Stereo Vision Tracking of Multiple Objects in Complex Indoor Environments

This paper presents a novel system capable of solving the problem of tracking multiple targets in a crowded, complex and dynamic indoor environment, like those typical of mobile robot applications. The proposed solution is based on a stereo vision set in the acquisition step and a probabilistic algo...

Full description

Bibliographic Details
Main Authors: Álvaro Marcos, José M. Cañas, Cristina Losada, Daniel Pizarro, Manuel Mazo, Miguel A. Sotelo, Juan C. García, Marta Marrón-Romera
Format: Article
Language:English
Published: MDPI AG 2010-09-01
Series:Sensors
Subjects:
Online Access:http://www.mdpi.com/1424-8220/10/10/8865/
_version_ 1798041522304712704
author Álvaro Marcos
José M. Cañas
Cristina Losada
Daniel Pizarro
Manuel Mazo
Miguel A. Sotelo
Juan C. García
Marta Marrón-Romera
author_facet Álvaro Marcos
José M. Cañas
Cristina Losada
Daniel Pizarro
Manuel Mazo
Miguel A. Sotelo
Juan C. García
Marta Marrón-Romera
author_sort Álvaro Marcos
collection DOAJ
description This paper presents a novel system capable of solving the problem of tracking multiple targets in a crowded, complex and dynamic indoor environment, like those typical of mobile robot applications. The proposed solution is based on a stereo vision set in the acquisition step and a probabilistic algorithm in the obstacles position estimation process. The system obtains 3D position and speed information related to each object in the robot’s environment; then it achieves a classification between building elements (ceiling, walls, columns and so on) and the rest of items in robot surroundings. All objects in robot surroundings, both dynamic and static, are considered to be obstacles but the structure of the environment itself. A combination of a Bayesian algorithm and a deterministic clustering process is used in order to obtain a multimodal representation of speed and position of detected obstacles. Performance of the final system has been tested against state of the art proposals; test results validate the authors’ proposal. The designed algorithms and procedures provide a solution to those applications where similar multimodal data structures are found.
first_indexed 2024-04-11T22:22:41Z
format Article
id doaj.art-353e86e0d80345ac911eaef1184b2350
institution Directory Open Access Journal
issn 1424-8220
language English
last_indexed 2024-04-11T22:22:41Z
publishDate 2010-09-01
publisher MDPI AG
record_format Article
series Sensors
spelling doaj.art-353e86e0d80345ac911eaef1184b23502022-12-22T04:00:00ZengMDPI AGSensors1424-82202010-09-0110108865888710.3390/s101008865Stereo Vision Tracking of Multiple Objects in Complex Indoor EnvironmentsÁlvaro MarcosJosé M. CañasCristina LosadaDaniel PizarroManuel MazoMiguel A. SoteloJuan C. GarcíaMarta Marrón-RomeraThis paper presents a novel system capable of solving the problem of tracking multiple targets in a crowded, complex and dynamic indoor environment, like those typical of mobile robot applications. The proposed solution is based on a stereo vision set in the acquisition step and a probabilistic algorithm in the obstacles position estimation process. The system obtains 3D position and speed information related to each object in the robot’s environment; then it achieves a classification between building elements (ceiling, walls, columns and so on) and the rest of items in robot surroundings. All objects in robot surroundings, both dynamic and static, are considered to be obstacles but the structure of the environment itself. A combination of a Bayesian algorithm and a deterministic clustering process is used in order to obtain a multimodal representation of speed and position of detected obstacles. Performance of the final system has been tested against state of the art proposals; test results validate the authors’ proposal. The designed algorithms and procedures provide a solution to those applications where similar multimodal data structures are found.http://www.mdpi.com/1424-8220/10/10/8865/3D trackingBayesian estimationstereo vision sensormobile robots
spellingShingle Álvaro Marcos
José M. Cañas
Cristina Losada
Daniel Pizarro
Manuel Mazo
Miguel A. Sotelo
Juan C. García
Marta Marrón-Romera
Stereo Vision Tracking of Multiple Objects in Complex Indoor Environments
Sensors
3D tracking
Bayesian estimation
stereo vision sensor
mobile robots
title Stereo Vision Tracking of Multiple Objects in Complex Indoor Environments
title_full Stereo Vision Tracking of Multiple Objects in Complex Indoor Environments
title_fullStr Stereo Vision Tracking of Multiple Objects in Complex Indoor Environments
title_full_unstemmed Stereo Vision Tracking of Multiple Objects in Complex Indoor Environments
title_short Stereo Vision Tracking of Multiple Objects in Complex Indoor Environments
title_sort stereo vision tracking of multiple objects in complex indoor environments
topic 3D tracking
Bayesian estimation
stereo vision sensor
mobile robots
url http://www.mdpi.com/1424-8220/10/10/8865/
work_keys_str_mv AT alvaromarcos stereovisiontrackingofmultipleobjectsincomplexindoorenvironments
AT josemcanas stereovisiontrackingofmultipleobjectsincomplexindoorenvironments
AT cristinalosada stereovisiontrackingofmultipleobjectsincomplexindoorenvironments
AT danielpizarro stereovisiontrackingofmultipleobjectsincomplexindoorenvironments
AT manuelmazo stereovisiontrackingofmultipleobjectsincomplexindoorenvironments
AT miguelasotelo stereovisiontrackingofmultipleobjectsincomplexindoorenvironments
AT juancgarcia stereovisiontrackingofmultipleobjectsincomplexindoorenvironments
AT martamarronromera stereovisiontrackingofmultipleobjectsincomplexindoorenvironments