Down-looking Images of Lake Trout (Salvelinus namaycush) and Round Goby (Neogobius melanostomus) to Support Automated Biomass Estimation
August 14, 2024
These data include in situ images of lake trout (Salvelinus namaycush) and round goby (Neogobius melanostomus) collected by an autonomous underwater vehicle (AUV) in Lakes Michigan and Superior in 2020 and 2021 and laboratory images of round goby collected by a GoPro in 2021. These images were collected and labeled to train and validate an algorithm for automated fish sizing and biomass estimation. The dataset includes original images, ground truth binary masks, where the designated benthic fish is represented by white pixels and the background by black pixels, and calibration images to correct any type of distortion on the imagery if needed.
Citation Information
Publication Year | 2024 |
---|---|
Title | Down-looking Images of Lake Trout (Salvelinus namaycush) and Round Goby (Neogobius melanostomus) to Support Automated Biomass Estimation |
DOI | 10.5066/P9E1DTYB |
Authors | Shadi (Contractor) Moradi, Peter C Esselman, Nicholas J Yeager, Jennifer M Morris, Joseph (Contractor) K Geisz |
Product Type | Data Release |
Record Source | USGS Asset Identifier Service (AIS) |
USGS Organization | Great Lakes Science Center |
Rights | This work is marked with CC0 1.0 Universal |
Related
A transferable approach for quantifying benthic fish sizes and densities in annotated underwater images
1. Benthic fishes are a common target of scientific monitoring but are difficult to quantify because of their close association to bottom habitats that are hard to access. Advances in image-acquisition technologies, machine vision, and deep learning have made capturing and quantifying fishes with cameras increasingly feasible. We present a method and open-source software called...
Authors
Peter C. Esselman, Shadi Moradi, Joseph K. Geisz, Christopher Roussi
Related
A transferable approach for quantifying benthic fish sizes and densities in annotated underwater images
1. Benthic fishes are a common target of scientific monitoring but are difficult to quantify because of their close association to bottom habitats that are hard to access. Advances in image-acquisition technologies, machine vision, and deep learning have made capturing and quantifying fishes with cameras increasingly feasible. We present a method and open-source software called...
Authors
Peter C. Esselman, Shadi Moradi, Joseph K. Geisz, Christopher Roussi