Construction and in-field experiment of low-cost binocular vision platform for pineapple harvesting robot

机译：菠萝收获机器人低成本双目视觉平台的构建与现场实验

获取原文

获取原文并翻译 | 示例

页面导航

摘要
著录项
相似文献
相关主题

摘要

Vision system is one of key parts of agricultural harvesting robots,which provides the fruit's position information for navigating the manipulator.Considering its applications in agriculture and the pineapple is big enough for recognition,this study presents a low-cost binocular vision platform for pineapple harvesting robots,which consists of low-cost CMOS (Complementary Metal Oxide Semiconductor) image sensors,a tripod,a binocular pan,a PC and software system; The calibration model and the calibration software were developed based on C--and OpenCV version 1.1,and Matlab calibration toolbox separately; The Zhang's algorithm was employed during the calibration.By experiment,the suitable calibration method for the constructed platform was selected.Based on the low-cost vision platform and developed pineapple recognition algorithms,3D position calculation experiments for pineapples were conducted in a pineapple field of Zhanjiang.The results showed that the depth errors were less than 6-8 em when the depth distance was around 1 m,and the errors were less than 2-3 cm after correcting the whole system.The low-cost platform performed well and its feasibility was proved.This study can provide a reference for the development of pineapple harvesting robots.%视觉系统是菠萝采摘机械的关键部件之一,可为采摘终端提供待采果实的位置导航信息.考虑到菠萝果形较大,易于识别,以及系统应用于农业领域,需尽可能降低成本.该研究选取双目视觉技术,采用低成本的CMOS视觉传感器,辅以三脚架、双目云台,以及计算机、软件系统,搭建低成本双目视觉标定平台；研究了标定模型及流程,并基于C--和OpenCVvl.l环境以及Matlab标定工具箱的软件环境平台,采用张正友标定算法,分别对视觉传感器进行标定试验,选取了适合本平台的标定方法.基于此平台和开发的菠萝果实识别算法,在湛江菠萝田间进行果实深度测量试验发现,果实测试距离小于1m时,深度误差在6～8 cm范围内,经软件算法校正后,误差控制在2～3 cm范围内,该平台试验结果良好,表明低成本试验平台具有可行性.该研究可为菠萝采摘机器人视觉系统的开发提供参考.

机译：视觉系统是农业收割机器人的关键部件之一，它为操纵机器人提供了水果的位置信息。考虑到其在农业中的应用以及菠萝的识别能力，该研究提供了一种低成本的双目视觉平台，用于菠萝收割机器人由低成本的CMOS（互补金属氧化物半导体）图像传感器，三脚架，双目镜，PC和软件系统组成；分别基于C和OpenCV 1.1版以及Matlab校准工具箱开发了校准模型和校准软件；在标定过程中采用了张氏算法。通过实验，选择了合适的标定平台标定方法。在低成本视觉平台的基础上，开发了菠萝识别算法，在菠萝田中进行了菠萝的3D位置计算实验。湛江。结果表明，深度距离在1 m左右时深度误差小于6-8 em，对整个系统进行校正后误差小于2-3 cm。视觉系统是菠萝采摘机械的关键部件之一，可为采摘终端提供待采果实的位置导航信息。考虑到菠萝果形较早该研究选择双目视觉技术，采用分辨率的CMOS视觉传感器，辅以三脚架，双目云台，以及计算机，软件系统，搭建校准双目视觉标定平台；研究了标定模型及流程，并基于C--和OpenCVvl.l环境以及Matlab标定工具箱的软件环境平台，采用张正友标定算法，分别对视觉传感器进行标定试验，拾取了适合本平台的标定方法。基于此平台和开发的菠萝果实识别算法，在湛江菠萝田间进行果实深度测量试验发现，果实测试距离小于1m时，深度误差在6〜8 cm范围内，经软件算法校正后，误差控制在2〜3 cm范围内，该平台试验结果良好，表明定向试验平台具有可行性性。该研究可为菠萝采摘机器人视觉系统的开发提供参考。

著录项

来源
《Proceedings of the Fourteenth International conference on mechanization of field experiments》|2012年|215-219|共5页
会议地点 Qingdao(CN)
作者
Li Bin; Wang Haifeng; Huang Wenqian; Zhang Chi;
展开▼
作者单位

National Engineering Research Center of Intelligent Equipment for Agdculture, Beijing 100089;

Chinese Academy of Modem Agricultural Mechanization Sciences, Beijing 100083;

National Engineering Research Center of Intelligent Equipment for Agdculture, Beijing 100089;

National Engineering Research Center of Intelligent Equipment for Agdculture, Beijing 100089;

展开▼
会议组织
原文格式 PDF
正文语种 eng
中图分类农业生产作业机械化工艺组织;
关键词
computer vision; experiment; calibration; pineapple harvesting; binocular vision; low-cost机器视觉; 试验; 标定; 菠萝采摘; 双目视觉; 低成本;

机译：computer vision; experiment; calibration; pineapple harvesting; binocular vision; low-cost%机器视觉;试验;标定;菠萝采摘;双目视觉;低成本;

相似文献

外文文献
中文文献
专利

1. IN-FIELD RECOGNITION AND NAVIGATION PATH EXTRACTION FOR PINEAPPLE HARVESTING ROBOTS [J] . Bin Li, Maohua Wang Intelligent automation and soft computing . 2013,第1期

机译：菠萝捕捞机器人的现场识别和导航路径提取
2. Dual-arm cooperation and implementing for robotic harvesting tomato using binocular vision [J] . Ling Xiao, Zhao Yuanshen, Gong Liang, Robotics and Autonomous Systems . 2019,第期

机译：双臂合作，用于使用双筒望远镜的机器人收获番茄
3. Cherry tomato harvesting robot using 3-D vision sensor (part 2) -- architecture of robot and harvesting experiment [J] . I Dewa Made Subrata, Tateshi Fujiura, Hisaya Yamada, 配管·装置·プラント技術 . 1998,第1期

机译：使用3-D Vision传感器（第2部分） - 机器人和收获实验的樱桃番茄收获机器人
4. Construction and in-field experiment of low-cost binocular vision platform for pineapple harvesting robot [C] . Li Bin, Wang Haifeng, Huang Wenqian, International conference on mechanization of field experiments . 2012

机译：菠萝收获机器人低成本双筒望远镜平台的构建与现场实验
5. A Robotic Proximal Sensing Platform for In-Field High-Throughput Crop Phenotyping [D] . Tuel, Taylor Leonard. 2019

机译：用于现场高通量作物表型的机器人近端传感平台
6. Fruit Detection and Pose Estimation for Grape Cluster–Harvesting Robot Using Binocular Imagery Based on Deep Neural Networks [O] . Wei Yin, Hanjin Wen, Zhengtong Ning, 2021

机译：基于深神经网络的双目图像葡萄簇收获机器人的果实检测与姿势估计
7. Development of a Bio-inspired Vision System for Mobile Micro-robots:In this paper, we present a new bio-inspired vision system for mobile micro-robots. The processing method takes inspiration from vision of locusts in detecting the fast approaching objects. Research suggested that locusts use wide-field visual neuron called the lobula giant movement detector to respond to imminent collisions. We employed the locusts' vision mechanism to motion control of a mobile robot. The selected image processing method is implemented on a developed extension module using a low-cost and fast ARM processor. The vision module is placed on top of a micro-robot to control its trajectory and to avoid obstacles. The observed results from several performed experiments demonstrated that the developed extension module and the inspired vision system are feasible to employ as a vision module for obstacle avoidance and motion control. [O] . Hu, Cheng, Arvin, Farshad, Yue, Shigang 2014

机译：开发用于移动微型机器人的生物启发视觉系统：在本文中，我们提出了一种用于移动微型机器人的新型生物启发视觉系统。该处理方法从检测快速接近物体的蝗虫视觉中获取灵感。研究表明，蝗虫使用称为小叶巨型运动探测器的宽视野神经元来应对即将发生的碰撞。我们采用蝗虫的视觉机制来控制移动机器人。所选择的图像处理方法使用低成本且快速的aRm处理器在开发的扩展模块上实现。视觉模块放置在微型机器人的顶部以控制其轨迹并避开障碍物。几次进行的实验观察到的结果表明，开发的扩展模块和灵感视觉系统可用作避障和运动控制的视觉模块。

Construction and in-field experiment of low-cost binocular vision platform for pineapple harvesting robot

摘要

著录项

相似文献

相关主题

期刊订阅