一种基于Dark Channel Prior图像去雾改进算法
An Improved Images Defogging Algorithm Based on Dark Prior Channel
DOI: 10.12677/CSA.2020.1012230, PDF,    科研立项经费支持
作者: 阳小燕, 宗建华, 夏国清：广州大学华软软件学院，广东 广州；许伦辉：广州大学华软软件学院，广东 广州;华南理工大学土木与交通学院，广东 广州
关键词: 图像去雾；Dark Channel Prior；滤波；去噪；Image Defogging； Dark Channel Prior； Filter； Denoising
摘要: 探测机器人视觉导航中，现场烟雾或者有色气体会直接导致回传的视频图像雾化且充满噪声，图像品质差，影响后续目标检测与跟踪。针对上述问题，本文提出了一种基于Dark Channel Prior图像去雾改进算法，该算法首先对采集到图像进行灰度化预处理，再用滤波器进行去噪处理，有效去除采图像中的噪声，使待处理图像更加平滑，最后使用Dark Channel Prior去雾算法进行去雾处理，得到高品质图像。根据仿真实验表明，本算法能够有效解决图像去雾中的噪声问题，提高传送画面的清晰度，并缩短图像处理时间，时实性更强。
Abstract: In the vision navigation of detection robot, the scene smoke or colored gas will directly cause the video image to be atomized and filled with noise, and the image quality will be poor, which will affect the subsequent target detection and tracking. In order to solve these problems, an improved fog removal algorithm based on Dark Prior Channel image is proposed in this paper. Firstly, the collected image is pre-processed by grayscale; then the noise is removed by filter; and the noise in the collected image is effectively removed; finally, we use the Dark Channel Prior algorithm to defog the image, and get the high quality image. The simulation results show that the algorithm can effectively solve the noise problem in image defogging, improve the clarity of the transmitted image, shorten the image processing time and improve the real-time performance.
文章引用：阳小燕, 许伦辉, 宗建华, 夏国清. 一种基于Dark Channel Prior图像去雾改进算法[J]. 计算机科学与应用, 2020, 10(12): 2189-2196. https://doi.org/10.12677/CSA.2020.1012230

参考文献

[1] 张登, 银鞠铭, 烨钱雯. 图像去雾算法研究现状与展望[J]. 南京邮电大学学报(自然科学版), 2020(5): 1-11.
[2] 杨燕, 姜沛沛, 岳辉. 基于线性变换的自适应透射率去雾算法[J]. 工程科学与技术. 2020(5): 194-200.
[3] 何宜鸿, 李彦锋, 黄树恺, 谭万钏. 基于深度卷积神经网络的自适应图像去雾算法[J]. 电子科技, 2020(8): 70-73.
[4] 邹昌帆, 黄富瑜, 朱晓兵, 孙明, 冯志义. 一种用于自动调焦图像的降噪方法[J]. 光学仪器, 2016(1): 45-48.
[5] 乔元秀, 程朋乐. 林火烟雾图像识别技术研究[J]. 计算机科学与应用, 2016, 6(8): 465-471.
[6] 李冠章, 罗武胜, 李沛, 吕海宝. 修正Retinex照射反射模型的彩色图像增强[J]. 光学技术, 2010, 36(2): 205-208.
[7] 苑尚博, 高轶琛, 宋笑影, 等. 暗通道结合小波变换的雾天图像复原[J]. 计算机应用与软件, 2015, 32(10): 192-195.
[8] Meng, G.F., Wang, Y., Duan, J.Y., Xiang, S.M. and Pan, C.H. (2013) Efficient Image Dehazing with Boundary Constraint and Contextual Regularization. IEEE International Conference on Computer Vision, 9, 617-624. [Google Scholar] [CrossRef] 
[9] 邵明省. 基于混合暗通道算法的图像去雾研究[J]. 计量学报, 2020(7): 796-800.
[10] 赵阳, 王剑, 曹浩男. 基于自适应改进的遥感图像去雾算法研究[J]. 电子设计工程, 2019(19): 164-169.
[11] 乔美丽, 王平, 杜宏伟, 刘新新. 基于雾浓度的去雾方法[J]. 计算机科学与应用, 2018, 8(12): 1813-1822.
[12] 温立民, 巨永锋, 张昌利, 王会峰. 基于改进Kuwahara滤波的图像去雾算法[J]. 控制工程, 2019(5): 997-1002.
[13] Fan, Y. and Wu, X.F. (2013) A Research for Image Defogging Algorithm. Applied Mechanics and Materials, 26, 1653-1656. [Google Scholar] [CrossRef] 
[14] Zhang, X.J., Ng, M.K. and Bai, M. (2017) A Fast Algorithm for Deconvolution and Poisson Noise Removal. Journal of Scientific Computing, 75, 1535-1554. [Google Scholar] [CrossRef] 
[15] Ma, R.Q. and Zhang, S.J. (2019) An Improved Color Image Defogging Algorithm Using Dark Channel Model and Enhancing Saturation. Optik—International Journal for Light and Electron Optics, 18, 997-1000. [Google Scholar] [CrossRef] 
[16] He, K.M., Sun, J. and Tang, X.O. (2011) Single Image Haze Re-moval Using Dark Channel Prior. IEEE Transactions on Pattern Analysis and Machine Intelligence, 33, 2341-2353. [Google Scholar] [CrossRef] 
[17] Guo, F., Tang, J. and Cai, Z.-X. (2014) Objective Measurement for Image Defogging Algorithms. Journal of Central South University, 21, 272-286. [Google Scholar] [CrossRef]