田间害虫图像数据采集困难,并且传统的检测模型大多使用复杂的特征金字塔(Feature pyramid network,FPN)结构提升精度,这在一定程度上影响了检测的实时性。为此,本研究通过设计诱虫灯装置构建害虫数据集FieldPest5,并且对无FPN结构的检...田间害虫图像数据采集困难,并且传统的检测模型大多使用复杂的特征金字塔(Feature pyramid network,FPN)结构提升精度,这在一定程度上影响了检测的实时性。为此,本研究通过设计诱虫灯装置构建害虫数据集FieldPest5,并且对无FPN结构的检测器YOLOF进行改进,提出兼顾检测精度和效率的害虫检测模型YOLOF_PD。首先,增加Cutout数据增强方法缓解害虫图像中的遮挡问题,并且使用CIoU损失函数获得更好的框回归位置;其次,在原有坐标注意力机制(Coordinate attention,CA)的全局平均池化(Global average pooling,GAP)路径中增加全局最大池化(Global max pooling,GMP)路径,并且使用可学习参数自适应更新不同路径的权重,提出自适应坐标注意力机制(Adaptive coordinate attention,ACA),增强模型的信息表征能力;最后,对YOLOF膨胀编码器中的Projector和Residual模块进行改进,在Projector模块的3×3卷积后引入ACA注意力机制,在Residual模块中融合3×3的深度可分离卷积和1×1的逐点卷积,提出Dilated_Dwise_ACA编码器,提高YOLOF对小尺度害虫的检测性能。实验结果表明:改进后的YOLOF_PD模型在FieldPest5测试集上的平均精度均值(Mean average precision,mAP)为93.7%,较改进前提升2.1个百分点,并且检测时图像传输速率为42.4 f/s,能够满足害虫快速检测的要求。对比Cascade R CNN、RetinaNet、ATSS等模型,YOLOF_PD模型在检测效果和检测速度方面均取得了良好性能。展开更多
Surface defects can affect the quality of steel plate.Many methods based on computer vision are currently applied to surface defect detection of steel plate.However,their real-time performance and object detection of ...Surface defects can affect the quality of steel plate.Many methods based on computer vision are currently applied to surface defect detection of steel plate.However,their real-time performance and object detection of small defect are still unsatisfactory.An improved object detection network based on You Only Look One-level Feature(YOLOF)is proposed to show excellent performance in surface defect detection of steel plate,called DLF-YOLOF.First,the anchor-free detector is used to reduce the network hyperparameters.Secondly,deformable convolution network and local spatial attention module are introduced into the feature extraction network to increase the contextual information in the feature maps.Also,the soft non-maximum suppression is used to improve detection accuracy significantly.Finally,data augmentation is performed for small defect objects during training to improve detection accuracy.Experiments show the average precision and average precision for small objects are 42.7%and 33.5%at a detection speed of 62 frames per second on a single GPU,respectively.This shows that DLF-YOLOF has excellent performance to meet the needs of industrial real-time detection.展开更多
文摘田间害虫图像数据采集困难,并且传统的检测模型大多使用复杂的特征金字塔(Feature pyramid network,FPN)结构提升精度,这在一定程度上影响了检测的实时性。为此,本研究通过设计诱虫灯装置构建害虫数据集FieldPest5,并且对无FPN结构的检测器YOLOF进行改进,提出兼顾检测精度和效率的害虫检测模型YOLOF_PD。首先,增加Cutout数据增强方法缓解害虫图像中的遮挡问题,并且使用CIoU损失函数获得更好的框回归位置;其次,在原有坐标注意力机制(Coordinate attention,CA)的全局平均池化(Global average pooling,GAP)路径中增加全局最大池化(Global max pooling,GMP)路径,并且使用可学习参数自适应更新不同路径的权重,提出自适应坐标注意力机制(Adaptive coordinate attention,ACA),增强模型的信息表征能力;最后,对YOLOF膨胀编码器中的Projector和Residual模块进行改进,在Projector模块的3×3卷积后引入ACA注意力机制,在Residual模块中融合3×3的深度可分离卷积和1×1的逐点卷积,提出Dilated_Dwise_ACA编码器,提高YOLOF对小尺度害虫的检测性能。实验结果表明:改进后的YOLOF_PD模型在FieldPest5测试集上的平均精度均值(Mean average precision,mAP)为93.7%,较改进前提升2.1个百分点,并且检测时图像传输速率为42.4 f/s,能够满足害虫快速检测的要求。对比Cascade R CNN、RetinaNet、ATSS等模型,YOLOF_PD模型在检测效果和检测速度方面均取得了良好性能。
基金supported by the Natural Science Foundation of Liaoning Province(No.2022-MS-353)Basic Scientific Research Project of Education Department of Liaoning Province(Nos.2020LNZD06 and LJKMZ20220640)。
文摘Surface defects can affect the quality of steel plate.Many methods based on computer vision are currently applied to surface defect detection of steel plate.However,their real-time performance and object detection of small defect are still unsatisfactory.An improved object detection network based on You Only Look One-level Feature(YOLOF)is proposed to show excellent performance in surface defect detection of steel plate,called DLF-YOLOF.First,the anchor-free detector is used to reduce the network hyperparameters.Secondly,deformable convolution network and local spatial attention module are introduced into the feature extraction network to increase the contextual information in the feature maps.Also,the soft non-maximum suppression is used to improve detection accuracy significantly.Finally,data augmentation is performed for small defect objects during training to improve detection accuracy.Experiments show the average precision and average precision for small objects are 42.7%and 33.5%at a detection speed of 62 frames per second on a single GPU,respectively.This shows that DLF-YOLOF has excellent performance to meet the needs of industrial real-time detection.
