Multi target tracking on Aerial videos

Gellért Máttyus, Csaba Benedek, T. Szirányi

Research output: Chapter in Book/Report/Conference proceedingConference contribution

1 Citation (Scopus)

Abstract

In this paper we propose a new method to detect and track multiple moving targets on image sequences recorded by Unmanned Aerial Vehicles (UAVs). Our approach focuses on challenging urban scenarios, where several object are simultaneously moving in various directions, and we must expect frequent occlusions caused by other moving vehicles or static scene objects such as buildings and bridges. In addition, since the UAVs are flying at relatively low altitude, the 3D-ness of the scene affects strongly the camera motion compensation process, and the independent object motions may be often confused by artifacts of frame registration. Our method enables real time operation, processing 320x240 frames at around 15 fps and 640×480 frames at 5 fps.

Original languageEnglish
Title of host publicationInternational Archives of the Photogrammetry, Remote Sensing and Spatial Information Sciences - ISPRS Archives
PublisherInternational Society for Photogrammetry and Remote Sensing
Volume38
Edition1W17
Publication statusPublished - 2015
EventISPRS Istanbul Workshop 2010 on Modeling of Optical Airborne and Spaceborne Sensors - Istanbul, Turkey
Duration: Oct 11 2010Oct 13 2010

Other

OtherISPRS Istanbul Workshop 2010 on Modeling of Optical Airborne and Spaceborne Sensors
CountryTurkey
CityIstanbul
Period10/11/1010/13/10

Fingerprint

Unmanned aerial vehicles (UAV)
Target tracking
video
Antennas
Motion compensation
Cameras
artifact
building
Processing
scenario
vehicle
method

Keywords

  • Motion compensation
  • Motion detection
  • Multi object tracking
  • UAV video

ASJC Scopus subject areas

  • Information Systems
  • Geography, Planning and Development

Cite this

Máttyus, G., Benedek, C., & Szirányi, T. (2015). Multi target tracking on Aerial videos. In International Archives of the Photogrammetry, Remote Sensing and Spatial Information Sciences - ISPRS Archives (1W17 ed., Vol. 38). International Society for Photogrammetry and Remote Sensing.

Multi target tracking on Aerial videos. / Máttyus, Gellért; Benedek, Csaba; Szirányi, T.

International Archives of the Photogrammetry, Remote Sensing and Spatial Information Sciences - ISPRS Archives. Vol. 38 1W17. ed. International Society for Photogrammetry and Remote Sensing, 2015.

Research output: Chapter in Book/Report/Conference proceedingConference contribution

Máttyus, G, Benedek, C & Szirányi, T 2015, Multi target tracking on Aerial videos. in International Archives of the Photogrammetry, Remote Sensing and Spatial Information Sciences - ISPRS Archives. 1W17 edn, vol. 38, International Society for Photogrammetry and Remote Sensing, ISPRS Istanbul Workshop 2010 on Modeling of Optical Airborne and Spaceborne Sensors, Istanbul, Turkey, 10/11/10.
Máttyus G, Benedek C, Szirányi T. Multi target tracking on Aerial videos. In International Archives of the Photogrammetry, Remote Sensing and Spatial Information Sciences - ISPRS Archives. 1W17 ed. Vol. 38. International Society for Photogrammetry and Remote Sensing. 2015
Máttyus, Gellért ; Benedek, Csaba ; Szirányi, T. / Multi target tracking on Aerial videos. International Archives of the Photogrammetry, Remote Sensing and Spatial Information Sciences - ISPRS Archives. Vol. 38 1W17. ed. International Society for Photogrammetry and Remote Sensing, 2015.
@inproceedings{c768675038c34596af8f7aca385c142e,
title = "Multi target tracking on Aerial videos",
abstract = "In this paper we propose a new method to detect and track multiple moving targets on image sequences recorded by Unmanned Aerial Vehicles (UAVs). Our approach focuses on challenging urban scenarios, where several object are simultaneously moving in various directions, and we must expect frequent occlusions caused by other moving vehicles or static scene objects such as buildings and bridges. In addition, since the UAVs are flying at relatively low altitude, the 3D-ness of the scene affects strongly the camera motion compensation process, and the independent object motions may be often confused by artifacts of frame registration. Our method enables real time operation, processing 320x240 frames at around 15 fps and 640×480 frames at 5 fps.",
keywords = "Motion compensation, Motion detection, Multi object tracking, UAV video",
author = "Gell{\'e}rt M{\'a}ttyus and Csaba Benedek and T. Szir{\'a}nyi",
year = "2015",
language = "English",
volume = "38",
booktitle = "International Archives of the Photogrammetry, Remote Sensing and Spatial Information Sciences - ISPRS Archives",
publisher = "International Society for Photogrammetry and Remote Sensing",
edition = "1W17",

}

TY - GEN

T1 - Multi target tracking on Aerial videos

AU - Máttyus, Gellért

AU - Benedek, Csaba

AU - Szirányi, T.

PY - 2015

Y1 - 2015

N2 - In this paper we propose a new method to detect and track multiple moving targets on image sequences recorded by Unmanned Aerial Vehicles (UAVs). Our approach focuses on challenging urban scenarios, where several object are simultaneously moving in various directions, and we must expect frequent occlusions caused by other moving vehicles or static scene objects such as buildings and bridges. In addition, since the UAVs are flying at relatively low altitude, the 3D-ness of the scene affects strongly the camera motion compensation process, and the independent object motions may be often confused by artifacts of frame registration. Our method enables real time operation, processing 320x240 frames at around 15 fps and 640×480 frames at 5 fps.

AB - In this paper we propose a new method to detect and track multiple moving targets on image sequences recorded by Unmanned Aerial Vehicles (UAVs). Our approach focuses on challenging urban scenarios, where several object are simultaneously moving in various directions, and we must expect frequent occlusions caused by other moving vehicles or static scene objects such as buildings and bridges. In addition, since the UAVs are flying at relatively low altitude, the 3D-ness of the scene affects strongly the camera motion compensation process, and the independent object motions may be often confused by artifacts of frame registration. Our method enables real time operation, processing 320x240 frames at around 15 fps and 640×480 frames at 5 fps.

KW - Motion compensation

KW - Motion detection

KW - Multi object tracking

KW - UAV video

UR - http://www.scopus.com/inward/record.url?scp=84923814144&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=84923814144&partnerID=8YFLogxK

M3 - Conference contribution

AN - SCOPUS:84923814144

VL - 38

BT - International Archives of the Photogrammetry, Remote Sensing and Spatial Information Sciences - ISPRS Archives

PB - International Society for Photogrammetry and Remote Sensing

ER -