改进RetinaNet的工艺流程检测算法  

Improved RetinaNet process flow detection algorithm

作　　者：李玮 高林[1] Li Wei;Gao Lin(School of Automation and Electronic Engineering,Qingdao University of Science and Technology,Qingdao 266061,China)

机构地区：[1]青岛科技大学自动化与电子工程学院,青岛266061

出　　处：《电子测量与仪器学报》2023年第7期104-112,共9页Journal of Electronic Measurement and Instrumentation

基　　金：国家自然科学基金(61971253);山东省自然科学基金(ZR2021MFZ23)项目资助。

摘　　要：现阶段,图像深度学习算法无法检测时序性的工艺流程问题。本文针对针织机械山板总成的人为装配工艺进行研究,提出MS-RetinaNet目标检测算法。借鉴自然语言处理的思想,引入Swin-Transformer结构,保留了CNN结构的层次性,弥补了CNN结构对于高层语义信息融合不足的问题,增强了全局与细节学习能力;使用改进的GIoU Loss,增加判定因子式,缓解损失计算退化的影响,优化边界框回归效果;根据多尺度目标参数,采用最佳锚框比,提高了召回率和检测精度;设计时序检测头,使算法具有判别目标先后顺序和逻辑关系的能力。实验结果表明,算法AP可达90.3%,高于当前主流算法2%以上,单张图片检测速度约46 ms,满足了工艺流程的时序检测要求,综合性能优越。At this stage,the image deep learning algorithm cannot detect the chronological process problem.In this paper,the artificial assembly process of the mountain board assembly of knitting machinery is studied,and the MS-RetinaNet object detection algorithm is proposed.Using the idea of natural language processing for reference,the Swing-Transformer structure is introduced to retain the hierarchy of CNN structure,make up for the lack of high-level semantic information fusion in CNN structure,and enhance the ability to learn overall and details.The improved GIoU Loss is used to increase the judgment factor formula,mitigate the impact of loss calculation degradation,and optimize the regression effect of the bounding box.According to the multi-scale target parameters,the best anchor frame ratio is adopted to improve the recall rate and detection accuracy.The chronological detector is designed to enable the algorithm to distinguish the sequence and logical relationship of the target.The experimental results show that the algorithm AP can reach 90.3%,which is more than 2%higher than the current mainstream algorithm.The detection speed of a single image is about 46 ms,meeting the chronological detection requirements of the process flow,and the overall performance is superior.

关 键 词：工艺流程 MS-RetinaNet Swin-Transformer 判定因子式 检测头 

分 类 号：TP391.4[自动化与计算机技术—计算机应用技术] TN05[自动化与计算机技术—计算机科学与技术]