Cascade Active Learning for Evolution Pattern Extraction from SAR Image Time Series

In this paper, a cascade active learning approach relying on a coarse-to-fine strategy for evolution pattern indexing is developed, which allows fast indexing and hidden spatial and temporal pattern discovery in multi-temporal SAR images. In this approach, a hierarchical multi-level image representation is adopted and each level is associated with a specific patch size. SVM active learning is applied at each level to obtain reliable samples and reduce the manual effort in labeling the images. When moving to a new level, all the negative patches are neglected and the learning at the new level focuses only on the positive patches. In this way, the computation burden in annotating large data set could be remarkably reduced while keeping the accuracy. Through temporal pattern retrieval, the cascade active learning has been compared with a baseline SVM active learning operating only at the last level in terms of both accuracy and time complexity. We have demonstrated that cascade active learning can not only achieves better accuracy but also reduce remarkably the computation time