Detection of Spider Mites on Labrador Beans through Machine Learning Approaches Using Custom Datasets

TL;DR

This paper presents a machine learning approach using custom RGBN datasets and a two-stage detection model to identify spider mites on Labrador beans, achieving improved accuracy over traditional methods.

Contribution

It introduces a novel two-stage detection model with RGBN data and demonstrates its effectiveness in early plant disease detection.

Findings

3.6% increase in mAP with two-stage model

90.62% validation accuracy with sequential CNN

6.25% accuracy improvement using RGBN data

Abstract

Amidst growing food production demands, early plant disease detection is essential to safeguard crops; this study proposes a visual machine learning approach for plant disease detection, harnessing RGB and NIR data collected in real-world conditions through a JAI FS-1600D-10GE camera to build an RGBN dataset. A two-stage early plant disease detection model with YOLOv8 and a sequential CNN was used to train on a dataset with partial labels, which showed a 3.6% increase in mAP compared to a single-stage end-to-end segmentation model. The sequential CNN model achieved 90.62% validation accuracy utilising RGBN data. An average of 6.25% validation accuracy increase is found using RGBN in classification compared to RGB using ResNet15 and the sequential CNN models. Further research and dataset improvements are needed to meet food production demands.