Skip to main content

LUP Student Papers

LUND UNIVERSITY LIBRARIES

Evaluation of Real-Time Single-Object Tracking Algorithms in a Non-Stationary Robotic Agent

Klintefors, Pierre LU (2021) KOGM20 20211
Cognitive Science
Abstract
Visual object tracking is a fairly easy task for humans but a challenging problem in computer vision and thereby in humanoid implementation. Most of the existing object tracking evaluations are performed with prerecorded video footage, often with a stationary camera. This is not representative of a humanoid platform. The aim of the present thesis was to evaluate different object tracking algorithms’ suitability for being implemented in a humanoid by testing the algorithms’ performance in real-time using a non-stationary robotic agent. The results reflect a general trade-off between accuracy and computational cost. Kernelised correlation filters are depicted as a suitable choice for single-object tracking systems with limited computational... (More)
Visual object tracking is a fairly easy task for humans but a challenging problem in computer vision and thereby in humanoid implementation. Most of the existing object tracking evaluations are performed with prerecorded video footage, often with a stationary camera. This is not representative of a humanoid platform. The aim of the present thesis was to evaluate different object tracking algorithms’ suitability for being implemented in a humanoid by testing the algorithms’ performance in real-time using a non-stationary robotic agent. The results reflect a general trade-off between accuracy and computational cost. Kernelised correlation filters are depicted as a suitable choice for single-object tracking systems with limited computational power. Deep learning tracking algorithms is argued to be the better choice for systems with sufficient computational power. (Less)
Please use this url to cite or link to this publication:
author
Klintefors, Pierre LU
supervisor
organization
course
KOGM20 20211
year
type
H2 - Master's Degree (Two Years)
subject
keywords
Object Tracking, Computer Vision, Humanoid, Cognitive Science, Correlation Filter, Deep Learning, Object Tracking Evaluation
language
English
id
9053825
date added to LUP
2021-07-06 10:26:54
date last changed
2021-07-06 10:26:54
@misc{9053825,
  abstract     = {{Visual object tracking is a fairly easy task for humans but a challenging problem in computer vision and thereby in humanoid implementation. Most of the existing object tracking evaluations are performed with prerecorded video footage, often with a stationary camera. This is not representative of a humanoid platform. The aim of the present thesis was to evaluate different object tracking algorithms’ suitability for being implemented in a humanoid by testing the algorithms’ performance in real-time using a non-stationary robotic agent. The results reflect a general trade-off between accuracy and computational cost. Kernelised correlation filters are depicted as a suitable choice for single-object tracking systems with limited computational power. Deep learning tracking algorithms is argued to be the better choice for systems with sufficient computational power.}},
  author       = {{Klintefors, Pierre}},
  language     = {{eng}},
  note         = {{Student Paper}},
  title        = {{Evaluation of Real-Time Single-Object Tracking Algorithms in a Non-Stationary Robotic Agent}},
  year         = {{2021}},
}