Vertical Axis Detection for Sport Video Analytics

When processing video, it is normally assumed that cameras are vertically oriented such that people appear upright, which helps simplify subsequent processing such as person detection. In real situations, due to the need to provide maximum coverage of the viewing space, cameras are usually placed with arbitrary orientations so the apparent vertical axis of the videos captured may not correspond to the true vertical direction of the captured scene. To rectify this situation, we propose a classification-based system, which normalizes the video to compensate for the camera orientation. We demonstrate the performance of the system for outdoor sports video. Our system works as follows: from an arbitrary set of sports videos, we first automatically create a training/testing image dataset, in which players have various orientations. Our classifier is a stacked autoencoder connected to a softmax output layer, which is trained using this dataset to estimate the orientation of players. The orientation of an input video is normalized according to the orientations of player patches, whose angles of orientation are estimated by above trained classifier. Experiments conducted on a hockey field video dataset show that the proposed system is able to estimate the true vertical axis of an input video accurately.