特征提取
人工智能
卷积神经网络
计算机科学
棱锥(几何)
模式识别(心理学)
特征(语言学)
分割
交叉熵
熵(时间箭头)
交叉口(航空)
图像分割
人工神经网络
计算机视觉
工程类
数学
几何学
物理
哲学
量子力学
航空航天工程
语言学
作者
Yu Liu,Huaxi Xiao,Jiaming Xu,Jingyi Zhao
出处
期刊:IEEE Transactions on Instrumentation and Measurement
[Institute of Electrical and Electronics Engineers]
日期:2022-01-01
卷期号:71: 1-10
被引量:29
标识
DOI:10.1109/tim.2022.3165287
摘要
The application of computer vision technology in defect detection of industrial products is a popular research direction in recent years. This article presents the pyramid feature convolutional neural network (CNN) for defect detection of rail surfaces. First, multi-scale feature maps are extracted based on the characteristics of defects and backgrounds by the pyramid feature extraction module (PFEM). Then the feature maps are input to a lightweight network consisting of a small number of parameters. The network is trained with only 40% data of the dataset using binary cross-entropy loss function and the intersection of union (IOU) loss function. In the experiment, the performance of the proposed method is evaluated using the rail surface defect dataset (RSDD) dataset by comparing it with other methods. The experimental results show that the segmentation performance and real-time performance of the proposed method are better than those of other methods.
科研通智能强力驱动
Strongly Powered by AbleSci AI