Deep Learning and Computer Vision for business optimization of Danish SMEs


The use of Artificial Intelligence (AI) technologies such as Deep Learning and Computer Vision is becoming an increasingly important competition advantage for enterprises in a variety of industries. For small and medium sized enterprises (SMEs), the lack of resources for employers with AI competences, means it can be challenging to compete against large businesses.

However, the increasing availability of open-sourced large-scale datasets and AI technologies and research, could be utilized by SMEs to optimize their business.

This PhD project focuses on Deep Learning and Computer Vision technologies e.g., Convolutional Neural Networks (CNNs), Vision Transformers (ViTs), Self-supervised Learning and Data Augmentation and applies these to concrete Danish SMEs business cases, using their real-world datasets, in order to research how the technologies can be used to optimize their business models.


Explorative study of Edge devices and Object Detectors for Autonomous Lawn Mowers

With: Conpleks Innovation ApS.

Semantic Segmentation of 3D point clouds of steel constructions

With: Inropa A/S

Deep Learning-based Anomaly Detection in Fuel Cell Electrodes with SerEnergy

With: SerEnergy (Advent Technologies)

Scientific Work

Deep Learning-based Anomaly Detection on X-ray Images of Fuel Cell Electrodes
Jensen, S. B.Moeslund, T. B. & Andreasen, S. J., 5 Feb 2022, Proceedings of the 17th International Joint Conference on Computer Vision, Imaging and Computer Graphics Theory and Applications, Volume 4: VISAPP.SCITEPRESS Digital Library, p. 1-10 10 p.


This PhD project is funded by Ambolt ApS and the AI Denmark initiative which is funded by Industriens Fond.


PhD Fellow: Simon Buus Jensen 

Supervisor: Thomas B. Moeslund