Hardwood in a forest

Doctoral project: Advanced identification methods for the forest industry through CV/AI

The project intends to create opportunities for continued digitalisation in the forest industry. This concerns everything from traceability to quality assessments.

Project information

Doctoral student
Dag Björnberg
Supervisor
Morgan Ericsson
Assistant supervisors
Johan Lindeberg, Rafael Martins, Jonas Nordqvist
Participating organizations
Linnaeus University, Softwerk
Financiers
Softwerk, The Knowledge Foundation (KK-stiftelsen)
Timetable
Sept 2021 – Sept 2025
Subject
Computer and information science (Department of Computer Science and Media Technology, Faculty of Technology)

More about the project

The forest industry is facing digitalisation, which places demands on improved models for automation. This can be anything from recognizing logs through the production chain to quality assessments based on, for example, pith location or annual ring density.

The project thus follows two main tracks:

  • Work with a recognition algorithm to be able to follow logs between different stations at sawmills, which are based on AI. This lays the foundation for being able to develop models for traceability of logs throughout the entire production chain.
  • Creation of controlled training data using Generative Adversarial Networks, which is an image generation method based on AI. Through this procedure, we can create images with controlled pith location and age that can later be used as training data in order to make quality assessments. In this way, we can not only generate a lot of training data but also avoid manual marking, which can be very time consuming.

Although the work has a clear connection to the forest industry, the methods we use are more general, which we hope can create added value not only in the forest industry, but in AI as a research area in general.

The project is part of the research in the research group Data Intensive Software Technologies and Applications (DISTA) and the Linnaeus University Centre for Data Intensive Sciences and Applications (DISA).