Abstract
Desert classification is the fundamental for preventing and/or controlling desertification. Topographical features of desert remote sensing images change constantly due to the uncertainty of desert terrain, illumination, and other properties. Therefore, it is a very challenging task to accurately classify desert areas. In order to quickly and accurately classify desert from remote sensing images, this paper proposed a multi-scale residual network based on an attention mechanism. The network used conventional convolutions to perform preliminary feature extraction on images, and subsequently adopted a multi-scale residual module to further process the feature maps. Based on the idea of fusing multi-scale features, the multi-scale residual module effectively reduced information loss and possible gradient disappearance because of using skip connections. By introducing the attention mechanism, dependencies between feature channels were established, as a result, the network could recalibrate channel characteristic responses adaptively. Experimental results showed that the proposed network had better generalization ability and a higher accuracy on classification of multispectral desert remote sensing images compared with other methods.
Similar content being viewed by others
References
Belgiu, M. and Drăguţ, L.L., 2016, Random forest in remote sensing: a review of applications and future directions. ISPRS Journal of Photogrammetry and Remote Sensing, 114, 24–31.
Fu, G., Liu, C., Zhou, R., Sun, T., and Zhang, Q., 2017, Classification for high resolution remote sensing imagery using a fully convolutional network. Remote Sensing, 9, 498.
Guli, J., Liang, S., Yi, Q., and Liu, J., 2015, Vegetation dynamics and responses to recent climate change in xinjiang using leaf area index as an indicator. Ecological Indicators, 58, 64–76.
Hamida, A.B., Benoit, A., Lambert, P., and Amar, C.B., 2018, 3-D deep learning approach for remote sensing image classification. IEEE Transactions on Geoscience and Remote Sensing, 56, 4420–4434.
He, K., Zhang, X., Ren, S., and Sun, J., 2016, Deep residual learning for image recognition. IEEE Conference on Computer Vision and Pattern Recognition (CVPR), Las Vegas, Jun. 27–30, p. 770–778.
Hu, G., Dong, Z., Lu, J., and Yan, C., 2012, Driving forces responsible for aeolian desertification in the source region of the Yangtze River from 1975 to 2005. Environmental Earth Sciences, 66, 257–263.
Hu, J., Shen, L., and Sun, G., 2018, Squeeze-and-excitation networks. IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR). Salt Lake City, Jun. 18–23, p. 7132–7141.
Hu, L., Xiaofeng, W., and Yaqi, G., 2004, Analysis and assessment of land desertification in Xinjiang based on RS and GIS. Journal of Geographical Sciences, 14, 159–166.
Hu, W., Huang, Y., Wei, L., Zhang, F., and Li, H., 2015, Deep convolutional neural networks for hyperspectral image classification. Journal of Sensors, 2015, 258619.
Huang, G., Liu, Z., Van Der Maaten, L., and Weinberger, K.Q, 2017, Densely connected convolutional networks. IEEE Conference on Computer Vision and Pattern Recognition (CVPR). Honolulu, Jul. 21–26, p. 4700–4708.
Ioffe, S. and Szegedy, C., 2015, Batch normalization: accelerating deep network training by reducing internal covariate shift. arXiv: 1502.03167. https://arxiv.org/abs/1502.03167 [Accessed on 11 July 2020].
Jian, W., Rong, D.G., Jun, L.W., Hong, W.L., and Han, T., 2002, Primary study on the multi-layer remote sensing information extraction of desertification land types by using decision tree technology. IEEE International Geoscience and Remote Sensing Symposium (IGARSS), Toronto, Jun. 24–28, p. 2513–2515.
Jiang, T., Liu, X., and Wu, L., 2018, Method for mapping rice fields in complex landscape areas based on pre-trained convolutional neural network from HJ-1 A/B data. ISPRS International Journal of Geo-Information, 7, 418.
Kadavi, P.R. and Lee, C.W., 2018, Land cover classification analysis of volcanic island in Aleutian Arc using an Artificial Neural Network (ANN) and a Support Vector Machine (SVM) from Landsat imagery. Geosciences Journal, 22, 653–665.
Krizhevsky, A., Sutskever, I., and Hinton, G.E., 2012, Imagenet classification with deep convolutional neural networks. Proceedings of the 25th International Conference on Neural Information Processing Systems, Lake Tahoe, Dec. 3–8, p. 1097–1105.
LeCun, Y., Bottou, L., Bengio, Y., and Haffner, P., 1998, Gradient-based learning applied to document recognition. Proceedings of the IEEE, 86, 2278–2324.
Liu, B., Li, Y., Li, G., and Liu, A., 2019, A spectral feature based convolutional neural network for classification of sea surface oil spill. ISPRS International Journal of Geo-Information, 8, 160.
Lin, M., Chen, Q., and Yan, S., 2013, Network in network. ArXiv: 1312.4400. https://arxiv.org/abs/1312.4400v2 [Accessed on 11 July 2020].
Moghaddam, M.H.R., Sedighi, A., Fasihi, S., and Firozjaei, M.K., 2018, Effect of environmental policies in combating aeolian desertication over Sejzy Plain of Iran. Aeolian Research, 35, 19–28.
Moosavi, V., Shamsi, S.R.F., Moradi, H., and Shirmohammadi, B., 2014, Application of Taguchi method to satellite image fusion for object-oriented mapping of Barchan dunes. Geosciences Journal, 18, 45–59.
Moustafa, O.R.M. and Cressman, K., 2015, Using the enhanced vegetation index for deriving risk maps of desert locust (Schistocerca gregaria, Forskal) breeding areas in Egypt. Journal of Applied Remote Sensing, 8, 084897.
Réjichi, S. and Chaabane, F., 2015, Feature extraction using PCA for VHR satellite image time series spatio-temporal classification. IEEE International Geoscience and Remote Sensing Symposium (IGARSS), Milan, Jul. 26–31, p. 485–488.
Rumelhart, D.E., Hinton, G.E., and Williams, R.J., 1986, Learning representations by back-propagating errors. Nature, 323, 533–536.
Seydgar, M., Alizadeh Naeini, A., Zhang, M., Li, W., and Satari, M., 2019, 3-D convolution-recurrent networks for spectral-spatial classification of hyperspectral Images. Remote Sensing, 11, 883.
Simonyan, K. and Zisserman, A., 2014, Very deep convolutional networks for large-scale image recognition. arXiv: 1409.1556. https://arxiv.org/abs/1409.1556 [Accessed on 11 July 2020].
Szegedy, C., Liu, W., Jia, Y., Sermanet, P., Reed, S., Anguelov, D., Vanhoucke, V., and Rabinovich, A., 2015, Going deeper with convolutions. IEEE Conference on Computer Vision and Pattern Recognition (CVPR), Boston, Jun. 7–12, p. 1–9.
Szegedy, C., Vanhoucke, V., Ioffe, S., Shlens, J., and Wojna, Z., 2016, Rethinking the inception architecture for computer vision. IEEE Conference on Computer Vision and Pattern Recognition (CVPR). Las Vegas, Jun. 27–30, p. 2818–2826.
Valle, H.F.D., Rostagno, C.M., Coronato, F.R., Bouza, P.J., and Blanco, P.D., 2008, Sand dune activity in north-eastern Patagonia. Journal of Arid Environments, 72, 411–422.
Wang, J. and Li, W., 2002, Primary study on the multi-layer remote sensing information extraction of desertification land types by using decision tree technology. IEEE International Geoscience and Remote Sensing Symposium (IGARSS). Toronto, Jun. 24–28, p. 2513–2515.
Xia, M., Liu, W.A., Shi, B., Weng, L., and Liu, J., 2019a, Cloud/snow recognition for multispectral satellite imagery based on a multidimensional deep residual network. International Journal of Remote Sensing, 40, 156–170.
Xia, M., Liu, W., Xu, Y., Wang, K., and Zhang, X., 2019b, Dilated residual attention network for load disaggregation. Neural Computing and Applications, 31, 8931–8953
Xia, M., Qian, J., Zhang, X., Liu, J., and Xu, Y., 2020a, River segmentation based on separable attention residual network. Journal of Applied Remote Sensing, 14, 032602.
Xia, M., Zhang, X., Liu, W., Weng, L., and Xu, Y., 2020b, Multi-stage feature constraints learning for age estimation. IEEE Transactions on Information Forensics and Security, 15, 2417–2428.
Xie, S., Girshick, R., Dollár, P., Tu, Z., and He, K., 2017, Aggregated residual transformations for deep neural networks. IEEE Conference on Computer Vision and Pattern Recognition (CVPR), Honolulu, Jul. 21–26, p. 1492–1500.
Yang, X., Zhang, K., Jia, B., and Ci, L., 2005, Desertification assessment in China: an overview. Journal of Arid Environments, 63, 517–531.
Yue, Y., Ye, X., Zou, X., Wang, J.A., and Gao, L., 2017, Research on land use optimization for reducing wind erosion in sandy desertified area: a case study of Yuyang County in Mu Us Desert, China. Stochastic Environmental Research and Risk Assessment, 31, 1371–1387.
Zhang, F., Tiyip, T., Johnson, V.C., Kung, H., Ding, J., Zhou, M., Fan, Y., and Kelimu, A., 2015, Evaluation of land desertification from 1990 to 2010 and its causes in Ebinur Lake region, Xinjiang China. Environmental Earth Sciences, 73, 5731–5745.
Zhang, L., Yue, L., and Xia, B., 2003, The study of land desertification in transitional zones between the MU US Desert and the Loess Plateau using RS and GIS — a case study of the Yulin region. Environmental Geology, 44, 530–534.
Acknowledgments
This work is supported in part by, the National Natural Science Foundation of PR China (61773219), the Natural Science Foundation of Jiangsu (BK20161533), and Qing Lan Project of Jiangsu Province. The authors declare no conflict of interest.
Author information
Authors and Affiliations
Corresponding author
Additional information
Publisher’s Note Springer Nature remains neutral with regard to jurisdictional claims in published maps and institutional affiliations.
Rights and permissions
About this article
Cite this article
Weng, L., Wang, L., Xia, M. et al. Desert classification based on a multi-scale residual network with an attention mechanism. Geosci J 25, 387–399 (2021). https://doi.org/10.1007/s12303-020-0022-y
Received:
Accepted:
Published:
Issue Date:
DOI: https://doi.org/10.1007/s12303-020-0022-y