当前位置: X-MOL 学术J. Sens. › 论文详情
Our official English website, www.x-mol.net, welcomes your feedback! (Note: you will need to create a separate account there.)
Composite Clustering Sampling Strategy for Multiscale Spectral-Spatial Classification of Hyperspectral Images
Journal of Sensors ( IF 1.9 ) Pub Date : 2020-06-15 , DOI: 10.1155/2020/9637839
Chenming Li 1 , Xiaoyu Qu 1 , Yao Yang 1 , Dan Yao 1 , Hongmin Gao 1 , Zaijun Hua 1
Affiliation  

In recent years, many high-performance spectral-spatial classification methods were proposed in the field of hyperspectral image classification. At present, a great quantity of studies has focused on developing methods to improve classification accuracy. However, some research has shown that the widely adopted pixel-based random sampling strategy is not suitable for spectral-spatial hyperspectral image classification algorithms. Therefore, a composite clustering sampling strategy is proposed, which can greatly reduce the overlap between the training set and the test set, while making sample points in the training set sufficiently representative in the spectral domain. At the same time, in order to solve problems of a three-dimensional Convolutional Neural Network which is commonly used in spectral-spatial hyperspectral image classification methods, such as long training time and large computing resource requirements, a multiscale spectral-spatial hyperspectral image classification model based on a two-dimensional Convolutional Neural Network is proposed, which effectively reduces the training time and computing resource requirements.

中文翻译:

高光谱图像多尺度光谱空间分类的复合聚类采样策略

近年来,在高光谱图像分类领域中提出了许多高性能的光谱空间分类方法。目前,大量研究集中在开发提高分类准确性的方法上。然而,一些研究表明,广泛采用的基于像素的随机采样策略不适用于光谱空间高光谱图像分类算法。因此,提出了一种复合聚类采样策略,该策略可以大大减少训练集和测试集之间的重叠,同时使训练集中的采样点在频谱域中具有足够的代表性。同时,为了解决在光谱空间高光谱图像分类方法中常用的三维卷积神经网络的问题,
更新日期:2020-06-15
down
wechat
bug