计算机工程与应用2019，Vol.55Issue(16)：235-239,245,6.DOI:10.3778/j.issn.1002-8331.1901-0068
基于改进的全卷积神经网络的路面裂缝分割技术
Pavement Crack Segmentation Technology Based on Improved Fully Convolutional Networks
摘要
Abstract
Cracks are one of the important diseases on the pavement surface. Traditional crack detection relies on manual visual inspection, which is time consuming and labor intensive. Although traditional image processing techniques can make crack detection and segmentation more automated to some extent. However, image processing techniques are sus-ceptible to some noise caused by illumination, blur, and the like. In order to complete the segmentation and detection of pavement cracks in complex environments, a segmentation method based on improved Fully Convolutional Networks (FCN)is proposed. According to the established data set, the traditional FCN and the optimized FCN are trained. The test results show that the mean Intersection over Union(mean_IoU)is improved, so the proposed method can segment the cracks accurately.关键词
裂缝检测/图像处理/全卷积网络(FCN)/平均交并比Key words
crack detection/ image processing/ Fully Convolutional Networks(FCN)/ mean intersection over union分类
信息技术与安全科学引用本文复制引用
翁飘,陆彦辉,齐宪标,杨守义..基于改进的全卷积神经网络的路面裂缝分割技术[J].计算机工程与应用,2019,55(16):235-239,245,6.基金项目
河南省技术创新引导专项(No.182106000027) （No.182106000027）
深圳市海外高层次人才资金(No. KQTD2015033114415450). （No. KQTD2015033114415450）
