ABSTRACT
The shooting conditions of remote sensing images often cause them to be covered by clouds and fog, and remote sensing images handle more details more strictly, so it is very difficult to defog remote sensing images. In this paper, we propose an optical remote sensing image defogging algorithm based on different wavelengths. Firstly, the algorithm increases the transmittance attenuation value of the three channels to the initial energy value of the image based on different wavelength attenuation. Secondly, we use deep learning methods to segment the dense fog areas and determine the global atmosphere light candidate area to estimate the global atmosphere light. Finally, the proposed algorithm uses the atmospheric scattering model to defog the three channels respectively, and the final experimental results are obtained. Experimental results show that our method can achieve better defogging image effect and quality.
- Zhang Zheng, Li Qi, Xu Zhihai, Feng Huajun, and Chen Yueting. (2019). Remote sensing image dehazing by combining color lines and dark channels. Optics and Precision Engineering (1), 10.Google Scholar
- Arnfred, J. T., and Winkler, S. (2016). A general framework for image feature matching without geometric constraints. Pattern Recognition Letters, 73, 26-32.Google ScholarDigital Library
- He, K., Sun, J., and Tang, X. (2010). Single image haze removal using dark channel prior. IEEE transactions on pattern analysis and machine intelligence, 33(12), 2341-2353.Google Scholar
- Berman, D., and Avidan, S. (2016). Non-local image dehazing. In Proceedings of the IEEE conference on computer vision and pattern recognition (pp. 1674-1682).Google ScholarCross Ref
- Chen, Z., Ou, B., and Tian, Q. (2019). An improved dark channel prior image defogging algorithm based on wavelength compensation. Earth Science Informatics, 12(4), 501-512.Google ScholarCross Ref
- Xie, F., Shi, M., Shi, Z., Yin, J., and Zhao, D. (2017). Multilevel cloud detection in remote sensing images based on deep learning. IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing, 10(8), 3631-3640.Google ScholarCross Ref
- Tao, Y., Xu, M., Zhang, F., Du, B., and Zhang, L. (2017). Unsupervised-restricted deconvolutional neural network for very high resolution remote-sensing image classification. IEEE Transactions on Geoscience and Remote Sensing, 55(12), 6805-6823.Google ScholarCross Ref
- Luo, Y., Zhou, L., Wang, S., and Wang, Z. (2017). Video satellite imagery super resolution via convolutional neural networks. IEEE Geoscience and Remote Sensing Letters, 14(12), 2398-2402.Google ScholarCross Ref
- Li, E., Xia, J., Du, P., Lin, C., and Samat, A. (2017). Integrating multilayer features of convolutional neural networks for remote sensing scene classification. IEEE Transactions on Geoscience and Remote Sensing, 55(10), 5653-5665.Google ScholarCross Ref
- Huang, B., Zhi, L., Yang, C., Sun, F., and Song, Y. (2020). Single satellite optical imagery dehazing using SAR image prior based on conditional generative adversarial networks. In Proceedings of the IEEE/CVF winter conference on applications of computer vision (pp. 1806-1813).Google ScholarCross Ref
- Wieland, M., Li, Y., and Martinis, S. (2019). Multi-sensor cloud and cloud shadow segmentation with a convolutional neural network. Remote Sensing of Environment, 230, 111203.Google ScholarCross Ref
- Yang, J., Guo, J., Yue, H., Liu, Z., Hu, H., and Li, K. (2019). CDnet: CNN-based cloud detection for remote sensing imagery. IEEE Transactions on Geoscience and Remote Sensing, 57(8), 6195-6211.Google ScholarCross Ref
- Zhang, H., and Patel, V. M. (2018). Densely connected pyramid dehazing network. In Proceedings of the IEEE conference on computer vision and pattern recognition (pp. 3194-3203).Google ScholarCross Ref
- Xie, L., Wang, H., Wang, Z., and Cheng, L. (2020, July). DHD-Net: A Novel Deep-Learning-based Dehazing Network. In 2020 International Joint Conference on Neural Networks (IJCNN) (pp. 1-7). IEEE.Google Scholar
- Qin, X., Wang, Z., Bai, Y., Xie, X., and Jia, H. (2020, April). FFA-Net: Feature fusion attention network for single image dehazing. In Proceedings of the AAAI Conference on Artificial Intelligence (Vol. 34, No. 07, pp. 11908-11915).Google Scholar
- Ju Mingye, Zhang Dengyin, and Ji Yingtian. (2016). Image dehazing algorithm based on fog concentration estimation. Acta Automatica Sinica, 42(9), 13.Google Scholar
- Kang, L. W., Lin, C. W., and Fu, Y. H. (2011). Automatic single-image-based rain streaks removal via image decomposition. IEEE transactions on image processing, 21(4), 1742-1755.Google Scholar
- Grohnfeldt, C., Schmitt, M., and Zhu, X. (2018, July). A conditional generative adversarial network to fuse SAR and multispectral optical data for cloud removal from Sentinel-2 images. In IGARSS 2018-2018 IEEE International Geoscience and Remote Sensing Symposium (pp. 1726-1729). IEEE.Google Scholar
- Huang, B., Zhi, L., Yang, C., Sun, F., and Song, Y. (2020). Single satellite optical imagery dehazing using SAR image prior based on conditional generative adversarial networks. In Proceedings of the IEEE/CVF winter conference on applications of computer vision (pp. 1806-1813).Google ScholarCross Ref
Index Terms
- Optical Remote Sensing Image Defogging Algorithm based on Different Wavelength
Recommendations
Adaptive dehazing control factor based fast single image dehazing
AbstractThe single image dehazing is performed using atmospheric scattering model (ASM). The ASM is based on transmission and atmospheric light. Thus, accurate estimation of transmission is essential for quality single image dehazing. Single image ...
Image dehazing based on dark channel prior and brightness enhancement for agricultural remote sensing images from consumer-grade cameras
Highlights- An improved dehazing enhancement method based on DCP was proposed.
- Logarithmic ...
AbstractRemote sensing technology has been widely used for monitoring crop fields and other agricultural applications. However, the clarity of remote sensing images is often affected by clouds and chaotic media in the atmosphere. Image ...
Unsupervised Defogging for Rotary Kilns Image
Advances and Trends in Artificial Intelligence. Theory and ApplicationsAbstractImage processing of rotary kilns is extremely important for their combustion efficiency. Most of the current image processing on kilns is focused on image classification, but image defogging is also one of the key aspects, which is still a ...
Comments