吉林大学学报(工学版) ›› 2021, Vol. 51 ›› Issue (1): 323-330.doi: 10.13229/j.cnki.jdxbgxb20190835

• 通信与控制工程 • 上一篇    

基于优化MSR的夜间道路图像增强方法

刘富1,2(),刘璐2,侯涛2,刘云2()   

  1. 1.吉林大学 汽车仿真与控制国家重点实验室,长春 130022
    2.吉林大学 通信工程学院,长春 130022
  • 收稿日期:2019-08-23 出版日期:2021-01-01 发布日期:2021-01-20
  • 通讯作者: 刘云 E-mail:liufu@jlu.edu.cn;liuyun313@jlu.edu.cn
  • 作者简介:刘富(1968-),男,教授,博士生导师.研究方向:模式识别.E-mail:liufu@jlu.edu.cn
  • 基金资助:
    国家自然科学基金重点项目(51835006);中国博士后科学基金项目(2019M651204)

Night road image enhancement method based on optimized MSR

Fu LIU1,2(),Lu LIU2,Tao HOU2,Yun LIU2()   

  1. 1.State Key Laboratory of Automotive Simulation and Control,Jilin University,Changchun 130022,China
    2.College of Communication Engineering,Jilin University,Changchun 130022,China
  • Received:2019-08-23 Online:2021-01-01 Published:2021-01-20
  • Contact: Yun LIU E-mail:liufu@jlu.edu.cn;liuyun313@jlu.edu.cn

摘要:

为了提高夜间道路图像质量,提升目标在图像中的可见度及对比度,降低夜间道路图像目标检测难度,提出了一种基于优化多尺度Retinex算法(MSR)的夜间道路图像增强方法。首先,将RGB图像转换到YUV色彩空间;其次,将最小可觉差(JND)的倒数作为MSR算法中入射图像的系数构建优化MSR算法,并利用该优化算法对Y通道进行亮度自适应调节,同时对U、V通道按比例调整得到新图像;然后,将得到的新图像与原始图像按照1:1比例结合以保留图像细节;最后,利用限制对比度自适应直方图均衡化方法(CLAHE)提升图像对比度,得到最终增强图像。在包含有770张夜间道路图像的数据集上开展实验,结果表明:本文方法实现了夜间道路图像亮度自适应调节,缓解了图像亮度不均匀的情况,增强了图像的清晰度,增加了图像的细节信息,利用支持向量机算法(SVM)进行前方车辆检测,漏检率、误检率分别下降了2.61%、4.35%。

关键词: 模式识别与智能系统, 图像处理, 夜间图像增强, 优化MSR算法, 亮度自适应调节

Abstract:

In order to improve the image quality of night roads, to promote the visibility and contrast of the target in the image, and to reduce the difficulty of target detection in night road image, a night road image enhancement method based on the optimized Multi-scale Retinex (Multi scale retinex,MSR) algorithm is proposed in this paper. First, the Red, Green and Blue (RGB) image is converted to the YUV color space. Secondly, the optimized MSR algorithm is constructed by using the reciprocal of the Just Noticeable Distortion (Just noticeable distortion,JND) as the coefficient before the incident image in the MSR algorithm, which is used to adjust the brightness of the channel Y adaptively. Meanwhile, the channels of U and V are proportionally adjusted to obtain a new image, which is then combined with the original image in a 1∶1 ratio to preserve the image details. Finally, the Contrast-limited Adaptive Histogram Equalization method (CLAHE) is used to improve image contrast. Experiments on datasets containing 770 images of night road show that the proposed method exhibits the ability to adaptive adjustment of night image brightness, alleviate uneven brightness of the image, enhance the sharpness of nighttime images and the detail information of image. By using the support vector machine algorithm to detect vehicles in image, the missed detection rate and false detection rate are decreased by 2.61% and 4.35%, respectively..

Key words: pattern recognition and intelligent system, image processing, night image enhancement, optimizing MSR algorithm, brightness adaptive adjustment

中图分类号: 

  • TP301.6

图1

Retinex原理图"

图2

夜间道路图像增强流程框图"

图3

夜间道路数据集"

图4

道路灯光复杂环境"

图5

道路灯光较暗环境"

图6

小区灯光分布不均匀环境"

图7

小区灯光较暗环境"

图8

图像评价指标结果对比"

表1

图像增强前后分类实验结果对比 (%)"

增强方法准确率召回率误检率漏检率F1-measure

原始图像

MSRCR

文献[17]

本 文

93.90

93.00

92.61

97.40

93.91

92.17

90.43

96.52

6.09

6.09

5.22

1.74

6.09

7.83

9.57

3.48

93.90

92.58

91.51

96.96

1 朱爱国. 汽车驾驶员夜间安全行车技术分析[J]. 时代汽车, 2018(3): 8-9.
Zhu Ai-guo. Analysis of car driver's night safety driving technique[J]. Auto Time, 2018(3): 8-9.
2 周苏, 钱辰, 肖建华. 基于单目视觉的前方车辆检测方法[C]∥ 第十五届国际汽车交通安全学术会议论文集, 重庆, 2018: 321-327.
Zhou Su, Qian Chen, Xiao Jian-hua. A vehicles detection algorithm based on monocular vision[C]∥Proceeding of the 15th International Forum of Automotive Traffic Safety, Chongqing,2018: 321-327.
3 徐岩, 孙美双. 基于卷积神经网络的水下图像增强方法[J]. 吉林大学学报:工学版, 2018, 48(6): 1895-1903.
Xu Yan, Sun Mei-shuang. Enhancing underwater image based on convolutional neural networks[J]. Journal of Jilin University(Engineering and Technology Edition), 2018, 48(6): 1895-1903.
4 Dong X, Pang Y, Wen J. Fast efficient algorithm for enhancement of low lighting video[C]∥IEEE International Conference on Multimedia and Expo,Barcelona,USA, 2011:1-6.
5 Li J, Li S Z, Pan Q, et al. Illumination and motion-based video enhancement for night surveillance[C]∥IEEE International Workshop on Visual Surveillance & Performance Evaluation of Tracking & Surveillance, Beijing, China, 2005: 169-175.
6 Fattal R, Lischinski D, Werman M. Gradient domain high dynamic range compression[C]∥ACM on Conference on Computer Graphics & Interactive Techniques, San Antonio, Texas,USA, 2002: 249-256.
7 Land E H. Recent advances in retinex theory and some implications for cortical computations:color vision and the nature image[J]. Proceedings of the National Academy of Sciences of the United States of America, 1983, 80(16): 5163-5169.
8 Jobson D J, Rahman Z, Woodell G A. Properties and performance of a center/surround retinex[J]. IEEE Transactions on Image Processing, 1997, 6(3): 451-462.
9 Jobson D J, Rahman Z, Woodell G A. A multiscale retinex for bridging the gap between color images and the human observation of scenes[J]. IEEE Transactions on Image Processing, 1997, 6(7): 965-976.
10 Lin H, Shi Z. Multi-scale retinex improvement for nighttime image enhancement[J]. Optik-International Journal for Light and Electron Optics, 2014, 125(24): 7143-7148.
11 徐跃书. 不良环境下的视频增强[D]. 北京:北京邮电大学信息与通信工程学院, 2017.
Xu Yue-shu. Video enhancement under bad light[D]. Beijing:School of Information and Communication Engineering,Beijing University of Post and Telecommunications, 2017.
12 Land E H, McCann J J. Lightness and retinex theory[J]. Journal of the Optical Society of America, 1971, 61(1): 1-11.
13 Rahman Z U, Jobson D J, Woodell G A. Multi-scale retinex for color image enhancement[C]∥International Conference on Image Processing, Lausanne, Switzerland, 1996:1003-1006.
14 乔丽, 刘继华. 基于直方图均衡变换的彩色YUV图像边缘检测方法[J]. 电视技术, 2018, 42(4): 20-25.
Qiao Li, Liu Ji-hua. Color YUV image edge detection method based on histogram equalization transform[J]. Video Engineering, 2018, 42(4): 20-25.
15 Chou C H, Li Y C. A perceptually tuned subband image coder based on the measure of just-noticeable-distortion profile[J]. IEEE Transactions on Circuits and Systems for Video Technology,1995,5(6):467-476.
16 Zhang X, Lin W, Xue P. Just-noticeable difference estimation with pixels in images[J]. Journal of Visual Communication and Image Representation,2008, 19(1): 30-41.
17 Fu Q, Jung C, Xu K. Retinex-based perceptual contrast enhancement in images using luminance adaptation[J]. IEEE Access, 2018, 6: 61277-61286.
18 Zuiderveld K. Contrast Limited Adaptive Histogram Equalization[M]. New York: Academic Press Professional, Inc., 1994.
19 Jobson D J, Rahman Z U, Woodell G A. The statistics of visual representation[J]. Visual Information Processing, 2002, 4736(2): 25-35.
20 郑肇葆, 郑宏. 基于图像信息熵的图像分类[J]. 测绘地理信息, 2018, 43(5): 1-3.
Zheng Zhao-bao, Zheng Hong. Image classification based on image information entropy[J].Journal of Geomatics, 2018, 43(5): 1-3.
21 肖祥元, 景文博, 赵海丽. 基于峰值信噪比改进的图像增强算法[J]. 长春理工大学学报:自然科学版, 2017, 40(4): 83-86, 92.
Xiao Xiang-yuan, Jing Wen-bo, Zhao Hai-li. An improved image enhancement algorithm based on the peak-signal to noise ratio[J]. Journal of Changchun University of Science and Technology, 2017, 40(4): 83-86, 92.
22 Dalal N, Triggs B. Histograms of oriented gradients for human detection[C]∥IEEE Computer Society Conference on Computer Vision and Pattern Recognition(CVPR'05), San Diego, CA, USA, 2005: 886-893.
23 Khammari A, Nashashibi F, Abramson Y, et al. Vehicle detection combining gradient analysis and AdaBoost classification[C]∥Intelligent Transportation Systems, Vienna, Austria, 2005:66-71.
[1] 刘哲, 徐涛, 宋余庆, 徐春艳. 基于NSCT变换和相似信息鲁棒主成分分析模型的图像融合技术[J]. 吉林大学学报(工学版), 2018, 48(5): 1614-1620.
[2] 刘富, 兰旭腾, 侯涛, 康冰, 刘云, 林彩霞. 基于优化k-mer频率的宏基因组聚类方法[J]. 吉林大学学报(工学版), 2018, 48(5): 1593-1599.
[3] 车翔玖, 王利, 郭晓新. 基于多尺度特征融合的边界检测算法[J]. 吉林大学学报(工学版), 2018, 48(5): 1621-1628.
[4] 梁士利, 柴宗谦, 张玲, 吴颜生, 曹春雷. 基于偏X型细胞自动机的图像加密方法[J]. 吉林大学学报(工学版), 2017, 47(5): 1653-1660.
[5] 何光, 张铭, 袁双石. 微机电系统后坐保险机构温度相关动态特性[J]. 吉林大学学报(工学版), 2017, 47(1): 145-150.
[6] 李健, 李赫宇, 姚汝婧, 吴林. 基于均值滤波的改进 Canny 算法在核磁共振图像边缘检测中的应用[J]. 吉林大学学报(工学版), 2016, 46(5): 1704-1709.
[7] 肖钟捷. 基于小波空间特征谱熵的数字图像识别[J]. 吉林大学学报(工学版), 2015, 45(6): 1994-1998.
[8] 韩成, 张超, 秦贵和, 薛耀红, 杨帆, 范静涛, 刘文静. 大型正交多幕投影系统光辐射补偿算法[J]. 吉林大学学报(工学版), 2015, 45(4): 1266-1273.
[9] 张金果,郭海涛,吴君鹏,李依桐. 改进的最小交叉Tsallis熵的小目标声呐图像分割[J]. 吉林大学学报(工学版), 2014, 44(3): 834-839.
[10] 黄德天, 刘雪超, 吴志勇, 梁敏华. 基于CameraLink的高速图像采集处理系统设计[J]. 吉林大学学报(工学版), 2013, 43(增刊1): 309-312.
[11] 冯鑫, 王晓明, 党建武, 沈瑜. 基于插值Directionlet变换的图像融合方法[J]. 吉林大学学报(工学版), 2013, 43(04): 1127-1132.
[12] 金立生, 咸化彩, 祖力, 孙玉芹, 侯海晶, 牛清宁. 小区民用车辆车牌自动识别算法[J]. 吉林大学学报(工学版), 2012, 42(增刊1): 166-169.
[13] 段跃华, 张肖宁. 基于CT断层扫描图像的混凝土粗集料三维虚拟筛分[J]. , 2012, 42(04): 918-923.
[14] 王芳荣, 林晓珑, 王晓鹏, 张佳全, 张铁强, 冯毅. 粘胶长丝在线实时监测系统设计与处理算法[J]. 吉林大学学报(工学版), 2011, 41(增刊2): 288-291.
[15] 林晓珑, 张铁强, 张佳全, 何丽桥. 粘纤用喷丝板堵孔状态自动检测系统[J]. 吉林大学学报(工学版), 2011, 41(增刊1): 293-296.
Viewed
Full text


Abstract

Cited

  Shared   
  Discussed   
No Suggested Reading articles found!