Lightweight Plant Disease Detection With Adaptive Multi‐Scale Model and Relationship‐Based Knowledge Distillation

Expert Systems, Год журнала: 2025, Номер 42(6)

Опубликована: Апрель 27, 2025

ABSTRACT Plant disease detection is able to control spread and help prevent significant food production losses. However, existing methods are still limited different target scales high model parameters. To this end, we develop a novel framework, that is, FPDD‐Net, for lightweight plant detection. It based on YOLOv8 with an adaptive multi‐scale (AMSM) relationship‐based knowledge distillation (RKD). More specifically, the original cross stage partial (CSP) bottleneck replaced by AMSM effectively fuse features. Next, Alpha‐IoU loss optimization adopted aligning predicted boxes more precisely ground truth, leading fewer localization errors. Finally, RKD introduced assist training further improve performance of evaluate our network, FPDD‐Net trained tested two typical datasets, village dataset plant‐doc dataset. Experimental results indicated has advantages over peer methods.

Язык: Английский

---

Automated Detection of Rice Crop Disorder Using Deep Learning Techniques

Lecture notes in computer science, Год журнала: 2025, Номер unknown, С. 154 - 166

Опубликована: Янв. 1, 2025

Язык: Английский

---

Research on Rice Disease Detection Based on Improved YOLOv8s

Lecture notes in electrical engineering, Год журнала: 2025, Номер unknown, С. 50 - 60

Опубликована: Янв. 1, 2025

Язык: Английский

---

Advancements in Image Processing Techniques for Assessing Biotic and Abiotic Stress in Rice Plants

Advances in computational intelligence and robotics book series, Год журнала: 2025, Номер unknown, С. 1 - 42

Опубликована: Май 22, 2025

Over five years, significant advancements in image-processing techniques have emerged for assessing biotic and abiotic stresses rice plants. This review compiles analyzes recent research developments, highlighting innovative methodologies stress detection management. It covers a range of techniques, including hyperspectral imaging, thermal machine learning approaches, which been crucial accurately identifying quantifying factors. The integration these methods with modern computational tools allows precise monitoring early stress, facilitating timely interventions. Additionally, the addresses challenges limitations current suggests potential directions. By providing an extensive overview state-of-the-art this study serves as valuable resource researchers practitioners agricultural science technology.

Язык: Английский

---

MC-ShuffleNetV2: A lightweight model for maize disease recognition

Egyptian Informatics Journal, Год журнала: 2024, Номер 27, С. 100503 - 100503

Опубликована: Июль 6, 2024

Язык: Английский

---