MTDF: Multi-Level Cooperative Fusion of GM-PHD Filters for Online Multiple Human Tracking

MOT16-01


Benchmark:

MOT16 |

Short name:

MTDF

Detector:

Public

Description:

n/a

Project page / code:

n/a

Reference:

Z. Fu, F. Angelini, J. Chambers, S. Naqvi. Multi-Level Cooperative Fusion of GM-PHD Filters for Online Multiple Human Tracking. In IEEE Transactions on Multimedia, 2019.

Processing:

Online

Last submitted:

May 15, 2018 (2 years ago)

Published:

July 30, 2018 at 17:58:00 CET

Submissions:

3

Open source:

No

Hardware:

i7 3.5GHz; GTX 1060

Runtime:

1.5 Hz

Benchmark performance:

Sequence MOTA IDF1 MOTP MT ML FP FN Recall Precision FAF ID Sw. Frag
MOT1645.740.172.6107 (14.1)276 (36.4)12,01884,97053.489.02.01,987 (37.2)3,377 (63.2)

Detailed performance:

Sequence MOTA IDF1 MOTP MT ML FP FN Recall Precision FAF ID Sw. Frag
MOT16-0126.131.769.44101,0143,64443.073.12.365130
MOT16-0356.643.872.836225,30239,12862.692.53.59951,704
MOT16-0642.646.771.835899005,54152.087.00.8177257
MOT16-0733.128.970.95131,5309,09544.382.53.1291473
MOT16-0826.124.176.86251,25510,90934.882.32.0203277
MOT16-1240.448.075.112338174,04051.383.90.989124
MOT16-1424.434.569.49841,20012,61331.883.01.6167412

Raw data: