基于最小二乘法的早期作物行中心线检测方法  

Early Stage Crop Rows Detection Based on Least Square Method

作　　者：司永胜[1,2] 姜国权[3] 刘刚[2] 高瑞[2] 刘兆祥[2] 

机构地区：[1]河北农业大学信息科学与技术学院,保定071001 [2]中国农业大学现代精细农业系统集成研究教育部重点实验室,北京100083 [3]河南理工大学计算机科学与技术学院,焦作454003

出　　处：《农业机械学报》2010年第7期163-167,185,共6页Transactions of the Chinese Society for Agricultural Machinery

基　　金：国家"863"高技术研究发展计划资助项目(2006AA10A304;2006AA10Z255);中国农业大学研究生科研创新专项资助项目

摘　　要：提出了一种基于最小二乘法的早期作物行中心线检测算法。利用G-R颜色特征因子分割作物与背景。根据作物与杂草的长度属性去除部分杂草噪声,应用垂直投影法动态检测作物行数,并提取作物行中点为特征点,获得特征点图像。利用特征点间的邻近关系对特征点进行分类,对归类后的特征点进行两次最小二乘法拟合,得到作物行中心线。对于有作物缺失的作物行,采用统计条形区域内特征点数量的方法判别检测结果的可信度。实验结果表明,算法能克服杂草和作物缺失的影响,实时地提取小麦、玉米和大豆作物行,平均每幅图像处理时间小于150 ms。To improve real-time performance of agriculture vehicle navigation,an algorithm based on least square method for detection of crop rows,especially of crops in the early stage of growth was proposed.Crops were segmented from background by the index of G-R.Parts of the noises of weeds in the image were eliminated according to their length.Crop line numbers were detected dynamically by vertical projection method.Center points of crop rows were extracted as feature points and were classified into different clusters.Least square method was used twice for fitting the center line of crop row to the feature points.The number of the feature points was counted to judge the reliability of the detection result of crop row with plant deficiency.The experimental result showed that the algorithm could overcome the effect of weed noise and plant deficiency.The average time of image processing was less than 150ms.

关 键 词：农业机械 导航 机器视觉 图像分割 直线检测 最小二乘法 

分 类 号：TP242.62[自动化与计算机技术—检测技术与自动化装置]