Forest pest monitoring and early warning using UAV remote sensing and computer vision techniques

• Published in: Scientific reports Vol. 15; no. 1; pp. 401 - 20
• Main Authors: Li, Xiaoyu, Wang, AChuan
• Format: Journal Article
• Language: English
• Published: London Nature Publishing Group UK 02.01.2025; Nature Publishing Group; Nature Portfolio
• Subjects: Adversarial attacks; Early warning; Environmental monitoring; Forest pest monitoring; Forests; Humanities and Social Sciences; multidisciplinary; Object detection; Pests; Remote sensing; Science; Science (multidisciplinary); Soft-thresholding adaptive filtering; UAV remote sensing; Unmanned aerial vehicles; Warning systems; Wilt; Forest pest monitoring; Real-time detection transformer (RTDETR); Object detection; Early warning; Cascaded group attention; UAV remote sensing; Adversarial attacks; Soft-thresholding adaptive filtering
• ISSN: 2045-2322; 2045-2322
• DOI: 10.1038/s41598-024-84464-3

Unmanned aerial vehicle (UAV) remote sensing has revolutionized forest pest monitoring and early warning systems. However, the susceptibility of UAV-based object detection models to adversarial attacks raises concerns about their reliability and robustness in real-world deployments. To address this challenge, we propose SC-RTDETR, a novel framework for secure and robust object detection in forest pest monitoring using UAV imagery. SC-RTDETR integrates a soft-thresholding adaptive filtering module and a cascaded group attention mechanism into the Real-time Detection Transformer (RTDETR) architecture, significantly enhancing its resilience against adversarial perturbations. Extensive experiments on a real-world pine wilt disease dataset demonstrate the superior performance of SC-RTDETR, with an improvement of 7.1% in mean Average Precision (mAP) and 6.5% in F1-score under strong adversarial attack conditions compared to state-of-the-art methods. The ablation studies and visualizations provide insights into the effectiveness of the proposed components, validating their contributions to the overall robustness and performance of SC-RTDETR. Our framework offers a promising solution for accurate and reliable forest pest monitoring in non-secure environments.