Feature extraction of a synchronized swimmer from aerial and underwater videos

Abstract

Vision-based feature extraction of a synchronized swimmer doing figures was done in hopes of correcting and improving synchronized swimmer’s ability to do figures. In gathering data, two cameras were used. One was stationed at a calculated distance above the water, and the other camera was placed underwater directly above the other camera. In this article feature extraction of the three figures synchronized swimming, Porpoise, Neptunus, and Ballerina, and the ssential image processing techniques used to combine the two perspectives together were covered. The results showed that empirically extracted threshold limits for the skin region produced smooth feature extracted foregrounds.