+高级检索
首页 > 过刊浏览>2024年第47卷第18期 >145-154
PDF HTML阅读 XML下载 导出引用 引用提醒
基于轻量级算法的水上垃圾小目标检测研究
作者:
作者单位:

1.三峡大学水电工程智能视觉监测湖北省重点实验室 宜昌 443002; 2.三峡大学湖北省建筑质量检测装备工程技术 研究中心 宜昌 443002; 3.三峡大学计算机与信息学院 宜昌 443002; 4.荆楚理工学院大数据研究中心 荆门 448000

中图分类号:

TP391.41; TN40

基金项目:

湖北省大学生创新创业训练计划（S202311075047）项目资助


Research on small object detection of waterborne debris based on lightweight algorithms
Author:
  • Xu Jinda

    Xu Jinda

    1.Hubei Key Laboratory of Intelligent Vision Based Monitoring for Hydroelectric Engineering, China Three Gorges University， Yichang 443002, China； 2.Hubei Province Engineering Technology Research Center for Construction Quality Testing Equipment, China Three Gorges University，Yichang 443002, China； 3.College of Computer and information Technology, China Three Gorges University，Yichang 443002, China
    在期刊界中查找
    在百度中查找
    在本站中查找
  • Chen Cifa

    Chen Cifa

    2.Hubei Province Engineering Technology Research Center for Construction Quality Testing Equipment, China Three Gorges University，Yichang 443002, China； 3.College of Computer and information Technology, China Three Gorges University，Yichang 443002, China； 4.Big Data Research Center, Jingchu University of Technology，Jingmen 448000, China
    在期刊界中查找
    在百度中查找
    在本站中查找
  • Zhang Shang

    Zhang Shang

    1.Hubei Key Laboratory of Intelligent Vision Based Monitoring for Hydroelectric Engineering, China Three Gorges University， Yichang 443002, China； 2.Hubei Province Engineering Technology Research Center for Construction Quality Testing Equipment, China Three Gorges University，Yichang 443002, China； 3.College of Computer and information Technology, China Three Gorges University，Yichang 443002, China
    在期刊界中查找
    在百度中查找
    在本站中查找
Affiliation:

1.Hubei Key Laboratory of Intelligent Vision Based Monitoring for Hydroelectric Engineering, China Three Gorges University， Yichang 443002, China; 2.Hubei Province Engineering Technology Research Center for Construction Quality Testing Equipment, China Three Gorges University，Yichang 443002, China; 3.College of Computer and information Technology, China Three Gorges University，Yichang 443002, China; 4.Big Data Research Center, Jingchu University of Technology，Jingmen 448000, China

  • 摘要
    • | |
  • 访问统计
    • |
  • 参考文献
    • |
  • 相似文献
    • |
  • 引证文献
    • | |
  • 文章评论
    摘要:

    针对水上漂浮垃圾检测中微小目标物体数量占比高、检测画面易受到水面波动和岸边环境反光等多重因素的干扰、检测模型庞大的参数量和计算量对终端的部署的设备性能要求高等问题，拟提出一种轻量化、高精度、实时性的检测模型LS-YOLO。首先，该算法利用HS-FPN金字塔网络设计构造YOLOv8的Neck网络结构，构建的网络结构牺牲小部分精度，显著降低了模型的参数数量和计算复杂度。其次，通过引入CAA上下文锚定注意机制改进HS-FPN，捕获远程上下文信息来回升检测精度。然后通过更换损失函数为具有动态聚焦机制的Wise-IoUv3，大幅提升检测效果，增加模型鲁棒性。最后，使用LAMP剪枝技术对模型进行剪枝，减小模型的参数量和计算量。实验结果表明，改进后的LS-YOLO相比基准模型mAP50提升了0.9%，回归率提升了3.2%，参数量降至基准模型的19.83%，计算量降至基线的44.44%，模型大小降至基线的22.22%。经过优化后的检测算法不仅显著提升了检测性能与特征提取的精准度，同时也便于在资源受限的硬件平台上的部署操作。

    Abstract:

    To address the high proportion of small target objects in waterborne debris detection, the interference caused by multiple factors such as water surface fluctuations and shoreline reflections, and the high demands on device performance due to the large number of parameters and computational load of detection models, we propose a lightweight, high-precision, real-time detection model, LS-YOLO. First, this algorithm uses the HS-FPN pyramid network design to construct the Neck network structure of YOLOv8. The constructed network structure sacrifices a small part of the accuracy and significantly reduces the number of parameters and computational complexity of the model. Secondly, HS-FPN is improved by introducing the CAA context-anchored attention mechanism to capture remote contextual information to improve detection accuracy. Then, by replacing the loss function with Wise-IoUv3, which features a dynamic focusing mechanism, the detection performance is significantly improved, increasing the robustness of the model. Finally, LAMP pruning technology is used to prune the model to reduce the number of parameters and calculations of the model. The experiment shows that the improved LS-YOLO has a 0.9% increase in mAP50 compared to the baseline model, a 3.2% increase in recall, a reduction in parameters to 19.83% of the baseline model, a reduction in computational cost to 44.44%, and a reduction in model size to 22.22%. The optimized detection algorithm not only significantly improves detection performance and feature extraction accuracy, but also facilitates deployment on resource-constrained hardware platforms.

    参考文献
    相似文献
    引证文献
引用本文

徐尽达,陈慈发,张上.基于轻量级算法的水上垃圾小目标检测研究[J].电子测量技术,2024,47(18):145-154

复制
分享
文章指标
  • 点击次数:
  • 下载次数:
  • HTML阅读次数:
  • 引用次数:
历史
  • 在线发布日期: 2024-12-20
文章二维码
您是第5087408 位访问者
主管单位：北京电子控股有限责任公司
主办单位：北京无线电技术研究所
地址：北京市东城区北河沿大街79号
电话：13810562337
电子测量技术 ® 2025 版权所有