A Hybrid Feature Fusion Traffic Sign Detection Algorithm Based on YOLOv7

Autonomous driving technology has entered a period of rapid development,and traffic sign detection is one of the important tasks.Existing target detection networks are difficult to adapt to scenarios where target sizes are seriously imbalanced,and traffic sign targets are small and have unclear features,which makes detection more difficult.Therefore,we propose aHybrid Feature Fusion Traffic Sign detection algorithmbased onYOLOv7(HFFTYOLO).First,a self-attention mechanism is incorporated at the end of the backbone network to calculate feature interactions within scales;Secondly,the cross-scale fusion part of the neck introduces a bottom-up multi-path fusion method.Design reuse paths at the end of the neck,paying particular attention to cross-scale fusion of highlevel features.In addition,we found the appropriate channel width through a lot of experiments and reduced the superfluous parameters.In terms of training,a newregression lossCMPDIoUis proposed,which not only considers the problem of loss degradation when the aspect ratio is the same but the width and height are different,but also enables the penalty term to dynamically change at different scales.Finally,our proposed improved method shows excellent results on the TT100K dataset.Compared with the baseline model,without increasing the number of parameters and computational complexity,AP0.5 and AP increased by 2.2%and 2.7%,respectively,reaching 92.9%and 58.1%.

C2Net-YOLOv5: A Bidirectional Res2Net-Based Traffic Sign Detection Algorithm

Rapid advancement of intelligent transportation systems(ITS)and autonomous driving(AD)have shown the importance of accurate and efficient detection of traffic signs.However,certain drawbacks,such as balancing accuracy and real-time performance,hinder the deployment of traffic sign detection algorithms in ITS and AD domains.In this study,a novel traffic sign detection algorithm was proposed based on the bidirectional Res2Net architecture to achieve an improved balance between accuracy and speed.An enhanced backbone network module,called C2Net,which uses an upgraded bidirectional Res2Net,was introduced to mitigate information loss in the feature extraction process and to achieve information complementarity.Furthermore,a squeeze-and-excitation attention mechanism was incorporated within the channel attention of the architecture to perform channel-level feature correction on the input feature map,which effectively retains valuable features while removing non-essential features.A series of ablation experiments were conducted to validate the efficacy of the proposed methodology.The performance was evaluated using two distinct datasets:the Tsinghua-Tencent 100K and the CSUST Chinese traffic sign detection benchmark 2021.On the TT100K dataset,the method achieves precision,recall,and Map0.5 scores of 83.3%,79.3%,and 84.2%,respectively.Similarly,on the CCTSDB 2021 dataset,the method achieves precision,recall,and Map0.5 scores of 91.49%,73.79%,and 81.03%,respectively.Experimental results revealed that the proposed method had superior performance compared to conventional models,which includes the faster region-based convolutional neural network,single shot multibox detector,and you only look once version 5.

Research on Traffic Sign Detection Based on Improved YOLOv8

Aiming at solving the problem of missed detection and low accuracy in detecting traffic signs in the wild, an improved method of YOLOv8 is proposed. Firstly, combined with the characteristics of small target objects in the actual scene, this paper further adds blur and noise operation. Then, the asymptotic feature pyramid network (AFPN) is introduced to highlight the influence of key layer features after feature fusion, and simultaneously solve the direct interaction of non-adjacent layers. Experimental results on the TT100K dataset show that compared with the YOLOv8, the detection accuracy and recall are higher. .

Traffic Sign Detection with Low Complexity for Intelligent Vehicles Based on Hybrid Features

Globally traffic signs are used by all countries for healthier traffic flow and to protect drivers and pedestrians.Consequently,traffic signs have been of great importance for every civilized country,which makes researchers give more focus on the automatic detection of traffic signs.Detecting these traffic signs is challenging due to being in the dark,far away,partially occluded,and affected by the lighting or the presence of similar objects.An innovative traffic sign detection method for red and blue signs in color images is proposed to resolve these issues.This technique aimed to devise an efficient,robust and accurate approach.To attain this,initially,the approach presented a new formula,inspired by existing work,to enhance the image using red and green channels instead of blue,which segmented using a threshold calculated from the correlational property of the image.Next,a new set of features is proposed,motivated by existing features.Texture and color features are fused after getting extracted on the channel of Red,Green,and Blue(RGB),Hue,Saturation,and Value(HSV),and YCbCr color models of images.Later,the set of features is employed on different classification frameworks,from which quadratic support vector machine(SVM)outnumbered the others with an accuracy of 98.5%.The proposed method is tested on German Traffic Sign Detection Benchmark(GTSDB)images.The results are satisfactory when compared to the preceding work.

A Deep Learning Model of Traffic Signs in Panoramic Images Detection

To pursue the ideal of a safe high-tech society in a time when traffic accidents are frequent,the traffic signs detection system has become one of the necessary topics in recent years and in the future.The ultimate goal of this research is to identify and classify the types of traffic signs in a panoramic image.To accomplish this goal,the paper proposes a new model for traffic sign detection based on the Convolutional Neural Network for com-prehensive traffic sign classification and Mask Region-based Convolutional Neural Networks(R-CNN)implementation for identifying and extracting signs in panoramic images.Data augmentation and normalization of the images are also applied to assist in classifying better even if old traffic signs are degraded,and considerably minimize the rates of discovering the extra boxes.The proposed model is tested on both the testing dataset and the actual images and gets 94.5%of the correct signs recognition rate,the classification rate of those signs discovered was 99.41%and the rate of false signs was only around 0.11.

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 for Autonomous Vehicle Using Optimized YOLOv7 and Convolutional Block Attention Module

The infrastructure and construction of roads are crucial for the economic and social development of a region,but traffic-related challenges like accidents and congestion persist.Artificial Intelligence(AI)and Machine Learning(ML)have been used in road infrastructure and construction,particularly with the Internet of Things(IoT)devices.Object detection in Computer Vision also plays a key role in improving road infrastructure and addressing trafficrelated problems.This study aims to use You Only Look Once version 7(YOLOv7),Convolutional Block Attention Module(CBAM),the most optimized object-detection algorithm,to detect and identify traffic signs,and analyze effective combinations of adaptive optimizers like Adaptive Moment estimation(Adam),Root Mean Squared Propagation(RMSprop)and Stochastic Gradient Descent(SGD)with the YOLOv7.Using a portion of German traffic signs for training,the study investigates the feasibility of adopting smaller datasets while maintaining high accuracy.The model proposed in this study not only improves traffic safety by detecting traffic signs but also has the potential to contribute to the rapid development of autonomous vehicle systems.The study results showed an impressive accuracy of 99.7%when using a batch size of 8 and the Adam optimizer.This high level of accuracy demonstrates the effectiveness of the proposed model for the image classification task of traffic sign recognition.

LLTH‑YOLOv5:A Real‑Time Traffic Sign Detection Algorithm for Low‑Light Scenes

Traffic sign detection is a crucial task for autonomous driving systems.However,the performance of deep learning-based algorithms for traffic sign detection is highly affected by the illumination conditions of scenarios.While existing algo-rithms demonstrate high accuracy in well-lit environments,they suffer from low accuracy in low-light scenarios.This paper proposes an end-to-end framework,LLTH-YOLOv5,specifically tailored for traffic sign detection in low-light scenarios,which enhances the input images to improve the detection performance.The proposed framework comproses two stages:the low-light enhancement stage and the object detection stage.In the low-light enhancement stage,a lightweight low-light enhancement network is designed,which uses multiple non-reference loss functions for parameter learning,and enhances the image by pixel-level adjustment of the input image with high-order curves.In the object detection stage,BIFPN is introduced to replace the PANet of YOLOv5,while designing a transformer-based detection head to improve the accuracy of small target detection.Moreover,GhostDarkNet53 is utilized based on Ghost module to replace the backbone network of YOLOv5,thereby improving the real-time performance of the model.The experimental results show that the proposed method significantly improves the accuracy of traffic sign detection in low-light scenarios,while satisfying the real-time requirements of autonomous driving.

Real-time detection network for tiny traffic sign using multi-scale attention module

As one of the key technologies of intelligent vehicles, traffic sign detection is still a challenging task because of the tiny size of its target object. To address the challenge, we present a novel detection network improved from yolo-v3 for the tiny traffic sign with high precision in real-time. First, a visual multi-scale attention module(MSAM), a light-weight yet effective module, is devised to fuse the multi-scale feature maps with channel weights and spatial masks. It increases the representation power of the network by emphasizing useful features and suppressing unnecessary ones. Second, we exploit effectively fine-grained features about tiny objects from the shallower layers through modifying backbone Darknet-53 and adding one prediction head to yolo-v3. Finally, a receptive field block is added into the neck of the network to broaden the receptive field. Experiments prove the effectiveness of our network in both quantitative and qualitative aspects. The m AP@0.5 of our network reaches 0.965 and its detection speed is55.56 FPS for 512 × 512 images on the challenging Tsinghua-Tencent 100 k(TT100 k) dataset.

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.

基于轻量化YOLOv5的交通标志检测

为了提高道路交通标志的检测速度,提出一种基于轻量化YOLOv5的改进模型。首先,使用Ghost卷积和深度分离卷积(DWConv)构建新的主干模块,减少计算量和参数量;引入加权特征融合网络(BiFPN)结构,增强特征融合能力;将CIoU损失函数替换为SIoU损失函数,关注真实锚框与预测的角度信息,提升检测精度。其次,对TT100K数据集进行优化,筛选出标签个数大于200的交通标志图片和标注信息共24类。最后,实验结果取得84%的准确率、81.2%的召回率和85.4%的所有类别平均精确率的平均值mAP@0.5,相比原始YOLOv5,参数量减少29.0%,计算量减少29.4%,mAP@0.5仅下降0.1百分点,检测帧率提升了34帧/s。使用改进后的模型进行检测,检测速度有了明显提升,基本达到了在保持检测精度的基础上压缩模型的目的。

基于Transformer的交通标志检测模型研究

【目的】为了解决在复杂环境下,对小目标特征困难以及对小目标检测效果不佳等问题,提出了一种基于Transformer的交通标志检测基干模型。【方法】通过充分利用卷积和Transformer的优势,构建了一种注意力融合的多尺度特征提取基干模型,能够使基干网络以全局上下文信息为支撑,有选择地增强有用信息的特征,并抑制不重要的特征。此外,为了在增强特征融合的同时防止网络退化,还加入了类池连接。最后,在TT100K数据集上进行实验。【结果】实验结果表明,以该模型为骨干的元体系结构取得了最高84%的mAP,与基线模型相比m AP最大提升约7%。【结论】模型在提高特征提取效果的同时,也为交通标志检测提供了一种新的思路。

基于轻量化SSD的交通标志检测算法

实时精确的交通标志检测是自动驾驶和智能交通的关键技术。针对现有智能检测算法检测复杂真实道路场景下的交通标志速度慢、无法较好地适用于嵌入式终端设备的问题,提出了一种基于轻量化SSD的交通标识检测算法。该算法采用MobileNetV3_large网络替代VGG16网络,可减少模型参数,提高检测实时性;利用添加SE模块的逆残差结构B-neck替换对应的标准卷积增强低层特征层的语义信息;设计改进RFB网络提升小交通标志的检测能力,重新设置预设先验框的尺寸,提升模型对特定数据集的检测能力。实验结果表明,改进SSD算法在中国交通标志检测数据集上的mAP值可达89.04%,比MobileNet-SSD算法提高了5.26%;帧率可达60 frames/s,比SSD算法提高了23 frames/s。所提算法具有较高的实时性和检测精度,对复杂交通环境具有更好的鲁棒性。

A three-stage real-time detector for traffic signs in large panoramas

Traffic sign detection is one of the key components in autonomous driving.Advanced autonomous vehicles armed with high quality sensors capture high definition images for further analysis.Detecting traffic signs,moving vehicles,and lanes is important for localization and decision making.Traffic signs,especially those that are far from the camera,are small,and so are challenging to traditional object detection methods.In this work,in order to reduce computational cost and improve detection performance,we split the large input images into small blocks and then recognize traffic signs in the blocks using another detection module.Therefore,this paper proposes a three-stage traffic sign detector,which connects a Block Net with an RPN–RCNN detection network.Block Net,which is composed of a set of CNN layers,is capable of performing block-level foreground detection,making inferences in less than 1 ms.Then,the RPN–RCNN two-stage detector is used to identify traffic sign objects in each block;it is trained on a derived dataset named TT100 KPatch.Experiments show that our framework can achieve both state-of-the-art accuracy and recall;its fastest detection speed is 102 fps.

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。

基于多尺度YOLOv5的交通标志检测

针对小目标交通标志检测存在的检测精度低、漏检率高等问题,提出了一种基于多尺度融合的YOLOv5改进算法。在主干网络后输出4个有效特征层以便更好地融合多尺度信息,在主干网络输出的3个特征层中添加改进的多尺度融合注意力机制CBAM_U,以提升网络的检测能力;在Path Aggregation Network(PANet)下采样过程中添加Fusion模块,促进不同感受野下特征的细融合;在YOLOHand前加入Adaptively Spatial Feature Fusion(ASFF)模块解决特征金字塔融合的不一致性,进一步提升网络的表达能力。实验结果表明,提出的方法相比于原始YOLOv5网络在CCTSDB数据集中mAP@0.5提升了3.07%,召回率提升了3.83%,查准率提升了1.64%,F1-Score提升了2.66%,相比于其他检测算法,改进后的YOLOv5算法在复杂场景中具有更好的鲁棒性。

智能交通感知新范式:面向元宇宙的交通标志检测架构

交通标志检测对智能交通系统和智能驾驶的安全稳定运行具有重要作用。数据分布不平衡、场景单一会对模型性能造成较大影响,而建立一个完备的真实交通场景数据集需要昂贵的时间成本和人工成本。基于此,该文提出一个面向元宇宙的交通标志检测新范式以缓解现有方法对真实数据的依赖。首先,通过建立元宇宙和物理世界之间的场景映射和模型映射,实现检测算法在虚实世界之间的高效运行。元宇宙作为一个虚拟化的数字世界,能够基于物理世界完成自定义场景构建,为模型提供海量多样的虚拟场景数据。同时,该文结合知识蒸馏和均值教师模型建立模型映射,应对元宇宙和物理世界之间存在的数据差异问题。其次,为进一步提高元宇宙下的训练模型对真实驾驶环境的适应性,该文提出启发式注意力机制,通过对特征的定位和学习来提高检测模型的泛化能力。所提架构在CURE-TSD,KITTI,VKITTI数据集上进行实验验证。实验结果表明,所提面向元宇宙的交通标志检测器在物理世界具有优异的检测效果而不依赖大量真实场景,检测准确率达到89.7%,高于近年来其他检测方法。

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。

基于改进YOLOv5s的交通标识检测算法

针对交通标识在图像中占比小、检测精度低且周围环境复杂等问题,提出一种基于改进YOLOv5s的算法.首先,在主干网络部分添加注意力机制ECA(Efficient Channel Attention,高效通道注意力),增强网络的特征提取能力,有效解决了周围环境复杂的问题;其次,提出HASPP(Hybrid Atrous Spatial Pyramid Pooling,混合空洞空间金字塔池化),增强了网络结合上下文的能力;最后,修改网络中的Neck结构,使高层特征与底层特征有效融合,同时避免了跨卷积层造成的信息丢失.实验结果表明,改进后的算法在交通标识数据集上取得了94.4%的平均检测精度、74.1%的召回率以及94.0%的精确率,较原始算法分别提升了3.7、2.8、3.4个百分点.

基于双向嵌套级联残差的交通标志检测方法

交通标志检测是自动驾驶领域的一个重要课题,其对于检测系统的实时性和精度都有非常高的要求。目标检测领域中的YOLOv3算法是业界公认在精度和速度上都处于前列的一种算法。文中以YOLOv3检测算法作为基础网络,提出一种双向嵌套级联残差单元(bid⁃NCR),替换掉原网络中顺序堆叠的标准残差块。双向嵌套级联残差单元的两条残差边采用相同的结构,都是一次卷积操作加上一次级联残差处理,两条边上级联的标准残差块的数量可以调节,从而形成不同的深度差。然后将两条边的结果逐像素相加,最后再做一次卷积操作。相较于标准残差块,双向嵌套级联残差单元拥有更强的特征提取能力和特征融合能力。文中还提出跨区域压缩模块(CRC),它是对2倍率下采样卷积操作的替代,旨在融合跨区域的通道数据,进一步加强主干网络输入特征图所包含的信息。实验结果表明:提出的模型在CCTSDB数据集上mAP(0.5)、mAP(0.5∶0.95)分别达到96.86%、68.66%,FPS达到66.09帧。相比于YOLOv3算法,3个指标分别提升1.23%、10.35%、127.90%。