JPDA_m: Joint Probabilistic Data Association Revisited


Benchmark:

Short name:

JPDA_m

Detector:

Public

Description:

In this paper, we revisit the joint probabilistic data association (JPDA) technique and propose a novel solution based on recent developments in finding the m-best solutions to an integer linear program. The key advantage of this approach is that it makes JPDA computationally tractable in applications with high target and/or clutter density, such as spot tracking in fluorescence microscopy sequences and pedestrian tracking in surveillance footage. We also show that our JPDA algorithm embedded in a simple tracking framework is surprisingly competitive with state-of-the-art global tracking methods in these two applications, while needing considerably less processing time.

Project page / code:

Reference:

H. Rezatofighi, A. Milan, Z. Zhang, Q. Shi, A. Dick, I. Reid. Joint Probabilistic Data Association Revisited. In ICCV, 2015.

Processing:

Batch

Last submitted:

April 14, 2015 (4 years ago)

Published:

April 22, 2015 at 09:02:53 CET

Submissions:

2

Open source:

No

Hardware:

3 GHz, 1 Core

Benchmark performance:

Sequence MOTA IDF1 MOTP MT ML FP FN ID Sw.
2D MOT 201523.833.868.236.0419.06,37340,084365

Detailed performance:

Sequence MOTA IDF1 MOTP MT ML FP FN ID Sw.
ADL-Rundle-111.235.769.35.010.02,7645,44158
ADL-Rundle-332.332.868.03.013.08016,02064
AVG-TownCentre18.331.266.810.0143.02585,56123
ETH-Crossing14.923.171.10.020.048491
ETH-Jelmoli35.649.571.53.018.01451,4828
ETH-Linthescher7.012.372.81.0174.01128,1848
KITTI-1637.347.972.60.04.011693516
KITTI-1931.447.165.95.017.06532,98529
PETS09-S2L237.634.065.95.08.01,0164,858139
TUD-Crossing60.970.268.44.03.0443852
Venice-115.425.871.30.09.04603,38417

Raw data:


JPDA_m