Differentiable Programming for Hyperspectral Unmixing using a Physics-based Dispersion Model
Differentiable Programming for Hyperspectral Unmixing using a Physics-based Dispersion Model
复制标题
DOI：
10.1007/978-3-030-58583-9_39
复制
发表时间：
2020-07
期刊：
影响因子：
--
通讯作者：
J. Janiczek;Parth Thaker;Gautam Dasarathy;C. Edwards;P. Christensen;Suren Jayasuriya
中科院分区：
文献类型：
--
作者：
J. Janiczek;Parth Thaker;Gautam Dasarathy;C. Edwards;P. Christensen;Suren Jayasuriya
高光谱分解是一项重要的遥感任务，其应用包括材料识别和分析。特征光谱特征使许多纯材料可以从可见光到红外光谱中识别出来，但由于非线性和变化因素，量化它们在混合物中的存在是一项具有挑战性的任务。在本文中，从基于物理的方法考虑光谱变化，并通过可微分编程将其纳入端到端光谱分解算法。引入色散模型来模拟真实的光谱变化，并提出了一种有效的参数拟合方法。然后，该色散模型被用作综合分析光谱解混算法中的生成模型。此外，引入了使用卷积神经网络来预测生成模型参数的逆渲染技术，以在训练数据可用时提高性能和速度。结果在红外和可见光到近红外 (VNIR) 数据集上均达到了最先进的水平，并显示出未来基于物理的模型与深度学习在高光谱分解中的协同作用的前景。
Hyperspectral unmixing is an important remote sensing task with applications including material identification and analysis. Characteristic spectral features make many pure materials identifiable from their visible-to-infrared spectra, but quantifying their presence within a mixture is a challenging task due to nonlinearities and factors of variation. In this paper, spectral variation is considered from a physics-based approach and incorporated into an end-to-end spectral unmixing algorithm via differentiable programming. The dispersion model is introduced to simulate realistic spectral variation, and an efficient method to fit the parameters is presented. Then, this dispersion model is utilized as a generative model within an analysis-by-synthesis spectral unmixing algorithm. Further, a technique for inverse rendering using a convolutional neural network to predict parameters of the generative model is introduced to enhance performance and speed when training data is available. Results achieve state-of-the-art on both infrared and visible-to-near-infrared (VNIR) datasets, and show promise for the synergy between physics-based models and deep learning in hyperspectral unmixing in the future.