Robust Extrinsic Camera Calibration from Trajectories in Human-Populated Environments

Abstract. This paper proposes a novel robust approach to perform inter-camera and ground-camera calibration in the context of visual monitoring of human-populated areas. By supposing that the monitored agents evolve on a single plane and that the cameras intrinsic parameters are known, we use the im...

ver descrição completa

Detalhes bibliográficos
Autores: Baqueiro Victorín, Guillermo, Hayet, Jean Bernard
Tipo de documento: artigo
Estado:Versão publicada
Data de publicação:2012
País:México
Recursos:Instituto Politécnico Nacional
Repositório:Repositorio Digital del IPN
OAI Identifier:oai:www.repositoriodigital.ipn.mx:123456789/14811
Acesso em linha:http://www.repositoriodigital.ipn.mx/handle/123456789/14811
Access Level:Acceso aberto
Palavra-chave:Keywords. Calibration, computer vision, tracking, videosurveillance and multiple camera systems.
Descrição
Resumo:Abstract. This paper proposes a novel robust approach to perform inter-camera and ground-camera calibration in the context of visual monitoring of human-populated areas. By supposing that the monitored agents evolve on a single plane and that the cameras intrinsic parameters are known, we use the image trajectories of moving objects as tracked by standard trackers in a RANSAC paradigm to estimate the extrinsic parameters of the different cameras. We illustrate the performance of our algorithm on several challenging experimental setups and compare it to existing approaches.