白芦笋采收机器人视觉定位与采收路径优化方法

doi:10.12133/j.smartag.2020.2.4.202009-SA003

Smart Agriculture ›› 2020, Vol. 2 ›› Issue (4): 65-78.doi: 10.12133/j.smartag.2020.2.4.202009-SA003

• 专刊--农业机器人与智能装备 • 上一篇下一篇

白芦笋采收机器人视觉定位与采收路径优化方法

李扬^1,²(), 张萍⁴, 苑进^1,³(), 刘雪美^1,²

^1.山东农业大学机械与电子工程学院，山东泰安 271018
^2.山东省园艺机械与装备重点实验室，山东泰安 271018
^3.山东省农业装备智能化工程实验室，山东泰安 271018
^4.山东农业大学信息科学与工程学院，山东泰安 271018

收稿日期:2020-09-28 修回日期:2020-10-28 出版日期:2020-12-30
基金资助:
国家自然科学基金项目(51675317);山东省重点研发计划项目(2017GNC12110)
作者简介:李扬（1982－），男，副教授，博士后，研究方向为智能控制技术。E-mail：mtlyab@sdau.edu.cn。
通信作者:

Visual Positioning and Harvesting Path Optimization of White Asparagus Harvesting Robot

LI Yang^1,²(), ZHANG Ping⁴, YUAN Jin^1,³(), LIU Xuemei^1,²

^1.School of Mechanical and Electronic Engineering, Shandong Agricultural University, Tai'an 271018, China
^2.Shandong Provincial Key Laboratory of Horticultural Machinery and Equipment, Tai'an 271018, China
^3.Shandong Agricultural Equipment Intelligent Engineering Laboratory, Tai'an 271018, China
^4.School of Information Science and Engineering, Shandong Agricultural University, Tai'an 271018, China

Received:2020-09-28 Revised:2020-10-28 Online:2020-12-30

摘要/Abstract

摘要：

依据笋芽出土状态的选择性收获是目前白芦笋公认的最佳收获方式。针对采收过程中机器视觉识别笋尖存在笋尖与垄面纹理和颜色相近等识别难题，本研究提出了一种变尺度感兴趣区域（ROI）检测方法，融合图像色域变换、直方图均值化、形态学和纹理滤波等技术，研究了笋尖识别与精准定位方法；在定位多笋尖坐标基础上，提出了多笋芽的采收路径优化方法，解决了因采收路径不合理导致的采收效率低的问题。首先，通过机器人视觉系统实时采集采收区域图像并进行RGB三通道高斯滤波，采用HSV色域变换并进行直方图均值化处理。在此基础上，对笋尖、土壤进行特征聚类分析，根据笋芽抽发程度研究变尺度ROI检测方法，对采集图像中笋尖的形态学以及笋尖和土壤的纹理进行统计学分析，设定笋尖的似圆度阈值，并参考纹理特征参数，判定笋尖位置，计算其几何中心，获得笋尖轮廓中心坐标。其次，为实现白芦笋的高效采收，根据多目标点与集箱点的位置分布，本研究设计了一种基于多叉树遍历的采收路径优化算法，以获得多个目标笋尖的最优采收路径。最后，搭建采收机器人试验平台开展了笋尖定位与采收验证性试验。结果表明，视觉系统对白芦笋的识别率可达98.04%，笋尖轮廓中心坐标的定位最大误差X方向为0.879 mm，Y方向为0.882 mm，采收笋的个数在不同情况下，采用路径优化后的末端执行器运动距离平均可节省43.89%，末端执行器定位成功率达到100%，在实验室环境下的白芦笋采收率达到88.13%，验证了采用视觉定位的白芦笋采收机器人选择性采收的可行性。

关键词: 白芦笋, 采收机器人, 选择性采收, 视觉定位, 采收路径优化, 笋尖识别

Abstract:

For white asparagus selective harvesting is the best harvesting method determined by its growth characteristics. Focusing on the difficulties that the texture and the color of shoot tips are similar with ridge surface under machine vision, the recognition method of asparagus shoots and precise positioning were studied in this research. A changeable scale ROI detection method was proposed, with the fusion of color transformation, histogram averaging, morphology and texture filtering. After that, a harvesting path optimization method of multiple asparaguses was proposed, which solved the problem of harvesting efficiency reduction caused by unreasonable harvesting paths. Firstly, real-time acquisition of the image and individual RGB channel Gaussian filtering were implemented. Based on the HSV color transformation and histogram averaging processing, the asparagus shoot and soil feature clustering analysis were carried out. According to the sprout degrees of asparaguses, the changeable scale ROI detection method was studied. The morphology and the texture of the shoot, and soil were statistically analyzed. According to the texture feature parameters, the position of shoot was determined and its geometric center was calculated. Secondly, in order to improve harvesting efficiency, a path optimization algorithm based on multiple asparaguses was designed according to the locations of the asparaguses and the bins to obtain the optimal harvesting path. Finally, in order to verify the reliability of the proposed methods, asparagus shoot location and harvest verification tests were carried out on the established harvesting test platform. The results showed that the recognition rate of white asparagus in the visual system was more than 98.04%, the maximum positioning error of the center coordinate of the white asparagus shoot was 0.879 mm in X direction and 0.882 mm in Y direction, and the average reduction of end-effector motion distance could be 43.89% after path optimization under different circumstances, the success rate of end-effector localization was 100% and the harvest rate of white asparagus in the laboratory test was 88.13%. The research verified the feasibility of the visual positioning and harvesting path optimization of the white asparagus selective harvesting robot.

Key words: white asparagus, harvesting robot, selective harvesting, visual positioning, harvesting path optimization, asparagus shoot recognition

中图分类号:

TP242.6

李扬, 张萍, 苑进, 刘雪美. 白芦笋采收机器人视觉定位与采收路径优化方法[J]. 智慧农业（中英文）, 2020, 2(4): 65-78.

LI Yang, ZHANG Ping, YUAN Jin, LIU Xuemei. Visual Positioning and Harvesting Path Optimization of White Asparagus Harvesting Robot[J]. Smart Agriculture, 2020, 2(4): 65-78.

参考文献

1	鲁博. 我国芦笋产业的发展现状及发展趋势[J]. 上海蔬菜, 2018(4): 3-4, 12.
1	LU B. Development status and development trend of asparagus industry in China[J]. Shanghai Vegetables, 2018(4): 3-4, 12
2	苑进. 选择性收获机器人技术研究进展与分析[J].农业机械学报, 2020, 52(9): 1-17.
2	YUAN J. Research progress analysis of robotics selective harvesting technologies[J]. Transactions of the CSAM, 2020, 52(9): 1-17.
3	DONG F, HEINEMANN W, KASPER R. Development of a row guidance system for an autonomous robot for white asparagus harvesting[J]. Computers and Electronics in Agriculture, 2011, 79(2): 216-225.
4	ARNDT G R, RUDZIEJEWSKI R, STEWART V A. On the future of automated selective asparagus harvesting technology[J]. Computers and Electronics in Agriculture, 1997, 16: 137-145.
5	BAYLOU P, HADJ AMOR E B, MONFION N, et al. Detection and 3-D localization by stereoscopic visual sensor and its application to a robot for picking asparagus[J]. Pattern Recognition, 1984, 17(4): 377- 384.
6	陈度, ZHANG Q, 王书茂, 等. 芦笋机械化收获技术现状与发展分析[J]. 中国农业大学学报, 2016, 21(4): 113-120.
6	CHEN D, ZHANG Q, WANG S, et al. Current status and future solutions for asparagus mechanical harvesting[J]. Journal of China Agricultural University, 2016, 21(4): 113-120.
7	薛忠, 宋德庆, 刘恩平, 等. 国内外芦笋种植收获机械化研究进展[J]. 中国农业科技导报, 2014, 16(2): 79-84.
7	XUE Z, SONG D, LIU E, et al. Frontier of asparagus planting and harvesting mechanization in the world[J]. Journal of Agricultural Science and Technology, 2014, 16(2): 79-84.
8	王侨, 陈兵旗, 寇春荣, 等. 基于机器视觉的玉米种粒定向定位摆放装置研制[J].农业工程学报, 2017, 33(11): 19-28.
8	WANG Q, CHEN B, KOU C, et al. Development of corn grain directional positioning device based on machine vision[J]. Transactions of the CSAE, 2017, 33(11): 19-28.
9	李文采, 李家鹏, 田寒友, 等. 基于RGB颜色空间的冷冻猪肉储藏时间机器视觉判定[J]. 农业工程学报, 2019, 35(3): 294-300.
9	LI W, LI J, TIAN H, et al. Machine vision determination of frozen pork storage time based on RGB color space[J]. Transactions of the CSAE, 2019, 35(3): 294-300
10	吴薇, 王宜怀, 程曦, 等. 基于机器视觉的武夷岩茶做青程度识别研究[J]. 山西农业大学学报(自然科学版), 2019, 39(2): 86-92.
10	WU W, WANG Y, CHENG X, et al. Study on the recognition of Wuyiyan tea based on machine vision[J]. Journal of Shanxi Agricultural University (Natural Science Edition), 2019, 39(2): 86-92
11	冯剑锋. 基于单目视觉的环境特征提取与位姿估计算法研究[D]. 杭州: 浙江理工大学, 2018.
11	FENG J. Research on environment feature extraction and pose estimation algorithm based on monocular vision[D]. Hangzhou: Zhejiang Sci-Tech University, 2018.
12	刘媛媛, 王跃勇, 于海业, 等. 基于多阈值图像分割算法的秸秆覆盖率检测[J]. 农业机械学报, 2018, 49(12): 27-35, 55.
12	LIU Y, WANG Y, YU H, et al. Stalk coverage detection based on multi-threshold image segmentation algorithm[J]. Transactions of the CSAM, 2018, 49(12): 27-35, 55.
13	王海青, 姬长英, 顾宝兴, 等. 基于机器视觉和支持向量机的温室黄瓜识别[J]. 农业机械学报, 2012, 43(3): 163-167, 180.
13	WANG H, JI C, GU B, et al. Greenhouse cucumber recognition based on machine vision and support vector machine[J]. Transactions of the CSAM, 2012, 43(3): 163-167, 180.
14	陈凤萍, 齐建华. 旋转不变纹理特征在图像模式识别中应用仿真[J]. 计算机仿真, 2019, 36(2): 353-356.
14	CHEN F, QI J. Application of rotation-invariant texture feature in image pattern recognition[J]. Computer Simulation, 2019, 36(2): 353-356.
15	王新忠. 温室番茄收获机器人选择性收获作业信息获取与路径规划研究[D]. 镇江: 江苏大学, 2012.
15	WANG X. Studies on information acquisition and path planning of greenhouse tomato harvesting robot with selective harvesting operation[D]. Zhenjiang: Jiangsu University, 2012.
16	刘雪美, 杜帅, 苑进, 等. 白芦笋选择性收获机末端执行器作业分析与试验[J]. 农业机械学报, 2018, 49(4): 110-120.
16	LIU X, DU S, YUAN J, et al. Analysis and experiment of the end-effector of white asparagus selective harvester[J]. Transactions of the CSAM, 2018, 49(4): 110-120.
17	LI J, LIU X, ZOU L, et al. Analysis of the interaction between end-effectors, soil and asparagus during a harvesting process based on discrete element method[J]. Biosystems Engineering, 2020, 196: 127-144.

[1]	段罗佳, 杨福增, 闫彬, 史帅旗, 秦纪凤. 苹果生产智能底盘与除草及收获装备技术研究进展[J]. 智慧农业(中英文), 2022, 4(3): 24-41.
[2]	黄梓宸, SUGIYAMA Saki. 日本设施农业采收机器人研究应用进展及对中国的启示[J]. 智慧农业(中英文), 2022, 4(2): 135-149.

白芦笋采收机器人视觉定位与采收路径优化方法

Visual Positioning and Harvesting Path Optimization of White Asparagus Harvesting Robot

在线阅读

知网下载

本地下载

可视化

摘要/Abstract

引用本文

使用本文

参考文献

相关文章 2

编辑推荐

Metrics

本文评价