDR图像代替原LDR图像进行识别。实验结果表明, 该方法可较好地提高交通标志牌的检测与识别正确率。
Abstract
The existing methods of traffic sign detection and recognition based on low dynamic range (LDR) images can achieve ideal results in good exposure environment. But they are vulnerable to the limitation of lighting and weather conditions, leading to weak robustness. For this reason, we propose a recognition method based on the high dynamic range (HDR) technology. The captured LDR images under different exposure conditions are adaptively stretched in the luminance range by the improved inverse tone mapping algorithm, generating two sub-images separately. Then an HDR image produced by the multi-exposure fusion algorithm is used instead of the original LDR images for recognition. The experimental results show that the proposed method can greatly improve the accuracy of traffic sign detection and recognition.
张淑芳, 朱彤. 一种基于HDR技术的交通标志牌检测和识别方法[J]. 激光与光电子学进展, 2018, 55(9): 091006. Zhang Shufang, Zhu Tong. A Method of Traffic Sign Detection and Recognition Based on HDR Technology[J]. Laser & Optoelectronics Progress, 2018, 55(9): 091006.