结合空洞卷积和迁移学习改进YOLOv4的X光安检危险品检测

Improved YOLOv4 for dangerous goods detection in X-ray inspection combined with atrous convolution and transfer learning

由于X光安检图像存在背景复杂,重叠遮挡现象严重,危险品摆放方式、形状差异较大等问题,导致检测难度较高。针对上述问题,本文在YOLOv4的基础上,结合空洞卷积对其网络结构进行改进,加入空洞空间金字塔池化(Atrous Space Pyramid Pooling,ASPP)模型,以此增大感受野,聚合多尺度上下文信息。然后,通过K-means聚类方法生成更适合X光安检危险品检测的初始候选框。其中,模型训练时采用余弦退火优化学习率,进一步加速模型收敛,提高模型检测精度。实验结果表明,本文提出的ASPP-YOLOv4检测算法在SIXRay数据集上的mAP达到85.23%。该方法能有效减少X光安检图像中危险品的误检率,提高小目标危险品的检测能力。

In response to the complex backgrounds of X-ray security images,serious overlap and occlusion phenomena,and the large differences in the placement and shape of dangerous goods,this paper improves the network structure of YOLOv4 for dangerous objects detection by combining atrous convolution with the At-rous Space Pyramid Pooling(ASPP)model to increase receptive field and aggregate multi-scale context in-formation.Then,the K-means clustering method is used to generate an initial candidate frame that is more suitable for dangerous goods detection in X-ray inspection images.Cosine annealing is used to optimize the learning rate in model training to further accelerate model convergence and improve model detection accur-acy.The experimental results show that the proposed ASPP-YOLOv4 in this paper can obtain an mAP of 85.23%on the SIXRay dataset.The model can effectively reduce the false detection rate of dangerous goods in X-ray security images and improve the detection ability of small targets.