LPC_MOT: Learning a Proposal Classifier for Multiple Object Tracking

MOT16-01


Benchmark:

MOT20 | MOT17 | MOT16 |

Short name:

LPC_MOT

Detector:

Public

Description:

This approach is devised by Tsinghua University and AIBEE Inc.

Reference:

Tsinghua University & AIBEE Research.

Last submitted:

January 22, 2021 (1 month ago)

Published:

January 22, 2021 at 12:57:20 CET

Submissions:

1

Project page / code:

n/a

Open source:

No

Hardware:

GTX 1080 TI 20 cores

Runtime:

4.3 Hz

Benchmark performance:

Sequence MOTA IDF1 MOTP MT ML FP FN Recall Precision FAF ID Sw. Frag
MOT1658.867.678.4207 (27.3)266 (35.0)6,16768,43262.594.91.0435 (7.0)628 (10.1)

Detailed performance:

Sequence MOTA IDF1 MOTP MT ML FP FN Recall Precision FAF ID Sw. Frag
MOT16-0147.655.177.6810643,27148.998.00.11416
MOT16-0369.876.378.271193,23828,18773.095.92.2106161
MOT16-0655.157.879.270867414,37362.190.60.66588
MOT16-0743.854.577.28111,3257,76152.586.62.790155
MOT16-0842.954.881.717242059,31344.497.30.33248
MOT16-1249.262.381.420382313,96152.294.90.32228
MOT16-1434.945.476.7137836311,56637.495.00.5106132

Raw data:


LPC_MOT