Gesture Spotting in Low-Quality Video with Features Based on Curvature Scale Space

Player´s gesture and action spotting in sports video is a key task in automatic analysis of the video material at a high level. In many sports views, the camera covers a large part of the sports arena, so that the area of player´s region is small, and has large motion. These make the determination of the player´s gestures and actions a challenging task. To overcome these problems, we propose a method based on curvature scale space templates of the player´s silhouette. The use of curvature scale space makes the method robust to noise and our method is robust to significant shape corruption of a part of player´s silhouette. We also propose a new recognition method which is robust to noisy sequence of posture and needs only a small amount of training data, which is essential characteristic for many practical applications