【摘要】 针对工件表面小缺陷经常由于数量少且视觉特征不明显而导致的被漏检和错判的问题,提出一种基于CutMix和YOLOv3的工件表面小缺陷识别方法CSYOLOv3.使用贝塔分布动态调整的CutMix方法在网络训练时动态扩充训练集中小缺陷的数量;并对YOLOv3网络进行了改进,拆分其浅层大特征图,取部分与预测分支的特征图融合以保留浅层的小缺陷特征;使用加权的改进损失函数对网络进行训练,提高网络对小缺陷的重视程度和识别准确率.该方法在RTX 2060Ti GPU下对512×512像素的缺陷图片进行识别,速度可以达到14.09帧/s,识别mAP为71.80%,比常用目标检测方法高出5%～10%.对于小于64×64像素的小缺陷,方法的mAP达到64.15%,比YOLOv3-GIoU高出14%.所提出的CSYOLOv3方法能够有效地识别工件表面缺陷,对小缺陷的识别效果有明显提升.更多还原

【Abstract】 Surface small defects are often missed and incorrectly detected due to their small quantity and unapparent visual features. A method named CSYOLOv3, which is based on CutMix and YOLOv3, is proposed to solve such a problem. First, a four-image CutMix method is used to increase the small-defect quantity, and the process is dynamically adjusted based on the beta distribution. Then, the classic YOLOv3 is improved to detect small defects accurately. The shallow and large feature maps are split, and several of them are merged with the feature maps of the predicted branch to preserve the shallow features. The loss function of YOLOv3 is optimized and weighted to improve the attention to small defects. Finally, this method is used to detect 512 × 512 pixel images under RTX 2060 Ti GPU, which can reach the speed of 14.09 frame/s, and the mAP is 71.80%, which is 5%-10% higher than that of other methods. For small defects below 64 × 64 pixels, the mAP of the method reaches 64.15%, which is 14% higher than that of YOLOv3-GIoU. The surface defects of the workpiece can be effectively detected by the proposed method, and the performance in detecting small defects is significantly improved.更多还原