Details
| Original language | English |
|---|---|
| Title of host publication | Proceedings of 2nd International Conference on Computer Science and Network Technology |
| Subtitle of host publication | ICCSNT 2012 |
| Pages | 284-287 |
| Number of pages | 4 |
| Publication status | Published - 2012 |
| Event | 2nd International Conference on Computer Science and Network Technology, ICCSNT 2012 - Changchun, China Duration: 29 Dec 2012 → 31 Dec 2012 |
Publication series
| Name | Proceedings of 2nd International Conference on Computer Science and Network Technology, ICCSNT 2012 |
|---|
Abstract
In this paper, we study object categories detection with a variety of geometric contexts. Usually, object categories are always associated with certain context information. It can help to remove false positive detection. With geometric contextual features, a support vector machine is trained to re-evaluate the initial detection results. Moreover, for the case of that there are determined object categories in an image and the region where an object exists is known, we convert the problem of object categories detection into the one of classification of several object categories. The region can be classified as the one with maximal initial detection score. Alternatively, the detection score for every object category model can be the re-evaluated result of a SVM trained with initial detection score and related geometric context feature. The proposed methods are verified on the dataset of PASCAL VOC 2010. The experimental results demonstrate that accuracy of detection can be improved further with the help of geometric context.
Keywords
- detection, geometric context, object cateories
ASJC Scopus subject areas
- Computer Science(all)
- Computer Networks and Communications
Cite this
- Standard
- Harvard
- Apa
- Vancouver
- BibTeX
- RIS
Proceedings of 2nd International Conference on Computer Science and Network Technology: ICCSNT 2012. 2012. p. 284-287 6525939 (Proceedings of 2nd International Conference on Computer Science and Network Technology, ICCSNT 2012).
Research output: Chapter in book/report/conference proceeding › Conference contribution › Research › peer review
}
TY - GEN
T1 - Object Categories Detection with Incorporated Geometric Context
AU - Chen, Mianshu
AU - Ostermann, Joern
AU - Dragon, Ralf
PY - 2012
Y1 - 2012
N2 - In this paper, we study object categories detection with a variety of geometric contexts. Usually, object categories are always associated with certain context information. It can help to remove false positive detection. With geometric contextual features, a support vector machine is trained to re-evaluate the initial detection results. Moreover, for the case of that there are determined object categories in an image and the region where an object exists is known, we convert the problem of object categories detection into the one of classification of several object categories. The region can be classified as the one with maximal initial detection score. Alternatively, the detection score for every object category model can be the re-evaluated result of a SVM trained with initial detection score and related geometric context feature. The proposed methods are verified on the dataset of PASCAL VOC 2010. The experimental results demonstrate that accuracy of detection can be improved further with the help of geometric context.
AB - In this paper, we study object categories detection with a variety of geometric contexts. Usually, object categories are always associated with certain context information. It can help to remove false positive detection. With geometric contextual features, a support vector machine is trained to re-evaluate the initial detection results. Moreover, for the case of that there are determined object categories in an image and the region where an object exists is known, we convert the problem of object categories detection into the one of classification of several object categories. The region can be classified as the one with maximal initial detection score. Alternatively, the detection score for every object category model can be the re-evaluated result of a SVM trained with initial detection score and related geometric context feature. The proposed methods are verified on the dataset of PASCAL VOC 2010. The experimental results demonstrate that accuracy of detection can be improved further with the help of geometric context.
KW - detection
KW - geometric context
KW - object cateories
UR - http://www.scopus.com/inward/record.url?scp=84880224125&partnerID=8YFLogxK
U2 - 10.1109/ICCSNT.2012.6525939
DO - 10.1109/ICCSNT.2012.6525939
M3 - Conference contribution
AN - SCOPUS:84880224125
SN - 9781467329644
T3 - Proceedings of 2nd International Conference on Computer Science and Network Technology, ICCSNT 2012
SP - 284
EP - 287
BT - Proceedings of 2nd International Conference on Computer Science and Network Technology
T2 - 2nd International Conference on Computer Science and Network Technology, ICCSNT 2012
Y2 - 29 December 2012 through 31 December 2012
ER -