Traffic Sign Recognition Using an Attentive Context Region-Based Detection Framework

LIU Zhigang; DU Juan; TIAN Feng; WEN Jiazheng

doi:10.1049/cje.2021.08.005

Volume 30 Issue 6

Nov. 2021

Turn off MathJax

Article Contents

Article Navigation > Chinese Journal of Electronics > 2021 > 30(6): 1080-1086

LIU Zhigang, DU Juan, TIAN Feng, et al., “Traffic Sign Recognition Using an Attentive Context Region-Based Detection Framework,” Chinese Journal of Electronics, vol. 30, no. 6, pp. 1080-1086, 2021, doi: 10.1049/cje.2021.08.005

Citation:

LIU Zhigang, DU Juan, TIAN Feng, et al., “Traffic Sign Recognition Using an Attentive Context Region-Based Detection Framework,” Chinese Journal of Electronics, vol. 30, no. 6, pp. 1080-1086, 2021, doi: 10.1049/cje.2021.08.005

Citation:

PDF( 3494 KB)

Traffic Sign Recognition Using an Attentive Context Region-Based Detection Framework

doi: 10.1049/cje.2021.08.005

1. School of Computer and Information Technology, Northeast Petroleum University, Daqing 163318, China;
2. Postdoctoral Workstation on Applied Technology Research Institute, Northeast Petroleum University, Daqing 163318, China.;
3. Department of Computer Science for Artificial Intelligence, University of Nottingham Ningbo, Ningbo 315100, China

Funds:

This work is supported by the National Natural Science Foundation of China (No.61502094, No.51774090, No.51104030) and the Heilongjiang Province Natural Science Foundation of China (No.LH2020F003).

Received Date: 2019-02-20
Rev Recd Date: 2021-07-22

Available Online: 2021-09-23

Publish Date: 2021-11-05

Abstract

Abstract

Accurate small traffic sign recognition is more important for the safety of intelligent transportation systems. A recognition framework named attentive context region-based detection framework (AC-RDF) is proposed in this paper. We construct the attentive context feature for the recognition of small traffic signs, which combines the target information and the contextual information by the concatenation operation following a pointwise convolutional layer. The proposed attentive context feature exploits the surrounding information for a given object proposal. Next, we propose a novel attentive loss function to replace the original crossentropy function. It distinguishes hard negative samples from easy positive ones in the total loss, allows the proposed framework to obtain enough training, and further improve the recognition accuracy. The proposed method is evaluated on the challenging Tsinghua-Tencent 100K dataset. The experimental results indicate that the attentive context region-based detection framework is superior at detecting small traffic signs and achieves stateof-the-art performance compared with other methods.
- Small traffic sign,
- Attentive context,
- Attentive loss,
- Hard negative samples

FullText(HTML)

References(23)

References

S. Houben, J. Stallkamp, J. Salmen, et al., "Detection of traffic signs in real-world images:The German traffic sign detection benchmark", Proc. of IEEE International Joint Conference on Neural Networks (IJCNN), Dallas, Texas, USA, pp.1-8, 2013.

J. Stallkamp, M. Schlipsing, J. Salmen, et al., "The German traffic sign recognition benchmark:A multi-class classification competition", Proc. of IEEE International Joint Conference on Neural Networks (IJCNN), San Jose, California, USA, pp.1453-1460, 2011.

J. Greenhalgh and M. Mirmehdi, "Real-time detection and recognition of road traffic signs", IEEE Transactions on Intelligent Transportation Systems, Vol.13, No.4, pp.1498-1506, 2012.

H. Fleyeh and E. Davami, "Eigen-based traffic sign recognition", IET Intelligent Transport Systems, Vol.5, No.3, pp.190-196, 2020.

Z. Liu, J. Du, M. Wang, et al., "ADCM:Attention dropout convolutional module", Neurocomputing, Vol.394, pp.95-104, 2020.

N. Barnes, A. Zelinsky and L. S. Fletcher, "Real-time speed sign detection using the radial symmetry detector", IEEE Transactions on Intelligent Transportation Systems, Vol.9, No.2, pp.322-332, 2008.

M. Mathias, R. Timofte, R. Benenson, et al., "Traffic sign Recognition-How far are we from the solution", Proc. of IEEE International Joint Conference on Neural Networks (IJCNN), Dallas, Texas, USA, pp.1-8, 2013.

S. Liu, Y. Wu, Y. Ji, et al., "Research on security of key algorithms in intelligent driving system", Chinese Journal of Electronics, Vol.28, No.1, pp.30-38, 2019

Y. Yang, H. Luo, H. Xu, et al., "Towards real-time traffic sign detection and classification", IEEE Transactions on Intelligent Transportation Systems, Vol.17, No.7, pp.2022-2031, 2016.

Z. Huang, Y. Yu, J. Gu, et al., "An efficient method for traffic sign recognition based on extreme learning machine", IEEE Transactions on Cybernetics, Vol.47, No.4, pp.920-933, 2018.

X.Hou, H. Zhao and Y. Ma, "Fast image segmentation algorithm based on superpixel multi-feature fusion", Chinese Journal of Electronics, Vol.47, No.10, pp.2126-2132, 2019

H. Yan, H. Zhou and H. Zhang, "Automatic malware classification via PRICoLBP", Chinese Journal of Electronics, Vol.27, No.4, pp.853-859, 2018

P. Dollár, Z. Tu, P. Perona, et al., "Integral channel features", Proc. of the British Machine Conference, London, UK, pp.1-11, 2009.

P. Dollár, R. Appel, S. Belongie, et al., "Fast feature pyramids for object detection", IEEE Transactions on Pattern Analysis and Machine Intelligence, Vol.36, No.8, pp.1532-1545, 2014.

Y. Wu, Y. Liu, J. Li, et al., "Traffic sign detection based on convolutional neural networks", Proc. of IEEE International Joint Conference on Neural Networks (IJCNN), Dallas, Texas, USA, pp.1-7. 2013.

R. Qian, B. Zhang, Y. Yue, et al., "Robust Chinese traffic sign detection and recognition with deep convolutional neural network", Proc. of IEEE International Conference Natural Computation, Zhangjiajie, China, pp.791-796, 2015.

Y. Zhu, C. Zhang, D. Zhou, et al., "Traffic sign detection and recognition using fully convolutional network guided proposals", Neurocomputing, Vol.214, pp.758-766, 2016.

D. Ciresan, U. Meier and J. Schmidhuber, "Multi-column deep neural networks for image classification", Proc. of IEEE Conference on Computer Vision and Pattern RecoAgnition (CVPR), Rhode, Island, pp.3642-3649, 2012.

P. Sermanet and Y. LeCun, "Traffic sign recognition with multi-scale convolutional networks", Proc. of IEEE International Joint Conference on Neural Networks (IJCNN), San Jose, California, USA, pp.2809-2813, 2011.

J. Jin, K. Fu and C. Zhang, "Traffic sign recognition with hinge loss trained convolutional neural networks", IEEE Transactions on Intelligent Transportation Systems, Vol.15, No.5, pp.1991-2000, 2014.

A.Shrivastava, A.Gupta and R.Girshick, "Training regionbased object detectors with online hard example mining", Proc. of IEEE Conference on Computer Vision and Pattern RecoAgnition (CVPR),Las Vegas, Nevada, pp.3642-3649, 2016.

Girshick and Ross, "Fast R-CNN", Proc. of IEEE International Conference on Computer Vision (ICCV), Santiago, Chile, pp.1440-1448, 2015.

Z. Zhu, D. Liang, S. Zhang, et al., "Traffic-sign detection and classification in the wild", Proc. of IEEE Conference on Computer Vision and Pattern Recognition (CVPR), Las Vegas, Nevada, pp.2110-2118, 2016.

Relative Articles

Supplements(0)

Cited By

Proportional views