利用卷积神经网络提取高分辨率遥感图像喀斯特森林信息
DOI:
作者:
作者单位:

作者简介:

通讯作者:

中图分类号:

S771.8

基金项目:

国家自然科学基金项目(面上项目,重点项目,重大项目)


Karst Forest Extraction from High Resolution Remote Sensing Images Using Convolutional Neural Network
Author:
Affiliation:

Fund Project:

  • 摘要
  • |
  • 图/表
  • |
  • 访问统计
  • |
  • 参考文献
  • |
  • 相似文献
  • |
  • 引证文献
  • |
  • 资源附件
  • |
  • 文章评论
    摘要:

    针对喀斯特地区高分辨率遥感图像受山区复杂地形的影响存在阴影区域,“同物异谱”和“异物同谱”现象严重,传统的机器学习算法提取森林植被精度不高的问题,根据实践经验将多源多特征融合构成提取喀斯特森林信息特征,改进标准的卷积神经网络(CNN),将支持向量机与卷积神经网络相结合(CNN-SVM)应用于遥感分类,并与CNN、随机森林(RF)、支持向量机(SVM)等方法进行比较。结果表明,CNN-SVM、CNN两种深度学习方法的提取喀斯特森林信息精度均明显高于RF和SVM等浅层模型方法。CNN-SVM综合了CNN提取遥感高阶特征的能力和SVM的分类性能,分类精度在90%以上,高于标准的CNN。深度学习CNN可有效地区分农作物、提高喀斯特森林植被信息的提取精度。

    Abstract:

    There are shaded areas resulted from the hilly effects of complex terrain in karst regions. It is very difficult to extract forest accurately from remote sensing images using traditional machine learning algorithms because of serious phenomena of different spectra with same object and same subject with different spectra. Therefore, the karst forest extraction features were got from multi-feature fusion from multi-source remote sesning data. Then a hybrid CNN–SVM classifier designed by replacing the last output layer of CNN (convolutional neural network) with an SVM (support vector machine) classifier was proposed for land use classification with high resolution remote sensing images. The classified accuracy with CNN–SVM was compared to those with CNN, SVM and RF (random forest). Results show that deep learning classifiers, such as CNN-SVM and CNN, show their superiority over RF and SVM traditional non-deep classifiers in extracting karst forest. As CNN worked as a trainable high-level feature extractor and SVM performed as a recognizer in CNN-SVM, the classification accuracies of high resolution remote sensing images with CNN-SVM classifier are over 90%. CNN-SVM classifier has a little better performance than CNN implementations. Deep learning CNN classifier can be used to distinguish forest from crops with higher accuracy.

    参考文献
    相似文献
    引证文献
引用本文

王修信,杨路路,汤谷云,等. 利用卷积神经网络提取高分辨率遥感图像喀斯特森林信息[J]. 科学技术与工程, 2020, 20(17): 6773-6777.
Wang Xiuxin, Yang Lulu, Tang Guyun, et al. Karst Forest Extraction from High Resolution Remote Sensing Images Using Convolutional Neural Network[J]. Science Technology and Engineering,2020,20(17):6773-6777.

复制
分享
文章指标
  • 点击次数:
  • 下载次数:
  • HTML阅读次数:
  • 引用次数:
历史
  • 收稿日期:2019-09-19
  • 最后修改日期:2020-03-01
  • 录用日期:2019-12-19
  • 在线发布日期: 2020-07-07
  • 出版日期:
×
律回春渐,新元肇启|《科学技术与工程》编辑部恭祝新岁!
亟待确认版面费归属稿件,敬请作者关注