Theatrical Lighting Design plays a crucial role in enhancing audience experiences and emotions during performances. However, lighting concepts are often developed from scratch, with limited interaction from previous performances and automation systems. Recent advancements in Deep-Learning and Natural Language Processing (NLP) offer the ability to assist with the automation of theatrical lighting design, significantly decreasing the time taken to create a production. This study conducts research into the utilisation of Generative Adversarial Networks (GANs) to create new designs, as well as NLP for script understanding.
This study also proposes a new technological framework, which utilises the identified methods to create a set of designs from an unmarked script. In addition, the solution offers the ability to control physical lighting infrastructure through the widely adopted ANSI E1.11 lighting standard. A method is also proposed for controlling Art-Net equipment over a REST-based API. The study finally discusses future research, and identifies potential methods for adapting the framework for various other lighting industries.
PLEASE NOTE: You must be a member of the University of Lincoln to be able to view this dissertation. Please log in here.