Details
| Originalsprache | Englisch |
|---|---|
| Titel des Sammelwerks | Proceedings |
| Untertitel | 2014 IEEE Conference on Computer Vision and Pattern Recognition Workshops, CVPRW 2014 |
| Herausgeber (Verlag) | IEEE Computer Society |
| Seiten | 770-777 |
| Seitenumfang | 8 |
| ISBN (elektronisch) | 9781479943098, 9781479943098 |
| Publikationsstatus | Veröffentlicht - 24 Sept. 2014 |
| Veranstaltung | 2014 IEEE Conference on Computer Vision and Pattern Recognition Workshops, CVPRW 2014 - Columbus, USA / Vereinigte Staaten Dauer: 23 Juni 2014 → 28 Juni 2014 |
Publikationsreihe
| Name | IEEE Computer Society Conference on Computer Vision and Pattern Recognition Workshops |
|---|---|
| ISSN (Print) | 2160-7508 |
| ISSN (elektronisch) | 2160-7516 |
Abstract
In this paper, we analyze the relationship between the corresponding descriptors computed from multimodal images with focus on visual and infrared images. First the descriptors are regressed by means of linear regression as well as Gaussian process. We apply different covariance functions and inference methods for Gaussian process. Then the descriptors detected from visual images are mapped to infrared images through the regression results. Predictions are assessed in two ways: the statistics of absolute error between true values and actual values, and the precision score of matching the predicted descriptors to the original infrared descriptors. Experimental results show that regression methods achieve a well-assessed relationship between corresponding descriptors from multiple modalities.
ASJC Scopus Sachgebiete
- Informatik (insg.)
- Maschinelles Sehen und Mustererkennung
- Ingenieurwesen (insg.)
- Elektrotechnik und Elektronik
Zitieren
- Standard
- Harvard
- Apa
- Vancouver
- BibTex
- RIS
Proceedings: 2014 IEEE Conference on Computer Vision and Pattern Recognition Workshops, CVPRW 2014. IEEE Computer Society, 2014. S. 770-777 6910069 (IEEE Computer Society Conference on Computer Vision and Pattern Recognition Workshops).
Publikation: Beitrag in Buch/Bericht/Sammelwerk/Konferenzband › Aufsatz in Konferenzband › Forschung › Peer-Review
}
TY - GEN
T1 - Feature regression for multimodal image analysis
AU - Yang, Michael Ying
AU - Yong, Xuanzi
AU - Rosenhahn, Bodo
PY - 2014/9/24
Y1 - 2014/9/24
N2 - In this paper, we analyze the relationship between the corresponding descriptors computed from multimodal images with focus on visual and infrared images. First the descriptors are regressed by means of linear regression as well as Gaussian process. We apply different covariance functions and inference methods for Gaussian process. Then the descriptors detected from visual images are mapped to infrared images through the regression results. Predictions are assessed in two ways: the statistics of absolute error between true values and actual values, and the precision score of matching the predicted descriptors to the original infrared descriptors. Experimental results show that regression methods achieve a well-assessed relationship between corresponding descriptors from multiple modalities.
AB - In this paper, we analyze the relationship between the corresponding descriptors computed from multimodal images with focus on visual and infrared images. First the descriptors are regressed by means of linear regression as well as Gaussian process. We apply different covariance functions and inference methods for Gaussian process. Then the descriptors detected from visual images are mapped to infrared images through the regression results. Predictions are assessed in two ways: the statistics of absolute error between true values and actual values, and the precision score of matching the predicted descriptors to the original infrared descriptors. Experimental results show that regression methods achieve a well-assessed relationship between corresponding descriptors from multiple modalities.
UR - http://www.scopus.com/inward/record.url?scp=84908548323&partnerID=8YFLogxK
U2 - 10.1109/cvprw.2014.118
DO - 10.1109/cvprw.2014.118
M3 - Conference contribution
AN - SCOPUS:84908548323
T3 - IEEE Computer Society Conference on Computer Vision and Pattern Recognition Workshops
SP - 770
EP - 777
BT - Proceedings
PB - IEEE Computer Society
T2 - 2014 IEEE Conference on Computer Vision and Pattern Recognition Workshops, CVPRW 2014
Y2 - 23 June 2014 through 28 June 2014
ER -