首页> 外文会议>International Conference on Remote Sensing for Marine and Coastal Environments >Mapping and Improving Frequency, Accuracy, and Interpretation of Land Cover Change: ClassifyingCoastal Louisiana With 1990, 1993, 1996, and 1999 Landsat Thematic Mapper Image Data
【24h】

Mapping and Improving Frequency, Accuracy, and Interpretation of Land Cover Change: ClassifyingCoastal Louisiana With 1990, 1993, 1996, and 1999 Landsat Thematic Mapper Image Data

机译:绘制和改善土地覆被变化的频率,准确性和解释:用1990、1993、1996和1999年Landsat专题制图仪图像数据对路易斯安那州沿海地区进行分类

获取原文

摘要

Abstract-Landsat Thematic Mapper images and collateral data sources were used to classify the land coverof the Mermentau River Basin within the chenier coastal plain and the adjacent uplands of Louisiana, USA.Landcover classes followed that of the National Oceanic and Atmospheric Administration's Coastal ChangeAnalysis Program; however, classification methods needed to be developed to meet these national standards.Our first classification was limited to the Mermentau River Basin (MRB) in southcentral Louisiana, and theyears of 1990, 1993, and 1996. To overcome problems due to class spectral inseparable, spatial and spectracontinuums, mixed landcovers, and abnormal transitions, we separated the coastal area into regions ofcommonality and applying masks to specific land mixtures. Over the three years and 14 landcover classes(aggregating the cultivated land and grassland, and water and floating vegetation classes), overall accuraciesranged from 82% to 90%. To enhance landcover change interpretation, three indicators were introduced asLocation Stability, Residence stability, andTurnover. Implementing methodssubstantiated in the multiple date MRBclassification, we spatially extended theclassification to the entire Louisiana coast andtemporally extended the original 1990, 1993,1996 classifications to 1999 (Figure 1). We alsoadvanced the operational functionality of theclassification and increased the credibility ofchange detection results. Increasedoperational functionality that resulted indiminished user input was for the most partgained by implementing a classification logicbased on forbidden transitions. The logicdetected and corrected misclassifications andmostly alleviated the necessity of subregionseparation prior to the classification. The newmethods provided an improved ability formore timely detection and response tolandcover impact.
机译:摘要利用Landsat专题制图仪图像和附带的数据源对美国路易斯安那州高尼尔沿海平原和邻近山地内梅门道河流域的土地覆盖进行分类。土地覆盖类别遵循美国国家海洋与大气管理局的海岸变化分析计划;但是,必须开发出满足这些国家标准的分类方法。我们的第一个分类仅限于路易斯安那州中南部的梅门多河流域(MRB),以及1990、1993和1996年。为解决由于光谱不可分割而引起的问题,空间连续谱和光谱连续谱,混合的土地覆盖物以及异常的过渡,我们将沿海地区划分为共同区域,并对特定的土地混合物应用了遮罩。在过去的三年中,共有14个土地覆被类别(总计耕地和草地,水和浮动植被类别),总体准确度从82%到90%不等。为了增强对土地覆被变化的解释,引入了三个指标:位置稳定性,居住稳定性和周转率。在多日期MRB分类中证实了实施方法,我们在空间上将分类扩展到整个路易斯安那州海岸,并暂时将原始的1990、1993、1996分类扩展到1999年(图1)。我们还改进了分类的操作功能,并提高了变更检测结果的可信度。通过实现基于禁止转换的分类逻辑,可以最大程度地提高导致用户输入减少的操作功能。该逻辑检测并纠正了错误分类,并最大程度地减轻了在分类之前进行子区域分隔的必要性。新方法提供了改进的功能,可以更及时地发现和响应土地覆被影响。

著录项

相似文献

  • 外文文献
  • 专利
获取原文

客服邮箱:kefu@zhangqiaokeyan.com

京公网安备:11010802029741号 ICP备案号:京ICP备15016152号-6 六维联合信息科技 (北京) 有限公司©版权所有
  • 客服微信

  • 服务号