Image fusion dehazing algorithm based on minimum channel and logarithmic attenuation
-
摘要:
雾天各类图像采集系统获取的图像颜色退化,细节模糊,严重影响户外成像系统的稳定性和有效性,因此研究图像去雾技术很有必要。针对暗通道一类去雾算法边缘去雾不彻底问题,提出一种基于最小值通道与对数衰减的融合去雾算法。首先,对有雾图像的最小值通道图进行对数衰减作为先验假设条件,再进行交叉双边滤波消除纹理效应,在操作前后分别进行下采样和上采样操作以提高运算速度,求出初始透射率;然后,用Canny算子检测最小值通道图得到的边缘进行对数衰减,得到边缘信息图,将初始透射率与边缘信息图进行加权融合构成优化透射率;最后,结合改进的四叉树搜索法求得的大气光值反解大气散射模型,恢复无雾图像。实验结果表明:所提算法可以有效抑制光晕现象,去除边缘残雾,且实时性好。
Abstract:The image color degradation and blurred details acquired by various image acquisition systems in foggy weather seriously affect the stability and effectiveness of outdoor imaging system, so it is necessary to study image dehazing technology. Aimed at the incomplete edge dehazing of dark channel dehazing algorithm, a fusion dehazing method based on the minimum channel and logarithmic attenuation is proposed. Firstly, the logarithmic attenuation of the minimum channel map of the foggy image is taken as a priori hypothesis, and then cross-bilateral filtering is performed to eliminate the texture effect. Before and after the operation, downsampling and upsampling operations are performed respectively to improve the operation speed, then we get the initial transmittance. Secondly, Canny operator is used to detect the edge of the minimum channel and logarithmic attenuation is carried out to obtain the edge information map. The initial transmittance and the edge information map are weighted and fused to compose the optimal transmittance. Finally, the atmospheric light value obtained by the improved quadtree search method is used to solve the atmospheric scattering model and restore the fog-free image. The experimental results demonstrate that the proposed algorithm can effectively suppress halo effect and remove edge residual fog, and has good real-time performance.
-
Key words:
- image dehazing /
- image fusion /
- minimum channel /
- logarithmic mapping /
- cross-bilateral filtering
-
-
[1] 高若婉, 梅树立, 李丽, 等.基于小波精细积分与暗通道的农田图像去雾算法[J].农业机械学报, 2019, 50(S1):167-174. http://www.cnki.com.cn/Article/CJFDTotal-NYJX2019S1026.htmGAO R W, MEI S L, LI L, et al.Farmland image dehazing method based on wavelet precise integration and dark channel prior[J].Transactions of the Chinese Society of Agricultural Machinery, 2019, 50(S1):167-174(in Chinese). http://www.cnki.com.cn/Article/CJFDTotal-NYJX2019S1026.htm [2] 刘海波, 杨杰, 吴正平, 等.基于暗通道先验和Retinex理论的快速单幅图像去雾方法[J].自动化学报, 2015, 41(7):1264-1273. http://www.wanfangdata.com.cn/details/detail.do?_type=perio&id=xxydn201804016LIU H B, YANG J, WU Z P, et al.A fast single image dehazing method based on dark channel prior and Retinex theory[J].Acta Automatica Sinica, 2015, 41(7):1264-1273(in Chinese). http://www.wanfangdata.com.cn/details/detail.do?_type=perio&id=xxydn201804016 [3] 马忠丽, 文杰.融合边缘信息的单尺度Retinex海雾去除算法[J].计算机辅助设计与图形学学报, 2015, 27(2):217-225. http://www.wanfangdata.com.cn/details/detail.do?_type=perio&id=jsjfzsjytxxxb2015020004MA Z L, WEN J.Single-scale Retinex sea fog removal algorithm fused the edge information[J].Journal of Computer-Aided Design and Computer Graphics, 2015, 27(2):217-225(in Chinese). http://www.wanfangdata.com.cn/details/detail.do?_type=perio&id=jsjfzsjytxxxb2015020004 [4] 云海姣, 吴志勇, 王冠军, 等.结合直方图均衡和模糊集理论的红外图像增强[J].计算机辅助设计与图形学学报, 2015, 27(8):1498-1505. http://www.wanfangdata.com.cn/details/detail.do?_type=perio&id=jsjfzsjytxxxb201508018YUN H J, WU Z Y, WANG G J, et al.Enhancement of infrared image combined with histogram equalization and fuzzy set theory[J].Journal of Computer-Aided Design and Computer Graphics, 2015, 27(8):1498-1505(in Chinese). http://www.wanfangdata.com.cn/details/detail.do?_type=perio&id=jsjfzsjytxxxb201508018 [5] CAI B L, XU X M, JIA K, et al.Dehaze net:An end-to-end system for single image haze removal[J].IEEE Transactions on Image Processing, 2016, 25(11):5187-5198. doi: 10.1109/TIP.2016.2598681 [6] CHEN D D, HE M M, FAN Q N, et al.Gated context aggregation network for image dehazing and deraining[C]//2019 IEEE Winter Conference on Applications of Computer Vision.Piscataway: IEEE Press, 2019: 1375-1383. [7] DU Y X, LI X.Perceptually optimized generative adversarial network for single image dehazing[EB/OL].(2018-05-03)[2019-10-20].https://arxiv.org/abs/1805.01084. [8] HE K M, SUN J, TANG X O.Single image haze removal using dark channel prior[C]//IEEE Conference on Computer Vision and Pattern Recognition(CVPR).Piscataway: IEEE Press, 2009: 1956-1963. [9] HE K M, SUN J, TANG X O.Guided image filtering[C]//Proceedings of the 2010 Conference on Computer Vision, 2010: 1-14. [10] 陈书贞, 任占广, 练秋生.基于改进暗通道和导向滤波的单幅图像去雾算法[J].自动化学报, 2016, 42(3):455-465. http://www.wanfangdata.com.cn/details/detail.do?_type=perio&id=D01111331CHEN S Z, REN Z G, LIAN Q S.Single image dehazing algorithm based on improved dark channel prior and guided filter[J].Acta Automatica Sinica, 2016, 42(3):455-465(in Chinese). http://www.wanfangdata.com.cn/details/detail.do?_type=perio&id=D01111331 [11] 杨燕, 陈高科, 周杰.基于高斯权重衰减的迭代优化去雾算法[J].自动化学报, 2019, 45(4):819-828. http://www.wanfangdata.com.cn/details/detail.do?_type=perio&id=zdhxb201904016YANG Y, CHEN G K, ZHOU J.Iterative optimization defogging algorithm using Gaussian weight decay[J].Acta Automatica Sinica, 2019, 45(4):819-828(in Chinese). http://www.wanfangdata.com.cn/details/detail.do?_type=perio&id=zdhxb201904016 [12] 杨燕, 陈高科.基于光补偿和逐像素透射率的图像复原算法[J].通信学报, 2017, 38(5):48-56. http://www.wanfangdata.com.cn/details/detail.do?_type=perio&id=txxb201705006YANG Y, CHEN G K.Single image visibility restoration using optical compensation and pixel-by-pixel transmission estimation[J].Journal on Communications, 2017, 38(5):48-56(in Chinese). http://www.wanfangdata.com.cn/details/detail.do?_type=perio&id=txxb201705006 [13] YANG Y, ZHANG C, LIU L L, et al.Visibility restoration of single image captured in dust and haze weather conditions[J].Multidim System Sign Process, 2020, 31:619-633. doi: 10.1007/s11045-019-00678-z [14] MCCARTNEY E J.Optics of the atmosphere:Scattering by mole-cules and particles[M].New York:John Wiley and Sons, 1976:421. [15] 王泽胜, 董宝田, 赵芳璨, 等.基于改进暗通道先验的交通图像去雾新方法[J].控制与决策, 2018, 33(3):486-490. http://www.wanfangdata.com.cn/details/detail.do?_type=perio&id=kzyjc201803013WANG Z S, DONG B T, ZHAO F C, et al.Improved dehazing method for traffic images based on dark channel prior[J].Control and Decision, 2018, 33(3):486-490(in Chinese). http://www.wanfangdata.com.cn/details/detail.do?_type=perio&id=kzyjc201803013 [16] KIM J H, JANG W D, SIM J Y, et al.Optimized contrast enhancement for real-time image and video dehazing[J].Journal of Visual Communication and Image Representation, 2013, 24(3):410-425. doi: 10.1016/j.jvcir.2013.02.004 [17] ZHU Q, MAI J, SHAO L.A fast single image haze removal algorithm using color attenuation prior[J].IEEE Transactions on Image Processing, 2015, 24(11):3522-3533. doi: 10.1109/TIP.2015.2446191 [18] WANG W, YUAN X, WU X, et al.Fast image dehazing method based on linear transformation[J].IEEE Transactions on Multimedia, 2017, 19(6):1142-1155. http://ieeexplore.ieee.org/document/7814312 [19] XU Y, WEN J, FEI L, et al.Review of video and image defogging algorithms and related studies on image restoration and enhancement[J].IEEE Access, 2017, 4(1):165-188. http://www.wanfangdata.com.cn/details/detail.do?_type=perio&id=79a7d9205c5cb3d782feadb3d8a98ac3 [20] MENG G F, WANG Y, DUAN J.Efficient image dehazing with boundary constraint and contextual regularization[C]//IEEE International Conference on Computer Vision(ICCV).Piscataway: IEEE Press, 2014: 617-624. [21] HAUTIERE N, TAREAL J P, AUBERT D, et al.Blind contrast enhancement assessment by gradient ratioing at visible edges[J].Image Analysis and Stereology, 2011, 27(2):87-95. doi: 10.5566/ias.v27.p87-95 [22] YU X, XIAO C, DENG M, et al.A classification algorithm to distinguish image as haze or non-haze[C]//Sixth International Conference on Image and Graphics.Piscataway: IEEE Press, 2011: 286-289.