Deep Learning-Based Tracking and Lineage Reconstruction of Ligament Breakup
Summary: arXiv:2604.08711v1 Announce Type: cross
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.
Framework Overview
The proposed framework consists of two distinct stages:
- Stage 1: Object Detection
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.
- Stage 2: Temporal Relationship Modeling
The second stage employs a Transformer-augmented multilayer perceptron to classify 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.
Significance of the Framework
Together, the framework enables:
- Automated reconstruction of fragmentation trees.
- Preservation of parent-child lineage.
- 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. This advancement represents a significant step forward in the understanding of liquid breakup dynamics, which has implications across various fields including material science, fluid mechanics, and even biomedical applications.
Conclusion
The two-stage deep learning framework discussed in this article addresses critical limitations in conventional tracking methodologies for liquid breakup analysis. By combining advanced object detection with temporal modeling, it opens new avenues for research and practical applications in the study of fluid dynamics and atomization processes.