首页> 外国专利> METHOD FOR RECOGNIZING TREETOP, DEVICE FOR RECOGNIZING TREETOP, AND PROGRAM FOR RECOGNIZING TREETOP

METHOD FOR RECOGNIZING TREETOP, DEVICE FOR RECOGNIZING TREETOP, AND PROGRAM FOR RECOGNIZING TREETOP

机译:识别树的方法,识别树的设备以及识别树的程序

摘要

PROBLEM TO BE SOLVED: To provide a method for automatically recognizing the top of a single tree: and to provide a device for automatically recognizing the top of a single tree.;SOLUTION: The device for recognizing a treetop is provided with a tree-height calculation part 14, a search range determination part 17, a second treetop shape index number calculation part 41, a second treetop determination part 43, a threshold value calculation part 35, a local area setting part 36 and the like, reads in tree-height grid data corresponding to the search range from a file 15, changes a prescribed value for making the treetop shape clearer based on the maximum and minimum values of an aspect ratio in the grid data, obtains new upground divergence and underground divergence using the changed maximal value and the changed minimum value, averages the treetop shape index calculated from these divergence, and equalizes the averaged treetop shape index in the local area or a gaunsian filter to be calculated as the treetop shape index in the search range, so that the sum of the average value and the standard deviation of the image in the preset local area is obtained as a threshold value Hgi, the treetop shape index which is larger than the threshold value Hgi is extracted as a treetop part, and an optimum top point of the single tree is determined based on the treetop part.;COPYRIGHT: (C)2009,JPO&INPIT
机译:解决的问题:提供一种用于自动识别单棵树的顶部的方法:并提供一种用于自动识别单棵树的顶部的设备。解决方案:用于识别树顶的设备具有树高。计算部分14,搜索范围确定部分17,第二树梢形状指标数目计算部分41,第二树梢确定部分43,阈值计算部分35,局部区域设置部分36等读取树高与来自文件15的搜索范围相对应的网格数据,基于网格数据中纵横比的最大值和最小值,更改用于使树顶形状更清晰的规定值,并使用更改后的最大值获得新的地面发散度和地下发散度以及改变后的最小值,将根据这些差异计算出的树顶形状指数取平均值,并将局部区域或高斯滤波器的平均树顶形状指数均等化在搜索范围内将其计算为树顶形状索引,从而获得预设局部区域中图像的平均值和标准偏差之和作为阈值Hgi,该树顶形状索引大于阈值将Hgi提取为树梢部分,并根据树梢部分确定单棵树的最佳顶点。;版权所有:(C)2009,JPO&INPIT

著录项

相似文献

  • 专利
  • 外文文献
  • 中文文献
获取专利

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