Deep Learning-Based Tracking and Lineage Reconstruction of Ligament Breakup

2026-04-09

AI Summary

This study addresses the challenge of modeling one-to-many fragmentation events in liquid sheet breakup, which traditional multi-object tracking methods fail to capture, thereby hindering accurate reconstruction of lineage relationships between ligaments and droplets. To overcome this limitation, the authors propose a two-stage deep learning framework: first, an enhanced Faster R-CNN architecture (ResNet-50 with FPN) detects ligaments and droplets; second, a Transformer-augmented multilayer perceptron explicitly models inter-frame relationships—continuous, fragmented, or unrelated—by integrating physics-informed geometric features and morphology-preserving synthetic data. This approach is the first to incorporate one-to-many fragmentation directly into the tracking pipeline, achieving 86.1% accuracy, 93.2% precision, and 100% recall in fragmentation identification, with an overall detection F1-score of 0.872. It also successfully extracts key atomization statistics, including fragment multiplicity and droplet size distribution.

Technology Category

• Computer Vision: Motion & Tracking
• Intelligent Robots: Multimodal Perception & Sensor Fusion
• Machine Learning: Multimodal Learning

Application Category

• Search and Retrieval-Augmented AI: Retrieval-Augmented Generation (RAG) and multi-modal RAG
• Security and Privacy: Data transparency and provenance
• Semantics and Knowledge: Methods to enhance, augment, integrate or synergize semantic models such as knowledge graphs and LLMs

Abstract

The disintegration of liquid sheets into ligaments and droplets involves highly transient, multi-scale dynamics that are difficult to quantify from high-speed shadowgraphy images. Identifying droplets, ligaments, and blobs formed during breakup, along with tracking across frames, is essential for spray analysis. However, conventional multi-object tracking frameworks impose strict one-to-one temporal associations and cannot represent one-to-many fragmentation events. In this study, we present a two-stage deep learning framework for object detection and temporal relationship modeling across frames. The framework captures ligament deformation, fragmentation, and parent-child lineage during liquid sheet disintegration. In the first stage, a Faster R-CNN with a ResNet-50 backbone and Feature Pyramid Network detects and classifies ligaments and droplets in high-speed shadowgraphy recordings of an impinging Carbopol gel jet. A morphology-preserving synthetic data generation strategy augments the training set without introducing physically implausible configurations, achieving a held-out F1 score of up to 0.872 across fourteen original-to-synthetic configurations. In the second stage, a Transformer-augmented multilayer perceptron classifies inter-frame associations into continuation, fragmentation (one-to-many), and non-association using physics-informed geometric features. Despite severe class imbalance, the model achieves 86.1% accuracy, 93.2% precision, and perfect recall (1.00) for fragmentation events. Together, the framework enables automated reconstruction of fragmentation trees, preservation of parent-child lineage, and extraction of breakup statistics such as fragment multiplicity and droplet size distributions. By explicitly identifying children droplets formed from ligament fragmentation, the framework provides automated analysis of the primary atomization mode.

Problem

• ligament breakup
• multi-object tracking
• fragmentation events
• lineage reconstruction
• high-speed shadowgraphy

Innovation

• deep learning
• fragmentation tracking
• lineage reconstruction
• synthetic data augmentation
• Transformer-based association