SELECTING TRAINING SAMPLES AUTOMATICALLY FROM VHR SATELLITE IMAGES FOR IMAGE CLASSIFICATION

Fawzy, Mohamed; Khodary, Farag; Mostafa, Yasser G.

doi:10.21608/sej.2021.155929

	SELECTING TRAINING SAMPLES AUTOMATICALLY FROM VHR SATELLITE IMAGES FOR IMAGE CLASSIFICATION
Sohag Engineering Journal
Article 7, Volume 1, Issue 1, March 2021, Page 71-84 PDF (1.61 MB)
Document Type: Original research articles
DOI: 10.21608/sej.2021.155929
View on SCiNiTO
Authors
Mohamed Fawzy ¹; Farag Khodary¹; Yasser G. Mostafa²
¹Civil Eng. Dept., Faculty of Engineering, South Valley University, Qena, Egypt
²Civil Eng. Dept., Faculty of Engineering, Sohag University, Sohag, Egypt
Abstract
Classification is one of the most significant phases for remote sensing image interpretation. All the supervised classifiers need sufficient and efficient training samples, which are usually selected manually and labeled by visual inspection or field survey. Selecting training samples manually requires more time and human effort. A new method is proposed for automatic selection of training samples from a Very High Resolution (VHR) satellite image. The proposed method is tested for selecting training samples automatically for standard supervised pixel-based classification methods instead of manual samples selection. The proposed method uses a set of indices with specific thresholds to identify the training areas for each class. A certain part of each index histogram can be chosen for each class and consider as training samples. Automatic training samples are compared with manual samples for three standard classification methods. The average accuracy achieved by the proposed automatic sample selection is promising; 76.56% for maximum likelihood classifier, 74.06% for spectral correlation mapper classifier, and 70.00% for spectral angle mapper classifier. Although their accuracy scores are slightly nearby classification with manually selected samples by an average of 1.74% for maximum likelihood, 2.44% for spectral correlation mapper, and 3.75% for spectral angle mapper classifier.
Keywords
Feature extraction; images classification; training samples; worldview-2


References
[1] X. Huang, C. Weng, Q. Lu, T. Feng, and L. Zhang, "Automatic labelling and selection of training samples for high-resolution remote sensing image classification over urban areas," Remote sensing, vol. 7, pp. 16024-16044, 2015. [2] Faten, Y. Mostafa, M. A. Yousef, and Y. A. Abas, "Using of high resolution satellite images for updating large scale mapping in Egypt," J. Eng. Sci, vol. 42, pp. 1122-1137, 2014. [3] C. Li, J. Wang, L. Wang, L. Hu, and P. Gong, "Comparison of classification algorithms and training sample sizes in urban land classification with Landsat thematic mapper imagery," Remote sensing, vol. 6, pp. 964-983, 2014. [4] G. M. Foody and A. Mathur, "The use of small training sets containing mixed pixels for accurate hard image classification: Training on mixed spectral responses for classification by a SVM," Remote sensing of environment, vol. 103, pp. 179-189, 2006. [5] G. M. Foody, "The significance of border training patterns in classification by a feedforward neural network using back propagation learning," International Journal of Remote Sensing, vol. 20, pp. 3549-3562, 1999. [6] R. Bardhan, R. Debnath, and S. Bandopadhyay, "A conceptual model for identifying the risk susceptibility of urban green spaces using geo-spatial techniques," Modeling Earth Systems and Environment, vol. 2, p. 144, 2016. [7] T. G. Van Niel, T. R. McVicar, and B. Datt, "On the relationship between training sample size and data dimensionality: Monte Carlo analysis of broadband multi-temporal classification," Remote sensing of environment, vol. 98, pp. 468-480, 2005. [8] M. Fawzy, Y. Mostafa, and F. Khodary, "AUTOMATIC INDICES BASED CLASSIFICATION METHOD FOR MAP UPDATING USING VHR SATELLITE IMAGES," JES. Journal of Engineering Sciences, vol. 48, pp. 845-868, 2020. [9] Faten, Y. Mostafa, and M. A. Yousef, "THE OPTIMAL METHOD FOR CLASSIFYING HIGH RESOLUTION SATELLITE IMAGES IN EGYPT ENVIRONMENT," J. Eng. Sci, vol. 42, pp. 1106–1121, 2014. [10] Y. Mostafa and A. Abdelhafiz, "Shadow identification in high resolution satellite images in the presence of water regions," Photogrammetric Engineering & Remote Sensing, vol. 83, pp. 87-94, 2017. [11] P. Sarabandi, F. Yamazaki, M. Matsuoka, and A. Kiremidjian, "Shadow detection and radiometric restoration in satellite high resolution images," in IGARSS 2004. 2004 IEEE International Geoscience and Remote Sensing Symposium, 2004, pp. 3744-3747. [12] N. Otsu, "A threshold selection method from gray-level histograms," IEEE transactions on systems, man, and cybernetics, vol. 9, pp. 62-66, 1979. [13] J. B. Campbell and R. H. Wynne, Introduction to remote sensing: Guilford Press, 2011. [14] A. Farrag and Y. Mostafa, "Comparison of Land Cover Change Detection Techniques with Satellite Images: Case Study in Assiut, Egypt," Civil Engineering Research Magazine, Al-Azhar University, vol. 28, pp. 983-996, 2006. [15] J. Richards, "Remote Sensing Digital Image Analysis," ed, 2013, pp. 99-125. [16] Y. Mostafa, ""Comparison of Land Cover Change Detection Methods Using SPOT Images". M.SC Thesis civil Engineering Dept., Assiut University Egypt.," 2006.
Statistics Article View: 250 PDF Download: 408