Edge ML Technique for Smart Traffic Management in Intelligent Transportation Systems

Abstract

In urban traffic, a Dynamic Traffic Light System (DTLS) is an important aspect of automatic driving. DTLS estimates the time of the light signal from images of dynamically changing road traffic. In conventional traffic light systems, light signals are enabled at predefined or fixed time intervals without having information on the current traffic density on the road. This static behavior of the traffic light system increases unnecessary waiting time on the road, eventually creating traffic jams, environmental pollution, and other health emergencies. The smart traffic light system addresses these issues with self-learning algorithms and dynamically allows traffic to pass by learning current traffic density. In this paper, a visionbased DTLS is proposed using the YOLO (You Only Look Once) object detection algorithm that detects and counts the total number of vehicles on the roads of a traffic signal junction. The traffic signals are tuned based on the computed traffic to minimize the overall delay at that junction. Moreover, the traffic junctions are facilitated to communicate with the adjacent junctions to transmit the cumulative traffic delay observed. This delay is used to prioritize traffic passing through salient blocks like schools, offices, hospitals, etc. The paper aims to minimize the overhead incurred in both computations of traffic (using approximate computing) and in communication networks (using low-power technologies of IEEE 802.15.4 standard, specifically DSME MAC and/or LoRaWAN). The proposed system accomplishes its objective of smart city infrastructure by optimizing the traffic flow. Further, the paper provides a mechanism for green traffic corridors for emergency vehicles.

Ideology of Urban Road Transport Chaos and Accident Risk Management for Sustainable Transport Systems

“…The developed approach can be integrated with the Internet of Things (IoT) [120][121][122]. Within the framework of this approach, the collection of initial data on the characteristics of traffic flows can be carried out using the YOLOv5 neural network.…”

“…In the future, the developed neural network model can be modified to detect and predict traffic accidents in real time. At the same time, the use of cloud sensors [120] can provide storage and highspeed processing of a large amount of source data. The additional use of edge computing technology [122] will reduce the load on computing systems.…”