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

Kód výsledku v IS VaVaI

<a href="https://www.isvavai.cz/riv?ss=detail&h=RIV%2F00216305%3A26230%2F16%3APU121605" target="_blank" >RIV/00216305:26230/16:PU121605 - isvavai.cz</a>

Výsledek na webu

<a href="http://ieeexplore.ieee.org/document/7780697/" target="_blank" >http://ieeexplore.ieee.org/document/7780697/</a>

DOI - Digital Object Identifier

<a href="http://dx.doi.org/10.1109/CVPR.2016.328" target="_blank" >10.1109/CVPR.2016.328</a>

Jazyk výsledku

angličtina

Název v původním jazyce

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

Popis výsledku v původním jazyce

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.

Název v anglickém jazyce

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

Popis výsledku anglicky

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.

Druh

D - Stať ve sborníku

CEP obor

—

OECD FORD obor

10201 - Computer sciences, information science, bioinformathics (hardware development to be 2.2, social aspect to be 5.8)

Projekt

<a href="/cs/project/TE01020155" target="_blank" >TE01020155: Centrum pro rozvoj dopravních systémů</a><br>

Návaznosti

P - Projekt vyzkumu a vyvoje financovany z verejnych zdroju (s odkazem do CEP)

Rok uplatnění

2016

Kód důvěrnosti údajů

S - Úplné a pravdivé údaje o projektu nepodléhají ochraně podle zvláštních právních předpisů

Název statě ve sborníku

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

ISBN

978-1-4673-8851-1

ISSN

1063-6919

e-ISSN

—

Počet stran výsledku

10

Strana od-do

3006-3015

Název nakladatele

IEEE Computer Society

Místo vydání

Las Vegas

Místo konání akce

Las Vegas

Datum konání akce

26. 6. 2016

Typ akce podle státní příslušnosti

WRD - Celosvětová akce

Kód UT WoS článku

000400012303008