Dynamic Atomic Column Detection in Transmission Electron Microscopy Videos via Ridge Estimation

TL;DR

This paper introduces a novel ridge detection method for analyzing TEM videos, enabling continuous tracking of atomic objects over time by leveraging spatio-temporal correlations, surpassing traditional frame-by-frame approaches.

Contribution

The paper develops new ridge detection algorithms tailored for spatio-temporal data, allowing explicit trajectory estimation of atomic objects in TEM videos, including objects that temporarily disappear and reappear.

Findings

Method is highly effective in simulations

Achieves notable improvements in TEM experiments

Handles stochastic appearance and disappearance of objects

Abstract

Ridge detection is a classical tool to extract curvilinear features in image processing. As such, it has great promise in applications to material science problems; specifically, for trend filtering relatively stable atom-shaped objects in image sequences, such as Transmission Electron Microscopy (TEM) videos. Standard analysis of TEM videos is limited to frame-by-frame object recognition. We instead harness temporal correlation across frames through simultaneous analysis of long image sequences, specified as a spatio-temporal image tensor. We define new ridge detection algorithms to non-parametrically estimate explicit trajectories of atomic-level object locations as a continuous function of time. Our approach is specially tailored to handle temporal analysis of objects that seemingly stochastically disappear and subsequently reappear throughout a sequence. We demonstrate that the proposed method is highly effective and efficient in simulation scenarios, and delivers notable performance improvements in TEM experiments compared to other material science benchmarks.