基于改进YOLOv5的皮革抓取点识别及定位

doi:10.19677/j.issn.1004-7964.2024.01.005

皮革科学与工程 ›› 2024, Vol. 34 ›› Issue (1): 32-40.doi: 10.19677/j.issn.1004-7964.2024.01.005

基于改进YOLOv5的皮革抓取点识别及定位

金光, 任工昌^*, 桓源, 洪杰

陕西科技大学机电工程学院,陕西西安 710021

收稿日期:2023-06-09 修回日期:2023-07-08 接受日期:2023-07-12 出版日期:2024-02-01 上线日期:2024-01-08
通讯作者: *任工昌（1962-）,男,二级教授,博士生导师,主要研究方向为产品创新理论,机器人创新设计。E-mail：rengc@sust.edu.cn。
作者简介:金光（1996-）,男,硕士研究生,主要研究方向为机器视觉,深度学习。E-mail：862922896@qq.com。
基金资助:
陕西省重点研发计划资助项目（2022GY-250）; 西安市科技计划项目（23ZDCYJSGG0016-2022）

Grab Point Identification and Localization of Leather based on Improved YOLOv5

JIN Guang, REN Gongchang^*, HUAN Yuan, HONG Jie

College of Mechanical and Electrical Engineering, Shaanxi University of Science and Technology, Xi'an 710021, China

Received:2023-06-09 Revised:2023-07-08 Accepted:2023-07-12 Published:2024-02-01 Online:2024-01-08

摘要/Abstract

摘要： 为实现机器人对皮革抓取点的精确定位,文章通过改进YOLOv5算法,引入coordinate attention注意力机制到Backbone层中,用Focal-EIOU Loss对CIOU Loss进行替换来设置不同梯度,从而实现了对皮革抓取点快速精准的识别和定位。利用目标边界框回归公式获取皮革抓点的定位坐标,经过坐标系转换获得待抓取点的三维坐标,采用Intel RealSense D435i深度相机对皮革抓取点进行定位实验。实验结果表明：与Faster R-CNN算法和原始YOLOv5算法对比,识别实验中改进YOLOv5算法的准确率分别提升了6.9%和2.63%,召回率分别提升了8.39%和2.63%,mAP分别提升了8.13%和0.21%;定位实验中改进YOLOv5算法的误差平均值分别下降了0.033 m和0.007 m,误差比平均值分别下降了2.233%和0.476%。

关键词: 皮革, 抓取点定位, 机器视觉, YOLOv5, CA注意力机制

Abstract: In order to achieve precise localization of leather grasping points by robots, this study proposed an improved approach based on the YOLOv5 algorithm. The methodology involved the integration of the coordinate attention mechanism into the Backbone layer and the replacement of the CIOU Loss with the Focal-EIOU Loss to enable different gradients and enhance the rapid and accurate recognition and localization of leather grasping points. The positioning coordinates of the leather grasping points were obtained by using the target bounding box regression formula, followed by the coordinate system conversion to obtain the three-dimensional coordinates of the target grasping points. The experimental positioning of leather grasping points was conducted by using the Intel RealSense D435i depth camera. Experimental results demonstrate the significant improvements over the Faster R-CNN algorithm and the original YOLOv5 algorithm. The improved YOLOv5 algorithm exhibited an accuracy enhancement of 6.9% and 2.63%, a recall improvement of 8.39% and 2.63%, and an mAP improvement of 8.13% and 0.21% in recognition experiments, respectively. Similarly, in the positioning experiments, the improved YOLOv5 algorithm demonstrated a decrease in average error values of 0.033m and 0.007m, and a decrease in error ratio average values of 2.233% and 0.476%.

Key words: leather, grab point positioning, machine vision, YOLOv5, coordinate attention

中图分类号:

TP391

金光, 任工昌, 桓源, 洪杰. 基于改进YOLOv5的皮革抓取点识别及定位[J]. 皮革科学与工程, 2024, 34(1): 32-40.

JIN Guang, REN Gongchang, HUAN Yuan, HONG Jie. Grab Point Identification and Localization of Leather based on Improved YOLOv5[J]. Leather Science and Engineering, 2024, 34(1): 32-40.

参考文献

[1] 马军. 我国皮革产品出口现状及竞争力分析[J].中国皮革,2023,52(5):1-3.
MA J.Export situation and competitiveness of chineseleather products[J].China Leather,2023,52(5):1-3.(in Chinese)
[2] Huan Y,Ren G C,Su X Y,et al.A versatile end effector for grabbing and spreading of flaky deformableobject manipulation[J].Mechanical Sciences,2023,14(1):111-123.
[3] 刘书磊,任工昌,桓源,等.双臂拉伸铺展皮革的方法设计与算法实现[J].皮革科学与程,2023,33(1):21-25.
LIU S L,REN G C,HUAN Y,et al.Method design and algorithm realization of stretching leather with two arms[J].Leather Sci and Eng,2023,33(1):21-25.(in Chinese)
[4] Onoro-Rubio D,Lopez-Sastre R J.Towards perspective-free object counting with deep learning[C].Amsterdam:European Conference on Computer Vision,2016:615-629.
[5] XU M,GE Z,JIANG X,et al.Depth information guided crowd counting for complex crowd scenes[J].Pattern Recognition Letters,2019,125:563-569.
[6] CHEN S W,Shivakumar S S,Dcunha S,et al.Counting apples and oranges with deep learning:a data-driven approach[J].IEEE Robotics and Automation Letters,2017,2(2):781-788.
[7] Girshick R.Fast R-CNN[C].Santiago:Proceedings of the IEEE International Conference on Computer Vision,2015:1440-1448.
[8] Ren S,He K,Girshick R,et al.Faster R-CNN:Towards real-time object detection with region proposal networks[J].Advances in Neural Information Processing Systems,2015,28:91-99.
[9] Li J,Liang X,Shen S,et al.Scale-aware Fast r-cnn for pedestrian etection[J].IEEE Transactions on Multimedia,2017,20(4):985-996.
[10] Liu W,Anguelov D,Erhan D,et al.SSD:Single shot multibox detector[C].Cham:European Conference on Computer Vision.Springer.2016:21-37.
[11] Womg A,Shafiee Mohammad J,Li F,et al.Tiny SSD:A tiny single-shot detection deep convolutional neural network for real-time embedded object detection[C].Toronto:2018 15th Conference on Computer and Robot Vision(CRV),2018:95-101.
[12] Wang X,Hua X,Xiao F,et al.Multi-object detection in traffic scenes based on improved SSD[J].Electronics,2018,7(11):302.
[13] Zhai S,Shang D,Wang S,et al.DF-SSD:An improved SSD object detection algorithm based on DenseNet and feature fusion[J].IEEE Access,2020,8:24344-24357.
[14] Redmon J,Divvala S,Girshick R,et al.You only look once:Unified,real-time object detection[C].Las Vegas:Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition,2016:779-788.
[15] Redmon J,Farhadi A.YOLO9000:better,faster,stronger[C].Honolulu:Proceedings of the IEEE Conferenceon Computer Vision and Pattern Recognition,2017:6517-6525.
[16] Redmon J,Farhadi A.YOLOv3:An incremental improvement[EB/OL].(2018-04-08)[2022-08-12].https://arxiv.org/abs/1804.02767.
[17] Alexey B,Wang C,Liao H.YOLOv4:Optimal speed and accuracy of object detection[EB/OL].(2020-04-23)[2022-08- 12].https://arxiv.org/abs/2004.10934.
[18] 段洁利,王昭锐,邹湘军,等.采用改进YOLOv5的蕉穗识别及其底部果轴定位[J].农业工程学报,2022,38(19):122-130.
DUAN J L,WANG Z R,ZOU X J,et al.Recognition ofbananas to locate bottom fruit axis using improved YOLOv5[J].Transactions of the Chinese Society of Agricultural Engineering,2022,38(19):122-130.(in Chinese)
[19] 杨秋妹,陈淼彬,黄一桂,等.基于改进YOLOv5n的猪只盘点算法[J].农业机械学报,2023,54(1):251-262.
YANG Q M,CHEN M B,HUANG Y G,et al.Pig counting algorithm based on improved YOLO v5n[J].Transactions of the Chinese Society for Agricultural Machinery,2023,54(1):251-262.(in Chinese)
[20] Fu L,Yang Z,Wu F,et al.YOLO-Banana:A lightweight neural network for rapid detection of banana bunches and stalks in the natural environment[J].Agronomy,2022,12(2):391.
[21] 祁宣豪,智敏.图像处理中注意力机制综述[J].计算机科学与探索,2023:1-20.
QI X H,ZHI M.A Review of Attention mechanisms in image processing[J].Journal of Frontiers of Computer Science&Technology,2023:1-20.(in Chinese)
[22] Hou Q,Zhou D,Feng J.Coordinate attention for efficient mobile network design[EB/OL].(2021-03-04)[2022-08-12].https://arxiv.org/abs/2103.02907.
[23] Zhang Y,Ren W,Zhang Z,et al.Focal and efficient IOU loss for accurate bounding box regression[EB/OL].(2022-07-16)[2022-08-12].https://arxiv.org/abs/2101.08158.
[24] Elfwing S,Uchibe E,Doya K.Sigmoid-weighted linear units for neural network function approximation in reinforcement learning[J].Neural Networks,2017,107:3-11.

基于改进YOLOv5的皮革抓取点识别及定位

Grab Point Identification and Localization of Leather based on Improved YOLOv5

PDF

可视化

摘要/Abstract

引用本文

使用本文

参考文献

相关文章 15

编辑推荐

Metrics

本文评价

[1]	李昊, 吴承承, 王志新, 王亚平, 廖学品, 石碧. 钆-钡/天然皮革复合可穿戴X射线屏蔽材料的制备及性能[J]. 皮革科学与工程, 2024, 34(3): 9-16.
[2]	王宁, 周雷, 章宦胜, 胡秀红, 苗洁. 超高效液相色谱-串联质谱法测定皮革中9种双酚类物质[J]. 皮革科学与工程, 2024, 34(3): 58-65.
[3]	唐亚娜, 王巍. 羌族挑花刺绣图案在皮革服装中的应用研究[J]. 皮革科学与工程, 2024, 34(3): 101-107.
[4]	何秀, 张金伟, 周建飞, 曾运航, 张春晓, 税科林, 程海明. 《皮革生产实习》课程思政元素的融入设计与实践[J]. 皮革科学与工程, 2024, 34(3): 119-124.
[5]	王嘉瑞, 马宏瑞, 高骏驰, 郝永永, 朱超. 制革不同工段皮革碎料中铬的稳定性研究[J]. 皮革科学与工程, 2024, 34(2): 7-13.
[6]	吕斌, 张翎钰, 石传晋, 高党鸽, 马建中. 微乳液皮革脱脂剂的制备及性能研究[J]. 皮革科学与工程, 2024, 34(2): 14-21.
[7]	赵嘉敏, 马建中, 周永香. 层状复合氢氧化物在制革工业中的应用探讨[J]. 皮革科学与工程, 2024, 34(2): 37-46.
[8]	郑好, 吴晶, 吴芳, 刘文庆. 七巧板原理在可拆卸式皮革包袋造型设计中的应用[J]. 皮革科学与工程, 2024, 34(2): 77-83.
[9]	曾钦宇, 孟凯宁, 王媛麟. 人工智能语境下的皮革制品设计路径研究[J]. 皮革科学与工程, 2024, 34(2): 91-98.
[10]	陈伟长, 柳周青. 家居摆设的皮革材料工艺技法与中国风的审美关系探讨[J]. 皮革科学与工程, 2024, 34(2): 99-105.
[11]	陈晓芬, 董宏坤. 杭州市皮革产业的发展、挑战和应对策略研究（2019~2022）[J]. 皮革科学与工程, 2024, 34(2): 106-110.
[12]	何秀, 张金伟, 周建飞, 曾运航, 张春晓, 税科林, 程海明. 《皮革生产实习》线上线下混合式教学模式探索与实践[J]. 皮革科学与工程, 2024, 34(2): 111-116.
[13]	谢辉, 戴玲. 皮革供应商要素品牌营销策略研究[J]. 皮革科学与工程, 2024, 34(2): 117-122.
[14]	韩明真, 江卓成, 谢果, 曾运航, 王亚楠. 鞣制过程中皮革在转鼓内的形变特征及受力分析[J]. 皮革科学与工程, 2024, 34(1): 1-7.
[15]	任可帅, 桑军, 步巧巧, 周建飞, 林炜. 皮革领域“双碳”标准体系的构建研究[J]. 皮革科学与工程, 2024, 34(1): 41-46.