English

Multi-Object Tracking and Segmentation via Neural Message Passing

Computer Vision and Pattern Recognition 2022-07-18 v1

Abstract

Graphs offer a natural way to formulate Multiple Object Tracking (MOT) and Multiple Object Tracking and Segmentation (MOTS) 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. 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 exploit contextual features. It then jointly predicts both final solutions for the data association problem and segmentation masks for all objects in the scene while exploiting synergies between the two tasks. We achieve state-of-the-art results for both tracking and segmentation in several publicly available datasets. Our code is available at github.com/ocetintas/MPNTrackSeg.

Keywords

Cite

@article{arxiv.2207.07454,
  title  = {Multi-Object Tracking and Segmentation via Neural Message Passing},
  author = {Guillem Braso and Orcun Cetintas and Laura Leal-Taixe},
  journal= {arXiv preprint arXiv:2207.07454},
  year   = {2022}
}

Comments

arXiv admin note: substantial text overlap with arXiv:1912.07515

R2 v1 2026-06-25T00:56:45.645Z