期刊论文

中文

计算机工程与应用

1002-8331

2023

59

11

188-194

10.3778/j.issn.1002-8331.2203-0048

国家社会科学基金项目(19BTQ005)；

本校为第一机构

针对在复杂场景口罩佩戴检测中存在的多尺度、多角度和遮挡等问题，提出一种基于改进FCOS的复杂场景口罩佩戴检测算法。首先在算法的骨干网络中引入Res2Net的分组残差连接结构，提高网络对不同尺度口罩的特征提取能力，并在其中集成可变形卷积，拓展其对未知形状物体的建模能力；然后设计一种集成注意力机制的特征金字塔，为不同的特征通道赋予不同的权重，抑制无用的特征信息；最后根据目标口罩的相关统计特征自动地划分正负样本，提高不同尺度口罩的样本质量，并引入Generalized Focal Loss联合训练样本的分类分数和定位质量分数，提升算法性能。实验结果表明，在复杂场景下的口罩佩戴检测中，...

Aiming at the problems of multi-scale,multi angle and occlusion in mask wearing detection in complex scenes,a mask wearing detection algorithm in complex scenes based on improved FCOS is proposed in this paper.Firstly,in order to improve the feature extraction ability o...MORE Aiming at the problems of multi-scale,multi angle and occlusion in mask wearing detection in complex scenes,a mask wearing detection algorithm in complex scenes based on improved FCOS is proposed in this paper.Firstly,in order to improve the feature extraction ability of the network for masks with different scales,the pa...