Highlight scene extraction in real time from baseball live video

Abstract

This paper proposes a method to automatically extract highlight scenes from sports (baseball) live video in real time and to allow users to retrieve them. For this purpose, sophisticated speech recognition is employed to convert the speech signal into the text and to extract a group of keywords in real time. Image processing detects, also in real time, the pitcher scenes and extracts pitching sections starting from a pitcher scene and ending at the successive pitcher scene. Highlight scenes are extracted as the pitching sections with the keywords such as home run, two-base hit and three-base hit extracted from speech signals.

A Survey on Visual Content-Based Video Indexing and Retrieval

“…It is noted that most current approaches for scene segmentation exploit the characteristics of specific video domains such as movies, TVs, and news broadcasts [150], [152], [153], for example, using the production rules by which movies or TV shows are composed. The accuracy of scene segmentation is improved, but it is necessary to construct a priori model for each application.…”

Automatic Multilevel Temporal Video Structuring

“…In [17] the detection is based on the concept of logical story units and inter-shot dissimilarity measure. Different approaches [18] proposed combine audio features and low level visual descriptors. In [19] color and motion information are integrated in the decision process.…”

“…A mosaic approach is introduced in [13] that use information specific to some camera setting or physical location to determine boundaries. More recent techniques [18], [19] apply concepts as temporal constraints and visual similarity.…”

The effect of media richness factors on representativeness for video skim

“…Some of which will be included in the skim. However, the segmentation of the video sequence is divided into different types of lengths, such as shot (Li et al, 2006;Le et al, 2008), scene (Ngo et al, 2005;Li et al, 2006;Chasanis et al, 2009), interesting event (Ariki et al, 2003), and the segmentation of complete speech (Taskiran et al, 2001). These authors used different separating schemes to form a basic unit of segmentation.…”