高忠文;于立国;

• 1:哈尔滨理工大学

摘要(Abstract)：

针对小尺寸、远距离的交通标志检测过程中缺少信息的问题,以改进的更快速区域卷积神经网络(Faster R-CNN)检测器为基础,结合生成对抗网络(GAN)的目标检测算法实现对小目标交通标志的检测。Faster R-CNN首先根据期望目标设定合适的锚点数量,生成包含小目标的候选区域,再使用生成网络对候选区域中的模糊小目标进行上采样,生成高分辨率图像,最后使用分类损失函数与回归损失函数对判别网络进行改进。试验结果表明,Faster R-CNN和生成对抗网络相结合的检测算法可以提高远距离小目标交通标志检测性能。

关键词(KeyWords)： 交通标志检测;更快速区域卷积神经网络;生成对抗网络;超分辨重建

Abstract:

Keywords:

基金项目(Foundation):

作者(Authors): 高忠文;于立国;

DOI: 10.19620/j.cnki.1000-3703.20190694

参考文献(References)：

• [1]REDMON J,DIVVALA S,GIRSHICK R,et al.You Only Look Once:Unified,Real-Time Object Detection[C]//IEEEConference on Computer Vision and Pattern Recognition,2016:779-788.
• [2]LIU W,ANGUELOV D,ERHAN D,et al.SSD:Single Shot Multi Box Detector[C]//European Conference on Computer Vision,2016:21-37.
• [3]REN S,HE K,GIRSHICK R,et al.Faster R-CNN:Towards Real-Time Object Detection with Region Proposal Networks[J].IEEE Transactions on Pattern Analysis and Machine Intelligence,2015,39(6):1137-1149.
• [4]BELL S,ZITNICK C L,BALA K,et al.Inside-Outside Net:Detecting Objects in Context with Skip Pooling and Recurrent Neural Networks[C]//IEEE Conference On Computer Vision&Pattern Recognition,2015:2874-2883.
• [5]HE K,ZHANG X,REN S,et al.Spatial Pyramid Pooling in Deep Convolutional Networks for Visual Recognition[J].IEEE Transactions on Pattern Analysis&Machine Intelligence,2015,37(9):1904-1916.
• [6]EGGERT C,BREHM S,WINSCHEL A,et al.A Closer Look:Small Object Detection in Faster R-CNN[C]//2017IEEE International Conference on Multimedia and Expo(ICME).IEEE Computer Society,2017:167-174.
• [7]XU X,SUN D,PAN J,et al.Learning to Super-Resolve Blurry Face and Text Images[C]//The IEEE International Conference on Computer Vision(ICCV),2017:251-260.
• [8]CHEN X,DU K K,ZHU Y.3d Object Proposals for Accurate Object Class Detection[C]//Proceedings of Neural Information Processing Systems,2015:424-432.
• [9]GOODFELLOW I J,POUGET-ABADIE J,MIRZA M,et al.Generative Adversarial Networks[J].Advances in Neural Information Processing Systems,2014,3:2672-2680.
• [10]LEDIG C,THEIS L,HUSZAR F,et al.Photo-Realistic Single Image Super-Resolution Using a Generative Adversarial Network[C]//IEEE Conference On Computer Vision&Pattern Recognition,2017:105-114.
• [11]王坤峰,苟超,段艳杰.生成式对抗网络GAN的研究进展与展望[J].自动化学报,2017(3):321-332.
• [12]HE K,ZHANG X,REN S,et al.Deep Residual Learning for Image Recognition[C]//Proceedings of the IEEEConference on Computer Vision&Pattern recognition,2016:770-778.