Analysis of Hyperspectral Data by Means of Transport Models and Machine Learning
Analysis of Hyperspectral Data by Means of Transport Models and Machine Learning
复制标题
DOI：
10.1109/igarss39084.2020.9323215
复制
发表时间：
2020-09
期刊：
影响因子：
--
通讯作者：
W. Czaja;Dong Dong-Dong;P. Jabin;Franck Olivier Ndjakou Njeunje
中科院分区：
文献类型：
--
作者：
W. Czaja;Dong Dong-Dong;P. Jabin;Franck Olivier Ndjakou Njeunje
我们提出了一种新的物理启发方法来分析高光谱图像（HSI）。该方法基于图的传输模型的概念。该方法推广了现有的降维和特征提取算法，用动态系统取代了扩散过程作为估计接近度的度量。这种方法允许我们在复杂的数据结构中利用不同的和新的关系，例如在恒指中产生的关系。我们通过提出一种特定的多尺度算法来证明这一点，该算法使用传输模型来翻译有关材料类别上下文相似性的信息，以增强特征提取和分类结果。用一系列的计算实验说明了这一点。
We present a new physics-inspired method for analysis of hyperspectral imagery (HSI). The method is based on the concept of transport models for graphs. The proposed approach generalizes existing dimension reduction and feature extraction algorithms, by replacing the role of diffusion processes, as a measure of estimating proximity, with dynamical systems. This approach allows us to exploit different and new relationships within the complex data structures, such as those arising in HSI. We demonstrate this by proposing a specific multi-scale algorithm in which transport models are used to translate the information about contextual similarities of material classes to enhance feature extraction and classification results. This point is illustrated with a series of computational experiments.