Multi-Pedestrians Tracking via Convolutional neural network

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

Short name:

MPT

Benchmark:

Description:

Shihua Huang; Lu Wang. Northeastern University (Shenyang, Liaoning Province, China)

Hardware:

3.5 GHZ ,1 Core

Detector:

Private

Processing:

Online

Last submitted:

May 21, 2017 (1 year ago)

Published:

December 28, 2018 at 02:55:36 CET

Submissions:

1

Open source:

No

Project page / code:

n/a

Reference:

Anonymous submission

Benchmark performance:

MOTAMOTPFAFMTMLFPFNID Sw.FragSpecificationsDetector
61.678.72.334.7 % 19.4 % 13,78155,1919621,4363.5 GHZ ,1 CorePrivate
IDF1ID PrecisionID Recall
58.066.551.4

Detailed performance:

Sequence MOTA IDF1 MOTP FAF GT MT ML FP FN ID Sw Frag
MOT16-0142.242.977.73.62352.2 % 8.7 % 1,6082,0494249
MOT16-0371.562.378.93.714847.3 % 9.5 % 5,57923,882288528
MOT16-0661.065.280.70.722140.7 % 19.0 % 8203,570113152
MOT16-0758.053.078.42.35433.3 % 5.6 % 1,1745,561123188
MOT16-0836.739.879.71.86320.6 % 28.6 % 1,1549,305127183
MOT16-1245.458.979.01.18624.4 % 33.7 % 1,0043,4854358
MOT16-1445.952.175.83.316423.8 % 23.8 % 2,4427,339226278

Raw data:

n/a


MPT