School of Mechanical Engineering, North China University of Water Resources and Electric Power, No. 36 Beihuan Road, Zhengzhou 450045, China.
Sensors (Basel). 2022 Jun 29;22(13):4933. doi: 10.3390/s22134933.
COVID-19 is highly contagious, and proper wearing of a mask can hinder the spread of the virus. However, complex factors in natural scenes, including occlusion, dense, and small-scale targets, frequently lead to target misdetection and missed detection. To address these issues, this paper proposes a YOLOv5-based mask-wearing detection algorithm, YOLOv5-CBD. Firstly, the Coordinate Attention mechanism is introduced into the feature fusion process to stress critical features and decrease the impact of redundant features after feature fusion. Then, the original feature pyramid network module in the feature fusion module was replaced with a weighted bidirectional feature pyramid network to achieve efficient bidirectional cross-scale connectivity and weighted feature fusion. Finally, we combined Distance Intersection over Union with Non-Maximum Suppression to improve the missed detection of overlapping targets. Experiments show that the average detection accuracy of the YOLOv5-CBD model is 96.7%-an improvement of 2.1% compared to the baseline model (YOLOv5).
新型冠状病毒（COVID-19）传染性极强，正确佩戴口罩可以阻碍病毒传播。然而，自然场景中存在遮挡、密集、小目标等复杂因素，常导致目标漏检和误检。针对这些问题，本文提出了一种基于 YOLOv5 的戴口罩检测算法 YOLOv5-CBD。首先，在特征融合过程中引入坐标注意力机制，突出关键特征，减少特征融合后冗余特征的影响。然后，用加权双向特征金字塔网络替换特征融合模块中原有的特征金字塔网络模块，实现高效的双向跨尺度连接和加权特征融合。最后，结合交并比和非极大值抑制来提高重叠目标的漏检率。实验表明，YOLOv5-CBD 模型的平均检测精度为 96.7%，比基线模型（YOLOv5）提高了 2.1%。
