Change Detection and Classification using Hyperspectral Imagery

Hyperspectral Imagery is a field with various applications in the present world. Classification and Change Detection (CD) have been fields of great importance over the years. Powerful tools are built by combining these two approaches, HSI with classification and with change detection. Deep learning-based land-cover classification and change detection algorithms have made significant advancements during recent times. In this paper, a band-specific feature extraction and classification method using 2D and 3D CNN (Hybrid Spectral Net) is being projected, which is computationally more accessible. Also, a change detection algorithm uses the Slow Feature Analysis (SFA) technique and fully connected layers of a neural network to give a binary classification. So initially, we aimed to do the multiclass classification by combining classification and change detection in one module. But a dataset with the ground truth value and bitemporal was required, which was not available, so both classification and change detection have been implemented on different datasets.