Abstract
Sequential atmospheric polarization patterns can provide information for navigation when cues from a satellite source are not available. However, the real scenarios with extreme environments often cause corruption of captured atmospheric polarization data which makes the navigation unreliable. So this encourages us to focus on the atmospheric polarization patterns prediction (APP) topic. In this paper, we try to investigate and fill the gap in this task. We first propose a dataset called the Temporal Polarization 1072 (TP1072) dataset to compensate for the lack of the dataset, which makes future research more possible. And further, we propose a novel and efficient deep learning sequential prediction model named Multi-Scale Spatial Transform Network (MSST-Net) for that topic. The overall model includes a Spatial Transform decoder (STD) and an adversarial learning-based Physical Property Learning (PPL) strategy. The STD makes the model can perceive the sequential pattern easily which significantly increases prediction accuracy. And the PPL constrains the overall model to achieve more accurate physical property. The extensive experiments prove that both two modules are complement with each other and also demonstrate that our model can effectively capture the spatio-temporal cues of the atmospheric polarization mode.
Supported by organization x.
This is a preview of subscription content, log in via an institution to check access.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
References
Azulay, A., Weiss, Y.: Why do deep convolutional networks generalize so poorly to small image transformations? (2018)
Bréon, F.M.: Comment on Rayleigh-scattering calculations for the terrestrial atmosphere. Appl. Opt. 37(3), 428–429 (1998)
Bucholtz, A.: Rayleigh-scattering calculations for the terrestrial atmosphere. Appl. Opt. 34(15), 2765–73 (1995)
Byeon, W., Wang, Q., Srivastava, R.K., Koumoutsakos, P.: Contextvp: fully context-aware video prediction. In: Proceedings of the European Conference on Computer Vision (ECCV), pp. 753–769 (2018)
Chu, J., Zhao, K., Qiang, Z., Wang, T.: Construction and performance test of a novel polarization sensor for navigation. Sens. Actuators A Phys. 148(1), 75–82 (2008)
Emberton, S., Chittka, L., Cavallaro, A.: Underwater image and video dehazing with pure haze region segmentation. Comput. Vis. Image Understand. 168, 145–156 (2018)
Gruev, V., Perkins, R.: A 1 mpixel CCD image sensor with aluminum nanowire polarization filter. In: Proceedings of 2010 IEEE International Symposium on Circuits and Systems (ISCAS) (2010)
Horváth, G., Barta, A., Gál, J., Suhai, B., Haiman, O.: Ground-based full-sky imaging polarimetry of rapidly changing skies and its use for polarimetric cloud detection. Appl. Opt. 41(3), 543–559 (2002)
Isola, P., Zhu, J.Y., Zhou, T., Efros, A.A.: Image-to-image translation with conditional adversarial networks. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 1125–1134 (2017)
Kaneko, T., Ushiku, Y., Harada, T.: Label-noise robust generative adversarial networks. arXiv e-prints (2018)
Lotter, W., Kreiman, G., Cox, D.: Deep predictive coding networks for video prediction and unsupervised learning (2016)
Mayer, B.: Radiative transfer in the cloudy atmosphere. Eur. Phys. J. Conf. 1, 75–99 (2009)
Pust, N.J., Shaw, J.A.: Dual-field imaging polarimeter using liquid crystal variable retarders. Appl. Opt. 45, 5470 (2006)
Pezzaniti, J.L., Chenault, D.B.: A division of aperture MWIR imaging polarimeter. In: Proceedings of SPIE - The International Society for Optical Engineering vol. 44, no. 3, pp. 515–533 (2005)
Shi, X., Chen, Z., Wang, H., Yeung, D.Y., Wong, W.K., Woo, W.C.: Convolutional LSTM network: A machine learning approach for precipitation nowcasting. MIT Press (2015)
Siewert, C.E.: A discrete-ordinates solution for radiative-transfer models that include polarization effects. J. Quant. Spectrosc. Radiat. Transf. 64(3), 227–254 (2000)
Srivastava, N., Mansimov, E., Salakhutdinov, R.: Unsupervised learning of video representations using LSTMs. JMLR.org (2015)
Tao, Q., et al.: Retrieving the polarization information for satellite-to-ground light communication. J. Opt. 17(8), 085701 (2015)
Tulyakov, S., Liu, M.Y., Yang, X., Kautz, J.: MocoGAN: decomposing motion and content for video generation (2017)
Xu, Z., Du, J., Wang, J., Jiang, C., Ren, Y.: Satellite image prediction relying on GAN and LSTM neural networks. In: ICC 2019-2019 IEEE International Conference on Communications (ICC), pp. 1–6 (2019). https://doi.org/10.1109/ICC.2019.8761462
Schechner, Y.Y., Narasimhan, S.G., Nayar, S.K.: Polarization-based vision through haze. Appl. Opt. 42, 511 (2003)
Zhao, H., Xu, W., Ying, Z., Li, X., Bo, J.: Polarization patterns under different sky conditions and a navigation method based on the symmetry of the AOP map of skylight. Opt. Express 26(22), 28589 (2018)
Zhu, J.Y., Park, T., Isola, P., Efros, A.A.: Unpaired image-to-image translation using cycle-consistent adversarial networks. In: 2017 IEEE International Conference on Computer Vision (ICCV) (2017)
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2021 Springer Nature Switzerland AG
About this paper
Cite this paper
Dang, T. et al. (2021). Multi-Scale Spatial Transform Network for Atmospheric Polarization Prediction. In: Peng, Y., Hu, SM., Gabbouj, M., Zhou, K., Elad, M., Xu, K. (eds) Image and Graphics. ICIG 2021. Lecture Notes in Computer Science(), vol 12888. Springer, Cham. https://doi.org/10.1007/978-3-030-87355-4_40
Download citation
DOI: https://doi.org/10.1007/978-3-030-87355-4_40
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-030-87354-7
Online ISBN: 978-3-030-87355-4
eBook Packages: Computer ScienceComputer Science (R0)