Scholarlink

<p>Object detection is a critical task in computer vision, enabling advancements across domains such as autonomous systems, surveillance, and smart devices. This paper presents a hybrid approach leveraging both MobileNet and YOLOv8 to address the challenges of resource constraints and the demand for high detection accuracy. For deployment on devices with limited resources, MobileNetV2, a lightweight and effective architecture, is used to provide dependable performance with minimal computational overhead. YOLOv8-s is integrated to achieve high accuracy in scenarios where computational resources are less restricted. By combining these models, the proposed approach balances computational efficiency and detection precision, offering scalability for diverse real-world applications. Comprehensive evaluations on benchmark datasets demonstrate that MobileNet excels in real-time performance for edge devices, while YOLOv8 provides superior accuracy for complex detection tasks. The results underline the effectiveness of this hybrid strategy for utilization on resource constraint devices and highlights the potential of integrating lightweight and high-accuracy models to enhance object detection systems, paving the way for innovative and adaptable solutions.</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

MOLO: a hybrid approach using MobileNet and YOLO for object detection on resource constrained devices

  • 期刊论文

  • 出版模式：

    开放获取

  • 发表日期：

    2025年10月27日

查看全文
  • Khushboo Khurana,
  • Pravinkumar Sonsare,
  • Devesh Borkar,
  • Hardik Thakkar,
  • Om Bhagat

摘要

Object detection is a critical task in computer vision, enabling advancements across domains such as autonomous systems, surveillance, and smart devices. This paper presents a hybrid approach leveraging both MobileNet and YOLOv8 to address the challenges of resource constraints and the demand for high detection accuracy. For deployment on devices with limited resources, MobileNetV2, a lightweight and effective architecture, is used to provide dependable performance with minimal computational overhead. YOLOv8-s is integrated to achieve high accuracy in scenarios where computational resources are less restricted. By combining these models, the proposed approach balances computational efficiency and detection precision, offering scalability for diverse real-world applications. Comprehensive evaluations on benchmark datasets demonstrate that MobileNet excels in real-time performance for edge devices, while YOLOv8 provides superior accuracy for complex detection tasks. The results underline the effectiveness of this hybrid strategy for utilization on resource constraint devices and highlights the potential of integrating lightweight and high-accuracy models to enhance object detection systems, paving the way for innovative and adaptable solutions.