Computer Vision News - March 2021

232 Artificial Intelligence Computer Vision News has found great new stories, written somewhere else by somebody else. We share them with you, adding a short comment. Enjoy! A I S P O T L I G H T N E W S Artificial Intelligence Software Detects Ocean Plastics from the Air Let’s start with a lovely project coming from Barcelona and called MARLIT . Young researchers from Universitat de Barcelona have developed an AI to detect and quantify marine litter through aerial imagery. We talk about literally millions of tons every year. Help! Odei García-Garin, Morgana Vighi and their co-authors hope to improve on current methods of tracking the litter ’s distribution, by observing from planes and boats. For this, deep learning neural networks have been trained on more than 3,800 aerial images of the Mediterranean to be able to reliably detect and quantify plastic floating on the surface. Read More Beyond the Unknown: Applications of Artificial Intelligence in Space AI and its wide range of applications are contributing to space industry use-cases too! Image processing algorithm chart galaxies, supernovas, stars, blackholes and cosmic events; images from the Hubble Space Telescope are used to simulate galaxy formation and classify them using deep learning. NASA and Google have teamed up to train AI algorithms to sift through the data from the Kepler mission to look for signals from an exoplanet crossing in front of its parent star. Thanks to AI, satellite imagery provides new insights and (believe it or not) a Robonaut is going to replace astronauts on the riskiest tasks. Read More Artificial Intelligence in Longevity Medicine Apparently, understanding the aging process requires monitoring of millions of parameters in many different types of datasets that change very slowly during the human life , especially in genetically and socio-culturally diverse populations . AI can be a precious help in the task of finding complex patterns in large volumes of longitudinal data. Deep Learning contributes to calculate estimates of an individual’s biological age state based on data extracted from routine blood analyses. In this way, clinicians could precisely assess and monitor individual health risks and tailor appropriate interventions or changes in lifestyle for each specific patient. Read More