Unsupervised Processing of Vehicle Appearance for Automatic Understanding in Traffic Surveillance

Kód výsledku v IS VaVaI

<a href="https://www.isvavai.cz/riv?ss=detail&h=RIV%2F00216305%3A26230%2F15%3APU117039" target="_blank" >RIV/00216305:26230/15:PU117039 - isvavai.cz</a>

Výsledek na webu

<a href="http://dx.doi.org/10.1109/DICTA.2015.7371318" target="_blank" >http://dx.doi.org/10.1109/DICTA.2015.7371318</a>

DOI - Digital Object Identifier

<a href="http://dx.doi.org/10.1109/DICTA.2015.7371318" target="_blank" >10.1109/DICTA.2015.7371318</a>

Jazyk výsledku

angličtina

Název v původním jazyce

Unsupervised Processing of Vehicle Appearance for Automatic Understanding in Traffic Surveillance

Popis výsledku v původním jazyce

This paper deals with unsupervised collection of information from traffic surveillance video streams. Deployment of usable traffic surveillance systems requires minimizing of efforts per installed camera - our goal is to enroll a new view on the street without any human operator input. We propose a method of automatically collecting vehicle samples from surveillance cameras, analyze their appearance and fully automatically collect a fine-grained dataset. This dataset can be used in multiple ways, we are explicitly showcasing the following ones: fine-grained recognition of vehicles and camera calibration including the scale. The experiments show that based on the automatically collected data, make&model vehicle recognition in the wild can be done accurately: average precision 0.890. The camera scale calibration (directly enabling automatic speed and size measurement) is twice as precise as the previous existing method. Our work leads to automatic collection of traffic statistics without the costly need for manual calibration or make&model annotation of vehicle samples. Unlike most previous approaches, our method is not limited to a small range of viewpoints (such as eye-level cameras shots), which is crucial for surveillance applications.

Název v anglickém jazyce

Unsupervised Processing of Vehicle Appearance for Automatic Understanding in Traffic Surveillance

Popis výsledku anglicky

This paper deals with unsupervised collection of information from traffic surveillance video streams. Deployment of usable traffic surveillance systems requires minimizing of efforts per installed camera - our goal is to enroll a new view on the street without any human operator input. We propose a method of automatically collecting vehicle samples from surveillance cameras, analyze their appearance and fully automatically collect a fine-grained dataset. This dataset can be used in multiple ways, we are explicitly showcasing the following ones: fine-grained recognition of vehicles and camera calibration including the scale. The experiments show that based on the automatically collected data, make&model vehicle recognition in the wild can be done accurately: average precision 0.890. The camera scale calibration (directly enabling automatic speed and size measurement) is twice as precise as the previous existing method. Our work leads to automatic collection of traffic statistics without the costly need for manual calibration or make&model annotation of vehicle samples. Unlike most previous approaches, our method is not limited to a small range of viewpoints (such as eye-level cameras shots), which is crucial for surveillance applications.

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

Výsledek vznikl pri realizaci vícero projektů. Více informací v záložce Projekty.

Návaznosti

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

Rok uplatnění

2015

Kód důvěrnosti údajů

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

Název statě ve sborníku

Digital Image Computing: Techniques and Applications (DICTA), 2015 International Conference on

ISBN

978-1-4673-6795-0

ISSN

—

e-ISSN

—

Počet stran výsledku

8

Strana od-do

1-8

Název nakladatele

Australian Pattern Recognition Society

Místo vydání

Adelaide

Místo konání akce

Adelaide

Datum konání akce

23. 11. 2015

Typ akce podle státní příslušnosti

WRD - Celosvětová akce

Kód UT WoS článku

000380485600107