Shortwave Infrared Image Dehazing Based on Dark Channel Prior
-
摘要: 针对短波红外成像系统在雾霾天气下存在图像质量模糊、分辨率低等问题,本文提出了一种基于暗通道先验理论的短波红外图像去雾算法。本文首先通过改进的暗通道先验得到暗通道图像数据,然后基于暗通道数据对大气光进行估计;为了避免目标局部高亮或细节模糊,采用引导滤波和多尺度Retinex(Multi-scale retinex,MSR)对透射率图进行细化和增强处理,最后结合大气散射模型来反演出去雾图像。实验结果表明,经此算法处理后的短波红外图像在主观视觉和客观指标方面均得到了较好的验证,去雾效果显著、细节特征丰富且明亮度适宜。Abstract: To solve the problems of blurred image quality and low-resolution weather haze in shortwave infrared imaging systems, a shortwave infrared image-defogging algorithm based on a dark channel prior is proposed. First, the algorithm obtains the dark-channel image data using an improved dark-channel prior. Then, the atmospheric light is estimated based on the dark channel data. To avoid local highlights or blurred details of the target, the transmittance map is refined and enhanced using guided filtering and multi-scale retinex (MSR). Finally, the defogged image is inverted using the atmospheric scattering model. The shortwave infrared image processed by this algorithm was verified in terms of subjective vision and objective indicators, displaying a remarkable defogging effect, rich details, and appropriate brightness.
-
Keywords:
- shortwave infrared /
- dehaze /
- dark channel prior /
- MSR
-
-
表 1 不同算法的峰值信噪比
Table 1 Peak single to noise ratio of different algorithms
表 2 不同算法的平均梯度
Table 2 Average gradient of different algorithms
-
[1] WU Q, ZHANG J, REN W, et al. Accurate transmission estimation for removing haze and noise from a single image[J]. IEEE Transactions on Image Processing, 2020, 29: 2583-2597. DOI: 10.1109/TIP.2019.2949392
[2] WANG P, FAN Q, ZHANG Y, et al. A novel dehazing method for color fidelity and contrast enhancement on mobile devices[J]. IEEE Transactions on Consumer Electronics, 2018, 65(1): 47-56.
[3] Yoav Y, Schechner, Srinivasa G, et al. Polarization-based vision through haze[J]. Applied Optics, 2003, 42: 511-525. DOI: 10.1364/AO.42.000511
[4] Narasimhan S G, Nayar S K. Vision and the atmosphere[C]// International Conference on Computer Graphics and Interactive Techniques. ACM, 2008, 48: 233-254.
[5] XU Z, LIU X, CHEN X. Fog removal from video sequences using contrast limited adaptive histogram equalization[C]//International Conference on Computational Intelligence & Software Engineering. IEEE, 2009: 1-4.
[6] LI Jia. Application of image enhancement method for digital images based on Retinex theory[J]. Optik - International Journal for Light and Electron Optics, 2013, 124(23): 5986-5988. DOI: 10.1016/j.ijleo.2013.04.115
[7] Seow M J, Asari V K. Ratio rule and homomorphic filter for enhancement of digital colour image[J]. Neurocomputing, 2006(7/9): 69.
[8] BO J, ZHANG W, ZHAO J, et al. Gray-Scale image dehazing guided by scene depth information[J]. Mathematical Problems in Engineering, 2016, 2016: 1-10.
[9] Tarel J P, N Hautière. Fast visibility restoration from a single color or gray level image[C]//IEEE International Conference on Computer Vision. IEEE, 2010: 2201-2208.
[10] HE K. Single image haze removal using dark channel prior[J]. IEEE Transactions on Pattern Analysis and Machine Intelligence, 2009, 33: 2341-2353.
[11] 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
[12] LI J, ZHANG H, YUAN D, et al. Single image dehazing using the change of detail prior[J]. Neurocomputing, 2015, 156: 1-11. DOI: 10.1016/j.neucom.2015.01.026
[13] Singh V. Single image dehazing using gradient channel prior[J]. Applied Intelligence: The International Journal of Artificial Intelligence, Neural Networks, and Complex Problem-Solving Technologies, 2019, 49(12): 4276-4293.
[14] 林森, 孙彭辉. 改进暗通道窗口与透射率修正的图像去雾[J]. 电光与控制, 2022, 29(11): 55-60. https://www.cnki.com.cn/Article/CJFDTOTAL-DGKQ202211010.htm LIN Sen, SUN Penghui. Improved image dehazing with dark channel window and transmittance correction[J]. Electrooptic and control, 2022, 29(11): 55-60. https://www.cnki.com.cn/Article/CJFDTOTAL-DGKQ202211010.htm
[15] Mccann J. Retinex Theory[M]. New York: Springer, 2015.
[16] 李娜, 邓家先, 崔亚妮, 等. 基于暗通道先验的红外图像清晰化及FPGA实现[J]. 红外与激光工程, 2021, 50(3): 111-120. https://www.cnki.com.cn/Article/CJFDTOTAL-HWYJ202103014.htm LI Na, DENG Jiaxian, CUI Yani, et al. Infrared image clarity based on dark channel prior and FPGA implementation[J]. Infrared and Laser Engineering, 2021, 50(3): 111-120. https://www.cnki.com.cn/Article/CJFDTOTAL-HWYJ202103014.htm
[17] HE K, SUN J, TANG X. Guided image filtering[J]. IEEE Transactions on Pattern Analysis and Machine Intelligence, 2013, 35(6): 1397-1409. DOI: 10.1109/TPAMI.2012.213
[18] 张承泓, 李范鸣, 吴滢跃. 基于自适应引导滤波的子带分解多尺度Retinex红外图像增强[J]. 红外技术, 2019, 41(4): 31-36. http://hwjs.nvir.cn/article/id/hwjs201904005 ZHANG Chenghong, LI Fanming, WU Yingyue. Multi-scale Retinex infrared image enhancement with subband decomposition based on adaptive guided filtering[J]. Infrared Technology, 2019, 41(4): 31-36. http://hwjs.nvir.cn/article/id/hwjs201904005
[19] LIU X, ZHANG H, CHEUNG Y M, et al. Efficient single image dehazing and denosing[J]. Computer Vision and Image Understanding, 2017: 23-33. Doi: 10.1016/j.cviu.2017.08.002.
[20] Ehsan S M, Imran M, Ullah A, et al. A single image dehazing technique using the dual transmission maps strategy and gradient-domain guided image filtering[J]. IEEE Access, 2021(99): 89055-89063. Doi: 10.1109/ACCESS.2021.3090078.
[21] YAN S, ZHU J, YUN K, et al. An infrared image dehazing method based on modified dark channel prior[C]//International Conference on Biometrics, Microelectronic Sensors, and Artificial Intelligence (BMSAI). SPIE, 2022, 12252: 132-138.
[22] 程铁栋, 卢晓亮, 易其文, 等. 一种结合单尺度Retinex与引导滤波的红外图像增强方法[J]. 红外技术, 2021, 43(11): 1081. http://hwjs.nvir.cn/article/id/b49a0a09-e295-40e6-9736-24a58971206e CHENG Tiedong, LU Xiaoliang, YI Qiwen, et al. An infrared image enhancement method combining single-scale Retinex and guided filtering[J]. Infrared Technology, 2021, 43(11): 1081-1088. http://hwjs.nvir.cn/article/id/b49a0a09-e295-40e6-9736-24a58971206e
-
期刊类型引用(1)
1. 程知,陶寅,邓灶辉,高丽萍,沐超,杜丽丽. 融合残差密集块和对比正则化的单幅图像去雾方法研究. 合肥大学学报. 2025(02): 98-106+122 . 百度学术
其他类型引用(3)