Skip to main navigation Skip to search Skip to main content

CNN Based Vehicle Counting with Virtual Coil in Traffic Surveillance Video

  • Beijing Institute of Technology
  • Peking University

Research output: Chapter in Book/Report/Conference proceedingConference contributionpeer-review

Abstract

This paper presents an efficient method of vehicle counting based on convolutional neural network (CNN) with virtual coils. Within virtual coils, foreground is obtained by background substraction. Vehicle is then detected by voting of virtual coil sub-regions. To deal with vehicle cross-lane cases, a cascade classifier combining connected component analysis (CCA) and CNN is adopted. Experiments are carried out on seven real traffic videos. The proposed approach works well on recognizing cross-lane vehicles, achieving above 90% accuracy with real-time processing speed.

Original languageEnglish
Title of host publicationProceedings - 2015 IEEE International Conference on Multimedia Big Data, BigMM 2015
PublisherInstitute of Electrical and Electronics Engineers Inc.
Pages280-281
Number of pages2
ISBN (Electronic)9781479986880
DOIs
StatePublished - 9 Jul 2015
Externally publishedYes
Event1st IEEE International Conference on Multimedia Big Data, BigMM 2015 - Beijing, China
Duration: 20 Apr 201522 Apr 2015

Publication series

NameProceedings - 2015 IEEE International Conference on Multimedia Big Data, BigMM 2015

Conference

Conference1st IEEE International Conference on Multimedia Big Data, BigMM 2015
Country/TerritoryChina
CityBeijing
Period20/04/1522/04/15

Keywords

  • CCA
  • CNN
  • vehicle counting
  • virtual coil

Fingerprint

Dive into the research topics of 'CNN Based Vehicle Counting with Virtual Coil in Traffic Surveillance Video'. Together they form a unique fingerprint.

Cite this