• 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 >APPLICATION OF OBJECT-BASED IMAGE ANALYSIS AND SUPPORT VECTOR MACHINE IN MAPPING MANGROVE FOREST USING LIDAR AND ORTHOPHOTO: A CASE STUDY IN CALATAGAN, BATANGAS
【24h】

APPLICATION OF OBJECT-BASED IMAGE ANALYSIS AND SUPPORT VECTOR MACHINE IN MAPPING MANGROVE FOREST USING LIDAR AND ORTHOPHOTO: A CASE STUDY IN CALATAGAN, BATANGAS

机译：基于对象的图像分析和支持向量机在使用LIDAR和Orthophoto测绘红树林中的应用 - 以Calatagan，Batangas在案例研究

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

摘要

Efforts have been made in conserving the mangrove forests of Calatagan, Batangas. In fact, the local government of Calatagan inked Sangguniang Bayan Resolution No. 76 on 8 September 2009 creating the Calatagan Mangrove Forest Conservation Park centering in Brgy. Quilitisan. As an aid in the conservation and environmental assessment of the said mangrove forest, this study presents a method in producing fine-scale map of these protected areas. The study site covers four coastal barangays (Balibago, Talisay, Carretunan and Quilitisan). Serving as inputs in image classification, airborne LiDAR (Light Detection and Ranging) data and orthophotograph measuring 14 km~2 were provided by DREAM LiDAR (Disaster Risk and Exposure Assessment for Mitigation). Combinations of multi-threshold and multiresolution segmentation enabled the pre-processing stage before moving on with the classification. It was observed that non-ground features are best segmented by giving weights to nDSM, pit-free CHM, average intensity and number of returns arithmetic (highest/lowest, highest*lowest). Rule-based approach was implemented in identifying artificial surfaces such as buildings and fences; then, the Support Vector Machine (SVM) algorithm was applied in classifying the remaining non-ground objects. Before proceeding to the final classification, statistical analysis was performed in the exported sample objects. From the available training inputs, features with high coefficient of variation (＞40%: nDSM, pit-free CHM and asymmetry) were removed to improve the classification accuracy. Fifteen features with low coefficient of variation (＜ 38%) were selected for the training phase of SVM; two from orthophoto-derived vegetation indices (VIgreen and VARIgreen), seven from LiDAR-derived layers (number of returns, vertical features and intensity) and 6 from geometry features (roundness, shape index, rectangular fit, compactness, density and elliptic fit). Applying accuracy assessment based on test and training area (TTA) mask derived from validation points, the producer's and user's accuracy for mangrove, artificial surfaces and other vegetation were above 0.96. As a result, the overall accuracy of the produced finescale mangrove map was 0.98 with a Kappa Index of Agreement of 0.97. The mapping product can then be used by local government unit and management agencies as a reference in baseline assessment of mangrove resources, and in planning and implementing further conservation efforts.
机译：努力在节省巴拉邦加的卡拉加班的红树林森林方面取得了努力。事实上，卡拉加曼当地政府在2009年9月8日在2009年9月8日创造了Calatagan Mangrove森林保护公园，在Brgy中创建了Calatagan Mangrove森林保护公园。 Quilitisan。本研究凭借对该美洲红树林的保护和环境评估，介绍了生产这些保护区的微尺度图的方法。该研究网站涵盖了四个沿海巴兰日（巴利比亚，Talisay，Carretunan和Quilitisan）。用作图像分类中的输入，通过梦想激光雷达（减缓灾害风险和暴露评估）提供14公里〜2的空中激光雷达（光检测和测距）数据和正交仪。在继续分类之前，多阈值和多分辨率分割的组合使得预处理阶段能够进行分类。观察到，通过向NDSM，无易磁的CHM，平均强度和返回算术数（最高/最低，最高*最低）来说，最佳分段是最佳分割的。基于规则的方法在识别建筑物和围栏等人造表面来实施;然后，应用支持向量机（SVM）算法在分类剩余的非接地对象时应用。在进行最终分类之前，在出口的样本对象中进行统计分析。从可用的训练输入中，除去具有高系数的特征（> 40％：NDSM，无易磁性CHM和不对称），以提高分类精度。选择具有低变异系数（<38％）的十五个特征，用于SVM的训练阶段;两种来自矫正植被指数（vigreen和Varigreen），七个来自LiDar衍生的层（返回，垂直特征和强度）和6个来自几何特征（圆度，形状指数，矩形配合，密度，密度和椭圆拟合） 。基于测试和训练区域（TTA）掩模的准确性评估来自验证点，生产者和用户的红树林，人造表面和其他植被的准确性，高于0.96。因此，生产的FineScale红树林地图的总体准确性为0.98，Kappa协议的kappa指数为0.97。当地政府单位和管理机构可以使用映射产品作为红树林资源基线评估的参考，并在规划和实施进一步的保护努力中。

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