CEM_16: Continuous Energy Minimization for Multi-target Tracking


Video not available.

Benchmark:

MOT16 |

Short name:

CEM_16

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.

Project page / code:

n/a

Reference:

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

Processing:

Batch

Last submitted:

March 22, 2016 (4 years ago)

Published:

March 21, 2016 at 00:00:00 CET

Submissions:

1

Open source:

No

Hardware:

3 GHz, 1 CPU

Runtime:

5,919.0 Hz

Benchmark performance:

Sequence MOTA IDF1 MOTP MT ML FP FN Recall Precision FAF ID Sw. Frag
MOT1633.20.075.859 (7.8)413 (54.4)6,837114,32237.390.91.2642 (17.2)731 (19.6)

Detailed performance:

Sequence MOTA IDF1 MOTP MT ML FP FN Recall Precision FAF ID Sw. Frag
MOT16-0128.40.072.34101234,42030.994.10.33631
MOT16-0338.30.075.917593,25161,11041.693.02.2168238
MOT16-0633.00.074.2151225587,02839.189.00.5138141
MOT16-0728.40.074.142679310,79433.987.51.6107125
MOT16-0826.70.080.063063211,55331.089.11.07774
MOT16-1234.90.077.911536514,71943.184.60.73435
MOT16-149.50.073.611931,40715,23717.669.81.97475

Raw data: