Tracking and counting vehicles in traffic video sequences using particle filtering

This paper presents a new method to track and count vehicles in video traffic sequences. The proposed method uses image processing, particle filtering, and motion coherence to group particles in videos, forming convex shapes that are analyzed for potential vehicles. This analysis takes into consider...

Full description

Saved in:
Bibliographic Details
Published in2013 IEEE International Instrumentation and Measurement Technology Conference (I2MTC) pp. 812 - 815
Main Authors Bouvie, Christiano, Scharcanski, Jacob, Barcellos, Pablo, Lopes Escouto, Fabiano
Format Conference Proceeding
LanguageEnglish
Published IEEE 01.05.2013
Subjects
computer vision
Filtering
Histograms
Image color analysis
image processing
particles clustering
Tracking
Tracking loops
vehicle count
vehicle tracking
Vehicles
video processing
Video sequences
Online AccessGet full text
ISBN9781467346214
1467346217
ISSN1091-5281
DOI10.1109/I2MTC.2013.6555527

Cover

More Information
Summary:This paper presents a new method to track and count vehicles in video traffic sequences. The proposed method uses image processing, particle filtering, and motion coherence to group particles in videos, forming convex shapes that are analyzed for potential vehicles. This analysis takes into consideration the convex shape of the objects and background information to merge or split the groupings. After a vehicle is identified, it is tracked using the similarity of color histograms on windows centered at the particle locations.
ISBN:9781467346214
1467346217
ISSN:1091-5281
DOI:10.1109/I2MTC.2013.6555527