Techniques for automatic video content derivation

In this paper, we focus on the use of three different techniques that support automatic derivation of video content from raw video data, namely, a spatio-temporal rule-based method, hidden Markov models, and dynamic Bayesian networks. These techniques are validated in the particular domain of tennis and Formula 1 race videos. We present the experimental results for the detection of events such as net-playing, rally, service. and forehand stroke among others in the Tennis domain, as well as excited speech, start, fly-out, passing, and highlights in the Formula 1 domain.

• Type: Conference
• Year: 2003
• Where: ICIP
• Authors: Milan Petkovic, Vojkan Mihajlovic, Willem Jonker
• Keywords: Dynamic Bayesian Networks, ICIP 2003, Image Processing, Particular Domain, Raw Video Data, Spatio-temporal Rule-based Method, Tennis Domain