An Adaptive Pseudo-Labeled Sample Generation Approach to Unsupervised Multiclass Change Detection in Bitemporal Remote Sensing Images

Multiclass change detection (CD) in multitemporal multispectral/hyperspectral remote sensing images is a significant yet challenging task, particularly when prior knowledge and ground reference data are not available. This article proposes a novel adaptive pseudo-labeled sample generation (APSG) approach to address this challenge, which bridges the gap between data-driven unsupervised CD and supervised CD methodologies. In particular, the spectral difference image is first projected into a 2-D polar domain using an adaptive spectral change vector representation (ASCVR). Subsequently, a novel method for generating multiple pseudo-labeled candidate sample selection regions is developed to automatically analyze the statistical distribution and characteristics of change and no-change classes in bitemporal images, thereby producing high-confidence pseudo-labeled samples. Finally, a sequential pseudo-labeled sample selection and generation strategy incorporated into the CD process is designed to enable robust multiclass CD. Multiclass CD results are further enhanced by incorporating spatial–spectral information. The effectiveness of the proposed method has been validated on three publicly available bitemporal remote sensing datasets, outperforming the traditional CD approaches and the deep learning (DL)-based unsupervised multiclass CD methods in terms of the improvement of overall accuracy (OA) (1%–5%). The generated pseudo-labeled samples represent intrinsic change clusters and their feature distributions within the dataset, thus resulting in a data-driven approach. These pseudo-labeled samples serve as critical inputs for both machine learning (ML)- and DL-based CD methods utilizing multispectral/hyperspectral data at medium-to-low spatial resolution. This approach enables reliable multiclass CD across diverse land-cover scenarios without requiring prior information.