Background subtraction using ensembles of classifiers with an extended feature set
The limitations of foreground segmentation in difficult environments using standard color space features often result in poor performance during autonomous tracking. This work presents a new approach for classification of foreground and background pixels in image sequences by employing an ensemble o...
Main Author: | |
---|---|
Format: | Others |
Published: |
Scholar Commons
2008
|
Subjects: | |
Online Access: | https://scholarcommons.usf.edu/etd/338 https://scholarcommons.usf.edu/cgi/viewcontent.cgi?article=1337&context=etd |