CEM: Continuous Energy Minimization for Multi-target Tracking


Benchmark:

Short name:

CEM

Detector:

Public

Description:

Contrary to recent approaches, we focus on designing a continuous energy that corresponds
to a more complete representation of the problem, rather than one that
is amenable to global optimization. Besides the image evidence, the
energy function takes into account physical constraints, such as target
dynamics, mutual exclusion, and track persistence. In addition, partial
image evidence is handled with explicit occlusion reasoning, and
different targets are disambiguated with an appearance model. To
nevertheless find strong local minima of the proposed non-convex energy
we construct a suitable optimization scheme that alternates between
continuous conjugate gradient descent and discrete trans-dimensional
jump moves. These moves, which are executed such that they always reduce
the energy, allow the search to escape weak minima and explore a much
larger portion of the search space of varying dimensionality.

[Parameters]
wtEdet=0.56906
wtEdyn=2.1107
wtEexc=0.86348
wtEper=1.4427
wtEreg=0.5
wtEapp=0
lambda=0.19852

Project page / code:

Reference:

A. Milan, S. Roth, K. Schindler. Continuous Energy Minimization for Multitarget Tracking. In IEEE TPAMI, 2014.

Processing:

Batch

Last submitted:

February 19, 2020 (1 month ago)

Published:

November 01, 2014 at 03:09:33 CET

Submissions:

2

Open source:

Yes

Hardware:

2.6 GHz, 16 Cores

Benchmark performance:

Sequence MOTA IDF1 MOTP MT ML FP FN ID Sw.
2D MOT 201519.30.070.761.0335.014,18034,591813

Detailed performance:

Sequence MOTA IDF1 MOTP MT ML FP FN ID Sw.
ADL-Rundle-19.20.071.47.04.03,9044,46582
ADL-Rundle-315.40.071.76.09.03,2465,28276
AVG-TownCentre-2.60.068.913.0122.02,1704,979186
ETH-Crossing18.20.071.43.015.0797338
ETH-Jelmoli36.20.071.76.013.04801,11028
ETH-Linthescher18.40.073.810.0142.03286,88380
KITTI-1631.60.072.31.03.027885926
KITTI-199.90.065.63.015.01,8532,86792
PETS09-S2L244.90.070.25.06.06574,506150
TUD-Crossing61.60.073.24.02.04834728
Venice-117.70.071.03.04.01,1372,56057

Raw data:


CEM