Thesis subject
MSc thesis topic: Segmentation of vineyard rows in individual images and orthomosaic using deep learning techniques
UAVs have enabled a great revolution in agriculture due to the important reduction in costs they present, together with a rapid data acquisition. The combination of UAV data with Artificial Intelligence and Deep Learning has provided the farmer with new tools to know the state of the crop in more detail.
The identification of vineyard rows and the estimation of their dimensions and the in-between gaps they present, are of importance for the monitoring and management of the vineyards. Therefore, being able to identify each row and extract agronomic features of interest can prepare the farmer with useful information about the status of the vineyard.
Relevance to research/projects at GRS or other groups
- FlexiGroBots (INF department)
Objectives
- Train an algorithm for individual images and orthomosaic that allows the segmentation of vineyard rows
- Extract features with agronomical interests from the rows detected
- Literature
Barros, T., Conde, P., Gonçalves, G., Premebida, C., Monteiro, M., Ferreira, C. S. S., & Nunes, U. J. (2022). Multispectral vineyard segmentation: A deep learning comparison study. Computers and Electronics in Agriculture, 195, 106782. - Nolan, A. P., Park, S., O’Connell, M., Fuentes, S., Ryu, D., & Chung, H. (2015). Automated detection and segmentation of vine rows using high resolution UAS imagery in a commercial vineyard. Proceedings - 21st International Congress on Modelling and Simulation, MODSIM 2015, 1406–1412.
- Pádua, L., Adão, T., Hruška, J., Guimarães, N., Marques, P., Peres, E., & Sousa, J. J. (2020). Vineyard Classification Using Machine Learning Techniques Applied to RGB-UAV Imagery. IGARSS 2020 - 2020 IEEE International Geoscience and Remote Sensing Symposium, 6309–6312.
Requirements
- UAV enthusiast
- Willing work with AI and DL
- Excited to work with high-tech platforms
Theme: Sensing & measuring