Learning data association without data association: An EM approach to neural assignment prediction

05/02/2021
by   Michael Burke, et al.
8

Data association is a fundamental component of effective multi-object tracking. Current approaches to data-association tend to frame this as an assignment problem relying on gating and distance-based cost matrices, or offset the challenge of data association to a problem of tracking by detection. The latter is typically formulated as a supervised learning problem, and requires labelling information about tracked object identities to train a model for object recognition. This paper introduces an expectation maximisation approach to train neural models for data association, which does not require labelling information. Here, a Sinkhorn network is trained to predict assignment matrices that maximise the marginal likelihood of trajectory observations. Importantly, networks trained using the proposed approach can be re-used in downstream tracking applications.

READ FULL TEXT
research
05/17/2023

S^3Track: Self-supervised Tracking with Soft Assignment Flow

In this work, we study self-supervised multiple object tracking without ...
research
08/06/2022

Transformer-based assignment decision network for multiple object tracking

Data association is a crucial component for any multiple object tracking...
research
02/26/2018

Beyond Pixels: Leveraging Geometry and Shape Cues for Online Multi-Object Tracking

This paper introduces geometry and object shape and pose costs for multi...
research
06/26/2017

Deep Network Flow for Multi-Object Tracking

Data association problems are an important component of many computer vi...
research
02/19/2018

Machine Learning Methods for Solving Assignment Problems in Multi-Target Tracking

Data association and track-to-track association, two fundamental problem...
research
11/24/2014

Multiple object tracking with context awareness

Multiple people tracking is a key problem for many applications such as ...
research
07/15/2021

MeNToS: Tracklets Association with a Space-Time Memory Network

We propose a method for multi-object tracking and segmentation (MOTS) th...

Please sign up or login with your details

Forgot password? Click here to reset