Long-term High Resolution Image Dataset of Antarctic Coastal Benthic Fauna

• Published in: Scientific Data
• Main Authors: Marini, Simone, Bonofiglio, Federico, Corgnati, Lorenzo Paolo, Bordone, Andrea, Schiaparelli, Stefano, Peirano, Andrea
• Format: Text
• Language: English
• Published: Nature Publishing Group UK 2022
• Subjects: Data Descriptor; Antarctic; The Antarctic; Antarc*; Antarctica
• Online Access: http://www.ncbi.nlm.nih.gov/pmc/articles/PMC9719491/; http://www.ncbi.nlm.nih.gov/pubmed/36463241; https://doi.org/10.1038/s41597-022-01865-7

Antarctica is a remote place, the continent is covered by ice and its surrounding coastal areas are frozen for the majority of the year. Due to its peculiarity the observation of the underwater organisms is particularly difficult, complicated by logistic factors. We present a long-term dataset consisting of 755 images acquired by using a non-invasive, autonomous imaging device and encompassing both the Antarctic daylight and dark periods, including the corresponding transition phases. All images have the same field of view showing the benthic fauna and part of the water column above, including fishes present in the monitored period. All the images are manually annotated after a visual inspection performed by expert biologists. The extended monitoring period and the annotated images make the dataset a valuable benchmark suitable for studying the dynamics of the long-term Antarctic underwater fauna as well as for developing and testing algorithms for automated image analysis focused on the recognition and classification of the Antarctic organisms and the automated analysis of their long-term dynamics.