Master Thesis - Generation of synthetic faces using deep learning
Passionate about road safety and AI? Join our thesis to enhance driver monitoring systems using synthetic video. Develop realistic datasets to improve detection of driver fatigue and distraction.
Why This Matters
Driver Monitoring Systems (DMS) are critical to enhancing road safety by detecting fatigue, distraction, and other risk factors that lead to accidents. However, gathering large-scale, high-quality driver video data can be challenging due to privacy issues, accessibility limits, and unpredictable driving conditions. This master’s thesis offers you a unique opportunity to address these challenges by developing synthetic video datasets that simulate real-world driving scenarios, such as varying lighting conditions, facial expressions, and driver behavior. Your work will enable more efficient DMS development, contributing to safer driving experiences globally.
Your Role in the Project
In this master thesis project, you will:
- Conduct a literature review to assess the current state-of-the-art and propose an innovative approach to synthetic video generation for DMS.
- Implement algorithms in Python and PyTorch to generate realistic driver monitoring videos.
- Train and evaluate these algorithms using real-world data.
- Document your findings in a thesis report, with the potential to co-author a conference research paper.
What We’re Looking For
We are looking for motivated students who have:
- A background in computer science, electrical engineering, physics engineering, or similar.
- Strong programming skills, particularly in Python.
- A passion for artificial intelligence, machine learning, and synthetic data generation.
- Experience with machine learning frameworks like PyTorch is a bonus.
What’s in it for You?
- Work with cutting-edge AI and synthetic data generation technologies to improve driver safety.
- Collaborate with a team of experts at the forefront of autonomous driving research.
- Gain experience in the fast-evolving field of DMS, contributing to real-world advancements in road safety.
- Build a strong professional network with global industry leaders in autonomous driving technology.
How to Apply & Important Details
This project is suitable for one or two students. If you are applying with a partner, please mention this in your application but submit individual applications, including your CV, motivational letter, and grade transcripts.
- Planned start: January 13, 2025 (with flexibility).
- Final application date: November 15th, 2024 (applications are reviewed on an ongoing basis).
- Duration: 30 ECTS.
For more details or questions about the project, please contact: john.dahl@zenseact.com.
- Competence area
- Opportunities for Students, Graduates & Innovators
- Locations
- Gothenburg, Sweden
- Remote status
- Hybrid
Gothenburg, Sweden
About Zenseact
One purpose, one product
We are a software company focused on transforming car safety. By developing a complete software stack for autonomous driving and advanced driver-assistance systems, we aim to eliminate car accidents and make roads safer for all. Founded by Volvo Cars, Zenseact operates globally, with teams in Gothenburg and Lund, Sweden; Munich, Germany; and Shanghai, China.
Master Thesis - Generation of synthetic faces using deep learning
Passionate about road safety and AI? Join our thesis to enhance driver monitoring systems using synthetic video. Develop realistic datasets to improve detection of driver fatigue and distraction.
Loading application form
Already working at Zenseact?
Let’s recruit together and find your next colleague.