Open Access Open Access  Restricted Access Subscription or Fee Access

Satellite Image Classification using Deep Learning

Pragati Pejlekar, Poonam Sanjay Choudhari, Pooja Mohan Gund, Ashish bhimrao Shinde

Abstract


Satellite imagery is essential for lots of applications along with catastrophe response, regulation enforcement, and monitoring an environment. These packages require the guide identity of objects and facilities in imagery. Because the geographical areas to be protected are large and the analysts needed to do the searches are scarce, automation is required. Yet traditional item detection and category algorithms are too inaccurate and unreliable to clear up the problem. Deep gaining knowledge refers to a group of machine mastering algorithms that have shown promise in automating such tasks. Using convolutional neural networks, it has achieved total success in photograph knowledge. In this study, we use them to solve the problem of object and facility repute in high resolution multispectral satellite data. The device is made up of a collection of convolutional neural networks and supplementary neural networks that link satellite metadata with image capabilities. It is written in Python and runs on a Linux server with an NVIDIA Titan X GPU, using the Keras and TensorFlow deep learning libraries.


Full Text:

PDF

References


Gong P, Howarth PJ. Land-use classification of SPOT HRV data using a cover frequency method.Int J Remote Sens. 1992; 13(8): 1459–1471.

Pal M, Mather PM. An assessment of the effectiveness of decision tree methods for land coverclassification. Remote Sens Environ. 2003; 86(4): 554–565.

Zhang H, Hou D, Zhou Z. A Novel Lane Detection Algorithm Based on Support Vector Machine. Progress in Electromagnetics Research Symposium, Hangzhou, China. 2005 Aug 22–26; 1: 390–394.

Luand D, Weng Q. A survey of image classification methods and techniques for improving classification performance. Int J Remote Sens. 2007; 28(5): 823–870.

Fang C, Wen H. A new classification method based on Cloude Pottier eigenvalue/eigenvector decomposition. IEEE International Proceedings Geoscience and Remote sensing symposium, IGARSS’05. 2005; 1: 4.

Mercier G, Girard-Ardhuin F. Partially Supervised Oil-Slick Detection by SAR Imagery Using Kernel Expansion. IEEE Trans Geosci Remote Sens. 2006; 44(10): 2839–2846.

Melgani F, Serpico SB, Vernazza G. Fusion of Multitemporal Contextual Information by Neural Networks for Multisensor Remote Sensing Image Classification. Integr Comput Aided Eng. 2003;10(1): 81–90.

Greiwe A. An unsupervised image end member definition approach. 1st EARSeL Workshop of

the SIG Urban Remote Sensing. 2006.

Yen CC, Kuo SS. Degraded documents recognition using pseudo 2D hidden Markov models in Gray-scale images. Proc SPIE. 1994; 2277: 180–191.

Kurian J, Karunakaran V. A survey on image classification methods. Int J Adv Res Electron Commun Eng (IJARECE). 2012 Oct 4; 1(4): 69–72.

Mnih V, Hinton G. Learning to detect roads in high-resolution aerial images. In Proceedings of the 11th European Conference on Computer Vision (ECCV). 2010 Sep; 210–223.

Romero A, Gatta C, Camps-Valls G. Unsupervised deep feature extraction of hyperspectral images. 2014 6th Workshop on Hyperspectral Image and Signal Processing: Evolution in Remote Sensing (WHISPERS). 2014; 1–4.

Rouse JW, Haas RH, Schell JA, Deering DW. Monitoring vegetation systems in the great plains with ERTS. NASA Goddard Space Flight Center 3d ERTS-1 Symposium. 1974; 309–317.

Saxe A, Koh PW, Chen Z, Bhand M, Suresh B, Ng A. On random weights and unsupervised feature learning. In: Getoor L, Scheffer T, editors. Proceedings of the 28th International Conference on Machine Learning (ICML-11), ICML’11; New York, NY, USA; ACM. 2011 Jun;1089–1096.

Scherer D, Müller A, Behnke S. Evaluation of pooling operations in convolutional architectures for object recognition. In International conference on artificial neural networks. 2010 Sep 15; 92–101. Springer, Berlin, Heidelberg.

Soh LK, Tsatsoulis C. Texture analysis of sar sea ice imagery using gray level co-occurrence matrices. IEEE Trans Geosci Remote Sens. 1999; 37(2): 780–795.

Taigman Y, Yang M, Ranzato M, Wolf L. DeepFace: Closing the Gap to Human-Level Performance in Face Verification. In Conference on Computer Vision and Pattern Recognition(CVPR). 2013.

Tokarczyk P, Montoya J, Schindler K. An evaluation of feature learning methods for high resolution image classification. ISPRS Ann Photogram, Remote Sens Spat Inf Sci. 2012; I-3: 389–394.

Tucker CJ. Red and photographic infrared linear combinations for monitoring vegetation. Remote Sens Environ. 1979; 8(2): 127–150.

Vaduva C, Gavat I, Datcu M. Deep learning in very high-resolution remote sensing image information mining communication concept. In 2012 Proceedings of the 20th European Signal Processing Conference (EUSIPCO). 2012 Aug; 2506–2510.




DOI: https://doi.org/10.37628/ijosct.v8i1.794

Refbacks

  • There are currently no refbacks.