MPNTrack: Learning a Neural Solver for Multiple Object Tracking

MOT20-04


Benchmark:

Short name:

MPNTrack

Detector:

Public

Description:

Graphs offer a natural way to formulate Multiple Object Tracking (MOT) within the tracking-by-detection paradigm. However, they also introduce a major challenge for learning methods, as defining a model that can operate on such a structured domain is not trivial. As a consequence, most learning-based work has been devoted to learning better features for MOT, and then using these with well-established optimization frameworks. In this work, we exploit the classical network flow formulation of MOT to define a fully differentiable framework based on Message Passing Networks (MPNs). By operating directly on the graph domain, our method can reason globally over an entire set of detections and predict final solutions. Hence, we show that learning in MOT does not need to be restricted to feature extraction, but it can also be applied to the data association step. We show a significant improvement in both MOTA and IDF1 on three publicly available benchmarks.

Reference:

G. Brasó, L. Leal-Taixé. Learning a Neural Solver for Multiple Object Tracking. In CVPR, 2020.

Last submitted:

October 28, 2020 (1 month ago)

Published:

November 01, 2020 at 20:36:48 CET

Submissions:

1

Open source:

Yes

Hardware:

NVIDIA Quadro P5000

Runtime:

6.5 Hz

Benchmark performance:

Sequence MOTA IDF1 MOTP MT ML FP FN Recall Precision FAF ID Sw. Frag
MOT2057.659.179.0474 (38.2)279 (22.5)16,953201,38461.194.93.81,210 (19.8)1,420 (23.2)

Detailed performance:

Sequence MOTA IDF1 MOTP MT ML FP FN Recall Precision FAF ID Sw. Frag
MOT20-0477.071.279.6376487,45955,20479.996.73.6506611
MOT20-0636.039.877.1391134,83179,64940.091.74.8425504
MOT20-0757.459.979.5411790613,06160.595.71.5120124
MOT20-0825.936.177.3181013,75753,47031.086.54.7159181

Raw data:


MPNTrack