We found a match
Your institution may have access to this item. Find your institution then sign in to continue.
- Title
PM-YOLO: A Powdery Mildew Automatic Grading Detection Model for Rubber Tree.
- Authors
Li, Yuheng; Chen, Qian; Zhu, Jiazheng; Li, Zengping; Wang, Meng; Zhang, Yu
- Abstract
Simple Summary: Powdery mildew is a significant disease affecting rubber trees, which reduces yield and quality by forming white fungal patches on leaves. Although in recent years, object detection technologies in agriculture application have improved, many cases especially small-scale regions remain undetected. In this study, we proposed PM-YOLO, an advanced detection model for automatically grading rubber tree powdery mildew. The proposed model integrates innovative modules to achieve superior performance, (1) Feature Focus and Diffusion Mechanism (FFDM) enhances multi-scale feature integration, and (2) Dimension-Aware Selective Integration (DASI) module optimizes the detection of small targets. Additionally, we developed an automatic grading algorithm to quantify disease severity using a precise, formula-driven approach based on leaf damage. Furthermore, we constructed a powdery mildew datasets containing 6200 images with 38,000 annotations for powdery mildew detection task. Experimental results demonstrated that PM-YOLO outperformed the state-of-the-art methods in precision and recall. This work offers an approach for early detection and management of powdery mildew, thereby promoting sustainable rubber tree cultivation. Powdery mildew has become a significant disease affecting the yield and quality of rubber trees in recent years. It typically manifests on the leaf surface at an early stage, rapidly infecting and spreading throughout the leaves. Therefore, early detection and intervention are essential to reduce the resulting losses due to this disease. However, the conventional methods of disease detection are both time-consuming and labor-intensive. In this study, we proposed a novel deep-learning-based approach for detecting powdery mildew in rubber trees, even in complex backgrounds. First, to address the lack of existing datasets on rubber tree powdery mildew, we constructed a dataset comprising 6200 images and 38,000 annotations. Second, based on the YOLO framework, we integrated a multi-scale fusion module that combines a Feature Focus and Diffusion Mechanism (FFDM) into the neck of the detection architecture. We designed an overall focus diffusion architecture and introduced a Dimension-Aware Selective Integration (DASI) module to enhance the detection of small powdery mildew targets, naming the model PM-YOLO. Furthermore, we proposed an automatic grading detection algorithm to evaluate the severity of powdery mildew on rubber tree leaves. The experimental results demonstrated that the proposed method achieved 86.9% mean average precision (mAP) and 85.6% recall, which outperformed the standard YOLOv10 by 7.6% mAP and 8.2% recall. This approach offered accurate and real-time detection of powdery mildew rubber trees, providing an effective solution for early diagnosis through automated grading.
- Subjects
AGRICULTURAL technology; DETECTION algorithms; LEAF anatomy; RUBBER; EARLY diagnosis; DEEP learning
- Publication
Insects (2075-4450), 2024, Vol 15, Issue 12, p937
- ISSN
2075-4450
- Publication type
Academic Journal
- DOI
10.3390/insects15120937