Abstract
Current development of security sensor networks and their processing algorithms use pre-recorded or abstract data streams for testing, often missing important ground truth for validation. This paper proposes a simulation-based test bed, presenting an approach to use commercial off the shelf virtual reality environments to create adaptive simulations of sensors, data streams and scenarios for training and testing perceptive algorithms. An example using airborne visual multi object tracking is discussed and validated.
| Original language | English |
|---|---|
| Title of host publication | Communications in Computer and Information Science |
| Pages | 212-215 |
| Number of pages | 4 |
| Volume | 318 CCIS |
| DOIs | |
| Publication status | Published - 2012 |
| Event | 7th Future Security Research Conference 2012 - Bonn, Germany Duration: Sep 4 2012 → Sep 6 2012 |
Publication series
| Name | Communications in Computer and Information Science |
|---|---|
| Volume | 318 CCIS |
| ISSN (Print) | 18650929 |
Other
| Other | 7th Future Security Research Conference 2012 |
|---|---|
| Country | Germany |
| City | Bonn |
| Period | 9/4/12 → 9/6/12 |
Fingerprint
Keywords
- computer vision
- security networks
- simulation
- virtual reality
ASJC Scopus subject areas
- Computer Science(all)
Cite this
Data simulation and testing of visual algorithms in synthetic environments for security sensor networks. / Hummel, Georg; Kovács, Levente; Stütz, Peter; Szirányi, T.
Communications in Computer and Information Science. Vol. 318 CCIS 2012. p. 212-215 (Communications in Computer and Information Science; Vol. 318 CCIS).Research output: Chapter in Book/Report/Conference proceeding › Conference contribution
}
TY - GEN
T1 - Data simulation and testing of visual algorithms in synthetic environments for security sensor networks
AU - Hummel, Georg
AU - Kovács, Levente
AU - Stütz, Peter
AU - Szirányi, T.
PY - 2012
Y1 - 2012
N2 - Current development of security sensor networks and their processing algorithms use pre-recorded or abstract data streams for testing, often missing important ground truth for validation. This paper proposes a simulation-based test bed, presenting an approach to use commercial off the shelf virtual reality environments to create adaptive simulations of sensors, data streams and scenarios for training and testing perceptive algorithms. An example using airborne visual multi object tracking is discussed and validated.
AB - Current development of security sensor networks and their processing algorithms use pre-recorded or abstract data streams for testing, often missing important ground truth for validation. This paper proposes a simulation-based test bed, presenting an approach to use commercial off the shelf virtual reality environments to create adaptive simulations of sensors, data streams and scenarios for training and testing perceptive algorithms. An example using airborne visual multi object tracking is discussed and validated.
KW - computer vision
KW - security networks
KW - simulation
KW - virtual reality
UR - http://www.scopus.com/inward/record.url?scp=84867677715&partnerID=8YFLogxK
UR - http://www.scopus.com/inward/citedby.url?scp=84867677715&partnerID=8YFLogxK
U2 - 10.1007/978-3-642-33161-9_31
DO - 10.1007/978-3-642-33161-9_31
M3 - Conference contribution
AN - SCOPUS:84867677715
SN - 9783642331602
VL - 318 CCIS
T3 - Communications in Computer and Information Science
SP - 212
EP - 215
BT - Communications in Computer and Information Science
ER -