Remote Sensing

Remote Sensing is the research area in which the Earth's surface is studied, usually using the reflectance spectrum of the Sun. Vision Lab has built expertise in the processing and analysis of multispectral and hyperspectral remote sensing images. Topics of research include the development of techniques for image denoising, restoration, fusion, segmentation, classification and spectral unmixing. Recently, research is shifted to more close-range applications, for which we have our own acquisition equipement (spectrometer 400-2500 nm; VNIR camera 400-900 nm and SWIR camera 1000-1700 nm). Applications are material characterization (corrosion, soil moisture, powder material composition).

Journal publications


P. Gosh, Roy, S. Kumar, Koirala, B., Rasti, B., and Scheunders, P., Hyperspectral Unmixing using Transformer Network, IEEE Transactions on Geoscience and Remote Sensing, vol. 60, pp. 1-16, 2022.PDF icon transformer_unmixing_author_version_to_upload.pdf (14.65 MB)
G. Zhang, Scheunders, P., Cerra, D., and Muller, R., Shadow-aware nonlinear spectral unmixing for hyperspectral imagery, IEEE-JSTARS, Journal of Selected Topics in Applied Earth Observations and Remote Sensing, vol. 15, pp. 5514-5533, 2022.PDF icon shadow-aware_nonlinear_spectral_unmixing_for_hyperspectral_imagery.pdf (9.51 MB)
K. Rafiezadeh Sahi, Ghamisi, P., Rasti, B., Scheunders, P., and Gloaguen, R., Unsupervised Data Fusion with Deeper Perspective: A Novel Multi-Sensor Deep Clustering Algorithm, IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing , vol. 15, pp. 284-296, 2022.PDF icon mdc_jstars-final_version.pdf (6.53 MB)


B. Rasti and Koirala, B., SUnCNN: Sparse Unmixing Using Unsupervised Convolutional Neural Network, IEEE Geoscience and Remote Sensing Letters, vol. 19, pp. 1-5, 2021.PDF icon ieee_grsl_sundip.pdf (2.34 MB)