Title: DefectTrack: a deep learning-based multi-object tracking algorithm for quantitative defect analysis of in-situ TEM videos in real-time

Journal Article · · Scientific Reports

Abstract In-situ irradiation transmission electron microscopy (TEM) offers unique insights into the millisecond-timescale post-cascade process, such as the lifetime and thermal stability of defect clusters, vital to the mechanistic understanding of irradiation damage in nuclear materials. Converting in-situ irradiation TEM video data into meaningful information on defect cluster dynamic properties (e.g., lifetime) has become the major technical bottleneck. Here, we present a solution called the DefectTrack , the first dedicated deep learning-based one-shot multi-object tracking (MOT) model capable of tracking cascade-induced defect clusters in in-situ TEM videos in real-time. DefectTrack has achieved a Multi-Object Tracking Accuracy (MOTA) of 66.43% and a Mostly Tracked (MT) of 67.81% on the test set, which are comparable to state-of-the-art MOT algorithms. We discuss the MOT framework, model selection, training, and evaluation strategies for in-situ TEM applications. Further, we compare the DefectTrack with four human experts in quantifying defect cluster lifetime distributions using statistical tests and discuss the relationship between the material science domain metrics and MOT metrics. Our statistical evaluations on the defect lifetime distribution suggest that the DefectTrack outperforms human experts in accuracy and speed.

Research Organization:
Argonne National Laboratory (ANL), Argonne, IL (United States)
Sponsoring Organization:
US Air Force Office of Scientific Research (AFOSR); USDOE; USDOE Laboratory Directed Research and Development (LDRD) Program; USDOE Office of Science (SC)
Grant/Contract Number:
AC02-06CH11357
OSTI ID:
1888833
Journal Information:
Scientific Reports, Journal Name: Scientific Reports Journal Issue: 1 Vol. 12; ISSN 2045-2322
Publisher:
Nature Publishing GroupCopyright Statement
Country of Publication:
United Kingdom
Language:
English

References (45)

The Hungarian method for the assignment problem journal March 1955
Fundamentals of Radiation Materials Science book January 2017
Tracking Objects as Points book January 2020
Towards Real-Time Multi-Object Tracking book January 2020
Microsoft COCO: Common Objects in Context book January 2014
Performance Measures and a Data Set for Multi-target, Multi-camera Tracking book January 2016
On the histogram as a density estimator:L 2 theory journal December 1981
The Pascal Visual Object Classes (VOC) Challenge journal September 2009
ImageNet Large Scale Visual Recognition Challenge journal April 2015
MOTChallenge: A Benchmark for Single-Camera Multiple Target Tracking journal December 2020
FairMOT: On the Fairness of Detection and Re-identification in Multiple Object Tracking journal September 2021
In-situ observation of cascade damage in nickel and copper under heavy ion irradiation journal March 1991
Radiation-Induced Effects on Microstructure book August 2020
A computer vision approach for automated analysis and classification of microstructural image data journal December 2015
A deep learning based automatic defect analysis framework for In-situ TEM ion irradiations journal September 2021
Recent advances in small object detection based on deep learning: A review journal May 2020
Review: Evolution of stacking fault tetrahedra and its role in defect accumulation under cascade damage conditions journal July 2004
Helium bubble formation in nickel under in-situ krypton and helium ions dual-beam irradiation journal January 2022
In situ transmission electron microscopy with dual ion beam irradiation and implantation journal March 2021
Automated Detection of Helium Bubbles in Irradiated X-750 journal October 2020
Deep Learning for Atomically Resolved Imaging journal August 2018
Machine Learning to Reveal Nanoparticle Dynamics from Liquid-Phase TEM Videos journal July 2020
AutoDetect-mNP: An Unsupervised Machine Learning Algorithm for Automated Analysis of Transmission Electron Microscope Images of Metal Nanoparticles journal February 2021
Robust single-particle tracking in live-cell time-lapse sequences journal July 2008
Understanding the physical metallurgy of the CoCrFeMnNi high-entropy alloy: an atomistic simulation study journal January 2018
Magnetic control of tokamak plasmas through deep reinforcement learning journal February 2022
Deep learning for cellular image analysis journal May 2019
Advanced Steel Microstructural Classification by Deep Learning Methods journal February 2018
Deep Learning for Semantic Segmentation of Defects in Advanced STEM Images of Steels journal September 2019
Deep learning detection of nanoparticles and multiple object tracking of their dynamic evolution during in situ ETEM studies journal February 2022
Aesthetic Frequency Classifications journal November 1976
Handbook of Methods of Applied Statistics. Volume I: Techniques of Computation Descriptive Methods, and Statistical Inference. Volume II: Planning of Surveys and Experiments. I. M. Chakravarti, R. G. Laha, and J. Roy, New York, John Wiley; 1967, $9.00. journal September 1968
On optimal and data-based histograms journal January 1979
High-Speed tracking-by-detection without using image information conference August 2017
Extending IOU Based Multi-Object Tracking by Visual Information conference November 2018
Improving the Robustness of Deep Neural Networks via Stability Training conference June 2016
Person Re-identification in the Wild conference July 2017
Deep High-Resolution Representation Learning for Human Pose Estimation conference June 2019
Mask R-CNN conference October 2017
Deep High-Resolution Representation Learning for Visual Recognition journal October 2021
A New Approach to Linear Filtering and Prediction Problems journal March 1960
Evaluating Multiple Object Tracking Performance: The CLEAR MOT Metrics journal January 2008
An Asymptotically Optimal Window Selection Rule for Kernel Density Estimates journal December 1984
Frontiers of in situ electron microscopy journal January 2015
Incorporating Geomechanical and Dynamic Hydraulic-Fracture-Property Changes Into Rate-Transient Analysis: Example From the Haynesville Shale journal August 2013