首页|期刊简介|投稿指南|分类索引|刊文选读|订阅指南|资料|样刊邮寄查询|常见问题解答|联系我们
王佃来,宿爱霞,刘文萍. 基于BP改进的KNN算法在北京密云土地覆盖分类中的应用[J]. 科学技术与工程, 2020, 20(23): 9464-9471.
WANG Dian-lai,SU Ai-xia,LIU Wen-ping.Application of Land Cover Classification In Miyun District of Beijing City Using Landsat-5 TM Remote Sensing Images Based on BP neural network Improved KNN Algorithm[J].Science Technology and Engineering,2020,20(23):9464-9471.
基于BP改进的KNN算法在北京密云土地覆盖分类中的应用
Application of Land Cover Classification In Miyun District of Beijing City Using Landsat-5 TM Remote Sensing Images Based on BP neural network Improved KNN Algorithm
投稿时间:2019-08-07  修订日期:2020-05-07
DOI:
中文关键词:  KNN 土地覆盖分类  遥感图像 BP神经网络
英文关键词:knn  land cover  classification remote  sensing images  bp neural  network
基金项目:北京市科技计划“影响北京生态安全的重大钻蛀性害虫防控技术研究与示范”(项目编号:Z171100001417005);中央高校基本科研业务费专项(2015ZCQ-XX)
        
作者单位
王佃来 首钢工学院 信息工程系
宿爱霞 中国软件评测中心
刘文萍 北京林业大学 信息学院
摘要点击次数: 138
全文下载次数: 49
中文摘要:
      针对K-Nearest Neighbor (KNN)算法在土地覆盖分类中存在将山体阴影覆盖下植被误分成水体的问题,提出了改进的KNN算法。该算法充分利用神经网络能有效区分山体阴影覆盖下植被和水体的特性,实现BP神经网络与KNN算法的融合,整体提高了北京市密云区土地覆盖分类精度。实验结果表明:相对于SVM、随机森林、BP神经网络和KNN算法,本文提出的算法分类精度最高,达到了95.20%,分类精度比未改进KNN算法提高了6.43%。本文提出算法的kappa系数在对比算法中也是最高的,达到0.93。此外,实验结果也表明本文算法可应用于中分辨率遥感图像分类中。
英文摘要:
      Aiming at the problem that KNN algorithm misclassifies vegetation under shadow of mountain into water area in land cover classification, an improved KNN algorithm which combines the BP neural network algorithm with KNN algorithm taking advantage of the neural network’s characteristics of the high accuracy of distinguish vegetation under shadow of mountain from water area is proposed. The experimental results show that classification accuracy of the improved KNN algorithm is the highest compared with SVM, random forest, BP neural network and KNN algorithm, and accuracy of classification reaches 95.20%. The classification accuracy of the improved KNN algorithm is higher 6.43% than the unimproved KNN algorithm. The kappa coefficient of the improved KNN algorithm is also highest among the contrasting algorithms, and reaches 0.93. In addition, the improved KNN algorithm can apply to the classification of moderate resolution remote sensing images.
查看全文  查看/发表评论  下载PDF阅读器
关闭
你是第32690650位访问者
版权所有:科学技术与工程编辑部
主管:中国科学技术协会    主办:中国技术经济学会
Tel:(010)62118920 E-mail:stae@vip.163.com
京ICP备05035734号-4
技术支持:本系统由北京勤云科技发展有限公司设计

京公网安备 11010802029091号