AdTobKF: Adaptive Tobit Kalman-based tracking

TUD-Crossing


Benchmark:

Short name:

AdTobKF

Detector:

Public

Description:

n/a

Reference:

K. Loumponias, A. Dimou, N. Vretos, P. Daras. Adaptive Tobit Kalman-Based Tracking. In 2018 14th International Conference on Signal-Image Technology \& Internet-Based Systems (SITIS), 2018.

Last submitted:

November 20, 2017 (2 years ago)

Published:

July 12, 2019 at 17:00:44 CET

Submissions:

3

Project page / code:

n/a

Open source:

No

Hardware:

Runtime:

206.5 Hz

Benchmark performance:

Sequence MOTA IDF1 MOTP MT ML FP FN Recall Precision FAF ID Sw. Frag
2D MOT 201524.834.570.829 (4.0)375 (52.0)6,20139,32136.078.11.1666 (18.5)1,300 (36.1)

Detailed performance:

Sequence MOTA IDF1 MOTP MT ML FP FN Recall Precision FAF ID Sw. Frag
ADL-Rundle-118.738.471.8492,2265,28443.264.44.560138
ADL-Rundle-330.638.572.82158166,17739.283.01.360112
AVG-TownCentre22.136.568.781045744,88831.679.71.3106231
ETH-Crossing16.121.674.4018782717.596.20.088
ETH-Jelmoli35.948.073.06181611,42943.787.30.43656
ETH-Linthescher10.416.173.81169657,90211.594.10.13455
KITTI-1639.252.071.51314586948.985.20.72152
KITTI-1922.937.366.52208493,19240.371.70.881213
PETS09-S2L238.231.369.0378474,89249.384.91.9221348
TUD-Crossing53.056.572.8232348256.396.40.11326
Venice-114.726.372.4094883,37925.970.81.12661

Raw data: