Remote sensing image dehazing algorithm based on adaptive SLIC

Yu Hang; Li Chenyang; Liu Zhiheng; Zhou Suiping; Guo Yuru

doi:10.11834/jrs.20242532

Views : 0 下载量: 24 CSCD: 0 更多指标

R-PDF
PDF
Export
Share
Collection
Album

Remote sensing image dehazing algorithm based on adaptive SLIC
Pages: 1-14(2024)
Published Online： 07 March 2024 ，
DOI： 10.11834/jrs.20242532

扫描看全文

余航，李晨阳，刘志恒，周绥平，郭玉茹.XXXX.基于自适应SLIC的遥感影像去雾算法.遥感学报，XX（XX）： 1-14

Yu Hang，Li Chenyang，Liu Zhiheng，Zhou Suiping，Guo Yuru. XXXX. Remote sensing image dehazing algorithm based on adaptive SLIC. National Remote Sensing Bulletin， XX（XX）：1-14
余航，李晨阳，刘志恒，周绥平，郭玉茹.XXXX.基于自适应SLIC的遥感影像去雾算法.遥感学报，XX（XX）： 1-14 DOI： 10.11834/jrs.20242532.

Yu Hang，Li Chenyang，Liu Zhiheng，Zhou Suiping，Guo Yuru. XXXX. Remote sensing image dehazing algorithm based on adaptive SLIC. National Remote Sensing Bulletin， XX（XX）：1-14 DOI： 10.11834/jrs.20242532.

摘要

遥感影像由于雾霾的原因导致清晰度下降，增添了遥感影像目标检测和地物分割任务的困难。提出一种基于自适应SLIC的遥感影像去雾算法，主要包括：首先，针对有雾遥感影像出现局部区域高亮问题，使用改进的Retinex算法，对输入遥感影像进行对比度增强，保留图像细节，以减少伪影现象，扩展图像的对比度动态范围，准确估计遥感影像大气强度值；其次，提出了一种自适应SLIC算法，解决超像素数目参数设定的困难，对输入遥感影像进行超像素分割，避免局部对比度强烈区域对固定窗口的影响，从而获得更加精确的透射率估计；最后，基于暗通道先验原理和大气散射模型恢复出无雾遥感影像。使用所提算法和He等人、Zhu等人、Han等人和Nie等人的四种算法进行对比，分别在公开数据集Inria Aerial Image Dataset和RICE Image Dataset进行去雾效果比较。主观上，所提算法处理后的遥感影像颜色更真实、去雾更彻底、地物更清晰，能更好的保留影像细节信息；客观上，所提算法处理后的图像信息熵平均值为7.56，峰值信噪比平均值为22.05，结构相似性平均值为0.87，均高于其他四种算法。所提出的去雾算法模型，综合了图像增强与恢复的优点，使得去雾后的遥感影像更加自然真实，更好的恢复出遥感影像细节信息。

Abstract

Objective Remote sensing images are degraded in clarity due to haze

which adds difficulties to remote sensing image target detection

feature segmentation tasks and remote sensing image information interpretation. The remote sensing image defogging method based on deep learning is time-consuming due to the large number of model parameters and the dependence on the amount of remote sensing image data. The remote sensing image dehazing method based on image enhancement does not fully consider the degradation mechanism of remote sensing images in hazy

which makes it difficult to adapt to remote sensing images in different scenes and easily loses image information leading to image distortion. The remote sensing image dehazing method based on physical model requires manual setting of parameters when refining the transmittance

and at the same time

as the contrast of remote sensing images is not completely enhanced

the overall colour of the dehazed images is dark and the fog remains in local areas. Method To solve the above problems and improve the quality of remote sensing image dehazing

a remote sensing image dehazing method based on image enhancement and physical modeling is proposed. An adaptive SLIC-based remote sensing image dehazing algorithm is proposed

which mainly includes: Firstly

for the problem of local area highlighting in hazy remote sensing images

and and the problem of atmospheric intensity value calculation bias problem

an improved Retinex algorithm is used to contrast-enhance the input remote sensing images to preserve image details in order to reduce artifacts

extend the dynamic range of image contrast

and accurately estimate the atmospheric intensity value of remote sensing images. Secondly

an adaptive SLIC algorithm is proposed to solve the difficulty of setting the parameter of the number of superpixels and perform superpixel segmentation on the input remote sensing image to avoid the influence of the local contrast intensity region on the fixed window

to obtain a more accurate transmittance estimation. Finally

a haze-free remote sensing image is recovered based on the dark channel a priori principle and atmospheric scattering model. The proposed method can achieve adaptive dehazing of remote sensing images without manual parameter setting. Results The proposed algorithm is compared with the four algorithms of He et al.

Zhu et al.

Han et al. and Nie et al.

and the dehazing effects are compared in the publicly available datasets Inria Aerial Image Dataset and RICE Image Dataset

respectively. Subjectively

the remote sensing images processed by the proposed algorithm have more realistic color

more complete dehazing

clearer features

and can better retain image detail information. Objectively

the mean value of image information entropy

peak signal-to-noise ratio and structural similarity of the proposed algorithm is 7.56

22.05

and 0.87

which are higher than the other four algorithms. Conclusion The proposed dehazing algorithm model integrates the advantages of image enhancement and recovery

which makes the dehazed remote sensing images more natural and realistic and better recovers the remote sensing image detail information.

关键词

遥感图像去雾自适应SLIC暗通道先验Retinex超像素分割

Keywords

Remote sensing image dehazingAdaptive SLICDark channel a prioriRetinexSuperpixel segmentation

references

Hudson R D and Hudson J W. 1975. The military applications of remote sensing by infrared. Proceedings of the IEEE, 63(1): 104-128 [DOI: 10.1109/PROC.1975.9711http://dx.doi.org/10.1109/PROC.1975.9711].

Zhang C, Cheng H, Chen Z and Zheng W. 2008. The Development of Hyperspectral Remote Sensing and Its Threatening to Military Equipments. Electro-Optic Technology Application, 23: 10–12.

张朝阳, 程海峰, 陈朝辉, 郑文伟. 2008. 高光谱遥感的发展及其对军事装备的威胁. 光电技术应用, 23, 10–12 [DOI: 10.3969/j.issn.1673-1255.2008.01.003http://dx.doi.org/10.3969/j.issn.1673-1255.2008.01.003].

Stevens M M. 1988. Application of Remote Sensing to the Assessment of Surface Characteristics of Selected MojaveDesert Playas for Military Purposes. Ph.ThesisD, University of Missouri-Rolla, Rolla, MO, USA.

Qin P, Cai Y, Liu J, Fan P and Sun M. 2021. Multilayer feature extraction network for military ship detection from high-resolution optical remote sensing images. IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing, 14, 11058-11069 [DOI: 10.1109/JSTARS.2021.3123080http://dx.doi.org/10.1109/JSTARS.2021.3123080].

Wang F, Zhou K, Wang M and Wang Q. 2020. The Impact Analysis of Land Features to JL1-3B Nighttime Light Data at Parcel Level: Illustrated by the Case of Changchun, China. Sensors, 20(18): 5447 [DOI: 10.3390/s20185447].

Liu D and Han L. 2022. Semi-automatic extraction and mapping of farmlands based on high-resolution remote sensing images. International journal of pattern recognition and artificial intelligence(1), 36 [DOI: 10.1142/S0218001422540027http://dx.doi.org/10.1142/S0218001422540027]

Mancini F and Pirotti F. 2021. Innovations in Photogrammetry and Remote Sensing: Modern Sensors, New Processing Strate-gies and Frontiers in Applications. Sensors, 21: 2420 [DOI: 10.3390/s21072420].

Zhu Z, Luo Y, Wei H, Li Y, Qi G, Mazur N, Li Y and Li P. 2021. Atmospheric Light Estimation Based Remote Sensing Image Dehazing. Remote Sensing, 13: 2432 [DOI: 10.3390/rs13132432].

Jiang B, Chen G, Wang J, Ma H, Wang L, Wang Y and Chen X. 2021. Deep dehazing network for remote sensing image with non-uniform haze. Remote Sensing, 13 (21), 4443 [DOI: 10.3390/rs13214443].

Zhu Z, Luo Y, Qi G, Meng J, Li Y and Mazur N. 2021. Remote Sensing Image Dehazing Networks Based on Dual Self-Attention Boost Residual Octave Convolution. Remote Sensing, 13(16): 3104 [DOI: 10.3390/rs13163104].

Liu S, Shi H and Guo Z. 2022. Research on defog algorithm of single remote sensing image based on deep learning. CIBDA 2022; 3rd International Conference on Computer Information and Big Data Applications, 1-5.

Tang Q, Yang J, He X, Jia W, Zhang Q and Liu H. 2021. Nighttime image dehazing based on Retinex and dark channel prior using Taylor series expansion. Computer Vision and Image Understanding, 202: 103086 [DOI: 10.1016/j.cviu.2020.103086].

Wu H and Tan Z. 2020. An image dehazing algorithm based on single-scale retinex and homomorphic filtering. Communications, Signal Processing, and Systems: Proceedings of the 8th International Conference on Communications, Signal Processing, and Systems 8th. Springer Singapore, 2020: 1482-1493 [DOI: 10.1007/978-981-13-9409-6_178http://dx.doi.org/10.1007/978-981-13-9409-6_178].

Kumar R P and Naganaik M. 2023. OptiMD-3D DCNN: A Framework for Restoring the Haze-Free Images by Image Dehazing Techniques Using Heuristic Approach of Adaptive Lifting Wavelet Transform. Cybernetics and Systems, 1-32 [DOI: 10.1080/01969722.2023.2176624http://dx.doi.org/10.1080/01969722.2023.2176624].

Huang Y, Liu Y, Liu H, Shui Y, Zhao G, Chu J, Situ G, Li Z, Zhou J and Liang H. 2021. Multi-View Optical Image Fusion and Reconstruction for Defogging without a Prior In-Plane. Photonics, 8(10):454. [DOI: 10.3390/photonics8100454].

Nayar S K and Narasimhan S G. 1999. Vision in bad weather. Proceedings of the Seventh IEEE International Conference on Computer Vision, 2: 820-827 [DOI: 10.1109/ICCV.1999.790306http://dx.doi.org/10.1109/ICCV.1999.790306].

He K, Sun J and Tang X. 2009. Single image haze removal using dark channel prior. 2009 IEEE Conference on Computer Vision and Pattern Recognition: 20-25 [DOI: 10.1109/TPAMI.2010.168http://dx.doi.org/10.1109/TPAMI.2010.168].

Jiao L, Shi Z and Wei T. 2012. Fast haze removal for a single remote sensing image using dark channel prior. 2012 International Conference on Computer Vision in Remote Sensing: 132-135 [DOI: 10.1109/CVRS.2012.6421247http://dx.doi.org/10.1109/CVRS.2012.6421247]

Xie F, Chen J and Pan X. 2018. Adaptive Haze Removal for Single Remote Sensing Image. IEEE Access, 6: 67982-67991 [DOI: 10.1109/ACCESS.2018.2879893http://dx.doi.org/10.1109/ACCESS.2018.2879893]

Zhang Z, Li Q, Xu Z, Feng H and Chen Y. 2019. Color-line and dark channel based dehazing for remote sensing images. Optics and Precision Engineering, 27(01): 181-190

张峥, 李奇, 徐之海, 冯华君, 陈跃庭. 2019. 结合颜色线和暗通道的遥感图像去雾. 光学精密工程, 27(01): 181-190 [DOI: 10.3788/OPE.20192701.0181http://dx.doi.org/10.3788/OPE.20192701.0181].

Bi G, Si G and Zhao Y. 2022. Haze Removal for a Single Remote Sensing Image Using Low-Rank and Sparse Prior. IEEE Transactions on Geoscience and Remote Sensing, 60(5615513): 1-13 [DOI: 10.1109/TGRS.2021.3135975http://dx.doi.org/10.1109/TGRS.2021.3135975]

Rahman Z, Jobson D J and Woodell G A. 1996. Multi-scale retinex for color image enhancement. Proceedings of 3rd IEEE International Conference on Image Processing, 3: 1003-1006 [DOI: 10.1109/ICIP.1996.560995http://dx.doi.org/10.1109/ICIP.1996.560995].

Wu Y, Zhao Z, Wu W, Lin Y and Wang M. 2019. Automatic glioma segmentation based on adaptive superpixel. BMC Med Imaging, 19(1): 73 [DOI: 10.1186/s12880-019-0369-6].

Zhang Y, Liu K, Dong Y, K Wu and Hu X. 2020. Semisupervised Classification Based on SLIC Segmentation for Hyperspectral Image. IEEE Geoscience and Remote Sensing Letters, 17(8): 1440-1444 [DOI: 10.1109/LGRS.2019.2945546http://dx.doi.org/10.1109/LGRS.2019.2945546].

Goh K L, Ng G W, Hamzah M and Chai S S. 2021. Sizes of Superpixels and their Effect on Interactive Segmentation. 2021 IEEE International Conference on Artificial Intelligence in Engineering and Technology (IICAIET): 1-5 [DOI: 10.1109/IICAIET51634.20http://dx.doi.org/10.1109/IICAIET51634.20].

Zhu Z, Luo Y, Wei H, Li Y and Li P. 2021. Atmospheric light estimation based remote sensing image dehazing. Remote Sensing, 13(13), 2432 [DOI: 10.3390/rs13132432].

Han J, Zhang S, Fan N and Ye Z. 2022. Local patchwise minimal and maximal values prior for single optical remote sensing image dehazing. Information Sciences, 606, 173-193 [DOI: 10.1016/j.ins.2022.05.033http://dx.doi.org/10.1016/j.ins.2022.05.033].

Nie J, Wei W, Zhang L, Yuan J, Wang Z and Li H. 2022. Contrastive Haze-Aware Learning for Dynamic Remote Sensing Image Dehazing. IEEE Transactions on Geoscience and Remote Sensing, 60, 1-11 [DOI: 10.1109/TGRS.2022.3220940http://dx.doi.org/10.1109/TGRS.2022.3220940].

Long Y, Gong Y, Xiao Z and Liu Q. 2017. Accurate Object Localization in Remote Sensing Images Based on Convolutional Neural Networks. IEEE Transactions on Geoscience and Remote Sensing, 55(5): 2486-2498 [DOI: 10.1109/TGRS.2016.2645610http://dx.doi.org/10.1109/TGRS.2016.2645610].

Lin D, Xu G, Wang X, Wang Y, Sun X and Fu K. 2019. A Remote Sensing Image Dataset for Cloud Removal. 2019 IEEE Conference on Computer Vision and Pattern Recognition. [DOI: 10.48550/arXiv.1901.00600http://dx.doi.org/10.48550/arXiv.1901.00600].

Emmanuel M, Yuliya T, Guillaume C and Pierre A. 2017. Can Semantic Labeling Methods Generalize to Any City? The Inria Aerial Image Labeling Benchmark. 2017 IEEE International Geoscience and Remote Sensing Symposium (IGARSS): 3226-3229 [DOI: 10.1109/IGARSS.2017.8127684http://dx.doi.org/10.1109/IGARSS.2017.8127684].

Alert me when the article has been cited

提交

Hyperspectral unmixing network considering spectral information and superpixel segmentation

A two-branch remote sensing image dehazing network based on hierarchical feature interaction and enhanced receptive field

Hyperspectral anomaly detection via combining adaptive window saliency detection and improved superpixel segmentation

Adaptive superpixel segmentation of SAR images using an adaptive adjustment strategy for seeds

Ocean Internal Wave Detection in SAR Images by Combining Superpixel Segmentation and Saliency Features