A pursuit method for video annotation
Video annotation is a process of describing or elaborating on objects or events represented in video. Part of this process involves time consuming manual interactions to define spatio-temporal entities - such as a region of interest within the video. This dissertation proposes a pursuit method for v...
Main Author: | |
---|---|
Language: | English |
Published: |
University of British Columbia
2012
|
Online Access: | http://hdl.handle.net/2429/43613 |
id |
ndltd-LACETR-oai-collectionscanada.gc.ca-BVAU.-43613 |
---|---|
record_format |
oai_dc |
spelling |
ndltd-LACETR-oai-collectionscanada.gc.ca-BVAU.-436132013-06-05T04:21:05ZA pursuit method for video annotationFoley-Fisher, ZoltanVideo annotation is a process of describing or elaborating on objects or events represented in video. Part of this process involves time consuming manual interactions to define spatio-temporal entities - such as a region of interest within the video. This dissertation proposes a pursuit method for video annotation to quickly define a particular type of spatio-temporal entity known as a point- based path. A pursuit method is particularly suited to annotation contexts when a precise bounding region is not needed, such as when annotators draw attention to objects in consumer video. We demonstrate the validity of the pursuit method with measurements of both accuracy and annotation time when annotators create point-based paths. Annotator tool designers can now chose a pursuit method for suitable annotation contexts.University of British Columbia2012-11-27T18:39:52Z2012-11-27T18:39:52Z20122012-11-272013-05Electronic Thesis or Dissertationhttp://hdl.handle.net/2429/43613eng |
collection |
NDLTD |
language |
English |
sources |
NDLTD |
description |
Video annotation is a process of describing or elaborating on objects or events represented in video. Part of this process involves time consuming manual interactions to define spatio-temporal entities - such as a region of interest within the video.
This dissertation proposes a pursuit method for video annotation to quickly define a particular type of spatio-temporal entity known as a point- based path. A pursuit method is particularly suited to annotation contexts when a precise bounding region is not needed, such as when annotators draw attention to objects in consumer video.
We demonstrate the validity of the pursuit method with measurements of both accuracy and annotation time when annotators create point-based paths. Annotator tool designers can now chose a pursuit method for suitable annotation contexts. |
author |
Foley-Fisher, Zoltan |
spellingShingle |
Foley-Fisher, Zoltan A pursuit method for video annotation |
author_facet |
Foley-Fisher, Zoltan |
author_sort |
Foley-Fisher, Zoltan |
title |
A pursuit method for video annotation |
title_short |
A pursuit method for video annotation |
title_full |
A pursuit method for video annotation |
title_fullStr |
A pursuit method for video annotation |
title_full_unstemmed |
A pursuit method for video annotation |
title_sort |
pursuit method for video annotation |
publisher |
University of British Columbia |
publishDate |
2012 |
url |
http://hdl.handle.net/2429/43613 |
work_keys_str_mv |
AT foleyfisherzoltan apursuitmethodforvideoannotation AT foleyfisherzoltan pursuitmethodforvideoannotation |
_version_ |
1716588433273520128 |