综合特征分段组稀疏编码的交通标志识别方法

doi:10.3778/j.issn.1673-9418.2412052

摘要/Abstract

摘要： 随着无人驾驶、辅助驾驶等技术的发展，交通标志识别（TSR）问题被更多的研究者所关注。目前，在普通交通环境下的TSR问题得到了较好的解决，但当环境中存在交通标志模糊、部分遮挡等噪声干扰时，其TSR的处理效果并不理想。针对该问题进行研究，提出了一种新颖的结合孪生网络的综合特征分段组稀疏编码的TSR问题解决方法。提取交通标志的多个不同尺度特征编码，并提出利用综合特征编码的方法来表征交通标志；通过提出的分段组稀疏编码方法对交通标志的综合特征编码进行优化，以改善模型对编码的学习能力，提高编码的鲁棒性；构建了用于分段组稀疏编码训练的孪生神经网络模型，该模型因其简单的结构和较少的层数使其不易出现过拟合问题，同时所提模型也具有较少的参数量，较大幅度提升了模型的运算速度。实验表明，所提方法在TT100K数据集原始环境、运动模糊环境中，与目前SOTA模型最好成绩相比其准确率、精确率、召回率与F1分数等评价指标相近，模型参数量减少70.8%，FPS提升51.4%；在部分遮挡噪声环境中，各指标均显著优于目前SOTA模型最好成绩，尤其在遮挡率为60%时，所提方法的准确率和FPS分别较目前SOTA模型最好成绩提升了0.118和27 FPS。

关键词: 计算机视觉, 交通标志识别, 分段组稀疏编码, 孪生神经网络

Abstract: With the development of technologies such as autonomous driving and advanced driver assistance systems, the issue of traffic sign recognition (TSR) has garnered increasing attention from researchers. Currently, TSR in normal traffic environments has been well addressed, but the performance degrades significantly when there are noise interferences such as blurred or partially obstructed traffic signs. A novel TSR problem solving method combining siamese network and comprehensive feature segmentation group sparse coding is proposed to address this issue. Firstly, multiple different scale feature encodings of traffic signs are extracted, and a method using comprehensive feature encoding to represent traffic signs is proposed. Secondly, the proposed segment group sparse coding method optimizes the comprehensive feature encoding of traffic signs to enhance the model’s learning ability and improve the robustness of the encoding. Finally, a twin neural network model is constructed to train the segment group sparse coding. Due to its simple structure and fewer layers, this model is less prone to overfitting. Additionally, the proposed model requires fewer parameters, significantly improving computational speed. Experiments show that the proposed method achieves performance on par with the current SOTA models in terms of accuracy, precision, recall, and F1-score on the TT100K dataset in both the original and motion-blurred environments. Moreover, the computational parameters are reduced by 70.8%, and FPS is increased by 51.4%. In environments with partially obstructed signs, the proposed method performs notably better than the current SOTA models, especially when the occlusion rate reaches 60%, where accuracy and FPS are improved by 0.118 and 27 FPS respectively.

Key words: computer vision, traffic sign recognition, segmented group sparse coding, siamese neural network

朱逸峰, 奚峥皓, 郑阳, 刘翔, 刘亚奇, 张星. 综合特征分段组稀疏编码的交通标志识别方法[J]. 计算机科学与探索, 2025, 19(10): 2712-2721.

ZHU Yifeng, XI Zhenghao, ZHENG Yang, LIU Xiang, LIU Yaqi, ZHANG Xing. Traffic Sign Recognition Method Based on Comprehensive Feature Segmentation Group Sparse Coding[J]. Journal of Frontiers of Computer Science and Technology, 2025, 19(10): 2712-2721.

参考文献

[1] SAADNA Y, BEHLOUL A. An overview of traffic sign detection and classification methods[J]. International Journal of Multimedia Information Retrieval, 2017, 6(3): 193-210.
[2] ARDIANTO S, CHEN C J, HANG H M. Real-time traffic sign recognition using color segmentation and SVM[C]//Proceedings of the 2017 International Conference on Systems, Signals and Image Processing. Piscataway: IEEE, 2017: 1-5.
[3] GONZALEZ á, GARRIDO M á, LLORCA D F, et al. Auto-matic traffic signs and panels inspection system using computer vision[J]. IEEE Transactions on Intelligent Transportation Systems, 2011, 12(2): 485-499.
[4] KUO W J, LIN C C. Two-stage road sign detection and recognition[C]//Proceedings of the 2007 IEEE International Conference on Multimedia and Expo. Piscataway: IEEE, 2007: 1427-1430.
[5] WALI S B, HANNAN M A, HUSSAIN A, et al. An automatic traffic sign detection and recognition system based on colour segmentation, shape matching, and SVM[J]. Mathematical Problems in Engineering, 2015(1): 250461.
[6] ZAKLOUTA F, STANCIULESCU B. Warning traffic sign recognition using a HOG-based K-d tree[C]//Proceedings of the 2011 IEEE Intelligent Vehicles Symposium. Piscataway: IEEE, 2011: 1019-1024.
[7] KUS M C, GOKMEN M, ETANER-UYAR S. Traffic sign recognition using scale invariant feature transform and color classification[C]//Proceedings of the 2008 23rd International Symposium on Computer and Information Sciences. Piscataway: IEEE, 2008: 1-6.
[8] REN F X, HUANG J S, JIANG R Y, et al. General traffic sign recognition by feature matching[C]//Proceedings of the 2009 24th International Conference on Image and Vision Computing. Piscataway: IEEE, 2009: 409-414.
[9] STALLKAMP J, SCHLIPSING M, SALMEN J, et al. Man vs. computer: benchmarking machine learning algorithms for traffic sign recognition[J]. Neural Networks, 2012, 32: 323-332.
[10] GIRSHICK R.Fast R-CNN[EB/OL]. [2024-10-14]. https://arxiv.org/abs/1504.08083.
[11] LI X, XU Z H, SHEN X, et al. Detection of cervical cancer cells in whole slide images using deformable and global context aware faster RCNN-FPN[J]. Current Oncology, 2021, 28(5): 3585-3601.
[12] HE K, GKIOXARI G, DOLLáR P, et al. Mask R-CNN[C]//Proceedings of the 2017 IEEE International Conference on Computer Vision. Piscataway: IEEE, 2017: 2961-2969.
[13] HUANG T Y, CHENG M, YANG Y L, et al. Tiny object detection based on YOLOv5[C]//Proceedings of the 5th International Conference on Image and Graphics Processing. New York: ACM, 2022: 45-50.
[14] ZHAO H Y, ZHANG H P, ZHAO Y Y. YOLOv7-sea: object detection of maritime UAV images based on improved YOLOv7[C]//Proceedings of the 2023 IEEE/CVF Winter Conference on Applications of Computer Vision. Piscataway: IEEE, 2023: 233-238.
[15] KOCH G, ZEMEL R, SALAKHUTDINOV R. Siamese neural networks for one-shot image recognition[C]//Proceedings of the 32nd International Conference on Machine Learning, 2015.
[16] CHANG M H, PYUN J Y, AHMAD M B, et al. Modified color co-occurrence matrix for image retrieval[C]//Advances in Natural Computation: the 1st International Conference. Berlin, Heidelberg: Springer, 2005: 43-50.
[17] BELONGIE S, MALIK J, PUZICHA J. Shape matching and object recognition using shape contexts[J]. IEEE Transactions on Pattern Analysis and Machine Intelligence, 2002, 24(4): 509-522.
[18] PARK D K, JEON Y S, WON C S. Efficient use of local edge histogram descriptor[C]//Proceedings of the 2000 ACM Workshops on Multimedia. New York: ACM, 2000: 51-54.
[19] FOGEL I, SAGI D. Gabor filters as texture discriminator[J]. Biological Cybernetics, 1989, 61(2): 103-113.
[20] LIU H P, LIU Y L, SUN F C. Traffic sign recognition using group sparse coding[J]. Information Sciences, 2014, 266: 75-89.
[21] NEWEY W K. Adaptive estimation of regression models via moment restrictions[J]. Journal of Econometrics, 1988, 38(3): 301-339.
[22] ZHONG Z, ZHENG L, KANG G, et al. Random erasing data augmentation[J]. Proceedings of the AAAI Conference on Artificial Intelligence, 2020, 34(7): 13001-13008.
[23] 谷明琴, 蔡自兴, 李仪, 等. 基于多模型表示的交通标志识别算法设计[J]. 控制与决策, 2013, 28(6): 844-848.
GU M Q, CAI Z X, LI Y, et al. Traffic sign recognition algorithm design based on multi-modal representation[J]. Control and Decision, 2013, 28(6): 844-848.
[24] WANG J F, CHEN Y, DONG Z K, et al. Improved YOLOv5 network for real-time multi-scale traffic sign detection[J]. Neural Computing and Applications, 2023, 35(10): 7853-7865.
[25] WANG C Y, BOCHKOVSKIY A, LIAO H M. YOLOv7: trainable bag-of-freebies sets new state-of-the-art for real-time object detectors[C]//Proceedings of the 2023 IEEE/CVF Conference on Computer Vision and Pattern Recognition. Piscataway: IEEE, 2023: 7464-7475.
[26] WANG W H, XIE E Z, LI X, et al. Pyramid vision transformer: a versatile backbone for dense prediction without convolutions[C]//Proceedings of the 2021 IEEE/CVF International Conference on Computer Vision. Piscataway: IEEE, 2021: 548-558.
[27] MANZARI O N, KASHIANI H, DEHKORDI H A, et al. Robust transformer with locality inductive bias and feature normalization[J]. Engineering Science and Technology, an International Journal, 2023, 38: 101320.
[28] HAN K, XIAO A, WU E, et al. Transformer in transformer[C]//Advances in Neural Information Processing Systems 34, 2021: 15908-15919.
[29] MINGWIN S, SHISU Y, WANWAG Y, et al. Revolutionizing traffic sign recognition: unveiling the potential of vision transformers[EB/OL]. [2024-10-15]. https://arxiv.org/abs/2404. 19066.
[30] KHALIFA A A, ALAYED W M, ELBADAWY H M, et al. Real-time navigation roads: lightweight and efficient convolutional neural network (LE-CNN) for Arabic traffic sign recognition in intelligent transportation systems (ITS)[J]. Applied Sciences, 2024, 14(9): 3903.
[31] CUI Y, HAN Y, GUO D. TS-DETR: multi-scale DETR for traffic sign detection and recognition[J]. Pattern Recognition Letters, 2025, 190: 147-152.
[32] LIU Y, CHENG D, ZHANG D W, et al. Capsule networks with residual pose routing[J]. IEEE Transactions on Neural Networks and Learning Systems, 2025, 36(2): 2648-2661.
[33] HAN S, ZHOU Z, CHEN J, et al. Uncertainty-aware graph structure learning[EB/OL]. [2025-02-20]. https://arxiv.org/abs/2502.12618.