地球信息科学学报 ›› 2022, Vol. 24 ›› Issue (9): 1803-1816.doi: 10.12082/dqxxkx.2022.220188

• 遥感科学与应用技术 • 上一篇    下一篇

基于不确定性分析的遥感分类空间分层及评估方法

吴亚楠1,2(), 郭长恩3, 于东平3, 段爱民3, 刘玉1, 董士伟1,*(), 单东方1, 吴耐明4, 李西灿2   

  1. 1.北京市农林科学院信息技术研究中心,北京 100097
    2.山东农业大学信息科学与工程学院,泰安 271018
    3.山东省地质矿产勘查开发局八〇一水文地质工程地质大队,济南 250014
    4.北京北建大建筑设计研究院有限公司,北京 100044
  • 收稿日期:2022-04-13 出版日期:2022-09-25 发布日期:2022-11-25
  • 通讯作者: *董士伟(1984— ),男,山东泰安人,高级工程师,博士,主要从事时空数据分析研究。 E-mail: dshiwei2006@163.com
  • 作者简介:吴亚楠(1996— ),女,山东东营人,硕士研究生,主要从事土地利用变化与遥感应用研究。E-mail: 1224273284@qq.com
  • 基金资助:
    国家重点研发计划课题(2021YFD1500204);国家自然科学基金项目(41801276)

Spatial Stratification and Evaluation Method of Remote Sensing Classification based on Uncertainty Analysis

WU Yanan1,2(), GUO Chang'en3, YU Dongping3, DUAN Aimin3, Liu Yu1, DONG Shiwei1,*(), SHAN Dongfang1, WU Naiming4, LI Xican2   

  1. 1. Research Center of Information Technology, Beijing Academy of Agriculture and Forestry Sciences, Beijing 100097, China
    2. College of Information Science and Engineering, Shandong Agricultural University, Tai 'an 271018, China
    3. 801 Institute of Hydrogeology and Engineering Geology, Shandong Provincial Bureau of Geology & Mineral Resources, Jinan 250014, China
    4. Architectural Design and Research Institute of BUCEA Co. Ltd, Beijing 100044, China
  • Received:2022-04-13 Online:2022-09-25 Published:2022-11-25
  • Contact: DONG Shiwei
  • Supported by:
    National Key Research and Development Program of China(2021YFD1500204);National Natural Science Foundation of China(41801276)

摘要:

空间分层是准确度量遥感分类不确定性程度及其空间分布的基础与关键。本文提出了一种基于不确定性分析的遥感分类空间分层及评估方法,首先基于随机森林算法获取像元后验概率,确定分类不确定性度量指标;其次,采用模糊C均值进行空间分层;最后,对分层结果合理性进行定性与定量评估,并与同尺度数据产品精度评价结果及后验概率不确定性分层方法进行对比分析。以北京市顺义区Landsat 8 OLI遥感影像数据为例,研究结果表明:① 基于最大概率、模糊混淆指数和概率熵指标将顺义区分为不确定性大、中、小3层,相应的遥感数据层分类精度分别为62.28%、74.96%、79.31%;② 分类不确定性空间分层结果与度量指标大小的空间分布基本一致,错分地类图层与不确定性大层的地类空间分布基本一致;③ 遥感数据和数据产品的各层地类空间特征、层分类精度大小趋势一致,与总体分类精度相比,不确定性大层的层分类精度降低,不确定性小层的层分类精度提高;④ 与后验概率不确定性分层方法相比,本研究不确定性大层的层分类精度降低1.08%,不确定性中层提高3.58%,不确定性小层提高0.16%,q值由0.19提高到0.24,空间分异性更高。证实了研发的遥感分类不确定性空间分层结果的合理性。研究旨在提出适用于遥感分类的不确定性分层方案,用于优化遥感分类训练样本和精度评价验证样本的空间布设。

关键词: 不确定性, 空间分层, 度量指标, 遥感分类, 随机森林, 土地利用, 模糊C均值, 精度评价

Abstract:

Spatial stratification is the basis and key to accurately measure the uncertainty degree and spatial distribution of remote sensing classification. In this study, a spatial stratification and evaluation method of remote sensing classification was proposed based on uncertainty analysis. Firstly, the pixel posterior probability was obtained based on random forest algorithm, and measurement indices of classification uncertainty were determined. Secondly, spatial stratification was achieved using Fuzzy C-means. Finally, the rationality of the stratification results was qualitatively and quantitatively evaluated and compared with the stratification accuracy assessment results of data products at the same scale and the posterior probability uncertainty stratification method. Taking Landsat 8 OLI images of remote sensing data in Shunyi District of Beijing as an example, the results showed that: (1) The coverage of Shunyi District was divided into three strata including large, medium, and small uncertainties based on the indices of maximum probability, fuzzy confusion index, and probability entropy. The stratum classification accuracy of each stratum of remote sensing data was 62.28%, 74.96%, and 79.31%, respectively; (2) The spatial stratification results of classification uncertainty were basically consistent with the spatial distribution of the size of measurement indices, and the spatial distribution of misclassified stratum was basically consistent with that of large uncertainty stratum; (3) The spatial characteristics and classification accuracy of each stratum for remote sensing data and data products had the same trend. Compared with the overall accuracy of classification, the stratum classification accuracy of the large uncertainty stratum was reduced, and the stratum classification accuracy of the small uncertainty stratum was improved; (4) Compared with the posterior probability uncertainty stratification method, the stratum classification accuracy of the large uncertainty stratum decreased by 1.08%, and those of the middle uncertainty stratum and the small uncertainty stratum increased by 3.58% and 0.16%, respectively, and corresponding q value of the spatial method developed in this study increased from 0.19 to 0.24 with a higher spatial differentiation. This confirmed that the spatial stratification result of remote sensing classification developed in this study was reasonable. This study proposes an uncertainty stratification scheme for remote sensing classification to optimize the spatial layout of training samples for remote sensing classification and validation samples for accuracy evaluation.

Key words: uncertainty, spatial stratification, measurement indices, remote sensing classification, random forest, land use, fuzzy C-means, accuracy evaluation