Abstract
In this work we propose a dynamic scene model to provide information about the presence of salient motion in the scene, and that could be used for focusing the attention of a pan/tilt/zoom camera, or for background modeling purposes. Rather than proposing a set of saliency detectors, we define what we mean by salient motion, and propose a precise model for it. Detecting salient motion becomes equivalent to detecting a model change. We derive optimal online procedures to solve this problem, which enable a very fast implementation. Promising results show that our model can effectively detect salient motion even in severely cluttered scenes, and while a camera is panning and tilting.
| Original language | English |
|---|---|
| Title of host publication | 6th IEEE International Conference on Advanced Video and Signal Based Surveillance, AVSS 2009 |
| Pages | 490-495 |
| Number of pages | 6 |
| DOIs | |
| Publication status | Published - 2009 Dec 25 |
| Event | 6th IEEE International Conference on Advanced Video and Signal Based Surveillance, AVSS 2009 - Genova, Italy Duration: 2009 Sep 2 → 2009 Sep 4 |
Other
| Other | 6th IEEE International Conference on Advanced Video and Signal Based Surveillance, AVSS 2009 |
|---|---|
| Country | Italy |
| City | Genova |
| Period | 09/9/2 → 09/9/4 |
Fingerprint
All Science Journal Classification (ASJC) codes
- Artificial Intelligence
- Computer Vision and Pattern Recognition
- Signal Processing
- Electrical and Electronic Engineering
Cite this
}
A model change detection approach to dynamic scene modeling. / Kim, Seon Joo; Doretto, Gianfranco; Rittscher, Jens; Tu, Peter; Krahnstoever, Nils; Pollefeys, Marc.
6th IEEE International Conference on Advanced Video and Signal Based Surveillance, AVSS 2009. 2009. p. 490-495 5279913.Research output: Chapter in Book/Report/Conference proceeding › Conference contribution
TY - GEN
T1 - A model change detection approach to dynamic scene modeling
AU - Kim, Seon Joo
AU - Doretto, Gianfranco
AU - Rittscher, Jens
AU - Tu, Peter
AU - Krahnstoever, Nils
AU - Pollefeys, Marc
PY - 2009/12/25
Y1 - 2009/12/25
N2 - In this work we propose a dynamic scene model to provide information about the presence of salient motion in the scene, and that could be used for focusing the attention of a pan/tilt/zoom camera, or for background modeling purposes. Rather than proposing a set of saliency detectors, we define what we mean by salient motion, and propose a precise model for it. Detecting salient motion becomes equivalent to detecting a model change. We derive optimal online procedures to solve this problem, which enable a very fast implementation. Promising results show that our model can effectively detect salient motion even in severely cluttered scenes, and while a camera is panning and tilting.
AB - In this work we propose a dynamic scene model to provide information about the presence of salient motion in the scene, and that could be used for focusing the attention of a pan/tilt/zoom camera, or for background modeling purposes. Rather than proposing a set of saliency detectors, we define what we mean by salient motion, and propose a precise model for it. Detecting salient motion becomes equivalent to detecting a model change. We derive optimal online procedures to solve this problem, which enable a very fast implementation. Promising results show that our model can effectively detect salient motion even in severely cluttered scenes, and while a camera is panning and tilting.
UR - http://www.scopus.com/inward/record.url?scp=72349084897&partnerID=8YFLogxK
UR - http://www.scopus.com/inward/citedby.url?scp=72349084897&partnerID=8YFLogxK
U2 - 10.1109/AVSS.2009.30
DO - 10.1109/AVSS.2009.30
M3 - Conference contribution
SN - 9780769537184
SP - 490
EP - 495
BT - 6th IEEE International Conference on Advanced Video and Signal Based Surveillance, AVSS 2009
ER -