Physics-Informed Tracking (PIT)

TL;DR

Physics-Informed Tracking (PIT) is a novel video-based framework that combines neural autoencoders and physics constraints to accurately track particles without requiring labels, applicable in noisy conditions.

Contribution

The paper introduces a physics-informed loss and a split autoencoder architecture for unsupervised and supervised particle tracking, improving accuracy and physical consistency.

Findings

PILLS achieves sub-pixel tracking accuracy.

The framework performs well under noisy conditions.

Physics constraints improve tracking consistency.

Abstract

We propose Physics-Informed Tracking (PIT), a video-based framework for tracking a single particle from video, where a neural network autoencoder localizes a particle as a heatmap peak (landmark) and a differentiable physics module embedded in the autoencoder constrains several landmarks over time (a trajectory) to satisfy known dynamics. The novel Physics-Informed Landmark Loss (PILL) compares this predicted trajectory back against the landmarks, enforcing physical consistency without labels. Its supervised variant (PILLS) instead compares the prediction against ground-truth position, velocity, and bounce from simulation, enabling end-to-end backpropagation. To support supervised and unsupervised learning, we use an autoencoder with a split bottleneck that separates A) tracking-related structure via landmark heatmaps from B) background noise and subsequent image reconstruction. We evaluate a replicated 26 factorial design (n = 4 replicates, 64 configurations), showing that PILLS consistently achieves sub-pixel tracking accuracy for the bilinear and physics-refined decoder outputs under both clean and noisy conditions.