Details
| Original language | English |
|---|---|
| Publication status | E-pub ahead of print - 25 Jul 2016 |
Abstract
Keywords
- cs.CV
Cite this
- Standard
- Harvard
- Apa
- Vancouver
- BibTeX
- RIS
2016.
Research output: Working paper/Preprint › Preprint
}
TY - UNPB
T1 - Tracking with multi-level features
AU - Henschel, Roberto
AU - Leal-Taixé, Laura
AU - Rosenhahn, Bodo
AU - Schindler, Konrad
N1 - Submitted as an IEEE PAMI short article
PY - 2016/7/25
Y1 - 2016/7/25
N2 - We present a novel formulation of the multiple object tracking problem which integrates low and mid-level features. In particular, we formulate the tracking problem as a quadratic program coupling detections and dense point trajectories. Due to the computational complexity of the initial QP, we propose an approximation by two auxiliary problems, a temporal and spatial association, where the temporal subproblem can be efficiently solved by a linear program and the spatial association by a clustering algorithm. The objective function of the QP is used in order to find the optimal number of clusters, where each cluster ideally represents one person. Evaluation is provided for multiple scenarios, showing the superiority of our method with respect to classic tracking-by-detection methods and also other methods that greedily integrate low-level features.
AB - We present a novel formulation of the multiple object tracking problem which integrates low and mid-level features. In particular, we formulate the tracking problem as a quadratic program coupling detections and dense point trajectories. Due to the computational complexity of the initial QP, we propose an approximation by two auxiliary problems, a temporal and spatial association, where the temporal subproblem can be efficiently solved by a linear program and the spatial association by a clustering algorithm. The objective function of the QP is used in order to find the optimal number of clusters, where each cluster ideally represents one person. Evaluation is provided for multiple scenarios, showing the superiority of our method with respect to classic tracking-by-detection methods and also other methods that greedily integrate low-level features.
KW - cs.CV
M3 - Preprint
BT - Tracking with multi-level features
ER -