A High-Precision Plant Disease Detection Method Based on a Dynamic Pruning Gate Friendly to Low-Computing Platforms

Abstract

Timely and accurate detection of plant diseases is a crucial research topic. A dynamic-pruning-based method for automatic detection of plant diseases in low-computing situations is proposed. The main contributions of this research work include the following: (1) the collection of datasets for four crops with a total of 12 diseases over a three-year history; (2) the proposition of a re-parameterization method to improve the boosting accuracy of convolutional neural networks; (3) the introduction of a dynamic pruning gate to dynamically control the network structure, enabling operation on hardware platforms with widely varying computational power; (4) the implementation of the theoretical model based on this paper and the development of the associated application. Experimental results demonstrate that the model can run on various computing platforms, including high-performance GPU platforms and low-power mobile terminal platforms, with an inference speed of 58 FPS, outperforming other mainstream models. In terms of model accuracy, subclasses with a low detection accuracy are enhanced through data augmentation and validated by ablation experiments. The model ultimately achieves an accuracy of 0.94.

An Assessment of Human Inspection and Deep Learning for Defect Identification in Floral Wreaths

“…YOLOv4-tiny is the compressed version of YOLOv4 designed to train on machines with less computing power [40,41]. YOLOv4, an improved version of YOLOv3, generates bounding-box coordinates and assigns probabilities to each category, converting the object detection task into a regression problem [42]. Continuing with the YOLO family, Ultralytics proposed the YOLOv5 algorithm [43], which is smaller and more convenient, enabling flexible deployment and more accurate detection [44].…”