 |
Abstract: Development of an Automated Camera Control System for Virtual Production Using Real-Time Person Tracking [DE]
Lars Hötte, Development of an Automated Camera Control System for Virtual Production Using Real-Time Person Tracking, Hochschule Düsseldorf - University of Applied Sciences, Bachelor thesis, 24.02.2026.
The increasing complexity of virtual production environments combined with a shortage
of skilled professionals poses significant challenges for modern media productions. This
thesis presents the development and evaluation of an automated camera control system
for virtual production using real-time person tracking in the virtual studio at Düsseldorf
University of Applied Sciences. Following a comprehensive analysis of the state of the art,
the theoretical foundations of professional camera operation are developed. Cinematographic
design principles such as shot sizes, framing, and image composition are systematically
examined and formalized for algorithmic implementation. Based on this foundation, a system
was developed that receives tracking data via motion capture technology and translates
it into intelligent camera movements while considering design fundamentals. Middleware
handles hardware-level control of the robotics, while a script implements the cinematographic
logic. The system supports tracking of up to two persons, accounts for virtual objects,
and enables intuitive operation via external control software. The evaluation by industry
experts confirms the successful translation of cinematographic rules into algorithmic control.
The developed system represents a functional proof of concept, though it identifies further
optimization potential regarding movement harmonization and broadcast-quality imagery.
This work demonstrates the feasibility of rule-based automated camera operation and provides
a foundation for further research in the field of intelligent production systems.
Keywords:
Camera robotics, automation, image composition, virtual production, person
tracking, cinematography, motion capture, OSC protocol
Supervisor:
Prof. Jens Herder, Dr. Eng./Univ. of Tsukuba
Prof. Dr.-Ing. Thomas Bonse
Location:
The research took place at the Virtual Sets and Virtual Environments Laboratory.
Video
Tools and Credits
- Viz Artist 5, Viz Arc und Tracking Hub Software von Vizrt
- Captury Live - Captury - a DARI MOTION Company
- Virtuelles Studio der Hochschule Düsseldorf
|
|
