Scholarlink

<p>By 2025, distributed cloud computing services have become commonplace and widely adopted, transforming the IT landscape across industries and institutions. These services offer numerous benefits that enhance the efficiency and scalability of IT operations. With the recent surge and popularization of Artificial Intelligence image classification and image object detection workloads, cloud computing has become a popular method to train, evaluate, and serve such jobs. This article explores the AI image object detection frameworks of the three leading cloud providers—Amazon Web Services, Microsoft Azure, and Google—based on Convolutional Neural Network (CNN) architecture. It presents a practical comparative analysis of their respective solutions: Amazon Rekognition, Azure Custom Vision, and Vertex AI, alongside a locally trained object detection model using YOLO11m. The collected results, along with a discussion of the advantages, limitations, and key insights, are presented throughout the paper.</p>

错误：搜索内容不能为空，请输入英文关键词
错误：关键词超出字数限制，请精简
高级检索

Comparative analysis of cloud-based AI object detection services and YOLO11: performance, cost, and usability evaluation

  • 期刊论文

  • 出版模式：

    开放获取

  • 发表日期：

    2026年2月7日

查看全文
  • Ricardo Beck Feiten,
  • Edison Pignaton de Freitas,
  • Manuel M. Oliveira

摘要

By 2025, distributed cloud computing services have become commonplace and widely adopted, transforming the IT landscape across industries and institutions. These services offer numerous benefits that enhance the efficiency and scalability of IT operations. With the recent surge and popularization of Artificial Intelligence image classification and image object detection workloads, cloud computing has become a popular method to train, evaluate, and serve such jobs. This article explores the AI image object detection frameworks of the three leading cloud providers—Amazon Web Services, Microsoft Azure, and Google—based on Convolutional Neural Network (CNN) architecture. It presents a practical comparative analysis of their respective solutions: Amazon Rekognition, Azure Custom Vision, and Vertex AI, alongside a locally trained object detection model using YOLO11m. The collected results, along with a discussion of the advantages, limitations, and key insights, are presented throughout the paper.