SSP-GNN: Learning to Track via Bilevel Optimization

TL;DR

This paper introduces SSP-GNN, a multi-object tracking method that uses a graph neural network to compute edge costs in a tracking graph, learned end-to-end via bilevel optimization, and demonstrates favorable results in simulated scenarios.

Contribution

The paper presents a novel graph-based multi-object tracking framework that integrates a message-passing GNN with bilevel optimization for end-to-end learning.

Findings

Favorable performance compared to baseline in simulated scenarios.

Sensitivity analysis of scenario aspects and hyperparameters.

Effective end-to-end training of the tracker.

Abstract

We propose a graph-based tracking formulation for multi-object tracking (MOT) where target detections contain kinematic information and re-identification features (attributes). Our method applies a successive shortest paths (SSP) algorithm to a tracking graph defined over a batch of frames. The edge costs in this tracking graph are computed via a message-passing network, a graph neural network (GNN) variant. The parameters of the GNN, and hence, the tracker, are learned end-to-end on a training set of example ground-truth tracks and detections. Specifically, learning takes the form of bilevel optimization guided by our novel loss function. We evaluate our algorithm on simulated scenarios to understand its sensitivity to scenario aspects and model hyperparameters. Across varied scenario complexities, our method compares favorably to a strong baseline.