scholarly journals Traffic Light and Arrow Signal Recognition Based on a Unified Network

2021 ◽  
Vol 11 (17) ◽  
pp. 8066
Author(s):  
Tien-Wen Yeh ◽  
Huei-Yung Lin ◽  
Chin-Chen Chang
Keyword(s):  
High Performance ◽  
Focal Length ◽  
Computation Time ◽  
Urban Traffic ◽  
Signal Recognition ◽  
Traffic Light ◽  
Light Detection ◽  
Traffic Lights ◽  
Map Data ◽  
Detection And Recognition

We present a traffic light detection and recognition approach for traffic lights that utilizes convolutional neural networks. We also introduce a technique for identifying arrow signal lights in multiple urban traffic environments. For detection, we use map data and two different focal length cameras for traffic light detection at various distances. For recognition, we propose a new algorithm that combines object detection and classification to recognize the light state classes of traffic lights. Furthermore, we use a unified network by sharing features to decrease computation time. The results reveal that the proposed approach enables high-performance traffic light detection and recognition.

scholarly journals Prototyping a Traffic Light Recognition Device with Expert Knowledge

Information ◽  
2018 ◽  
Vol 9 (11) ◽  
pp. 278 ◽  
Author(s):  
Thiago Almeida ◽  
Hendrik Macedo ◽  
Leonardo Matos ◽  
Nathanael Vasconcelos
Keyword(s):  
Expert Knowledge ◽  
Support Vector ◽  
Background Suppression ◽  
Processing Unit ◽  
Driver Assistance ◽  
Traffic Light ◽  
Accuracy Rate ◽  
Light Detection ◽  
Vector Machines ◽  
Detection And Recognition

Traffic light detection and recognition (TLR) research has grown every year. In addition, Machine Learning (ML) has been largely used not only in traffic light research but in every field where it is useful and possible to generalize data and automatize human behavior. ML algorithms require a large amount of data to work properly and, thus, a lot of computational power is required to analyze the data. We argue that expert knowledge should be used to decrease the burden of collecting a huge amount of data for ML tasks. In this paper, we show how such kind of knowledge was used to reduce the amount of data and improve the accuracy rate for traffic light detection and recognition. Results show an improvement in the accuracy rate around 15%. The paper also proposes a TLR device prototype using both camera and processing unit of a smartphone which can be used as a driver assistance. To validate such layout prototype, a dataset was built and used to test an ML model based on adaptive background suppression filter (AdaBSF) and Support Vector Machines (SVMs). Results show 100% precision rate and recall of 65%.

scholarly journals TRAFFIC LIGHT DETECTION USING CONIC SECTION GEOMETRY

2016 ◽  
Vol III-1 ◽  
pp. 191-200
Author(s):  
S. Hosseinyalmdary ◽  
A. Yilmaz
Keyword(s):  
Prior Knowledge ◽  
Pose Estimation ◽  
Open Problem ◽  
Autonomous Vehicles ◽  
Conic Section ◽  
Traffic Light ◽  
Light Detection ◽  
State Recognition ◽  
Traffic Lights ◽  
Stereo Cameras

Traffic lights detection and their state recognition is a crucial task that autonomous vehicles must reliably fulfill. Despite scientific endeavors, it still is an open problem due to the variations of traffic lights and their perception in image form. Unlike previous studies, this paper investigates the use of inaccurate and publicly available GIS databases such as OpenStreetMap. In addition, we are the first to exploit conic section geometry to improve the shape cue of the traffic lights in images. Conic section also enables us to estimate the pose of the traffic lights with respect to the camera. Our approach can detect multiple traffic lights in the scene, it also is able to detect the traffic lights in the absence of prior knowledge, and detect the traffics lights as far as 70 meters. The proposed approach has been evaluated for different scenarios and the results show that the use of stereo cameras significantly improves the accuracy of the traffic lights detection and pose estimation.

scholarly journals Lightweight PVIDNet: A Priority Vehicles Detection Network Model Based on Deep Learning for Intelligent Traffic Lights

Sensors ◽  
2020 ◽  
Vol 20 (21) ◽  
pp. 6218
Author(s):  
Rodrigo Carvalho Barbosa ◽  
Muhammad Shoaib Ayub ◽  
Renata Lopes Rosa ◽  
Demóstenes Zegarra Rodríguez ◽  
Lunchakorn Wuttisittikulkij
Keyword(s):  
Deep Learning ◽  
Traffic Control ◽  
Detection System ◽  
Lightweight Design ◽  
Vehicle Detection ◽  
Activation Function ◽  
Urban Traffic ◽  
Vehicle Classification ◽  
Traffic Light ◽  
Traffic Lights

Minimizing human intervention in engines, such as traffic lights, through automatic applications and sensors has been the focus of many studies. Thus, Deep Learning (DL) algorithms have been studied for traffic signs and vehicle identification in an urban traffic context. However, there is a lack of priority vehicle classification algorithms with high accuracy, fast processing, and a lightweight solution. For filling those gaps, a vehicle detection system is proposed, which is integrated with an intelligent traffic light. Thus, this work proposes (1) a novel vehicle detection model named Priority Vehicle Image Detection Network (PVIDNet), based on YOLOV3, (2) a lightweight design strategy for the PVIDNet model using an activation function to decrease the execution time of the proposed model, (3) a traffic control algorithm based on the Brazilian Traffic Code, and (4) a database containing Brazilian vehicle images. The effectiveness of the proposed solutions were evaluated using the Simulation of Urban MObility (SUMO) tool. Results show that PVIDNet reached an accuracy higher than 0.95, and the waiting time of priority vehicles was reduced by up to 50%, demonstrating the effectiveness of the proposed solution.

Traffic light detection and recognition based on Haar-like features

2018 ◽  
Author(s):  
Sang-Hyuk Lee ◽  
Jung-Hawn Kim ◽  
Yong-Jin Lim ◽  
Joonhong Lim
Keyword(s):  
Traffic Light ◽  
Light Detection ◽  
Detection And Recognition

scholarly journals Bi-Level Optimization Model for Urban Traffic Control

2021 ◽  
Vol 21 (3) ◽  
pp. 108-126
Author(s):  
Krasimira Stoilova ◽  
Todor Stoilov ◽  
Stanislav Dimitrov
Keyword(s):  
Traffic Control ◽  
Optimization Model ◽  
Dynamical Behavior ◽  
Control Variable ◽  
Green Light ◽  
Urban Traffic ◽  
Traffic Light ◽  
Urban Network ◽  
Traffic Lights ◽  
Urban Traffic Control

Abstract The urban traffic control optimization is a complex problem because of the interconnections among the junctions and the dynamical behavior of the traffic flows. Optimization with one control variable in the literature is presented. In this research optimization model consisting of two control variables is developed. Hierarchical bi-level methodology is proposed for realization of integrated optimal control. The urban traffic management is implemented by simultaneously control of traffic light cycles and green light durations of the traffic lights of urban network of crossroads.

Traffic light detection and recognition for autonomous vehicles

2015 ◽  
Vol 22 (1) ◽  
pp. 50-56 ◽  
Author(s):  
Guo Mu ◽  
Zhang Xinyu ◽  
Li Deyi ◽  
Zhang Tianlei ◽  
An Lifeng
Keyword(s):  
Autonomous Vehicles ◽  
Traffic Light ◽  
Light Detection ◽  
Detection And Recognition

scholarly journals OPTIMIZATION OF MANAGEMENT OF URBAN LIGHTS WITH THE USE OF NEURAL NETWORKS

THE BULLETIN ◽  
2021 ◽  
Vol 389 (1) ◽  
pp. 14-17
Author(s):  
A.А. Suleimen ◽  
G.B. Kashaganova ◽  
G.B. Issayeva ◽  
B.R. Absatarova ◽  
M.C. Ibraev
Keyword(s):  
Neural Networks ◽  
Mathematical Model ◽  
Traffic Management ◽  
Urban Traffic ◽  
Control Parameters ◽  
Traffic Flows ◽  
Traffic Light ◽  
Traffic Lights ◽  
The Road ◽  
On The Road

One of the most pressing problems of large cities is the problem of traffic management of vehicles. The reason for this problem is an imperfect way to manage traffic flows. Traffic light regulation is of particular importance in traffic management. Most modern traffic light control systems operate at set time intervals and are not able to cope with the constantly changing situation on the road. A promising direction for solving this problem is to optimize the system using artificial neural networks. The advantage of neural networks is self-learning, which allows the system to adapt to the changing situation on the road. Despite numerous attempts, it has not yet been possible to obtain a high-quality mathematical model of urban traffic management. This model should determine the functional dependence of transport flow parameters on control parameters. Nowadays, traffic flows are regulated everywhere by means of traffic lights. If we can get a fairly accurate mathematical model of traffic flows, we can determine the optimal duration of the traffic signal phases to achieve the maximum capacity of the road network node. A fairly accurate mathematical model of traffic management that works in predictive mode will display an estimate of the optimal control parameters, as well as make correct decisions in emergency situations. Well-known mathematical models of road traffic take into account only the average values of traffic flows, and not the exact number of cars on each road section at a particular time.

scholarly journals Regulation Models of Crossroad Based on Wireless Sensor Networks and Notions of the Fluid Mechanics

2020 ◽  
Vol 9 (3) ◽  
pp. 2536-2541
Keyword(s):  
Traffic Control ◽  
Traffic Congestion ◽  
Information Technologies ◽  
Smart Cities ◽  
Urban Traffic ◽  
Wireless Sensor ◽  
Effective Control ◽  
Control Mechanisms ◽  
Traffic Light ◽  
Traffic Lights

The permanent growth of the population in smart cities has increased the number of vehicles. Consequently the problem of traffic congestion has become one of the main problems to be solved by today's traffic control systems, especially at traffic intersections. In fact, the traditional method which avoids the congestion in a crossroads is the classic command (Timing) by means of traffic lights. However, the traffic light management modes are sometimes based on classic models which make them unsuitable for the treatment of different experienced situations in traffic (either dense or fluid traffic). Fortunately, thanks to the significant progress made, especially the use of New Information Technologies and Communications for example Wireless Sensor Network, for the regulation of traffic, are solutions become central in the field of urban traffic management. They have made it possible to propose more effective control mechanisms to reduce the effects of traffic congestion. In this article, we will present the continuation of our work [1], the objective is to offer to the users of the road a crossing time as long as possible, while preventing the car cap to propagate over a distance that is set between two wireless sensors, to do this, we can act on the setting of the traffic light to regulate traffic in intersections.

Sign in / Sign up

Export Citation Format

Share Document