A lightweight detector with hybrid pooling and checkerboard attention for solar panel anomalies

iScience 2026 Open access

Read full text
Authors: Xing Yang, Hongye Fang, Fan Yang, Kailiang Li, Ru Cheng Han, Tongjie Li
DOI: 10.1016/j.isci.2026.115106
Cited by: 2
References: 22

Abstract

of 84.1% and a precision of 94.13%, surpassing existing YOLO models and classical detectors. When deployed on an NVIDIA Jetson Orin NX, the model sustains real-time inference at over 55 FPS in FP16 format, confirming its practical suitability for edge-based agricultural IoT device monitoring and sustainable agricultural applications.

Fields of Study & Subjects

Solar and Space Plasma Dynamics Photovoltaic System Optimization Techniques Solar Radiation and Photovoltaics

Publication details

Journal / source
iScience
Publisher
Elsevier BV
Volume
29
Issue
3
Pages
115106–115106
Publication date
20 February 2026
Language
EN