Modeling and Evaluation of Intelligent Monitoring Systems at Urban Intersections to Improve Real-Time Monitoring of Congestion and Traffic Safety

Abstract

Abstract:In recent decades, with the advent of technology and information technology, transportation systems have also been moving in this direction, and one of the challenges of the transportation system is due to the multiplicity and increase of vehicle management and control. Many techniques and methods have been proposed in this field that in today's world, the use of intelligent systems has a higher efficiency. In fact, safety has the ability to reduce the number of vehicles with minimal delay and create discomfort for the users depends directly in order and arrangement to facilitate the immediate and direct involvement of the vehicle in traffic flow. One of the ways to demonstrate the efficiency of intelligent monitoring systems is create model before the implementation phase. This article aims at modeling and evaluating an intelligent surveillance system at urban intersections, which is carried out using colored petri nets. In the proposed method, first, the urban intersection architecture is described with the benefit of traffic rules then, the inconsistency and coincidence states are determined and finally, reliability and response time are measured by the CpnTools with the help of Petri Nets. The results show that the intelligent monitoring equipment related to the intelligent surveillance system increases the safety of the road network and, finally, has secured and fluent traffic.

Referring expression comprehension model with matching detection and linguistic feedback

“…Generally, REC involves the research fields such as image segmentation, object classification, and texture recognition. Image segmentation is important to many research fields such as synthetic aperture radar (SAR) image registration [1], real‐time agricultural tractors [2], scour depth prediction [3], real‐time traffic monitoring [4] etc. A neural network with a hybrid algorithm of convolutional neural network (CNN) and multi‐layer perception CNN‐multilayer perceptron [5] are utilised for the image classification.…”