Weak perspective model of camera was adopted. First of all, image of calibration target was captured to obtain pixel coordinates of 48 target centroids. Then hidden parameters matrix of camera was calculated by using least square based on DLT. Location tests of ordered and disordered weeds in indoor soil trough showed that positioning errors of ordered and disordered weeds were 19.2mm and 22.8mm respectively by using established hidden parameters matrix of camera. The positioning accuracy could meet the requirement of precise spraying of herbicide.
参考文献
相似文献
引证文献
引用本文
尹建军,沈宝国,陈树人.基于机器视觉的田间杂草定位技术[J].农业机械学报,2010,41(6):163-166. of Field Weed Based on Machine Vision[J]. Transactions of the Chinese Society for Agricultural Machinery,2010,41(6):163-166