Attractive Events Detection in Soccer Videos Based on Identification of Shots
Tian Fang, Shi Ping · Advances in intelligent systems research/Advances in Intelligent Systems Research · 2013
The low-level feature based analysis method focuses on video and audio characteristics in a clip.The commonly used video characters include color and texture information of a frame.D. Yow, et al. [1] detected appealing events in a Abstr act The necessity of efficient identification and classification of shots in a soccer game ascends with the increasing popularity and quantity of soccer videos.This paper proposes an effective and real-time identifying system for attractive events, namely shooting shots in soccer video clips.Instead of directly accessing shooting shots, this system identifies close-up shots and audience shots, which generally accompany with shooting shots.Field shots are concerned in this system as well, since this sort of shots is frequently used to describe formations of a team, indicating its strategy.This system begins with the selection of key frames.The ratio of soccer pitch color pixels in the key frame is then calculated to detect long shots.By counting the amount of edge pixels, the differentiation between close-up shots and audience shots will be completed.In order to increase the accuracy, the approach of Key Region Detection is introduced.This innovative method is proven by experiments to be comparatively precise.Experimental results validate the effectiveness of this system.Keywor ds: field shots, close-up shots, audience shots, key frame. Intr oductionThe abstraction of soccer video enjoys high level of popularity, due to its ability to satisfy the requirements of audience, academic researchers and commercial campaigners.Approaches of soccer video abstraction could be generally divided into two groups: the low-level feature based analysis method and the high-level feature based analysis method.