Development of an AI-Driven Video Coding System for Animal Behavior Analysis
| dc.contributor.advisor | Szekely, Tamas | |
| dc.contributor.advisor | Miranda, Oscar | |
| dc.contributor.author | Nayef, Youns | |
| dc.contributor.department | DE--Természettudományi és Technológiai Kar--Biológiai és Ökológiai Intézet | hu_HU |
| dc.date.accessioned | 2026-01-07T09:15:22Z | |
| dc.date.available | 2026-01-07T09:15:22Z | |
| dc.date.created | 2025-11-28 | |
| dc.description.abstract | This thesis presents an AI system that uses YOLOv8 to automatically identify incubation and shading behaviors in the Madagascar plover. The model was trained on expert-annotated nest videos and achieved high accuracy when compared with manual observations. It worked especially well in videos with stable lighting and clear bird postures. Using the AI system also saved time, reducing annotation work by almost 30%. These results show that deep learning can help researchers study bird behavior more efficiently. With more data and additional behaviors, the system could become an even more useful tool for conservation research. | |
| dc.description.course | Biology | |
| dc.description.degree | MSc/MA | |
| dc.format.extent | 25 | |
| dc.identifier.uri | https://hdl.handle.net/2437/401735 | |
| dc.language.iso | en_US | |
| dc.rights.info | Hozzáférhető a 2022 decemberi felsőoktatási törvénymódosítás értelmében. | |
| dc.subject | AI-driven video analysis | |
| dc.subject | YOLOv8 | |
| dc.subject | Automated behavioral monitoring | |
| dc.subject | Madagascar plover | |
| dc.subject | Conservation ecology | |
| dc.subject.dspace | Biológiai tudományok | |
| dc.title | Development of an AI-Driven Video Coding System for Animal Behavior Analysis |
Fájlok
Eredeti köteg (ORIGINAL bundle)
1 - 1 (Összesen 1)
Nincs kép
- Név:
- Youns_bashar_THESIS.pdf
- Méret:
- 2.08 MB
- Formátum:
- Adobe Portable Document Format
- Leírás:
Engedélyek köteg
1 - 1 (Összesen 1)
Nincs kép
- Név:
- license.txt
- Méret:
- 2.35 KB
- Formátum:
- Item-specific license agreed upon to submission
- Leírás: