Enhanced YOLOv8 for accurate and efficient floating object detection on water surfaces

Abstract Detecting floating objects on water surfaces is critical for environmental monitoring and pollution control. We present SEDS-YOLOv8, an enhanced YOLOv8n variant that integrates Squeeze-and-Excitation (SE) attention, Distribution Shift Convolution (DSConv), and Enhanced Intersection over Uni...

Ausführliche Beschreibung

Bibliografische Detailangaben

Hauptverfasser:	YanPeng Cao, HaoWen Luo, MengDi Wang, Yue Wang, Hao Yan
Format:	Artigo
Sprache:	Inglês
Veröffentlicht:	Nature Portfolio 2025-12-01
Schriftenreihe:	Scientific Reports
Schlagworte:	Water surface floater detection Distribution shifting convolution Squeeze-and-excitation networks Lightweight model YOLOv8 Computer vision
Online-Zugang:	https://doi.org/10.1038/s41598-025-32817-x
Tags:	Tag hinzufügen Keine Tags, Fügen Sie das erste Tag hinzu!