Publication detail

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

SOCHOR, J. ŠPAŇHEL, J. HEROUT, A.

Original Title

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

Type

abstract

Language

English

Original Abstract

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. This extended abstract is based on previously published CVPR paper and extended journal version of the paper which is currently under review.

Authors

SOCHOR, J.; ŠPAŇHEL, J.; HEROUT, A.

Released

19. 7. 2017

Publisher

IEEE Computer Society

Location

Honolulu, HI

Pages from

1

Pages to

2

Pages count

2

BibTex

@misc{BUT168564,
  author="Jakub {Sochor} and Jakub {Špaňhel} and Adam {Herout}",
  title="BoxCars: 3D Boxes for Improved Fine-Grained Vehicle Recognition",
  booktitle="The Fourth Workshop on Fine-Grained Visual Categorization (CVPR 2017)",
  year="2017",
  pages="1--2",
  publisher="IEEE Computer Society",
  address="Honolulu, HI",
  note="abstract"
}