Using unmanned aerial vehicles (UAVs) to take aerial images and detect ships in harbors provides a new way of harbor monitoring. However, due to the limitation of computing resources and storage resources, ship detection on UAVs is very challenging, which puts a higher demand on model lightweighting. In this paper, we propose an efficient model lightweighting scheme based on knowledge distillation. We use two advanced large-scale models YOLOv7 and PP-YOLO as teacher models, and transfer the excellent detection ability of these two models to small-scale student models YOLOv7-tiny through knowledge distillation. This scheme not only greatly reduces the parameter scale and computation, but also retains the ship detection performance equivalent to that of large models.
Lightweight in-harbor ship detection based on UAV aerial images
International Conference on Remote Sensing, Surveying, and Mapping (RSSM 2023) ; 2023 ; Changsha, China
Proc. SPIE ; 12710 ; 127100U
2023-06-01
Conference paper
Electronic Resource
English
Ship Simulation Study of Grays Harbor Navigation Project, Grays Harbor, Washington
HENRY – Federal Waterways Engineering and Research Institute (BAW) | 1991
|Lightweight and Efficient Tiny-Object Detection Based on Improved YOLOv8n for UAV Aerial Images
DOAJ | 2024
|