Jul 2026· International Journal of Creative and Open Research in Engineering and Management· 0 citations
TL;DR
This article is analysis the process of convolutional neural networks (CNNs) and other approaches, underlining their assets, limitations, and applicability to real-time scenarios, and the compare analysis of traffic sign recognition systems.
Abstract
In India, it is a country that has a well-known and dense road network. On these roads, the traffic signals benefit the driver in delightful the driving conclusions appropriately. These traffic signals effort as the noiseless helper to the driver. These indicators tell approximately the complaint of the road forward. So that the driver can take the improved and effective conclusion nearby how to drive and what are the influences to take care of. Normally, these signs are used to presage the driver nearby the possessions which are constrained or which can help the driver to sidestep the coincidence. Occasionally these indicators are correspondingly rummage-sale to border the driver to go overhead the limitation restricted on that road, like the rapidity limit. Every driver on road must be accustomed with all these signs and this is confirmed while philanthropic driving license to any driver.
In this article, describe about the technique for road traffic sign detection and recognition. It is analysis the process of convolutional neural networks (CNNs) and other approaches, underlining their assets, limitations, and applicability to real-time scenarios. the article also discusses about the compare analysis of traffic sign recognition systems.
Keywords— Road Traffic Sign Detection, Traffic Sign Recognition (TSR), Deep Learning, Convolutional Neural Networks (CNN), Object Detection, YOLO, Faster R-CNN, Single Shot Detector (SSD).
Traffic signs are road facilities that communicate, direct, limit, caution or teach information, whether in the form of words or symbols. As the demand for the intelligence of vehicles is on the rise, there is a great need to invent and identify traffic signs automatically using technology. Nonetheless, the identification of traffic signs is not that easy, as a number of negative parameters exist, such as bad weather, change of perspective, physical impairment, and others. Currently, most of the available text mining algorithms help in processing the whole data to identify the traffic sign images. In this proposed research, an extensive sign board detection algorithm is developed where AlexNet image classification algorithm forms the premier stage. It is mainly focussed on the process of detection with the improvement of the traffic signs using a boundary enhancement algorithm along with the average filter. This helps in reducing the noise and enhances the sign to be fed into the classifier system. This approach enhances precision of 99.27%, sensitivity of 99.41% and specificity of 99.47%. Thus the proposed algorithm minimizes the time taken to detect the traffic sign in misty weather.
ASHWINI A, G. Santhiya, L. Suresh et al.· International Conference on...· 0 citations
The Advanced Driver Assistance Systems (ADAS) have a significance in enhancing road safety by identifying the
traffic signs and road surface problems in real-time. This research paper compares three models of object detection that are
based on YOLO algorithm and are YOLOv5, YOLOv7, and YOLOv8 for detecting Indian traffic signs and potholes. The
approach used in this research involved the steps of collecting dataset, annotating the data, processing the data, augmenting the
data, and training the model. The results after conducting the experiments show that every model has its own particular
functionalities. In case of traffic signs detection, YOLOv5 got the highest precision of 99.3 percent, however, YOLOv8 got the
highest recall of 83.3 percent and mAP50 of 88.7 percent, showing the capability of identifying the sign on different road
conditions. In case of pothole detection, YOLOv5 gave the best precision of 83.1 percent, but YOLOv7 performed best overall
with retrieval of recall of 76.7 percent and mAP of 79.0 percent and mAP range from 50 to 95 of 48.3 percent. The comparison
proves that the YOLO models of object detection are of great use in real-time ADAS and show good efficiency in road scene
perception.
G. Gayathri, C. Chandrika· International Journal for Re...· 0 citations
Ensuring road safety requires timely and accurate detection of lanes and roadside traffic signs, which are essential for assisting drivers and reducing accident risks. However, robust simultaneous detection remains challenging due to variations in illumination, occlusions, complex backgrounds, and diverse road conditions. This research introduces a novel vision-based system for lane detection and roadside traffic sign recognition using advanced artificial neural network architectures. In the pre-processing stage, Contrast Limited Adaptive Histogram Equalization (CLAHE) is applied to enhance image visibility under varying lighting conditions. For classification, a Self-Artificial Attentive Gated Neuro-Recurrent Unit (SAAG-NRU) is proposed, a novel architecture integrating deep artificial neural network (ANN) layers, Gated Recurrent Units (GRU), and a self-attention mechanism, enabling sequential refinement of features and prioritization of the most safety-relevant cues. In addition, YOLOv11 was utilized to train and detect traffic signs exclusively. For lane detection, a lane mask-based approach is implemented to accurately segment and highlight lane boundaries. The trained model was integrated into a Tkinter-based Graphical User Interface (GUI) to visualize real-time detection outputs effectively. Implemented using Python-based tools, the framework is validated against benchmark lane and traffic signs, demonstrating better performance compared to existing systems in terms of lane detection, achieving 91.11% precision, and traffic sign detection, attaining 96.88% precision. Therefore, the proposed system delivers fast, accurate, and robust simultaneous lane and traffic sign detection, significantly improving real-time road safety and driver assistance.
Viraj Sonawane, B. Agarkar, Sachin Chaudhari· International Journal of Adv...· 0 citations
Traffic Sign Detection and Recognition (TSDR)— the automatic localisation and classification of traffic signs from onboard cameras—is a fundamental component of Advanced Driver Assistance Systems (ADAS) and autonomous vehicles: approximately 1.3 million road fatalities occur annually worldwide, with driver inattention to traffic signs ranked the second most common contributing factor after speeding. However, existing TSDR approaches exhibit notable limitations: two-stage and transformer-based detectors are too slow for real-time onboard inference, anchor-based single-stage detectors require extensive anchor tuning and degrade sharply on small and distant signs, and most published systems neglect deployment readiness and region-specific sign diversity such as Indian signage. To overcome these problems, we propose a complete real-time TSDR pipeline built on YOLOv8, combining an anchor-free prediction head, a C2F backbone, and a Path Aggregation Network (PANet) neck, complemented by a multi-task CNN (EfficientNet-v2 with Online Hard Example Mining) for Indian traffic signs and ONNX export for edge deployment. In this paper, the pipeline is trained and evaluated end-to-end, and its results are positioned against a structured survey of the 2025–2026 state of the art (YOLO-BS, CPB-YOLOv8, FEBG-YOLOv8s, CRS-NET, and an optimised YOLOv7). Experimental results show that the proposed pipeline achieves Precision: 90.6%, Recall: 88.9%, and mAP@0.5: 93.1% (validation) / 92.3% (test) after only 30 epochs on the primary dataset; on the CCTSDB2021 benchmark, YOLOv8 attains mAP@0.5: 97.1% on the test split, outperforming both YOLOv7 and YOLOv9, while the multi-task CNN achieves state-of-the-art F1 = 98.0% on the Indian traffic sign dataset. The exported ONNX model retains full accuracy at 128 FPS on GPU, demonstrating a deployment-ready real-time system.
Hussain Bhanpurawala, Sonali Ajankar· 2026 7th International Confe...· 0 citations
Traffic jams in cities are getting worse as more number of cars hit the road. But most of the traffic systems still use fixed time signals. These systems give all lanes the same amount of green and red time, no matter what the traffic conditions are like. This often leads to wasting time on empty roads, waiting longer on busy roads, using more gas, polluting the air, and making drivers mad. Intelligent Traffic Control System might be able to help in these situations. This system helps in changing how traffic moves by using Deep Learning and Computer Vision. YOLOv8 is a new object detection model that can find cars, buses, trucks, and motorcycles. The system looks at how many vehicles on the road and adjusts the traffic lights. It gives time to the lanes that have a lot of traffic. One good thing about this system is that it can tell when an emergency vehicle is coming. It knows when an ambulance, fire engine or police car is on the way and it changes the lights so they can get through. This system helps with traffic because it can look at what’s happening and make changes. Helps cities have better transportation systems. The system reduces traffic jams which make traffic flow better and makes the roads clear, for the vehicles including the ambulances, fire engines and police vehicles.
G. Bharath Kumar, N. Jyothsna, B. Rachana et al.· International Conference on...· 0 citations
In long-haul freight transportation, driver fatigue and drowsiness are among the primary causes of road traffic accidents. To address this safety hazard, this focuses on long-haul truck driving scenarios and designs and implements a vision-based real-time monitoring and early warning system for long-haul truck driver drowsiness. The system collects video through a camera and utilizes deep learning algorithms to perform drowsiness recognition and risk assessment of the long-haul truck driver’s state. Based on the risk assessment results, it automatically warnings to the driver, thereby reducing the risk of accidents. This experiment not only completes a full closed-loop of data collection, state recognition, risk assessment, and warning feedback in laboratory, but also provides a systematic performance evaluation in both simulated and real-vehicle environments, verifying its engineering feasibility. The innovation of this study lies in the weighted fusion of multimodal temporal from the eyes and mouth. Through time-series analysis of multi-feature fusion, a comprehensive assessment of the long-haul truck driver’s drowsiness state is achieved, providing an technical solution for preventing long-haul truck driving accidents.
Yan Yang, Jing Li, Nan Jin et al.· 2026 IEEE International Conf...· 0 citations
We use cookies to run the site and, with your consent, for analytics and to show ads.
See our Cookie Policy.
