Online and Real-time Tracker using the GMPHD Filter with Group Management and Relative Motion Analysis


Short name:

GMMA_intp

Benchmark:

Description:

n/a

Hardware:

4.2 GHz, 4 Cores

Detector:

Public

Processing:

Online

Last submitted:

February 14, 2019 (9 months ago)

Published:

August 01, 2019 at 08:55:33 CET

Submissions:

2

Open source:

No

Project page / code:

n/a

Reference:

Y. Song, Y. Yoon, K. Yoon, M. Jeon. Online and Real-Time Tracking with the GMPHD Filter using Group Management and Relative Motion Analysis. In Proc. IEEE Int. Workshop Traffic Street Surveill. Safety Secur. (AVSS), 2018.

Benchmark performance:

MOTAMOTPFAFMTMLFPFNID Sw.FragSpecificationsDetector
27.370.91.46.5 % 43.1 % 7,84835,8179871,8484.2 GHz, 4 CoresPublic
IDF1ID PrecisionID Recall
36.651.928.3

Detailed performance:

Sequence MOTA IDF1 MOTP FAF GT MT ML FP FN ID Sw Frag
TUD-Crossing54.852.572.40.41323.1 % 7.7 % 764081426
PETS09-S2L241.027.068.92.8429.5 % 9.5 % 1,2174,122349528
ETH-Jelmoli37.048.572.80.84517.8 % 28.9 % 3651,1785570
ETH-Linthescher24.032.972.40.61977.1 % 60.4 % 7195,935135166
ETH-Crossing26.548.073.50.5263.8 % 46.2 % 113615914
AVG-TownCentre20.534.469.11.52262.2 % 47.3 % 6934,816172297
ADL-Rundle-115.035.372.53.73212.5 % 37.5 % 1,8296,02560232
ADL-Rundle-335.045.872.71.94413.6 % 31.8 % 1,1905,3625975
KITTI-1639.649.372.40.7170.0 % 11.8 % 1428592757
KITTI-1922.337.866.10.7623.2 % 32.3 % 7643,32664245
Venice-113.329.771.61.6170.0 % 41.2 % 7403,17143138

Raw data:

n/a


GMMA_intp