Background estimation in difficult light conditions

Kód výsledku v IS VaVaI

<a href="https://www.isvavai.cz/riv?ss=detail&h=RIV%2F68407700%3A21230%2F18%3A00322162" target="_blank" >RIV/68407700:21230/18:00322162 - isvavai.cz</a>

Výsledek na webu

<a href="https://ieeexplore.ieee.org/document/8376367/" target="_blank" >https://ieeexplore.ieee.org/document/8376367/</a>

DOI - Digital Object Identifier

<a href="http://dx.doi.org/10.1109/RADIOELEK.2018.8376367" target="_blank" >10.1109/RADIOELEK.2018.8376367</a>

Jazyk výsledku

angličtina

Název v původním jazyce

Background estimation in difficult light conditions

Popis výsledku v původním jazyce

This paper presents an approach to background estimation in video-sequences from surveillance cameras placed in places with unexpected and massive changes in light conditions such as tunnels or railroad tracks. In those locations, it is necessary to ensure the safety of persons who may be present in the observed area. In the case of automated video monitoring, safety can be ensured only if the algorithm used to detect and classify objects in the camera field of view has high efficiency. Since the most of the detection algorithms are based on the difference of the consecutive frames, complicated surroundings like moving wagons or reflections produce a high number of false alerts, so the performance of the algorithms is weak in term of the accuracy. In this paper, we propose a method to eliminate false detection caused by a change of illumination.

Název v anglickém jazyce

Background estimation in difficult light conditions

Popis výsledku anglicky

This paper presents an approach to background estimation in video-sequences from surveillance cameras placed in places with unexpected and massive changes in light conditions such as tunnels or railroad tracks. In those locations, it is necessary to ensure the safety of persons who may be present in the observed area. In the case of automated video monitoring, safety can be ensured only if the algorithm used to detect and classify objects in the camera field of view has high efficiency. Since the most of the detection algorithms are based on the difference of the consecutive frames, complicated surroundings like moving wagons or reflections produce a high number of false alerts, so the performance of the algorithms is weak in term of the accuracy. In this paper, we propose a method to eliminate false detection caused by a change of illumination.

Druh

D - Stať ve sborníku

CEP obor

—

OECD FORD obor

20201 - Electrical and electronic engineering

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

2018

Kód důvěrnosti údajů

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

Název statě ve sborníku

2018 28th International Conference Radioelektronika

ISBN

978-1-5386-2485-2

ISSN

—

e-ISSN

—

Počet stran výsledku

4

Strana od-do

1-4

Název nakladatele

IEEE (Institute of Electrical and Electronics Engineers)

Místo vydání

—

Místo konání akce

Praha

Datum konání akce

19. 4. 2018

Typ akce podle státní příslušnosti

WRD - Celosvětová akce

Kód UT WoS článku

—