首页|基于改进YOLOv5的黄花成熟度检测方法

基于改进YOLOv5的黄花成熟度检测方法

扫码查看
原文链接
  • 国家科技期刊平台
  • NETL
  • NSTL
  • 万方数据
为统一辨识标准，提高成熟黄花采摘的检测精度和实时性能，提出一种改进的GCS-BI YOLOv5图像检测算法。首先，利用轻量化神经网络(Ghost Net)精简模型结构，节省计算资源;其次，为兼顾图像通道信息、位置信息，交叉引入高效注意力机制(CBAM和SE)，提升图像特征感知能力和模型收敛速度;然后，采用加权双向特征金字塔网络(BI FPN)，融合多尺度图像信息，提升模型对不同目标的综合检测性能。结果表明，与原始算法YOLOv5相比，所提算法在模型体积、网络层数、参数量、浮点运算量等轻量化指标方面分别下降62。89%、33。12%、63。01%、68。39%;在精确度、召回率等性能指标方面分别提升7。77、6。28百分点;实时性能提升了33。81 f/s。可见，改进算法的综合性能较优，能够满足黄花成熟度检测的要求。
A Maturity Detection Method for Hemerocallis citrina Baroni Based on Improved YOLOv5
To unify identification standards and improve the detection accuracy and real-time performance of mature Hemerocallis citrina Baroni picking,an improved GCS-BI YOLOv5 image detection algorithm was proposed.Firstly,the Ghost lightweight neural networks were utilized to streamline the model structure and save computational resources. Secondly,in order to pay attention to the image channel information and position information simultaneously,efficient attention mechanisms,namely convolutional block attention module (CBAM)and squeeze-and-excitation(SE),were cross-introduced to improve the image feature perception ability and model convergence speed. Then,a weighted bi-directional feature pyramid network(BI FPN)was used to fuse the multi-scale image information and improve the comprehensive detection performance of the model for different targets.The experimental results showed that compared with the original algorithm,the lightweight metrics such as the model volume,network layers,number of parameters,and floating-point operation of the improved algorithm were reduced by 62.89％,33.12％,63.01％,68.39％,respectively.The performance metrics such as detection accuracy and recall rate were improved by 7.77,6.28 percentage points,respectively. Real-time detection performance was improved by 33.81 f/s. It can be seen that the improved algorithm has better comprehensive performance and can meet the requirements of Hemerocallis citrina Baroni maturity detection.

Hemerocallis citrina BaroniLightweight neural networksAttention mechanismCross-channel feature fusionDeep learningYOLOv5

盛彬

展开 >

山西大同大学 机电工程学院,山西 大同 037003

黄花 轻量化神经网络 注意力机制 跨通道特征融合 深度学习 YOLOv5

山西省高等学校科技创新项目山西大同大学教学改革创新项目山西大同大学科研项目

2023L276XJG20222162020Q13

2024

10.15933/j.cnki.1004-3268.2024.08.016

河南农业科学
河南省农业科学院

河南农业科学

CSTPCD北大核心
影响因子：0.787
ISSN：1004-3268
年,卷(期)：2024.53(8)
  • 11