GBR-DETR: A Real-Time Tomato Leaf Disease Detection Model for Edge Device Deployment.

Abstract

Tomato leaf diseases pose significant threats to crop yield and food security. However, in real-world cultivation environments, factors such as fluctuating illumination, varying leaf occlusion, and ambiguous lesion morphology often compromise detection accuracy. This paper presents the Gradient-aware Bidirectional Retentive Detection Transformer (GBR-DETR), a model designed for high-precision, real-time disease detection. This model is composed of two network structures and a retentive feature aggregation module: (1) a Multi-scale Gradient-Aware Transfer Network (MGAT-Net) is designed to encode gradient information through the Sobel operator, thereby enhancing the localization stability for small and blurry lesions; (2) a Bidirectional Context Pyramid Network (BCPN) is proposed to enable bidirectional interactions among multi-level features through a top-down and a bottom-up pathway, thereby generating multi-scale lesion features and bridging cross-scale semantic gaps; and (3) a Retentive Feature Aggregation Module (RFAM) is used to suppress background noise and establish global feature correlations, thereby enhancing the overall representation capability for lesion recognition. Experiments on the Multi-scenario Tomato Leaf Disease (M-TLD) dataset show that GBR-DETR yields gains of 3.12, 4.88, and 3.41 percentage points in mAP 50-95 , mAP 50 , and mAP 75 , respectively, over the baseline RT-DETR, while also outperforming representative DETR-based and CNN-based detectors. The model demonstrates robust generalization on the PlantDoc cross-domain benchmark, achieving a 2.11% improvement in mAP 50 over the baseline. Deployed on the NVIDIA Jetson Orin Nano with TensorRT FP16, it achieves 54 ms latency, enabling real-time disease monitoring on edge devices. This solution provides effective technical support for real-time disease monitoring in smart agriculture.

Plant phenotyping relevance

トマト葉の病斑・病害状態を画像から検出するモデルを開発し、複数データセットで比較検証、エッジデバイス実装まで評価しており、植物病害表現型の取得手法が中心である。

Code and data availability

The paper's M-TLD tomato leaf disease dataset (2212 images, 6581 annotations) and the GBR-DETR implementation/training code are explicitly stated to be publicly available at the authors' GitHub repository.