Please use this identifier to cite or link to this item:
Title: Deep learning with self-supervision and uncertainty regularization to count fish in underwater images
Author: Tarling, Penny
Cantor, Mauricio
Clapés i Sintes, Albert
Escalera Guerrero, Sergio
Keywords: Aprenentatge automàtic
Visió per ordinador
Processament digital d'imatges
Peixos marins
Machine learning
Computer vision
Digital image processing
Marine fishes
Issue Date: 4-May-2022
Publisher: Public Library of Science (PLoS)
Abstract: Effective conservation actions require effective population monitoring. However, accurately counting animals in the wild to inform conservation decision-making is difficult. Monitoring populations through image sampling has made data collection cheaper, wide-reaching and less intrusive but created a need to process and analyse this data efficiently. Counting animals from such data is challenging, particularly when densely packed in noisy images. Attempting this manually is slow and expensive, while traditional computer vision methods are limited in their generalisability. Deep learning is the state-of-the-art method for many computer vision tasks, but it has yet to be properly explored to count animals. To this end, we employ deep learning, with a density-based regression approach, to count fish in low-resolution sonar images. We introduce a large dataset of sonar videos, deployed to record wild Lebranche mullet schools (Mugil liza), with a subset of 500 labelled images. We utilise abundant unlabelled data in a self-supervised task to improve the supervised counting task. For the first time in this context, by introducing uncertainty quantification, we improve model training and provide an accompanying measure of prediction uncertainty for more informed biological decision-making. Finally, we demonstrate the generalisability of our proposed counting framework through testing it on a recent benchmark dataset of high-resolution annotated underwater images from varying habitats (DeepFish). From experiments on both contrasting datasets, we demonstrate our network outperforms the few other deep learning models implemented for solving this task. By providing an open-source framework along with training data, our study puts forth an efficient deep learning template for crowd counting aquatic animals thereby contributing effective methods to assess natural populations from the ever-increasing visual data.
Note: Reproducció del document publicat a:
It is part of: PLoS One, 2022, vol. 17, num. 5
Related resource:
ISSN: 1932-6203
Appears in Collections:Articles publicats en revistes (Matemàtiques i Informàtica)

Files in This Item:
File Description SizeFormat 
723322.pdf2.3 MBAdobe PDFView/Open

This item is licensed under a Creative Commons License Creative Commons