Temporal video segmentation: detecting the end-of-act in circus performance videos

• Published in: Multimedia tools and applications Vol. 76; no. 1; pp. 1379 - 1401
• Main Authors: Iwan, Lukman H., Thom, James A.
• Format: Journal Article
• Language: English
• Published: New York Springer US 2017; Springer Nature B.V
• Subjects: Analysis; Archives & records; Artificial intelligence; Cameras; Circuses; Computer Communication Networks; Computer Science; Content analysis; Data Structures and Information Theory; Digital video; Flashlights; Human performance; Image segmentation; Motion pictures; Multimedia; Multimedia computer applications; Multimedia Information Systems; Performing arts; Recall; Segments; Shot; Sound; Special Purpose and Application-Based Systems; Streams; Studies; Television programs; Image comparison; Sound detection; Audio classification; Machine learning; Image sequence analysis; Video temporal segmentation; Performing arts
• ISSN: 1380-7501; 1573-7721
• DOI: 10.1007/s11042-015-3130-3

The segmentation into acts of a circus performance video is challenging as the content has similar characteristics to other performance videos but is quite different from movies, TV programs, and home videos. Segmentation is useful as a long duration circus show usually contains several shorter segments that are acts. We propose a new method for detecting end-of-act within circus performance videos. Unlike other temporal video segmentation methods, this method does not rely on shot detection techniques and uses audio and video content analysis separately. First is audio content analysis, for detecting applause on the circus audio stream. Second is image analysis. The applause is further analyzed to test whether this applause occurs at the end-of-act. An end-of-act is detected, if the image(s) before and after the applause are different or there are black frames just after the applause. Otherwise, it is not the end-of-act. The experiment to detect end-of-act on Circus Oz performance videos achieved a 92.27 % recall and 49.05 % precision, providing useful clues that assist human annotators to segment circus video into acts.