Land cover classification of multispectral remote sensing images based on time-spectrum association features and multikernel boosting incremental learning
Land cover classification of multispectral remote sensing images based on time-spectrum association features and multikernel boosting incremental learning
复制标题
基于时谱关联特征和多核增量学习的多光谱遥感影像土地覆盖分类
DOI：
10.1117/1.jrs.13.044510
复制
发表时间：
2019-10
期刊：
影响因子：
--
通讯作者：
Yanping Wang
中科院分区：
文献类型：
--
作者：
Fukun Bi;Jinyuan Hou;Yuting Wang;Jing Chen;Yanping Wang
抽象的。近年来，基于多光谱遥感图像的土地覆盖分类技术已应用于环境监测的许多领域。现有的方法一般依赖于光谱波段的信息。然而，单时相多光谱图像的光谱信息不能概括地描述地物在不同时刻的光谱特征。此外，时间序列样本会随时间发生微小变化，很难连续保持分类性能。针对这些问题，提出了一种基于时间-谱关联特征和多核推进增量学习的多光谱图像土地覆盖分类方法。我们的方法分两个主要阶段进行。(1)我们提出了时间谱关联特征来获取不同地物的季节性光谱特征。(2)为了设计分类器，我们提出了多核Boosting方法，并介绍了一种多核Boosting分类学习，它使用连续的新样本通过低计算量和小规模的增量学习来更新分类器的权重。我们测试所提出的方法对一个公共的多光谱数据集Landsat-5。实验结果表明，提取的时谱关联特征能更好地表征不同地物的差异性，随着时间的推移，样本逐渐增加，分类器能达到更准确的分类效果。
Abstract. In recent years, land cover classification technology based on multispectral remote sensing images has been applied to many fields of environmental monitoring. The existing methods generally rely on the information of spectral bands. However, the spectral information of monotemporal multispectral images cannot be generalized to describe the spectral characteristics of the ground objects at different times. In addition, the time-series samples will slightly change over time, and it is difficult to maintain classification performance continuously. To address these problems, we propose a method of land cover classification for multispectral images based on the time-spectrum association feature and multikernel boosting incremental learning. Our method is conducted in two main stages. (1) We propose the time-spectrum association features to acquire the seasonal spectral characteristics different ground objects. (2) To design the classifiers, we propose multikernel boosting method and introduce a multikernel boosting classification learning, which uses continuous new samples to update the weights of the classifier by low-computational and small-scale incremental learning. We test the proposed method on a public multispectral dataset from Landsat-5. The experimental results show that the extracted time-spectrum association features can better characterize the differences of different ground objects, and the proposed classifier can reach more accurate classification with gradually increasing samples over time.
登录
查看更多内容
影响因子：
5
作者：
Bargiel, Damian;Herrmann, Sylvia
通讯作者：
Herrmann, Sylvia
影响因子：
13.5
作者：
H. Ren;Guangsheng Zhou;Feng Zhang
通讯作者：
H. Ren;Guangsheng Zhou;Feng Zhang
影响因子：
13.5
作者：
Chan, Jonathan Cheung-Wai;Paelinckx, Desire
通讯作者：
Paelinckx, Desire
影响因子：
--
作者：
Huang, Jinliang;Klemas, Victor
通讯作者：
Klemas, Victor
影响因子：
8.2
作者：
Konstantinos Karalas;G. Tsagkatakis;M. Zervakis;P. Tsakalides
通讯作者：
Konstantinos Karalas;G. Tsagkatakis;M. Zervakis;P. Tsakalides