Object detection model pruning with application to human recognition in UAV footage

dc.contributor.advisorКузьменко, Дмитроuk_UA
dc.contributor.authorБезбородов, Владиславuk_UA
dc.date.accessioned2025-09-04T13:10:25Z
dc.date.available2025-09-04T13:10:25Z
dc.date.issued2025
dc.description.abstractThis thesis explores the application of the model optimization techniques in object detection field with a focus on human recognition from UAV footage. Limitations of resource constrained devices and deployment of accurate yet lightweight models is a challenging task. To address this, we examine three core optimization approaches: quantization, pruning, and knowledge distillation. Each method is investigated and applied in the context of YOLOv8-based detectors. Through experimental evaluation and comparative analysis with models trained from scratch, we demonstrate these techniques can significantly reduce model size and inference latency while preserving favorable performance.en_US
dc.identifier.urihttps://ekmair.ukma.edu.ua/handle/123456789/36444
dc.language.isoen_USen_US
dc.statusfirst publisheden_US
dc.subjectmodel optimizationen_US
dc.subjectobject detectionen_US
dc.subjectUAV footageen_US
dc.subjectconstrained devicesen_US
dc.subjectbachelor`s thesisen_US
dc.titleObject detection model pruning with application to human recognition in UAV footageen_US
dc.typeOtheren_US
Files
Original bundle
Now showing 1 - 2 of 2
Loading...
Thumbnail Image
Name:
Bezborodov_Bakalavrska_robota.pdf
Size:
780.37 KB
Format:
Adobe Portable Document Format
Loading...
Thumbnail Image
Name:
Bezborodov_Bakalavrska_robota_1.pdf
Size:
291.79 KB
Format:
Adobe Portable Document Format
License bundle
Now showing 1 - 1 of 1
No Thumbnail Available
Name:
license.txt
Size:
1.71 KB
Format:
Item-specific license agreed upon to submission
Description: