[HTML][HTML] Semi-supervised and weakly-supervised deep neural networks and dataset for fish detection in turbid underwater videos

M Jahanbakht, MR Azghadi, NJ Waltham - Ecological Informatics, 2023 - Elsevier
Fish are key members of marine ecosystems, and they have a significant share in the
healthy human diet. Besides, fish abundance is an excellent indicator of water quality, as …

MFLD-net: a lightweight deep learning network for fish morphometry using landmark detection

A Saleh, D Jones, D Jerry, MR Azghadi - Aquatic Ecology, 2023 - Springer
Monitoring the morphological traits of farmed fish is pivotal in understanding growth,
estimating yield, artificial breeding, and population-based investigations. Currently …

How to track and segment fish without human annotations: a self-supervised deep learning approach

A Saleh, M Sheaves, D Jerry… - Pattern Analysis and …, 2024 - Springer
Tracking fish movements and sizes of fish is crucial to understanding their ecology and
behaviour. Knowing where fish migrate, how they interact with their environment, and how …

A novel hardware solution for efficient approximate fuzzy image edge detection

F Behbahani, MKQ Jooq, MH Moaiyeri… - IEEE Transactions on …, 2024 - ieeexplore.ieee.org
In practical fuzzy applications, such as image processing, the utilization of precise models in
hardware may not be the most efficient approach due to increased energy consumption and …

Feature fusion of body surface and motion-based instance segmentation for high-density fish in industrial aquaculture

Z Ye, J Zhou, B Ji, Y Zhang, Z Peng, W Ni, S Zhu… - Aquaculture …, 2024 - Springer
Fish phenoty** serves as a cornerstone for refined management and sustainable
development in industrialized aquaculture. High-precision instance segmentation for high …

A New Workflow for Instance Segmentation of Fish with YOLO

J Zhang, Y Wang - Journal of Marine Science and Engineering, 2024 - mdpi.com
The application of deep-learning technology for marine fishery resource investigation is still
in its infancy stage. In this study, we applied YOLOv5 and YOLOv8 methods to identify and …

Edge computing based real-time Nephrops (Nephrops norvegicus) catch estimation in demersal trawls using object detection models

E Avsar, JP Feekings, LA Krag - Scientific Reports, 2024 - nature.com
In demersal trawl fisheries, the unavailability of the catch information until the end of the
catching process is a drawback, leading to seabed impacts, bycatches and reducing the …

Novel use of deep neural networks on photographic identification of epaulette sharks (Hemiscyllium ocellatum) across life stages

M Lonati, M Jahanbakht, D Atkins… - Journal of Fish …, 2024 - Wiley Online Library
Photographic identification (photo ID) is an established method that is used to count animals
and track individuals' movements. This method performs well with some species of …

[HTML][HTML] Region Segmentation of Images Based on a Raster-Scan Paradigm

L Lukač, A Nerat, D Strnad, Š Horvat… - Journal of Sensor and …, 2024 - mdpi.com
This paper introduces a new method for the region segmentation of images. The approach is
based on the raster-scan paradigm and builds the segments incrementally. The pixels are …

A lightweight Transformer-based model for fish landmark detection

A Saleh, D Jones, D Jerry, MR Azghadi - arxiv preprint arxiv:2209.05777, 2022 - arxiv.org
Transformer-based models, such as the Vision Transformer (ViT), can outperform
onvolutional Neural Networks (CNNs) in some vision tasks when there is sufficient training …