期刊论文

中文

计算机系统应用

1003-3254

2023

32

06

251-259

10.15888/j.cnki.csa.009165

本校为第一机构

针对当前传统农作物病害语义分割方法精度不高、鲁棒性差等问题,本文提出了基于注意力机制的改进UNet草莓病害语义分割模型.首先,在编码器中加入CNN-Transformer混合结构,增强全局信息与局部细节信息的特征提取能力.其次,在解码器中将dual up-sample模块替换传统上采样,提高特征提取能力与分割精度.再使用hard-swish激活函数代替ReLU激活函数,更加平滑的曲线有助于提高泛化性和非线性特征提取能力,防止梯度消失.最后,通过使用结合交叉熵Dice损失函数,加强模型对分割结果的约束,进一步提升分割精度.实验采用了由7种草莓病害2 500张图像组成的数据集,在复杂背景下对草莓病害进行分割,语义分割像素...

The existing traditional semantic segmentation methods of crop diseases have low accuracy and poor robustness.In order to address these problems,an improved UNet semantic segmentation model of strawberry diseases based on an attention mechanism is proposed.Firstly,a CNN...MORE The existing traditional semantic segmentation methods of crop diseases have low accuracy and poor robustness.In order to address these problems,an improved UNet semantic segmentation model of strawberry diseases based on an attention mechanism is proposed.Firstly,a CNN-T...