Short name:
CEM_16
Benchmark:
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.
Hardware:
3 GHz, 1 CPU
Detector:
Public
Processing:
Batch
Last submitted:
March 22, 2016 (2 years ago)
Published:
March 21, 2016 at 00:00:00 CET
Submissions:
1
Open source:
No
Project page / code:
n/a
Reference:
A. Milan, S. Roth, K. Schindler. Continuous Energy Minimization for Multitarget Tracking. In IEEE TPAMI, 2014.
Benchmark performance:
MOTA | MOTP | FAF | MT | ML | FP | FN | ID Sw. | Frag | Specifications | Detector |
33.2 | 75.8 | 1.2 | 7.8 % | 54.4 % | 6,837 | 114,322 | 642 | 731 | 3 GHz, 1 CPU | Public |
IDF1 | ID Precision | ID Recall |
0.0 | 0.0 | 0.0 |
Detailed performance:
Sequence | MOTA | IDF1 | MOTP | FAF | GT | MT | ML | FP | FN | ID Sw | Frag |
MOT16-01 | 28.4 | 0.0 | 72.3 | 0.3 | 23 | 17.4 % | 43.5 % | 123 | 4,420 | 36 | 31 |
MOT16-03 | 38.3 | 0.0 | 75.9 | 2.2 | 148 | 11.5 % | 39.9 % | 3,251 | 61,110 | 168 | 238 |
MOT16-06 | 33.9 | 0.0 | 74.2 | 0.4 | 221 | 6.8 % | 56.6 % | 527 | 6,960 | 138 | 143 |
MOT16-07 | 28.3 | 0.0 | 74.1 | 1.6 | 54 | 7.4 % | 48.1 % | 793 | 10,808 | 107 | 126 |
MOT16-08 | 26.7 | 0.0 | 80.0 | 1.0 | 63 | 9.5 % | 47.6 % | 632 | 11,553 | 77 | 74 |
MOT16-12 | 34.9 | 0.0 | 77.9 | 0.7 | 86 | 12.8 % | 52.3 % | 651 | 4,719 | 34 | 35 |
MOT16-14 | 15.1 | 0.0 | 73.4 | 1.1 | 164 | 1.2 % | 72.0 % | 860 | 14,752 | 82 | 84 |
Raw data: