Annotated Underwater Images of Round Goby (Neogobius melanostomus) in the Great Lakes from 2020-2023 to Support Deep Learning and Fisheries Assessment

This dataset contains more than 37,000 high-resolution images of natural lake bottom habitats containing round goby (Neogobius melanostomus) captured by autonomous underwater vehicles (AUVs).  Round goby are invasive to the Laurentian Great Lakes, but are an important prey item for economically valuable predators, and thus of interest to managers.  Individual round goby within each image were manually traced to create binary masks and JSON files to support training and validation of deep learning algorithms to automatically detect round goby.  The data were collected in Lakes Michigan, Huron, and Ontario between June to September, 2020, 2021, 2022, and 2023 using two different camera systems integrated into L3Harris-OceanServer Iver3 AUVs.  Each image is attributed with information about its latitude, longitude, depth, altitude, and other values recorded by the AUVs’ on-board sensors and recorded in a metadata file (RoundGoby_Dataset_Metadata.csv).  To ensure the quality and accuracy of the data, the manual labels were inspected by three independent observers to verify their correctness, ensuring that no non-fish objects were mistakenly labeled as fish, and to exclude fish that were not round goby, background substrates, mussels, and fish-like objects.  The data are organized into zip files, each corresponding to different collection months, years, and camera systems.  Zip files contain (i) raw RGB images, (ii) ground truth binary masks, (iii) JSON files with polygon coordinates, (iv) bounding box coordinates in pixels, and (v) bounding box coordinates in YOLO format to support algorithm development.  Collectively, this dataset provides a comprehensive resource for automating the detection and sizing of round goby in color images.