| dc.rights.license | CC-BY-NC-ND | |
| dc.contributor.advisor | Externe beoordelaar - External assesor, | |
| dc.contributor.author | Gkikas, Haris | |
| dc.date.accessioned | 2022-09-09T01:04:32Z | |
| dc.date.available | 2022-09-09T01:04:32Z | |
| dc.date.issued | 2022 | |
| dc.identifier.uri | https://studenttheses.uu.nl/handle/20.500.12932/42484 | |
| dc.description.sponsorship | Utrecht University | |
| dc.language.iso | EN | |
| dc.subject | Yield prediction is crucial for optimizing apple orchards. Recent research on the application of
unmanned aerial vehicles (UAVs) remote sensing and convolutional neural networks (CNNs) object
detection techniques, demonstrated a great potential for improved yield estimations. However, several
major challenges exist in CNN-based yield estimation in orchards using UAV platforms, including
illumination variance, occlusion conditions and the small scale of the fruits — as appear in aerial scenery.
I | |
| dc.title | Counting Apples: Deep Learning-based Fruit Yield
Estimation from High-Resolution UAV Imagery | |
| dc.type.content | Master Thesis | |
| dc.rights.accessrights | Open Access | |
| dc.subject.keywords | yield estimation; deep learning; object detection; UAV; super-resolution | |
| dc.subject.courseuu | Geographical Information Management and Applications (GIMA) | |
| dc.thesis.id | 9081 | |
