# Overview

Early accurate diagnosis and quantification of crop diseases are crucial for precision management by allowing targeted interventions at the field level. Effective diagnosis and control measures are dependent on symptom recognition and severity assessment (in the vast majority of cases, diseases exhibit a range of visual symptoms, e.g. coloured spots or streaks). At present, these are mainly achieved by visual observation and estimation.  

Recent advancements in digital imaging have facilitated the development of a variety of image-based methods for plant management that are capable of performing automated image acquisition and analysis. These methods have shown great potential for automated crop disease diagnosis based on images from RGB (red, green and blue), thermal, multispectral, and hyperspectral sensors.

Particularly, hyperspectral imagery (HSI), which contains more narrow spectral bands over a contiguous spectral range, provides detailed spectral–spatial information of the disease infestation and offers the potential to provide better diagnostic accuracy.

In this challenge, we will mainly focus on the accurate diagnosis of crop diseases from hyperspectral imagery (in this case, yellow rust disease). The benchmark model for this competition is based on our published paper on remote sensing [1]. 

[1. A Deep Learning-Based Approach for Automated Yellow Rust Disease Detection from High-Resolution Hyperspectral UAV Images](https://www.mdpi.com/2072-4292/11/13/1554)

![](https://raw.githubusercontent.com/robeson1010/Agvision/main/imgs/hy.png)

# Challenge keywords
Remote sensing; Hyperspectral; Crop disease; Deep learning 


# Workshop/conference

This challenge is part of the conference on “[The Fourth conference of Monitoring, Early Warning, and Scientific Management of Vegetation Pests and Diseases]()” in Aug 2023.

# Publication and Future Plans 

We will write a summary paper of top 5 winning methods to be published in Remote Sensing Special issue of “Monitoring, Early Warning, and Scientific Management of Vegetation Pests and Diseases”.  
Our goal is to update the dataset with different types of diseases and continue to make it available for research use.