CNN based Multi Target Tracking

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

Short name:

CNNMTT

Benchmark:

Description:

n/a

Hardware:

2.65 GHz, 4 Cores, GTX 960M

Detector:

Private

Processing:

Online

Last submitted:

December 08, 2016 (2 years ago)

Published:

August 15, 2018 at 03:12:56 CET

Submissions:

2

Open source:

No

Project page / code:

n/a

Reference:

Mahmoudi, N., Ahadi, S. M., & Rahmati, M. (2018). Multi-target tracking using CNN-based features: CNNMTT. Multimedia Tools and Applications, 1-20.

Benchmark performance:

MOTAMOTPFAFMTMLFPFNID Sw.FragSpecificationsDetector
65.278.41.132.4 % 21.3 % 6,57855,8969462,2832.65 GHz, 4 Cores, GTX 960MPrivate
IDF1ID PrecisionID Recall
62.273.753.8

Detailed performance:

Sequence MOTA IDF1 MOTP FAF GT MT ML FP FN ID Sw Frag
MOT16-0162.761.678.20.72352.2 % 13.0 % 3282,0431661
MOT16-0375.467.578.61.414854.1 % 8.8 % 2,08223,375216904
MOT16-0661.459.976.70.522136.2 % 19.9 % 5873,712154241
MOT16-0757.652.479.31.45431.5 % 7.4 % 7156,090116259
MOT16-0840.946.079.42.06325.4 % 25.4 % 1,2658,462155191
MOT16-1247.857.880.00.38619.8 % 43.0 % 2854,0053790
MOT16-1447.156.076.01.816414.6 % 27.4 % 1,3168,209252537

Raw data:


CNNMTT