Fine-grained vehicle recognition by deep Convolutional Neural Network

Kun Huang, Bailing Zhang

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

12 Citations (Scopus)

Abstract

Vehicle recognition has been an important topic in intelligent transportation. However, to recognize different vehicle models from a same make is difficult as there are many near-identical cars under different brand names. In this paper, we investigated fine-grained vehicle recognition via deep Convolutional Neural Network (CNN). Vehicle and the corresponding parts are localized with the help of Region-based Convolutional Neural Networks (RCNN) and their features from a set of pre-trained CNNs are aggregated to train a SVM classifier. We created a fine-grained vehicle dataset and performed subsequent experiments, with preliminary results showing the potentials of the method.

Original languageEnglish
Title of host publicationProceedings - 2016 9th International Congress on Image and Signal Processing, BioMedical Engineering and Informatics, CISP-BMEI 2016
PublisherInstitute of Electrical and Electronics Engineers Inc.
Pages465-470
Number of pages6
ISBN (Electronic)9781509037100
DOIs
Publication statusPublished - 13 Feb 2017
Event9th International Congress on Image and Signal Processing, BioMedical Engineering and Informatics, CISP-BMEI 2016 - Datong, China
Duration: 15 Oct 201617 Oct 2016

Publication series

NameProceedings - 2016 9th International Congress on Image and Signal Processing, BioMedical Engineering and Informatics, CISP-BMEI 2016

Conference

Conference9th International Congress on Image and Signal Processing, BioMedical Engineering and Informatics, CISP-BMEI 2016
Country/TerritoryChina
CityDatong
Period15/10/1617/10/16

Keywords

  • Fine-grained vehicle recognition
  • Region-based Convolutional Neural Networks
  • part detection

Fingerprint

Dive into the research topics of 'Fine-grained vehicle recognition by deep Convolutional Neural Network'. Together they form a unique fingerprint.

Cite this