首页|Reports Outline Robotics and Automation Study Results from University of the Sou th Toulon-Var (Subject-independent Diver Gesture Classification Using Upper Limb Movement)
Reports Outline Robotics and Automation Study Results from University of the Sou th Toulon-Var (Subject-independent Diver Gesture Classification Using Upper Limb Movement)
扫码查看
点击上方二维码区域，可以放大扫码查看
原文链接
NETL
NSTL
By a News Reporter-Staff News Editor at Robotics & Machine Learning DailyNews Daily News-A new study on Robotics - Robotics and Automation is now available. Accordingto news reporting originating in La Gard e, France, by NewsRx journalists, research stated, "This letterfocuses on categ orizing diver gestures by analyzing angle features extracted from the movements of theirupper limbs without exploiting information encoded by the hands, as is generally the case in the literature.Our approach is intended to be as generic as possible, in order to enable gesture recognition, whatever thediver's equipm ent, and to use the usual signs used by divers."Funders for this research include Region Provence-Alpes-Cote d'Azur, Notilo Plus /Delair Marine Company.The news reporters obtained a quote from the research from the University of the South Toulon-Var,"New shallow RNN pipelines based on LSTM and GRU are proposed and evaluated with regard to a DTWKNNdeterministic baseline. For underwater g estures, a preliminary energy-based SVM separation stageis introduced to distin guish between one-arm and two-arm gestures. All classification strategies are validated using a leave-one-out protocol on a motion capture dataset comprising 14 divers performing 11distinct gestures. The database was collected in-house wit h a total of 1078 individual gesture recordings.The SVM separation stage clearl y improves the results, from 15% for DTW-KNN to 5% f or RNNs."
La GardeFranceEuropeRobotics and A utomationRoboticsUniversity of the South Toulon-Var
NETL
NSTL
