Hierarchical Deep Learning Model for Identifying Similar Targets in UAV Imagery
Drones, Vol. 9, No. 11, Article 743
Editorial summary
A cascade first proposes objects with Faster R-CNN, extracts detailed features with specialised YOLO models and separates similar classes with FT-Transformer. Experiments compare this staged approach with a flat classifier to assess how well it distinguishes visually similar targets in UAV imagery.
Bibliographic reference
Use the publisher’s record for the citation format required by your journal or organisation.
Dmytro Borovyk, Oleksander Barmak, Pavlo Radiuk, Iurii Krak. "Hierarchical Deep Learning Model for Identifying Similar Targets in UAV Imagery". Drones, Vol. 9, No. 11, Article 743, 2025. https://doi.org/10.3390/drones9110743
Test a method against your business task.
Describe the decision your system needs to support and the data you have. We assess whether a method fits, define a prototype and agree how to measure its quality, response time and operating cost.