Detection and description of human running behaviour in sports video multimedia database

Abstract

Motion description is an example of high-level video processing. It is attracting increasing interest in the computer vision community, due to its wide spectrum of applications. In such applications as multimedia database systems, motion descriptors act as a high-level query tool. We propose a periodic motion detection and description algorithm. We demonstrate that the descriptor extracted by the algorithm can characterise the human running behaviour. It can also serve as a basis for the classification of the human running activity. Experimental results based on Barcelona Olympic Games image sequences show the benefits of the proposed algorithm.