Traffic Light Detection Research Articles

Traffic Light Detection using Ensemble Learning by Boosting with Color-Based Data Augmentation

Recent advancements in deep neural networks have significantly improved the detection and recognition of traffic lights for advanced driver assistance systems (ADAS). Traditional methods often rely on identifying traffic light boxes and then recognizing individual signal lights, which can be problematic due to variations in bulb arrangements across different regions. To address this limitation, we propose a novel traffic light detection method that directly recognizes individual signal lights. Our two-stage approach combines data augmentation and ensemble learning to achieve high detection rates. By learning color characteristics from validation sets, we can effectively identify signal light candidates with a 97.26% accuracy rate. Subsequent classification results in a recognition accuracy of 98.6%, surpassing the performance of existing state-of-the-art traffic light detection algorithms. Code and dataset are available at https://github.com/981124/yolov7_traffic_light_detect.

Ultrasensitive dim-light neuromorphic vision sensing via momentum-conserved reconfigurable van der Waals heterostructure

Reconfigurable phototransistors featuring bipolar photoresponses are favorable for manipulating high-performance neuromorphic vision sensory. Here, we present a momentum-conserved reconfigurable phototransistor based on the van der Waals heterojunction between methylammonium lead iodide perovskite and two-dimensional Bi2O2Se semiconductor, which exhibits a synergistic interplay of interband hot-carrier transitions and reconfigurable heterointerface band alignments, eventually achieving the ultrahigh bipolar optoelectronic performances with the photoresponsivity of 6×107 AW−1, accompanied by the specific detectivity of 5.2×1011 Jones, and the dynamic range of 110 dB. Moreover, A 3×3 heterotransistor array is fabricated to perform in-sensor analog multiply-accumulate operations even under the challenging dim illumination of 0.1 μWcm−2 that comparable to natural moonlight. The reconfigurable heterotransistor array can be further adopted to enhance the traffic-light detection under dim-light conditions. Our advancement in momentum-conserved reconfigurable heterotransistor signifies a leap forward in real-time, energy-efficient, and low-light image processing for neuromorphic vision sensors.

Electric Vehicle Energy Management via Traffic Light Detection and Segmental Velocity Forecasting

Abstract Predictive-based power control has been widely recognized as a promising approach to boost driving range and improve system-level energy efficiency for electric vehicles (EVs), in which vehicle velocity forecasting generally serves as a preliminary input to optimally schedule the operations of varying on-board electrical and thermal systems. A segment-based velocity forecasting approach for individual commuting vehicles developed in this study reveals that it is challenging to forecast the velocity at intersection segments only using the velocity data. To address this challenge, this study seeks to develop a YOLO-V2-based object detection deep network to recognize the traffic lights in advance, and leverage the detected signals to establish a forecasting model that integrates with the probability-based hybrid forecasting approach. The case study results show that the traffic light detection-based forecasting model can significantly improve the forecasting accuracy for intersection segments. Based on the forecasting velocity 5-15 seconds ahead, the effectiveness of model predictive control-based energy management strategy is further evaluated with a liquid-based battery thermal control system. The proposed Battery Thermal Management System (BTMS) model shows promising results in maintaining battery temperature within an appropriate range, thus improving the overall energy efficiency of the EV. Moreover, a traffic light-based real-time energy management framework is developed to directly control the power demand from the Air Conditioning (AC) system.

KCS-YOLO: An Improved Algorithm for Traffic Light Detection under Low Visibility Conditions

KCS-YOLO: An Improved Algorithm for Traffic Light Detection under Low Visibility Conditions

TLDM: An Enhanced Traffic Light Detection Model Based on YOLOv5

Traffic light detection and recognition are crucial for enhancing the security of unmanned systems. This study proposes a YOLOv5-based traffic light-detection algorithm to tackle the challenges posed by small targets and complex urban backgrounds. Initially, the Mosaic-9 method is employed to enhance the training dataset, thereby boosting the network’s ability to generalize and adapt to real-world scenarios. Furthermore, the Squeeze-and-Excitation (SE) attention mechanism is incorporated to improve the network. Moreover, the YOLOv5 algorithm’s loss function is optimized by substituting it with Efficient Intersection over Union loss (EIoU_loss), which addresses issues like missed detection and false alarms. Experimental results demonstrate that the model trained with this enhanced network achieves an mAP (mean average precision) of 99.4% on a custom dataset, which is 6.3% higher than that of the original YOLOv5, while maintaining a detection speed of 74 f/s. Therefore, this algorithm offers higher detection accuracy and effectively meets real-time operational requirements. The proposed method has a strong application potential, and can be widely used in the field of automatic driving, assisted driving, etc. Its application is not only of great significance in improving the accuracy and speed of traffic sign detection, but also can provide technical support for the development of intelligent transportation systems.

Traffic light detection algorithm based on improved YOLOXs

Abstract The detection and recognition of traffic lights play a vital role in driverless and assisted driving technology, given the rapid advancements in autonomous driving. Vehicles can receive crucial information about traffic signals by precisely locating and identifying traffic lights to ensure safety. To make the traffic light detection model more lightweight and improve the detection speed, this paper proposes an improved YOLOXs traffic light detection algorithm. Firstly, the Ghost module is used to enhance the backbone model of YOLOXs in lightweight, reduce the parameters quantity of the network, and enhance the detection speed. Then, the CBAM module is added to the YOLOX neck model to direct the model’s focus toward the target area and ensure the accuracy of traffic light detection. Many experiments on the S2TLD public datasets display that the enhanced model has fewer parameters and achieves accelerated detection speed, up to 112 FPS, which can achieve real-time detection effects. At the same time, in contrast to the primary network, the accuracy of the enhanced network is improved by 1%, reaching 97%. The recall rate increased by 1.2% to 96.2%; average accuracy increased by 0.3% to 97.1%.

Navigating Abnormal Environmental Conditions: Traffic Signal and Obstacle Detection for Autonomous Vehicles

Autonomous cars are the future smart cars anticipated to be efficient and crash avoiding ideal urban car of the future. The purpose of the project is to build up a car which can move with and without any driver. It just need a command from the user and then it will start moving towards the destination. The project aims to build a autonomous car prototype using Raspberry Pi processor. Sensor interfacing is used to provide necessary data from the real world to the car. The car is capable of reaching the given destination safely and intelligently thus avoiding the risk of human errors. Many existing algorithms like traffic light detection, obstacle detection and speed control are combined together to provide the necessary control to the car. The technology that autonomous cars and “connected vehicles” use would allow the vehicles to communicate with roadside infrastructure like traffic lights and road congestion, and then use this information to curtail fuel consumption and emissions significantly.

TRAFFIC LIGHT DETECTION WITH YOLO MODELS

The accurate detection and recognition of traffic lights are paramount in the realm of autonomous driving systems and intelligent traffic management. This study leverages the comprehensive cinTA_v2 Image Dataset on Robotflow, specifically designed for traffic light detection, to evaluate the performance of advanced You Only Look Once (YOLO) models, including YOLOv7l, YOLOv8n, YOLOv8s, and YOLOv8m. Through meticulous training and evaluation, we systematically analyze the models' ability to accurately detect and classify traffic light states (green, red, and yellow) under a variety of challenging conditions. Our findings reveal significant improvements in precision, recall, and mean Average Precision (mAP) across the models, with YOLOv8m demonstrating superior overall performance, especially in terms of mAP50-95, reflecting its enhanced capability in detecting small and partially obscured traffic lights. The study not only showcases the effectiveness of YOLO models in a critical application within the autonomous driving domain but also highlights the potential for further advancements in traffic light detection technologies. By discussing the challenges, limitations, and future directions, this work contributes to the ongoing efforts to improve road safety and efficiency through the application of cutting-edge artificial intelligence techniques.

Navigating Abnormal Environmental Conditions: Traffic Signal and Obstacle Detection for Autonomous Vehicles

Autonomous cars are the future smart cars anticipated to be efficient and crash avoiding ideal urban car of the future. The purpose of the project is to build up a car which can move with and without any driver. It just need a command from the user and then it will start moving towards the destination. The project aims to build a autonomous car prototype using Raspberry Pi processor. Sensor interfacing is used to provide necessary data from the real world to the car. The car is capable of reaching the given destination safely and intelligently thus avoiding the risk of human errors. Many existing algorithms like traffic light detection, obstacle detection and speed control are combined together to provide the necessary control to the car. The technology that autonomous cars and “connected vehicles” use would allow the vehicles to communicate with roadside infrastructure like traffic lights and road congestion, and then use this information to curtail fuel consumption and emissions significantly.

Automated Car: Intelligent Maneuver

Abstract: Automated vehicles are rapidly evolving to meet the demands of modern transportation systems, aiming for enhanced safety, efficiency, and user experience. Autonomous vehicles are also a big part of these technologies. The most important action of a driver has to do is to follow the lanes on the way to the destination. This research presents Intelligent Maneuver, a sophisticated framework integrating four key functionalities crucial for automated car navigation: object avoidance, traffic light detection, self-parking, and lane detection. Leveraging advanced computer vision techniques and sensors fusion our framework enables vehicles to navigate complex urban environments autonomously

Real-Time Traffic Light Recognition with Lightweight State Recognition and Ratio-Preserving Zero Padding

As online shopping is becoming mainstream, driven by the social impact of Coronavirus disease-2019 (COVID-19) as well as the development of Internet services, the demand for autonomous delivery mobile robots is rapidly increasing. This trend has brought the autonomous mobile robot market to a new turning point, with expectations that numerous mobile robots will be driving on roads with traffic. To achieve these expectations, autonomous mobile robots should precisely perceive the situation on roads with traffic. In this paper, we revisit and implement a real-time traffic light recognition system with a proposed lightweight state recognition network and ratio-preserving zero padding, which is a two-stage system consisting of a traffic light detection (TLD) module and a traffic light status recognition (TLSR) module. For the TLSR module, this work proposes a lightweight state recognition network with a small number of weight parameters, because the TLD module needs more weight parameters to find the exact location of traffic lights. Then, the proposed effective and lightweight network architecture is constructed by using skip connection, multifeature maps with different sizes, and kernels of appropriately tuned sizes. Therefore, the network has a negligible impact on the overall processing time and minimal weight parameters while maintaining high performance. We also propose to utilize a ratio-preserving zero padding method for data preprocessing for the TLSR module to enhance recognition accuracy. For the TLD module, extensive evaluations with varying input sizes and backbone network types are conducted, and then appropriate values for those factors are determined, which strikes a balance between detection performance and processing time. Finally, we demonstrate that our traffic light recognition system, utilizing the TLD module’s determined parameters, the proposed network architecture for the TLSR module, and the ratio-preserving zero padding method can reliably detect the location and state of traffic lights in real-world videos recorded in Gumi and Deagu, Korea, while maintaining at least 30 frames per second for real-time operation.

Traffic Light Detection and Recognition Using a Two-Stage Framework From Individual Signal Bulb Identification

Traffic Light Detection and Recognition Using a Two-Stage Framework From Individual Signal Bulb Identification

Deep Learning-Based Traffic Light Detection in a Custom Embedded Hardware Platform for ADAS Applications

Deep Learning-Based Traffic Light Detection in a Custom Embedded Hardware Platform for ADAS Applications

Integrating Recurrent Neural Networks with Convolutional Neural Networks for Enhanced Traffic Light Detection and Tracking

Integrating Recurrent Neural Networks with Convolutional Neural Networks for Enhanced Traffic Light Detection and Tracking

Performance investigation of two-stage detection techniques using traffic light detection dataset

<span>Using a camera to monitor an object or a group of objects over time is the process of object detection. It can be used for a variety of things, including security and surveillance, video communication, traffic light detection (TLD), object detection from compressed video in public places. In recent times, object tracking has become a popular topic in computer science particularly, the data science community, thanks to the usage of deep learning (DL) in artificial intelligence (AI). DL which convolutional neural network (CNN) as one of its techniques usually used two-stage detection methods in TLD. Despite all successes recorded in TLD through the use of two-stage detection methods, there is no study that has analyzed these methods in experimental research, studying the strength and witnesses by the researchers. Based on the needs this study analyses the applications of DL techniques in TLD. We implemented object detection for TLD using 5 two-stage detection methods with the traffic light dataset using a Jupyter notebook and the sklearn libraries. We present the achievements of two-stage detection methods in TLD, going by standard performance metrics used, FASTER-CNN was the best in detection accuracy, F1-score, precision and recall with 0.89, 0.93, 0.83 and 0.90 respectively.</span>

Real-time traffic monitoring system using IoT-aided robotics and deep learning techniques

The increasing number of vehicles on the road has made traffic regulations challenging to manage, particularly in large and crowded cities. Real-time traffic monitoring systems are one of the most important factors that enable efficient traffic flow and enhanced mobility. Therefore, vehicles and drivers have always needed reliable and accurate real-time traffic information. Recently, various solutions have been proposed to solve the problems and concerns in traffic situations. One alternative solution is vehicular cloud computing (VCC). Additionally, an IoT-aided robotic (IoRT) model has been developed with a modern architecture that integrates IoT sensor nodes and cameras to gather real-time traffic data. The main contributions of this research work are to implement two deep learning techniques based on modified LeNet-5 for real-time traffic sign recognition and the transfer learning-based Inception-V3 model for detecting and recognizing traffic lights. Furthermore, optimal distance was found between the ultrasonic sensors and the obstacles using ultrasonics’ waves time and speed to reduce road accidents. The data, which is collected by sensors and cameras, is processed using various image processing algorithms and it is sent to the cloud to be available for drivers and commuters through a mobile application. Test results indicate that the proposed models have significant improvements in terms of accuracy. The modified LeNet-5 achieved accuracy rates of 99.12% and 99.78% on the German Traffic Sign Recognition Benchmark (GTSRB) and extended GTSRB (EGTSRB) datasets, respectively, whereas the second model, trained on Laboratory for the Intelligent and Safe Automobiles (LISA) dataset, attained a 98.6% accuracy rate. Compared to the related traffic monitoring systems, the findings of this study outperform other works by 3.78% for traffic sign recognition and by 1.02% for traffic light detection and recognition.

Transfer Learning Based Traffic Light Detection and Recognition Using CNN Inception-V3 Model

Due to the lack of vehicle-to-infrastructure (V2I) communication in the existing transportation systems, traffic light detection and recognition is essential for advanced driver assistant systems (ADAS) and road infrastructure surveys. Additionally, autonomous vehicles have the potential to change urban transportation by making it safe, economical, sustainable, congestion-free, and transportable in other ways. Because of their limitations, traditional traffic light detection and recognition algorithms are not able to recognize traffic lights as effectively as deep learning-based techniques, which take a lot of time and effort to develop. The main aim of this research is to propose a traffic light detection and recognition model based on a transfer learning-based model that uses the Inception-V3 network model to significantly reduce the amount of training data and computing costs. The proposed model was trained and tested in the laboratory for the intelligent and safe automobiles (LISA) traffic light dataset, which has been augmented by several pre-processing methods. Then, using different convolution and pooling techniques, the retrieved layer-wise features were compared and analyzed. Lastly, great reliability and repeatability are seen based on statistical analysis when the transfer learning-based model is frequently retrained utilizing precise tuning parameters. The results demonstrate that a transfer learning-based model is capable of high-level recognition performance in the proposed model, with an accuracy rate of 98.6%.

Traffic Light Detection by Integrating Feature Fusion and Attention Mechanism

Path planning is a key problem in the design of autonomous driving systems, and accurate traffic light detection is very important for robust routing. In this paper, we devise an object detection model, which mainly focuses on traffic light classification at a distance. In the past, most techniques employed in this field were dominated by high-intensity convolutional neural networks (CNN), and many advances have been achieved. However, the size of traffic lights may be small, and how to detect them accurately still deserves further study. In the object detection domain, the scheme of feature fusion and transformer-based methods have obtained good performance, showing their excellent feature extraction capability. Given this, we propose an object detection model combining both the pyramidal feature fusion and self-attention mechanism. Specifically, we use the backbone of the mainstream one-stage object detection model consisting of a parallel residual bi-fusion (PRB) feature pyramid network and attention modules, coupling with architectural tuning and optimizer selection. Our network architecture and module design aim to effectively derive useful features aimed at detecting small objects. Experimental results reveal that the proposed method exhibits noticeable improvement in many performance indicators: precision, recall, F1 score, and mAP, compared to the vanilla models. In consequence, the proposed method obtains good results in traffic light detection.

TL-Detector: Lightweight Based Real-Time Traffic Light Detection Model for Intelligent Vehicles

With the leap-forward development of intelligent driving, traffic light detection with high accuracy and high speed is important for intelligent transportation systems to ensure safety. However, existing methods encounter difficulties in balancing the detection speed and accuracy. This paper aims to present a flexible and robust lightweight model TL (Traffic Light)-Detector for real-time detection of traffic light. The model is composed of three parts. An enhanced backbone network combined with G-module is proposed to generate abundant information and reduce computational load, and the coordinate attention mechanism is introduced to focus on location features thereby strengthening the feature extract ability. The lightweight neck promotes multi-scale feature information aggregation for feature fusion to build a lightweight feature fusion network. The lightweight detection head adopts anchor-free mechanism to eliminate the hyperparameters related to the anchor. The dataset TL2022 of traffic light is built based on real traffic sceneries. Experimental results show that TL-Detector has the best comprehensive performance. TL-Detector achieves a detection speed of 277 FPS and a precision of 73.24% with only 0.72 GFLOPs. The experiments on LaRA (La Route Automatisee) public traffic light dataset show the excellent generalization ability. It indicates that TL-Detector can effectively achieve accurate and real-time detection for traffic lights.

Traffic lights recognition in foggy weather based on YOLOv5

Autonomous driving technology has gradually matured. The main application is unmanned vehicles, which have begun to test on the road. However, there is a critical technical problem with mitigating interfering factors in efficient traffic light detection and recognition. Due to the size of traffic lights and the complex road conditions, the detection accuracy is not up to satisfactory. This paper proposes a Traffic Light Recognition system based on YOLOv5, which has high speed and accuracy. The system also tests foggy data which gain from image processing. The experimental results show that the method achieved 0.9943 in normal conditions and 0.9937 in foggy conditions. Overall, the efficiency of YOLOv5 meets the practical application requirements.