Prior-knowledge-based single-tree extraction

Prior-knowledge-based single-tree extraction
复制标题

基于先验知识的单树提取

DOI:
10.1080/01431161.2010.494633
复制
发表时间:
2011
影响因子:
3.4
通讯作者:
Weinacker
Weinacker
中科院分区:
工程技术3区
文献类型:
--
作者:
Heinzel;Weinacker

文献摘要

参考文献

被引文献

相似文献

从遥感数据中自动提取单株树木的研究有很多,但在温带茂密森林地区,结果仍然不足。由于树顶确定缺乏精确的平滑标准,使用数字表面模型的基于流域的常见算法往往会在复杂的星座中产生错误的结果。在本文中,介绍了一种新的方法,预先分类树冠大小,并将此信息作为先验知识用于单树提取。采用改进的灰度粒度法对树冠大小进行纹理分类,然后对单株树冠大小进行分水岭分割。该方法在10 km2的大面积上进行了应用,并在6个反映不同成分和困难成分的参考地块上进行了验证。准确率在64%到88%之间,与不依赖树冠大小的算法相比,对于落叶林和混合林,准确率平均提高了30%左右。
The automatic extraction of single trees from remotely sensed data is approached in numerous studies, but results are still insufficient in areas of dense temperate forest. Common watershed-based algorithms using digital surface models tend to produce erroneous results in difficult constellations because the treetop determination lacks an exact criterion for smoothing. In this article, a new approach is introduced that classifies crown size in advance and uses this information as prior knowledge for single-tree extraction. Crown size is classified from texture with an improved grey-scale granulometry followed by a crown size adapted watershed segmentation of single trees. The method is applied on a large area of 10 km2and verified on six reference plots reflecting diverse and difficult compositions. The accuracy varies between 64% and 88%, and shows an average improvement of about 30% for deciduous and mixed stands compared to a non-crown-size-dependent algorithm.
使用针对瑞典北方森林条件开发的算法,通过激光扫描在中欧混合山地森林中检测和测量单棵树木
DOI: --
发表时间: 2004
期刊:
影响因子: --
作者:
M. Heurich;A. Persson;J. Holmgren;E. Kennel
通讯作者: E. Kennel
基于激光雷达点云的森林内垂直结构分析和 3D 单树提取程序的开发
DOI: --
发表时间: 2007
期刊:
影响因子: --
作者:
Yunshen Wang;H. Weinacker;B. Koch
通讯作者: B. Koch
DOI: --
发表时间: 1993
影响因子: 2.6
作者:
Demin Wang;V. Haese;A. Bruno;J. Ronsin
通讯作者: J. Ronsin
使用胚粒模型对角膜内皮镜面图像进行粒度分析
DOI: 10.1016/j.compbiomed.2006.04.005
发表时间: 2007
影响因子: 7.7
作者:
M. E. Díaz;G. Ayala;R. Sebastián;L. Martínez
通讯作者: L. Martínez
分水岭分割中标记的知识
DOI: --
发表时间: 2007
期刊: International Conference on Computer Analysis of Images and Patterns
影响因子: --
作者:
S. Lefèvre
通讯作者: S. Lefèvre