arXiv subjects

Jason Monty

Publications and source records attributed to Jason Monty.

4 recordsLinked to original sources

arXiv2023

Knowledge Distillation for Feature Extraction in Underwater VSLAM

In recent years, learning-based feature detection and matching have outperformed manually-designed methods in in-air cases. However, it is challenging to learn the features in the underwater scenario due to the absence of annotated underwater datasets. This paper proposes a cross-modal knowledge distillation framework for training an underwater feature detection and matching network (UFEN). In particular, we use in-air RGBD data to generate synthetic underwater images based on a physical underwater imaging formation model and employ these as the medium to distil knowledge from a teacher model SuperPoint pretrained on in-air images. We embed UFEN into the ORB-SLAM3 framework to replace the ORB feature by introducing an additional binarization layer. To test the effectiveness of our method, we built a new underwater dataset with groundtruth measurements named EASI (https://github.com/Jinghe-mel/UFEN-SLAM), recorded in an indoor water tank for different turbidity levels. The experimental results on the existing dataset and our new dataset demonstrate the effectiveness of our method.

cs.CV↗

arXiv2023

Identifying regions of importance in wall-bounded turbulence through explainable deep learning

Despite its great scientific and technological importance, wall-bounded turbulence is an unresolved problem in classical physics that requires new perspectives to be tackled. One of the key strategies has been to study interactions among the energy-containing coherent structures in the flow. Such interactions are explored in this study for the first time using an explainable deep-learning method. The instantaneous velocity field obtained from a turbulent channel flow simulation is used to predict the velocity field in time through a U-net architecture. Based on the predicted flow, we assess the importance of each structure for this prediction using the game-theoretic algorithm of SHapley Additive exPlanations (SHAP). This work provides results in agreement with previous observations in the literature and extends them by revealing that the most important structures in the flow are not necessarily the ones with the highest contribution to the Reynolds shear stress. We also apply the method to an experimental database, where we can identify completely new structures based on their importance score. This framework has the potential to shed light on numerous fundamental phenomena of wall-bounded turbulence, including novel strategies for flow control.

physics.flu-dyn↗

arXiv2018

Hydroelastic interactions between water waves and floating freshwater ice

Hydroelastic interactions between regular water waves and floating freshwater ice are investigated using laboratory experiments for a range of incident wave periods and steepnesses. It is shown that only incident waves with sufficiently long period and large steepness break up the ice cover, and that the extent of breakup increases with increasing period and steepness. Further, it is shown that an increasing proportion of the incident wave propagates through the ice-covered water as period and steepness increase, indicating the existence of a positive feedback loop between ice breakup and increased wave propagation.

physics.ao-ph↗

arXiv2017

An experimental comparison of velocities underneath focussed breaking waves

Nonlinear wave interactions affect the evolution of steep wave groups, their breaking and the associated kinematic field. Laboratory experiments are performed to investigate the effect of the underlying focussing mechanism on the shape of the breaking wave and its velocity field. In this regard, it is found that the shape of the wave spectrum plays a substantial role. Broader underlying wave spectra leads to energetic plungers at a relatively low amplitude. For narrower spectra waves break at a higher amplitudes but with a less energetic spiller. Comparison with standard engineering methods commonly used to predict the velocity underneath extreme waves shows that, under certain conditions, the measured velocity profile strongly deviates from engineering predictions.

physics.ao-ph↗