Abstract
Thanks to the development of satellite remote sensing technology, more observing data are acquired and can be used for various purposes. However, statistical data show that half of the earth’s surface is covered by clouds, which may seriously influence the usability of remote sensing data. Most existing cloud detection methods are manual or semi-automatic methods with low efficiency. This paper focuses on automatic cloud detection over sea surface from Advanced Very High Resolution Radiometer (AVHRR) data. A novel cloud detection framework named DBN-Otsu Hybrid Model (DOHM) has been proposed, which combines Deep Belief Networks (DBN) and Otsu’s method for the first time. DOHM adopts adaptive thresholds to replace manual interventions, implementing full automation. Experimental results show that DOHM achieves the highest average accuracy ratio among the six detection methods. Moreover, DOHM makes a good balance between False Alarm Rate (FAR) and Miss Rate (MR).
This is a preview of subscription content, log in via an institution.
Buying options
Tax calculation will be finalised at checkout
Purchases are for personal use only
Learn about institutional subscriptionsReferences
Cazorla, A., Husillos, C., Antón, M., Alados-Arboledas, L.: Multi-exposure adaptive threshold technique for cloud detection with sky imagers. Sol. Energy 114, 268–277 (2015)
Jedlovec, G.J., Haines, S.L., LaFontaine, F.J.: Spatial and temporal varying thresholds for cloud detection in GOES imagery. IEEE Trans. Geosci. Remote Sens. 46(6), 1705–1717 (2008)
Andjunyang, Q.W.: A hybrid thresholding algorithm for cloud detection on ground-based color images. J. Atmos. Ocean. Technol. 28, 1286–1296 (2011)
Liu, S., Zhang, Z., Xiao, B., Cao, X.: Ground-based cloud detection using automatic graph cut. IEEE Geosci. Remote Sens. Lett. 12(6), 1342–1346 (2017)
Champion, N.: Automatic detection of clouds and shadows using high resolution satellite image time series. Int. Arch. Photogramm. Remote Sens. Spat. Inf. Sci. XLI-B3, 475–479 (2016)
Başeski, E., Cenaras, Ç.: Texture and color based cloud detection. In: International Conference on Recent Advances in Space Technologies, pp. 32–36. IEEE, London (2015)
Liu, S., Zhang, L., Zhang, Z., Wang, C., Xiao, B.: Automatic cloud detection for all-sky images using superpixel segmentation. IEEE Geosci. Remote Sens. Lett. 12(2), 354–358 (2014)
Li, Z., Shen, H., Li, G., Xia, P., Gamba, L.Zhang: Multi-feature combined cloud and cloud shadow detection in GaoFen-1 wide field of view imagery. Remote Sens. Environ. 191, 342–358 (2016)
Rossi, R., Basili, R., Frate, F.D., Luciani, M., Mesiano, F.: Techniques based on support vector machines for cloud detection on QuickBird satellite imagery. In: 2011 IEEE International Geoscience and Remote Sensing Symposium, pp. 515–518. IEEE, Vancouver (2011)
Yuan, Y., Hu, X.: Bag-of-words and object-based classification for cloud extraction from satellite imagery. IEEE J. Sel. Top. Appl. Earth Obs. Remote Sens. 8(8), 4197–4205 (2015)
Xu, L., Wong, A., Clausi, D.A.: A novel Bayesian spatial-temporal random field model applied to cloud detection from remotely sensed imagery. IEEE Trans. Geosci. Remote Sens. 55(9), 4913–4924 (2017)
Zhang, Q., Xiao, C.: Cloud detection of RGB color aerial photographs by progressive refinement scheme. IEEE Trans. Geosci. Remote Sens. 52(11), 7264–7275 (2014)
Bengio, Y.: Learning deep architectures for AI. Found. Trends Mach. Learn. 2(1), 1–127 (2009)
Hinton, G.E., Salakhutdinov, R.R.: Reducing the dimensionality of data with neural networks. Science 313(5786), 504–507 (2006)
Larochelle, H., Bengio, Y.: Exploring strategies for training deep neural networks. J. Mach. Learn. Res. 10, 1–40 (2009)
Zhu, Z., Wang, S., Woodcock, C.E.: Improvement and expansion of the Fmask algorithm: cloud, cloud shadow, and snow detection for Landsats 4–7, 8, and Sentinel 2 images. Remote Sens. Environ. 15(9), 269–277 (2015)
Goff, M.L., Tourneret, J.Y., Wendt, H., Ortner, M., Spigai, M.: Distributed boosting for cloud detection. In: 2016 IEEE International Geoscience and Remote Sensing Symposium, pp. 134–146. IEEE, Beijing (2016)
Xie, F., Shi, M., Shi, Z., Yin, J., Zhao, D.: Multilevel cloud detection in remote sensing images based on deep learning. IEEE J. Sel. Top. Appl. Earth Obs. Remote Sens. 10(8), 3631–3640 (2017)
Shi, C., Wang, Y., Wang, C., Xiao, B.: Ground-based cloud detection using graph model built upon superpixels. IEEE Geosci. Remote Sens. Lett. 9(9), 1–5 (2017)
Li, Z., Shen, H., Li, H., Zhang, L.: Automatic cloud and cloud shadow detection in GF-1 WFV imagery using multiple features. In: 2016 IEEE International Geoscience and Remote Sensing Symposium (IGARSS), pp. 7612–7615. IEEE, Beijing (2016)
Islam, T., et al.: CLOUDET: a cloud detection and estimation algorithm for passive microwave imagers and sounders aided by Naïve Bayes classifier and multilayer perceptron. IEEE J. Sel. Top. Appl. Earth Obs. Remote Sens. 8(9), 4296–4301 (2015)
Ufuk, D.U., Demirpolat, C., Demirci, M.F.: Fast cloud detection using low-frequency components of satellite imagery. In: Signal Processing and Communications Applications Conference. IEEE, Malatya (2017)
Hinton, G.E., Osindero, S., Teh, Y.W.: A fast learning algorithm for deep belief nets. Neural Comput. 18(7), 1527–1554 (2006)
An, Z., Shi, Z.: Scene learning for cloud detection on remote-sensing images. IEEE J. Sel. Top. Appl. Earth Obs. Remote Sens. 8(8), 4206–4222 (2015)
Acknowledgement
The satellite data are provided by Satellite Ground Station of Ocean University of China.
This work is supported by the National Natural Science Foundation of China (61572448, 61673357), the Natural Science Foundation of Shandong Province (ZR2014JL043), and the Key R&D Program of Shandong Province (2018GSF120015).
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2018 Springer Nature Singapore Pte Ltd.
About this paper
Cite this paper
Qiu, M., Yin, H., Chen, Q., Liu, Y. (2018). Automatic Cloud Detection Based on Deep Learning from AVHRR Data. In: Zhou, ZH., Yang, Q., Gao, Y., Zheng, Y. (eds) Artificial Intelligence. ICAI 2018. Communications in Computer and Information Science, vol 888. Springer, Singapore. https://doi.org/10.1007/978-981-13-2122-1_10
Download citation
DOI: https://doi.org/10.1007/978-981-13-2122-1_10
Published:
Publisher Name: Springer, Singapore
Print ISBN: 978-981-13-2121-4
Online ISBN: 978-981-13-2122-1
eBook Packages: Computer ScienceComputer Science (R0)