基于卷积神经网络的多场景道路坑洼图像检测  

Multi-scene road pothole image detection based on convolutional neural network

作　　者：陈鹏 应骏[1] CHEN Peng;YING Jun(College of Information,Mechanical and Electrical Engineering,Shanghai Normal University,Shanghai 201418,China)

机构地区：[1]上海师范大学信息与机电工程学院,上海201418

出　　处：《上海师范大学学报（自然科学版）》2020年第1期96-101,共6页Journal of Shanghai Normal University(Natural Sciences)

摘　　要：对图像进行预处理,用卷积神经网络的方法训练数据集及调整参数,建立坑洼检测模型.实验结果表明:本算法的执行效果好于直接进行坑洼检测的方式,为道路坑洼检测提供了良好的解决方案.In this paper,the image was preprocessed firstly,then the dataset was trained and the parameters were adjusted by the convolutional neural network method.The experimental results showed that the performance of the algorithm was better than identifying the potholes directly,which provided a preferable solution for road pothole detection.

关 键 词：道路坑洼 检测 卷积神经网络 

分 类 号：TP391.41[自动化与计算机技术—计算机应用技术]