基于视觉伺服的蝴蝶兰种苗切割系统设计与试验

翟永杰; 胡东阳; 苑朝; 王家豪; 张鑫; 刘亚军

doi:10.11975/j.issn.1002-6819.2022.06.017

基于视觉伺服的蝴蝶兰种苗切割系统设计与试验

1.
华北电力大学自动化系，保定 071003
2.
湖北壹鸣生物科技有限公司，钟祥 431900

基金项目: 国家自然科学基金资助重点项目（U21A20486）

计量
- 文章访问数: 246
- HTML全文浏览量: 0
- PDF下载量: 3562
出版历程
- 收稿日期: 2021-12-28
- 修回日期: 2022-02-18
- 发布日期: 2022-03-30

Design and experiments of phalaenopsis seedling cutting system using visual servo

1.
Department of Automation, North China Electric Power University, Baoding 071003, China
2.
Hubei Artisan Biotech Co., Ltd., Zhongxiang 431900, China

摘要

摘要: 蝴蝶兰种苗自动化切割可降低组培苗染病几率，提高种苗品质。为实现蝴蝶兰种苗自动化切割，该研究针对种苗结构特性提出基于拟合直线的切点定位方法，并配合切割方法设计了弹性切割末端，搭建了基于视觉伺服的蝴蝶兰种苗切割系统。首先，采用深度学习模型对采集到的图像进行目标检测；然后，根据检测结果使用基于几何规则的切割点定位算法计算切点；最后，将切割坐标传输给切割执行机构完成切割作业。目标检测试验中，ShuffleNet v2-YOLOv5模型检测精度达96.7%，权重文件大小1.3 MB，平均检测时间0.026 s。种苗切割试验中，切割合格率高于86%，单株平均切割时间小于18 s。该系统能有效完成蝴蝶兰种苗切割任务，为蝴蝶兰组培苗自动化生产提供新思路。
- 目标检测 /
- 深度学习 /
- 视觉伺服 /
- 蝴蝶兰种苗 /
- 切点定位 /
- 切割系统
Abstract: Abstract: The tissue culture technology of phalaenopsis has gradually matured in recent years. Seedling stem cutting has been one of the most critical steps in the process of the tissue culture industry. An automatic cutting system can greatly contribute to reducing the probability of infection for the better quality of seedlings. In this study, a cutting-point positioning system was proposed for the automatic cutting of phalaenopsis seedlings using a visual servo. The elastic cutting end was also designed using the fitting straight line for the structural characteristics of seedlings. The seedling cutting system was mainly composed of the seedling visual detection, cutting coordinate positioning, and seedling cutting execution modules. Specifically, the seedlings were firstly photographed with an industrial camera, and then the images were transmitted and saved to the core computing unit. Shuffle Net v2 - YOLOv5 model was used for the target detection of the collected images, in order to realize the accurate detection of the seedling stem, blade, and black tuber. Secondly, the saved image was identified to evaluate the feasibility of cutting performance. The image data was then extracted from the detection frame, where the image contour in the frame was extracted to fill the maximum connected region. The stem straight-line fitting with the distance correction was used to make the connected region pixels near the black tuber position closer to the cutting center. Thirdly, the cutting-point positioning was implemented to verify the resulting data using geometric profiles. Finally, the cutting coordinate was transmitted to the cutting actuator for the cutting operation. The cutting-end design fully considered the characteristics of phalaenopsis seedlings and the cutting environment of tissue culture seedlings. The structure reduced the impact force of cutting tools when performing the cutting tasks. As such, a stable and effective operation was achieved at the cutting end for the rapid replacement of sterile consumables. A user interface was also designed to cooperate with the cutting system for the phalaenopsis seedling cutting, including the display of target detection and cutting coordinates, as well as the cutting control modules. Various components of the seedling were monitored to predict the parameters of the manipulator at each joint, particularly for the end speed over the control area. A target detection experiment was conducted to compare the Faster-RCNN, YOLOv4, YOLOv5, and MobileNet v2-YOLOv5 detection models. ShuffleNet v2-YOLOv5 model presented a higher detection accuracy of 96.7%, a weight file size 1.3 MB, and an average detection time of 0.026 s, suitable for seedling image detection. In the seedling cutting test, the cutting qualified rate was higher than 86% than before, and the average cutting time per plant was less than 18 s. The finding can lay the foundation for the phalaenopsis seedling cutting system with two-arm cooperation.
- target detection /
- deep learning /
- visual servoing /
- phalaenopsis seedlings /
- cutting point positioning /
- cutting system

HTML全文

参考文献(29)

[1]	Li C, Dong N, Zhao Y M, et al. A review for the breeding of orchids: Current achievements and prospects[J]. Horticultural Plant Journal, 2021, 7(5): 380-392.
[2]	Gallo F R, Souza L A, Milaneze-Gutierre M A, et al. Seed structure and in vitro seedling development of certain Laeliinae species (Orchidaceae)[J]. Revista Mexicana de Biodiversidad, 2016, 87(1): 68-73.
[3]	Chang Y W, Hsiao Y K, Ko C C, et al. A Grading System of Pot-Phalaenopsis Orchid Using YOLO-V3 Deep Learning Model[C]//International Conference on Network-Based Information Systems. Springer, Cham, 2020: 498-507.
[4]	任桂萍，王小菁，朱根发. 不同光质的LED对蝴蝶兰组织培养增殖及生根的影响[J]. 植物学报，2016，51(1)：81-88.Ren Guiping, Wang Xiaojing, Zhu Genfa. Effect of LED in different light qualities on growth of Phalaenopsis plantlets[J]. Chinese Bulletin of Botany, 2016, 51(1): 81-88. (in Chinese with English abstract)
[5]	张彦妮，边红琳，陈立新. 蝴蝶兰幼嫩花梗组织培养和快速繁殖[J]. 草业科学，2011，28(4)：590-596.Zhang Yanni, Bian Honglin, Chen Lixin. Tissue culture and rapid propagation of pedicels of early flowering Phalaenopsis amabilis[J]. Pratacultural Science, 2011, 28(4): 590-596 (in Chinese with English abstract)
[6]	Li X, Ding Q, Sun J Q. Remaining useful life estimation in prognostics using deep convolution neural networks[J]. Reliability Engineering & System Safety, 2018, 172: 1-11.
[7]	郭瑞，于翀宇，贺红，等. 采用改进YOLOv4算法的大豆单株豆荚数检测方法[J]. 农业工程学报，2021，37(18)：179-187.Guo Rui, Yu Chongyu, He Hong, et al. Detection method of soybean pod number per plant using improved YOLOv4 algorithm[J]. Transactions of the Chinese Society of Agricultural Engineering (Transactions of the CSAE), 2021, 37(18): 179-187. (in Chinese with English abstract)
[8]	贾伟宽，孟虎，马晓慧，等. 基于优化Transformer网络的绿色目标果实高效检测模型[J]. 农业工程学报，2021，37(14)：163-170.Jia Weikuan, Meng Hu, Ma Xiaohui, et al. Efficient detection model of green target fruit based on optimized Transformer network[J]. Transactions of the Chinese Society of Agricultural Engineering (Transactions of the CSAE), 2021, 37(14): 163-170. (in Chinese with English abstract)
[9]	Zahid A, Mahmud M S, He Long, et al. Technological advancements towards developing a robotic pruner for apple trees: A review[J]. Computers and Electronics in Agriculture, 2021, 189: 106383.
[10]	Quan L Z, Feng H Q, Lv Y J, et al. Maize seedling detection under different growth stages and complex field environments based on an improved faster R-CNN[J]. Biosystems Engineering, 2019, 184: 1-23.
[11]	Wu D H, Lv S C, Jiang M, et al. Using channel pruning-based YOLO v4 deep learning algorithm for the real-time and accurate detection of apple flowers in natural environments[J]. Computers and Electronics in Agriculture, 2020, 178: 105742.
[12]	杨柯，胡志超，于昭洋，等. 基于深度学习目标测定的大蒜收获切根装置设计与试验[J]. 农业机械学报，2022，53(1)：123-132.Yang Ke, Hu Zhichao, Yu Zhaoyang, et al. Design and experiment of garlic harvesting and cutting root device based on deep learning target determination[J]. Transactions of the Chinese Society for Agricultural Machinery, 2022, 53(1): 123-132 (in Chinese with English abstract)
[13]	郑太雄，江明哲，冯明驰. 基于视觉的采摘机器人目标识别与定位方法研究综述[J]. 仪器仪表学报，2021，42(9)：28-51.Zheng Taixiong, Jiang Mingzhe, Feng Mingchi. Vision based target recognition and location for picking robot: A review[J]. Transactions of the Chinese Society for Agricultural Machinery, 2021, 42(9): 28-51. (in Chinese with English abstract)
[14]	李涛，邱权，赵春江，等. 矮化密植果园多臂采摘机器人任务规划[J]. 农业工程学报，2021，37(2)：1-10.Li Tao, Qiu Quan, Zhao Chunjiang, et al. Task planning of multi-arm harvesting robots for high-density dwarf orchards[J]. Transactions of the Chinese Society of Agricultural Engineering (Transactions of the CSAE), 2021, 37(2): 1-10. (in Chinese with English abstract)
[15]	陈飞，葛云，张立新，等. 红花采摘机器人集条预定位机构设计与试验[J]. 农业工程学报，2021，37(15)：10-19.Chen Fei, Ge Yun, Zhang Lixin, et al. Design and experiment of the strip-collected pre-positioning mechanism for safflower picking robots[J]. Transactions of the Chinese Society of Agricultural Engineering (Transactions of the CSAE), 2021, 37(15): 10-19. (in Chinese with English abstract)
[16]	李国进，黄晓洁，李修华，等. 采用轻量级网络MobileNetV2的酿酒葡萄检测模型[J]. 农业工程学报，2021，37(17)：168-176.Li Guojin, Huang Xiaojie, Li Xiuhua, et al. Detection model for wine grapes using MobileNetV2 lightweight network[J]. Transactions of the Chinese Society of Agricultural Engineering (Transactions of the CSAE), 2021, 37(17): 168-176. (in Chinese with English abstract)
[17]	宁政通，罗陆锋，廖嘉欣，等. 基于深度学习的葡萄果梗识别与最优采摘定位[J]. 农业工程学报，2021，37(9)：222-229.Ning Zhengtong, Luo Lufeng, Liao Jiaxin, et al. Recognition and the optimal picking point location of grape stems based on deep learning[J]. Transactions of the Chinese Society of Agricultural Engineering (Transactions of the CSAE), 2021, 37(9): 222-229. (in Chinese with English abstract)
[18]	赵德安，吴任迪，刘晓洋，等. 基于YOLO深度卷积神经网络的复杂背景下机器人采摘苹果定位[J]. 农业工程学报，2019，35(3)：164-173.Zhao Dean, Wu Rendi, Liu Xiaoyang, et al. Apple positioning based on YOLO deep convolutional neural network for picking robot in complex background[J]. Transactions of the Chinese Society of Agricultural Engineering (Transactions of the CSAE), 2019, 35(3): 164-173. (in Chinese with English abstract)
[19]	Ren S, He K, Girshick R, et al. Faster R-CNN: Towards real-time object detection with region proposal networks[C]//Advances in Neural Information Processing Systems, 2015, 28: 91-99.
[20]	Cai Z, Vasconcelos N. Cascade R-CNN: Delving into high quality object detection[C]//Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, 2018: 6154-6162.
[21]	Dai J, Li Y, He K, et al. R-FCN: Object detection via region-based fully convolutional networks[C]//Advances in Neural Information Processing Systems, 2016: 379-387.
[22]	Zhu Y, Zhao C, Wang J, et al. CoupleNet: Coupling global structure with local parts for object detection[C]//Proceedings of the IEEE International Conference on Computer Vision, 2017: 4126-4134.
[23]	Ma N, Zhang X, Zheng H T, et al. Shufflenet v2: Practical guidelines for efficient cnn architecture design[C]//Proceedings of the European Conference on Computer Vision (ECCV). 2018: 116-131.
[24]	Peter J. Rousseeuw, Sabine V. Robust estimation in very small samples[J]. Computational Statistics and Data Analysis, 2002, 40(4): 741-758.
[25]	崔海华，漏华铖，田威，等. 轨道式爬行机器人制孔基准的视觉高精度定位[J]. 光学学报，2021，41(9)：179-188.Cui Haihua, Lou Huacheng, Tian Wei, et al. High-precision visual positioning of hole-making datum for orbital crawling robot[J]. Acta Optica Sinica, 2021, 41(9): 179-188. (in Chinese with English abstract)
[26]	郭丽，索素敏，徐明辉. 组织培养中不同消毒处理对野生薄皮木种子萌发的影响[J]. 分子植物育种：2022，20(4)：1325-1330.Guo Li, Suo Sumin, Xu Minghui. Effects of different disinfection treatments on seed germination of wild leptodermis oblonga bge. in tissue culture[J]. Molecular Plant Breeding, 2022, 20(4): 1325-1330. (in Chinese with English abstract)
[27]	黄歆怡，谢振兴，陆祖正，等. 罗氏蝴蝶兰的无菌播种与快速繁殖[J]. 植物生理学报，2020，56(4)：693-699.Huang Xinyi, Xie Zhenxing, Lu Zuzheng, et al. Aseptic seeding and rapid propagation of Phalaenopsis lobbi[J]. Plant Physiology Journal, 2020, 56(4): 693-699. (in Chinese with English abstract)
[28]	Bochkovskiy A, Wang C Y, Liao H Y M. Yolov4: Optimal speed and accuracy of object detection[J]. arXiv preprint arXiv: 2004. 10934, 2020.
[29]	湖北省质量技术监督局. 蝴蝶兰组培苗工厂化生产技术规程：DB42/T 1448-2018[S]. 武汉：湖北省农业科学院，2018.

施引文献(9)

期刊类型引用(6)

1.	袁庆霓，齐建友，虞宏建. 基于深度强化学习的机械臂视觉伺服智能控制. 计算机集成制造系统. 2025(03): 998-1013 . 百度学术
2.	李艳冬，李运兴，殷益明，赵根，张飞雪，史星雲. 基于主成分分析蝴蝶兰质量评价模型建立. 北方园艺. 2024(06): 61-68 . 百度学术
3.	苑朝，张鑫，王家豪，赵明雪，徐大伟. 基于显著性特征的蝴蝶兰组培苗夹取点检测方法. 农业工程学报. 2023(13): 151-159 . 本站查看
4.	肖哲非，马田田，张军文，李彦龙，沈建. 基于深度学习的高压水鱼片切段装置控制系统设计. 渔业现代化. 2023(05): 79-89 . 百度学术
5.	翟永杰，王家豪，张鑫，胡东阳，王乾铭，徐大伟，刘亚军. 基于语义分割视觉伺服的种苗自动夹取系统设计. 智能系统学报. 2023(06): 1259-1267 . 百度学术
6.	周馨曌，吴烽云，邹湘军，蒙贺伟，张芸齐，罗锡文. 基于多目标识别的葡萄果串采摘点定位方法. 农业工程学报. 2023(22): 166-177 . 本站查看