RT-DETR-AGWZ based on RT-DETR-R50 improves strawberry disease detection and localization under complex field conditions and reduces in false-positive detections and localization errors.
Abstract
Accurate strawberry disease detection under complex field conditions is challenging because lesion appearance and scale vary considerably and disease regions are often affected by occlusion, illumination changes, and complex backgrounds. To improve feature representation and multi-scale information interaction, this study proposes RT-DETR-AGWZ based on RT-DETR-R50. The proposed model introduces BottleNeck_Attention for spatial feature enhancement, GLSA for global–local contextual modeling, WaveletUnPool for Haar-basis-constrained structured upsampling, and Zoom_cat for multi-scale feature alignment and fusion. Experiments were conducted on a cleaned, self-collected strawberry disease dataset using a frozen group-aware data partition. Across three independent runs on the validation set, RT-DETR-AGWZ achieved a mean Precision of 0.948±0.006, Recall of 0.944±0.006, mAP@0.5 of 0.969±0.002, and mAP@0.5:0.95 of 0.836±0.008. Compared with RT-DETR-R50, the mean mAP@0.5:0.95 increased by approximately 1.93 percentage points, from 0.817±0.012 to 0.836±0.008. Error analysis further showed reductions in false-positive detections and localization errors, and RT-DETR-AGWZ achieved the best overall detection performance among the representative detectors evaluated under the same experimental protocol. These results indicate that the proposed multi-domain collaborative optimization strategy improves strawberry disease detection and localization under complex field conditions.
Alation and comparative studies confirm that LMF-YOLO outperforms mainstream YOLO variants in balancing computational efficiency with detection sensitivity, providing a robust technical solution for mobile-intelligent strawberry disease diagnostics.
Yu-Zhen Niu, Ping Lin· Frontiers in Plant Science· 0 citations
IFMA-Net’s potential for accurate pest and disease identification in practical agricultural sensing scenarios is demonstrated and perturbation experiments showed higher retention than ResNet-50 under random occlusion but substantial degradation under severe Gaussian noise.
Li-Li Song, Zhen-Xue Chen, Cheng-Yun Liu et al.· Italian National Conference...· 0 citations
Image-based rice disease models often lose reliability under domain shifts caused by varying backgrounds, symptom scales, and acquisition conditions. This study presents a linked two-stage design to investigate whether observational agronomic context can mitigate such transfer degradation. In Stage A, four instance-seg...
Sakya Tuan, Anh Tuan Quoc Phan, Vinh Chi Luong et al.· 2026 10th International Conf...· 0 citations
Plant diseases are a risk to agricultural productivity and require accurate and real-time detection of the disease under various field conditions. In this study, a novel YOLO-based plant disease detection framework which uses attention mechanism is proposed called YOLO-LeafNet, focusing on the multi-crop plant disease...
S. K. Mohan Raju, D. Santhakumar· International Conference on...· 0 citations
Results show that SSW-YOLO improves the performance of multi-class rice disease and pest-induced damage detection on the evaluated dataset and shows potential for accurate rice disease identification and intelligent monitoring.
Yin-Gan Shao, M. Devaraj· Agronomy· 0 citations
We use cookies to run the site and, with your consent, for analytics and to show ads.
See our Cookie Policy.