Simon Leminen Madsen

PhD Student

Simon Leminen Madsen

Profile

Simon Leminen Madsen is a PhD student at the Department of Engineering at Aarhus University. He is part of the Signal Processing research group that focuses on the application of new technologies in signal processing and machine learning for precision agriculture, geophysics, audio systems and more.

Simon received the Master of Science in Electrical Engineering from Aarhus University in January 2016. His Master’s thesis covered research on expression recognition using state-of-the-art machine learning algorithms in form of deep convolutional neural network.

His research interests include Machine Learning, Generative Models, Deep Learning, Computer Vision, Signal and Image Processing

 

PhD project description

Project title: Reinforced Weed Classification utilizing Context Data and Deep Generative Models
Main supervisor: Prof. (Docent), Henrik Karstoft
Co-supervisor: Senior Researcher, Rasmus Nyholm Jørgensen
Project period: Feb 2017 to Jan 2020

This project is part of the Innovation Fund Denmark project RoboWeedMaPS. The overall goal of RoboWeedMaPS is to substantially reduce the amount of herbicides in modern crop farming, which will benefit society, the environment and the farmer. To achieve this, a more efficient and precise deployment of herbicides is needed. The project will incorporate automated vision systems to assess the optimum weed treatment and thereby eliminate the need for intermediate manual decision-making and data processing.

This project seeks to apply machine learning, specifically deep learning, to automatically classify weed species and their current development stage from images. To improve the certainty of the classification, it should incorporate context relevant data such as site-specific cropping history, past weed registrations, etc. The project will also explore the potential of generating photo realistic image samples of weeds using deep generative models. These artificial samples are expected to be used for creating a more robust weed classification model. Generative models can potentially also be used to improve the quality of unfocused and blurred images.

View all (4) »

ID: 96870082