The Job

Master Thesis: Computer Vision for Recognition of Manual Assembly Activities

Teknik, data och digitalt · Mjukvaru- och webbutveckling · Mjukvaruutveckling · Datavetenskap

Gå med för uppdateringar

I korthet

This Master Thesis project at Volvo Penta in Vara, Sweden, focuses on developing a Computer Vision solution to automatically identify completed manual assembly activities. The project involves designing, evaluating, and comparing relevant computer vision and machine learning methods suitable for an industrial production environment.

Ansvarsområden

  • Investigate how a Computer Vision-based solution can identify completed work activities at a manual assembly station.
  • Design and evaluate a concept for using image or video data to identify defined assembly activities.
  • Evaluate and compare relevant Computer Vision and neural-network-based methods for analysis.
  • Collect image and/or video data from the selected workstation at Volvo Penta’s Vara Factory.
  • Define assembly activities to be identified and annotate relevant objects, activities, or process states.
  • Create training, validation, and test datasets.
  • Observe variations in how activities are performed.

Krav

  • Suitable for Master’s thesis work.
  • Students in Computer Science, Artificial Intelligence, Machine Learning, Data Science, Automation, Robotics, Mechatronics, Electrical Engineering, or related fields.
  • Ability to design and evaluate a concept using image or video data.
  • Familiarity with relevant Computer Vision and neural-network-based methods.
  • Consideration of theoretical model accuracy and suitability for a real industrial environment.
  • Experience with data collection, annotation, and dataset creation.
  • Understanding of potential evaluation criteria including robustness, inference time, computational requirements, camera positioning, lighting, occlusion, and integration with existing systems.

Önskade kvalifikationer

  • Focus on selecting and motivating suitable technical approaches.
  • Empirical evaluation of performance for the selected industrial use case.
  • Not limited from the beginning to a specific neural network architecture.
  • Final outcome should consist of both a technical evaluation and a recommendation.
  • Potential to integrate with existing production and automation systems.

Förmåner

  • Opportunity to shape sustainable transport and infrastructure solutions for the future.
  • Work with next-gen technologies and collaborative teams.
  • Gain expertise in analyzing image or video data from an assembly station.
  • Potential to complement existing production and automation systems.
  • Hands-on experience at Volvo Penta’s Vara Factory.
  • Opportunity to work with some of the sharpest and most creative brains in the field.
  • Be part of a global and diverse team of highly skilled professionals.
#computer vision#machine learning#assembly#manufacturing#thesis#master thesis#automation#robotics#data science#artificial intelligence
Volvo Group Logo

Företag

Volvo Group

Publicerade jobb

för 1 dag sedan

Upphör

om 1 månad

Anställningstyp

Praktik

Arbetsform

På plats

Erfarenhetsnivå

Student

Platser

Vara, Sweden

Kvalifikation

Masterexamen

Sökande

Ansök tidigt