MOANA: Modeling of Object Appearance by Normalized Adaptation for 3D Multiple Object Tracking

PETS09-S2L2


Benchmark:

Short name:

MOANA

Detector:

Public

Description:

(1) 3D Kalman-filter-based tracking for fully visible object(s)
(2) Cross-matching based on adaptive appearance modeling for partially occluded/grouped object(s)
(3) Re-identification based on adaptive appearance modeling for seriously occluded object(s)

Project page / code:

n/a

Processing:

Online

Last submitted:

December 06, 2017 (2 years ago)

Published:

September 04, 2018 at 01:28:28 CET

Submissions:

3

Open source:

No

Hardware:

4.20 GHz, 4 Cores

Runtime:

19.4 Hz

Benchmark performance:

Sequence MOTA IDF1 MOTP MT ML FP FN Recall Precision FAF ID Sw. Frag
3D MOT 201552.762.456.376 (28.4)59 (22.0)2,2265,55166.983.52.5167 (2.5)586 (8.8)

Detailed performance:

Sequence MOTA IDF1 MOTP MT ML FP FN Recall Precision FAF ID Sw. Frag
AVG-TownCentre0.00.00.000000.00.00.000
PETS09-S2L20.00.00.000000.00.00.000

Raw data: