Description:
This project aims to explore AI-based approaches to improve handheld image acquisition of vineyard traps via smartphones. In particular, it intends to explore innovative ways to segment these insect traps, for instance through automatic landmark detection using deep learning. Having the segmentation contours of the trap, a comparative study with multiple state-of-the-art approaches for perspective correction should be performed, with the main goal of assessing the perspective correction performance of each approach and respective image quality loss.
Outcome:
Increase FhP background knowledge in handheld image acquisition approaches. EyesOnTraps project contribution.
Author: João Alves Costa
Type: MSc thesis
Partner: FEUP – Faculdade de Engenharia da Universidade do Porto
Year: 2021