Multiannual Change Detection Using a Weakly Supervised 3-D CNN in HR SITS

In recent years, deep learning methods, in particular convolutional neural networks (CNNs), have been increasingly used in change detection (CD). However, most CNN-based CD methods are primarily designed for analyzing only a single pair of images due to the challenge of collecting and constructing ground reference data during the system-training phase. Consequently, the existing CD methods, particularly those focused on detecting multiannual changes, exhibit limited capability in extracting comprehensive spatiotemporal information. To address this limitation, we propose a novel weakly supervised deep-learning-based technique for CD exploiting a 3-D CNN architecture to extract spatiotemporal information. Our technique incorporates a fine-tuning stage to effectively capture temporal patterns from a yearly Satellite Image Time Series (SITS) by using different 3-D convolutional layers. It also exploits a multifeature hypertemporal change vector analysis (CVA) for multiannual change identification. The proposed approach is tested on a four-year dataset in Amazonia and gained the highest yearly CD accuracy of 88.59%, 97.27%, and 87.87% for 2017, 2018, and 2019, respectively.