Tracklet Confidence Siamese

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

Short name:

TC_SIAMESE

Benchmark:

Description:

n/a

Hardware:

3.7 GHZ, 4 Core

Detector:

Public

Processing:

Online

Last submitted:

April 09, 2018 (3 months ago)

Published:

April 02, 2018 at 04:17:21 CET

Submissions:

4

Open source:

No

Project page / code:

n/a

Reference:

Y. Yoon, Y. Song, K. Yoon, M. Jeon. Online Multiple-Object Tracking using Selective Deep Appearance Matching. In IEEE/IEIE The International Conference on Consumer Electronics (ICCE) Asia, 2018.

Benchmark performance:

MOTAMOTPFAFMTMLFPFNID Sw.FragSpecificationsDetector
20.271.11.12.6 % 67.5 % 6,12742,5962948253.7 GHZ, 4 CorePublic
IDF1ID PrecisionID Recall
32.656.422.9

Detailed performance:

Sequence MOTA IDF1 MOTP FAF GT MT ML FP FN ID Sw Frag
TUD-Crossing49.361.773.50.41323.1 % 23.1 % 82470715
PETS09-S2L228.931.069.11.5420.0 % 33.3 % 6626,086104218
ETH-Jelmoli30.950.572.40.4456.7 % 48.9 % 1941,551741
ETH-Linthescher9.016.272.30.21970.5 % 87.3 % 1977,925739
ETH-Crossing16.027.371.70.3260.0 % 69.2 % 56786112
AVG-TownCentre3.612.969.00.72260.4 % 86.3 % 2936,593732
ADL-Rundle-114.638.671.25.13218.8 % 25.0 % 2,5495,35742149
ADL-Rundle-334.940.172.81.1446.8 % 31.8 % 6995,8664975
KITTI-1629.241.873.20.4170.0 % 29.4 % 911,0981536
KITTI-1918.932.667.00.6621.6 % 45.2 % 6833,60546154
Venice-114.833.072.61.4175.9 % 47.1 % 6213,259954

Raw data:


TC_SIAMESE