Counting crowded moving objects
Research output: Contribution to journal › Conference article › Research › peer-review
Standard
Counting crowded moving objects. / Rabaud, Vincent; Belongie, Serge.
In: Proceedings of the IEEE Computer Society Conference on Computer Vision and Pattern Recognition, 2006, p. 705-711.Research output: Contribution to journal › Conference article › Research › peer-review
Harvard
APA
Vancouver
Author
Bibtex
}
RIS
TY - GEN
T1 - Counting crowded moving objects
AU - Rabaud, Vincent
AU - Belongie, Serge
PY - 2006
Y1 - 2006
N2 - In its full generality, motion analysis of crowded objects necessitates recognition and segmentation of each moving entity. The difficulty of these tasks increases considerably with occlusions and therefore with crowding. When the objects are constrained to be of the same kind, however, partitioning of densely crowded semi-rigid objects can be accomplished by means of clustering tracked feature points. We base our approach on a highly parallelized version of the KLT tracker in order to process the video into a set of feature trajectories. While such a set of trajectories provides a substrate for motion analysis, their unequal lengths and fragmented nature present difficulties for subsequent processing. To address this, we propose a simple means of spatially and temporally conditioning the trajectories. Given this representation, we integrate it with a learned object descriptor to achieve a segmentation of the constituent motions. We present experimental results for the problem of estimating the number of moving objects in a dense crowd as a function of time.
AB - In its full generality, motion analysis of crowded objects necessitates recognition and segmentation of each moving entity. The difficulty of these tasks increases considerably with occlusions and therefore with crowding. When the objects are constrained to be of the same kind, however, partitioning of densely crowded semi-rigid objects can be accomplished by means of clustering tracked feature points. We base our approach on a highly parallelized version of the KLT tracker in order to process the video into a set of feature trajectories. While such a set of trajectories provides a substrate for motion analysis, their unequal lengths and fragmented nature present difficulties for subsequent processing. To address this, we propose a simple means of spatially and temporally conditioning the trajectories. Given this representation, we integrate it with a learned object descriptor to achieve a segmentation of the constituent motions. We present experimental results for the problem of estimating the number of moving objects in a dense crowd as a function of time.
UR - http://www.scopus.com/inward/record.url?scp=33845571601&partnerID=8YFLogxK
U2 - 10.1109/CVPR.2006.92
DO - 10.1109/CVPR.2006.92
M3 - Conference article
AN - SCOPUS:33845571601
SP - 705
EP - 711
JO - I E E E Conference on Computer Vision and Pattern Recognition. Proceedings
JF - I E E E Conference on Computer Vision and Pattern Recognition. Proceedings
SN - 1063-6919
T2 - 2006 IEEE Computer Society Conference on Computer Vision and Pattern Recognition, CVPR 2006
Y2 - 17 June 2006 through 22 June 2006
ER -
ID: 302053753