Graph@FIT Submission to the NVIDIA AI City Challenge 2018
The result's identifiers
Result code in IS VaVaI
<a href="https://www.isvavai.cz/riv?ss=detail&h=RIV%2F00216305%3A26230%2F18%3APU130721" target="_blank" >RIV/00216305:26230/18:PU130721 - isvavai.cz</a>
Result on the web
<a href="https://ieeexplore.ieee.org/document/8575345" target="_blank" >https://ieeexplore.ieee.org/document/8575345</a>
DOI - Digital Object Identifier
<a href="http://dx.doi.org/10.1109/CVPRW.2018.00018" target="_blank" >10.1109/CVPRW.2018.00018</a>
Alternative languages
Result language
angličtina
Original language name
Graph@FIT Submission to the NVIDIA AI City Challenge 2018
Original language description
In our submission to the NVIDIA AI City Challenge, we address speed measurement of vehicles and vehicle re-identification. For both these tasks, we use a calibration method based on extracted vanishing points. We detect and track vehicles by a CNN-based detector and we construct 3D bounding boxes for all vehicles. For the speed measurement task, we estimate the speed from the movement of the bounding box in the 3D space using the calibration. Our approach to vehicle re-identification is based on extraction of visual features from "unpacked" images of the vehicles. The features are aggregated in temporal domain to obtain a single feature descriptor for the whole track. Furthermore, we utilize a validation network to improve the re-identification accuracy.
Czech name
—
Czech description
—
Classification
Type
D - Article in proceedings
CEP classification
—
OECD FORD branch
10201 - Computer sciences, information science, bioinformathics (hardware development to be 2.2, social aspect to be 5.8)
Result continuities
Project
Result was created during the realization of more than one project. More information in the Projects tab.
Continuities
P - Projekt vyzkumu a vyvoje financovany z verejnych zdroju (s odkazem do CEP)
Others
Publication year
2018
Confidentiality
S - Úplné a pravdivé údaje o projektu nepodléhají ochraně podle zvláštních právních předpisů
Data specific for result type
Article name in the collection
NVIDIA AI City Challenge 2018 (CVPRW)
ISBN
978-1-5386-6100-0
ISSN
—
e-ISSN
—
Number of pages
8
Pages from-to
77-84
Publisher name
IEEE Computer Society
Place of publication
Salt Lake City
Event location
Salt Lake City
Event date
Jun 18, 2018
Type of event by nationality
WRD - Celosvětová akce
UT code for WoS article
000457636800011