A Comparative Study of Video Segmentation Techniques for Graduate Detection in Thai Graduation Ceremonies

Simple item page
dc.contributor.authorChungmarisakul, Chanasorn
dc.contributor.authorChawuthai, Rathachai
dc.date.accessioned2026-08-06T10:49:21Z
dc.date.available2026-08-06T10:49:21Z
dc.date.issued2025-01-01
dc.description.abstractGraduation ceremonies are significant occasions usually documented on lengthy, difficult-to-navigate videos. To make more satisfaction of the video needs to remove other participants and restore clear areas into short segments focused on particular graduates. By using YOLOv8 for efficient participant segmentation and the Segment Anything Model (SAM2) for accurate tracking, this study expands on earlier research by preparing videos for inpainting. The results establish the foundation for a complete system that combines inpainting, segmentation, and detection to produce polished, customized graduation video clips.
dc.identifier.citation22nd International Conference on Electrical Engineering Electronics Computer Telecommunications and Information Technology Ecti Con 2025, 2025
dc.identifier.doi10.1109/ECTI-CON64996.2025.11100560
dc.identifier.other2-s2.0-105014354085
dc.identifier.urihttps://dspace.kmitl.ac.th/handle/123456789/16496
dc.source22nd International Conference on Electrical Engineering Electronics Computer Telecommunications and Information Technology Ecti Con 2025
dc.subjectObject detection
dc.subjectSegment Anything Model (SAM2)
dc.subjectsegmentation
dc.subjectYOLOv8
dc.titleA Comparative Study of Video Segmentation Techniques for Graduate Detection in Thai Graduation Ceremonies
dc.typeConference Paper

Files

Collections

Research