Audio as a support to scene change detection and characterization of video sequences

Saraceno, C.; Leonardi, Riccardo

doi:10.1109/icassp.1997.595320

Cited by 53 publications

(21 citation statements)

References 7 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…Numerous algorithms have been created to detect the presence of specific objects in a video [5], automatically segment a film into sub-scenes [18,37] and extract symbolic information such as annotations [9] or jersey numbers in sport videos [45]. Signal processing of audio streams also constitutes an established and active research field within computer science.…”

Section: Player Experience As Output Streamsmentioning

confidence: 99%

Feedback-based gameplay metrics

Marczak

Vught

Schott

et al. 2012

Proceedings of the 8th Australasian Conference on Interactive Entertainment: Playing the System

View full text Add to dashboard Cite

The application of gameplay metrics to empirically express a player's engagement with the game system has become more appealing to a broader range of researchers beyond the computer sciences. Within game studies, the appropriation and use of gameplay metrics not only further shifts these methods beyond formalized user testing (e.g. with the aim of product improvement) but creates a demand for a more universal approach to game metric extraction that can be applied to a wider range of games and account for different social science research agendas. Set in the context of a study into player experiences with participants aged 14-16 years of age, a method of articulating and identifying key moments of game-play pertinent to an analysis of experience with simulated violence was required [38]. This paper describes a pragmatic solution to the need to study a range of games that were determined not by the researchers but the study's participants. The solution exploits and examines the audio-video feedbacks presented to the player as part of their engagement with a game system. This paper broadly outlines this mode of metric extraction and its application to research that seeks to understand the nature of engagement and player motivations across a mixed methodology approach.

show abstract

Section: Player Experience As Output Streamsmentioning

confidence: 99%

Feedback-based gameplay metrics

Marczak

Vught

Schott

et al. 2012

Proceedings of the 8th Australasian Conference on Interactive Entertainment: Playing the System

View full text Add to dashboard Cite

show abstract

“…The Audio and motion features have been used to improve shot boundary detection. Classification of audio according to silence, speech, music, or noise and use this information to verify shot boundaries hypothesized by image-based features [5]. An algorithm for shot clustering using speaker identification is presented in [6].…”

Section: Introductionmentioning

confidence: 99%

A Shot Boundary Detection Technique Based on Local Color Moments in YCbCr Color Space

Angadi¹,

Naik²

2012

Computer Science &Amp; Information Technology (CS &Amp; IT)

View full text Add to dashboard Cite

show abstract

“…Recently there has been interest in using both audio and visual information for scene change detection. In [3], different audio classes are detected sequentially, and this information is later combined with the probability value for a visual cut detection. In [4], scene breaks are detected as audio-visual breaks, where each break is based on dissimilarity index values calculated for audio, color and motion features.…”

Section: Introductionmentioning

confidence: 99%

Detection of Documentary Scene Changes by Audio-Visual Fusion

Velivelli¹,

Ngo

Huang³

2003

Lecture Notes in Computer Science

View full text Add to dashboard Cite

Abstract. The concept of a documentary scene was inferred from the audio-visual characteristics of certain documentary videos. It was observed that the amount of information from the visual component alone was not enough to convey a semantic context to most portions of these videos, but a joint observation of the visual component and the audio component conveyed a better semantic context. From the observations that we made on the video data, we generated an audio score and a visual score. We later generated a weighted audio-visual score within an interval and adaptively expanded or shrunk this interval until we found a local maximum score value. The video ultimately will be divided into a set of intervals that correspond to the documentary scenes in the video. After we obtained a set of documentary scenes, we made a check for any redundant detections.

show abstract

Audio as a support to scene change detection and characterization of video sequences

Cited by 53 publications

References 7 publications

Feedback-based gameplay metrics

Feedback-based gameplay metrics

A Shot Boundary Detection Technique Based on Local Color Moments in YCbCr Color Space

Detection of Documentary Scene Changes by Audio-Visual Fusion

Contact Info

Product

Resources

About