• 主题
高级搜索  >
历史搜索 清空历史
首页> 外文会议>Asian conference on remote sensingACRS >OBJECT-BASED IMAGE ANALYSIS FOR MANGROVES EXTRACTION USING LIDAR DATASETS AND ORTHOPHOTO
【24h】

OBJECT-BASED IMAGE ANALYSIS FOR MANGROVES EXTRACTION USING LIDAR DATASETS AND ORTHOPHOTO

机译：使用LIDAR Datasets和Orthophoto的红树林提取的对象的图像分析

获取原文
页面导航
  • 摘要
  • 著录项
  • 相似文献
  • 相关主题

摘要

Light Detection and Ranging (LiDAR) is a new type of remote sensing technique which uses light pulses to measure distances and to generate three-dimensional point clouds of the Earth's surface. In this study, LiDAR together with Orthophotos will be used to analyze the geophysical features of the terrain and create a Mangrove map. The dataset that we have were first pre-processed using the LAStools software, a software that is used to process LiDAR data sets and create different layers and derivatives. All the aforementioned layers together with the orthophoto were used to derive the Mangrove class. Object-based Image Analysis (OBIA) was performed using eCognition. It analyzes a group of pixels with similar properties called objects, as compared to the traditional pixel-based. Multi-threshold and multiresolution segmentation were used to delineate the different classes and split the image into objects. There are two levels of classification, first is the separation of Land from Water. This was done through the use of the Multi-threshold segmentation. Then the Land class was segmented using all the derived layers through the Multiresolution segmentation algorithm. Parameters such as shape, compactness, and scale was used to define different objects from the land class. These objects were then assigned into different classes such as built-ups, bare land, high vegetation, low vegetation, and the Mangrove classes using hierarchical and semi-automated classification. These classification methods includes Nearest Neighbor, Feature Space Optimization (FSO) and Support Machine Vector (SVM). Different feature properties aid in the classification such as Mean layer values, standard deviation values, and geometric values of all the derived layers. This workflow was applied in the classification of Mangroves to a LiDAR dataset in Carcar City, Cebu in the Philippines. Accuracies from 87-95% were achieved using the different methods of classification. The process presented in shows that LiDAR data and its derivatives can be used in generating Mangrove maps.
机译：光检测和测距（LIDAR）是一种新型的，它使用光脉冲来测量距离，并产生对地球表面的三维点云遥感技术。在这项研究中，激光雷达与正射影像一起将被用于分析地形的地球物理特征，并创建一个红树林地图。数据集，我们已首次用LAStools软件，用于处理LiDAR数据集并创建不同的层和衍生物软件预处理。所有与该正射影像一起前述层用于推导红树类。基于对象的图像分析（OBIA）使用eCognition进行。它分析一组具有相似特性的称为对象像素的，相比于传统的基于像素的。多阈值和多分辨率分割被用来描绘不同类和图像分割为对象。有两种分类层次，第一是土地的从水中分离。这是通过使用多阈值分割的实现。然后土地类是通过多分辨率分割算法使用所有派生层分段。参数，例如形状，紧凑性和尺度被用来定义从土地类不同的对象。然后，这些对象被分配到不同的类别，如内置式视窗，裸地，植被高，低植被，以及使用分层和半自动化分类红树类。这些分类方法包括近邻，功能空间优化（FSO）和支持向量机（SVM）。不同的特征性助剂在分类如平均数层值，标准偏差值，并且所有派生层的几何值。此工作流程在红树林在Carcar市，宿务菲律宾激光雷达数据集的分类应用。采用分级的不同方法实现了由87-95％的精度。在显示，激光雷达数据和它的衍生物可以在产生红树地图中使用所提出的方法。

著录项

相似文献

  • 外文文献
  • 中文文献
  • 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