计算机工程与应用 ›› 2023, Vol. 59 ›› Issue (10): 213-220.DOI: 10.3778/j.issn.1002-8331.2202-0287

• 图形图像处理 • 上一篇    下一篇

改进YOLOv4的轻量级遥感图像建筑物检测模型

丁飞,石颉,吴宏杰   

  1. 1.苏州科技大学 电子与信息工程学院,江苏 苏州 215009
    2.苏州科技大学 江苏省建筑智慧节能重点实验室,江苏 苏州 215009
  • 出版日期:2023-05-15 发布日期:2023-05-15

Lightweight Building Detection Model Based on YOLOv4 Optimization for Remote Sensing Images

DING Fei, SHI Jie, WU Hongjie   

  1. 1.School of Electronic and Information Engineering, Suzhou University of Science and Technology, Suzhou, Jiangsu 215009, China
    2.Jiangsu Provincial Key Laboratory of Building Intelligent Energy Conservation, Suzhou University of Science and Technology, Suzhou, Jiangsu 215009, China
  • Online:2023-05-15 Published:2023-05-15

摘要: 针对现有建筑物检测模型检测精度低下,模型体积较大,导致遥感图像检测速度和精度无法平衡,不利于后期部署等问题,提出一种基于YOLOv4优化的轻量级遥感图像建筑物检测模型。利用轻量化网络GhostNet替换CSP DarkNet53进行特征提取;借鉴稠密连接思想,提出了Dense-PANet特征融合模块;将ECA注意力机制引入Ghost模块,替换特征融合颈部网络的传统卷积。实验结果表明,提出的模型与YOLOv4相比,牺牲少量检测速度,但是平均精度提高了0.96个百分点,召回率提升了1.08个百分点,模型体积降低了71.39%,浮点计算量降低了76.60%,能有效满足遥感图像建筑物检测的需求。

关键词: 建筑物检测, YOLOv4, 轻量级, 特征融合, ECA注意力机制

Abstract: Aiming at the problems of low detection accuracy and large model size of existing building detection models, which lead to unbalanced speed and accuracy of remote sensing image detection and unfavorable to later deployment, a lightweight building detection model based on YOLOv4 optimization for remote sensing images is proposed. Firstly, GhostNet, a lightweight network, is used to replace CSP DarkNet53 for feature extraction. Secondly, the Dense-PANet feature fusion module is proposed by drawing on the idea of dense connection. Finally, the ECA attention mechanism is introduced into the Ghost module to replace the traditional convolution of the neck network. The experimental results show that the model proposed in this paper, compared with YOLOv4, sacrifices a small amount of detection speed, but increases the average precision by 0.96 percentage points, the recall by 1.08 percentage points, and decreases the model volume by 71.39%, the floating point of operations by 76.60%, which can effectively meet the demand of remote sensing image building detection.

Key words: building detection, YOLOv4, lightweight, feature fusion, ECA attention mechanism