Preprint Article Version 1 This version is not peer-reviewed

Aerial Multispectral Imagery for Plant Disease Detection; Radiometric Calibration Necessity Assessment

Version 1 : Received: 12 February 2019 / Approved: 13 February 2019 / Online: 13 February 2019 (10:40:40 CET)

How to cite: Pourazar, H.; Samadzadegan, F.; Dadrass Javan, F. Aerial Multispectral Imagery for Plant Disease Detection; Radiometric Calibration Necessity Assessment. Preprints 2019, 2019020111 (doi: 10.20944/preprints201902.0111.v1). Pourazar, H.; Samadzadegan, F.; Dadrass Javan, F. Aerial Multispectral Imagery for Plant Disease Detection; Radiometric Calibration Necessity Assessment. Preprints 2019, 2019020111 (doi: 10.20944/preprints201902.0111.v1).

Abstract

In recent years, using multispectral cameras on UAVs has provided an opportunity to capture separate bands that offer the extraction of spectral features used for early detection of diseased plants. One of the main steps in disease detection is radiometric calibration that converts digital numbers to reflectance values commonly using white reference panels. This paper focused on the necessity of radiometric calibration to distinguish disease trees in orchards based on aerial multi-spectral images. For this purpose, two study sites with various climate conditions and tree species as well as different disease types were selected where multispectral images were taken using a multirotor UAV. The impact of radiometric correction on plant disease detection was assessed in two ways: 1) comparison of separability between the healthy and diseased classes using T-test and entropy distances; 2) radiometric calibration effect on the accuracy of classification. The experimental result showed the insignificant effect of radiometric calibration on separability criteria. Furthermore, based on T-test and entropy distances criteria, NIR and R spectral features made highest distances between healthy and Greening infected citrus trees, respectively, at the first study site while NDRE and BNDVI spectral features made highest distances between healthy and peach leaf curl infected trees, respectively, at the other study site. In the second strategy, the experimental result showed that radiometric calibration had no effect on the accuracy of classification. As a result, the overall accuracy and kappa values for both un-calibrated and calibrated orthomosaic classifications of the citrus orchard were 96.6% and 0.94%, respectively, using five spectral bands as well as DVI, NDRE, NDVI and GNDVI vegetation indices using a random forest classifier. The experimental results were also similar at the other study site. Therefore, the overall accuracy and kappa values for both the un-calibrated and calibrated orthomosaic classifications were 96.1%, 0.92, respectively, using five spectral bands as well as NDRE, BNDVI, GNDVI, DVI, and NDVI vegetation indices.

Subject Areas

Multispectral; Radiometric calibration; Classification; Plant disease; Aerial imagery

Comments (0)

We encourage comments and feedback from a broad range of readers. See criteria for comments and our diversity statement.

Leave a public comment
Send a private comment to the author(s)
Views 0
Downloads 0
Comments 0
Metrics 0


×
Alerts
Notify me about updates to this article or when a peer-reviewed version is published.