A genetically generated drone A/V composition using video analysis as a 'disturbance factor' to the fitness function

Tristan McGuire, Giuseppe Torre

Research output: Chapter in Book/Report/Conference proceedingConference contributionpeer-review

Abstract

This paper discusses the development of an audio-visual composition based on genetic algorithms strategies. The genetic algorithm's fitness function dynamically adjusts the optimisation targets linked to the mechanisms responsible for the generating of drone soundscapes. The fitness function continuously changes based on the results of an analysis of the visual elements of the artwork thus acting as disturbance factor. In doing so, the audio material never achieves full optimisation and constantly shapes itself. The paper offers both a technical and aesthetic analysis of the development of the composition.

Original languageEnglish
Title of host publication10th AAAI Conference on Artificial Intelligence and Interactive Digital Entertainment
PublisherAI Access Foundation
Pages30-34
Number of pages5
VolumeWS-14-18
ISBN (Electronic)978-157735687-5
DOIs
Publication statusPublished - 2014
Event10th AAAI Conference on Artificial Intelligence and Interactive Digital Entertainment, AIIDE 2014 - Raleigh, United States
Duration: 4 Oct 2014 → …

Conference

Conference10th AAAI Conference on Artificial Intelligence and Interactive Digital Entertainment, AIIDE 2014
Country/TerritoryUnited States
CityRaleigh
Period4/10/14 → …

Fingerprint

Dive into the research topics of 'A genetically generated drone A/V composition using video analysis as a 'disturbance factor' to the fitness function'. Together they form a unique fingerprint.

Cite this