The week's pick
Random Articles
Reseach Article
Matsar: A Comprehensive Machine Learning Approach for Polsar Data Processing
| International Journal of Computer Applications |
| Foundation of Computer Science (FCS), NY, USA |
| Volume 187 - Number 3 |
| Year of Publication: 2025 |
| Authors: Samay Shetty, Samay Shetty, Jose Akkarapatty, Soham Pal, Aarya Shinde, Avinash Dhiran, Bhakti Talele, Sai Gurav, Varsha Turkar, Yogesh Agarwadkar, Gulab Singh |
10.5120/ijca2025924824
|
Samay Shetty, Samay Shetty, Jose Akkarapatty, Soham Pal, Aarya Shinde, Avinash Dhiran, Bhakti Talele, Sai Gurav, Varsha Turkar, Yogesh Agarwadkar, Gulab Singh . Matsar: A Comprehensive Machine Learning Approach for Polsar Data Processing. International Journal of Computer Applications. 187, 3 ( May 2025), 23-29. DOI=10.5120/ijca2025924824
Abstract
Polarimetric Synthetic Aperture Radar (PolSAR) data collection has evolved considerably over the years. Access to PolSAR data was initially limited due to its high cost, but now an increasing amount of free data is available, greatly advancing progress in the field. PolSAR, a microwave remote sensing technology, provides invaluable insights into Earth's surface through the analysis of polarimetric properties of radar signals. PolSARPro and SNAP are widely utilized free and open-source software programs developed by the European Space Agency (ESA). They include a few classifiers like Wishart (in PolSARPro), Support Vector Machine (in PolSARPro) and Random Forest (in SNAP). However, these programs have some limitations like they can only apply one classifier at a time for a specific area, and in PolSARPro, classifiers can be applied on coherency [T3] or covariance [C3] matrices, not on stacked decomposed images or various features. Additionally, these software tools do not support parallel computing. To address these issues a new user-friendly GUI-based tool: MATSAR, is proposed to make PolSAR data processing easy for everyone from experienced researchers to novices. By integrating advanced processing capabilities with an intuitive interface, MATSAR aims to facilitate broader and more effective utilization of PolSAR data, offering a solution to the current limitations faced in the field.
References
- Hess, L., Melack, J., Filoso, S., & Wang, N. Y. (1995). Delineation of inundated area and vegetation along the Amazon floodplain with the SIR-C synthetic aperture radar. IEEE Transactions on Geoscience and Remote Sensing, 33(4), 896–904. https://doi.org/10.1109/36.406675
- Otukei, J. R., Blaschke, T., Collins, M., &Maghsoudi, Y. (2011). Analysis of ALOS PALSAR and TerraSAR-X data for protected area mapping: A case of the Bwindi Impenetrable National Park-Uganda. IEEE Transactions on Geoscience and Remote Sensing, pp. 348–351.
- Deschamps, B., McNairn, H., Shang, J., & Jiao, X. (2012). Towards operational radar-only crop type classification: Comparison of a traditional decision tree with a random forest classifier. Canadian Journal of Remote Sensing, 38(1), 60–68. https://doi.org/10.5589/m12-012
- Hara, Y., Atkins, R., Yueh, S., Shin, R., & Kong, J. (1994). Application of neural networks to radar image classification. IEEE Transactions on Geoscience and Remote Sensing, 32(1), 100–109. https://doi.org/10.1109/36.285193
- Chen, K. S., Huang, W. P., Tsay, D. H., & Amar, F. (1996). Classification of multifrequency polarimetric SAR imagery using a dynamic learning neural network. IEEE Transactions on Geoscience and Remote Sensing, 34(3), 814–820. https://doi.org/10.1109/36.499786
- Hellmann, M., Jager, G., Kratzschmar, E., &Habermeyer, M. (1999). Classification of full polarimetric SAR-Data using artificial neural networks and fuzzy algorithms. IEEE Geoscience and Remote Sensing Symposium (IGARSS'09), 4, 1995–1997.
- Fukuda, S., Katagiri, R., &Hirosawa, H. (2002). Unsupervised approach for polarimetric SAR image classification using support vector machines. IEEE IGARSS'02, 5, 2599–2601.
- Wu, Y., &Vapnik, V. N. (1999). Statistical learning theory. Technometrics, 41(4), 377. https://doi.org/10.2307/1271368
- Turkar, V., Masurkar, A., Das, A., &Daruwala, R. (2023). Development of Generalized Machine Learning Model to Classify PolSAR Data. IGARSS 2023 - IEEE International Geoscience and RemoteSensingSymposium. https://doi.org/10.1109/igarss52108.2023.10281706.
- Turkar, V., Checker, J., De, S., & Singh, G. (2022). Impact of G4U and 7-component target decomposition on PolSAR image semantic segmentation. Advances in Space Research, 70(12), 3798–3810. https://doi.org/10.1016/j.asr.2022.05.034
Index Terms
Keywords