Related references
Note: Only part of the references are listed.
Article
Computer Science, Artificial Intelligence
Hongyang Wei et al.
Summary: This paper proposes a traffic sign detection method called MTSDet, which utilizes attention mechanism network and path aggregation feature pyramid network to improve the detection performance and accuracy of traffic signs.
APPLIED INTELLIGENCE
(2023)
Article
Computer Science, Artificial Intelligence
Junfan Wang et al.
Summary: In this paper, an improved feature pyramid model named AF-FPN is proposed for the challenging task of traffic sign detection in unmanned driving systems. By utilizing an adaptive attention module and a feature enhancement module, AF-FPN reduces information loss and enhances the representation ability of the feature pyramid. The original feature pyramid network in YOLOv5 is replaced with AF-FPN, improving the detection performance for multi-scale targets while ensuring real-time detection. Additionally, a new automatic learning data augmentation method is proposed to enrich the dataset and improve model robustness for practical scenarios.
NEURAL COMPUTING & APPLICATIONS
(2023)
Article
Computer Science, Hardware & Architecture
Yongliang Zhang et al.
Summary: In this study, a new approach is proposed to address the challenges of traffic sign detection in complex traffic scenes. By designing a multi-scale feature extraction module, cascade feature fusion module, and attention mechanism module based on YOLOv4 algorithm, the algorithm's ability to simultaneously locate and classify traffic signs is significantly improved. Experimental results on a newly created dataset demonstrate that the improved algorithm achieves a mean average precision of 84.44%, outperforming several major CNN-based object detection algorithms for the same task.
JOURNAL OF SUPERCOMPUTING
(2023)
Article
Computer Science, Information Systems
Yi Li et al.
Summary: Traffic sign detection is an important technology in autonomous driving. This paper proposes an improved one-stage traffic sign detection algorithm, Attention-YOLO V4, to achieve real-time and accurate detection of traffic signs.
MULTIMEDIA TOOLS AND APPLICATIONS
(2023)
Article
Computer Science, Artificial Intelligence
Lanmei Wang et al.
Summary: In this paper, a model for detecting traffic signs, CDFF and CDFF-s, is proposed. The model achieves accurate and fast detection of objects of different sizes by applying improved activation function, context and semantic fusion module, feature fusion module, and a loss function optimized for small objects.
NEURAL COMPUTING & APPLICATIONS
(2023)
Article
Computer Science, Information Systems
Vipul Sharma et al.
Summary: This study proposes an enhanced yolov4-tiny traffic sign identification method, which can be easily deployed on mobile or embedded devices to address the difficulties of high parameters, low accuracy, and poor real-time performance in traffic sign recognition. The method incorporates Octave Convolution, convolutional block attention module, and Simplified Path Aggregation Network to improve the model's efficiency, accuracy, and recognition speed. Experimental results show that the proposed method achieves good recognition performance on TT100K and CCTSDB datasets.
JOURNAL OF VISUAL COMMUNICATION AND IMAGE REPRESENTATION
(2023)
Article
Chemistry, Analytical
Jinqi Chu et al.
Summary: Traffic sign detection is essential for intelligent transportation and deep learning has been utilized successfully. This paper proposes a model with global feature extraction capabilities and a lightweight detection head to enhance the accuracy of small traffic sign detection. The proposed algorithm achieves an accuracy of 86.3%, recall of 82.1%, mAP@0.5 of 86.5%, mAP@0.5:0.95 of 65.6% on the TT100K dataset, with a stable frame rate of 73 frames per second for real-time detection.
Article
Chemistry, Multidisciplinary
Nesrine Triki et al.
Summary: Artificial Intelligence (AI) is integrated with Advanced Driver Assistance Systems (ADAS) and/or Automated Driving Systems (ADS) in the automotive industry to produce intelligent and autonomous vehicles. This paper proposes an approach for Traffic Sign Recognition (TSR) in the automotive industry, aiming to build a real-time system that can analyze, detect, and classify traffic signs accurately. The proposed methodology combines the Haar cascade technique with a deep CNN model classifier, achieving high testing accuracy rates of 98.56% and 99.91%, and F1-measure rates of 99%. The developed TSR system is evaluated and validated on a Raspberry Pi 4 board, confirming its reliable performance.
APPLIED SCIENCES-BASEL
(2023)
Article
Automation & Control Systems
Yufei Zhang et al.
Summary: Traffic Signs Recognition (TSR) is a crucial technology for implementing Automatic Driving System (ADS) and Advanced Driver Assistant System (ADAS). This study proposes an SNN-CNN hybrid network with RRAM-implemented weights to improve the efficiency of TSR. Experimental results show that the proposed hybrid network achieves similar accuracy to state of the art CNN method with reduced weight scale (-69.21%) and lower power consumption (-81.55%).
ENGINEERING APPLICATIONS OF ARTIFICIAL INTELLIGENCE
(2023)
Article
Computer Science, Information Systems
Xu Yuan et al.
Summary: This paper proposes YOLOv5S-A2, an improved traffic sign recognition method, which achieves faster detection speed and smaller model size by using data augmentation, path aggregation module in Feature Pyramid Network (FPN), and attention detection head module. Experimental results show that our method outperforms other advanced technologies on the TT100K dataset and demonstrates its generality on the GTSDB dataset.
Article
Computer Science, Artificial Intelligence
Yanting Zhang et al.
Summary: This study introduces a detection-by-tracking methodology to enhance the robustness and performance of traffic sign detection in videos by exploring temporal and spatial correlations. Experimental results demonstrate the effectiveness of this approach and its potential for generalization to other object detection tasks in videos.
APPLIED INTELLIGENCE
(2022)
Article
Engineering, Civil
Zhengshuai Wang et al.
Summary: In this article, a two-stage approach for traffic sign recognition is proposed, which utilizes prior knowledge and a novel lightweight superclass detector to improve performance. Experimental results demonstrate significant improvements in both processing speed and detection performance.
IEEE TRANSACTIONS ON INTELLIGENT TRANSPORTATION SYSTEMS
(2022)
Article
Engineering, Civil
Weidong Min et al.
Summary: This study proposes a traffic sign recognition method based on semantic scene understanding and structural traffic sign location, which accurately detects traffic signs by establishing a scene structure model and using an improved object detection algorithm, thus overcoming the limitations of existing methods.
IEEE TRANSACTIONS ON INTELLIGENT TRANSPORTATION SYSTEMS
(2022)
Article
Chemistry, Analytical
Muhammad Atif et al.
Summary: Automatic Traffic Sign Detection and Recognition is crucial for safe traffic circulation. This study proposes a novel Traffic Sign Recognition system that combines machine learning with classifiers to analyze frames sampled by vehicle sensors. Experimental results show that this method significantly reduces misclassifications and has the potential to be a reliable solution for Traffic Sign Recognition.
Article
Computer Science, Information Systems
Jozsef Suto
Summary: Traffic sign detection is an important part of advanced driver-assistance systems and autonomous vehicles. This research focuses on improving the image enhancement step of object detection methods for traffic sign detection. The proposed method shows increased performance and low computational cost, making it suitable for embedded systems.
Article
Engineering, Civil
Erfeng Gao et al.
Summary: In this study, a novel traffic sign detection framework is proposed to address the challenges of small sign size and long-tailed data distribution. An adaptive and attentive feature fusion module is introduced to improve feature representation, and a hierarchical group softmax head is used to handle the long-tailed data problem.
IEEE TRANSACTIONS ON INTELLIGENT TRANSPORTATION SYSTEMS
(2022)
Article
Engineering, Civil
Jing Yu et al.
Summary: The detection and recognition of traffic signs is crucial for enabling unmanned driving. This paper proposes a fusion model that utilizes the relationship between multiple images to quickly and accurately detect and recognize traffic signs in a driving video sequence. The proposed model achieves over 90% accuracy, surpassing the baseline method.
IEEE TRANSACTIONS ON INTELLIGENT TRANSPORTATION SYSTEMS
(2022)
Article
Engineering, Electrical & Electronic
Kan Xie et al.
Summary: With the rise of self-driving vehicles, smartly obeying traffic rules has become crucial. To address privacy risks, privacy-preserving federated learning is used for traffic sign recognition training. The introduction of Spike Neural Networks enables efficient and rapid training.
IEEE TRANSACTIONS ON VEHICULAR TECHNOLOGY
(2022)
Article
Geography, Physical
Yongtao Yu et al.
Summary: Traffic signs play an essential role in modern transportation activities. However, vision factors pose challenges to high-quality recognition. In this paper, a novel neural network model is proposed, achieving competitive accuracy in traffic sign recognition.
ISPRS JOURNAL OF PHOTOGRAMMETRY AND REMOTE SENSING
(2022)
Article
Computer Science, Artificial Intelligence
Ali Rasteh et al.
Summary: This paper introduces a method for internet traffic recognition using machine learning techniques, specifically looking at packet size and time of arrival. By using spiking neural networks, the researchers achieved high accuracy and improved simplicity compared to previous approaches. The study suggests that spiking neural networks are well-suited for encrypted internet traffic classification.
Article
Chemistry, Analytical
Xuan Wang et al.
Summary: The detection and recognition of traffic signs is a crucial and challenging task for driverless cars. This paper proposes an optimization strategy based on the YOLOv4 network to improve the accuracy of small object detection for traffic signs.
Article
Engineering, Electrical & Electronic
Yingbiao Yao et al.
Summary: This paper proposes an improved YOLOv4-Tiny for real-time traffic sign detection by addressing three problems in the original model. The proposed adaptive feature pyramid network and receptive field blocks enhance the fusion of features and feature extraction ability. Experimental results demonstrate that the proposed network outperforms the original model in terms of precision, recall rate, and mAP, and achieves good comprehensive performance in accuracy and speed compared to state-of-the-art approaches. The improved method effectively improves the performance of traffic sign detection.
SIGNAL PROCESSING-IMAGE COMMUNICATION
(2022)
Article
Multidisciplinary Sciences
Jie Hu et al.
Summary: This paper proposes a traffic sign detection and recognition paradigm based on deep learning algorithms, which improves performance through PDCM, SCAM, and GSConv methods, achieving satisfactory results in experiments.
Article
Chemistry, Multidisciplinary
Xiang Gao et al.
Summary: This paper proposes an improved traffic sign detection method based on Faster R-CNN, which addresses the shortcomings of existing algorithms in weather and light influence, distant sign detection, and similar sign discrimination. The proposed method incorporates feature pyramid fusion, deformable convolution, and ROI align to improve the accuracy and performance of traffic sign detection, especially in extreme environments.
APPLIED SCIENCES-BASEL
(2022)
Article
Chemistry, Multidisciplinary
Shaojian Song et al.
Summary: The proposed video object detection and recognition method has a wide range of applications in self-driving vehicles, intelligent transportation systems, and video surveillance. By employing data augmentation and improving the algorithm structure, our method has significantly enhanced detection performance and accuracy.
APPLIED SCIENCES-BASEL
(2021)
Article
Computer Science, Artificial Intelligence
Yuanyuan Liu et al.
Summary: TSingNet proposes a new traffic sign detection network that effectively detects and recognizes small and occluded traffic signs by learning scale-aware and context-rich features. It outperforms state-of-the-art methods in detecting and recognizing traffic signs in the wild through extensive experiments.
Article
Computer Science, Information Systems
Jinghao Cao et al.
Summary: This paper proposes an improved Sparse R-cnn model and a novel Res2Nest backbone network to enhance the performance of traffic sign detection algorithms through improved multi-scale representation and the use of attention mechanisms, showing better results than traditional object detection models in experiments.
Article
Computer Science, Information Systems
Zhuang-Zhuang Wang et al.
Summary: This paper presents a deep learning small-object detection method based on image super-resolution, which improves the speed and accuracy of small-object detection by enhancing network structure and feature fusion methods. Experiment results show higher accuracy and speed compared to existing methods.
Article
Computer Science, Artificial Intelligence
Zhenwen Liang et al.
NEURAL COMPUTING & APPLICATIONS
(2020)
Article
Computer Science, Artificial Intelligence
Amal Bouti et al.
Review
Computer Science, Artificial Intelligence
Kang Tong et al.
IMAGE AND VISION COMPUTING
(2020)
Article
Computer Science, Information Systems
Jameel Ahmed Khan et al.
MULTIMEDIA TOOLS AND APPLICATIONS
(2020)
Article
Engineering, Electrical & Electronic
Zhanwen Liu et al.
IET INTELLIGENT TRANSPORT SYSTEMS
(2020)
Article
Computer Science, Information Systems
Liman Liu et al.
Article
Computer Science, Theory & Methods
Xianghua Xu et al.
FUTURE GENERATION COMPUTER SYSTEMS-THE INTERNATIONAL JOURNAL OF ESCIENCE
(2019)
Article
Computer Science, Artificial Intelligence
Yuan Yuan et al.
IEEE TRANSACTIONS ON IMAGE PROCESSING
(2019)
Article
Chemistry, Analytical
Jingwei Cao et al.
Review
Computer Science, Artificial Intelligence
Zhong-Qiu Zhao et al.
IEEE TRANSACTIONS ON NEURAL NETWORKS AND LEARNING SYSTEMS
(2019)
Article
Engineering, Civil
Yan Tian et al.
IEEE TRANSACTIONS ON INTELLIGENT TRANSPORTATION SYSTEMS
(2019)
Article
Computer Science, Artificial Intelligence
Yassmina Saadna et al.
NEURAL COMPUTING & APPLICATIONS
(2019)
Article
Computer Science, Information Systems
Zhonghong Ou et al.
Article
Computer Science, Software Engineering
Yizhi Song et al.
COMPUTATIONAL VISUAL MEDIA
(2019)
Article
Computer Science, Theory & Methods
Justin M. Johnson et al.
JOURNAL OF BIG DATA
(2019)
Article
Computer Science, Artificial Intelligence
Ahmed Madani et al.
NEURAL COMPUTING & APPLICATIONS
(2018)
Article
Computer Science, Artificial Intelligence
Yawar Rehman et al.
IET IMAGE PROCESSING
(2018)
Article
Chemistry, Analytical
Jameel Ahmed Khan et al.
Article
Physics, Multidisciplinary
Shaocui Guo et al.
Proceedings Paper
Computer Science, Artificial Intelligence
Kaiming He et al.
2017 IEEE INTERNATIONAL CONFERENCE ON COMPUTER VISION (ICCV)
(2017)
Article
Computer Science, Artificial Intelligence
Selcan Kaplan Berkaya et al.
EXPERT SYSTEMS WITH APPLICATIONS
(2016)
Article
Engineering, Civil
Yi Yang et al.
IEEE TRANSACTIONS ON INTELLIGENT TRANSPORTATION SYSTEMS
(2016)
Article
Computer Science, Artificial Intelligence
Haojie Li et al.
Article
Computer Science, Artificial Intelligence
J. M. Lillo-Castellano et al.
Article
Chemistry, Analytical
Shouyi Yin et al.
