摘要
为提升特定道路图像数据集的质量,提出一种基于深度卷积生成式对抗网络(deep convolutional generative adversarial networks,DCGAN)的沥青路面裂缝图像生成方法。首先,通过车载运动相机拍摄和人工手机拍摄相结合的方式自主采集裂缝图像,得到较均衡且样本特征丰富的小型图像集;其次,对原始图像进行滤波去噪以及伽马变换操作,增强图中裂缝特征的辨识度,建立沥青路面裂缝数据训练集;第三,构建深度卷积生成式对抗神经网络模型,调整沥青路面裂缝图像生成网络的参数,并优化其网络超参数,更真实地生成路面裂缝图像数据集;最后,利用Faster R-CNN(regional convolutional neural network)检测网络对生成裂缝图像进行检测,验证生成图像在检测网络中的有效性。研究结果表明:基于深度卷积生成式对抗网络的方法能够生成较逼真裂缝图像;与常规增广方式相比,本文提出的方法能够更加有效地解决特定条件下数据集数量不足和质量不高的问题;将生成的虚拟图像与真实路面图像共同输入检测模型可以提高路面裂缝检测精度。
An asphalt pavement crack image generation method was proposed based on deep convolutional generative adversarial network(DCGAN) to improve the quality of a specific pavement image dataset. Firstly, the crack images were captured by a combination of in-vehicle motion camera photography and manual cell phone photography to obtain a more balanced and feature-rich sample small image set. Secondly, original images were denoised by filtering and gamma transformed to enhance the recognition of crack features in the plots, so that a training set of asphalt pavement crack data was created. Thirdly, a deep convolutional generative adversarial neural network model was constructed. The parameters of asphalt pavement crack image generation network were adjusted and its network hyperparameters was optimized to achieve a more realistic generation of pavement crack image dataset. Finally, faster regional convolutional neural network(R-CNN) detection network was used to detect the generated crack images, which can verify the effectiveness of the generated images in the detection network. The results show that the method based on deep convolutional generative adversarial network can generate more realistic crack images. The proposed method can address the problem of insufficient quantity and low quality of datasets under specific conditions more effectively than conventional augmentation methods.Inputting generated virtual images and real pavement images into the detection model can improve the pavement crack detection accuracy.
作者
裴莉莉
孙朝云
孙静
李伟
张赫
PEI Lili;SUN Zhaoyun;SUN Jing;LI Wei;ZHANG He(School of Information Engineering,Chang'an University,Xi'an 710064,China;Computer Network Center,Shihezi University,Shihezi 832003,China;Xi'an Xiangteng Micro-Electronics Technology Co.Ltd.,Xi'an 710068,China)
出处
《中南大学学报（自然科学版）》
EI
CAS
CSCD
北大核心
2021年第11期3899-3906,共8页
Journal of Central South University:Science and Technology
基金
国家重点研发计划项目(2018YFB1600202)
长安大学博士研究生创新能力培养项目(300203211241)。
关键词
道路检测
图像生成
深度卷积生成式对抗网络
深度学习
pavement detection
image generation
deep convolutional generation adversarial network(DCGAN)
deep learning
