Learning a Neural Solver for Multiple Object Tracking
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 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.
Code (1)
Tasks
Multi-Object TrackingMultiple Object TrackingObjectObject TrackingSimilar Papers 제목 키워드 기반
Fusion of Head and Full-Body Detectors for Multi-Object Tracking
In order to track all persons in a scene, the tracking-by-detection paradigm has proven to be a very effective approach. Yet, relying solely on a single detector is also a major limitation, as useful image information mi…
Multi-Object TrackingObject TrackingMaking Higher Order MOT Scalable: An Efficient Approximate Solver for Lifted Disjoint Paths
We present an efficient approximate message passing solver for the lifted disjoint paths problem (LDP), a natural but NP-hard model for multiple object tracking (MOT). Our tracker scales to very large instances that come…
Multiple Object TrackingObject TrackingKnotResolver: Tracking self-intersecting filaments in microscopy using directed graphs
Quantification of microscopy time-series of in vitro reconstituted motor driven microtubule (MT) transport in 'gliding assays' is typically performed using computational object tracking tools. However, these are limited …
Contour DetectionObject TrackingTime SeriesOpen-Set Semantic Uncertainty Aware Metric-Semantic Graph Matching
Underwater object-level mapping requires incorporating visual foundation models to handle the uncommon and often previously unseen object classes encountered in marine scenarios. In this work, a metric of semantic uncert…
Graph MatchingLoop Closure DetectionObjectLearning a Neural Solver for Multiple Object Tracking
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 …
Multi-Object TrackingMultiple Object TrackingObjectObject Tracking