A Real-time Deep Graph Matching for Multi-object Tracking

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

Short name:

youtu_face

Benchmark:

Description:

Hardware:

2.5GHz,2 Core

Detector:

Private

Processing:

Batch

Last submitted:

April 26, 2018 (1 year ago)

Published:

May 06, 2019 at 04:27:37 CET

Submissions:

1

Open source:

No

Project page / code:

n/a

Reference:

Benchmark performance:

MOTAMOTPFAFMTMLFPFNID Sw.FragSpecificationsDetector
56.875.61.143.3 % 21.2 % 6,45219,6424599002.5GHz,2 CorePrivate
IDF1ID PrecisionID Recall
59.467.653.1

Detailed performance:

Sequence MOTA IDF1 MOTP FAF GT MT ML FP FN ID Sw Frag
TUD-Crossing87.678.274.50.11376.9 % 7.7 % 1312046
PETS09-S2L267.844.775.11.44233.3 % 4.8 % 6292,286187225
ETH-Jelmoli52.566.378.41.24544.4 % 33.3 % 5256701127
ETH-Linthescher66.367.179.50.719741.6 % 28.9 % 8762,0785971
ETH-Crossing76.280.284.80.32638.5 % 34.6 % 5817658
AVG-TownCentre68.677.771.41.622653.5 % 15.5 % 7281,46650226
ADL-Rundle-145.254.375.51.53228.1 % 21.9 % 7734,2953266
ADL-Rundle-352.552.078.91.54429.5 % 13.6 % 9433,8295893
KITTI-1649.564.671.11.61741.2 % 5.9 % 3395041645
KITTI-1939.059.368.41.26233.9 % 22.6 % 1,2182,01031119
Venice-143.854.874.70.81729.4 % 35.3 % 3502,208614

Raw data:


youtu_face
SAS