Scholarlink

<p>With the escalating demand for precise coal gangue detection in industrial applications, the development of efficient and robust object detection architectures is imperative. In this study, we introduce L-DEYO, an innovative lightweight deep learning model specifically designed for intelligent coal gangue recognition in resource-constrained environments. L-DEYO integrates a hierarchical feature extraction mechanism with a progressive training paradigm, optimizing both detection accuracy and inference speed without necessitating additional annotated datasets. Comprehensive evaluations reveal that L-DEYO attains a mean average precision (mAP) of 37.6% on the COCO benchmark, achieving real-time performance at 497 frames per second (FPS) on an NVIDIA Tesla T4 GPU. Notably, the model's modular design facilitates efficient training on a single 8&#xa0;GB RTX 4060 GPU, resulting in a substantial reduction in computational overhead. These findings underscore L-DEYO's efficacy and scalability, offering a viable solution for large-scale deployment in industrial coal gangue detection systems. Access to our method is available at <a href="https://github.com/srcuyan/L-DEYO.git">https://github.com/srcuyan/L-DEYO.git</a><Emphasis Type="Underline">.</Emphasis></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

L-DEYO: An optimized lightweight model for intelligent coal gangue recognition

  • 期刊论文

  • 发表日期：

    2025年4月1日

查看全文
  • Sitong Yan,
  • Wei Liu,
  • Ziyi Yang,
  • Enqi Zhang,
  • Yasheng Chang

摘要

With the escalating demand for precise coal gangue detection in industrial applications, the development of efficient and robust object detection architectures is imperative. In this study, we introduce L-DEYO, an innovative lightweight deep learning model specifically designed for intelligent coal gangue recognition in resource-constrained environments. L-DEYO integrates a hierarchical feature extraction mechanism with a progressive training paradigm, optimizing both detection accuracy and inference speed without necessitating additional annotated datasets. Comprehensive evaluations reveal that L-DEYO attains a mean average precision (mAP) of 37.6% on the COCO benchmark, achieving real-time performance at 497 frames per second (FPS) on an NVIDIA Tesla T4 GPU. Notably, the model's modular design facilitates efficient training on a single 8 GB RTX 4060 GPU, resulting in a substantial reduction in computational overhead. These findings underscore L-DEYO's efficacy and scalability, offering a viable solution for large-scale deployment in industrial coal gangue detection systems. Access to our method is available at https://github.com/srcuyan/L-DEYO.git.