A spatiotemporal cube model for analyzing satellite image time series: Application to land-cover mapping and change detection

Abstract

Satellite image time series (SITS) data have been widely used in resource investigations and environmental monitoring. However, three characteristics of geographic objects (i.e., spatiotemporal heterogeneity, spatiotemporal correlation and scale characteristics) pose great challenges to SITS analysis; while, existing studies ignore these characteristics, leading to unsatisfactory SITS analysis results including land-cover classification and change detection. Aiming at integratively measuring and expressing these three characteristics, this study proposes a spatiotemporal cube model and a spatiotemporal multi-resolution segmentation (ST-MRS) method for analyzing SITS. First, the novel spatiotemporal model, ST-cube, is introduced to reduce the spectral heterogeneity in spatial and temporal domains. Both spatial and temporal heterogeneities are considered and defined while constructing the spatiotemporal segmentation model. Second, the ST-MRS method is proposed by extending the existing mono-temporal MRS method into spatiotemporal domain to segment SITS into relatively homogeneous ST-cubes. Third, a novel unsupervised method is developed to evaluate the segmentation results of the ST-MRS method. In experiments, we apply this method to Shunyi District in Beijing, China, generate ST-cubes at different spatiotemporal scales, and compare our method with existing ones for SITS classification. Furthermore, the intra-annual seasonal changes of land covers are detected based on ST-cubes classification results. The results indicate the effectiveness and superiority of the ST-cubes in representing geographic objects and analyzing spatiotemporal characteristics over existing pixel- and object-based methods, contributing to a wider range of applications and analysis of SITS.