Pre-Locator Incorporating Swin-Transformer Refined Classifier for Traffic Sign Recognition

In the field of traffic sign recognition,traffic signs usually occupy very small areas in the input image.Most object detection algorithms directly reduce the original image to a specific size for the input model during the detection process,which leads to the loss of small object information.Addi-tionally,classification tasks are more sensitive to information loss than local-ization tasks.This paper proposes a novel traffic sign recognition approach,in which a lightweight pre-locator network and a refined classification network are incorporated.The pre-locator network locates the sub-regions of the traffic signs from the original image,and the refined classification network performs the refinement recognition task in the sub-regions.Moreover,an innovative module(named SPP-ST)is proposed,which combines the Spatial Pyramid Pool module(SPP)and the Swin-Transformer module as a new feature extractor to learn the special spatial information of traffic sign effec-tively.Experimental results show that the proposed method is superior to the state-of-the-art methods(82.1 mAP achieved on 218 categories in the TT100k dataset,an improvement of 19.7 percentage points compared to the previous method).Moreover,both the result analysis and the output visualizations further demonstrate the effectiveness of our proposed method.The source code and datasets of this work are available at https://github.com/DijiesitelaQ/TSOD.

Research and Implementation of Traffic Sign Recognition Algorithm Model Based on Machine Learning

Traffic sign recognition is an important task in intelligent transportation systems, which can improve road safety and reduce accidents. Algorithms based on deep learning have achieved remarkable results in traffic sign recognition in recent years. In this paper, we build traffic sign recognition algorithms based on ResNet and CNN models, respectively. We evaluate the proposed algorithm on public datasets and compare. We first use the dataset of traffic sign images from Kaggle. And then designed ResNet-based and CNN-based architectures that can effectively capture the complex features of traffic signs. Our experiments show that our ResNet-based model achieves a recognition accuracy of 99% on the test set, and our CNN-based model achieves a recognition accuracy of 98% on the test set. Our proposed approach has the potential to improve traffic safety and can be used in various intelligent transportation systems.

Traffic sign recognition algorithm based on shape signature and dual-tree complex wavelet transform

A novel traffic sign recognition system is presented in this work. Firstly, the color segmentation and shape classifier based on signature feature of region are used to detect traffic signs in input video sequences. Secondly, traffic sign color-image is preprocessed with gray scaling, and normalized to 64×64 size. Then, image features could be obtained by four levels DT-CWT images. Thirdly, 2DICA and nearest neighbor classifier are united to recognize traffic signs. The whole recognition algorithm is implemented for classification of 50 categories of traffic signs and its recognition accuracy reaches 90%. Comparing image representation DT-CWT with the well-established image representation like template, Gabor, and 2DICA with feature selection techniques such as PCA, LPP, 2DPCA at the same time, the results show that combination method of DT-CWT and 2DICA is useful in traffic signs recognition. Experimental results indicate that the proposed algorithm is robust, effective and accurate.

New method for recognition of circular traffic sign based on radial symmetry and pseudo-zernike moments

Recognizing various traffic signs,especially the popular circular traffic signs,is an essential task for implementing advanced driver assistance system.To recognize circular traffic signs with high accuracy and robustness,a novel approach which uses the so-called improved constrained binary fast radial symmetry（ICBFRS） detector and pseudo-zernike moments based support vector machine（PZM-SVM） classifier is proposed.In the detection stage,the scene image containing the traffic signs will be converted into Lab color space for color segmentation.Then the ICBFRS detector can efficiently capture the position and scale of sign candidates within the scene by detecting the centers of circles.In the classification stage,once the candidates are cropped out of the image,pseudo-zernike moments are adopted to represent the features of extracted pictogram,which are then fed into a support vector machine to classify different traffic signs.Experimental results under different lighting conditions indicate that the proposed method has robust detection effect and high classification accuracy.

FPGA-Based Traffic Sign Recognition for Advanced Driver Assistance Systems

This paper presents the implementation of an embedded automotive system that detects and recognizes traffic signs within a video stream. In addition, it discusses the recent advances in driver assistance technologies and highlights the safety motivations for smart in-car embedded systems. An algorithm is presented that processes RGB image data, extracts relevant pixels, filters the image, labels prospective traffic signs and evaluates them against template traffic sign images. A reconfigurable hardware system is described which uses the Virtex-5 Xilinx FPGA and hardware/software co-design tools in order to create an embedded processor and the necessary hardware IP peripherals. The implementation is shown to have robust performance results, both in terms of timing and accuracy.

A New Speed Limit Recognition Methodology Based on Ensemble Learning:Hardware Validation

Advanced DriverAssistance Systems(ADAS)technologies can assist drivers or be part of automatic driving systems to support the driving process and improve the level of safety and comfort on the road.Traffic Sign Recognition System(TSRS)is one of themost important components ofADAS.Among the challengeswith TSRS is being able to recognize road signs with the highest accuracy and the shortest processing time.Accordingly,this paper introduces a new real time methodology recognizing Speed Limit Signs based on a trio of developed modules.Firstly,the Speed Limit Detection(SLD)module uses the Haar Cascade technique to generate a new SL detector in order to localize SL signs within captured frames.Secondly,the Speed Limit Classification(SLC)module,featuring machine learning classifiers alongside a newly developed model called DeepSL,harnesses the power of a CNN architecture to extract intricate features from speed limit sign images,ensuring efficient and precise recognition.In addition,a new Speed Limit Classifiers Fusion(SLCF)module has been developed by combining trained ML classifiers and the DeepSL model by using the Dempster-Shafer theory of belief functions and ensemble learning’s voting technique.Through rigorous software and hardware validation processes,the proposedmethodology has achieved highly significant F1 scores of 99.98%and 99.96%for DS theory and the votingmethod,respectively.Furthermore,a prototype encompassing all components demonstrates outstanding reliability and efficacy,with processing times of 150 ms for the Raspberry Pi board and 81.5 ms for the Nano Jetson board,marking a significant advancement in TSRS technology.

Resource Efficient Hardware Implementation for Real-Time Traffic Sign Recognition

Traffic sign recognition (TSR, or Road Sign Recognition, RSR) is one of the Advanced Driver Assistance System (ADAS) devices in modern cars. To concern the most important issues, which are real-time and resource efficiency, we propose a high efficiency hardware implementation for TSR. We divide the TSR procedure into two stages, detection and recognition. In the detection stage, under the assumption that most German traffic signs have red or blue colors with circle, triangle or rectangle shapes, we use Normalized RGB color transform and Single-Pass Connected Component Labeling (CCL) to find the potential traffic signs efficiently. For Single-Pass CCL, our contribution is to eliminate the “merge-stack” operations by recording connected relations of region in the scan phase and updating the labels in the iterating phase. In the recognition stage, the Histogram of Oriented Gradient (HOG) is used to generate the descriptor of the signs, and we classify the signs with Support Vector Machine (SVM). In the HOG module, we analyze the required minimum bits under different recognition rate. The proposed method achieves 96.61% detection rate and 90.85% recognition rate while testing with the GTSDB dataset. Our hardware implementation reduces the storage of CCL and simplifies the HOG computation. Main CCL storage size is reduced by 20% comparing to the most advanced design under typical condition. By using TSMC 90 nm technology, the proposed design operates at 105 MHz clock rate and processes in 135 fps with the image size of 1360 × 800. The chip size is about 1 mm2 and the power consumption is close to 8 mW. Therefore, this work is resource efficient and achieves real-time requirement.

Traffic sign recognition based on subspace

The features extracted by principle component analysis(PCA) are the best descriptive and the features extracted by linear discriminant analysis(LDA) are the most classifiable. In this paper, these two methods are combined and a PC-LDA approach is used to extract the features of traffic signs. After obtaining the binary images of the traffic signs through normalization and binarization, PC-LDA can extract the feature subspace of the traffic sign images with the best description and classification. The extracted features are recognized by using the minimum distance classifier. The approach is verified by using MPEG7 CE Shape-1 Part-B computer shape library and traffic sign image library which includes both standard and natural traffic signs. The results show that under the condition that the traffic sign is in a nature scene, PC-LDA approach applied to binary images in which shape features are extracted can obtain better results.

Traffic Sign Recognition Based on CNN and Twin Support Vector Machine Hybrid Model

With the progress of deep learning research, convolutional neural networks have become the most important method in feature extraction. How to effectively classify and recognize the extracted features will directly affect the performance of the entire network. Traditional processing methods include classification models such as fully connected network models and support vector machines. In order to solve the problem that the traditional convolutional neural network is prone to over-fitting for the classification of small samples, a CNN-TWSVM hybrid model was proposed by fusing the twin support vector machine (TWSVM) with higher computational efficiency as the CNN classifier, and it was applied to the traffic sign recognition task. In order to improve the generalization ability of the model, the wavelet kernel function is introduced to deal with the nonlinear classification task. The method uses the network initialized from the ImageNet dataset to fine-tune the specific domain and intercept the inner layer of the network to extract the high abstract features of the traffic sign image. Finally, the TWSVM based on wavelet kernel function is used to identify the traffic signs, so as to effectively solve the over-fitting problem of traffic signs classification. On GTSRB and BELGIUMTS datasets, the validity and generalization ability of the improved model is verified by comparing with different kernel functions and different SVM classifiers.

Logistic Regression Based Model for Improving the Accuracy and Time Complexity of ROI’s Extraction in Real Time Traffic Signs Recognition System

Designing accurate and time-efficient real-time traffic sign recognition systems is a crucial part of developing the intelligent vehicle which is the main agent in the intelligent transportation system.Traffic sign recognition systems consist of an initial detection phase where images transportaand colors are segmented and fed to the recognition phase.The most challenging process in such systems in terms of time consumption is the detection phase.The trade off in previous studies,which proposed different methods for detecting traffic signs,is between accuracy and computation time,Therefore,this paper presents a novel accurate and time-efficient color segmentation approach based on logistic regression.We used RGB color space as the domain to extract the features of our hypothesis;this has boosted the speed of our approach since no color conversion is needed.Our trained segmentation classifier was tested on 1000 traffic sign images taken in different lighting conditions.The results show that our approach segmented 974 of these images correctly and in a time less than one-fifth of the time needed by any other robust segmentation method.

CNN-based Traffic Sign Recognition

Background:The rapid development of the automobile industry has led to an increase in the output and holdings of automobiles year by year,which has brought huge challenges to the current traffic management.Method:This paper adopts a traffic sign recognition technology based on deep convolution neural network(CNN):step 1,preprocess the collected traffic sign images through gray processing and near interpolation;step 2,automatically extract image features through the convolutional layer and the pooling layer;step 3,recognize traffic signs through the fully connected layer and the Dropout technology.Purpose:Artificial intelligence technology is applied to traffic management to better realize intelligent traffic assisted driving.Results:This paper adopts an Adam optimization algorithm for calculating the loss value.The average accuracy of the experimental classification is 98.87%.Compared with the traditional gradient descent algorithm,the experimental model can quickly converge in a few iteration cycles.

基于Cache-DCN YOLOX算法的交通标志检测方法研究

针对传统方式识别交通标志算法存在的检测精度较低的问题,提出了一种基于Cache-DCN YOLOX算法的交通标志识别方法;在该方法中,使用DCN可变形卷积替换backbone中的普通卷积,有效地增大了模型的感受野,提高了特征提取能力;使用EIoU损失函数代替YOLOX中的GIoU损失函数,优化了训练模型,提高了收敛的速度;优化设计了YOLOX算法中的强弱两阶段的训练过程,增强了模型的泛化性能,同时加入cache方案,进一步提高了检测精度;在交通标志数据集TT100K上进行了实验,提出方法的检测精度为67.2%,比原YOLOX算法的检测精度提升了6.4%,同时,在被遮挡的小目标等多种受干扰的环境下,提出的方法能够精确地检测出交通标志,并有着较好的置信度,满足实际需求。

应用双通道卷积神经网络的交通标识识别方法

针对交通标识识别问题,传统的LeNet-5网络结构对于交通标识识别准确率低,识别速度慢,并且忽略天气等自然因素的影响。通过卷积神经网络技术,提出一种基于LeNet-5改进的双通道、多尺度的网络结构模型。在双通道结构中每个通道包含两个分支结构,且每个通道的卷积个数和图像尺度不同,通过不同尺度图像的特征提取,使图像特征变得更为丰富。其次,改进后的网络结构大大增加卷积核的个数。最后,通过更改Sigmoid激活函数为ReLu激活函数,更改随机梯度下降算法为Adam算法,并添加Dropout层来防止过拟合,从而提高交通标识识别率。改进网络的识别率为98.6%,上下浮动0.5%,相对与传统的LeNet-5网络结构,识别率提高15%以上,验证得出改进的网络结构具有一定的鲁棒性。

基于几何透视图像预处理和CNN的全景图像交通标志识别算法

为解决深度学习方法在高清全景图像中检测交通标志遇到图形处理器资源不足、小目标容易漏检、检测速度过慢等问题,采用小目标过采样训练数据生成方法、图像分块和几何透视检测预处理方法以及改进的轻量神经网络Improved-Tiny-YOLOv3,提出了一种基于深度学习的轻量级全景图像中交通标志检测方法。并在Tsinghua-Tencent 100K数据集上进行了实验,mAP值达到92.7%,在Nvidia 1080Ti显卡上检测速度可达到20 FPS,实验结果验证了所提方法的有效性。

基于CF-YOLO的雾霾交通标志识别

针对现有交通标志检测模型在雾霾环境下出现漏检、错检以及参数较大等问题,设计一种基于YOLOv5s改进的CF-YOLO检测模型。为加强在雾霾环境中对交通标志的检测能力,提出一种基于颜色衰减先验的自适应伽马变换图像预处理算法;为增强对目标的定位能力及检测精度,将坐标注意力机制融合到网络中;为实现模型轻量化,引入FasterNetBlock构建网络。实验结果表明,改进算法在雾霾环境下交通标志检测相比原YOLOv5模型权重减少了2.3 MB,精度提高了8.5个百分点。

基于YOLOv5的轻量化交通标志检测方法

针对目前交通标志检测深度学习网络模型体积大、参数多,难以满足在计算资源有限的移动设备和嵌入式设备中部署的问题,提出一种基于YOLOv5的轻量化交通标志检测模型。该模型利用GhostNet思想重新建构YOLOv5网络,同时在特征提取层引入坐标注意力机制(coordinate attention, CA),并将原边框损失函数CIOU替换为SIOU,最后使用NVIDIA的加速推理框架TensorRT对改进模型加快推理速度。在CCTSDB2021交通标志数据集中验证了改进模型的可行性,实验结果表明,改进模型较于原模型,模型大小减小了53.5%,参数量压缩了50%,而精度仅损失0.1%,且模型推理速度提升了2%;经过TensorRT加速推理后,推理速度甚至提升了57.4%,达到了4 ms。改进模型实现了模型的轻量化,精度损失小,推理速度快,相比原模型更适合部署到嵌入式移动设备中。

基于改进ResNet模型的交通标志识别算法

本文提出了一种基于改进残差网络ResNet50模型的图像识别方法。通过引入圆形LBP算法,提取图像内部的纹理信息构成纹理图谱;同时在网络中加入通道注意力机制(Efficient Channel Attention,ECA)提高模型性能,使得改进后的算法更适合识别交通标志。该方法在GTSRB和BelgiumTS交通标志数据集上的准确率分别达到99.7%和98.3%,有效提高了智能系统识别交通标志的准确率和驾驶的安全性。

基于多注意力的改进YOLOv5s小目标检测算法

交通标志识别应用中待检测目标多为小目标,因其携带信息少、定位精度要求高、易被环境噪声淹没等特点成为当前交通标志检测的难点.针对小目标交通标志漏检、误检、检测准确率低等问题,本文设计了一种用于小目标检测的STDYOLOv5s(Small target detection YOLOv5s)模型.首先,通过增加上采样和Prediction输出层数获得了更丰富的位置信息,解决了YOLOv5s模型在处理小目标时信息不足的问题,增强了对图像的全局理解能力;其次,在每个C3模块之后添加CA(Coordinate attention)注意力机制并在每个输出层前添加Swin-T注意力机制模块,增加了网络对多层特征信息的捕捉,提高了小目标的检测性能;最后,充分利用SIoU惩罚函数同时考虑目标形状、空间关系的特点,更好地捕捉不同尺寸的目标在图像中的位置关系,提高目标位置的精确性.所提模型在TT100K数据集上进行了验证实验,实验结果表明本文方法不仅保持了YOLOv5s模型的轻量性和快速性,在精确率、召回率和平均精度三个指标上也有所提升,提高了小目标检测的精确性.

融合RepVGG的YOLOv5交通标志识别算法

实现自动驾驶的安全性需要准确检测交通标志。针对传统方法在交通标志检测方面存在准确度不高的问题,提出一种融合RepVGG模块的改进YOLOv5的交通标志识别算法。首先通过将RepVGG模块替换原算法中的部分CBS模块,增强了特征提取能力。并在特征融合模块引入通道注意力模块(channel block attention module,CBAM),强化检测模型的抗干扰能力。最后,在网络训练过程中,使用高效交并比(efficient-IoU,EIoU)损失函数实现对目标更精确的定位,提高算法的检测精度与迭代速度。实验结果表明,改进后的YOLOv5算法迭代速度更快,在CCTSDB交通标志数据集上,其相较于原YOLOv5算法的准确率、召回率和平均准确率分别提升了4.99%、3.62%、1.73%,能够更好地应用到实践当中。

基于FMS-YOLOv5s的轻量化交通标志识别算法

针对目前的道路交通标志模型有着检测速度慢、模型大和参数多的缺点,提出了一种基于YOLOv5s算法的轻量化交通标志识别算法。首先引入轻量化FasterNet网络,利用该网络中的FasterNet Block结构与原主干网络的C3融合,形成一种全新的C3Faster结构;接着将原网络的损失函数修改为基于最小点距离(MPDIoU)的损失函数,来提高边界框回归的准确性和效率;最后结合高效且轻量的置换注意力机制(shuffle attention,SA),提高模型的泛化能力和稳定性。在CCTSDB 2021数据集上的实验结果表明,与原网络相比,改进后模型的参数量、模型大小、GFLOPs分别减少了17.5%、17.5%和20%;同时mAP@0.5、mAP@0.75、mAP@0.5:0.95分别提升了2.3%、3.4%和2.4%。而且与YOLOv3-tiny等其他算法对比,所提出的算法有明显的优越性,能满足各种场景下移动端实时性的需求。