孪生神经网络交通标志编码识别算法

doi:10.3778/j.issn.1002-8331.2201-0408

摘要/Abstract

摘要： 交通标志识别技术正在被逐步应用到汽车辅助驾驶领域。但是，遮挡、污损、天气环境变化等因素会严重影响交通标志识别的准确性和稳定性。针对该问题，提出了一种基于孪生神经网络的交通标志编码识别模型。该模型将交通标志的识别问题视为交通标志的卷积特征编码识别问题。通过卷积神经网络对交通标志训练样本和基准样本进行特征提取与编码。再利用孪生神经网络进行编码对比，结合对比损失函数对编码器训练调整。通过全连接层对输入通路的标志卷积编码进行重新组合与分类，从而实现交通标识的识别。实验结果表明，所提的基于改进孪生神经网络的编码器模型对存在运动模糊与遮挡的标志图像能生成有效、鲁棒的特征编码，相较于其他先进算法，具有更高的识别准确率。

关键词: 机器视觉, 交通标志, 对比学习, 孪生神经网络, 特征相似性度量

Abstract: Traffic sign recognition has been applied to the assistant driving system. However, some factors, such as occlusion, contamination damage and weather can seriously affect the accuracy and robustness of traffic sign recognition function. To solve this problem, a traffic sign encoding and classification method based on the Siamese neural network is developed. The method treats the traffic sign recognition problem as a convolutional feature code recognition problem. Firstly, the method uses convolutional neural network to extract and encode features of training samples and reference samples. Secondly, the method uses Siamese neural network to compare the feature code of training samples and reference samples and trains the encoder with contrastive loss. With the help of a fully connected layer, the method can recombine and classify the convolutional feature code of input in the end. The experimental results show that this method can produce effective and robust feature code of traffic sign under motion blur and occlusion conditions. Compared to other advanced methods, this method has higher accuracy.

Key words: machine vision, traffic sign, contrastive learning, siamese neural network, feature-based similarity measure

吕秉略, 奚峥皓, 邵宇超. 孪生神经网络交通标志编码识别算法[J]. 计算机工程与应用, 2023, 59(11): 105-111.

LYU Binglue, XI Zhenghao, SHAO Yuchao. Traffic Sign Recognition Algorithm Based on Siamese Neural Network with Encoder[J]. Computer Engineering and Applications, 2023, 59(11): 105-111.

参考文献

[1] KASSANI P H，TEOH A B J.A new sparse model for traffic sign classification using soft histogram of oriented gradients[J].Applied Soft Computing，2017，52：231-246.
[2] GECER B，AZZOPARDI G，PETKOV N.Color-blob-based COSFIRE filters for object recognition[J].Image and Vision Computing，2017，57：165-174.
[3] MADANI A，YUSOF R.Traffic sign recognition based on color，shape，and pictogram classification using support vector machines[J].Neural Computing and Applications，2018，30（9）：2807-2817.
[4] GUDIGAR A，CHOKKADI S，RAGHAVENDRA U，et al.Local texture patterns for traffic sign recognition using higher order spectra[J].Pattern Recognition Letters，2017，94：202-210.
[5] AZIZ S，YOUSSEF F.Traffic sign recognition based on multi-feature fusion and ELM classifier[J].Procedia Computer Science，2018，127：146-153.
[6] ELLAHYANI A，EL ANSARI M，EL JAAFARI I.Traffic sign detection and recognition based on random forests[J].Applied Soft Computing，2016，46：805-815.
[7] ZAKLOUTA F，STANCIULESCU B.Real-time traffic-sign recognition using tree classifiers[J].IEEE Transactions on Intelligent Transportation Systems，2012，13（4）：1507-1514.
[8] LU K，DING Z，GE S.Sparse-representation-based graph embedding for traffic sign recognition[J].IEEE Transactions on Intelligent Transportation Systems，2012，13（4）：1515-1524.
[9] LIU H，LIU Y，SUN F.Traffic sign recognition using group sparse coding[J].Information Sciences，2014，266：75-89.
[10] GOODFELLOW I，BENGIO Y，COURVILLE A，et al.Deep learning[M].Cambridge：MIT Press，2016.
[11] SIMONYAN K，ZISSERMAN A.Very deep convolutional networks for large-scale image recognition[J].arXiv：1409.1556，2014.
[12] HE K，ZHANG X，REN S，et al.Deep residual learning for image recognition[C]//Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition，2016：770-778.
[13] SHUSTANOV A，YAKIMOV P.CNN design for real-time traffic sign recognition[J].Procedia Engineering，2017，201：718-725.
[14] LUO H，YANG Y，TONG B，et al.Traffic sign recognition using a multi-task convolutional neural network[J].IEEE Transactions on Intelligent Transportation Systems，2017，19（4）：1100-1111.
[15] LI J，WANG Z.Real-time traffic sign recognition based on efficient CNNs in the wild[J].IEEE Transactions on Intelligent Transportation Systems，2018，20（3）：975-984.
[16] CHOPRA S，HADSELL R，LECUN Y.Learning a similarity metric discriminatively，with application to face verification[C]//2005 IEEE Computer Society Conference on Computer Vision and Pattern Recognition（CVPR’05），2005：539-546.
[17] CHEN X，HE K.Exploring simple siamese representation learning[J].arXiv：2011.10566，2020.
[18] ZHONG Z，ZHENG L，KANG G，et al.Random erasing data augmentation[C]//Proceedings of the AAAI Conference on Artificial Intelligence，2020：13001-13008.
[19] JADERBERG M，SIMONYAN K，ZISSERMAN A，et al.Spatial transformer networks[J].arXiv：1506.02025，2015.
[20] ARCOS-GARCíA á，ALVAREZ-GARCIA J A，SORIA-MORILLO L M.Deep neural network for traffic sign recognition systems：an analysis of spatial transformers and stochastic optimisation methods[J].Neural Networks，2018，99：158-165.
[21] CIREAAN D，MEIER U，MASCI J，et al.Multi-column deep neural network for traffic sign classification[J].Neural Networks，2012，32：333-338.