Volume : 2, Issue : 2, February - 2013

A Literature Review on Event Detection Based Video Summarization

Bhavsar Barkha Harishkumar, Devang Pandya

Abstract :

Video summaries provide condensed and succinct representation of the content of a video stream through a combination of still images, video segments, graphical representation and textual descriptors. The translation of low level content in video sequences into high level semantic concepts is a research topic that has received much interest in recent years. We propose fully automatic and computationally efficient framework for analysis and summarization of soccer videos using event based features. The processing framework includes some novel low–level soccer video processing algorithms, such as dominant color detection, robust shot boundary detection, and shot classification as well as some higher level algorithm such as corner event detection, referee detection and penalty box detection. Here we have presented the algorithm for parsing the structure of produced soccer programs. We have used different methods such as morphological image processing method which is used for extracting the interested area, which is in our case corner of the ground, segmentation for detecting the corner vertical pillars, which are extracted through Canny Edge Detection method. Different mathematical model such as HMM and Hough transformation are used for the purpose of getting efficient and accurate result.