基于改进R-FCN的交通标志检测

doi:10.19678/j.issn.1000-3428.0060093

摘要/Abstract

摘要： 为在交通标志检测过程中同时满足精度和速度的需求，建立一种改进的基于区域全卷积网络（R-FCN）的交通标志检测模型。通过K-means聚类算法对数据集进行分析，选择合适的锚点框。对特征提取网络ResNet101进行结构简化，只使用前25层来提取特征，以缩短检测时间。在模型中引入可变形卷积和可变形位置敏感RoI池化层，以提高模型对交通标志的感应能力。模型训练过程中使用在线困难样本挖掘策略从而减少简单样本数量。在交通标志检测数据集GTSDB上的实验结果表明，该模型对交通标志位置信息较敏感，AP₅₀和AP₇₅指标分别达到97.8%和94.7%，检测时间缩至48 ms，检测精度与速度优于Faster R-CNN、R-FCN等模型。

关键词: 交通标志, 区域全卷积网络, ResNet101网络, 可变形卷积, 可变形位置敏感RoI池化

Abstract: To meet both the precision and speed requirements in the process of traffic sign detection, this paper proposes an improved traffic sign detection model based on improved Region-based Fully Convolutional Network(R-FCN).By analyzing the data set through the K-means clustering algorithm, the appropriate anchor box is selected.Then the structure of the feature extraction network, ResNet101, is simplified, and only the first 25 layers are used for feature extraction to reduce the detection time.The deformable convolution and the deformable position-sensitive RoI pooling layer are introduced into the model to improve the ability of the model to sense traffic signs.In the training process, the online hard example mining strategy is used to reduce the number of simple samples.The experimental results on the GTSDB dataset for traffic sign detection show that the improved model is more sensitive to traffic sign location information.Its AP₅₀ reaches 97.8%, and the AP₇₅ reaches 94.7%.The model also reduces the detection time to 48 ms, displaying a higher accuracy and speed than Faster R-CNN, R-FCN and other models.

Key words: traffic sign, Region-based Fully Convolutional Network(R-FCN), ResNet101, deformable convolution, deformable position-sensitive RoI pooling

中图分类号:

TP391

喻清挺, 喻维超, 喻国平. 基于改进R-FCN的交通标志检测[J]. 计算机工程, 2021, 47(12): 285-290,298.

YU Qingting, YU Weichao, YU Guoping. Traffic Sign Detection Based on Improved R-FCN[J]. Computer Engineering, 2021, 47(12): 285-290,298.

http://www.ecice06.com/CN/Y2021/V47/I12/285

图/表 12

20211214182845

20211214182849

20211214182852

20211214182856

20211214182859

20211214182903

20211214182906

20211214182909

20211214182913

20211214182916

20211214182920

20211214182923

参考文献

[1] RUTA A, LI YO M, LIU X H.Towards real-time traffic sign recognition by class-specific discriminative features[EB/OL].[2020-10-02].https://bura.brunel.ac.uk/bitstream/2438/14127/1/FullText.pdf.
[2] GAO X, HONG K, PASSMORE P, et al.Colour vision model-based approach for segmentation of traffic signs[J].Eurasip Journal on Image & Video Processing, 2008(1):1-7.
[3] 王方石, 王坚, 李兵, 等.基于深度属性学习的交通标志检测[J].吉林大学学报(工学版), 2018, 48(1):319-329. WANG F S, WANG J, LI B, et al.Deep attribute learning based traffic sign detection[J].Journal of Jilin University(Engineering and Technology Edition), 2018, 48(1):319-329.(in Chinese)
[4] LOY G, BARNES N.Fast shape-based road sign detection for a driver assistance system[C]//Proceedings of 2004 IEEE/RSJ Internatioal Conference on Intelligent Robots and Systems.Washington D.C., USA:IEEE Press, 2004:70-75.
[5] 朱双东, 张懿, 陆晓峰.三角形交通标志的智能检测方法[J].中国图象图形学报, 2006, 11(8):1127-1131. ZHU S D, ZHANG Y, LU X F.Intelligent approach for triangle traffic sign detection[J].Journal of Image and Graphics, 2006, 11(8):1127-1131.(in Chinese)
[6] XIE Y, LIU L F, LI C H, et al.Unifying visual saliency with HOG feature learning for traffic sign detection[C]//Proceedings of 2009 IEEE Intelligent Vehicles Symposium.Washington D.C., USA:IEEE Press, 2009:24-29.
[7] ZAKLOUTA F, STANCIULESCU B.Real-time traffic sign recognition using spatially weighted HOG trees[C]//Proceedings of 2011 International Conference on Advanced Robotics.Washington D.C., USA:IEEE Press, 2011:61-66.
[8] BARÓ X, ESCALERA S, VITRIÀ J, et al.Traffic sign recognition using evolutionary Adaboost detection and forest-ECOC classification[J].IEEE Transactions on Intelligent Transportation Systems, 2009, 10(1):113-126.
[9] KRIZHEVSKY A, SUTSKEVER I, HINTON G E.Imagenet classification with deep convolutional neural networks[EB/OL].[2020-10-02].https://web.cs.ucdavis.edu/~yjlee/teaching/ecs289g-winter2018/alexnet.pdf.
[10] ZHU Z, LIANG D, ZHANG S H, et al.Traffic-sign detection and classification in the wild[C]//Proceedings of IEEE Conference on Computer Vision and Pattern Recognition.Washington D.C., USA:IEEE Press, 2016:2110-2118.
[11] ZHANG Z, ZHOU X L, CHAN S X, et al.Faster R-CNN for small traffic sign detection[C]//Proceedings of CCF Chinese Conference on Computer Vision.Berlin, Germany:Springer, 2017:155-165.
[12] REN S, HE K M, GIRSHICK R, et al.Faster R-CNN:towards real-time object detection with region proposal networks[J].IEEE Transactions on Pattern Analysis & Machine Intelligence, 2017, 39(6):1137-1149.
[13] ZHANG J M, HUANG M T, JIN X K, et al.A real-time Chinese traffic sign detection algorithm based on modified YOLOv2[J].Algorithms, 2017, 10(4):127-129.
[14] LIU Z G, DU J, TIAN F, et al.MR-CNN:a multi-scale region-based convolutional neural network for small traffic sign recognition[J].IEEE Access, 2019, 7:57120-57128.
[15] REDMON J, DIVVALA S, GIRSHICK R, et al.You only look once:unified, real-time object detection[C]//Proceedings of IEEE Conference on Computer Vision and Pattern Recognition.Washington D.C., USA:IEEE Press, 2016:779-788.
[16] LIU W, ANGUELOV D, ERHAN D, et al.SSD:single shot multibox detector[C]//Proceedings of European Conference on Computer Vision.Berlin, Germany:Springer, 2016:21-37.
[17] LIN T Y, DOLLÁR P, GIRSHICK R, et al.Feature pyramid networks for object detection[C]//Proceedings of IEEE Conference on Computer Vision and Pattern Recognition.Washington D.C., USA:IEEE Press, 2017:2117-2125.
[18] DAI J F, LI Y, HE K M, et al.R-FCN:object detection via region-based fully convolutional networks[EB/OL].[2020-10-02].https://arxiv.org/pdf/1605.06409.pdf.
[19] DAI J F, QI H Z, XIONG Y W, et al.Deformable convolutional networks[C]//Proceedings of IEEE International Conference on Computer Vision.Washington D.C., USA:IEEE Press, 2017:764-773.
[20] HE K M, ZHANG X Y, REN S Q, et al.Deep residual learning for image recognition[C]//Proceedings of IEEE Conference on Computer Vision and Pattern Recognition.Washington D.C., USA:IEEE Press, 2016:770-778.
[21] SHRIVASTAVA A, GUPTA A, GIRSHICK R.Training region-based object detectors with online hard example mining[C]//Proceedings of IEEE Conference on Computer Vision and Pattern Recognition.Washington D.C., USA:IEEE Press, 2016:761-769.
[22] HOUBEN S, STALLKAMP J, SALMEN J, et al.Detection of traffic signs in real-world images:the German traffic sign detection benchmark[C]//Proceedings of 2013 International Joint Conference on Neural Networks.Washington D.C., USA:IEEE Press, 2013:1-8.
[23] BOCHKOVSKIY A, WANG C Y, LIAO H Y M.YOLOv4:optimal speed and accuracy of object detection[EB/OL].[2020-10-02].https://arxiv.org/pdf/2004.10934.pdf.

选择文件类型/文献管理软件名称

选择包含的内容