Kernel Extreme Learning Machine for Hyperspectral Image Classification

Yıl 2023, , 198 - 212, 28.09.2023

Mustafa Üstüner

https://doi.org/10.48123/rsgis.1237772

Öz

Hyperspectral images have been actively used in many real-life applications, primarily in remote sensing, since it provides detailed and rich spectral information. There are several challenges in hyperspectral image classification because of the high spectral dimension and the complex structure and hence the advanced classification algorithms (ensemble learning and kernel-based methods) are usually preferred. In this study, the ability of kernel extreme learning machine for the classification of hyperspectral image was investigated and the classification performance was compared with two machine learning algorithms (support vector machines and random forest). “Indian Pines” hyperspectral dataset was used in this experimental study and there are 16 land cover classes in the study area. The principal component analysis was used for the dimensionality reduction and first 40 principal components were selected. The classification was performed for both original dataset and dimensionality reduction applied data. Highest classification accuracies were achieved by support vector machines with overall accuracies of 91,64% and 83,45% for the original dataset and dimensionality reduction applied data, respectively. Furthermore, the original data achieved higher performance with respect to dimensionality reduction applied data in terms of overall accuracy for all methods.

Anahtar Kelimeler

Remote sensing, Extreme learning machine, Hyperspectral

Çekirdek Tabanlı Aşırı Öğrenme Makinesi ile Hiperspektral Görüntü Sınıflandırma

Öz

Hiperspektral görüntüler, zengin spektral bilgi içerdiklerinden dolayı uzaktan algılama başta olmak üzere birçok alanda etkin bir şekilde kullanılmaktadır. Yüksek spektral boyutu ve karmaşık yapılarından dolayı, hiperspektral görüntülerin sınıflandırılmasında bazı sıkıntılar yaşanmaktadır ve bu nedenle sınıflandırma işlemlerinde ileri düzey algoritmalar (topluluk öğrenme algoritmaları, çekirdek tabanlı yöntemler vb.) tercih edilmektedir. Bu çalışma kapsamında, çekirdek tabanlı aşırı öğrenme makinesinin (ÇAÖM) hiperspektral görüntü sınıflandırmadaki kabiliyeti araştırılmış ve sınıflandırma performansı, iki farklı makine öğrenme algoritması (destek vektör makineleri ve rastgele orman) ile karşılaştırılmıştır. Çalışma kapsamında “Indian Pines” hiperspektral veri seti kullanılmıştır ve çalışma alanında 16 adet arazi örtüsü sınıfı bulunmaktadır. Boyut indirgeme amacıyla veriye temel bileşenler analizi yöntemi uygulanmıştır. Sınıflandırma işlemi hem orijinal hiperspektral verisine hem de temel bileşenler analizi ile boyutu indirgenmiş veriye uygulanmıştır. Boyut indirgeme işlemi sonucunda ilk 40 temel bileşen bant olarak seçilmiştir. En yüksek sınıflandırma doğrulukları hem orijinal veri seti için (%91,64) hem de boyutu indirgenmiş veri seti için (%83,45) DVM yöntemi ile elde edilmiştir. Ayrıca, orijinal veri setinin sınıflandırılması ile elde edilen doğrulukların boyutu indirgenmiş verinin sınıflandırması ile elde edilen doğruluklardan daha yüksek olduğu tespit edilmiştir.

Anahtar Kelimeler

Uzaktan algılama, Aşırı öğrenme makinesi, Hiperspektral

Kaynakça

• Adam, E., Mutanga, O., Odindi, J., & Abdel-Rahman, E. M. (2014). Land-use/cover classification in a heterogeneous coastal landscape using RapidEye imagery: evaluating the performance of random forest and support vector machines classifiers. International Journal of Remote Sensing, 35(10), 3440-3458.
• Akar, Ö., & Güngör, O. (2012). Classification of multispectral images using Random Forest Algorithm. Journal of Geodesy and Geoinformation, 1(2), 105-112.
• Baumgardner, M. F., Biehl, L. L., & Landgrebe, D. A. (2015). 220 band aviris hyperspectral image data set: June 12, 1992 Indian pine test site 3. Purdue University Research Repository, 10(7), 991. doi:/10, 4231, R7RX991C.
• Bazi, Y., & Melgani, F. (2006). Toward an optimal SVM classification system for hyperspectral remote sensing images. IEEE Transactions on Geoscience and Remote Sensing, 44(11), 3374-3385.
• Bazi, Y., Alajlan, N., Melgani, F., AlHichri, H., Malek, S., & Yager, R. R. (2014). Differential evolution extreme learning machine for the classification of hyperspectral images. IEEE Geoscience and Remote Sensing Letters, 11(6), 1066-1070.
• Belgiu, M., & Drăguţ, L. (2016). Random forest in remote sensing: A review of applications and future directions. ISPRS Journal of Photogrammetry and Remote Sensing, 114, 24-31.
• Bioucas-Dias, J. M., Plaza, A., Dobigeon, N., Parente, M., Du, Q., Gader, P., & Chanussot, J. (2012). Hyperspectral unmixing overview: Geometrical, statistical, and sparse regression-based approaches. IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing, 5(2), 354-379.
• Bioucas-Dias, J. M., Plaza, A., Camps-Valls, G., Scheunders, P., Nasrabadi, N., & Chanussot, J. (2013). Hyperspectral remote sensing data analysis and future challenges. IEEE Geoscience and Remote Sensing Magazine, 1(2), 6-36.
• Bilgin, G. (2009). Hiperspektral görüntülerin eğiticisiz bölütlenmesi (Doktora tezi). Yıldız Teknik Üniversitesi, İstanbul, Türkiye.
• Camps-Valls, G., Gómez-Chova, L., Calpe-Maravilla, J., Martín-Guerrero, J. D., Soria-Olivas, E., Alonso-Chordá, L., & Moreno, J. (2004). Robust support vector method for hyperspectral data classification and knowledge discovery. IEEE Transactions on Geoscience and Remote Sensing, 42(7), 1530-1542.
• Camps-Valls, G., & Bruzzone, L. (2005). Kernel-based methods for hyperspectral image classification. IEEE Transactions on Geoscience and Remote Sensing, 43(6), 1351-1362.
• Cao, F., Yang, Z., Ren, J., Chen, W., Han, G., & Shen, Y. (2019). Local block multilayer sparse extreme learning machine for effective feature extraction and classification of hyperspectral images. IEEE Transactions on Geoscience and Remote Sensing, 57(8), 5580-5594.
• Chen, C., Li, W., Su, H., & Liu, K. (2014). Spectral-spatial classification of hyperspectral image based on kernel extreme learning machine. Remote Sensing, 6(6), 5795-5814.
• Congalton, R. G. (1991). A review of assessing the accuracy of classifications of remotely sensed data. Remote sensing of environment, 37(1), 35-46.
• Congalton, R.G., & Green, K. (2019). Assessing the accuracy of remotely sensed data: Principles and practices, Third Edition. Boca Raton, FL: CRC Press.
• Datta, D., Mallick, P. K., Bhoi, A. K., Ijaz, M. F., Shafi, J., & Choi, J. (2022). Hyperspectral Image Classification: Potentials, Challenges, and Future Directions. Computational Intelligence and Neuroscience, 2022, 3854635. doi: 10.1155/2022/3854635.
• Dihkan, M., Guneroglu, N., Karsli, F., & Guneroglu, A. (2013). Remote sensing of tea plantations using an SVM classifier and pattern-based accuracy assessment technique. International Journal of Remote Sensing, 34(23), 8549-8565.
• Dixon, B., & Candade, N. (2008). Multispectral landuse classification using neural networks and support vector machines: one or the other, or both?. International Journal of Remote Sensing, 29(4), 1185-1206.
• ELM. (2023, January 17). Basic ELM algorithms. Retrieved from http://www.extreme-learning-machines.org/elm_codes.html.
• Ergul, U., & Bilgin, G. (2017, May). Hyperspectral image classification with hybrid kernel extreme learning machine. In 2017 25th Signal Processing and Communications Applications Conference (SIU), 2017. Proceedings. (pp. 1-4). IEEE.
• Ergul, U., & Bilgin, G. (2020). MCK-ELM: multiple composite kernel extreme learning machine for hyperspectral images. Neural Computing and Applications, 32(11), 6809-6819.
• Foody, G. M. (2002). Status of land cover classification accuracy assessment. Remote sensing of Environment, 80(1), 185-201.
• Foody, G. M., & Mathur, A. (2004). A relative evaluation of multiclass image classification by support vector machines. IEEE Transactions on Geoscience and Remote Sensing, 42(6), 1335-1343.
• Foody, G. M. (2009). Sample size determination for image classification accuracy assessment and comparison. International Journal of Remote Sensing, 30(20), 5273-5291.
• Gao, F., Wang, Q., Dong, J., & Xu, Q. (2018). Spectral and spatial classification of hyperspectral images based on random multi-graphs. Remote Sensing, 10(8), 1271. doi: 10.3390/rs10081271.
• Ghamisi, P., Yokoya, N., Li, J., Liao, W., Liu, S., Plaza, J., ... & Plaza, A. (2017a). Advances in hyperspectral image and signal processing: A comprehensive overview of the state of the art. IEEE Geoscience and Remote Sensing Magazine, 5(4), 37-78.
• Ghamisi, P., Plaza, J., Chen, Y., Li, J., & Plaza, A. J. (2017b). Advanced spectral classifiers for hyperspectral images: A review. IEEE Geoscience and Remote Sensing Magazine, 5(1), 8-32.
• Gislason, P. O., Benediktsson, J. A., & Sveinsson, J. R. (2006). Random forests for land cover classification. Pattern Recognition Letters, 27(4), 294-300.
• Gu, Y., Chanussot, J., Jia, X., & Benediktsson, J. A. (2017). Multiple kernel learning for hyperspectral image classification: A review. IEEE Transactions on Geoscience and Remote Sensing, 55(11), 6547-6565.
• Hidalgo, D. R., Cortés, B. B., & Bravo, E. C. (2021). Dimensionality reduction of hyperspectral images of vegetation and crops based on self-organized maps. Information Processing in Agriculture, 8(2), 310-327.
• Huang, C., Davis, L. S., & Townshend, J. R. G. (2002). An assessment of support vector machines for land cover classification. International Journal of Remote Sensing, 23(4), 725-749.
• Huang, G. B., Zhou, H., Ding, X., & Zhang, R. (2012). Extreme learning machine for regression and multiclass classification. IEEE Transactions on Systems, Man, and Cybernetics, Part B (Cybernetics), 42(2), 513-529.
• Kavzoglu, T., & Colkesen, I. (2009). A kernel functions analysis for support vector machines for land cover classification. International Journal of Applied Earth Observation and Geoinformation, 11(5), 352-359.
• Kavzoğlu, T., & Çölkesen, İ. (2010). Destek vektör makineleri ile uydu görüntülerinin sınıflandırılmasında kernel fonksiyonlarının etkilerinin incelenmesi. Harita Dergisi, 144(7), 73-82.
• Li, J., Xi, B., Du, Q., Song, R., Li, Y., & Ren, G. (2018). Deep kernel extreme-learning machine for the spectral–spatial classification of hyperspectral imagery. Remote Sensing, 10(12), 2036. doi: 10.3390/rs10122036.
• Mathur, A., & Foody, G. M. (2008). Crop classification by support vector machine with intelligently selected training data for an operational application. International Journal of Remote Sensing, 29(8), 2227-2240.
• Maxwell, A. E., Warner, T. A., & Fang, F. (2018). Implementation of machine-learning classification in remote sensing: An applied review. International Journal of Remote Sensing, 39(9), 2784-2817.
• Melgani, F., & Bruzzone, L. (2004). Classification of hyperspectral remote sensing images with support vector machines. IEEE Transactions on Geoscience and Remote Sensing, 42(8), 1778-1790.
• Mohan, A., Sapiro, G., & Bosch, E. (2007). Spatially coherent nonlinear dimensionality reduction and segmentation of hyperspectral images. IEEE Geoscience and Remote Sensing Letters, 4(2), 206-210.
• Pal, M. (2005). Random forest classifier for remote sensing classification. International Journal of Remote Sensing, 26(1), 217-222.
• Pal, M. (2009). Extreme‐learning‐machine‐based land cover classification. International Journal of Remote Sensing, 30(14), 3835-3841.
• Pal, M., Maxwell, A. E., & Warner, T. A. (2013). Kernel-based extreme learning machine for remote-sensing image classification. Remote Sensing Letters, 4(9), 853-862.
• Plaza, A., Benediktsson, J. A., Boardman, J., Brazile, J., Bruzzone, L., Camps-Valls, G., ... & Trianni, G. (2006, July). Advanced processing of hyperspectral images. In 2006 IEEE International Symposium on Geoscience and Remote Sensing, 2006. Proceedings. (pp. 1974-1978). IEEE.
• Plaza, A., Martínez, P., Plaza, J., & Pérez, R. (2005). Dimensionality reduction and classification of hyperspectral image data using sequences of extended morphological transformations. IEEE Transactions on Geoscience and Remote Sensing, 43(3), 466-479.
• Rasti, B., Hong, D., Hang, R., Ghamisi, P., Kang, X., Chanussot, J., & Benediktsson, J. A. (2020). Feature extraction for hyperspectral imagery: The evolution from shallow to deep: Overview and toolbox. IEEE Geoscience and Remote Sensing Magazine, 8(4), 60-88.
• Rodarmel, C., & Shan, J. (2002). Principal component analysis for hyperspectral image classification. Surveying and Land Information Science, 62(2), 115-122.
• Rodriguez-Galiano, V. F., Ghimire, B., Rogan, J., Chica-Olmo, M., & Rigol-Sanchez, J. P. (2012). An assessment of the effectiveness of a random forest classifier for land-cover classification. ISPRS Journal of Photogrammetry and Remote Sensing, 67, 93-104.
• Samat, A., Du, P., Liu, S., Li, J., & Cheng, L. (2014). E2LMs: Ensemble Extreme Learning Machines for Hyperspectral Image Classification. IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing, 7(4), 1060-1069.
• Su, Y., Gao, L., Jiang, M., Plaza, A., Sun, X., & Zhang, B. (2023). NSCKL: Normalized Spectral Clustering With Kernel-Based Learning for Semisupervised Hyperspectral Image Classification. IEEE Transactions on Cybernetics, 53(10), 6649-6662.
• Tuia, D., Camps-Valls, G., Matasci, G., & Kanevski, M. (2010). Learning relevant image features with multiple-kernel classification. IEEE Transactions on Geoscience and Remote Sensing, 48(10), 3780-3791.
• Wang, M., Chen, H., Yang, B., Zhao, X., Hu, L., Cai, Z., ... & Tong, C. (2017). Toward an optimal kernel extreme learning machine using a chaotic moth-flame optimization strategy with applications in medical diagnoses. Neurocomputing, 267, 69-84.
• Waske, B., Benediktsson, J. A., & Sveinsson, J. R. (2012). Random forest classification of remote sensing data. In C.H. Chen (Eds.), Signal and Image Processing for Remote Sensing (pp. 365-374), New York, NY: CRC Pres.
• Xie, F., Lei, C., Jin, C., & An, N. (2020). A novel spectral–spatial classification method for hyperspectral image at superpixel level. Applied Sciences, 10(2), 463. doi: 10.3390/app10020463.
• Zhou, Y., Peng, J., & Chen, C. P. (2015). Extreme learning machine with composite kernels for hyperspectral image classification. IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing, 8(6), 2351-2360.
• Zhou, L., & Ma, L. (2019). Extreme learning machine-based heterogeneous domain adaptation for classification of hyperspectral images. IEEE Geoscience and Remote Sensing Letters, 16(11), 1781-1785.