GM_PHD_DAL: Online Multi-object Visual Tracking using a GM-PHD Filter with Deep Appearance Learning

MOT16-01


Benchmark:

MOT16 |

Short name:

GM_PHD_DAL

Detector:

Public

Description:

n/a

Reference:

N. Baisa. Online Multi-object Visual Tracking using a GM-PHD Filter with Deep Appearance Learning. In 2019 22th International Conference on Information Fusion (FUSION), 2019.

Last submitted:

March 21, 2019 (1 year ago)

Published:

February 11, 2019 at 22:59:20 CET

Submissions:

2

Open source:

No

Hardware:

3 GHZ, 1 Core

Runtime:

3.5 Hz

Benchmark performance:

Sequence MOTA IDF1 MOTP MT ML FP FN Recall Precision FAF ID Sw. Frag
MOT1635.126.676.653 (7.0)390 (51.4)2,350111,88638.696.80.44,047 (104.8)5,338 (138.2)

Detailed performance:

Sequence MOTA IDF1 MOTP MT ML FP FN Recall Precision FAF ID Sw. Frag
MOT16-0122.019.773.6213634,81824.796.20.1107170
MOT16-0340.927.476.712441,00958,34844.297.90.72,3933,121
MOT16-0640.236.874.2181121256,45744.097.60.1313371
MOT16-0729.523.674.942633210,71034.494.40.7472638
MOT16-0828.525.380.352923711,49831.395.70.4229310
MOT16-1236.034.877.78443134,84241.691.70.3155230
MOT16-1414.215.675.6412227115,21317.792.30.4378498

Raw data:


GM_PHD_DAL