Our new X account is live! Follow @wizwand_team for updates
WorkDL logo mark

Learning a Neural Solver for Multiple Object Tracking

About

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 \textit{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. Our code is available at https://bit.ly/motsolv .

Guillem Bras\'o, Laura Leal-Taix\'e• 2019

Related benchmarks

TaskDatasetResultRank
Multiple Object TrackingMOT17 (test)
MOTA58.8
921
Multiple Object TrackingMOT20 (test)
MOTA57.6
358
Multi-Object TrackingMOT16 (test)
MOTA58.6
228
Multi-Object TrackingMOT17
MOTA58.8
55
Multi-Object TrackingKITTI (test)--
51
Multiple Object Tracking2D MOT15 (test)
MOTA51.5
34
Multi-target trackingKITTI Pedestrian (test)
MOTA46.23
33
Multiple Object TrackingMOT16
MOTA58.6
15
Multi-Object TrackingMOT20 Public detections (test)
IDF159.1
6
Showing 9 of 9 rows

Other info

Follow for update