Nighttime Dehazing Algorithm with Adaptive Global Brightness Compensation
-
摘要: 针对夜间雾霾天气情况下还原的去雾图像存在颜色失真、纹理损失严重、去雾效果差等问题,本文提出了一种夜间去雾算法,采用自适应全局亮度补偿、同态滤波、限制对比度自适应直方图均衡化算法以及联合双边滤波对降质图像进行处理,结合大气散射模型得到还原的去雾图像。实验结果表明,该算法的夜间去雾效果好、处理速度快,较对比算法在对比度、平均梯度以及信息熵上均有改善,有效减少了还原图像的颜色失真、纹理损失。
-
关键词:
- 夜间去雾 /
- 自适应全局亮度补偿 /
- 同态滤波 /
- 限制对比度自适应直方图均衡化算法 /
- 联合双边滤波
Abstract: To address the problems of color distortion, heavy texture loss, and poor dehazing effect in the dehazing images of hazing nights, this study proposes a night-time dehazing algorithm. Adaptive global brightness compensation, homomorphic filtering, contrast limited adaptive histogram equalization algorithm, and joint bilateral filtering were used to process the hazing images, and the dehazing images were obtained by combining the atmospheric scattering model. The experimental results show that this method has a better night dehazing effect and faster processing speed than the comparison algorithms. The contrast, mean gradients, and entropy are improved, and the color distortion and texture loss are effectively reduced. -
表 1 几种客观评价结果的比较
Table 1. Comparison of several objective evaluation results
Image Method c g e t/s (1) in Fig.4(600×431) Original 43.68 3.36 7.52 - Ref. 14 60.81 2.33 5.46 2.93 Ref. 8 46.19 2.81 6.88 3.78 Ref. 15 62.23 4.16 7.13 12.73 Ours 91.41 4.83 7.38 1.67 (2) in Fig.4(600×431) Original 72.19 4.25 7.53 - Ref. 14 74.27 2.72 5.34 2.62 Ref. 8 69.14 3.51 6.88 3.66 Ref. 15 87.15 4.86 7.36 12.81 Ours 93.31 5.81 7.44 1.39 (3) in Fig.4(600×431) Original 54.76 4.42 7.35 - Ref. 14 50.54 2.69 5.99 2.37 Ref. 8 49.19 3.57 6.77 4.01 Ref. 15 83.15 5.36 7.24 12.88 Ours 95.35 6.78 7.43 1.54 (4) in Fig.4 (600×431) Original 88.22 4.44 7.62 - Ref. 14 86.25 4.61 5.78 2.66 Ref. 8 76.13 4.71 6.98 3.73 Ref. 15 121.71 5.77 7.23 12.91 Ours 137.34 6.43 7.57 1.44 -
[1] ZHANG Jing, CAO Yang, FANG Shuai, et al. Fast haze removal for nighttime image using maximum reflectance prior[C]//Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, 2017: 7418-7426. [2] 董浩伟, 陈洁. 一种基于大气散射模型和Retinex的红外图像去雾算法[J]. 红外技术, 2019, 41(4): 347-356. http://hwjs.nvir.cn/article/id/hwjs201904009DONG Haowei, CHEN Jie. Infrared image defogging algorithm based on atmospheric scattering model and Retinex[J]. Infrared Technology, 2019, 41(4): 347-356. http://hwjs.nvir.cn/article/id/hwjs201904009 [3] YU Teng, SONG Kang, MIAO Pu, et al. Nighttime single image dehazing via pixel-wise alpha blending[J]. IEEE Access, 2019, 7: 114619-114630. doi: 10.1109/ACCESS.2019.2936049 [4] 陆士猛, 刘昌锦. 无人机侦察图像快速去雾算法[J]. 红外技术, 2015, 37(10): 847-851. http://hwjs.nvir.cn/article/id/hwjs201510008LU Shimeng, LIU Changjin. The fast haze removal algorithm for UAV reconnaissance image[J]. Infrared Technology, 2015, 37(10): 847-851. http://hwjs.nvir.cn/article/id/hwjs201510008 [5] 黄黎红. 一种基于单尺度Retinex的雾天降质图像增强新算法[J]. 应用光学, 2010, 31(5): 728-733. https://www.cnki.com.cn/Article/CJFDTOTAL-YYGX201005013.htmHUANG Lihong. Fog-degraded image enhancement based on singlescale Retinex[J]. Journal of Applied Optics, 2010, 31(5): 728-733. https://www.cnki.com.cn/Article/CJFDTOTAL-YYGX201005013.htm [6] HE K, SUN J, TANG X. Single image haze removal using dark channel prior[J]. IEEE Transactions on Pattern Analysis and Machine Intelligence, 2010, 33(12): 2341-2353. http://www.robots.ox.ac.uk/~vgg/rg/papers/hazeremoval.pdf [7] HE K, SUN J, TANG X. Guided image filtering[J]. IEEE Transactions on Pattern Analysis and Machine Intelligence, 2012, 35(6): 1397-1409. [8] 徐兴贵, 杨平, 刘永利. 基于全尺度Retinex算法的夜间图像去雾[J]. 微电子学与计算机, 2017, 34(7): 132-136 https://www.cnki.com.cn/Article/CJFDTOTAL-WXYJ201707028.htmXU Xinggui, YANG Ping, LIU Yongli. Night image dehazing based on full-scale Retinex algorithm[J]. Microelectronics & Computer, 2017, 34(7): 132-136. https://www.cnki.com.cn/Article/CJFDTOTAL-WXYJ201707028.htm [9] 丁雪梅, 李为相, 毛祥宇. 基于Retinex和对比度约束的夜间去雾[J]. 计算机工程与设计, 2018, 39(9): 2856-2860. https://www.cnki.com.cn/Article/CJFDTOTAL-SJSJ201809028.htmDING Xuemei, LI Weixiang, MAO Xiangyu. Night dehazing based on Retinex and contrast constraint[J]. Computer Engineering and Design, 2018, 39(9): 2856-2860. https://www.cnki.com.cn/Article/CJFDTOTAL-SJSJ201809028.htm [10] Srinivasa G Narasimhan, Shree K Nayar. Vision and the atmosphere[J]. International Journal of Computer Vision, 2002, 48(3): 233-254. doi: 10.1023/A:1016328200723 [11] 李炼, 李维嘉, 吴耀中. 基于红色暗通道先验理论与CLAHE算法的水下图像增强算法[J]. 中国舰船研究, 2019, 14(S1): 175-182. https://www.cnki.com.cn/Article/CJFDTOTAL-JCZG2019S1027.htmLI Lian, LI Weijia, WU Yaozhong. An underwater image enhancement algorithm based on RDCP and CLAHE[J]. Chinese Journal of Ship Research, 2002, 48(3): 233-254. https://www.cnki.com.cn/Article/CJFDTOTAL-JCZG2019S1027.htm [12] 成宝芝, 张丽丽. 基于双边滤波的最优波段子空间高光谱异常目标检测[J]. 液晶与显示, 2019, 34(9): 897-904. https://www.cnki.com.cn/Article/CJFDTOTAL-YJYS201909009.htmCHENG Baozhi, ZHANG Lili. Optimal bands subspace anomaly detection for hyperspectral imagery based on bilateral filtering[J]. Chinese Journal of Liquid Crystals and Displays, 2019, 34(9): 897-904. https://www.cnki.com.cn/Article/CJFDTOTAL-YJYS201909009.htm [13] 杨燕, 李一菲, 岳辉. 一种自适应的多级透射率估计去雾算法[J]. 光子学报, 2019, 48(3): 310001. https://www.cnki.com.cn/Article/CJFDTOTAL-GZXB201903023.htmYANG Yan, LI Yifei, YUE Hui. An adaptive multiscale transmission estimation dehazing algorithm[J]. Acta Photonica Sinica, 2019, 48(3): 310001. https://www.cnki.com.cn/Article/CJFDTOTAL-GZXB201903023.htm [14] 高强, 胡辽林, 陈鑫. 基于暗通道补偿与大气光值改进的图像去雾方法[J]. 激光与光电子学进展, 2020, 57(6): 150-156. https://www.cnki.com.cn/Article/CJFDTOTAL-JGDJ201507018.htmGAO Qiang, HU Liaolin, CHEN Xin. Image dehazing method based on dark channel compensation and improvement of atmospheric light value[J]. Laser & Optoelectronics Process, 2020, 57(6): 150-156. https://www.cnki.com.cn/Article/CJFDTOTAL-JGDJ201507018.htm [15] LI Y, TAN R T, Brown M S. Nighttime haze removal with glow and multiple light colors[C]//Proceedings of the IEEE International Conference on Computer Vision, 2015: 226-234.