Raw images, annotations, and vvipr code archive to support 'Evaluating thermal and color sensors for automating detection of penguins and pinnipeds in images collected with an unoccupied aerial system''

<p>Images, annotations,&nbsp;and code archived here were used in the paper &quot;Evaluating a machine learning approach to detect penguins and pinnipeds in thermal and color images collected with an unoccupied aerial system&quot; submitted for publication in Drones. The files&nbsp;contain raw thermal and color images of aggregations of gentoo (<em>Pygoscelis papua</em>) and chinstrap&nbsp; (<em>P. antarcticus</em>) penguins and Antarctic fur seals (<em>Arctocephalus gazella</em>). All images were collected with the Flir DuoPro R camera (Teledyne FLIR LLC, Wilsonville, OR, U.S.A.), carried into flight under an APH-28 hexacopter (Aerial Imaging Solutions, LLC, Old Lyme, CT, U<strong>.</strong>S<strong>.</strong>A<strong>.)</strong>&nbsp;at Cape Shirreff, Livingston Island, Antarctica (60.79 &deg;W, 62.46 &deg;S), during the austral summer of 2019-20. All aerial surveys occurred under the Marine Mammal Protection Act Permit No. 20599 granted by the Office of Protected Resources/National Marine Fisheries Service, the Antarctic Conservation Act Permit No. 2017-012, NMFS-SWFSC Institutional Animal Care and Use Committee Permit No. SWPI 2014-03R, and all domestic and international UAS flight regulations. The annotations of the images were conducted using VIAME desktop software (v 0.16.1 or later;<a href="https://github.com/VIAME/VIAME">https://github.com/VIAME</a>) or the online using the DIVE interface (https://viame.kitware.com/). Model results were assessed with the vvipr code (v.0.3.2), archived here&nbsp;and available online (https://github.com/us-amlr/vvipr/releases/tag/v0.3.2).</p> <p>&nbsp;</p>