【作者】 李明；

【Author】 Li Ming1,Dai Sihui1,Kenji Imou2,Liu Zhonghua1,Liu Rouqiao3,Shu Liangbin3(1.Hunan Agricultural University,Changsha 410128,China 2.Biological and Environmental Mechanism Lab.,Tokyo 110-0001,Japan 3.Hunan Shuangfeng Nongyou Group Company,Shuangfeng,China)

【机构】 湖南农业大学工学院； 国家植物功能成分利用工程技术研究中心；

【摘要】 开发的一种基于全方位视觉传感器的农业机械定位系统,其定位精度主要决定于标识方位角度的计算准确度。该文主要研究了采用低频滤波除噪,提取出图像中人工标识的算法。该算法中,除噪后,计算图像中红色像素的强度,并设置红色阈值提取红色特征像素,以相邻像素的欧几里得几何距离来划分像素块,每像素块的重心作为标识在图像中的位置;求出图像中标识与相机投影中心的方位角度;在复杂环境中,采用蓝色块来辅助红色标识判别人工标识。通过图像标识识别实验验证了除噪处理的有效性;并在面积为30m×30m的室外平地上,选取25个测量位置进行了实验。实验结果为标识方位角平均绝对误差和均方根误差分别为1.89°和2.18°。研究表明该算法可行,求出的标识方位角误差较小,运行速度较快和鲁棒性较强。更多还原

【Abstract】 The position accuracy is mainly decided by the accuracy of landmark directional angle for the developed localization system of agricultural machinery based on omnidirectional vision sensor.This paper mainly studies algorithms about low pass filter eliminating noise and artificial landmark features detection.After eliminating noise,the red pixels’ intensity was calculated and the red landmark pixels beyond the threshold were extracted.Based on the Euclid geometrical distance of neighbor pixels,the pixels small area was divided and the center of gravity was calculated for the extracted small area representing the candidate of one landmark.The algorithm provided the blue patch as compensation to further distinguish the landmark from other objects in a complex environment.The landmark detection experiment proved that the low pass filter eliminating noise was effective.Experiments were conducted on the level ground in a 30×30-m area outside.25 test positions were equably chosen to test.Results showed that the MAE and RMSE of landmark direction angles were 1.89 degree and 2.18 degree,respectively.The proposed algorithm is feasible.The error of landmark direction angle is less and the program running speed is fast and better robustness.更多还原