基于Canny-YOLO的目标检测方法改进研究

Research on improved target detection method based on Canny-YOLO

针对当前军工工业产品缺陷检测能力不足的问题,以生产中普遍存在的小目标缺陷检测为切入点,提出了一种基于Canny-YOLOv7算法的融合增强模型。该模型主要通过Canny边缘检测算法识别图像中的潜在缺陷区域并对缺陷区域特征进行增强,在此基础上对YOLOv7模型进行针对性改进以提升泛化能力。首先,为增强模型对于细微缺陷特征的提取能力,使用Swin Transformer (STR)模块替换原始主干网络中的ELAN模块。其次,采用SIOU损失函数使得改进模型能快速学习到准确的目标定位。最后,采用LeakyReLU激活函数减少函数计算开销,进一步提升模型检测速度。实验结果表明,在相同数据集下,提出的增强模型平均检测精度达到97.5%,相较于原始YOLOv7模型提升了4.6%,检测速度(FPS)为52.45,满足实时检测需求。

To address the problem of insufficient defect detection capabilities in current military and industrial products,a fusion enhancement model based on the Canny-YOLOv7 algorithm was proposed focusing on small target defect detection that is commonly employed in production.The model primarily utilizes the Canny edge detection algorithm to identify potential defect areas in images,enhancing the features of these areas.Based on this,the YOLOv7 model was improved to enhance its generalization ability.First,to improve the model’s capability to extract subtle defect features,the ELAN module in the original backbone network was replaced with the Swin Transformer(STR)module.Second,the SIOU loss function was incorporated,enabling the improved model to quickly learn accurate target positioning.Finally,the LeakyReLU activation function was adopted to reduce computational overhead and further improve the model’s detection speed.Experimental results demonstrate that,under the same dataset,the proposed enhanced model achieves an average detection accuracy of 97.5%,which is 4.6%higher than that of the original YOLOv7 model.Additionally,the detection speed(FPS)reaches 52.45,meeting real-time detection requirements.