Abstract
| Original language | English |
|---|---|
| Title of host publication | Proceedings of the2015 IEEE International Conference on Image Processing (ICIP 2015), 27-30 September 2015, Quebec City, Canada |
| Place of Publication | Piscataway |
| Publisher | Institute of Electrical and Electronics Engineers |
| Pages | 3180-3184 |
| ISBN (Print) | 978-1-4799-8339-1 |
| DOIs | |
| Publication status | Published - 2015 |
| Event | 22nd IEEE International Conference on Image Processing (ICIP 2015) - Quebec, Canada Duration: 27 Sep 2015 → 30 Sep 2015 Conference number: 22 http://www.icip2015.org/ |
Conference
| Conference | 22nd IEEE International Conference on Image Processing (ICIP 2015) |
|---|---|
| Abbreviated title | ICIP 2015 |
| Country | Canada |
| City | Quebec |
| Period | 27/09/15 → 30/09/15 |
| Internet address |
Fingerprint
Cite this
}
Real-time semantic context labeling for image understanding. / Pieck, M.A.R.; Sommen, van der, F.; Zinger, S.; With, de, P.H.N.
Proceedings of the2015 IEEE International Conference on Image Processing (ICIP 2015), 27-30 September 2015, Quebec City, Canada. Piscataway : Institute of Electrical and Electronics Engineers, 2015. p. 3180-3184.Research output: Chapter in Book/Report/Conference proceeding › Conference contribution › Academic › peer-review
TY - GEN
T1 - Real-time semantic context labeling for image understanding
AU - Pieck, M.A.R.
AU - Sommen, van der, F.
AU - Zinger, S.
AU - With, de, P.H.N.
PY - 2015
Y1 - 2015
N2 - The use of context information in a scene is an important aid for full semantic scene understanding in security and surveillance applications. To this end, this paper presents an innovative semantic context-labeling algorithm for three context classes, trading-off quality and real-time execution. Our system consists of three consecutive stages: image segmentation, region-based feature extraction and classification. We propose the joint use of the features color in HSV space, texture from Gabor filters and spatial context, in combination with the Directional Nearest Neighbor (DNN) method for constructing the undirected graph for segmentation. Compared to recent literature, this combination is over 35 times faster and achieves a coverability rate that is 65% higher.
AB - The use of context information in a scene is an important aid for full semantic scene understanding in security and surveillance applications. To this end, this paper presents an innovative semantic context-labeling algorithm for three context classes, trading-off quality and real-time execution. Our system consists of three consecutive stages: image segmentation, region-based feature extraction and classification. We propose the joint use of the features color in HSV space, texture from Gabor filters and spatial context, in combination with the Directional Nearest Neighbor (DNN) method for constructing the undirected graph for segmentation. Compared to recent literature, this combination is over 35 times faster and achieves a coverability rate that is 65% higher.
U2 - 10.1109/ICIP.2015.7351390
DO - 10.1109/ICIP.2015.7351390
M3 - Conference contribution
SN - 978-1-4799-8339-1
SP - 3180
EP - 3184
BT - Proceedings of the2015 IEEE International Conference on Image Processing (ICIP 2015), 27-30 September 2015, Quebec City, Canada
PB - Institute of Electrical and Electronics Engineers
CY - Piscataway
ER -