Multiple classifier system for remote sensing image classification: a review.

Multiple classifier system for remote sensing image classification: a review.
复制标题

遥感图像分类的多分类器系统:综述

DOI:
10.3390/s120404764
复制
发表时间:
2012
期刊:
Sensors (Basel, Switzerland)
影响因子:
--
通讯作者:
Liu S
Liu S
中科院分区:
其他
文献类型:
--
作者:
Du P;Xia J;Zhang W;Tan K;Liu Y;Liu S

文献摘要

参考文献

被引文献

相似文献

近二十年来,多分类器系统(MCS)或分类器集成在提高遥感图像分类精度和可靠性方面显示出巨大的潜力。虽然有很多文献涵盖了MCS方法,但缺乏对遥感分类器集成设计的基本原理和趋势进行全面的文献综述。因此,为了给MCS方法提供一个参考点,本文试图明确地回顾MCS的遥感实现,并提出一些改进的方法。通过多源遥感影像,包括高空间分辨率影像(QuickBird)、高光谱影像(OMISII)和多光谱影像(Landsat ETM+),对现有算法和改进算法的有效性进行了分析和评价。实验结果表明,MCS可以有效提高遥感图像分类的精度和稳定性,多样性测度对于多分类器组合具有积极作用。此外,本研究为未来的研究、算法改进和促进遥感界MCS知识积累提供了路线图。
Over the last two decades, multiple classifier system (MCS) or classifier ensemble has shown great potential to improve the accuracy and reliability of remote sensing image classification. Although there are lots of literatures covering the MCS approaches, there is a lack of a comprehensive literature review which presents an overall architecture of the basic principles and trends behind the design of remote sensing classifier ensemble. Therefore, in order to give a reference point for MCS approaches, this paper attempts to explicitly review the remote sensing implementations of MCS and proposes some modified approaches. The effectiveness of existing and improved algorithms are analyzed and evaluated by multi-source remotely sensed images, including high spatial resolution image (QuickBird), hyperspectral image (OMISII) and multi-spectral image (Landsat ETM+). Experimental results demonstrate that MCS can effectively improve the accuracy and stability of remote sensing image classification, and diversity measures play an active role for the combination of multiple classifiers. Furthermore, this survey provides a roadmap to guide future research, algorithm enhancement and facilitate knowledge accumulation of MCS in remote sensing community.
DOI: 10.1016/j.patcog.2004.01.008
发表时间: 2004-07-01
影响因子: 8
作者:
Czyz, J;Kittler, J;Vandendorpe, L
通讯作者: Vandendorpe, L
DOI: 10.1016/s0262-8856(01)00045-2
发表时间: 2001-08-01
影响因子: 4.7
作者:
Giacinto, G;Roli, F
通讯作者: Roli, F
DOI: 10.1016/j.rse.2004.06.017
发表时间: 2004-10-30
影响因子: 13.5
作者:
Foody, GM;Mathur, A
通讯作者: Mathur, A
DOI: 10.1023/a:1007515423169
发表时间: 1999-07-01
期刊: MACHINE LEARNING
影响因子: 7.5
作者:
Bauer, E;Kohavi, R
通讯作者: Kohavi, R
DOI: 10.1109/tgrs.2006.876708
发表时间: 2006-10-01
影响因子: 8.2
作者:
Fauvel, Mathieu;Chanussot, Jocelyn;Benediktsson, Jon Atli
通讯作者: Benediktsson, Jon Atli