期刊论文

中文

河南农业科学

1004-3268

2024

53

03

151-157

10.15933/j.cnki.1004-3268.2024.03.016

31870532:国家自然科学基金 2021JJ31163:湖南省自然科学基金资助项目 XJK20BGD048:湖南省教育科学十三五规划基金资助项目

本校为第一机构

为实现自然环境下蓝莓的精确快速检测,在YOLO v5s的基础上提出了一种结合轻量级网络和注意力机制的改进算法.首先,在主干网络和检测头的位置去除了最大目标检测层的结构,因而降低模型的参数量,增强模型对小目标的检测能力.其次,将MHSA(Multi-head self-attention,多头自注意力)替换了SPPF(Spatial pyramid pooling-fast,快速空间金字塔池化)前面的C3模块,使模型学习到更全面的特征表示,增强模型对蓝莓图像中复杂空间关系和上下文信息的理解能力.最后,在C3模块中加入了S-PSA(Sequential polarized self-attention,顺序极化自注意力),以便模型能够更好地捕捉特征图中相邻区域之间的上下文依赖关系...

To achieve precise and rapid detection of blueberries in natural environments,an improved algorithm combining lightweight networks and attention mechanisms was proposed based on YOLO v5s.Firstly,the structure of the maximum object detection layer was removed at the positions of the backbone network and detection heads,thereby reducing the number of model parameters and enhancing the model's ability to detect small targets.Secondly,MHSA(Multi-head self-attention)was used to replace the C3 module before SPPF(Spatial pyramid pooling-fast),enabling the model to learn more comprehensive feature rep...