基于图像分析的树木自然倒向测定方法  

The Method of Determining Natural Falling Direction of Trees Based on Image Analysis

作　　者：李方剑 杨铁滨 徐华东 LI Fangjian;YANG Tiebin;XU Huadong(College of Mechanical and Electrical Engineering,Northeast Forestry University,Harbin 150040,China)

机构地区：[1]东北林业大学机电工程学院,哈尔滨150040

出　　处：《森林工程》2025年第2期321-329,共9页Forest Engineering

基　　金：国家自然科学基金项目(31870537);黑龙江省自然科学基金面上项目(C201410)。

摘　　要：为解决在链锯伐木作业过程中树木自然倒向预测不准确时易发生安全事故,造成人员伤亡和财产损失的问题,提出一种基于智能手机图像分析的树木自然倒向测定方法。采用基于K-means聚类算法改进的Close-Form图像抠图算法提取图像中目标树木,利用亚像素形心定位法确定单幅图像树木质心位置,基于空间向量复合及投影法则分别对树木进行三视角和双视角质心拟合,并计算出树木自然倒向。试验结果表明,三视角、双视角以及人工经验判别方法判断树木自然倒向的结果无显著性差异且具有高度一致性(方差检验统计量F为0.008,P=1.000>0.05;采样组内相关系数ICC为0.992,P=0.000<0.05)。由于双视角测量具有简便性,因此可用双视角判别方法测定树木自然倒向。扩展试验表明,双视角判别方法具有较高的准确性与稳定性(F=0.003,P=0.997>0.05),可为准确判断树木自然倒向提供参考。In order to solve the problem of inaccurate prediction of natural falling direction during chain-saw logging operations,which is prone to safety accidents and cause casualties and property losses,a method for determining the natural falling direction of trees based on smartphone image analysis is proposed.The target trees in the images are extracted using the Close-Form image matting algorithm based on K-means clustering algorithm improvement.The sub-pixel-centroid positioning method is used to determine the location of the tree center of gravity in a single image.The trees are fitted with three-angle and two-angle gravity center fitting according to the space vector composite and projection law,respectively,and calculate the natural falling direction.The experimental results show that there is no significant difference and high consistency between the results of three-angle,two-angle,and human experienced discrimination methods in judging the natural falling direction of trees(F=0.008,P=1.000>0.05;ICC is 0.990,P=0.000<0.05).Because of the simplicity of the two-angle measurement,the two-angle discrimination method can be used to determine the natural fall‐ing direction of trees.Extended experiments show that the two-angle discrimination method has high accuracy(F=0.003,P=0.997>0.05),and can provide a certain reference for accurately judging the natural falling direction of trees.

关 键 词：树木 自然倒向 质心拟合 图像分割 形心定位 

分 类 号：S771.3[农业科学—森林工程]