Improving active queries with a local segmentation step and application to land cover classification

Active queries is an active learning method used for classification of remote sensing images. It consists of three steps: hierarchical clustering, dendrogram division, and active label selection. The goal of active learning is to reduce the needed amount of labeled data while preserving classification accuracy. We propose to apply local segmentation as a new step preceding the hierarchical clustering. We are using the SLIC (simple linear iterative clustering) algorithm for dedicated image segmentation. This incorporates spatial knowledge which leads to an increased learning rate and reduces classification error. The proposed method is applied to six different areas of the Vaihingen dataset.