Abstract
Water body extraction from remote sensing image data has been becoming a really hot topic. Recently, researchers put forward numerous methods for water body extraction, while most of them rely on elaborative feature selection and enough number of training samples. Convolution Neural Network (CNN), one of the implementation models of deep learning, has strong capability for two-dimension images’ classification. A new water body extraction model based on CNNs is established for deep multi-feature learning. Before experiment, image enhancement will be done by Dark Channel Prior. Then we concatenate three kinds of features: spectral information, spatial information that is extracted by Extended Multi-attribute Profile (EMAP) and various water indexes firstly. Next, feature matrixes are acted as the input of CNN-based model for training and classifying. The experimental results showed that the proposed model has better classification performance than Support Vector Machine (SVM) and artificial neural network (ANN). On very limited training set, our model could learn unique and representative features for better water body extraction.
Similar content being viewed by others
REFERENCES
Willis, K.S., Remote sensing change detection for ecological monitoring in United States protected areas, Biol. Conserv., 2015, vol. 182, pp. 233–242.
González, M.P., Bonaccorso, E., and Papeş, M., Applications of geographic information systems and remote sensing techniques to conservation of amphibians in northwestern Ecuador, Glob. Ecol. Conserv., 2015, vol. 3, pp. 562–574.
Calvin, W.M., Littlefield, E.F., Kratt, C., Remote sensing of geothermal-related minerals for resource exploration in Nevada, Geothermics, 2015, vol. 53, pp. 517–526.
Volpi, M., Petropoulos, G.P., and Kanevski, M., Flooding extent cartography with Landsat TM imagery and regularized Kernel Fisher’s discriminant analysis, Comput. Geosci., 2013, vol. 57, pp. 24–31.
Brisco, B., Schmitt, A., Murnaghan, K., Kaya, S., and Roth, A., Sar polarimetric change detection for flooded vegetation, Int. J. Digit. Earth, 2013, vol. 6, pp. 103–114.
Chen, H.F., Wang, J.L., Chen, Z., Yang, L., and Xi, W., Comparison of water extraction methods in mountainous plateau region from TM image, Remote Sens. Technol. Appl., 2004, vol. 19, no. 6, pp. 479–484.
Jupp, D.L.B., Landsat based interpretation of the Cairns section of the Great Barrier Reef Marine Park, in Division of Water and Land Resources, Commonwealth Scientific and Industrial Research Organization, 1985.
Du, Y.Y. and Zhou, C.H., Automatically extracting remote sensing information for water bodies, J. Remote Sens., 1998, vol. 2, no. 4, pp. 264–269.
Wang, J., Zhang, Y., and Kong, G., The application of multi-band spectral relationship method in water body extraction, Mine Surv., 2004, vol. 4, pp. 30–32.
McFeeters, S.K., The use of Normalized Difference Water Index (NDWI) in the delineation of open water features, Int. J. Remote Sens., 1996, vol. 17, no. 7, pp. 1425–1432.
Xu, H., Fast information extraction of urban built-up land based on the analysis of spectral signature and normalized difference index, Geogr. Res., 2005, vol. 9, no. 5, pp. 589–595.
Jian, X., Chen, H., Xing, Z.Y., Fang, T., and Yin, L.Y., Influence of waterbody types on threshold of waterbody area extraction using remote sensing technology, Sci. Tech. Eng., 2014, vol. 14, no. 18, pp. 267–270.
Gao, F., Zhang, L., Wang, J., and Mei, J., Change detection in remote sensing images of damage areas with complex terrain using texture information and SVM, International Conference on Circuits and Systems (CAS 2015), 2015.
Mountrakis, G., Im, J., and Ogole, C., Support vector machines in remote sensing: A review, ISPRS J. Photogramm. Remote Sens., 2011, vol. 66, no. 3, pp. 247–259.
Kumar, P., et al., Comparison of support vector machine, artificial neural network, and spectral angle mapper algorithms for crop classification using LISS IV data, Int. J. Remote Sens., 2015, pp. 1604–1617.
Zhang, Y., Gao, J., and Wang, J., Detailed mapping of a salt farm from Landsat TM imagery using neural network and maximum likelihood classifiers: A comparison, Int. J. Remote Sens., 2007, vol. 28, no. 10, pp. 2077–2089.
Wang, Y., Huang, F., and Wei, Y., Water body extraction from LANDSAT ETM+ image using MNDWI and K-T transformation, IEEE 2013 21st International Conference on Geoinformatics, 2013, pp. 1–5.
Jiang Hao, et al., An automated method for extracting rivers and lakes from Landsat imagery, Remote Sens., 2014, vol. 6, no. 6, pp. 5067–5089.
Soille, P. and Pesaresi, M., Advances in mathematical morphology applied to geoscience and remote sensing, IEEE Trans. Geosci. Remote Sens., 2002, vol. 40, no. 9, pp. 2043–2055.
Marpu, P.R., Pedergnana, M., Mura, M.D., et al., Automatic generation of standard deviation attribute profiles for spectral–spatial classification of remote sensing data, IEEE Geosci. Remote Sens. Lett., 2013, vol. 10, no. 2, pp. 293–297.
Dalla Mura, M., Benediktsson, J.A., Waske, B., and Bruzzone, L., Morphological attribute profiles for the analysis of very high resolution images, IEEE Trans. Geosci. Remote Sens., 2010, vol. 48, no. 10, pp. 3747–3762.
Dalla Mura, M., et al., Extended profiles with morphological attribute filters for the analysis of hyperspectral data, Int. J. Remote Sens., 2010, vol. 31, no. 22, pp. 5975–5991.
Dalla Mura, M., et al., Classification of hyperspectral images by using extended morphological attribute profiles and independent component analysis, IEEE Geosci. Remote Sens. Lett., 2011, vol. 8, no. 3, pp. 542–546.
Marpu, P.R., Pedergnana, M., Dalla Mura, M., Benediktsson, J.A., and Bruzzone, L., Automatic generation of standard deviation attribute profiles for spectral-spatial classification of remote sensing data, IEEE Geosci. Remote Sens. Lett., 2013, vol. 10, no. 2, pp. 293–297.
Li, J., Huang, X., Gamba, P., Bioucas-Dias, J.M., Zhang, L., Benediktsson, J.A., and Plaza, A., Multiple feature learning for hyperspectral image classification, IEEE Trans. Geosci. Remote Sens., 2015, vol. 53, no. 3, pp. 1592–1606.
Hinton, G.E. and Salakhutdinov, R.R., Reducing the dimensionality of data with neural networks, Science, 2006, vol. 313, no. 5786, pp. 504–507.
Lecun, Y., Bottou, L., Bengio, Y., and Haffner, P., Gradient-based learning applied to document recognition, Proc. IEEE, 1998, vol. 86, no. 11, pp. 2278–2324.
Chen, Y., Han, C., Wang, C., Jeng, B., and Fan, K., The application of a convolution neural network on face and license plate detection, 18th International Conference on Pattern Recognition, 2006, vol. 3, pp. 552–555.
Krizhevsky, A., Sutskever, I., and Hinton, G.E., ImageNet classification with deep convolutional neural networks, Adv. Neural Inf. Process. Syst., 2012, vol. 2012.
Simonyan, K. and Zisserman, A., Very deep convolutional networks for large-scale image recognition, Eprint Arxiv, 2014.
Mnih, V. and Hinton, G.E., Learning to detect roads in high-resolution aerial images, Computer Vision-ECCV 2010; Lect. Notes Comput. Sci., 2010, vol. 6316, pp. 210–223.
Lü, Q., Dou, Y., Niu, X., Xu, J.Q., and Xia, F., Remote sensing image classification based on DBN model, J. Comput. Res. Dev., 2014, vol. 51, no. 9, pp. 1911–1918.
Yushi Chen, Zhouhan Lin, Xing Zhao, Gang Wang, and Yanfeng Gu, Deep learning-based classification of hyperspectral data, IEEE J. Sel. Top. Appl. Earth Obs. Remote Sens., 2014, vol. 7, no. 6, pp. 2094–2107.
Wei Hu, Yangyu Huang, Li Wei, Fan Zhang, and Hengchao Li, Deep convolutional neural networks for hyperspectral image classification, J. Sens., 2015, vol. 2015, Article ID 258619.
Fukushima, K., Neocognitron: A hierarchical neural network capable of visual pattern recognition, Neural Networks, 1988, vol. 1, no. 2, pp. 119–130.
Zhang Jian-Ming, Zhan Zhi-Cai, Cheng Ke-Yang, et al., Review on development of deep learning, J. JIangsu Univ., 2015, vol. 36, no. 2, pp. 191–200.
Bouvrie, J., Notes on Convolutional Neural Networks, 2006.
Wu Di and Zhu Qing-Song, The latest research progress of image dehazing, Acta Autom. Sin., 2015, vol. 41, no. 2, pp. 221–239.
He., K., Sun, J., and Tang, X., Single image haze removal using dark channel prior, IEEE Trans. Pattern Anal. Mach. Intell., 2009, no. 33, p. 5.
Zha, Y., Gao, J., and Ni, S., Use of normalized difference built-up index in automatically mapping urban areas from TM imagery, Int. J. Remote Sens., 2003, vol. 24, no. 3, pp. 583–594.
ACKNOWLEDGMENTS
This work was supported by the Natural Science Foundation of Xinjiang Uygur Autonomous Region (no. 2016D01C050).
Author information
Authors and Affiliations
Corresponding author
Additional information
The article is published in the original.
About this article
Cite this article
Yu, L., Zhang, R., Tian, S. et al. Deep Multi-Feature Learning for Water Body Extraction from Landsat Imagery. Aut. Control Comp. Sci. 52, 517–527 (2018). https://doi.org/10.3103/S0146411618060123
Received:
Accepted:
Published:
Issue Date:
DOI: https://doi.org/10.3103/S0146411618060123