GMPHD_15: Online Multi-Object Tracking with Hierarchical Data Association using the GMPHD filter

TUD-Crossing


Benchmark:

Short name:

GMPHD_15

Detector:

Public

Description:

Stage 1: low-level association between targets states and observations(i.e., detection responses), frame by frame
-We only used detection reponses with the positive confidence value among provided detection results

Stage 2: short tracklet elimination under the set length(parameter)
-Minimum tracklet length for mid-level association : 10

Stage 3: mid-level association between rough tracklets(almost fragmented or ID swtiched)
-Only Motion and size are used
-Appearance is not used

Reference:

Y. Song, M. Jeon. Online Multiple Object Tracking with the Hierarchically Adopted GM-PHD Filter using Motion and Appearance. In IEEE/IEIE The International Conference on Consumer Electronics (ICCE) Asia, 2016.

Last submitted:

December 05, 2016 (3 years ago)

Published:

December 05, 2016 at 10:21:45 CET

Submissions:

1

Open source:

No

Hardware:

3.5 GHz, 4 Cores

Runtime:

19.8 Hz

Benchmark performance:

Sequence MOTA IDF1 MOTP MT ML FP FN Recall Precision FAF ID Sw. Frag
2D MOT 201518.528.470.928 (3.9)399 (55.3)7,86441,76632.071.41.4459 (14.3)1,266 (39.5)

Detailed performance:

Sequence MOTA IDF1 MOTP MT ML FP FN Recall Precision FAF ID Sw. Frag
ADL-Rundle-110.028.472.12132,3665,95436.058.64.758176
ADL-Rundle-315.323.873.20181,3747,17429.468.52.264108
AVG-TownCentre16.328.470.091474135,54222.579.50.926103
ETH-Crossing6.422.574.221918075624.657.80.8311
ETH-Jelmoli34.342.872.25163171,33547.479.10.71659
ETH-Linthescher16.224.072.251425396,89622.879.10.54489
KITTI-1627.537.873.2051541,06137.680.60.71952
KITTI-1911.533.365.33171,2853,39436.560.31.250254
PETS09-S2L231.928.469.10134675,96538.188.71.1131315
TUD-Crossing50.549.272.3224148556.093.80.21929
Venice-113.222.871.5077283,20429.865.11.62970

Raw data: