Multi-Object Tracking with Quadruplet Convolutional Neural Networks

MOT16-01 MOT16-03 MOT16-06 MOT16-07 MOT16-08 MOT16-12 MOT16-14

Short name:

QuadMOT16

Benchmark:

Description:

n/a

Hardware:

3 GHZ, 1 Core, TITAN X

Detector:

Public

Processing:

Batch

Last submitted:

November 22, 2016 (8 months ago)

Published:

November 23, 2016 at 04:26:44 CET

Submissions:

1

Open source:

No

Project page / code:

n/a

Reference:

J. Son, M. Baek, M. Cho, B. Han. Multi-Object Tracking with Quadruplet Convolutional Neural Networks. In CVPR, 2017.

Benchmark performance:

MOTAMOTPFAFMTMLFPFNID Sw.FragSpecificationsDetector
44.176.41.114.6 % 44.9 % 6,38894,7757451,0963 GHZ, 1 Core, TITAN XPublic

Detailed performance:

Sequence MOTA MOTP FAF GT MT ML FP FN ID Sw Frag
MOT16-0130.874.80.32317.4 % 47.8 % 1194,2782643
MOT16-0351.076.32.114818.2 % 22.3 % 3,12547,704397561
MOT16-0649.276.80.222119.9 % 52.5 % 2605,5495182
MOT16-0741.977.21.55413.0 % 29.6 % 7688,62684108
MOT16-0829.979.40.96311.1 % 41.3 % 58211,0727484
MOT16-1238.076.20.68615.1 % 55.8 % 5164,5992832
MOT16-1424.073.81.41645.5 % 55.5 % 1,01812,94785186

Raw data:


QuadMOT16