Dynamic Atomic Column Detection in Transmission Electron Microscopy Videos via Ridge Estimation
This addresses the challenge of tracking atomic-level objects that stochastically disappear and reappear in TEM videos for material science applications, representing an incremental advancement over frame-by-frame methods.
The paper tackled the problem of detecting atomic columns in Transmission Electron Microscopy videos by developing a ridge detection method that analyzes temporal correlations across frames, resulting in notable performance improvements in experiments compared to benchmarks.
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.