Online Multi-Object Tracking with the GMPHD Filter Using Occlusion Group Management


Short name:

GMPHD_OGM

Benchmark:

Description:

n/a

Hardware:

Intel i7-7700K @ 4.2GHz, 4 Cores, no GPU

Detector:

Public

Processing:

Online

Last submitted:

June 04, 2019 (3 months ago)

Published:

May 27, 2019 at 09:29:55 CET

Submissions:

4

Open source:

No

Project page / code:

n/a

Reference:

Y. Song, K. Yoon, Y. Yoon, K. Yow, M. Jeon. Online Multi-Object Tracking Framework with the GMPHD Filter and Occlusion Group Management. In arXiv:1907.13347, 2019.

Benchmark performance:

MOTAMOTPFAFMTMLFPFNID Sw.FragSpecificationsDetector
30.771.61.111.5 % 38.1 % 6,50235,0301,0341,351Intel i7-7700K @ 4.2GHz, 4 Cores, no GPUPublic
IDF1ID PrecisionID Recall
38.855.629.8

Detailed performance:

Sequence MOTA IDF1 MOTP FAF GT MT ML FP FN ID Sw Frag
TUD-Crossing60.455.473.10.51338.5 % 15.4 % 1093111614
PETS09-S2L246.331.169.42.74214.3 % 9.5 % 1,1813,717280313
ETH-Jelmoli37.648.973.80.84515.6 % 31.1 % 3551,1775058
ETH-Linthescher24.331.974.30.41976.1 % 63.5 % 4546,173133140
ETH-Crossing29.547.474.80.3263.8 % 46.2 % 65633910
AVG-TownCentre29.143.068.62.622617.3 % 25.2 % 1,1543,541376511
ADL-Rundle-116.437.174.13.53215.6 % 46.9 % 1,7675,9724563
ADL-Rundle-337.246.474.10.74411.4 % 29.5 % 4195,9263941
KITTI-1643.457.272.90.6170.0 % 11.8 % 1278211539
KITTI-1926.438.366.10.6624.8 % 33.9 % 6233,25260145
Venice-117.528.775.00.6170.0 % 58.8 % 2483,5071117

Raw data:

n/a


GMPHD_OGM
UTA