Abstract
Traffic sign detection and recognition (TSDR) plays an important role in the fields for assistant driving, autonomous vehicle and so on. However, due to the complexity of real driving scene and variety of traffic signs, many challenging problems occurred, such as inaccurate color segmentation and time consumption of recognition algorithm based on deep learning. This paper describes an approach for efficiently detection and recognizing in real world scenarios. First of all, a traffic sign region of interest extraction algorithm based on multi-color space is proposed, the fusion future of HSV and RGB color space can obtain better color segmentation for the SVM classifier. Next a novel multi-scale two-stage lightweight network (MSTSN) is investigated, which adopts a coarse-to-fine strategy to improve recognition accuracy. Specially, the candidate Region of Interests (ROIs) are fed into a binary classification layer and only positive ones are further classified with multi-class classification network. The deeply separable convolution, residual structure and feature enhancement module is the bottleneck of MSTSN, which obtains more discriminative features and meets requirement for real-time performance. The experimental results successfully demonstrate effectiveness of our method.
Similar content being viewed by others
References
Agrawal S, Chaurasiya RK (2017) Ensemble of SVM for Accurate Traffic Sign Detection and Recognition. International Conference on Graphics and Signal Processing. ACM
Akatsuka H, Imai S (1987) Road signposts recognition system. In: proceedings of SAE vehicle highway infrastructure: safety compatibility, pp 189–196
Cheng P, Wu L, Zhang Y et al (2018) LOCO: Local Context Based Faster R-CNN for Small Traffic Sign Detection. International Conference on Multimedia Modeling
Ciresan D, Meier U, Schmidhuber J (2012) Multi-column deep neural networks for image classification. In: CVPR, pp 3642–3649
Ellahyani A, Mohamed EL, Ilyas EL, et al. (2016) Traffic Sign Detection and Recognition using Features Combination and Random Forests. International Journal of Advanced Computer Science and Applications, 7
Gao XW, Podladchikova L, Shaposhnikov D et al (2006) Recognition of traffic signs based on their colour and shape features extracted using human vision models. J Visual Commun Image Represent 17:675–685
Gomez-Moreno H, Maldonado-Bascon S, Gil-Jimenez P et al (2010) Goal evaluation of segmentation algorithms for traffic sign recognition. IEEE Trans Intell Transp Syst 11:917–930
Greenhalgh J, Mirmehdi M (2012) Real-time detectionn recognition of road traffic signs. IEEE Transactions on Intelligent Transportation Systems, pp 1498–1506
Greenhalgh J, Mirmehdi M (2012) Real-time detection and recognition of road traffic signs. IEEE Trans 13(4):1498–1506
He K, Zhang X, Ren S et al (2016) Deep Residual Learning for Image Recognition. IEEE Conference on Computer Vision and Pattern Recognition
Howard A, Sandler M, Chu G et al (2019) Searching for MobileNetV3. In: IEEE/CVF international conference on computer vision, pp 1314–1324
Howard A, Zhu M, Chen B et al (2017) MobileNets: Efficient Convolutional Neural Networks for Mobile Vision Applications. arXiv:1704.04861
Jia L, Zengfu W (2019) Real-time traffic sign recognition based on efficient CNNs in the wild. IEEE Trans Intell Transp Syst 20:1–10
Jie H, Li S, Gang S (2018) Squeeze-and-excitation networks. In: IEEE/CVF conference on computer vision and pattern recognition, pp 7132–7141
Jin J, Fu K, Zhang C (2014) Traffic sign recognition with hinge loss trained convolutional neural networks. In IEEE Trans 15(5):1991–2000
Jung S, Lee U, Jung J, et al. (2016) Real-time Traffic Sign Recognition system with deep convolutional neural network. International Conference on Ubiquitous Robots and Ambient Intelligence
Luo H, Yang Y, Tong B et al (2018) Traffic sign recognition using a Multi-Task convolutional neural network. IEEE Trans Intell Transp Syst 19:1100–1110
Madani A, Yusof R, Maliha A (2015) Traffic sign segmentation using supervised distance based classifiers. IEEE Control Conference
Onat E, Üzdil Ü (2015) Traffic sign classification using hough transform and SVM. In: Proceedings of signal processing and communications applications conference, pp 2161–2165
Sandler M, Howard A et al (2018) Mobilenetv2: Inverted Residuals and Linear Bottlenecks. In: IEEE/CVF conference on computer vision and pattern recognition, pp 4510–4520
Sermanet P, LeCun Y (2011) Traffic sign recognition with multi-scale convolutional networks. In: IJCNN, pp 2809–2813
Song Q, Zhang C, Tian Z et al (2018) Traffic sign recognition based on multiscale convolutional neural network. In: Journal of Hunan University: natural sciences edition, pp 131–137
Song W, fu M, Yi Y (2015) An efficient traffic sign recognition method for driverless cars. Robot 37(1):102–111
Yang Y, Luo H, Xu H, et al. (2016) Towards Real-Time Traffic Sign Detection and Classification. IEEE International Conference on Intelligent Transportation Systems
Yin S, Ouyang P, Liu L, Guo Y, Wei S (2015) Fast traffic sign recognition with a rotation invariant binary pattern based feature. Sensors 15(1):2161–2180
Zhang K, Sheng Y, Lv H (2015) Extraction of road traffic sign information based on a vehicle-borne mobile photogrammetric system. In: Photogramm Rec, pp 187–210
Zhu Z, Liang D, Zhang S et al (2016) Traffic-Sign Detection and Classification in the Wild. IEEE Conference on Computer Vision and Pattern Recognition
Acknowledgements
This work is supported by the National Natural Science Foundation of China (Grant No. U1833115).
Author information
Authors and Affiliations
Corresponding author
Additional information
Publisher’s note
Springer Nature remains neutral with regard to jurisdictional claims in published maps and institutional affiliations.
Mingzheng Hou and Xin Zhang have contributed equally to this paper.
Rights and permissions
About this article
Cite this article
Hou, M., Zhang, X., Chen, Y. et al. Traffic signs detection and recognition systems by light-weight multi-stage network. Multimed Tools Appl 81, 16155–16169 (2022). https://doi.org/10.1007/s11042-022-12201-x
Received:
Revised:
Accepted:
Published:
Issue Date:
DOI: https://doi.org/10.1007/s11042-022-12201-x