14 December 2024 in Ocean Engineering
16 April 2025 in IEEE Transactions on Geoscience and Remote Sensing
The problem of insufficient labeled samples has restricted the application of deep learning method in hyperspectral image classification tasks. Fusion of remote sensing images from different sources such as hyperspectral image, Lidar is a common strategy to improve the classification accuracy. However, obtaining multi-source registered remote sensing images of the same area is time-consuming, which limits the application of multi-source strategy in practice. Motivated by the recent success of large models in different fields, we propose to extract depth information from large models and fuse it with hyperspectral images to improve the small sample classification accuracy. Specifically, we use the pre-trained foundation large model to estimate the depth information of hyperspectral images as the depth features, and then input the original spectral features and depth features into the support vector machine to complete the classification. In order to further improve the classification accuracy, we propose to use the sliding window method to extract the depth features of different bands, so as to obtain more rich depth features. A large number of classification experiments on six benchmark datasets verify the effectiveness of the proposed method.
11 November 2024 in IEEE Transactions on Big Data
Voronoi diagram is commonly used to visualize geographical point dataset with a collection of plane-partitioned facets. As the size of the geographical point dataset increases, facets are densely distributed, and present different sizes and irregular shapes, leading to overdrawing and confusion problems, and hampering the visual perception of Voronoi diagram and insightful exploration of geographical point data. In this paper, we propose a novel Voronoi diagram generation framework to visualize and explore large-scale geographical point datasets. Firstly, an attribute-based blue noise sampling model is designed to select a subset of points to generate the simplified Voronoi diagram, retaining both the spatial distribution and attribute relationship of the original large-scale geographical points. Then a couple of optimization schemes are integrated into the sampling model to replace the representative points, aiming to enhance the visual perception of Voronoi diagram, such as shape balance and color characterization. Furthermore, we implement an interactive online Voronoi diagram generation tool, GeoVoronoi, enabling users to generate meaningful facets according to their requirements. Quantitative comparisons, case studies and user studies based on real-world datasets have demonstrated the effectiveness of our proposed method in the generation of credible Voronoi diagram and in-depth exploration of geographical point datasets.