Yang Shihao, Jiao Dongmei, Wang Tongkun, He Yan
College of Mechanical and Electrical Engineering, Qingdao University of Science and Technology, Qingdao 266061, China.
Sensors (Basel). 2022 May 21;22(10):3907. doi: 10.3390/s22103907.
With the development of neural networks, object detection based on deep learning is developing rapidly, and its applications are gradually increasing. In the tire industry, detecting speckle interference bubble defects of tire crown has difficulties such as low image contrast, small object scale, and large internal differences of defects, which affect the detection precision. To solve these problems, we propose a new feature pyramid network based on Faster RCNN-FPN. It can fuse features across levels and directions to improve small object detection and localization, and increase object detection precision. The method has proven its effectiveness through cross-validation experiments. On a tire crown bubble defect dataset, the mAP [0.5:0.95] increased by 2.08% and the AP0.5 increased by 2.4% over the original network. The results show that the improved network significantly improves detecting tire crown bubble defects.
随着神经网络的发展，基于深度学习的目标检测发展迅速，其应用也在逐渐增加。在轮胎行业中，检测轮胎胎冠的斑点干涉气泡缺陷存在图像对比度低、目标尺度小以及缺陷内部差异大等困难，这影响了检测精度。为了解决这些问题，我们提出了一种基于Faster RCNN-FPN的新型特征金字塔网络。它可以跨层级和方向融合特征，以提高小目标检测和定位能力，并提高目标检测精度。该方法已通过交叉验证实验证明了其有效性。在一个轮胎胎冠气泡缺陷数据集上，与原始网络相比，mAP [0.5:0.95]提高了2.08%，AP0.5提高了2.4%。结果表明，改进后的网络显著提高了检测轮胎胎冠气泡缺陷的能力。
