Submit

Login Login

Register Register

Home / Journals / CMC / Online First / doi:10.32604/cmc.2026.082431
Journal Menu
Special Issues
Table of Content

All issues

Online First

2026

2025

2024

2023

2022

2021

2020

2019

2018

2017

2016

2015

2014

2013

2012

2011

2010

2009

2008

2007

2006

2005

2004

Open Access

ARTICLE

Scale-Robust Cross-Scale Representation Learning for Aerial Crop Pest Recognition

Kemeng Zhu1, Dingju Zhu1,2,*, Shihua Mao1, Jinchen Wu3, Depeng Kong4, Kaileung Yung5, Andrew W. H. Ip6
1 School of Artificial Intelligence, South China Normal University, Foshan, China
2 School of Computer Science, South China Normal University, Guangzhou, China
3 Guangzhou Vocational College of Technology & Business, Guangzhou University, Guangzhou, China
4 Department of McCormick School of Engineering, Northwestern University, Evanston, IL, USA
5 Department of Industrial and Systems Engineering, Hong Kong Polytechnic University, Hong Kong, China
6 Department of Mechanical Engineering, University of Saskatchewan, Saskatoon, SK, Canada
* Corresponding Author: Dingju Zhu. Email: email

Computers, Materials & Continua https://doi.org/10.32604/cmc.2026.082431

Received 16 March 2026; Accepted 21 April 2026; Published online 09 May 2026

Abstract

Unmanned aerial vehicles (UAVs) have become an increasingly important platform for agricultural remote sensing, yet the accurate recognition of pests and diseases is frequently compromised by drastic scale variability and complex environmental backgrounds. To address these challenges, this study introduces a novel attention-driven approach centered on a Multi-Scale Grouped Channel–Spatial Dual Attention (MS-GCDA) mechanism. The MS-GCDA module achieves robust feature calibration by decoupling and jointly modeling multi-scale spatial contexts and grouped channel dependencies, which significantly enhances the model’s sensitivity to fine-grained disease symptoms while suppressing background clutter. This core mechanism is integrated into Augmented EfficientNet (AugEffNet), a lightweight architecture further optimized for edge deployment through a learnable Latent Feature Projection (LFP) strategy that bridges the gap between high-dimensional feature extraction and real-time inference. Experimental evaluations on a self-collected luffa dataset and the public AppleLeaf9 benchmark demonstrate the superior efficacy of the proposed MS-GCDA mechanism. The framework achieves an accuracy of 97.27% and an F1-score of 97.05%, outperforming representative lightweight models. Notably, while the MS-GCDA ensures diagnostic precision under varying flight altitudes, the integration of LFP optimizes the deployment pipeline, resulting in a 94.7% reduction in inference latency (from 127.57 to 6.68 ms) and a decrease in computational cost to 122.88M Floating Point Operations per Second (FLOPs). Real-world field experiments validate that the synergy between scale-aware attention and efficient feature projection provides a reliable and scalable solution for autonomous plant protection in precision agriculture.

Keywords

Lightweight network; unmanned aerial vehicles; complex context; plant disease; image recognition

  • 109

    View

  • 19

    Download

  • 0

    Like

Related articles
Copyright© 2026 Tech Science Press
© 1997-2026 TSP (Henderson, USA) unless otherwise stated

Share Link