Smartbay Marine Species Object Detection Training dataset

Data preprocessing The following pre-processing was applied to each image on the Roboflow platform: Auto-orientation of pixel data (with EXIF-orientation stripping) The following augmentation was applied to create 3 versions of each source image: Random brigthness adjustment of between -15 and +15 percent Random exposure adjustment of between -10 and +10 percent Random Gaussian blur of between 0 and 2.5 pixels Salt and pepper noise was applied to 0.1 percent of pixels Data splitting The initial training dataset was split as follows: 88% Training Set, 8%  Validation Set and 4% Test Set. Data labelling Aurelia aurita, Belone belone, Chelidonichthys lucerna, Chelon auratus, Chelon labrosus, Conger conger, Ctenolabrus rupestris, Cyclopterus lumpus, Dicentrarchus labrax, Entelurus aequoreus, Eutrigla gurnardus, Hippocampus guttulatus, Labrus bergylta, Labrus mixtus, Lophius_piscatorius, Merlangius merlangus, Mullus barbatus, Mullus surmuletus, Mustelus asterias, Parablennius gattorugine, Platichthys flesus, Pleuronectes platessa, Pollachius pollachius, Pomatoschistus pictus, Raja clavata, Raja undulata, Scomber scombrus, Scophthalmus maximus, Scyliorhinus canicula, Solea solea, Spondyliosoma cantharus, Squalus acanthias, Squatina squatina, Symphodus melops, Trisopterus luscus, Zeugopterus punctatus Parameters NA Data sources The imagery used in this training dataset consists of image frame captures from the Smartbay video Archive files, CC-BY imagery from the www.minka-sdg.org website and images taken by Eva Cullen in the "Galway Atlantaquaria" Aquarium in Galway, Ireland. Data quality Video frames were extracted from Smart Observatory and Galway Atlantaquaria video recordings for annotation usign CVAT and also ffmpeg. Target species CC-BY images were also downloaded from minka-sdg.org using a python minka-downloader script (https://github.com/obsea-upc/minka-downloader) Useful images were manually selected and annotated by the bursor students and collated into training datasets in Roboflow.   Data resizing The images are not resized. During the yolov8 training process the images are resized to 640x640 by default. Spatial coverage Smartbay Observatory Spiddal, Galway Bay, Ireland Galway Atlantaquaria, Seapoint Promenade Galway H91 T2FD, Ireland Minka-sdg.org Sample Imagery from Spanish and Portuguese waters  Contact information Data.Requests@Marine.ie