SOD-YOLO: A lightweight small object detection framework

SOD-YOLO: A lightweight small object detection framework

Abstract Currently, lightweight small object detection algorithms for unmanned aerial vehicles (UAVs) often employ group convolutions, resulting in high Memory Access Cost (MAC) and rendering them unsuitable for edge devices that rely on parallel computing. To address this issue, we propose the SOD-...

Full description

Saved in:
Bibliographic Details
Main Authors: Yunze Xiao, Nan Di
Format: Article
Language:English
Published: Nature Portfolio 2024-10-01
Series:Scientific Reports
Subjects:
Lightweight
Object Detection
SOD-YOLO
UAV Image
Online Access:https://doi.org/10.1038/s41598-024-77513-4
Tags: Add Tag
No Tags, Be the first to tag this record!

Internet

https://doi.org/10.1038/s41598-024-77513-4

Similar Items