Multi-Scale Action Recognition in Squash Match

Algorithms for human action recognition usually observe human motion only on particular level of detail. This approach requires complex algorithms to match the complexity of motion. High recognition rates are possible, when actions are distinct and clearly visible. However, this is not the case in many practical applications. To solve this we explore the possibility of developing more general action recognition algorithms by systematic reduction of complexity of human motion. The key to reducing complexity is in systematic decomposition of human motion to different scales, each representing different level of motion detail. Our approach was tested in the sports domain, on a particular problem of detecting the action of athlete hitting the ball with a racquet in the game of squash. Video recordings of actual tournament match were used, and manual annotations were provided by squash expert as a ground truth.