OptInOpt: Dual Optimization for Automatic Camera Calibration by Multi-Target Observations

Kód výsledku v IS VaVaI

<a href="https://www.isvavai.cz/riv?ss=detail&h=RIV%2F00216305%3A26230%2F19%3APU134956" target="_blank" >RIV/00216305:26230/19:PU134956 - isvavai.cz</a>

Výsledek na webu

<a href="http://dx.doi.org/10.1109/AVSS.2019.8909905" target="_blank" >http://dx.doi.org/10.1109/AVSS.2019.8909905</a>

DOI - Digital Object Identifier

<a href="http://dx.doi.org/10.1109/AVSS.2019.8909905" target="_blank" >10.1109/AVSS.2019.8909905</a>

Jazyk výsledku

angličtina

Název v původním jazyce

OptInOpt: Dual Optimization for Automatic Camera Calibration by Multi-Target Observations

Popis výsledku v původním jazyce

In this paper, we propose a new approach to automatic calibration of surveillance cameras. The proposed method is based on observing rigid objects in the scene and automatically estimating landmarks on these objects. The proposed approach can use arbitrary rigid objects, as was verified by experiments with a synthetic dataset, but vehicles were used during our experiments with real-life data. Landmarks on objects automatically detected by a convolutional neural network together with corresponding 3D positions in the object coordinate system are exploited during the camera calibration process. To determine 3D positions of the landmarks, fine-grained classification of the detected vehicles in the image plane is necessary. The proposed calibration method consists of dual optimization - optimization of objects positions in the world coordinate system and also optimization of the calibration parameters to minimize the re-projection error of the localized landmarks. The experiments show improvement in calibration accuracy over the existing method solving a similar problem furthermore with fewer restrictions on the input data. The calibration error on a real world dataset decreased from 6.88 % to 2.85 %.

Název v anglickém jazyce

OptInOpt: Dual Optimization for Automatic Camera Calibration by Multi-Target Observations

Popis výsledku anglicky

In this paper, we propose a new approach to automatic calibration of surveillance cameras. The proposed method is based on observing rigid objects in the scene and automatically estimating landmarks on these objects. The proposed approach can use arbitrary rigid objects, as was verified by experiments with a synthetic dataset, but vehicles were used during our experiments with real-life data. Landmarks on objects automatically detected by a convolutional neural network together with corresponding 3D positions in the object coordinate system are exploited during the camera calibration process. To determine 3D positions of the landmarks, fine-grained classification of the detected vehicles in the image plane is necessary. The proposed calibration method consists of dual optimization - optimization of objects positions in the world coordinate system and also optimization of the calibration parameters to minimize the re-projection error of the localized landmarks. The experiments show improvement in calibration accuracy over the existing method solving a similar problem furthermore with fewer restrictions on the input data. The calibration error on a real world dataset decreased from 6.88 % to 2.85 %.

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

2019

Kód důvěrnosti údajů

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

Název statě ve sborníku

16th IEEE International Conference on Advanced Video and Signal-based Surveillance

ISBN

978-1-7281-0990-9

ISSN

—

e-ISSN

—

Počet stran výsledku

8

Strana od-do

1-8

Název nakladatele

Institute of Electrical and Electronics Engineers

Místo vydání

Taipei

Místo konání akce

Taipei

Datum konání akce

18. 9. 2019

Typ akce podle státní příslušnosti

WRD - Celosvětová akce

Kód UT WoS článku

000524684300085