Making Higher Order MOT Scalable: An Efficient Approximate Solver for Lifted Disjoint Paths

08/24/2021
by   Andrea Hornakova, et al.
4

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 from long and crowded MOT sequences. Our approximate solver enables us to process the MOT15/16/17 benchmarks without sacrificing solution quality and allows for solving MOT20, which has been out of reach up to now for LDP solvers due to its size and complexity. On all these four standard MOT benchmarks we achieve performance comparable or better than current state-of-the-art methods including a tracker based on an optimal LDP solver.

READ FULL TEXT

page 12

page 13

page 31

page 32

research
06/25/2020

Lifted Disjoint Paths with Application in Multiple Object Tracking

We present an extension to the disjoint paths problem in which additiona...
research
05/23/2017

A Novel Multi-Detector Fusion Framework for Multi-Object Tracking

In order to track all persons in a scene, the tracking-by-detection para...
research
01/05/2022

GLAN: A Graph-based Linear Assignment Network

Differentiable solvers for the linear assignment problem (LAP) have attr...
research
02/28/2020

Scaling up Hybrid Probabilistic Inference with Logical and Arithmetic Constraints via Message Passing

Weighted model integration (WMI) is a very appealing framework for proba...
research
12/16/2019

Learning a Neural Solver for Multiple Object Tracking

Graphs offer a natural way to formulate Multiple Object Tracking (MOT) w...
research
04/16/2020

MPLP++: Fast, Parallel Dual Block-Coordinate Ascent for Dense Graphical Models

Dense, discrete Graphical Models with pairwise potentials are a powerful...
research
10/28/2022

Parallel Self-Avoiding Walks for a Low-Autocorrelation Binary Sequences Problem

A low-autocorrelation binary sequences problem with a high figure of mer...

Please sign up or login with your details

Forgot password? Click here to reset