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

TUD-Crossing PETS09-S2L2 ETH-Jelmoli ETH-Linthescher ETH-Crossing AVG-TownCentre ADL-Rundle-1 ADL-Rundle-3 KITTI-16 KITTI-19

Short name:

GMPHD_15

Benchmark:

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

Hardware:

3.5 GHz, 4 Cores

Detector:

Public

Processing:

Online

Last submitted:

December 05, 2016 (10 months ago)

Published:

December 05, 2016 at 10:21:45 CET

Submissions:

1

Open source:

No

Project page / code:

n/a

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.

Benchmark performance:

MOTAMOTPFAFMTMLFPFNID Sw.FragSpecificationsDetector
18.570.91.43.9 % 55.3 % 7,86441,7664591,2663.5 GHz, 4 CoresPublic
IDF1ID PrecisionID Recall
28.445.820.6

Detailed performance:

Sequence MOTA IDF1 MOTP FAF GT MT ML FP FN ID Sw Frag
TUD-Crossing50.549.272.30.21315.4 % 15.4 % 414851929
PETS09-S2L231.928.469.11.1420.0 % 31.0 % 4675,965131315
ETH-Jelmoli34.342.872.20.74511.1 % 35.6 % 3171,3351659
ETH-Linthescher16.224.072.20.51972.5 % 72.1 % 5396,8964489
ETH-Crossing6.422.574.20.8267.7 % 73.1 % 180756311
AVG-TownCentre16.328.470.00.92264.0 % 65.0 % 4135,54226103
ADL-Rundle-110.028.472.14.7326.3 % 40.6 % 2,3665,95458176
ADL-Rundle-315.323.873.22.2440.0 % 40.9 % 1,3747,17464108
KITTI-1627.537.873.20.7170.0 % 29.4 % 1541,0611952
KITTI-1911.533.365.31.2624.8 % 27.4 % 1,2853,39450254
Venice-113.222.871.51.6170.0 % 41.2 % 7283,2042970

Raw data:


GMPHD_15