Details
| Original language | English |
|---|---|
| Title of host publication | Proceedings of the IEEE Computer Society Conference on Computer Vision and Pattern Recognition |
| Publisher | IEEE Computer Society |
| Pages | 3542-3549 |
| Number of pages | 8 |
| ISBN (electronic) | 9781479951178, 9781479951178 |
| Publication status | Published - 24 Sept 2014 |
| Event | 27th IEEE Conference on Computer Vision and Pattern Recognition, CVPR 2014 - Columbus, United States Duration: 23 Jun 2014 → 28 Jun 2014 |
Publication series
| Name | Proceedings of the IEEE Computer Society Conference on Computer Vision and Pattern Recognition |
|---|---|
| ISSN (Print) | 1063-6919 |
Abstract
We present a novel method for multiple people tracking that leverages a generalized model for capturing interactions among individuals. At the core of our model lies a learned dictionary of interaction feature strings which capture relationships between the motions of targets. These feature strings, created from low-level image features, lead to a much richer representation of the physical interactions between targets compared to hand-specified social force models that previous works have introduced for tracking. One disadvantage of using social forces is that all pedestrians must be detected in order for the forces to be applied, while our method is able to encode the effect of undetected targets, making the tracker more robust to partial occlusions. The interaction feature strings are used in a Random Forest framework to track targets according to the features surrounding them. Results on six publicly available sequences show that our method outperforms state-of-the-art approaches in multiple people tracking.
Keywords
- image-based motion context, linear programming, multiple people tracking, social force model
ASJC Scopus subject areas
- Computer Science(all)
- Software
- Computer Science(all)
- Computer Vision and Pattern Recognition
Cite this
- Standard
- Harvard
- Apa
- Vancouver
- BibTeX
- RIS
Proceedings of the IEEE Computer Society Conference on Computer Vision and Pattern Recognition. IEEE Computer Society, 2014. p. 3542-3549 6909848 (Proceedings of the IEEE Computer Society Conference on Computer Vision and Pattern Recognition).
Research output: Chapter in book/report/conference proceeding › Conference contribution › Research › peer review
}
TY - GEN
T1 - Learning an image-based motion context for multiple people tracking
AU - Leal-Taixé, Laura
AU - Fenzi, Michele
AU - Kuznetsova, Alina
AU - Rosenhahn, Bodo
AU - Savarese, Silvio
PY - 2014/9/24
Y1 - 2014/9/24
N2 - We present a novel method for multiple people tracking that leverages a generalized model for capturing interactions among individuals. At the core of our model lies a learned dictionary of interaction feature strings which capture relationships between the motions of targets. These feature strings, created from low-level image features, lead to a much richer representation of the physical interactions between targets compared to hand-specified social force models that previous works have introduced for tracking. One disadvantage of using social forces is that all pedestrians must be detected in order for the forces to be applied, while our method is able to encode the effect of undetected targets, making the tracker more robust to partial occlusions. The interaction feature strings are used in a Random Forest framework to track targets according to the features surrounding them. Results on six publicly available sequences show that our method outperforms state-of-the-art approaches in multiple people tracking.
AB - We present a novel method for multiple people tracking that leverages a generalized model for capturing interactions among individuals. At the core of our model lies a learned dictionary of interaction feature strings which capture relationships between the motions of targets. These feature strings, created from low-level image features, lead to a much richer representation of the physical interactions between targets compared to hand-specified social force models that previous works have introduced for tracking. One disadvantage of using social forces is that all pedestrians must be detected in order for the forces to be applied, while our method is able to encode the effect of undetected targets, making the tracker more robust to partial occlusions. The interaction feature strings are used in a Random Forest framework to track targets according to the features surrounding them. Results on six publicly available sequences show that our method outperforms state-of-the-art approaches in multiple people tracking.
KW - image-based motion context
KW - linear programming
KW - multiple people tracking
KW - social force model
UR - http://www.scopus.com/inward/record.url?scp=84911365771&partnerID=8YFLogxK
U2 - 10.1109/CVPR.2014.453
DO - 10.1109/CVPR.2014.453
M3 - Conference contribution
AN - SCOPUS:84911365771
T3 - Proceedings of the IEEE Computer Society Conference on Computer Vision and Pattern Recognition
SP - 3542
EP - 3549
BT - Proceedings of the IEEE Computer Society Conference on Computer Vision and Pattern Recognition
PB - IEEE Computer Society
T2 - 27th IEEE Conference on Computer Vision and Pattern Recognition, CVPR 2014
Y2 - 23 June 2014 through 28 June 2014
ER -