Abstract
For the purpose of achieving effective detection of traffic signs and improving the network transfer ability in different road scenarios, a traffic sign detection network based on PosNeg-balanced anchors and domain adaptation named STDN is proposed. The network is mainly composed of an improved single-stage prediction network (ISPN) and a two-stage domain adaptive network (TDAN). Specifically, the ISPN is a unique single-stage detector that introduces an anchor frame calibration module and a feature matching module to alleviate the imbalance of positive and negative samples of anchor frames, strengthen the expression of feature alignment, and promote efficient detection. The TDAN uses global and local hierarchical domain adaptive modules to reduce inter-domain deviations and improve the network stability and inter-domain migration performance in complex, dynamic, and irregular road scene. The experimental results confirm that the STDN has the advantages of high detection accuracy, fast response speed, and excellent domain transfer performance. It has considerable potential for engineering applications.
Similar content being viewed by others
References
Zablocki, É.; Ben-Younes, H.; Pérez, P.; Cord, M.: Explain ability of vision-based autonomous driving systems: Review and challenges. arXiv (2021). http://arxiv.org/2101.05307.
Ayachi, R.; Afif, M.; Said, Y.; Abdelali, A.B.: Real-time implementation of traffic signs detection and identification application on graphics processing units. Int. J. Pattern Recogn. Artif. Intell. 35, 2150024 (2021)
Ibrahem, H.; Salem, A.; Kang, H.S.: Weakly supervised traffic sign detection in real time using single CNN architecture for multiple purposes. 2020 IEEE Int. Confer. Consumer Electr. (2020). Available: doi: https://doi.org/10.1109/icce46568.2020.9042974.
Shao, F.; Wang, X.; Meng, F.; Zhu, J.; Wang, D.; Dai, J.: Improved faster R-CNN traffic sign detection based on a second region of interest and highly possible regions proposal network. Sensors 19, 2288 (2019)
Zhang, J.; Xie, Z.; Sun, J.; Zou, X.; Wang, J.: A cascaded R-CNN with multiscale attention and imbalanced samples for traffic sign detection. IEEE Access 8, 29742–29754 (2020)
Liang, Z.; Shao, J.; Zhang, D.; Gao, L.: Traffic sign detection and recognition based on pyramidal convolutional networks. Neural Comput. Appl. 32, 256–264 (2020)
You, S.; Bi, Q.; Ji, Y.; Liu, S.; Feng, Y.; Wu, F.: Traffic sign detection method based on improved ssd. Information 11, 475 (2020)
Dewi, C.; Chen, R.C.; Liu, Y.T.; Jiang, X.; Hartomo, K.D.: Yolo V4 for advanced traffic sign recognition with synthetic training data generated by various GAN. IEEE Access 9, 97228–97242 (2021)
Arcos-Garcia, A.; Alvarez-Garcia, J.A.; Soria-Morillo, L.M.: Evaluation of deep neural networks for traffic sign detection systems. Neurocomputing 316, 332–344 (2018)
Wang, W.; Chen, S.; Xiang, Y.; Sun, J.; Li, H.; Wang, Z.; Li, B.: Sparsely-labeled source assisted domain adaptation. Pattern Recogn. 112, 107803 (2021)
Wang, W.; Li, P.; Wang, M.; Nie, F.; Wang, Z.; Li, H.: Confidence regularized label propagation based domain adaptation. Circuit Syst. Video Technol. 36, 9841 (2021)
Wang, W.; Li, H.; Ding, Z.; Nie, F.; Chen, J.; Dong, X.; Wang, Z.: Rethinking maximum mean discrepancy for visual domain adaptation. IEEE T Neural Netw. Learn. Syst. (2021). https://doi.org/10.1109/TNNLS.2021.3093468
Ben-David, S.; Blitzer, J.; Crammer, K.; Pereira, F.: Analysis of representations for domain adaptation. Adv. Neural Inform. Process. Syst. 19, 137 (2007)
Jiang, J.: A literature survey on domain adaptation of statistical classifiers. 3, 3(2008)
Nguyen, T. H.; Plank, B.; Grishman, R.: Semantic Representations for Domain Adaptation: A Case Study on the Tree Kernel-based Method for Relation Extraction. Proceeding 53rd Annual Meeting Association Computer Linguistics 7th International Joint Conference National Language Process. 2015. Available: doi: https://doi.org/10.3115/v1/p15-1062.
Yoo, H.J.: Deep convolution neural networks in computer vision: a review. IEIE T Smart Process. Comput. 4, 35–43 (2015)
Zhou, X.; Zhuo, J.; Krahenbuhl, P.: Bottom-up object detection by grouping extreme and center points. CVPR 3, 850–859 (2019)
Chen, Y.; Zhang, Z.; Cao, Y.; Wang, L.; Lin, S.; Hu, H.: Reppoints v2: Verification meets regression for object detection. (2020). https://arxiv.org/2007.08508.
Sun, Z.; Cao, S.; Yang, Y.; Kitani, K. M.: Rethinking transformer-based set prediction for object detection. In Proceedings of the IEEE/CVF International Conference on Computer Vision pp. 3611–3620 (2021).
Liu, W.; Anguelov, D.; Erhan, D.; Szegedy, C.; Reed, S.E.; Fu, C.; Berg, A.C.: SSD: single shot multibox detector. ECCV 2, 21–37 (2016)
Redmon, J.; Divvala, S.K.; Girshick, R.B.; Farhadi, A.: You only look once: Unified, real-time object detection. CVPR 6, 779–788 (2016)
Ren, S.; He, K.; Girshick, R.B.; Sun, J.: Faster R-CNN: towards real-time object detection with region proposal networks. IEEE Trans. Pattern Anal. Mach. Intell. 39, 1137–1149 (2017)
Shrivastava, A.; Gupta, A.; Girshick, R.B.: Training region-based object detectors with online hard example mining. CVPR 5, 761–769 (2016)
Lin, T.; Goyal, P.; Girshick, R.B.; He, K.; Doll, P.: Focal loss for dense object detection. ICCV 8, 2999–3007 (2017)
Li, B.; Liu, Y.; Wang, X.: Gradient harmonized singlestage detector. AAAI 7, 8577–8584 (2019)
Han, J.; Ding, J.; Li, J.; Xia, G.S.: Align deep features for oriented object detection. IEEE Geosci. Remote Sens. 612, 574 (2021)
Zhang, S.; Wen, L.; Bian, X.; Lei, Z.; Li, S.L.: Single-Shot Refinement Neural Network for Object Detection. 2018 IEEE/CVF Conference Computer Vision Pattern Recognition 2018. Available: doi: https://doi.org/10.1109/cvpr.2018.00442.
Chi, C.; Zhang, S.; Xing, J.; Lei, Z.; Li, S.Z.; Zou, X.: Selective refinement network for high performance face detection. Proceeding AAAI conference artificial intelligence 33, 8231-8238(2019)
Li, B.; Liu, Y.; Wang, X.: Gradient harmonized single-stage detector. Proceeding AAAI conference artificial intelligence 33, 8577-8584(2019)
Nie, J.; Anwer, R. M.; Cholakkal, H.; Khan, F. S.; Pang, Y.; Shao, L.: Enriched feature guided refinement network for object detection. Proceedings of the IEEE/CVF International Conference on Computer Vision pp. 9537–9546, (2019).
Saito, K.; Ushiku, Y.; Harada, T.; Saenko, K.: Strong-weak distribution alignment for adaptive object detection. In Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, pp. 6956–6965, (2019).
Chen, Y.; Li, W.; Sakaridis, C.; Dai, D.; Van Gool, L.: Domain adaptive faster RCNN for object detection in the wild. 2018 IEEE/CVF Conference Computer Vision Pattern Recognition 2018. Available: doi: https://doi.org/10.1109/cvpr.2018.00352.
RoyChowdhury, A.: Automatic adaptation of object detectors to new domains using self-training. 2019 IEEE/CVF Conference Computer Vision Pattern Recognition (2019).
Kim, T.; Jeong, M.; Kim, S.; Choi, S. Kim, C.: Diversify and Match: A Domain Adaptive Representation Learning Paradigm for Object Detection. 2019 IEEE/CVF Conference Computer Vision Pattern Recognition (2019). Available: doi: https://doi.org/10.1109/cvpr.2019.01274.
Hsu, H. K.; Yao, C. H.; Tsai, Y. H.; Hung, W. C.; Tseng, H. Y.; Singh, M.; Yang, M. H.: Progressive domain adaptation for object detection. In Proceedings of the IEEE/CVF Winter Conference on Applications of Computer Vision, pp. 749–757, (2020).
Liu, Y.; Liu, Z.; Fang, F.; Fu, Z.; Chen, Z.: Hierarchical domain-consistent network for cross-domain object detection. 2021 IEEE Int. Confer. Image Process. pp. 474–478, (2021).
Bahlmann, C.; Zhu, Y.; Ramesh, V.; Pellkofer, M.; Koehler, T.: A system for traffic sign detection, tracking, and recognition using color, shape, and motion information. IEEE Proceeding Intelligence Vehicles Symposium, pp. 255–260, (2005).
Zhu, Z.; Liang, D.; Zhang, S.; Huang, X.; Li, B.; Hu, S.: Traffic-sign detection and classification in the wild. In Proceedings of the IEEE conference on computer vision and pattern recognition, pp. 2110–2118, (2016).
Liu, Z.; Shen, C.; Fan, X.; Zeng, G.; Zhao, X.: Scale-aware limited deformable convolutional neural networks for traffic sign detection and classification. IET Intell. Transp. Syst. 14, 1712–1722 (2020)
Liu, Y.; Peng, J.; Xue, J.H.; Chen, Y.; Fu, Z.H.: TSingNet: Scale-aware and context-rich feature learning for traffic sign detection and recognition in the wild. Neurocomputing 447, 10–22 (2021)
Di, S.; Zhang, H.; Li, C.G.: Cross-domain traffic scene understanding: A dense correspondence-based transfer learning approach. IEEE T Intell. Transp. Syst. 19, 745–757 (2017)
Peng, X.; Li, Y.; Wei, X.; Luo, J.; Murphey, Y. L.: Traffic sign recognition with transfer learning. 2017 IEEE Symposium Series Computer Intelligence pp. 1–7, 2017.
Liu, Z.; Shen, C.; Qi, M.; Fan, X.: SADANet: integrating scale-aware and domain adaptive for traffic sign detection. IEEE Access 8, 77920–77933 (2020)
Wu, Y.; Li, Z.; Chen, Y.; Nai, K.; Yuan, J.: Real-time traffic sign detection and classification towards real traffic scene. Multim. Tools Appl. 79, 18201–18219 (2020)
Arruda, V.F.; Paixão, T.M.; Berriel, R.F.; Souza, A.F.D.; Badue, C.; Sebe, N.; Oliveira-Santos, T.: Cross-domain car detection using unsupervised image-to-image translation: from day to night. Comput. Vision Pattern Recogn. (2019). https://doi.org/10.1109/IJCNN.2019.8852008
Liu, Z.; Qi, M.; Shen, C.; Fang, Y.; Zhao, X.: Cascade saccade machine learning network with hierarchical classes for traffic sign detection. Sustain. Cities Soc. 67, 102700 (2021)
Tang, Q.; Hu, Y.: Single stage target detection algorithm based on positive and negative anchor frame equalization and feature alignment. Chinese J. Computer Aided Des. Gr. 32, 70–80 (2020)
Lin, T. Y.; Goyal, P.; Girshick, R. , He, K.; Dollár, P.: Focal Loss for Dense Object Detection. 2017 IEEE International Conference Computer Vision (2017).
Houben, S.; Stallkamp, J.; Salmen, J.; Schlipsing, M.; Igel, C. Detection of traffic signs in real-world images: The German Traffic Sign Detection Benchmark. 2013 International Joint Conference Neural Networks, pp. 1–8, (2013).
Zhu, Z.; Liang, D.; Zhang, S.; Huang, X.; Li, B.; Hu, S.: Traffic-Sign Detection and Classification in the Wild. 2016 IEEE Conference Computer Vision Pattern Recognition (2016). Available: doi: https://doi.org/10.1109/cvpr.2016.232.
Zhang, J.; Huang, M.; Jin, X.; Li, X.: A real-time chinese traffic sign detection algorithm based on modified YOLOv2. Algorithms 10, 127 (2017)
Ultralytics. yolov5. Available online: https://github.com/ultralytics/yolov5 (accessed on 18 May 2020).
Yu, C.; Wang, J.; Chen, Y.; Huang, M.: Transfer learning with dynamic adversarial adaptation network. 2019 IEEE International Conference Data Mining pp. 778–786, (2019).
Acknowledgements
We thank the anonymous reviewers for the helpful comments. We are grateful to the Department of Mechanical Engineering, College of Field Engineering and Army Engineering University, PLA.
Author information
Authors and Affiliations
Corresponding author
Rights and permissions
About this article
Cite this article
Lu, G., He, X., Wang, Q. et al. A Traffic Sign Detection Network Based on PosNeg-Balanced Anchors and Domain Adaptation. Arab J Sci Eng 48, 1333–1347 (2023). https://doi.org/10.1007/s13369-022-06818-1
Received:
Accepted:
Published:
Issue Date:
DOI: https://doi.org/10.1007/s13369-022-06818-1