A Data-Driven Approach to Classifying Wave Breaking in Infrared Imagery

Abstract

We apply deep convolutional neural networks (CNNs) to estimate wave breaking type (e.g., non-breaking, spilling, plunging) from close-range monochrome infrared imagery of the surf zone. Image features are extracted using six popular CNN architectures developed for generic image feature extraction. Logistic regression on these features is then used to classify breaker type. The six CNN-based models are compared without and with augmentation, a process that creates larger training datasets using random image transformations. The simplest model performs optimally, achieving average classification accuracies of 89% and 93%, without and with image augmentation respectively. Without augmentation, average classification accuracies vary substantially with CNN model. With augmentation, sensitivity to model choice is minimized. A class activation analysis reveals the relative importance of image features to a given classification. During its passage, the front face and crest of a spilling breaker are more important than the back face. For a plunging breaker, the crest and back face of the wave are most important, which suggests that CNN-based models utilize the distinctive ‘streak’ temperature patterns observed on the back face of plunging breakers for classification.

Surf Zone Waves at the Onset of Breaking: 1. LIDAR and IR Data Fusion Methods

“…Using these data fusion methods, we detect the onset of breaking and classify breaker type for 413 spilling and 111 plunging breakers. Methods to automate the image-based wave classification, including machine learning techniques, have been investigated (Buscombe & Carini, 2019). The frontal nature of breaking waves and the repeated streaky or unorganized IR signatures associated with different breaker types are features that machine-learning algorithms can exploit, and published results show that deep convolution neural networks classify breaker type from IR imagery with high skill (Buscombe & Carini, 2019).…”

Labeling Poststorm Coastal Imagery for Machine Learning: Measurement of Interrater Agreement

“…Labels or annotations are often added later, specific to a particular study. In some situations, labels can be assigned automatically-e.g., merging time-stamped images with time-stamped sensor data (e.g., Buscombe & Carini, 2019;Buscombe et al, 2020). But most of the time, labeling cannot be done programmatically and instead requires human interpretation (e.g., Ellenson et al, 2020;Liu et al, 2014;Buscombe & Ritchie, 2018;Morgan et al, 2019;Yang et al, 2021).…”

Wave Peel Tracking: A New Approach for Assessing Surf Amenity and Analysis of Breaking Waves

“…Video timestacks have been used for many years in coastal research [13] to measure or track breaking waves and wave runup [14][15][16][17]. Recent methods have involved the use of convolutional neural networks (CNN), for classifying beach states, wave breaker types and estimating wave height and wave period [18][19][20][21]. Wave crest tracking has been achieved through using a 'Mixture of Gaussians' approach and a spatial transformer network [22,23].…”