Traffic Sign Recognition Research Articles

Fast and Lightweight Vision-Language Model for Adversarial Traffic Sign Detection

Several attacks have been proposed against autonomous vehicles and their subsystems that are powered by machine learning (ML). Road sign recognition models are especially heavily tested under various adversarial ML attack settings, and they have proven to be vulnerable. Despite the increasing research on adversarial ML attacks against road sign recognition models, there is little to no focus on defending against these attacks. In this paper, we propose the first defense method specifically designed for autonomous vehicles to detect adversarial ML attacks targeting road sign recognition models, which is called ViLAS (Vision-Language Model for Adversarial Traffic Sign Detection). The proposed defense method is based on a custom, fast, lightweight, and salable vision-language model (VLM) and is compatible with any existing traffic sign recognition system. Thanks to the orthogonal information coming from the class label text data through the language model, ViLAS leverages image context in addition to visual data for highly effective attack detection performance. In our extensive experiments, we show that our method consistently detects various attacks against different target models with high true positive rates while satisfying very low false positive rates. When tested against four state-of-the-art attacks targeting four popular action recognition models, our proposed detector achieves an average AUC of 0.94. This result achieves a 25.3% improvement over a state-of-the-art defense method proposed for generic image attack detection, which attains an average AUC of 0.75. We also show that our custom VLM is more suitable for an autonomous vehicle compared to the popular off-the-shelf VLM and CLIP in terms of speed (4.4 vs. 9.3 milliseconds), space complexity (0.36 vs. 1.6 GB), and performance (0.94 vs. 0.43 average AUC).

A Semi-Supervised Learning Framework Combining CNN and Multiscale Transformer for Traffic Sign Detection and Recognition

A Semi-Supervised Learning Framework Combining CNN and Multiscale Transformer for Traffic Sign Detection and Recognition

Traffic Sign Detection Under Foggy Environment Using Machine Learning

Road signs are important to ensure smooth traffic flow without bottle necks or mishaps. Road symbols are the pictorial representations having different necessary information required to be understood by driver. Road signs in front of the vehicle are ignored by the drivers and this can lead to catastrophic accidents. This paper presents an overview of the traffic sign board detection and recognition and implements a procedure to extract the road sign from a natural complex image, processes it and alerts the driver using voice command It is implemented in such a way that it acts as a boon to drivers to make easy decisions. Traffic sign recognition is a critical component of modern intelligent transportation systems, contributing to road safety and efficient traffic management. This paper presents a novel approach to traffic sign recognition based on Convolutional Neural Networks (CNNs). Key Words: CNN, Pre-processing, Feature Extraction.

Traffic Sign Recognition using HIICNN Stack Ensemble Method

Abstract: This project introduces a novel deep convolutional neural network (CNN) model aimed at enhancing traffic sign recognition for autonomous vehicle technology and road safety. Employing a stacking ensemble approach, we combine multiple CNNs with diverse improvement techniques, including preprocessing for adverse weather conditions and shooting errors, and data augmentation to handle class imbalance. Through adjustments in learning rates during model training, we mitigate overfitting. Our ensemble model achieves an exceptional 99.4 percent test accuracy on the German Traffic Sign Recognition Benchmark (GTSRB) dataset, surpassing prior studies. We utilize gradient-weighted Class Activation Mapping (Grad-CAM) for model explain- ability and an evidential deep learning approach to quantify classification uncertainty. Our framework underscores the efficacy of combining preprocessing, ensemble learning, and transfer learning for superior perfor- mance and reliability in traffic sign recognition systems, contributing significantly to autonomous driving and road safety.

Traffic Sign Recognition Using Deep Learning

Abstract: Traffic sign recognition is a crucial component in advanced driver assistance systems and autonomous vehicles, enhancing road safety and overall transportation efficiency. Deep learning, specifically convolutional neural networks (CNNs), has emerged as a powerful tool for image based recognition tasks. The proposed deep learning-based traffic sign recognition system exhibits promising results, providing a foundation for the development of intelligent transportation systems. The trained model demonstrates remarkable accuracy in recognizing a wide range of traffic signs under different scenarios, including challenging lighting conditions and occlusions. The system's real-time performance is evaluated on both simulated and actual road scenarios, showcasing its feasibility for deployment in practical driving environments. The integration of such technology into vehicles holds great potential for enhancing road safety, reducing accidents, and contributing to the evolution of autonomous driving technology.

Traffic Sign Classification Using CNN

This study presents a novel approach for traffic sign classification leveraging Convolutional Neural Networks (CNNs). With the proliferation of autonomous vehicles and advanced driver assistance systems, accurate and efficient traffic sign recognition is imperative for safe and efficient navigation. The proposed CNN-based method utilizes deep learning techniques to automatically extract discriminative features from traffic sign images, enabling robust classification across diverse environmental conditions and variations in sign appearance. Experimental results demonstrate the effectiveness of the proposed approach. This research contributes to the advancement of intelligent transportation systems by providing a reliable and scalable solution for real-time traffic sign classification. Our findings highlight the potential of deep learning for robust and accurate traffic sign classification in real-world scenarios.

TRAFFIC SIGN RECOGNITION AND DETECTION using CNN

Roadside traffic indicators including yield and speed restriction signs are automatically detected using traffic sign classification. The evolution of traffic sign recognition systems that operate automatically regarding "smarter automobiles." For self-driving cars to effectively understand and comprehend the road, the need for recognizing traffic signs. Similar to this, for the purpose of support and safeguard drivers, "driver alert" systems in automobiles need to comprehend the surrounding road. With our technology, drivers wouldn't have to take their eyes off the road to see and understand traffic signs. Convolution neural networks allow for accurate classification of the signboards. More layers can be added to increase the precision. Here, training and testing are done using the GTSRB dataset; by optimizing the settings, traffic signs are reliably classified into 43 types, and detection speed also rises. Keywords Convolutional Neural Network, Smarter Cars

Traffic Sign Recognition Using Multi-Task Deep Learning for Self-Driving Vehicles.

Over the coming years, the advancement of driverless transport systems for people and goods that are designed to be used on fixed routes will revolutionize the transportation system. Therefore, for a safe transportation system, detecting and recognizing traffic signals based on computer vision has become increasingly important. Deep learning approaches, particularly convolutional neural networks, have shown exceptional performance in various computer vision applications. The goal of this research is to precisely detect and recognize traffic signs that are present on the streets using computer vision and deep learning techniques. Previous work has focused on symbol-based traffic signals, where popular single-task learning models have been trained and tested. Therefore, several comparisons have been conducted to select accurate single-task learning models. For further improvement, these models are employed in a multi-task learning approach. Indeed, multi-task learning algorithms are built by sharing the convolutional layer parameters between the different tasks. Hence, for the multi-task learning approach, different experiments have been carried out using pre-trained architectures like, for instance, InceptionResNetV2 and DenseNet201. A range of traffic signs and traffic lights are employed to validate the designed model. An accuracy of 99.07% is achieved when the entire network has been trained. To further enhance the accuracy of the model for traffic signs obtained from the street, a region of interest module is added to the multi-task learning module to accurately extract the traffic signs available in the image. To check the effectiveness of the adopted methodology, the designed model has been successfully tested in real-time on a few Riyadh highways.

Trusted Perception Method for Traffic Signs That Are Physically Attacked

Traffic sign recognition is a crucial method by which autonomous driving systems acquire road information, and is predominantly based on deep neural networks (DNNs). However, the recognition results of DNNs are not always trustworthy for traffic signs subject to abnormal disturbance. Recently, the phenomenon of adversarial examples successfully deceiving DNNs has garnered considerable attention. Because DNN-based computer vision techniques are becoming increasingly prevalent in traffic scenarios, the misclassification of attacked traffic signs by DNN classifiers poses serious safety hazards. Although numerous methods have been proposed for crafting physical adversarial examples that are robust in the real world, most existing defense approaches focus on digital attacks, which necessitate the adversary infiltrating the embedded system; thus, it becomes challenging to obtain results. A reliable approach for defending against physical adversarial traffic signs enables autonomous vehicles to achieve trusted perception of traffic signs. In this paper, we present a deep image prior-based pipeline to defend against robust adversarial traffic signs in the real world, an approach that circumvents the need for prior data sets during training. Our approach protects the safety of autonomous vehicles by performing image reconstruction of captured traffic sign images. The genuine traffic sign class can be inferred by leveraging the consistency of the victim classifier’s decision results for reconstructed images at different stages. Additionally, we evaluate the efficacy of our defense pipeline for detecting other potential types of physical adversarial traffic signs that may exist in the real world, thus demonstrating the generalizability of our approach.

MSGC-YOLO: An Improved Lightweight Traffic Sign Detection Model under Snow Conditions

Traffic sign recognition plays a crucial role in enhancing the safety and efficiency of traffic systems. However, in snowy conditions, traffic signs are often obscured by particles, leading to a severe decrease in detection accuracy. To address this challenge, we propose an improved YOLOv8-based model for traffic sign recognition. Initially, we introduce a Multi-Scale Group Convolution (MSGC) module to replace the C2f module in the YOLOv8 backbone. Data indicate that MSGC enhances detection accuracy while maintaining model lightweightness. Subsequently, to improve the recognition ability for small targets, we introduce an enhanced small target detection layer, which enhances small target detection accuracy while reducing parameters. In addition, we replaced the original BCE loss with the improved EfficientSlide loss to improve the sample imbalance problem. Finally, we integrate Deformable Attention into the model to improve the detection efficiency and performance of complex targets. The resulting fused model, named MSGC-YOLOv8, is evaluated on an enhanced dataset of snow-covered traffic signs. Experimental results show that the MSGC-YOLOv8 model is used for snow road traffic sign recognition. Compared with the YOLOv8n model mAP@0.5:0.95, mAP@0.5:0.95 is increased by 17.7% and 18.1%, respectively, greatly improving the detection accuracy. Compared with the YOLOv8s model, while the parameters are reduced by 59.6%, mAP@0.5 only loses 1.5%. Considering all aspects of the data, our proposed model shows high detection efficiency and accuracy under snowy conditions.

Traffic Sign Recognition for Vehicle Driving System Using Machine Learning

Traffic Sign Recognition for Vehicle Driving System Using Machine Learning

Real-Time Navigation Roads: Lightweight and Efficient Convolutional Neural Network (LE-CNN) for Arabic Traffic Sign Recognition in Intelligent Transportation Systems (ITS)

Smart cities are now embracing the new frontier of urban living, with advanced technology being used to enhance the quality of life for residents. Many of these cities have developed transportation systems that improve efficiency and sustainability, as well as quality. Integrating cutting-edge transportation technology and data-driven solutions improves safety, reduces environmental impact, optimizes traffic flow during peak hours, and reduces congestion. Intelligent transportation systems consist of many systems, one of which is traffic sign detection. This type of system utilizes many advanced techniques and technologies, such as machine learning and computer vision techniques. A variety of traffic signs, such as yield signs, stop signs, speed limits, and pedestrian crossings, are among those that the traffic sign detection system is trained to recognize and interpret. Ensuring accurate and robust traffic sign recognition is paramount for the safe deployment of self-driving cars in diverse and challenging environments like the Arab world. However, existing methods often face many challenges, such as variability in the appearance of signs, real-time processing, occlusions that can block signs, low-quality images, and others. This paper introduces an advanced Lightweight and Efficient Convolutional Neural Network (LE-CNN) architecture specifically designed for accurate and real-time Arabic traffic sign classification. The proposed LE-CNN architecture leverages the efficacy of depth-wise separable convolutions and channel pruning to achieve significant performance improvements in both speed and accuracy compared to existing models. An extensive evaluation of the LE-CNN on the Arabic traffic sign dataset that was carried out demonstrates an impressive accuracy of 96.5% while maintaining superior performance with a remarkably low inference time of 1.65 s, crucial for real-time applications in self-driving cars. It achieves high accuracy with low false positive and false negative rates, demonstrating its potential for real-world applications like autonomous driving and advanced driver-assistance systems.

Securing AI Models Against Backdoor Attacks: A Novel Approach Using Image Steganography

<p>Artificial Intelligence (AI) has become ubiquitous, transforming numerous domains including traffic sign recognition, defect detection, and healthcare. However, this widespread adoption has brought about significant cybersecurity challenges, particularly in the form of backdoor attacks, which manipulate training datasets to compromise model integrity. While the integration of AI has proven beneficial, there is a lack of comprehensive strategies to protect AI models from these covert attacks, necessitating innovative approaches for securing AI systems. In this study, we demonstrate a novel methodology that integrates image steganography with deep learning techniques, aiming to obscure backdoor triggers and enhance the resilience of AI models against these attacks. We employ a diverse set of AI models and conduct extensive evaluations in a traffic sign recognition scenario, specifically targeting the STOP sign. The results reveal that shallow models are challenged in learning trigger information and are sensitive to trigger settings, while deeper models achieve an impressive 98.03% attack success rate. The image steganography technique used requires minimal data adjustments, making the triggers more challenging to detect than with traditional methods. Our findings underscore the stealth and severity of backdoor attacks, emphasizing the need for advanced security measures in AI and contributing to the broader understanding and development of robust protections against such attacks.</p> <p> </p>

Deep learning-based path tracking control using lane detection and traffic sign detection for autonomous driving

Automated vehicles are a significant advancement in transportation technique, which provides safe, sustainable, and reliable transport. Lane detection, maneuver forecasting, and traffic sign recognition are the fundamentals of automated vehicles. Hence, this research focuses on developing a dynamic real-time decision-making system to obtain an effective driving experience in autonomous vehicles with the advancement of deep learning techniques. The deep learning classifier such as deep convolutional neural network (Deep CNN), SegNet and are utilized in this research for traffic signal detection, road segmentation, and lane detection. The main highlight of the research relies on the proposed Finch Hunt optimization, which involves the hyperparameter tuning of a deep learning classifier. The proposed real-time decision-making system achieves 97.44% accuracy, 97.56% of sensitivity, and 97.83% of specificity. Further, the proposed segmentation model achieves the highest clustering accuracy with 90.37% and the proposed lane detection model attains the lowest mean absolute error, mean square error, and root mean error of 17.76%, 11.32%, and 5.66% respectively. The proposed road segmentation model exceeds all the competent models in terms of clustering accuracy. Finally, the proposed model provides a better output for lane detection with minimum error, when compared with the existing model.

Real-Time Traffic Sign Detection and Recognition System using Computer Vision and Machine Learning

The use of computer vision technology for our system has taken a huge leap and has revolutionized the way in which road safety is managed and maintained. This part of the paper represents the key components and functionalities of such a system which helps in enhancing the road safety and also in traffic management. The proposed system is meant to contain computer vision algorithms and some machine learning techniques. These will help in detecting and recognizing the traffic signs in real time video streams. With the help of deep learning models like convolutional neural networks, the proposed system can precisely identify various traffic signs present on roads. The major components of the proposed system include a camera interface which will capture real time video frames from the road, image processing modules for color space conversions, binary thresholding, contour detection and a classification module for the purpose of sign recognition. Deep learning frameworks like TensorFlow and OpenCV libraries are used for image processing and model training In the proposed system. The real time nature of this system allows the spontaneous detection and recognition of traffic signs enabling us to change the road conditions. Hence, the system contributes to prevent accidents and provide timely warnings to drivers. In addition, this system offers potential applications in traffic management and for autonomous driving system. With the help of accurate information, the system can contribute towards more efficient traffic flow and reduce congestion on roads. Overall, the system has very good impacts in road safety and efficiency. It shows advancement in road safety and traffic management.

Comparative Study of Machine Learning Algorithms for Traffic Sign Recognition

The increasing integration of intelligent transportation systems has brought forth a critical need for accurate and efficient traffic sign detection algorithms. In this research, we conduct a comprehensive comparative analysis of four prominent convolutional neural network (CNN) architectures—LeNet, ResNet, VGG, and a standard CNN model—for their performance in traffic sign detection. The evaluation is conducted on a diverse dataset, utilizing the German Traffic Signs Recognition Benchmark (GTSRB). Our study encompasses an in-depth examination of accuracy metrics and performance under varying conditions, such as challenging lighting, occlusion, and environmental complexities. The results demonstrate nuanced differences in accuracy and computational efficiency among the algorithms. LeNet exhibits notable improvements in real-time processing, while ResNet showcases enhanced accuracy, and VGG demonstrates robustness in challenging conditions. The findings provide valuable insights into the strengths and weaknesses of each algorithm, aiding researchers and practitioners in selecting the most suitable model for specific traffic sign detection applications. This research contributes to advancing the field of computer vision in intelligent transportation systems, with implications for enhancing road safety and efficiency. Key Words: traffic sign recognition, deep learning, Res-Net, VGG19, CNN, LeNet.

A Comprehensive Analysis of AI/ML-enabled Predictive Maintenance Modelling for Advanced Driver-Assistance Systems

Advanced Driver-Assistance Systems (ADAS) are changing driver-vehicle interactions to improve road safety and reduce distractions. Technological advances like ADAS and AI in cars present societal challenges and opportunities. It shows how AI aids human-machine communication by improving motor skills. The auto industry is interested in ADAS because it can increase energy efficiency, safety, and comfort. Numerous studies have shown its benefits. ADAS and vehicle networking show promise, but establishing a sound control system is challenging. Model Predictive Control (MPC) is one answer to these problems. To manage higher-level connectivity and automation, the paper analyses and implements key research. It also finds issues and recommends solutions. The latest driverless car ADAS improvements have dramatically increased passenger safety. These systems are safer and more automated using sensors and ECUs. Most ADAS have RADAR, cameras, ultrasonic, and LiDAR. This work uses AI/ML-enabled Predictive Maintenance modelling to improve ADAS safety and longevity. AI and ML in Advanced Driver Assistance Systems (ADAS) are significant vehicle safety and reliability advances. AI/ML-enabled predictive maintenance detects and fixes ADAS component faults. ADAS predictive maintenance using AI/ML can detect issues, improve driver safety, and boost vehicle efficiency. Advanced sensor arrays and control units are needed for adaptive cruise control, traffic sign recognition, and lane-keeping assistance. AI/ML algorithms discover issues and enable early interventions in predictive maintenance models. Predictive maintenance is examined utilizing classical machine learning, deep learning, and reinforcement learning. Integration of numerous AI/ML models, real-time data processing, customization based on vehicle usage patterns, scalability, and adaptability of predictive maintenance models to new ADAS technologies are research gaps.

ADM- Road Eye: Advanced Traffic Sign Detection

In recent years, a plethora of systems have emerged for recognizing traffic signs. This paper offers a comprehensive overview of the latest and most effective approaches in detecting and categorizing traffic signs. The primary goal of detection techniques is to pinpoint the precise areas containing traffic signs, which are classified into three main categories: color-based, shape-based, and learning-based methods of Alex net, Desnse net, and Mobil net (ADM) models. Moreover, methods of classification are divided into two groups; those relying on manually crafted features such as HOG, LBP, SIFT, SURF, BRISK, and those leveraging deep learning. The paper summarizes various detection and classification methods, along with the datasets utilized, for quick reference. Additionally, it provides suggestions for future research directions and recommendations to enhance traffic sign recognition performance..

Optimizing Traffic Sign Detection and Recognition by Using Deep Learning

Optimizing Traffic Sign Detection and Recognition by Using Deep Learning

A YOLOv8-based approach for multi-class traffic sign detection

Recognizing traffic signs is a crucial task in autonomous vehicles to improve road safety. In this study, we propose a novel You Only Look Once version 8 (YOLOv8) model for identifying traffic signs. The model has been trained on the Kaggle dataset, which contains multiple traffic signs under different environments. The YOLOv8 model achieved an accuracy of 80.64% and a recall of 65.67% on test data. These metrics highlight the model's capability to recognize traffic signs. Notably, YOLOv8 brought about some notable improvements over earlier versions, such as enhanced detection in difficult situations and enhanced small-scale sign identification. The paper also explores the difficulties that arose throughout the model's training phase and provides workable solutions that were used to overcome these difficulties, improving the model's performance. The encouraging outcomes demonstrate the viability of implementing the YOLOv8-based strategy in practical traffic management systems, which is a positive advancement towards the creation of more sophisticated and dependable traffic sign recognition technology.