During his studies, Kim Bjerge researched methods for the automated monitoring of insects with computer vision and AI. He designed specialized camera traps capable of capturing insect images across various environments, integrating edge computing to enable real-time data processing in the field. His work includes research on deep learning models designed for detecting, classifying, and tracking insects in both time-lapse and video footage. Additionally, his research incorporates floral resource analysis, as well as clustering and hierarchical classification techniques to support accurate species identification. These innovations contribute to a more automated, scalable, and adaptable approach to insect monitoring, with applications in agriculture and biodiversity conservation.

The new research contributes with methods, code, datasets, and 10 papers about camera recording and deep learning algorithms for analyzing images of diurnal and nocturnal insects in their natural environments.

The PhD study was completed at Department of Electrical and Computer Engineering, Faculty of Technical Sciences, Aarhus University.

This summary was prepared by the PhD student.

Time: Friday 27. June 2025 at 13:00
Place: Building 5123, room 313, Aarhus University, Helsingforsgade 10, 8200 Aarhus N
Title of PhD thesis: Computer Vision and Deep Learning for Insect Monitoring
Contact information: Kim Bjerge, e-mail: kbe@ece.au.dk, tel.: +45 41 89 32 64
Members of the assessment committee:
Professor Joachim Denzler, Computer Vision Group, Friedrich-Schiller University Jena, Germany
Associate Professor Lars B. Pettersson, Biodiversity and Evolution, Lund University, Sweden
Professor Preben Kidmose (chair), Department of Electrical and Computer Engineering, Aarhus University, Denmark
Main supervisor: Professor Henrik Karstoft, Department of Electrical and Computer Engineering, Aarhus University, Denmark
Co-supervisor: Professor Toke T. Høye, Department of Ecoscience, Aarhus University, Denmark
Language: The PhD dissertation will be defended in English
Online link: https://aarhusuniversity.zoom.us/j/68612557165

The defence is public.
The PhD thesis is available for reading at the Graduate School of Technical Sciences/GSTS, Ny Munkegade 120, building 1521, 8000 Aarhus C.