Details
| Original language | English |
|---|---|
| Article number | 1460015 |
| Journal | International Journal of Pattern Recognition and Artificial Intelligence |
| Volume | 28 |
| Issue number | 7 |
| Publication status | Published - 2014 |
Abstract
Video Segmentation is a fundamental task in computer vision. In many sequences, appearance does not provide enough information to solve the problem. Time-of-Flight cameras provide additional information, namely depth, that can be integrated as an additional feature in a segmentation approach. Typically, the depth information is less sensitive to environment changes. Combined with appearance, this has the potential to be a more robust segmentation method. Motivated by the fact that a simple combination of two information sources might not be the best solution, a novel scheme based on Dempster's theory of evidence is proposed. In contrast to existing methods, the use of Dempster's theory of evidence allows to model inaccuracy and uncertainty. The inaccuracy of the information is influenced by an adaptive weight, that provides a measurement of how reliable a certain information might be. The proposed method is compared with others on a publicly available set of image sequences. The experiments show that the use of the proposed feature fusion improves the segmentation.
Keywords
- Dempster's theory of evidence, Feature fusion, RGB-D images, Video Segmentation
ASJC Scopus subject areas
- Computer Science(all)
- Software
- Computer Science(all)
- Computer Vision and Pattern Recognition
- Computer Science(all)
- Artificial Intelligence
Cite this
- Standard
- Harvard
- Apa
- Vancouver
- BibTeX
- RIS
In: International Journal of Pattern Recognition and Artificial Intelligence, Vol. 28, No. 7, 1460015, 2014.
Research output: Contribution to journal › Article › Research › peer review
}
TY - JOUR
T1 - Multi-sensor fusion for video segmentation
AU - Scheuermann, Björn
AU - Rosenhahn, Bodo
PY - 2014
Y1 - 2014
N2 - Video Segmentation is a fundamental task in computer vision. In many sequences, appearance does not provide enough information to solve the problem. Time-of-Flight cameras provide additional information, namely depth, that can be integrated as an additional feature in a segmentation approach. Typically, the depth information is less sensitive to environment changes. Combined with appearance, this has the potential to be a more robust segmentation method. Motivated by the fact that a simple combination of two information sources might not be the best solution, a novel scheme based on Dempster's theory of evidence is proposed. In contrast to existing methods, the use of Dempster's theory of evidence allows to model inaccuracy and uncertainty. The inaccuracy of the information is influenced by an adaptive weight, that provides a measurement of how reliable a certain information might be. The proposed method is compared with others on a publicly available set of image sequences. The experiments show that the use of the proposed feature fusion improves the segmentation.
AB - Video Segmentation is a fundamental task in computer vision. In many sequences, appearance does not provide enough information to solve the problem. Time-of-Flight cameras provide additional information, namely depth, that can be integrated as an additional feature in a segmentation approach. Typically, the depth information is less sensitive to environment changes. Combined with appearance, this has the potential to be a more robust segmentation method. Motivated by the fact that a simple combination of two information sources might not be the best solution, a novel scheme based on Dempster's theory of evidence is proposed. In contrast to existing methods, the use of Dempster's theory of evidence allows to model inaccuracy and uncertainty. The inaccuracy of the information is influenced by an adaptive weight, that provides a measurement of how reliable a certain information might be. The proposed method is compared with others on a publicly available set of image sequences. The experiments show that the use of the proposed feature fusion improves the segmentation.
KW - Dempster's theory of evidence
KW - Feature fusion
KW - RGB-D images
KW - Video Segmentation
UR - http://www.scopus.com/inward/record.url?scp=84929289022&partnerID=8YFLogxK
U2 - 10.1142/s0218001414600155
DO - 10.1142/s0218001414600155
M3 - Article
AN - SCOPUS:84929289022
VL - 28
JO - International Journal of Pattern Recognition and Artificial Intelligence
JF - International Journal of Pattern Recognition and Artificial Intelligence
SN - 0218-0014
IS - 7
M1 - 1460015
ER -