Infrared Image Dehazing Based on Improved Dark Channel Prior
-
摘要: 为了提高红外图像去雾效果,提出改进暗通道算法。首先利用近红外光在天空区域与非天空区域的穿透能力不同,天空区域的红外能量相对非天空区域能量较小,通过红外有雾图像的能量差异性划分为天空区域、非天空区域;接着天空区域的大气光值通过滑动窗口的像素亮度平均值计算,透射率考虑近红外波段衰减,非天空区域的大气光值、透射率通过改进暗通道算法计算;最后通过各区域大气光值、透射率恢复出无雾图像。实验结果表明,本文算法对红外图像去雾结果清晰,图像细节信息较好,评价指标较优。Abstract: To improve the effectiveness of infrared image dehazing, an improved dark channel was proposed. First, because the penetration ability of near-infrared light in the sky region is different from that in the non-sky region, and the infrared energy in the sky region is smaller than that in the non-sky region, the region was divided into sky and non-sky regions using the energy difference. Second, the atmospheric light value of the sky region was calculated using the average pixel brightness of the sliding window, the near-infrared wave attenuation was considered for the transmittance, and the atmospheric light value and transmittance of the non-sky region were calculated using the improved dark channel algorithm. Finally, the dehazed image was recovered from the atmospheric light value and transmittance of each region. The experimental results show that the dehazing output of the infrared image was clearer, the image detail information was better, and the evaluation index was better than those of other algorithms.
-
Key words:
- energy difference /
- sky region /
- sliding window /
- infrared image dehazing
-
表 1 天空区域灰度值与h(x)取最小值关系
Table 1. Relationship between gray value of sky area and minimum value of h(x)
Gray value of sky area h(x) ≤160 ≥1 161-170 ≥1.1 171-180 ≥1.6 181-190 ≥5 191-200 ≥10 201-210 ≥20 211-220 ≥35 221-230 ≥55 231-240 ≥80 241-255 ≥140 -
[1] 张健. 基于改进暗通道算法的红外图像去雾研究[J]. 激光与红外, 2021, 51(8): 1081-1087. doi: 10.3969/j.issn.1001-5078.2021.08.018ZHANG Jian. Infrared image dehazing based on improveddark channel prior algorithm[J]. Laser & Infrared, 2021, 51(8): 1081-1087. doi: 10.3969/j.issn.1001-5078.2021.08.018 [2] 曹海杰, 刘宁, 许吉, 等. 红外图像自适应逆直方图增强技术[J]. 红外与激光工程, 2020, 49(4): 0426003. https://www.cnki.com.cn/Article/CJFDTOTAL-HWYJ202004036.htmCAO Haijie, LIU Ning, XU Ji, et al. Infrared image adaptive inverse histogram enhancement technology[J]. Infrared and Laser Engineering, 2020, 49(4): 0426003. https://www.cnki.com.cn/Article/CJFDTOTAL-HWYJ202004036.htm [3] HE K M, SUN J, TANG X O. Guided image filtering[J]. IEEE Transactions on Pattern Analysis and Machine Intelligence, 2013, 35(6): 1397-1409. doi: 10.1109/TPAMI.2012.213 [4] 袁小燕, 张照锋, 顾振飞, 等. 基于大气散射模型的红外图像增强方法[J]. 电子器件, 2019, 42(1): 147-156. https://www.cnki.com.cn/Article/CJFDTOTAL-DZQJ201901029.htmYUAN Xiaoyan, ZHANG Zhaofeng, GU Zhenfei, et al. An infrared image enhancement method based on the atmospheric scattering model[J]. Chinese Journal of Electron Devices, 2019, 42(1): 147-156. https://www.cnki.com.cn/Article/CJFDTOTAL-DZQJ201901029.htm [5] ZHENG L, SHI H, GU M. Infrared traffic image enhancement algorithm based on dark channel prior and gamma correction[J]. Modern Physics Letters B, 2017, 31(19-21): 84-92. [6] 朱珍, 黄锐, 臧铁钢, 等. 基于加权近红外图像融合的单幅图像除雾方法[J]. 计算机科学, 2020, 47(8): 241-244. https://www.cnki.com.cn/Article/CJFDTOTAL-JSJA202008038.htmZHU Zhen, HUANG Rui, ZANG Tiegang, et al. Single image defogging method based on weighted near-infrared image fusion[J]. Computer Science, 2020, 47(8): 241-244. https://www.cnki.com.cn/Article/CJFDTOTAL-JSJA202008038.htm [7] 沈瑜, 党建武, 苟吉祥, 等. 近红外与可见光双通道传感器信息融合的去雾技术[J]. 光谱学与光谱分析, 2019, 39(5): 1420-1427. https://www.cnki.com.cn/Article/CJFDTOTAL-GUAN201905018.htmSHEN Yu, DANG Jianwu, GOU Jixiang, et al. A dehaze algorithm based on near-infrared and visible dual channel sensor information fusion[J]. Spectroscopy and Spectral Analysis, 2019, 39(5): 1420-1427. https://www.cnki.com.cn/Article/CJFDTOTAL-GUAN201905018.htm [8] 韩松臣, 黄畅昕, 李炜, 等. 一种改进的基于近红外图像的去雾方法[J]. 工程科学与技术, 2018, 50(2): 99-104. https://www.cnki.com.cn/Article/CJFDTOTAL-SCLH201802012.htmHAN Songchen, HUANG Changxin, LI Wei, et al An improved dehazing algorithm based on near infrared image[J]. Advanced Engineering Sciences, 2018, 50(2): 99-104. https://www.cnki.com.cn/Article/CJFDTOTAL-SCLH201802012.htm [9] HE K M, SUN J, TANG X O. Single image haze removal using dark channel prior[J]. IEEE Transactions on Pattern Analysis and Machine Intelligence, 2011, 33 (12): 2341-2353. doi: 10.1109/TPAMI.2010.168 [10] LI Y, ZHANG Y F, GENG A H, et al. Infrared image enhancement based on atmospheric scattering model and histogram equalization[J]. Optics & Laser Technology, 2016, 83(9): 99-107. [11] 梁恩辉, 周安然, 裴继红, 等. 基于能量图的海上红外图像目标分割方法[J]. 指挥信息系统与技术, 2018, 9(2): 79-84. https://www.cnki.com.cn/Article/CJFDTOTAL-ZHXT201802015.htmLIANG Enhui, ZHOU Enron, PEI Jihong, et al. Maritime infrared image target segmentation method based on energy map[J]. Command Information System And Technology, 2018, 9(2): 79-84. https://www.cnki.com.cn/Article/CJFDTOTAL-ZHXT201802015.htm [12] 左健宏, 蔺素珍, 禄晓飞, 等. 基于雾线暗原色先验的红外图像去雾算法[J]. 红外技术, 2020, 42(6): 552-558. http://hwjs.nvir.cn/article/id/hwjs202006007ZUO Jianhong, LIN Suzhen, LU Xiaofei, et al. Use of dark primary color priors for haze-line-based infrared image dehazing[J]. Infrared Technology, 2020, 42(6): 552-558. http://hwjs.nvir.cn/article/id/hwjs202006007 [13] 余佩伦, 施佺, 王晗. 并行生成网络的红外—可见光图像转换[J]. 中国图象图形学报, 2021, 26(10): 2346-2356. doi: 10.11834/jig.200113YU P L, SHI Q, WANG H. Infrared-to-visible image translation based on parallel generator network[J]. Journal of Image and Graphics, 2021, 26(10): 2346-2356. doi: 10.11834/jig.200113 [14] 全雪峰. 基于自适应大气光校正的图像去雾方法[J]. 计算机应用与软件, 2019, 36(3): 104-111. https://www.cnki.com.cn/Article/CJFDTOTAL-JYRJ201903021.htmQUAN Xuefeng. Image dehazing based on adaptive atmospheric light correction[J]. Computer Applications and Software, 2019, 36(3): 04-111. https://www.cnki.com.cn/Article/CJFDTOTAL-JYRJ201903021.htm [15] HAUTIERE N, TAREL J P, AUBERT D, et al. Blind contrast enhancement assessment by gradient ratioing at visible edges[J]. Image Analysis & Stereology Journal, 2008, 27(2): 87-95. [16] WANG Z, BOVIK A C, SHEIKH H R, et al. Image quality assessment: from error visibility to structural similarity[J]. IEEE Trans Image Process, 2004, 13(4): 600-612.