City Bus Monitoring Supported by Computer Vision and Machine Learning Algorithms

Artur Wilkowski , Marcin Luckner , Ihor Mykhalevych

Abstract

In this paper, there are proposed methods and algorithms supporting city traffic controllers in effective perception and analysis of the visual information from the public transport monitoring system implemented in the City of Warsaw. To achieve this goal, public transport vehicles must be recognised and tracked in the camera view. In this work, we describe a structure and give preliminary results for the detection and tracking system proposed. The algorithms discussed in this paper uses background subtraction to extract moving vehicles from the scene and the classification system to reject objects that are not city buses. Furthermore, a custom tracking module is utilized to enable labelling of city buses instances. During the test performed in the City of Warsaw the system was able to successfully detect 89% bus instances giving less than 15% erroneous detections.
Author Artur Wilkowski (FGC)
Artur Wilkowski,,
- Faculty of Geodesy and Cartography
, Marcin Luckner (FMIS / DSMKP)
Marcin Luckner,,
- Department of Structural Methods for Knowledge Processing
, Ihor Mykhalevych (FMIS)
Ihor Mykhalevych,,
- Faculty of Mathematics and Information Science
Pages326-336
Publication size in sheets0.5
Book Szewczyk Roman, Zieliński Cezary, Kaliczyńska Małgorzata (eds.): Automation 2019: Progress in Automation, Robotics and Measurement Techniques, Advances in Intelligent Systems and Computing, vol. 920, 2019, Springer International Publishing, ISBN 978-3-030-13272-9, [978-3-030-13273-6], 727 p., DOI:10.1007/978-3-030-13273-6
Keywords in PolishWidzenie maszynowe, Detekcja, Śledzenie, nadzór ruchu
Keywords in EnglishComputer vision, detection, tracking, traffic monitoring
Abstract in PolishW pracy opisano eksperyment dotyczący automatycznego rozpoznania autobusów komunikacji miejskiej na zapisie wideo. Problem polagał na wyodrębnieniu pojazdów z tła, a następnie na odróżnieniu autobusów miejskich od samochodów osobowych i innych autobusów. Osiągnięto skuteczność 85% w rozpoznawaniu autobusów przy 15% błednych rozpoznań innych pojazdów.
DOIDOI:10.1007/978-3-030-13273-6_31
URL https://link.springer.com/chapter/10.1007/978-3-030-13273-6_31
Languageen angielski
Score (nominal)15
ScoreMinisterial score = 15.0, 10-07-2019, ChapterFromConference
Publication indicators Scopus Citations = 0
Citation count*
Cite
Share Share

Get link to the record


* presented citation count is obtained through Internet information analysis and it is close to the number calculated by the Publish or Perish system.
Back