Classification of multi-spectral data with fine-tuning variants of representative models

Due to rapid urbanization, agriculture drought, and environmental pollution, significant efforts have been focused on land use and land cover (LULC) multi-spectral scene classification. Identifying the changes in land use and land cover can facilitate updating the geographical maps. Besides, the technical challenges in multi-spectral images with implicit deep learning models due to the nature of multi-modal, it tackles real-life issues such as the collection of large-scale high-resolution data. The limited training samples are considered a crucial challenge in LULC deep learning classification as requiring a huge number of training samples to ensure the optimal learning procedure. The present work has focused on considering the fraction of multi-spectral data (EuroSAT data) and evaluated the exemplary CNN architectures such as shallow network (VGG16) and deep network (ResNet152V2) with different tuning variants along with the additional layers prior to classification layer to improve the optimal training of the networks to classify the multi-spectral data. The performance of the thirteen spectral bands of EuroSAT dataset that contain ten scene classes of land use and land cover were analyzed band-wise and combination of spectral bands. For the scene class ‘Sea & lake’ the best accuracy obtained was 96.17% with individual band B08A and 95.7% with Color Infra Red (CIR) band combination. The analysis provided in this work enables the remote sensing research community to boost performance even if the multi-spectral dataset size is small.