Master's Thesis Student (30 hp) in Computer Vision - Fault Detection Using AI

Scania is leading the shift towards a sustainable transport system, creating mobility solutions that benefit businesses, society, and the environment. As part of this mission, our department plays a vital role in ensuring that vehicles are maintained, diagnosed, and upgraded in a high-quality, cost-effective manner.

About Us
We are an innovative, driven, and highly skilled team, passionate about leveraging AI for real-world applications. Our team consists of Data Scientists, Machine Learning Engineers, Data Engineers, and Cloud Engineers, all collaborating to develop state-of-the-art AI models. Our achievements have already positioned us as a leader in AI and data-driven innovation, and we are now looking to further advance our research and development by welcoming a Master’s Thesis Student to explore novel AI solutions in computer vision.

Thesis Project Overview
In this master’s thesis, you will explore the use of computer vision to detect faulty parts, cracks, leakages, and other anomalies in vehicle components, directly supporting Scania's commitment to vehicle quality and sustainability.

Your research will focus on developing, implementing, and evaluating advanced object detection techniques for fault detection in vehicle maintenance contexts. Key areas of focus will include:

• Developing and fine-tuning models (e.g., YOLO) for detecting defects such as cracks, leaks, or wear in vehicle parts.
• Exploring Vision-Language Models (VLMs) as a means of identifying and describing deviations in component conditions.
• Optimizing data collection and annotation processes, focusing on improving training data quality for real-time applications.

What You Will Learn

• Advanced object detection methodologies and their application in real-time environments.
• Handling and processing large-scale video streams and images for training AI models.
• Exploration of Vision-Language Models for automatic description and categorization of defects.
• Working in an Agile environment and collaborating with multidisciplinary teams within Scania.

Our Ideal Candidate
We are seeking a Master's student in Machine Learning, Data Science, Computer Vision, or a related field. You should possess knowledge or experience in:

• Python programming and cloud services like AWS.
• Machine learning algorithms and deep learning concepts.
• Image and video processing techniques, especially for object detection.
• An interest in applying AI to detect anomalies such as cracks, leakages, or wear in vehicle parts.

A structured, communicative, and collaborative mindset will ensure you thrive in our supportive and dynamic team. Fluency in English is required.
 

What We Offer
At Scania, you’ll find an inspiring workplace with ample opportunities for personal and professional growth. You’ll be supported throughout your thesis journey by experienced colleagues, working closely with cutting-edge technology in a real-world setting.

Contact Information
For more details about this thesis opportunity, please contact supervisor Olof Steinert, Strategic Product Planning and Advanced Analytics (EYSFS), olof.steinert@scania.com

Application
Number of students: 1-2 (you can apply separately or together)
Start date: Spring 2025
Estimated time needed: 20 weeks, Full-time

To apply, please send your CV, a cover letter detailing your interest in the project, and any relevant certificates. Applications will be reviewed on a rolling basis, with a final deadline of  2024-11-24.
 

A background check might be conducted for this position. We are conducting interviews continuously and may close the recruitment earlier than the date specified.     

Master’s Thesis Student (30 hp) in Computer Vision – Fault Detection Using AI