Estimation of intersection traffic density on decentralized architectures with deep networks

Yeshwanth, Chandan; Sooraj, P. S. Arun; Sudhakaran, Vinay; Raveendran, Varsha

doi:10.1109/isc2.2017.8090799

Cited by 14 publications

(6 citation statements)

References 13 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Neural networks were also used by other researchers in the development of automatic traffic control systems [22][20] [28]. Evolutionary algorithms and fuzzy logic were also used by many researchers [25][15][19] [16].…”

Section: Related Workmentioning

confidence: 99%

Dynamic Traffic Light System to Reduce The Waiting Time of Emergency Vehicles at Intersections within IoT Environment

Tashtoush

Al-Refai

Al-refai

et al. 2022

INT J COMPUT COMMUN, Int. J. Comput. Commun. Control

View full text Add to dashboard Cite

Traditional traffic light system, which works based on fixed cycle can be a main reason for traffic jam, due to lack of adaptation to road conditions. Traffic jam has a bad impact on drivers and road users due to the time delay it causes for road users to reach their destinations. This delay can cause a life threat in case of emergency vehicles, such as ambulance vehicles and police cars. One key solution to solve traffic jam on intersections is the dynamic traffic lights, where traffic light operation adapts based on the intersection traffic conditions. Since few of researches projects in the literature interested in solving traffic jam problem for emergency vehicles, the contribution of this paper is to introduces a novel approach to operate traffic light system. The new approach consists of two algorithms which are pure operation mode and hybrid operation mode. These operation modes aim to reduce the waiting time of emergency vehicles on traffic intersections. They assume that there is a smart infrastructure system uses Internet of Things (IoT) that can detect emergency vehicles arrival to an intersection. The smart infrastructure system switches traffic light operation from fixed cycle mode to dynamic mode. The dynamic mode manages traffic lights at intersections to reduce the waiting time of emergency vehicles. The paper presents a simulation of the proposed algorithms, highlights their advantages. In order to evaluate the efficiency of the new technique, we compared our approach with Wen algorithm in the literature and the Traditional traffic light system. Our evaluation study indicated that the proposed algorithms outperformed Wen technique and the Traditional system under different traffic scenarios

show abstract

Section: Related Workmentioning

confidence: 99%

Dynamic Traffic Light System to Reduce The Waiting Time of Emergency Vehicles at Intersections within IoT Environment

Tashtoush

Al-Refai

Al-refai

et al. 2022

INT J COMPUT COMMUN, Int. J. Comput. Commun. Control

View full text Add to dashboard Cite

show abstract

“…where γ is predefined and known to each node. It is noted that an adaptive γ corresponding to real traffic conditions is out of the scope of this paper, but can be locally estimated by calculating the number of received beacons [52] or with the use of edge computing servers [53].…”

Section: B Qf I Calculationsmentioning

confidence: 99%

A Proof-of-Quality-Factor (PoQF)-Based Blockchain and Edge Computing for Vehicular Message Dissemination

Ayaz

Sheng

Tian

et al. 2021

IEEE Internet Things J.

View full text Add to dashboard Cite

Blockchain applications in vehicular networks can offer many advantages including decentralization and improved security. However, most of consensus algorithms in blockchain are difficult to be implemented in a Vehicular Ad-Hoc Networks (VANET) without the help of edge computing services. For example, the connectivity in VANET only remains for a short period of time, which is not sufficient for highly time consuming consensus algorithms, e.g., Proof-of-Work, running on mobile edge nodes (vehicles). Other consensus algorithms also have some drawbacks, e.g. Proof-of-Stake (PoS) is biased towards nodes with higher amount of stakes and Proof-of-Elapsed-Time (PoET) is not highly secure against malicious nodes. For these reasons, we propose a voting blockchain based on Proof-of-Quality-Factor (PoQF) consensus algorithm, where threshold number of votes is controlled by edge computing servers. Specifically, PoQF includes voting for message validation and a competitive relay selection process based on probabilistic prediction of channel quality between transmitter and receiver. The performance bounds of failure and latency in message validation are obtained. The paper also analyzes the throughput of block generation, as well as the asymptotic latency, security and communication complexity of PoQF. An incentive distribution mechanism to reward honest nodes and punish malicious nodes is further presented and its effectiveness against collusion of nodes is proved using game theory. Simulation results show that PoQF reduces failure in validation by 11% and 15% as compared to PoS and PoET, respectively, and is 68 ms faster than PoET.

show abstract

“…General object detection frameworks can be used to detect vehicles from images (Girshick 2015; Redmon et al 2016;He et al 2017;Lin et al 2017), while as they are not tailored for vehicle detection, the performance is not satisfactory. In the transportation community, Bautista et al (2016) applied a convolutional neural network (CNN) for vehicle detection in low resolution traffic videos; Biswas et al (2019) combined two classical detection frameworks for accuracy consideration; and Yeshwanth et al (2017) extended to automatically segment the region of interest (ROI) based on optical flow. Recently, Zhang et al (2017b) generated a weighted mask to compensate for size variance caused by the perspective effect.…”

Section: Sydneymentioning

confidence: 99%

Turning Traffic Monitoring Cameras into Intelligent Sensors for Traffic Density Estimation

Hu¹,

Lam²,

Wong³

et al. 2021

Preprint

View full text Add to dashboard Cite

Accurate traffic state information plays a pivotal role in the Intelligent Transportation Systems (ITS), and it is an essential input to various smart mobility applications such as signal coordination and traffic flow prediction. The current practice to obtain the traffic state information is through specialized sensors such as loop detectors and speed cameras. In most metropolitan areas, traffic monitoring cameras have been installed to monitor the traffic conditions on arterial roads and expressways, and the collected videos or images are mainly used for visual inspection by traffic engineers. Unfortunately, the data collected from traffic monitoring cameras are affected by the 4L characteristics: Low frame rate, Low resolution, Lack of annotated data, and Located in complex road environments. Therefore, despite the great potentials of the traffic monitoring cameras, the 4L characteristics hinder them from providing useful traffic state information (e.g., speed, flow, density). This paper focuses on the traffic density estimation problem as it is widely applicable to various traffic surveillance systems. To the best of our knowledge, there is a lack of the holistic framework for addressing the 4L characteristics and extracting the traffic density information from traffic monitoring camera data. In view of this, this paper proposes a framework for estimating traffic density using uncalibrated traffic monitoring cameras with 4L characteristics. The proposed framework consists of two major components: camera calibration and vehicle detection. The camera calibration method estimates the actual length between pixels in the images and videos, and the vehicle counts are extracted from the deep-learning-based vehicle detection method. Combining the two components, high-granular traffic density can be estimated. To validate the proposed framework, two case studies were conducted in Hong Kong and Sacramento. The results show that the Mean Absolute Error (MAE) in camera calibration is less than 0.2 meters out of 6 meters, and the accuracy of vehicle detection under various conditions is approximately 90%. Overall, the MAE for the estimated density is 9.04 veh/km/lane in Hong Kong and 1.30 veh/km/lane in Sacramento. The research outcomes can be used to calibrate the speed-density fundamental diagrams, and the proposed framework can provide accurate and real-time traffic information without installing additional sensors.

show abstract

Estimation of intersection traffic density on decentralized architectures with deep networks

Cited by 14 publications

References 13 publications

Dynamic Traffic Light System to Reduce The Waiting Time of Emergency Vehicles at Intersections within IoT Environment

Dynamic Traffic Light System to Reduce The Waiting Time of Emergency Vehicles at Intersections within IoT Environment

A Proof-of-Quality-Factor (PoQF)-Based Blockchain and Edge Computing for Vehicular Message Dissemination

Turning Traffic Monitoring Cameras into Intelligent Sensors for Traffic Density Estimation

Contact Info

Product

Resources

About