• 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

在嵌入式系统上使用YOLO将无人机和地面机器人部署到智能物流中的技术要点。

Technical Aspects of Deploying UAV and Ground Robots for Intelligent Logistics Using YOLO on Embedded Systems.

作者信息

Dilmi Wissem, El Ferik Sami, Ouerdane Fethi, Khaldi Mustapha K, Saif Abdul-Wahid A

机构信息

Department of Control and Instrumentation Engineering, King Fahd University of Petroleum & Minerals, Dhahran 31261, Saudi Arabia.

Interdisciplinary Research Centre for Smart Mobility and Logistics (IRC-SML), King Fahd University of Petroleum & Minerals, Dhahran 31261, Saudi Arabia.

出版信息

Sensors (Basel). 2025 Apr 18;25(8):2572. doi: 10.3390/s25082572.

DOI:10.3390/s25082572
PMID:40285259
原文链接:https://pmc.ncbi.nlm.nih.gov/articles/PMC12031185/
Abstract

Automation of logistics enhances efficiency, reduces costs, and minimizes human error. Image processing-particularly vision-based AI-enables real-time tracking, object recognition, and intelligent decision-making, thereby improving supply chain resilience. This study addresses the challenge of deploying deep learning-based object detection on resource-constrained embedded platforms, such as NVIDIA Jetson devices on UAVs and ground robots, for real-time logistics applications. Specifically, we provide a comprehensive comparative analysis of YOLOv5 and YOLOv8, evaluating their performance in terms of inference speed, accuracy, and dataset-specific metrics using both the Common Objects in Context (COCO) dataset and a novel, custom logistics dataset tailored for aerial and ground-based logistics scenarios. A key contribution is the development of a user-friendly graphical user interface (GUI) for selective object visualization, enabling dynamic interaction and real-time filtering of detection results-significantly enhancing practical usability. Furthermore, we investigate and compare deployment strategies in both Python 3.9 and C# (ML. NET v3 and .NET Framework 7) environments, highlighting their respective impacts on performance and scalability. This research offers valuable insights and practical guidelines for optimizing real-time object detection deployment on embedded platforms in UAV- and ground robot-based logistics, with a focus on efficient resource utilization and enhanced operational effectiveness.

摘要

物流自动化可提高效率、降低成本并将人为错误降至最低。图像处理，尤其是基于视觉的人工智能，能够实现实时跟踪、目标识别和智能决策，从而提高供应链的弹性。本研究解决了在资源受限的嵌入式平台上部署基于深度学习的目标检测的挑战，例如用于无人机和地面机器人的NVIDIA Jetson设备，以实现实时物流应用。具体而言，我们对YOLOv5和YOLOv8进行了全面的比较分析，使用上下文常见物体（COCO）数据集以及为空中和地面物流场景量身定制的新颖自定义物流数据集，从推理速度、准确性和特定数据集指标方面评估它们的性能。一个关键贡献是开发了一个用户友好的图形用户界面（GUI）用于选择性目标可视化，实现动态交互和检测结果的实时过滤，显著提高了实际可用性。此外，我们研究并比较了在Python 3.9和C#（ML.NET v3和.NET Framework 7）环境中的部署策略，突出了它们对性能和可扩展性的各自影响。本研究为基于无人机和地面机器人的物流中嵌入式平台上的实时目标检测部署优化提供了有价值的见解和实用指南，重点在于高效的资源利用和增强的运营效果。

https://cdn.ncbi.nlm.nih.gov/pmc/blobs/1d14/12031185/2e2af1eb5467/sensors-25-02572-g018.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/1d14/12031185/6bbbee6ff52c/sensors-25-02572-g0A1.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/1d14/12031185/45a273c0e28d/sensors-25-02572-g001.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/1d14/12031185/0d68c186faf7/sensors-25-02572-g002.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/1d14/12031185/52610486aa58/sensors-25-02572-g003.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/1d14/12031185/2fbe2fd81954/sensors-25-02572-g004.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/1d14/12031185/3f29496eac25/sensors-25-02572-g005.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/1d14/12031185/f0940c5d2743/sensors-25-02572-g006.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/1d14/12031185/3dbac53016f4/sensors-25-02572-g007.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/1d14/12031185/80b5c416ba64/sensors-25-02572-g008.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/1d14/12031185/55205a4846de/sensors-25-02572-g009.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/1d14/12031185/180fa55bb24e/sensors-25-02572-g010.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/1d14/12031185/15455740b53c/sensors-25-02572-g011.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/1d14/12031185/6c698ea43b54/sensors-25-02572-g012.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/1d14/12031185/6ba559960027/sensors-25-02572-g013.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/1d14/12031185/4e6b23986a9a/sensors-25-02572-g014.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/1d14/12031185/08f5a22db127/sensors-25-02572-g015.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/1d14/12031185/eac66ea33ee4/sensors-25-02572-g016.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/1d14/12031185/6dbeef3163fd/sensors-25-02572-g017.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/1d14/12031185/2e2af1eb5467/sensors-25-02572-g018.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/1d14/12031185/6bbbee6ff52c/sensors-25-02572-g0A1.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/1d14/12031185/45a273c0e28d/sensors-25-02572-g001.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/1d14/12031185/0d68c186faf7/sensors-25-02572-g002.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/1d14/12031185/52610486aa58/sensors-25-02572-g003.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/1d14/12031185/2fbe2fd81954/sensors-25-02572-g004.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/1d14/12031185/3f29496eac25/sensors-25-02572-g005.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/1d14/12031185/f0940c5d2743/sensors-25-02572-g006.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/1d14/12031185/3dbac53016f4/sensors-25-02572-g007.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/1d14/12031185/80b5c416ba64/sensors-25-02572-g008.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/1d14/12031185/55205a4846de/sensors-25-02572-g009.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/1d14/12031185/180fa55bb24e/sensors-25-02572-g010.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/1d14/12031185/15455740b53c/sensors-25-02572-g011.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/1d14/12031185/6c698ea43b54/sensors-25-02572-g012.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/1d14/12031185/6ba559960027/sensors-25-02572-g013.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/1d14/12031185/4e6b23986a9a/sensors-25-02572-g014.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/1d14/12031185/08f5a22db127/sensors-25-02572-g015.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/1d14/12031185/eac66ea33ee4/sensors-25-02572-g016.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/1d14/12031185/6dbeef3163fd/sensors-25-02572-g017.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/1d14/12031185/2e2af1eb5467/sensors-25-02572-g018.jpg

相似文献

1
Technical Aspects of Deploying UAV and Ground Robots for Intelligent Logistics Using YOLO on Embedded Systems.在嵌入式系统上使用YOLO将无人机和地面机器人部署到智能物流中的技术要点。
Sensors (Basel). 2025 Apr 18;25(8):2572. doi: 10.3390/s25082572.
2
Automating container damage detection with the YOLO-NAS deep learning model.使用YOLO-NAS深度学习模型实现集装箱损坏检测自动化。
Sci Prog. 2025 Jan-Mar;108(1):368504251314084. doi: 10.1177/00368504251314084.
3
RFAG-YOLO: A Receptive Field Attention-Guided YOLO Network for Small-Object Detection in UAV Images.RFAG-YOLO：一种用于无人机图像中小目标检测的感受野注意力引导YOLO网络。
Sensors (Basel). 2025 Mar 30;25(7):2193. doi: 10.3390/s25072193.
4
Enhancing UAV Visual Landing Recognition with YOLO's Object Detection by Onboard Edge Computing.通过机载边缘计算利用YOLO目标检测增强无人机视觉着陆识别
Sensors (Basel). 2023 Nov 6;23(21):8999. doi: 10.3390/s23218999.
5
Framework for smartphone-based grape detection and vineyard management using UAV-trained AI.基于无人机训练的人工智能的智能手机葡萄检测与葡萄园管理框架。
Heliyon. 2025 Feb 6;11(4):e42525. doi: 10.1016/j.heliyon.2025.e42525. eCollection 2025 Feb 28.
6
Run Your 3D Object Detector on NVIDIA Jetson Platforms:A Benchmark Analysis.在 NVIDIA Jetson 平台上运行 3D 对象检测器：基准分析。
Sensors (Basel). 2023 Apr 15;23(8):4005. doi: 10.3390/s23084005.
7
Development of a deep learning-based surveillance system for forest fire detection and monitoring using UAV.基于深度学习的无人机森林火灾监测系统的开发。
PLoS One. 2024 Mar 12;19(3):e0299058. doi: 10.1371/journal.pone.0299058. eCollection 2024.
8
UAV-YOLOv8: A Small-Object-Detection Model Based on Improved YOLOv8 for UAV Aerial Photography Scenarios.无人机 - YOLOv8：一种基于改进YOLOv8的用于无人机航拍场景的小目标检测模型。
Sensors (Basel). 2023 Aug 15;23(16):7190. doi: 10.3390/s23167190.
9
Multimodal intelligent logistics robot combining 3D CNN, LSTM, and visual SLAM for path planning and control.结合3D卷积神经网络、长短期记忆网络和视觉同步定位与地图构建技术进行路径规划与控制的多模态智能物流机器人。
Front Neurorobot. 2023 Oct 16;17:1285673. doi: 10.3389/fnbot.2023.1285673. eCollection 2023.
10
A streamlined approach for intelligent ship object detection using EL-YOLO algorithm.一种使用EL-YOLO算法的智能船舶目标检测的简化方法。
Sci Rep. 2024 Jul 2;14(1):15254. doi: 10.1038/s41598-024-64225-y.

本文引用的文献

1
Lightweight UAV Landing Model Based on Visual Positioning.基于视觉定位的轻型无人机着陆模型
Sensors (Basel). 2025 Jan 31;25(3):884. doi: 10.3390/s25030884.
2
YOLO-APDM: Improved YOLOv8 for Road Target Detection in Infrared Images.YOLO-APDM：用于红外图像中道路目标检测的改进型YOLOv8
Sensors (Basel). 2024 Nov 10;24(22):7197. doi: 10.3390/s24227197.
3
Estimation of Strawberry Canopy Volume in Unmanned Aerial Vehicle RGB Imagery Using an Object Detection-Based Convolutional Neural Network.基于目标检测的卷积神经网络估算无人机 RGB 影像中草莓冠层体积。
Sensors (Basel). 2024 Oct 28;24(21):6920. doi: 10.3390/s24216920.
4
Modular YOLOv8 optimization for real-time UAV maritime rescue object detection.用于实时无人机海上救援目标检测的模块化YOLOv8优化
Sci Rep. 2024 Oct 18;14(1):24492. doi: 10.1038/s41598-024-75807-1.
5
Enhancing UAV Visual Landing Recognition with YOLO's Object Detection by Onboard Edge Computing.通过机载边缘计算利用YOLO目标检测增强无人机视觉着陆识别
Sensors (Basel). 2023 Nov 6;23(21):8999. doi: 10.3390/s23218999.
6
Research on the Recognition and Tracking of Group-Housed Pigs' Posture Based on Edge Computing.基于边缘计算的群养猪姿态识别与跟踪研究。
Sensors (Basel). 2023 Nov 3;23(21):8952. doi: 10.3390/s23218952.
7
Adaptation of YOLOv7 and YOLOv7_tiny for Soccer-Ball Multi-Detection with DeepSORT for Tracking by Semi-Supervised System.基于半监督系统，将YOLOv7和YOLOv7_tiny适配用于足球多检测，并结合DeepSORT进行跟踪
Sensors (Basel). 2023 Oct 25;23(21):8693. doi: 10.3390/s23218693.
8
Optimized deep learning vision system for human action recognition from drone images.用于从无人机图像中进行人体动作识别的优化深度学习视觉系统。
Multimed Tools Appl. 2023 Jun 2:1-22. doi: 10.1007/s11042-023-15930-9.
9
AIDeveloper: Deep Learning Image Classification in Life Science and Beyond.人工智能开发者：生命科学及其他领域的深度学习图像分类。
Adv Sci (Weinh). 2021 Jun;8(11):e2003743. doi: 10.1002/advs.202003743. Epub 2021 Mar 18.
10
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.