计算机与现代化 ›› 2024, Vol. 0 ›› Issue (08): 24-29.doi: 10.3969/j.issn.1006-2475.2024.08.005

• 人工智能 • 上一篇    下一篇

改进YOLOv5s的落叶树鸟巢检测方法



  

  1. (河海大学地球科学与工程学院,江苏 南京 211100)
  • 出版日期:2024-08-28 发布日期:2024-08-28
  • 基金资助:
    国家自然科学基金资助项目(41471276)

Improved Deciduous Tree Nest Detection Method Based on YOLOv5s

  1. (School of Earth Sciences and Engineering, Hohai University, Nanjing 211100, China)
  • Online:2024-08-28 Published:2024-08-28

摘要: 针对从落叶树上识别鸟巢具有目标较小、背景复杂、目标与背景易混淆等问题,本文提出一种基于YOLOv5s改进的落叶树鸟巢检测模型YOLOv5s-nest。在Backbone中插入改进的注意力机制Bi-CBAM,提升网络对小目标的感知能力;在Neck中引入SDI结构,以融合更多层次特征图和更高级的语义信息;在Neck中插入InceptionNeXt结构,用于提高模型的性能和运算效率;在Head检测头中将普通卷积替换为PConv,可以更高效地提取空间特征及提高检测效率。实验结果表明,改进模型的平均精确率达到了89.1%,相较于原始模型提高了6.8个百分点。

关键词: 落叶树, 鸟巢识别, 无人机影像, 深度学习, 目标检测

Abstract: To address the difficulty of detecting small bird nest targets in complex backgrounds, an improved YOLOv5s network architecture named YOLOv5s-nest is proposed. YOLOv5s-nest incorporates several enhancements: a refined attention mechanism called Bi-CBAM is inserted into the Backbone to effectively enhance the network’s perception of small targets; the SDI structure is introduced into the Neck to integrate more hierarchical feature maps and higher-level semantic information; the InceptionNeXt structure is inserted into the Neck to improve the model's performance and computational efficiency; and in the detection head, ordinary convolutions are replaced with PConv to efficiently extract spatial features and enhance detection efficiency. The experimental results show that the average precision of the improved model reached 89.1%, representing an increase of 6.8 percentage points compared to the original model.

Key words: deciduous trees, nest recognition, UAV image, deep learning, object detection

中图分类号: