Improving video segmentation algorithms by detection of and adaption to altered illumination
(2008) In Preprints in Mathematical Sciences 2008:9.- Abstract
- Changing illumination constitutes a serious challenge for video segmentation
algorithms, especially in outdoor scenes under cloudy conditions.
Rapid illumination changes, e.g. caused by varying cloud cover,
often cause existing segmentation algorithms to erroneously classify
large parts of the image as foreground.
Here a method that extends existing segmentation algorithms by
detecting illumination changes using a CUSUM detector and adjusting
the background model to conform with the new illumination is
presented. The method is shown to work for two segmentation algorithms,
and it is indicated how the method could be extended to other
algorithms.
Please use this url to cite or link to this publication:
https://lup.lub.lu.se/record/4730167
- author
- Lindström, Johan LU ; Lindgren, Finn LU ; Holst, Ulla LU and Åström, Karl LU
- organization
- publishing date
- 2008
- type
- Contribution to journal
- publication status
- unpublished
- subject
- in
- Preprints in Mathematical Sciences
- volume
- 2008:9
- pages
- 20 pages
- publisher
- Lund University
- external identifiers
-
- other:LUTFMS-5075-2008
- ISSN
- 1403-9338
- project
- Spatio-Temporal Estimation for Mixture Models and Gaussian Markov Random Fields - Applications to Video Analysis and Environmental Modelling
- language
- English
- LU publication?
- yes
- id
- a92d82ee-28cb-4371-a1ab-f0c4d1ed587c (old id 4730167)
- date added to LUP
- 2016-04-01 14:50:51
- date last changed
- 2018-11-21 20:30:44
@article{a92d82ee-28cb-4371-a1ab-f0c4d1ed587c, abstract = {{Changing illumination constitutes a serious challenge for video segmentation<br/><br> algorithms, especially in outdoor scenes under cloudy conditions.<br/><br> Rapid illumination changes, e.g. caused by varying cloud cover,<br/><br> often cause existing segmentation algorithms to erroneously classify<br/><br> large parts of the image as foreground.<br/><br> Here a method that extends existing segmentation algorithms by<br/><br> detecting illumination changes using a CUSUM detector and adjusting<br/><br> the background model to conform with the new illumination is<br/><br> presented. The method is shown to work for two segmentation algorithms,<br/><br> and it is indicated how the method could be extended to other<br/><br> algorithms.}}, author = {{Lindström, Johan and Lindgren, Finn and Holst, Ulla and Åström, Karl}}, issn = {{1403-9338}}, language = {{eng}}, publisher = {{Lund University}}, series = {{Preprints in Mathematical Sciences}}, title = {{Improving video segmentation algorithms by detection of and adaption to altered illumination}}, url = {{https://lup.lub.lu.se/search/files/4197794/4730169.pdf}}, volume = {{2008:9}}, year = {{2008}}, }