Measuring the Effects of Occlusion on Kernel Based Object Tracking Using Simulated Videos
Occlusion handling is one of the most studied problems for object tracking in computer vision. Many previous works claimed that occlusion can be handled effectively using Kalman filter, Particle filter and Mean Shift tracking methods. However, these methods were only tested on specific task videos...
Saved in:
Main Authors: | , , , |
---|---|
Format: | Article |
Language: | English |
Published: |
Elsevier
2012
|
Subjects: | |
Online Access: | http://ir.unimas.my/id/eprint/17380/1/Measuring%20the%20Effects%20of%20Occlusion%20on%20Kernel%20Based%20Object%20Tracking%20%28abstract%29.pdf http://ir.unimas.my/id/eprint/17380/ http://www.sciencedirect.com/science/article/pii/S1877705812026410 https://doi.org/10.1016/j.proeng.2012.07.241 |
Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
id |
my.unimas.ir.17380 |
---|---|
record_format |
eprints |
spelling |
my.unimas.ir.173802022-09-29T08:04:13Z http://ir.unimas.my/id/eprint/17380/ Measuring the Effects of Occlusion on Kernel Based Object Tracking Using Simulated Videos Beng, Yong Lee Lee, Hung Liew WaiShiang, Cheah Yin, Chai Wang T Technology (General) Occlusion handling is one of the most studied problems for object tracking in computer vision. Many previous works claimed that occlusion can be handled effectively using Kalman filter, Particle filter and Mean Shift tracking methods. However, these methods were only tested on specific task videos. In order to explore the actual potential of these methods, this paper examined the tracking methods with six simulation videos that consider various occlusion scenarios. Tracking performances are evaluated based on Sequence Frame Detection Accuracy (SFDA). The results show that Mean shift tracker would fail completely when full occlusion occurs as claimed by many previous works. In most cases, Kalman filter and Particle filter tracker achieved SFDA score between 0.3 and 0.4. It demonstrates that Particle filter tracker fails to detect object with arbitrary movement in one of the experiments. The effect of occlusion on each tracker is analysed with Frame Detection Accuracy (FDA) graph. Elsevier 2012 Article PeerReviewed text en http://ir.unimas.my/id/eprint/17380/1/Measuring%20the%20Effects%20of%20Occlusion%20on%20Kernel%20Based%20Object%20Tracking%20%28abstract%29.pdf Beng, Yong Lee and Lee, Hung Liew and WaiShiang, Cheah and Yin, Chai Wang (2012) Measuring the Effects of Occlusion on Kernel Based Object Tracking Using Simulated Videos. Procedia Engineering, 41. pp. 764-770. ISSN 1877-7058 http://www.sciencedirect.com/science/article/pii/S1877705812026410 https://doi.org/10.1016/j.proeng.2012.07.241 |
institution |
Universiti Malaysia Sarawak |
building |
Centre for Academic Information Services (CAIS) |
collection |
Institutional Repository |
continent |
Asia |
country |
Malaysia |
content_provider |
Universiti Malaysia Sarawak |
content_source |
UNIMAS Institutional Repository |
url_provider |
http://ir.unimas.my/ |
language |
English |
topic |
T Technology (General) |
spellingShingle |
T Technology (General) Beng, Yong Lee Lee, Hung Liew WaiShiang, Cheah Yin, Chai Wang Measuring the Effects of Occlusion on Kernel Based Object Tracking Using Simulated Videos |
description |
Occlusion handling is one of the most studied problems for object tracking in computer vision. Many previous works claimed that
occlusion can be handled effectively using Kalman filter, Particle filter and Mean Shift tracking methods. However, these methods were
only tested on specific task videos. In order to explore the actual potential of these methods, this paper examined the tracking methods
with six simulation videos that consider various occlusion scenarios. Tracking performances are evaluated based on Sequence Frame
Detection Accuracy (SFDA). The results show that Mean shift tracker would fail completely when full occlusion occurs as claimed by
many previous works. In most cases, Kalman filter and Particle filter tracker achieved SFDA score between 0.3 and 0.4. It demonstrates
that Particle filter tracker fails to detect object with arbitrary movement in one of the experiments. The effect of occlusion on each tracker
is analysed with Frame Detection Accuracy (FDA) graph. |
format |
Article |
author |
Beng, Yong Lee Lee, Hung Liew WaiShiang, Cheah Yin, Chai Wang |
author_facet |
Beng, Yong Lee Lee, Hung Liew WaiShiang, Cheah Yin, Chai Wang |
author_sort |
Beng, Yong Lee |
title |
Measuring the Effects of Occlusion on Kernel Based Object Tracking Using Simulated Videos |
title_short |
Measuring the Effects of Occlusion on Kernel Based Object Tracking Using Simulated Videos |
title_full |
Measuring the Effects of Occlusion on Kernel Based Object Tracking Using Simulated Videos |
title_fullStr |
Measuring the Effects of Occlusion on Kernel Based Object Tracking Using Simulated Videos |
title_full_unstemmed |
Measuring the Effects of Occlusion on Kernel Based Object Tracking Using Simulated Videos |
title_sort |
measuring the effects of occlusion on kernel based object tracking using simulated videos |
publisher |
Elsevier |
publishDate |
2012 |
url |
http://ir.unimas.my/id/eprint/17380/1/Measuring%20the%20Effects%20of%20Occlusion%20on%20Kernel%20Based%20Object%20Tracking%20%28abstract%29.pdf http://ir.unimas.my/id/eprint/17380/ http://www.sciencedirect.com/science/article/pii/S1877705812026410 https://doi.org/10.1016/j.proeng.2012.07.241 |
_version_ |
1745566035928416256 |
score |
13.209306 |