CameramanVis: Where the Camera Should Look

This paper introduces CameramanVis, an interactive visualization system for visualizing correlation between camera angles and player locations for soccer games. The system supports computer vision researchers to browse the soccer data, to identify camera angle and player location patterns, and to identify and compare outliers. The system visualizes camera angle, player locations and their correlation using three multi-form views. The system uses linked-highlighting to coordinate multiple views. In CameramanVis, we propose an intuitive spatial soccer field method to visualize features which are derived from player locations. Some preliminary user feedback suggests that CameramanVis is an effective tool for exploring correlation between camera angle and player locations. For long term sports analysis, we plan to use CameramanVis as a research prototype to investigate camera control, and multi-camera planning.