Publication Details
Feature extraction for efficient image and video segmentation
Beran Vítězslav, doc. Ing., Ph.D. (DCGM FIT BUT)
Color/Texture segmentation, Motion segmentation, RGB-D/T segmentation
The segmentation of sensory data of various domains is often crucial pre-processing step in many computer vision methods and applications. In this work, we propose a method that leverages the quantization of local features distributions for the depth and the temporal information. Three variants of the segmentation method is designed and evaluated reflecting various data domains: space (color and texture), temporal (motion) and depth domain. Each variant was tested on appropriate dataset showing the usability of designed method for applications like areal-image analysis, hand detection and moving-people detection. The pilot experiments shows the characteristics of the approach and computational costs of designed variants.
@INPROCEEDINGS{FITPUB11086,
author = "Jakub Vojvoda and V\'{i}t\v{e}zslav Beran",
title = "Feature extraction for efficient image and video segmentation",
pages = "75--80",
booktitle = "Proceedings - SCCG 2016: 32nd Spring Conference on Computer Graphics",
year = 2016,
location = "Smolenice, SK",
publisher = "Association for Computing Machinery",
ISBN = "978-1-4503-4436-4",
doi = "10.1145/2948628.2948631",
language = "english",
url = "https://www.fit.vut.cz/research/publication/11086"
}