改进的EfficientDet及直方图均衡化的工件检测算法研究  

Study on Algorithm of Workpiece Detection via Improved EfficientDet and Histogram Equalization

作　　者：石林坤 田怀文[1] 杨玉洁 SHI Linkun;TIAN Huaiwen;YANG Yujie(School of Mechanical Engineering,Southwest Jiaotong University,Chengdu 610031,China)

机构地区：[1]西南交通大学机械工程学院,成都610031

出　　处：《机械科学与技术》2023年第9期1445-1454,共10页Mechanical Science and Technology for Aerospace Engineering

摘　　要：针对流水线加工作业环境下工业机器人对工件检测及定位率较低,速度慢等问题,提出基于改进的EfficientDet工件检测神经网络模型。采用EfficientNet作为主干特征提取网络,利用Triplet Attention注意力机制代替原始的SE Attention机制,同时借鉴循环特征融合思想,采用Recursive-BiFPN循环特征融合网络结构。针对正负样本不均等问题,采用generalized focal loss改进原始focal loss损失函数。考虑到机械加工特定生产环境,采用直方图均衡化思想对数据进行对比度提高。最后利用工业相机建立自制数据集并进行模型训练,在复杂工业生产情况下,改进后的EfficientDet在mAP上较原始网络提高6.1%,同时速度提高到72帧/s。最后实验结果表明,该算法在生产环境下能快速准确地对工件进行定位检测,为实际生产需要提供新的解决思路。Aiming at the low detection and localization rate and slow speed of industrial robots to workpiece in assembly line processing environment,an improved EfficientDet neural network model for workpiece detection is proposed.EfficientNet was adopted as the backbone feature extraction network,Triplet Attention mechanism is used to replace the original squeeze-and-excitation(SE)Attention mechanism,and the recursive-efficient bidirectional cross-scale connections and weighted feature fusion cyclic feature merge network structure is used for reference of cyclic feature merge idea.To solve the unequal positive and negative samples,generalized focal loss is used to improve the original focal loss function.Considering the specific production environment of machining,histogram equalization is used to improve the contrast of data.Finally,the model was trained and established with an industrial camera.The improved model EfficientDet improved by 6.1%comparing with the original one in a complex industrial production situation,and its speed increased to 72 frames perframes per second.The experimental results show that the algorithm can quickly and accurately locate the workpiece in the production environment,which provides a new solution for the actual production needs.

关 键 词：工件检测 EfficientDet模型 Triplet Attention generalized focal loss 

分 类 号：TP301[自动化与计算机技术—计算机系统结构]