The Use of Multi-Sensor Video Surveillance System to Assess the Capacity of the Road Network
Open Access
- 1 February 2020
- journal article
- research article
- Published by Walter de Gruyter GmbH in Transport and Telecommunication Journal
- Vol. 21 (1), 15-31
- https://doi.org/10.2478/ttj-2020-0002
Abstract
Currently, in many cities around the world there is a significant increase in the number of vehicles, which leads to an aggravation of problems and contradictions in the road and transport system. This is especially true of traffic congestion, since the presence of the congestion leads to a number of negative consequences: an increase in travel time, additional fuel consumption and vehicle wear, stress and irritation of drivers and passengers, environmental poisoning and others. To solve the problem of congestion, it is necessary to have a reliable system for collecting information about the situation on the roads and a well-developed method for analyzing the collected information. The paper discusses the possibilities of collecting the required information using multi-touch video cameras and ways to improve them. A distinctive feature of this study is the registration of pedestrians crossing the road at the intersection. The aim of the work is to develop methods for collecting information using road sensor video surveillance systems in a traffic congestion and data processing using statistical methods such as: multiple regression analysis, cluster analysis, multidimensional scaling methods and others. The tasks were set: 1) to identify the most significant factors affecting the intensity of movement of vehicles at intersections in a congestion; 2) divide congestion into clusters with the identification of their characteristics; 3) to give a visual representation of multidimensional statistical information obtained with the help of multi-touch road video cameras.Keywords
This publication has 27 references indexed in Scilit:
- Vehicle detection from high-resolution aerial images using spatial pyramid pooling-based deep convolutional neural networksMultimedia Tools and Applications, 2016
- Rich Feature Hierarchies for Accurate Object Detection and Semantic SegmentationPublished by Institute of Electrical and Electronics Engineers (IEEE) ,2014
- Least Absolute Deviation Support Vector RegressionMathematical Problems in Engineering, 2014
- Vehicle recognition based on radar and vision sensor fusion for automatic emergency brakingPublished by Institute of Electrical and Electronics Engineers (IEEE) ,2013
- Multiple Kernel based KNN Classifiers for Vehicle ClassificationInternational Journal of Computer Applications, 2013
- Selective Search for Object RecognitionInternational Journal of Computer Vision, 2013
- Passive detection of vehicle loadingPublished by SPIE-Intl Soc Optical Eng ,2012
- AnSPSSR-Menu for Ordinal Factor AnalysisJournal of Statistical Software, 2012
- A Review of Computer Vision Techniques for the Analysis of Urban TrafficIEEE Transactions on Intelligent Transportation Systems, 2011
- Detection and classification of vehiclesIEEE Transactions on Intelligent Transportation Systems, 2002