• 文献检索
  • 文档翻译
  • 深度研究
  • 学术资讯
  • Suppr Zotero 插件Zotero 插件
  • 邀请有礼
  • 套餐&价格
  • 历史记录
应用&插件
Suppr Zotero 插件Zotero 插件浏览器插件Mac 客户端Windows 客户端微信小程序
定价
高级版会员购买积分包购买API积分包
服务
文献检索文档翻译深度研究API 文档MCP 服务
关于我们
关于 Suppr公司介绍联系我们用户协议隐私条款
关注我们

Suppr 超能文献

核心技术专利：CN118964589B侵权必究
粤ICP备2023148730 号-1Suppr @ 2026

文献检索

告别复杂PubMed语法，用中文像聊天一样搜索，搜遍4000万医学文献。AI智能推荐，让科研检索更轻松。

立即免费搜索

文件翻译

保留排版，准确专业，支持PDF/Word/PPT等文件格式，支持 12+语言互译。

免费翻译文档

深度研究

AI帮你快速写综述，25分钟生成高质量综述，智能提取关键信息，辅助科研写作。

立即免费体验

基于传统视觉与人工智能视觉的高速移动快递包裹位置校正算法研究

Research on the Algorithm of Position Correction for High-Speed Moving Express Packages Based on Traditional Vision and AI Vision.

作者信息

Dai Ning, Lu Zhehao, Chen Jingchao, Xu Kaixin, Hu Xudong, Yuan Yanhong

机构信息

Key Laboratory of Modern Textile Machinery & Technology of Zhejiang Province, Zhejiang Sci-Tech University, Hangzhou 310018, China.

出版信息

Sensors (Basel). 2024 Jan 30;24(3):892. doi: 10.3390/s24030892.

DOI:10.3390/s24030892
PMID:38339609
原文链接:https://pmc.ncbi.nlm.nih.gov/articles/PMC10857253/
Abstract

The rapid development of the logistics industry poses significant challenges to the sorting work within this sector. The fast and precise identification of moving express parcels holds immense significance for the performance of logistics sorting systems. This paper proposes a motion express parcel positioning algorithm that combines traditional vision and AI-based vision. In the traditional vision aspect, we employ a brightness-based traditional visual parcel detection algorithm. In the AI vision aspect, we introduce a Convolutional Block Attention Module (CBAM) and Focal-EIoU to enhance YOLOv5, improving the model's recall rate and robustness. Additionally, we adopt an Optimal Transport Assignment (OTA) label assignment strategy to provide a training dataset based on global optimality for the model training phase. Our experimental results demonstrate that our modified AI model surpasses traditional algorithms in both parcel recognition accuracy and inference speed. The combined approach of traditional vision and AI vision in the motion express parcel positioning algorithm proves applicable for practical logistics sorting systems.

摘要

物流行业的快速发展给该行业内的分拣工作带来了重大挑战。快速、精确地识别移动中的快递包裹对于物流分拣系统的性能具有极其重要的意义。本文提出了一种将传统视觉与基于人工智能的视觉相结合的运动快递包裹定位算法。在传统视觉方面，我们采用基于亮度的传统视觉包裹检测算法。在人工智能视觉方面，我们引入卷积块注意力模块（CBAM）和焦点-交并比（Focal-EIoU）来增强YOLOv5，提高模型的召回率和鲁棒性。此外，我们采用最优传输分配（OTA）标签分配策略，为模型训练阶段提供基于全局最优性的训练数据集。我们的实验结果表明，我们改进后的人工智能模型在包裹识别准确率和推理速度方面均超过传统算法。运动快递包裹定位算法中传统视觉与人工智能视觉相结合的方法被证明适用于实际的物流分拣系统。

https://cdn.ncbi.nlm.nih.gov/pmc/blobs/e254/10857253/ef22f48959d6/sensors-24-00892-g014.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/e254/10857253/02c13ac0aae6/sensors-24-00892-g001.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/e254/10857253/536a7ce6372f/sensors-24-00892-g002.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/e254/10857253/2ed817d5f92a/sensors-24-00892-g003.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/e254/10857253/3cde8fe3216a/sensors-24-00892-g004.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/e254/10857253/c8b68bbb3841/sensors-24-00892-g005.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/e254/10857253/f2e5f23882cf/sensors-24-00892-g006.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/e254/10857253/3ef0b5894ebb/sensors-24-00892-g007.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/e254/10857253/bce1727ddfa8/sensors-24-00892-g008.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/e254/10857253/dee82fbf10b8/sensors-24-00892-g009.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/e254/10857253/c8ce563eb1dd/sensors-24-00892-g010a.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/e254/10857253/d4500b48bca0/sensors-24-00892-g011.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/e254/10857253/3ea9adbb3bc1/sensors-24-00892-g012.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/e254/10857253/135940ae9e26/sensors-24-00892-g013.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/e254/10857253/ef22f48959d6/sensors-24-00892-g014.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/e254/10857253/02c13ac0aae6/sensors-24-00892-g001.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/e254/10857253/536a7ce6372f/sensors-24-00892-g002.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/e254/10857253/2ed817d5f92a/sensors-24-00892-g003.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/e254/10857253/3cde8fe3216a/sensors-24-00892-g004.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/e254/10857253/c8b68bbb3841/sensors-24-00892-g005.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/e254/10857253/f2e5f23882cf/sensors-24-00892-g006.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/e254/10857253/3ef0b5894ebb/sensors-24-00892-g007.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/e254/10857253/bce1727ddfa8/sensors-24-00892-g008.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/e254/10857253/dee82fbf10b8/sensors-24-00892-g009.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/e254/10857253/c8ce563eb1dd/sensors-24-00892-g010a.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/e254/10857253/d4500b48bca0/sensors-24-00892-g011.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/e254/10857253/3ea9adbb3bc1/sensors-24-00892-g012.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/e254/10857253/135940ae9e26/sensors-24-00892-g013.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/e254/10857253/ef22f48959d6/sensors-24-00892-g014.jpg

相似文献

1
Research on the Algorithm of Position Correction for High-Speed Moving Express Packages Based on Traditional Vision and AI Vision.基于传统视觉与人工智能视觉的高速移动快递包裹位置校正算法研究
Sensors (Basel). 2024 Jan 30;24(3):892. doi: 10.3390/s24030892.
2
Research on high-speed classification and location algorithm for logistics parcels based on a monocular camera.基于单目相机的物流包裹高速分类与定位算法研究
Sci Rep. 2024 Jul 10;14(1):15901. doi: 10.1038/s41598-024-66941-x.
3
Research on an Algorithm of Express Parcel Sorting Based on Deeper Learning and Multi-Information Recognition.基于深度学习和多信息识别的快递分拣算法研究。
Sensors (Basel). 2022 Sep 5;22(17):6705. doi: 10.3390/s22176705.
4
YOLOv5-KCB: A New Method for Individual Pig Detection Using Optimized K-Means, CA Attention Mechanism and a Bi-Directional Feature Pyramid Network.YOLOv5-KCB：一种使用优化 K-Means、CA 注意力机制和双向特征金字塔网络的个体猪检测新方法。
Sensors (Basel). 2023 May 31;23(11):5242. doi: 10.3390/s23115242.
5
CAM-YOLO: tomato detection and classification based on improved YOLOv5 using combining attention mechanism.CAM-YOLO：基于改进的YOLOv5并结合注意力机制的番茄检测与分类
PeerJ Comput Sci. 2023 Jul 20;9:e1463. doi: 10.7717/peerj-cs.1463. eCollection 2023.
6
Recognition of terminal buds of densely-planted Chinese fir seedlings using improved YOLOv5 by integrating attention mechanism.基于注意力机制改进YOLOv5对密植杉木幼苗顶芽的识别
Front Plant Sci. 2022 Oct 10;13:991929. doi: 10.3389/fpls.2022.991929. eCollection 2022.
7
YOLOv5-MS: Real-Time Multi-Surveillance Pedestrian Target Detection Model for Smart Cities.YOLOv5-MS：用于智慧城市的实时多监控行人目标检测模型
Biomimetics (Basel). 2023 Oct 9;8(6):480. doi: 10.3390/biomimetics8060480.
8
Surface defect detection of steel based on improved YOLOv5 algorithm.基于改进YOLOv5算法的钢材表面缺陷检测
Math Biosci Eng. 2023 Nov 1;20(11):19858-19870. doi: 10.3934/mbe.2023879.
9
Green Citrus Detection and Counting in Orchards Based on YOLOv5-CS and AI Edge System.基于 YOLOv5-CS 和 AI 边缘系统的果园青桔检测与计数。
Sensors (Basel). 2022 Jan 12;22(2):576. doi: 10.3390/s22020576.
10
Visual Sorting of Express Parcels Based on Multi-Task Deep Learning.基于多任务深度学习的快递包裹可视化分拣。
Sensors (Basel). 2020 Nov 27;20(23):6785. doi: 10.3390/s20236785.

引用本文的文献

1
Research on dimension measurement algorithm for parcel boxes in high-speed sorting system.高速分拣系统中包裹箱尺寸测量算法研究
Sci Rep. 2025 Jul 1;15(1):21980. doi: 10.1038/s41598-025-07730-y.

本文引用的文献

1
Research on an Algorithm of Express Parcel Sorting Based on Deeper Learning and Multi-Information Recognition.基于深度学习和多信息识别的快递分拣算法研究。
Sensors (Basel). 2022 Sep 5;22(17):6705. doi: 10.3390/s22176705.
2
Visual Sorting of Express Parcels Based on Multi-Task Deep Learning.基于多任务深度学习的快递包裹可视化分拣。
Sensors (Basel). 2020 Nov 27;20(23):6785. doi: 10.3390/s20236785.
3
Faster R-CNN: Towards Real-Time Object Detection with Region Proposal Networks.更快的 R-CNN：基于区域建议网络的实时目标检测。
IEEE Trans Pattern Anal Mach Intell. 2017 Jun;39(6):1137-1149. doi: 10.1109/TPAMI.2016.2577031. Epub 2016 Jun 6.