Training samples are usually required to train a classifier for supervised classification of very high spatial resolution (VHR) remote sensing images. However, labeling samples is often a labor-intensive and time-consuming task. To solve this problem, this study integrates histogram distribution analysis, double-window flexible pace search (DFPS), and box-whisker plot (BP) techniques into an iterative algorithm to enrich training samples. The major steps of the proposed algorithm are given as follows. First, to acquire the feature distribution of a class, a histogram of each class (HOC) based on the raw classification map is generated. Second, to cover the spectral heterogeneity of an intraclass, some pixel points in each bin of HOC are selected as the coarse training sample set (CTS). Third, to further purify the CTS, DFPS, and BP techniques are adopted to exclude outlier samples and select the representative samples to signify the corresponding class. Finally, the refined training samples are used to retrain the classifier, and the preceding steps are constructed as an iterative algorithm. Experiments were performed on three real VHR remote sensing images to demonstrate the superiorities of the proposed approach in improving classification performance with respect to the maps obtained directly by the initial training set. In addition, compared with cognate state-of-the-art methods, the proposed approach achieved an approximately 2%-13% improvement in classification accuracy. Code available here:https://github.com/ImgSciGroup/IEEE-GRSL-GSEA-Code.
Bibliographical notePublisher Copyright:
- Computed tomography
- Hyperspectral imaging
- Image classification
- Iterative methods
- Task analysis
- training sample collection
- very high-resolution remote sensing image.