There is provided a system and method for automated video processing of an input video signal using tracking of a single moveable bilaterally-targeted game-object involved in a team-based sporting event. The method includes: receiving the input video signal; analyzing the input video signal for one or more contextual feature maps; coding the one or more contextual feature maps; using a trained machine learning model, determining estimated coordinates of the single moveable bilaterally-targeted game-object for each group of one or more frames of the input video signal, the machine learning model receiving the coded one or more contextual feature maps as features to the machine learning model, the machine learning model trained using training data including a plurality of previously recorded training video signals each with associated coded one or more contextual feature maps, the training data further including ground truth data including screen coordinates of the single moveable bilaterally-targeted game-object.