面向X射线图像违禁品检测的GELAN-YOLOv8算法  

GELAN-YOLOv8 Algorithm for Contraband Detection in X-Ray Image

作　　者：骆远翔 刘春玲[1] 李想[1] Luo Yuanxiang;Liu Chunlin;Li Xiang(College of Information Engineering,Dalian University,Dalian 116000,Liaoning,China)

机构地区：[1]大连大学信息工程学院,辽宁大连116000

出　　处：《激光与光电子学进展》2025年第2期390-398,共9页Laser & Optoelectronics Progress

基　　金：辽宁省教育厅面上基金(LJKZ1184)。

摘　　要：针对X射线图像中违禁品轮廓信息复杂、形状变化大、存在尺寸较小违禁品造成的检测精度低和漏检问题,提出基于YOLOv8改进的GELAN-YOLOv8模型。首先引入基于通用高效层聚合网络(GELAN)的RepNCSPELAN模块,提高模型对违禁品特征的提取能力;其次结合动态可变形卷积(DCNv3)和RepNCSPELAN模块提出GELAN-RD模块,以适应姿态各异、尺寸角度变化程度大的违禁品;然后改进空间金字塔池化,使模型更能关注到小目标违禁品的特征信息;最后结合Inner-交并比(Inner-IoU)和Shape-IoU提出Inner-ShapeIoU,以减少检测违禁品时存在的误检和漏检现象并加快模型收敛的速度。结果表明,改进算法的mAP@0.5在SIXray数据集上较YOLOv8n提升2.8百分点,且性能优于YOLOv8s。GELAN-YOLOv8有效地实现了对X射线图像中违禁品的实时检测。Aiming at the problems of low detection accuracy and missed detection caused by complex contour information,large change of shape and small size contraband in X-ray images,an improved GELAN-YOLOv8 model based on YOLOv8 is proposed.First,the RepNCSPELAN module based on generalized efficient layer aggregation network(GELAN)is introduced to improve the feature extract ability for contraband.Second,the GELAN-RD module is proposed by combining deformable convolution v3(DCNv3)and RepNCSPELAN module to adapt contraband with different postures and serious changes in size and angle.Third,the spatial pyramid pooling is improved,so that the model can pay more attention to the feature information of small target contraband.Finally,the Inner-ShapeIoU is proposed by combining inner-intersection over union(Inner-IoU)and Shape-IoU to reduce the false detection and missed detection and speed up the convergence of the model.Results on the SIXray dataset show that the mAP@0.5 of the improved algorithm are 2.8 percentage points higher than YOLOv8n,and the performance is better than YOLOv8s.The GELAN-YOLOv8 effectively realizes the real-time detection of contraband in X-ray images.

关 键 词：X射线图像 违禁品检测 GELAN-YOLOv8 可变形卷积 损失函数优化 

分 类 号：TP391.4[自动化与计算机技术—计算机应用技术]