基于图像处理的甘蔗茎节识别与蔗芽检测
|
摘要
为实现机器能够准确无误的找到甘蔗蔗芽的位置,让切刀在指定的位置切割甘蔗,运用图像处理技术对甘蔗的茎节和蔗芽分别进行了定位识别。通过滤波去噪、颜色空间转换、图像融合获得图像的二值化信息;再通过LBP(Local Binary Pattern)纹理特性和形态学操作实现甘蔗区域的分割。之后,通过计算每个茎节上列像素值之和,统计出位于直线中线的像素值,即该像素值对应的列坐标为茎上的最优直线。最后,由蔗芽总是环绕茎节分布的特征,结合boundingRect函数,定位出蔗芽的位置。试验结果表明:该算法的甘蔗茎节识别率,在单节时能达到100%,在多节时稳定在80%以上,算法执行时间为0.507 s。
In order to locate the cane buds accurately and correctly and enable the cutter to work at the designed position. The image processing technology was used to locate and identify the stem segments and sugarcane buds of sugarcane. The binary information of image was obtained through filter denoising, color space conversion and image fusion; then the segmentation of sugarcane area is realized by LBP(Local Binary Pattern) texture characteristics and morphological operations. Then, by calculating the sum of the column pixel values on each stem segment, the pixel value of the line in the straight line is counted, that is, the column coordinate corresponding to the pixel value is the optimal straight line on the stem. Finally, the location of cane bud was determined by the characteristics of the cane bud distribution around the stem node and boundingRect function. The experimental results show that the recognition rate of sugarcane stem section can reach up to 100% in single section and more than 80% in multi-section, and the algorithm execution time is 0.507 s.
In order to locate the cane buds accurately and correctly and enable the cutter to work at the designed position. The image processing technology was used to locate and identify the stem segments and sugarcane buds of sugarcane. The binary information of image was obtained through filter denoising, color space conversion and image fusion; then the segmentation of sugarcane area is realized by LBP(Local Binary Pattern) texture characteristics and morphological operations. Then, by calculating the sum of the column pixel values on each stem segment, the pixel value of the line in the straight line is counted, that is, the column coordinate corresponding to the pixel value is the optimal straight line on the stem. Finally, the location of cane bud was determined by the characteristics of the cane bud distribution around the stem node and boundingRect function. The experimental results show that the recognition rate of sugarcane stem section can reach up to 100% in single section and more than 80% in multi-section, and the algorithm execution time is 0.507 s.
引文
[1] 韦巧,杨宝玲,高振江.我国甘蔗产业化现状浅析[J].农机化研究,2015,37(4):247-254.
[2] 陆尚平,文友先,葛维,等.基于机器视觉的甘蔗茎节特征提取与识别[J].农业机械学报,2010,41(10):190-194.
[3] 黄亦其,黄体森,黄媚章,等.基于局部均值的甘蔗茎节识别[J].中国农机化学报,2017,38(02):76-80.
[4] Moshashai K,Almasi M,Minaei S,et al.Identification of sugarcane nodes using image processing and machine vision technology[J].International Journal of Agricultural Research,2008,3(5):357-364.
[5] 陆尚平,黄林,陈炳森,等.基于机器视觉的甘蔗种植机械化研究[J].广西农业机械化,2012(5):28-29,32.
[6] 肖超云,朱伟兴.基于Otsu准则及图像熵的阈值分割算法[J].计算机工程,2007,33(14):188-189,209.
[7] 沈鲁娟.基于LBP特征提取的纹理图像识别方法研究[D].天津:中国民航大学,2015:42-55.
[8] 简丽琼.选择局部二值模式的纹理识别[J].信息与电脑(理论版),2018(19):135-140+143.
[9] 张卫正,董寿银,齐晓祥,等.基于图像处理的甘蔗茎节识别与定位[J].农机化研究,2016(4):217-221.
[10] 石昌友,王美丽,刘欣然,等.基于机器视觉的不同类型甘蔗茎节识别[J].计算机应用,2019,39(04):1208-1213.
[11] 黄亦其,乔曦,唐书喜,等.基于Matlab的甘蔗茎节特征分布定位与试验[J].农业机械学报,2013,44(10):93-97,232.
[12] 陈红.基于计算机视觉的花生仁外观品质无损检测方法的研究[D].武汉:华中农业大学,2008:45-67.
[2] 陆尚平,文友先,葛维,等.基于机器视觉的甘蔗茎节特征提取与识别[J].农业机械学报,2010,41(10):190-194.
[3] 黄亦其,黄体森,黄媚章,等.基于局部均值的甘蔗茎节识别[J].中国农机化学报,2017,38(02):76-80.
[4] Moshashai K,Almasi M,Minaei S,et al.Identification of sugarcane nodes using image processing and machine vision technology[J].International Journal of Agricultural Research,2008,3(5):357-364.
[5] 陆尚平,黄林,陈炳森,等.基于机器视觉的甘蔗种植机械化研究[J].广西农业机械化,2012(5):28-29,32.
[6] 肖超云,朱伟兴.基于Otsu准则及图像熵的阈值分割算法[J].计算机工程,2007,33(14):188-189,209.
[7] 沈鲁娟.基于LBP特征提取的纹理图像识别方法研究[D].天津:中国民航大学,2015:42-55.
[8] 简丽琼.选择局部二值模式的纹理识别[J].信息与电脑(理论版),2018(19):135-140+143.
[9] 张卫正,董寿银,齐晓祥,等.基于图像处理的甘蔗茎节识别与定位[J].农机化研究,2016(4):217-221.
[10] 石昌友,王美丽,刘欣然,等.基于机器视觉的不同类型甘蔗茎节识别[J].计算机应用,2019,39(04):1208-1213.
[11] 黄亦其,乔曦,唐书喜,等.基于Matlab的甘蔗茎节特征分布定位与试验[J].农业机械学报,2013,44(10):93-97,232.
[12] 陈红.基于计算机视觉的花生仁外观品质无损检测方法的研究[D].武汉:华中农业大学,2008:45-67.