Details
| Original language | English |
|---|---|
| Pages (from-to) | 83-92 |
| Number of pages | 10 |
| Journal | Photogrammetrie, Fernerkundung, Geoinformation |
| Volume | 2013 |
| Issue number | 2 |
| Publication status | Published - 1 May 2013 |
Abstract
This article describes the application of stereoscopic analysis to typical image pairs from a surveillance camera network. An approach is presented that establishes correspondences between people detections across adjacent views and derives an estimation of body height for each person in the overlapping parts of the camera views. Dense image matching is applied to short stereoscopic sequences and the results are incorporated in a subsequent monocular tracking to improve the positioning accuracy. The method does not depend on a dedicated stereo setup of the camera network but is applicable to suitable image pairs in addition to monocular people detection and tracking. Based on realistic image sequences, the performance of the proposed approach is evaluated and compared to a current method for appearance-based data association.
Keywords
- Camera network, People tracking, Stereo vision, Video surveillance
ASJC Scopus subject areas
- Social Sciences(all)
- Geography, Planning and Development
- Physics and Astronomy(all)
- Instrumentation
- Earth and Planetary Sciences(all)
- Earth and Planetary Sciences (miscellaneous)
Cite this
- Standard
- Harvard
- Apa
- Vancouver
- BibTeX
- RIS
In: Photogrammetrie, Fernerkundung, Geoinformation, Vol. 2013, No. 2, 01.05.2013, p. 83-92.
Research output: Contribution to journal › Article › Research › peer review
}
TY - JOUR
T1 - A Stereoscopic Approach for the Association of People Tracks in Video Surveillance Systems
AU - Menze, Moritz
AU - Klinger, Tobias
AU - Muhle, Daniel
AU - Metzler, Jürgen
AU - Heipke, Christian
PY - 2013/5/1
Y1 - 2013/5/1
N2 - This article describes the application of stereoscopic analysis to typical image pairs from a surveillance camera network. An approach is presented that establishes correspondences between people detections across adjacent views and derives an estimation of body height for each person in the overlapping parts of the camera views. Dense image matching is applied to short stereoscopic sequences and the results are incorporated in a subsequent monocular tracking to improve the positioning accuracy. The method does not depend on a dedicated stereo setup of the camera network but is applicable to suitable image pairs in addition to monocular people detection and tracking. Based on realistic image sequences, the performance of the proposed approach is evaluated and compared to a current method for appearance-based data association.
AB - This article describes the application of stereoscopic analysis to typical image pairs from a surveillance camera network. An approach is presented that establishes correspondences between people detections across adjacent views and derives an estimation of body height for each person in the overlapping parts of the camera views. Dense image matching is applied to short stereoscopic sequences and the results are incorporated in a subsequent monocular tracking to improve the positioning accuracy. The method does not depend on a dedicated stereo setup of the camera network but is applicable to suitable image pairs in addition to monocular people detection and tracking. Based on realistic image sequences, the performance of the proposed approach is evaluated and compared to a current method for appearance-based data association.
KW - Camera network
KW - People tracking
KW - Stereo vision
KW - Video surveillance
UR - http://www.scopus.com/inward/record.url?scp=84877305029&partnerID=8YFLogxK
U2 - 10.1127/1432-8364/2013/0160
DO - 10.1127/1432-8364/2013/0160
M3 - Article
AN - SCOPUS:84877305029
VL - 2013
SP - 83
EP - 92
JO - Photogrammetrie, Fernerkundung, Geoinformation
JF - Photogrammetrie, Fernerkundung, Geoinformation
SN - 1432-8364
IS - 2
ER -