Detail publikace

BoxCars: 3D Boxes as CNN Input for Improved Fine-Grained Vehicle Recognition

SOCHOR, J. HEROUT, A. HAVEL, J.

Originální název

BoxCars: 3D Boxes as CNN Input for Improved Fine-Grained Vehicle Recognition

Typ

článek ve sborníku ve WoS nebo Scopus

Jazyk

angličtina

Originální abstrakt

We are dealing with the problem of fine-grained vehicle make&model recognition and verification. Our contribution is showing that extracting additional data from the video stream - besides the vehicle image itself - and feeding it into the deep convolutional neural network boosts the recognition performance considerably. This additional information includes: 3D vehicle bounding box used for "unpacking" the vehicle image, its rasterized low-resolution shape, and information about the 3D vehicle orientation. Experiments show that adding such information decreases classification error by 26% (the accuracy is improved from 0.772 to 0.832) and boosts verification average precision by 208% (0.378 to 0.785) compared to baseline pure CNN without any input modifications. Also, the pure baseline CNN outperforms the recent state of the art solution by 0.081. We provide an annotated set "BoxCars" of surveillance vehicle images augmented by various automatically extracted auxiliary information. Our approach and the dataset can considerably improve the performance of traffic surveillance systems.

Klíčová slova

Fine-grained recognition, vehicles, CNN, input modification

Autoři

SOCHOR, J.; HEROUT, A.; HAVEL, J.

Vydáno

10. 3. 2016

Nakladatel

IEEE Computer Society

Místo

Las Vegas

ISBN

978-1-4673-8851-1

Kniha

The IEEE Conference on Computer Vision and Pattern Recognition (CVPR)

ISSN

1063-6919

Periodikum

Proceedings of the IEEE Computer Society Conference on Computer Vision and Pattern Recognition

Číslo

6

Stát

neuvedeno

Strany od

3006

Strany do

3015

Strany počet

10

URL

BibTex

@inproceedings{BUT130949,
  author="Jakub {Sochor} and Adam {Herout} and Jiří {Havel}",
  title="BoxCars: 3D Boxes as CNN Input for Improved Fine-Grained Vehicle Recognition",
  booktitle="The IEEE Conference on Computer Vision and Pattern Recognition (CVPR)",
  year="2016",
  journal="Proceedings of the IEEE Computer Society Conference on Computer Vision and Pattern Recognition",
  number="6",
  pages="3006--3015",
  publisher="IEEE Computer Society",
  address="Las Vegas",
  doi="10.1109/CVPR.2016.328",
  isbn="978-1-4673-8851-1",
  issn="1063-6919",
  url="http://ieeexplore.ieee.org/document/7780697/"
}