A more effective and accurate improved Sobel algorithm has been developed to detect surface defects on heavy rails. The proposed method can make up for the mere sensitivity to X and Y directions of the Sobel algorithm...A more effective and accurate improved Sobel algorithm has been developed to detect surface defects on heavy rails. The proposed method can make up for the mere sensitivity to X and Y directions of the Sobel algorithm by adding six templates at different directions. Meanwhile, an experimental platform for detecting surface defects consisting of the bed-jig, image-forming system with CCD cameras and light sources, parallel computer system and cable system has been constructed. The detection results of the backfin defects show that the improved Sobel algorithm can achieve an accurate and efficient positioning with decreasing interference noises to the defect edge. It can also extract more precise features and characteristic parameters of the backfin defect. Furthermore, the BP neural network adopted for defects classification with the inputting characteristic parameters of improved Sobel algorithm can obtain the optimal training precision of 0.0095827 with 106 iterative steps and time of 3 s less than Sobel algorithm with 146 steps and 5 s. Finally, an enhanced identification rate of 10% for the defects is also confirmed after the Sobel algorithm is improved.展开更多
Abstract Objective To develop a new technique for assessing the risk of birth defects, which are a major cause of infant mortality and disability in many parts of the world. Methods The region of interest in this stud...Abstract Objective To develop a new technique for assessing the risk of birth defects, which are a major cause of infant mortality and disability in many parts of the world. Methods The region of interest in this study was Heshun County, the county in China with the highest rate of neural tube defects (NTDs). A hybrid particle swarm optimization/ant colony optimization (PSO/ACO) algorithm was used to quantify the probability of NTDs occurring at villages with no births. The hybrid PSO/ACO algorithm is a form of artificial intelligence adapted for hierarchical classification. It is a powerful technique for modeling complex problems involving impacts of causes. Results The algorithm was easy to apply, with the accuracy of the results being 69.5%+7.02% at the 95% confidence level. Conclusion The proposed method is simple to apply, has acceptable fault tolerance, and greatly enhances the accuracy of calculations.展开更多
金属零部件大量应用于生产生活的等各个领域,但其表面缺陷分布不均匀且部分特征微弱,常常造成金属零件表面缺陷检测的漏检和误检。针对这一问题,研究提出一种YOLOv5s-MD(you only look once-modified detection)算法。针对金属表面缺陷...金属零部件大量应用于生产生活的等各个领域,但其表面缺陷分布不均匀且部分特征微弱,常常造成金属零件表面缺陷检测的漏检和误检。针对这一问题,研究提出一种YOLOv5s-MD(you only look once-modified detection)算法。针对金属表面缺陷特征成分复杂的问题,引入改进的空间金字塔池化模块以提高算法对不同尺度微小目标的深度特征提取能力。针对金属表面缺陷特征分散及计算量增大问题,加入轻量化注意力机制及GSConv模块,提高模型对不同尺度缺陷特征的有效获取。考虑到金属表面缺陷尺寸信息无规律导致边界回归不匹配问题,采用考虑向量角度的损失函数。结果表明,提出的YOLOv5s-MD算法在对金属表面缺陷检测时,检测平均精度mAP@0.5达到75.3%,能够有效提升检测精度,降低误检率。展开更多
针对车辆漆面缺陷检测精度低、检测算法参数量大、难易样本不均匀等问题,提出一种基于改进YOLOv8的车辆漆面检测算法。首先,为了提升划痕状缺陷检测能力并降低模型规模,将DAT(Deformable Attention Transformer)注意力机制引入主干网络...针对车辆漆面缺陷检测精度低、检测算法参数量大、难易样本不均匀等问题,提出一种基于改进YOLOv8的车辆漆面检测算法。首先,为了提升划痕状缺陷检测能力并降低模型规模,将DAT(Deformable Attention Transformer)注意力机制引入主干网络来增强长距离特征依赖关系,同时使用幻影卷积(GhostConv)替换网络中的卷积(Conv)模块。然后,为了提升特征提取能力并进一步降低模型规模,结合FasterBlock模块与高效多尺度注意力(EMA)机制提出C2f-E(C2f Based on EMA)模块。接着,为了提高小目标检测性能,基于双向特征金字塔网络(BiFPN)进行设计,并增加小目标检测头与多尺度特征融合支路,提出BiFPN-D(BiFPN with Small Object Detection Head)颈部金字塔结构。最后,为了解决难易样本的平衡问题并提高针对小目标缺陷的检测性能,使用WIoUv3(Wise-Intersection over Union version 3)作为训练网络的损失函数。在自建的车辆漆面缺陷数据集上进行训练并开展对比实验。实验结果表明,相较于YOLOv8n,改进模型的均值平均精度(mAP@0.5)提高了5.5百分点、规模减小了1.4×106。展开更多
基金Project(51174151)supported by the National Natural Science Foundation of ChinaProject(2010Z19003)supported by the Major Scientific Research Program of Hubei Provincial Department of Education,ChinaProject(2010CDB03403)supported by the Natural Science Foundation of Science and Technology Department of Hubei Province,China
摘要A more effective and accurate improved Sobel algorithm has been developed to detect surface defects on heavy rails. The proposed method can make up for the mere sensitivity to X and Y directions of the Sobel algorithm by adding six templates at different directions. Meanwhile, an experimental platform for detecting surface defects consisting of the bed-jig, image-forming system with CCD cameras and light sources, parallel computer system and cable system has been constructed. The detection results of the backfin defects show that the improved Sobel algorithm can achieve an accurate and efficient positioning with decreasing interference noises to the defect edge. It can also extract more precise features and characteristic parameters of the backfin defect. Furthermore, the BP neural network adopted for defects classification with the inputting characteristic parameters of improved Sobel algorithm can obtain the optimal training precision of 0.0095827 with 106 iterative steps and time of 3 s less than Sobel algorithm with 146 steps and 5 s. Finally, an enhanced identification rate of 10% for the defects is also confirmed after the Sobel algorithm is improved.
基金supported by National Natural Science Foundation of China(No.41101431)the fourth installment special funding of China Postdoctoral Science Foundation(No.201104003)+1 种基金China Postdoctoral Science Foundation(No.20100470004)the State Key Funds of Social Science Project(Research on Disability Prevention Measurement in China,No.09&ZD072)
摘要Abstract Objective To develop a new technique for assessing the risk of birth defects, which are a major cause of infant mortality and disability in many parts of the world. Methods The region of interest in this study was Heshun County, the county in China with the highest rate of neural tube defects (NTDs). A hybrid particle swarm optimization/ant colony optimization (PSO/ACO) algorithm was used to quantify the probability of NTDs occurring at villages with no births. The hybrid PSO/ACO algorithm is a form of artificial intelligence adapted for hierarchical classification. It is a powerful technique for modeling complex problems involving impacts of causes. Results The algorithm was easy to apply, with the accuracy of the results being 69.5%+7.02% at the 95% confidence level. Conclusion The proposed method is simple to apply, has acceptable fault tolerance, and greatly enhances the accuracy of calculations.
摘要金属零部件大量应用于生产生活的等各个领域,但其表面缺陷分布不均匀且部分特征微弱,常常造成金属零件表面缺陷检测的漏检和误检。针对这一问题,研究提出一种YOLOv5s-MD(you only look once-modified detection)算法。针对金属表面缺陷特征成分复杂的问题,引入改进的空间金字塔池化模块以提高算法对不同尺度微小目标的深度特征提取能力。针对金属表面缺陷特征分散及计算量增大问题,加入轻量化注意力机制及GSConv模块,提高模型对不同尺度缺陷特征的有效获取。考虑到金属表面缺陷尺寸信息无规律导致边界回归不匹配问题,采用考虑向量角度的损失函数。结果表明,提出的YOLOv5s-MD算法在对金属表面缺陷检测时,检测平均精度mAP@0.5达到75.3%,能够有效提升检测精度,降低误检率。
摘要针对车辆漆面缺陷检测精度低、检测算法参数量大、难易样本不均匀等问题,提出一种基于改进YOLOv8的车辆漆面检测算法。首先,为了提升划痕状缺陷检测能力并降低模型规模,将DAT(Deformable Attention Transformer)注意力机制引入主干网络来增强长距离特征依赖关系,同时使用幻影卷积(GhostConv)替换网络中的卷积(Conv)模块。然后,为了提升特征提取能力并进一步降低模型规模,结合FasterBlock模块与高效多尺度注意力(EMA)机制提出C2f-E(C2f Based on EMA)模块。接着,为了提高小目标检测性能,基于双向特征金字塔网络(BiFPN)进行设计,并增加小目标检测头与多尺度特征融合支路,提出BiFPN-D(BiFPN with Small Object Detection Head)颈部金字塔结构。最后,为了解决难易样本的平衡问题并提高针对小目标缺陷的检测性能,使用WIoUv3(Wise-Intersection over Union version 3)作为训练网络的损失函数。在自建的车辆漆面缺陷数据集上进行训练并开展对比实验。实验结果表明,相较于YOLOv8n,改进模型的均值平均精度(mAP@0.5)提高了5.5百分点、规模减小了1.4×106。