基于ROS和深度学习的杏鲍菇智能分选系统设计

doi:10.13733/j.jcam.issn.2095-5553.2023.08.013

摘要/Abstract

摘要： 为解决杏鲍菇人工分选耗时低效、准确率低的问题，提出一种基于深度学习的分级检测与抓取检测双模型并联的杏鲍菇智能分选方法和机器人智能分选系统。通过深度相机采集杏鲍菇图像，采用机器人作为分选执行器，基于ROS(Robot Operating System)应用python和C++语言设计开发智能分选控制软件，基于PyQt设计开发监控管理系统。测试结果表明：本分选系统可自动实现杏鲍菇的分级检测和机器人分选抓取，单只杏鲍菇分选检测用时18ms，分级检测平均准确率为88.35%，机器人抓取成功率为98.33%，智能分选成功率为88.35%，证实系统整体的可行性与有效性，为其他农产品智能分选系统的整体实现提供新的解决思路。

关键词: 杏鲍菇；智能分选；深度学习；机器人抓取；机器人操作系统, 农产品加工

Abstract: In order to solve the problem of timeconsuming, inefficiency and low accuracy of manual sorting of Pleurotus eryngii, this paper proposes an intelligent sorting method and robot intelligent sorting system for Pleurotus eryngii, which is dualmodel parallel method of grading detection and grasp detection based on deep learning. The depth camera is used to collect the images of Pleurotus eryngii, and the robot is used as the sorting actuator. The intelligent sorting control software is designed based on ROS (Robot Operating System), python and C++ language, and the monitoring and management system is designed based on PyQt. The test results show that the sorting system can automatically realize the grading detection of Pleurotus eryngii and the robot sorting and grasping. The sorting detection of single Pleurotus eryngii takes 18ms, and the average accuracy of grading detection is 88.35%, the success rate of robot grasping is 98.33%, and the success rate of intelligent sorting is 88.35%, which confirms the feasibility and effectiveness of the system as a whole. It provides a new solution for the whole realization of intelligent sorting system of other agricultural products.

Key words: Pleurotus eryngii, intelligent sorting, deep learning, robot grasping, ROS

中图分类号:

S5： TP274.5： TP391.4

孙松丽, 温宏愿, 刘宾龄, 钟锦扬, 毛政兴. 基于ROS和深度学习的杏鲍菇智能分选系统设计[J]. 中国农机化学报, 2023, 44(8): 95-102.

Sun Songli, Wen Hongyuan, Liu Binling, Zhong Jinyang, Mao Zhengxing. Design of intelligent sorting system of Pleurotus eryngii based on ROS and deep learning[J]. Journal of Chinese Agricultural Mechanization, 2023, 44(8): 95-102.

参考文献

［1］　邹何, 夏雪, 王粟萍, 等. 杏鲍菇相关研究进展及其产业开发现状［J］. 食品工业, 2019, 40(2): 276-283.
Zou He, Xia Xue, Wang Suping, et al. Research progress and industry development status of Pleurotus eryngii ［J］. The Food Industry, 2019, 40(2): 276-283.
［2］　侯鹏帅, 刘玉乐, 宋欣, 等. 基于智能视觉识别的冬枣分选检测系统设计［J］. 中国农机化学报, 2020, 41(3): 109-114.
Hou Pengshuai, Liu Yule, Song Xin, et al. Sorting and detecting system design of winter jujube based on intelligent vision recognition ［J］. Journal of Chinese Agricultural Mechanization, 2020, 41(3): 109-114.
［3］　邓立苗, 杜宏伟, 徐艳, 等. 基于机器视觉的马铃薯智能分选方法与实现［J］. 中国农机化学报, 2015, 36(5): 145-150.
Deng Limiao, Du Hongwei, Xu Yan, et al. Implementation of intelligent potato grading method based on vision ［J］. Journal of Chinese Agricultural Mechanization, 2015, 36(5): 145-150.
［4］　何进荣, 石延新, 刘斌, 等. 基于DXNet模型的富士苹果外部品质分级方法研究［J］. 农业机械学报, 2021, 52(7): 379-385.
He Jinrong, Shi Yanxin, Liu Bin, et al. External quality grading method of Fuji apple based on deep learning ［J］. Transactions of the Chinese Society of Agricultural Machinery, 2021, 52(7): 379-385.
［5］　王斌. 基于深度图像和深度学习的机器人抓取检测算法研究［D］. 杭州: 浙江大学, 2019.
Wang Bin. Research on robotic grasping detection based on depth image and deep learning ［D］. Hangzhou: Zhejiang University, 2019.
［6］　夏晶, 钱堃, 马旭东, 等. 基于级联卷积神经网络的机器人平面抓取位姿快速检测［J］. 机器人, 2018, 40(6): 795-802.
Xia Jing, Qian Kun, Ma Xudong, et al. Fast planar grasp pose detection for robot based on cascaded deep Convolutional Neural Networks ［J］. Robot, 2018, 40(6): 795-802.
［7］　Lenz I, Lee H, Saxena A. Deep learning for detecting robotic grasps ［J］. The International Journal of Robotics Research, 2015, 34(4-5): 705-724.
［8］　Pinto L, Gupta A. Supersizing selfsupervision: Learning to grasp from 50k tries and 700 robot hours ［C］. 2016 IEEE International Conference on Robotics and Automation (ICRA). IEEE, 2016: 3406-3413.
［9］　Mahler J, Liang J, Niyaz S, et al. Dexnet 2.0: Deep learning to plan robust grasps with synthetic point clouds and analytic grasp metrics ［J］. arXiv Preprint arXiv:1703.09312, 2017.
［10］　Zeng A, Song S, Yu K T, et al. Robotic pickandplace of novel objects in clutter with multiaffordance grasping and crossdomain image matching ［J］. The International Journal of Robotics Research, 2022, 41(7): 690-705.
［11］　Asif U, Tang J, Harrer S. GraspNet: An efficient convolutional neural network for realtime grasp detection for lowpowered devices ［C］. IJCAI， 2018, 7: 4875-4882.
［12］　Wang D, Liu C, Chang F, et al. Highperformance pixellevel grasp detection based on adaptive grasping and graspaware network ［J］. IEEE Transactions on Industrial Electronics, 2021, 69(11): 11611-11621.
［13］　夏晶. 基于RGB-D和深度学习的机器人抓取检测［D］. 南京: 东南大学, 2019.
Xia Jing. Deeplearningbased robot grasp detection using RGB-D sensor ［D］. Nanjing: Southeast University, 2019.
［14］　Redmon J, Divvala S, Girshick R, et al. You only look once: Unified, realtime object detection ［C］. Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, 2016: 779-788.
［15］　Liu Y, Lu B H, Peng J, et al. Research on the use of YOLOv5 object detection algorithm in mask wearing recognition ［J］. World Scientific Research Journal, 2020, 6(11): 276-284.
［16］　闫彬, 樊攀, 王美茸, 等. 基于改进YOLOv5m的采摘机器人苹果采摘方式实时识别［J］. 农业机械学报, 2022, 53(9): 28-38, 59.
Yan Bin, Fan Pan, Wang Meirong, et al. Realtime apple picking pattern recognition for picking robot based on improved YOLOv5m ［J］. Transactions of the Chinese Society of Agricultural Machinery, 2022, 53(9): 28-38, 59.
［17］　喻柏炜. 基于卷积神经网络YOLOv5模型的图表识别方法［D］. 南昌: 南昌大学, 2021.
Yu Bowei. Method of chart recognition based on convolutional neural network YOLOv5 model ［D］. Nanchang: Nanchang University, 2021.
［18］　Morrison D, Corke P, Leitner J. Learning robust, realtime, reactive robotic grasping ［J］. The International Journal of Robotics Research, 2020, 39(2-3): 183-201.

[1]	丁宏斌, 吴亮, 臧泽鹏, 徐彦瑞, 黄晓鹏, 吴劲锋. 籽瓜固形物微波真空干燥特性及其品质研究[J]. 中国农机化学报, 2023, 44(8): 88-94.
[2]	孙振刚, , 陈健, 屈佳蕾, 廖芷柔, 王婷婷, 闫国琦, . 化橘红干燥技术与设备研究现状及对策[J]. 中国农机化学报, 2023, 44(8): 110-117.
[3]	张骏;石研研;华树春;. 中国农产品加工业企业家才能的集聚与生产率测度——基于地理、行业与组织规模的协同效应[J]. 中国农机化学报, 2019, 40(7): 208-214.