Quantitative and Qualitative Analysis of Agricultural Fields Based on Aerial Multispectral Images Using Neural Networks.

Abstract

This article presents an integrated system that uses the capabilities of unmanned aerial vehicles (UAVs) to perform a comprehensive crop analysis, combining qualitative and quantitative evaluations for efficient agricultural management. A convolutional neural network-based model, Detectron2, serves as the foundation for detecting and segmenting objects of interest in acquired aerial images. This model was trained on a dataset prepared using the COCO format, which features a variety of annotated objects. The system architecture comprises a frontend and a backend component. The frontend facilitates user interaction and annotation of objects on multispectral images. The backend involves image loading, project management, polygon handling, and multispectral image processing. For qualitative analysis, users can delineate regions of interest using polygons, which are then subjected to analysis using the Normalized Difference Vegetation Index (NDVI) or Optimized Soil Adjusted Vegetation Index (OSAVI). For quantitative analysis, the system deploys a pre-trained model capable of object detection, allowing for the counting and localization of specific objects, with a focus on young lettuce crops. The prediction quality of the model has been calculated using the AP (Average Precision) metric. The trained neural network exhibited robust performance in detecting objects, even within small images.

Plant phenotyping relevance

UAVマルチスペクトル画像から作物を検出・分割し、レタス個体の計数・位置推定と植生指標解析を行う統合システムが中心であり、植物状態・個体数の取得方法を評価している。

Code and data availability

The paper describes a custom UAV multispectral image dataset, CVAT annotations, and a trained Detectron2 model, but provides no public deposit, URL, or availability statement for any of them. The Data Availability Statement says only 'Data are contained within the article.' All URLs cited (COCO, Detectron2, Landsat, P.

No evidence-backed public reproduction asset is currently recorded.