Traffic Sign Detection via Efficient ROI Detector and Deep Convolution Neural Network

doi:10.23940/ijpe.20.10.p8.15661578

Int J Performability Eng ›› 2020, Vol. 16 ›› Issue (10): 1566-1578.doi: 10.23940/ijpe.20.10.p8.15661578

Previous Articles Next Articles

Traffic Sign Detection via Efficient ROI Detector and Deep Convolution Neural Network

Weiguo Pan^a,b,*, En Fu^a,b, Bingxin Xu^a,b, Songyin Dai^a,b, and Feng Pan^a,b

^aBeijing Key Laboratory of Information Service Engineering, Beijing Union University, Beijing, 100101, China;
^bCollege of Robotics, Beijing Union University, Beijing, 100020, China

Submitted on ; Revised on ; Accepted on
Contact: * E-mail address: ldtweiguo@buu.edu.cn
About author:Weiguo Pan is currently a lecturer in the Beijing Key Laboratory of Information Service Engineering at Beijing Union University. His research interests include machine learning, object detection, and intelligent driving.
En Fu is currently pursuing a master's degree in the College of Robotics at Beijing Union University. His research interests include machine learning and object detection.
Bingxin Xu is currently an associate professor in the Beijing Key Laboratory of Information Service Engineering at Beijing Union University. Her research interests include pattern recognition, computer vision, and digital image processing.
Songyin Dai is currently a faculty member in the Beijing Key Laboratory of Information Service Engineering at Beijing Union University. Her research interests include pattern recognition, computer vision, and digital image processing.
Feng Pan is currently an associate professor in the College of Robotics at Beijing Union University. His research interest includes machine learning and intelligent driving.

Abstract

Abstract: With the rapid development of intelligent driving and self-driving, how to quickly identify traffic signs in traffic scenes image is an urgent problem that needs to be solved. The existing object detection method can be divided into two categories: the one-staged method, which has a fast detection speed, and the two-stage method, which has higher detection accuracy. How to quickly and accurately detect targets in traffic scenes images is a current research focus. In this paper, an effective detection operator for the region of interest of traffic signs that utilizes the color, shape, and layout characteristics of traffic signs was proposed. It can accurately extract the region of interest in the traffic scene image for detection stage. The existing two-stage network was also fine-tuned to improve the accuracy of traffic sign detection. On the basis of the existing public data set, 13,000 images were collected and annotated to expand the training and test data. These data were used to verify the method proposed in this article. Experiments demonstrated that the proposed method has been improved in detection speed and detection accuracy.

Key words: region of interest, traffic sign, object detection, deep learning

Weiguo Pan, En Fu, Bingxin Xu, Songyin Dai, and Feng Pan. Traffic Sign Detection via Efficient ROI Detector and Deep Convolution Neural Network [J]. Int J Performability Eng, 2020, 16(10): 1566-1578.

Add to citation manager EndNote|Reference Manager|ProCite|BibTeX|RefWorks

References

1. S. Khalid, N. Muhammad,M. Sharif, “Automatic Measurement of the Traffic Sign with Digital Segmentation and Recognition,” IET Intelligent Transport Systems, Vol. 13, No. 2, pp. 269-279, February 2019
2. H. L. Luo, Y. Yang, B. Tong, F. C. Wu,B. Fan, “Traffic Sign Recognition using a Multi-Task Convolutional Neural Network,” IEEE Transactions on Intelligent Transportation Systems, Vol. 19, No. 4, pp. 1100-1111, April 2018
3. Z. L. He, F. T. Nan, X. F. Li, S. Y. Lee,Y. Yang, “Traffic Sign Recognition by Combining Global and Local Features based on Semi-Supervised Classification,” IET Intelligent Transport Systems, Vol. 14, No. 5, pp. 323-330, April 2020
4. Z. Zhu, J. M. Lu, R. R. Martin,S. M. Hu, “An Optimization Approach for Localization Refinement of Candidate Traffic Signs,” IEEE Transactions on Intelligent Transportation Systems, Vol. 18, No. 11, pp. 3006-3016, November 2017
5. J. Redmon, S. Divvala, R. Girshick,A. Farhadi, “You Only Look Once: Unified, Real-Time Object Detection,” inProceedings of 2016 IEEE Conference on Computer Vision and Pattern Recognition, pp. 779-788, Las Vegas, NV, December 2016
6. W. Liu, D. Anguelov, D. Erhan, C. Szegedy, S. Reed, C. Y. Fu, et al., “SSD: Singleshot Multibox Detector,” inProceedings of 14th European Conference on Computer Vision, pp. 21-37, Amsterdam, Netherlands, August 2016
7. J. Redmon and A. Farhadi, “YOLO9000: Better, Faster, Stronger,” inProceedings of IEEE Conference on Computer Vision and Pattern Recognition, pp. 6517-6525, Honolulu, HI, July 2017
8. J. Redmon and A. Farhadi, “YOLOv3: An Incremental Improvement,” arXiv:1804.02767, 2018
9. T. Lin, P. Goyal, R. Girshick,K. M. He, “Piotr Dollar. Focal Loss for Dense Object Detection,” inProceedings of International Conference on Computer Vision, pp. 2999-3007, Venice, Italy, December 2017
10. R. Girshick, J. Donahue, T. Darrell,J. Malik, “Rich Feature Hierarchies for Accurate Object Detection and Semantic Segmentation,” inProceedings of IEEE Conference on Computer Vision and Pattern Recognition, pp. 580-587, Columbus, USA, June 2014
11. R. Girshick, “Fast R-CNN,” inProceedings of IEEE International Conference on Computer Vision, pp. 1440-1448, Santiago, USA, December 2015
12. S. Q. Ren, K. M. He, R. Girshick,J. Sun, “Faster R-CNN: Towards Real-Time Object Detection with Region Proposal Networks,” IEEE Transactions on Pattern Analysis and Machine Intelligence, Vol. 39, No. 6, pp. 1137-1149, June 2017
13. K. M. He, G. Gkioxari, P. Dollár,R. Girshick, “Mask R-CNN,” inProceedings of IEEE International Conference on Computer Vision, pp. 2980-2988, Venice, Italy, October 2017
14. Y. Y. Zhu, M. H. Liao, M. K. Yang,W. Y. Liu, “Cascaded Segmentation-Detection Networks for Text-based Traffic Sign Detection,” IEEE Transactions on Intelligent Transportation Systems, Vol. 19, No. 1, pp. 209-219, January 2018
15. D. Tabernik and D. Skočaj, “Deep Learning for Large-Scale Traffic-Sign Detection and Recognition,” IEEE Transactions on Intelligent Transportation Systems, Vol. 21, No. 4, pp. 1427-1440, April 2020
16. U. Kamal, T. I. Tonmoy, S. Das,M. K. Hasan, “Automatic Traffic Sign Detection and Recognition using SegU-Net and a Modified Tversky Loss Function With L1-Constraint,” IEEE Transactions on Intelligent Transportation Systems, Vol. 21, No. 4, pp. 1467-1479, April 2020
17. Y. M. Jin, Y. S. Fu, W. Q. Wang, J. H. Guo, C. H. Ren,X. Xiang, “Multi-Feature Fusion and Enhancement Single Shot Detector for Traffic Sign Recognition,” IEEE Access, Vol. 8, pp. 38931-38940, February 2020
18. Y. Yuan, Z. T. Xiong,Q. Wang, “VSSA-NET: Vertical Spatial Sequence Attention Network for Traffic Sign Detection,” IEEE Transactions on Image Processing, Vol. 28, No. 7, pp. 3423-3434, July 2019
19. D. D. Wang, X. W. Hou, J. W. Xu, S. G. Yue,C. L. Liu, “Traffic Sign Detection using a Cascade Method With Fast Feature Extraction and Saliency Test,” IEEE Transactions on Intelligent Transportation Systems, Vol. 18, No. 12, pp. 3290-3302, December 2017
20. H. S.Lee and K. Kim, “Simultaneous Traffic Sign Detection and Boundary Estimation using Convolutional Neural Network,” IEEE Transactions on Intelligent Transportation Systems, Vol. 19, No. 5, pp. 1652-1663, May 2018

[1]	Janarthanan Sekar and Ganesh Kumar T. Hyperparameter Tuning in Deep Learning-Based Image Classification to Improve Accuracy using Adam Optimization [J]. Int J Performability Eng, 2023, 19(9): 579-586.
[2]	Sanjay Razdan, Himanshu Gupta, and Ashish Seth. D-SVM: A Deep Support Vector Machine Model with Different Kernel Types for Improved Intrusion Detection Performance [J]. Int J Performability Eng, 2023, 19(9): 598-606.
[3]	Aashita Rajput, Muskan Yadav, Sachin Yadav, Megha Chhabra, and Arun Prakash Agarwal. Patch-Based Breast Cancer Histopathological Image Classification using Deep Learning [J]. Int J Performability Eng, 2023, 19(9): 607-623.
[4]	Kavita Pandey, and Dhiraj Pandey. Real-Time Crop Disease Detection and Remedial Suggestion through Deep Learning-based Smartphone Application [J]. Int J Performability Eng, 2023, 19(8): 491-498.
[5]	Savita Khurana, Gaurav Sharma, and Bhawna Sharma. Hybrid Machine Learning Model for Load Prediction in Cloud Environment [J]. Int J Performability Eng, 2023, 19(8): 507-515.
[6]	Manvi Khatri and Ajay Sharma. Deep Learning Approach based on Iris, Face, and Palmprint Fusion for Multimodal Biometric Recognition System [J]. Int J Performability Eng, 2023, 19(6): 407-416.
[7]	Shreshtha Singh and Arun Sharma. State of the Art Convolutional Neural Networks [J]. Int J Performability Eng, 2023, 19(5): 342-349.
[8]	Vaishali Arya and Tapas Kumar. Boosting X-Ray Scans Feature for Enriched Diagnosis of Pediatric Pneumonia using Deep Learning Models [J]. Int J Performability Eng, 2023, 19(3): 175-183.
[9]	Shikha Choudhary and Bhawna Saxena. Image-Based Crop Disease Detection using Machine Learning Approaches: A Survey [J]. Int J Performability Eng, 2023, 19(2): 122-132.
[10]	Pavneet Singh, Jigyasa Chopra, Amandeep Singh, Nikita Nijhawan, and Kritika. Deep Learning Innovations for Enhanced Drusen Detection in Retinal Images [J]. Int J Performability Eng, 2023, 19(12): 779-787.
[11]	Mansi Mahendru and Sanjay Kumar Dubey. Portable Learning Approach towards Capturing Social Intimidating Activities using Big Data and Deep Learning Technologies [J]. Int J Performability Eng, 2022, 18(9): 668-678.
[12]	Sandhya Alagarsamy and Visumathi James. RNN LSTM-based Deep Hybrid Learning Model for Text Classification using Machine Learning Variant XGBoost [J]. Int J Performability Eng, 2022, 18(8): 545-551.
[13]	K. Lavanya, Smrithi Prakash, Yash Gedam, Altamash Aijaz, and L. Ramanathan. Real Time Digital Face Mask Detection using MobileNet-V2 and SSD with Apache Spark [J]. Int J Performability Eng, 2022, 18(8): 598-604.
[14]	Rajan Prasad Tripathi, Sunil Kumar Khatri, and Darelle Van Greunen. Relative Examination of Breast Malignant Growth Analysis Utilizing Different Machine Learning Algorithms [J]. Int J Performability Eng, 2022, 18(6): 417-425.
[15]	Poonam Narang, Ajay Vikram Singh, and Himanshu Monga. Hybrid Metaheuristic Approach for Detection of Fake News on Social Media [J]. Int J Performability Eng, 2022, 18(6): 434-443.

Traffic Sign Detection via Efficient ROI Detector and Deep Convolution Neural Network

PDF

Knowledge

Abstract

Cite this article

share this article

References

Related Articles 15

Recommended 0