Digital Repository
Of Polessky State University
ISSN (online): 2310-7413
Please use this identifier to cite or link to this item:
https://rep.polessu.by/handle/123456789/35540| Title: | Hybrid CNN-transformer model-based object detection methodology for UAV imagery |
| Authors: | Nguyen, Van Bach |
| Keywords: | UAV object detection YOLO RT-DETR hybrid model |
| Issue Date: | 2026 |
| Publisher: | Пинск : Полесский государственный университет |
| Citation: | Nguyen, Van Bach. Hybrid CNN-transformer model-based object detection methodology for UAV imagery / Nguyen Van Bach // Инжиниринг : теория и практика : материалы VI международной научно-практической конференции, Полесский государственный университет, г. Пинск, Республика Беларусь, 29-30 апреля 2026 г. / Полесский государственный университет [и др.]; редкол. Дунай В. И., Пригодич И. А., Чещевик В. Т. – Пинск : ПолесГУ, 2026. – С. 20-23. |
| Abstract: | This paper proposes a hybrid object detection method for UAV imagery by combining YOLO (CNN-based) and RT-DETR (transformer-based) models. The framework integrates a bounding box processing module with fusion strategies and a confidence-based selection mechanism. Experimental results show that the hybrid approach improves detection accuracy, achieving a 0.7 increase in mAP50. |
| Appears in Collections: | 2026 |
Files in This Item:
| File | Description | Size | Format | |
|---|---|---|---|---|
| Hybrid_CNN_transformer.pdf | 502.01 kB | Adobe PDF | View/Open |
Items in DSpace are protected by copyright, with all rights reserved, unless otherwise indicated.