摘要
设计以球形果实单体为对象的采摘终端装置,该装置主要由双目视觉系统、嵌入式控制核心、机械臂与采摘器组成。对番茄果实图像识别进行了算法设计,提出了约束性Hough变换圆形检测算法完成了遮挡果实分割,基于改进PMF立体对应点算法实现了果实左右图像的立体匹配,获取果实三维质心坐标。通过对番茄、苹果、柑橘3类果实的采摘试验,结果表明:装置各模块能够协调稳定工作,采摘终端对成熟果实的成功识别率达87.5%;成功采摘率达85%。
The terminal device was designed for spherical fruit picking.It was presented the working process and hardware structure of the device,including the binocular vision system,the embedded control core,the mechanical arm and the picker.The proposed algorithm of binding Hough transform circular detection could complete the occlusion fruit segmentation.Based on the improved PMF stereo correspondence point algorithm,the 3D matching of left and right fruit images was realized,and the 3 Dcentered coordinates of fruit were also obtained.The results of the picking experiments on tomato,apple and citrus fruits showed that the module could coordinate and work steadily with 87.5% of successful recognition rate and 85% of picking rate of the mature fruits.
作者
王润涛
李明
龚振平
WANG Run-tao 1, LIMing 1 ,GONG Zhen-ping 2(1. School of Information Engineering, Lingnan Normal University, Guangdong, Zhanjiang 524048, China; 2. Agricultural College, Northeast Agricultural University, Harbin, Heilongjiang 150030, Chin)
出处
《食品与机械》
CSCD
北大核心
2018年第7期93-97,100,共6页
Food and Machinery
基金
中国博士后科学基金(编号:2016M601406)
黑龙江省博士后基金(编号:LBH-Z15024)
东北农业大学SIPT项目(编号:201610224003)
关键词
双目视觉
球形果实
采摘终端
特征提取
立体匹配
binocular vision
the spherical fruit
picking terminal
feature extraction
stereo matching