Traffic signs support road safety and managing the flow of traffic, hence are an integral part of any vision system for autonomous driving. While the use of deep learning is well-known in traffic signs classification due to the high accuracy results obtained using convolutional neural networks (CNNs) (state of the art is 99.46\%), little is known about binarized neural networks (BNNs). Compared to CNNs, BNNs reduce the model size and simplify convolution operations and have shown promising results in computationally limited and energy-constrained devices which appear in the context of autonomous driving. This work presents a bottom-up approach for architecturing BNNs by studying characteristics of the constituent layers. These constituent layers (binarized convolutional layers, max pooling, batch normalization, fully connected layers) are studied in various combinations and with different values of kernel size, number of filters and of neurons by using the German Traffic Sign Recognition Benchmark (GTSRB) for training. As a result, we propose BNNs architectures which achieve more than $90\%$ for GTSRB (the maximum is $96.45\%$) and an average greater than $80\%$ (the maximum is $88.99\%$) considering also the Belgian and Chinese datasets for testing. The number of parameters of these architectures varies from 100k to less than 2M. The accompanying material of this paper is publicly available at https://github.com/apostovan21/BinarizedNeuralNetwork.

翻译：交通标志支持道路安全并管理交通流，因此是自动驾驶视觉系统中不可或缺的组成部分。尽管深度学习因使用卷积神经网络（CNN）获得高精度结果（当前最高水平为99.46%）而在交通标志分类中广为人知，但关于二值化神经网络（BNN）的研究却相对有限。与CNN相比，BNN减小了模型规模并简化了卷积运算，在自动驾驶场景中计算受限且能量受限的设备上展现出良好前景。本文采用自底向上的方法，通过研究BNN各组成层的特性来构建其架构。这些组成层（二值化卷积层、最大池化层、批归一化层、全连接层）以不同核大小、滤波器数量及神经元数量的多种组合形式，利用德国交通标志识别基准（GTSRB）进行训练研究。基于此，我们提出的BNN架构在GTSRB上达到超过90%的准确率（最高为96.45%），同时在比利时和中国数据集测试中平均准确率超过80%（最高为88.99%）。这些架构的参数数量介于10万至不足200万之间。本文配套资料已公开于https://github.com/apostovan21/BinarizedNeuralNetwork。