MotiCon: Learning an image-based motion context for multi-target tracking


Benchmark:

Short name:

MotiCon

Detector:

Public

Description:

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.

Project page / code:

Reference:

L. Leal-Taixé, M. Fenzi, A. Kuznetsova, B. Rosenhahn, S. Savarese. Learning an image-based motion context for multiple people tracking. In CVPR, 2014.

Processing:

Batch

Last submitted:

April 07, 2015 (4 years ago)

Published:

April 07, 2015 at 21:02:03 CET

Submissions:

1

Open source:

Yes

Hardware:

2.6 GHz, 1 core

Benchmark performance:

Sequence MOTA IDF1 MOTP MT ML FP FN ID Sw.
2D MOT 201523.129.470.934.0375.010,40435,8441,018

Detailed performance:

Sequence MOTA IDF1 MOTP MT ML FP FN ID Sw.
ADL-Rundle-11.030.470.36.04.04,4494,628136
ADL-Rundle-318.122.971.82.09.02,7555,355217
AVG-TownCentre11.923.070.32.0158.03535,87274
ETH-Crossing22.829.172.91.017.0137538
ETH-Jelmoli43.552.472.99.013.02951,10237
ETH-Linthescher18.324.077.73.0146.0987,12472
KITTI-1638.839.570.10.02.014286336
KITTI-1933.841.769.94.013.08872,552100
PETS09-S2L246.627.267.64.06.05604,354238
TUD-Crossing58.246.670.83.02.03240326
Venice-118.226.172.90.05.08202,83874

Raw data:


MotiCon