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


Video not available.

Rendering of new sequences is currently deactivated due to heavy load.

Rendering of new sequences is currently deactivated due to heavy load.

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)

Last submitted:

December 06, 2017 (4 years ago)

Published:

September 04, 2018 at 01:28:28 CET

Submissions:

3

Project page / code:

n/a

Open source:

No

Hardware:

4.20 GHz, 4 Cores

Runtime:

19.4 Hz

Benchmark performance:

Sequence MOTA IDF1 HOTA MT ML FP FN Rcll Prcn AssA DetA AssRe AssPr DetRe DetPr LocA FAF ID Sw. Frag
3D MOT 201552.762.40.076 (28.4)59 (22.0)2,2265,55166.983.50.00.00.00.00.00.00.02.5167 (2.5)586 (8.8)

Detailed performance:

Sequence MOTA IDF1 HOTA MT ML FP FN Rcll Prcn AssA DetA AssRe AssPr DetRe DetPr LocA FAF ID Sw. Frag
AVG-TownCentre0.00.00.000000.00.00.00.00.00.00.00.00.00.000
PETS09-S2L20.00.00.000000.00.00.00.00.00.00.00.00.00.000

Raw data: