基于卷积神经网络的路面坑槽与拥包病害识别

Identification Method of Pavement Potholes and Upheavals Disease Based on Convolutional Neural Networks

坑槽与拥包作为城市沥青路面的主要损坏类型,若不及时进行修复,会造成路面的结构性破坏,缩短道路的使用寿命。为了进一步提高路面坑槽与拥包的识别精度与效率,采用三维数据图像作为训练样本,提出新的卷积神经网络病害识别模型;采用激光面扫描技术获取高精度沥青路面三维数据,开发道路坑槽与拥包分类模型CNN 1。结果表明:CNN 1模型能够显著提高坑槽与拥包病害分类识别准确率和精确率,有效地提高了城市道路中坑槽与拥包病害的检测及分析效率。

As the dominating damage types of asphalt pavement,potholes and upheavals are likely to further develop and cause structural damage to the pavement,shortening the life of the road.In order to improve the recognition accuracy and efficiency of pavement potholes and upheavals,a new convolution neural network potholes and upheavals disease identification model is proposed by using 3-dimensional data images as training samples.Using the laser surface scanning technology to obtain the 3 Dimensional high-precision pavement data of the asphalt pavement to establish the classification model CNN 1.The results show that CNN 1 model can not only significantly improve the classification and recognition accuracy of pothole and upheaval but also effectively improves the detection efficiency and accuracy of pavement potholes and upheavals.