An Integrated Object Detection and Tracking Framework for Mobile Robots

William Kristian Juel; Frederik Haarslev; Norbert Krüger; Leon Bodenhagen

doi:10.5220/0009888405130520

An Integrated Object Detection and Tracking Framework for Mobile Robots

William Kristian Juel^*, Frederik Haarslev, Norbert Krüger, Leon Bodenhagen

^*Kontaktforfatter

Publikation: Kapitel i bog/rapport/konference-proceeding › Konferencebidrag i proceedings › Forskning › peer review

Abstract

In this paper, we propose an end-to-end-solution to the problem of multi-object tracking on a mobile robot. The tracking system consists of a process where we project 2D multi-object detections to the robots base frame, using RGB-D sensor data. These detections are then transformed to the map frame using a localization algorithm. This system predicts trajectories of humans and objects in the environment of the robot and can be adapted to work with any detector and track from multiple cameras. The system can then be used to build a temporally consistent costmap to improve navigation strategies.

Originalsprog	Engelsk
Titel	Proceedings of the 17th International Conference on Informatics in Control, Automation and Robotics - Volume 1: ICINCO : ICINCO
Redaktører	Oleg Gusikhin, Kurosh Madani, Janan Zaytoon
Vol/bind	1
Forlag	SCITEPRESS Digital Library
Publikationsdato	2020
Sider	513-520
ISBN (Elektronisk)	978-989-758-442-8
DOI	https://doi.org/10.5220/0009888405130520
Status	Udgivet - 2020
Begivenhed	17th International Conference on Informatics in Control, Automation and Robotics (ICINCO) - Varighed: 7. jul. 2020 → 9. jul. 2020

Konference

Konference	17th International Conference on Informatics in Control, Automation and Robotics (ICINCO)
Periode	07/07/2020 → 09/07/2020

Dokumenter og links

10.5220/0009888405130520

2 Afsluttet

SMOOTH: Seamless huMan-robot interactiOn fOr THe support of elderly people
Bodenhagen, L., Palinko, O., Manoonpong, P., Haarslev, F., Krüger, N., Juel, W. K., Kollakidou, A. & Naik, L.
01/04/2017 → 31/01/2021
Projekter: Projekt › Forskning
Health-CAT: Health Care Assisting Technology
Manoonpong, P., Bodenhagen, L., Juel, W. K., Haarslev, F., Palinko, O., Krüger, N., Kollakidou, A. & Naik, L.
01/02/2017 → 15/11/2020
Projekter: Projekt › EU

Citationsformater

Juel, W. K., Haarslev, F., Krüger, N., & Bodenhagen, L. (2020). An Integrated Object Detection and Tracking Framework for Mobile Robots. I O. Gusikhin, K. Madani, & J. Zaytoon (red.), Proceedings of the 17th International Conference on Informatics in Control, Automation and Robotics - Volume 1: ICINCO: ICINCO (Bind 1, s. 513-520). SCITEPRESS Digital Library. https://doi.org/10.5220/0009888405130520

Juel, William Kristian ; Haarslev, Frederik ; Krüger, Norbert et al. / An Integrated Object Detection and Tracking Framework for Mobile Robots. Proceedings of the 17th International Conference on Informatics in Control, Automation and Robotics - Volume 1: ICINCO: ICINCO. red. / Oleg Gusikhin ; Kurosh Madani ; Janan Zaytoon. Bind 1 SCITEPRESS Digital Library, 2020. s. 513-520

@inproceedings{fafc6e5dc2c2449cb4e69854e182089d,

title = "An Integrated Object Detection and Tracking Framework for Mobile Robots",

abstract = "In this paper, we propose an end-to-end-solution to the problem of multi-object tracking on a mobile robot. The tracking system consists of a process where we project 2D multi-object detections to the robots base frame, using RGB-D sensor data. These detections are then transformed to the map frame using a localization algorithm. This system predicts trajectories of humans and objects in the environment of the robot and can be adapted to work with any detector and track from multiple cameras. The system can then be used to build a temporally consistent costmap to improve navigation strategies.",

keywords = "Automation, Detection, Mobile robots, Perception system, Visual tracking",

author = "Juel, {William Kristian} and Frederik Haarslev and Norbert Kr{\"u}ger and Leon Bodenhagen",

year = "2020",

doi = "10.5220/0009888405130520",

language = "English",

volume = "1",

pages = "513--520",

editor = "Oleg Gusikhin and Kurosh Madani and Janan Zaytoon",

booktitle = "Proceedings of the 17th International Conference on Informatics in Control, Automation and Robotics - Volume 1: ICINCO",

publisher = "SCITEPRESS Digital Library",

note = "17th International Conference on Informatics in Control, Automation and Robotics (ICINCO) ; Conference date: 07-07-2020 Through 09-07-2020",

}

Juel, WK, Haarslev, F, Krüger, N & Bodenhagen, L 2020, An Integrated Object Detection and Tracking Framework for Mobile Robots. i O Gusikhin, K Madani & J Zaytoon (red), Proceedings of the 17th International Conference on Informatics in Control, Automation and Robotics - Volume 1: ICINCO: ICINCO. bind 1, SCITEPRESS Digital Library, s. 513-520, 17th International Conference on Informatics in Control, Automation and Robotics (ICINCO), 07/07/2020. https://doi.org/10.5220/0009888405130520

An Integrated Object Detection and Tracking Framework for Mobile Robots. / Juel, William Kristian; Haarslev, Frederik; Krüger, Norbert et al.

Proceedings of the 17th International Conference on Informatics in Control, Automation and Robotics - Volume 1: ICINCO: ICINCO. red. / Oleg Gusikhin; Kurosh Madani; Janan Zaytoon. Bind 1 SCITEPRESS Digital Library, 2020. s. 513-520.

Publikation: Kapitel i bog/rapport/konference-proceeding › Konferencebidrag i proceedings › Forskning › peer review

TY - GEN

T1 - An Integrated Object Detection and Tracking Framework for Mobile Robots

AU - Juel, William Kristian

AU - Haarslev, Frederik

AU - Krüger, Norbert

AU - Bodenhagen, Leon

PY - 2020

Y1 - 2020

N2 - In this paper, we propose an end-to-end-solution to the problem of multi-object tracking on a mobile robot. The tracking system consists of a process where we project 2D multi-object detections to the robots base frame, using RGB-D sensor data. These detections are then transformed to the map frame using a localization algorithm. This system predicts trajectories of humans and objects in the environment of the robot and can be adapted to work with any detector and track from multiple cameras. The system can then be used to build a temporally consistent costmap to improve navigation strategies.

AB - In this paper, we propose an end-to-end-solution to the problem of multi-object tracking on a mobile robot. The tracking system consists of a process where we project 2D multi-object detections to the robots base frame, using RGB-D sensor data. These detections are then transformed to the map frame using a localization algorithm. This system predicts trajectories of humans and objects in the environment of the robot and can be adapted to work with any detector and track from multiple cameras. The system can then be used to build a temporally consistent costmap to improve navigation strategies.

KW - Automation

KW - Detection

KW - Mobile robots

KW - Perception system

KW - Visual tracking

U2 - 10.5220/0009888405130520

DO - 10.5220/0009888405130520

M3 - Article in proceedings

VL - 1

SP - 513

EP - 520

BT - Proceedings of the 17th International Conference on Informatics in Control, Automation and Robotics - Volume 1: ICINCO

A2 - Gusikhin, Oleg

A2 - Madani, Kurosh

A2 - Zaytoon, Janan

PB - SCITEPRESS Digital Library

T2 - 17th International Conference on Informatics in Control, Automation and Robotics (ICINCO)

Y2 - 7 July 2020 through 9 July 2020

ER -

Juel WK, Haarslev F, Krüger N , Bodenhagen L. An Integrated Object Detection and Tracking Framework for Mobile Robots. I Gusikhin O, Madani K, Zaytoon J, red., Proceedings of the 17th International Conference on Informatics in Control, Automation and Robotics - Volume 1: ICINCO: ICINCO. Bind 1. SCITEPRESS Digital Library. 2020. s. 513-520 doi: 10.5220/0009888405130520

An Integrated Object Detection and Tracking Framework for Mobile Robots

Abstract

Konference

Dokumenter og links

Fingeraftryk

Relaterede Projekter

SMOOTH: Seamless huMan-robot interactiOn fOr THe support of elderly people

Health-CAT: Health Care Assisting Technology

Citationsformater