文献类型： 会议论文

第一作者： William Michael Laprade

作者： William Michael Laprade ¹ ; Jesper Cairo Westergaard ² ; Jon Nielsen ² ; Mads Nielsen ³ ; Anders Bjorholm Dahl ¹ ;

作者机构： 1.Department of Mathematics and Computer Science, Technical University of Denmark, 2800 Kongens Lygnby, Denmark

2.Department of Plant and Environmental Sciences, University of Copenhagen, 2630 Taastrup, Denmark

3.Department of Computer Science, University of Copenhagen, 2100 Kobenhavn O, Denmark

会议名称： Scandinavian Conference on Image Analysis

主办单位：

页码： 191-202

摘要： Hyperspectral imaging is central for remote sensing, and much research has been done on analysis methods for land surveillance using space- and air-borne imaging systems. Proximal hyperspectral imaging is also widely used in plant and agriculture science. It allows the remote capturing of leaf reflectance information in order to determine and classify plant health and disease. With the high information density in hyperspectral images, it becomes increasingly important to apply sophisticated feature extraction in order to reduce image dimensionality while retaining useful information. Autoencoders are one of the primary methods for deep learning-based feature extraction in hyperspectral images. We investigate different setups of autoencoders to encode the spatial and spectral dimensions in different orders and ways. To our surprise, the best turns out to be a 3D CNN, where the spectral dimension is treated in the same way as the spatial dimensions.

分类号： tp391