Research Repository

Spatio-temporal monitoring of wheat yellow rust using UAV multispectral imagery

Su, Jinya and Liu, Cunjia and Hu, Xiaoping and Xu, Xiangming and Guo, Lei and Chen, Wen-Hua (2019) 'Spatio-temporal monitoring of wheat yellow rust using UAV multispectral imagery.' Computers and Electronics in Agriculture, 167. p. 105035. ISSN 0168-1699

Temporal_third.pdf - Accepted Version
Available under License Creative Commons Attribution Non-commercial No Derivatives.

Download (1MB) | Preview


This work is focused on the spatio-temporal monitoring of winter wheat inoculated with various levels of yellow rust inoculum during the entire growth season. A dedicated work ow is devised to obtain time-series five-bands (visible-infrared) aerial imageries with a multispectral camera and an Unmanned Aerial Vehicle. A number of spectral indices are drawn so that the sensitive ones can be identi fied by statistical dependency analysis; particularly, their discriminating capabilities are evaluated at diffeerent stages for both wheat pixel segmentation and yellow rust severity. Then the spatial-temporal changes of sensitive bands/indices are evaluated and analysed quantitatively. A validation fi eld experiment was designed in 2017-2018 by inoculating wheat with one of the six levels of yellow rust inoculum. Five-bands RedEdge camera on-board DJI S1000 was used to capture aerial images at eight time points covering the entire growth season at an altitude of about 20 meters with a ground resolution of 1-1.5 cm/pixel. Experimental results via spatio-temporal analysis show that: (1) various bands/indices should be used for wheat segmentation at different stages; (2) no bands/indices differences are observed for yellow rust inoculated wheat plots in both incubation stage (9 days after inoculation) and early onset stage (25 days after inoculation); (3) NIR and Red are the sensitive bands for wheat yellow rust in disease stages (45 days after inoculation); and their normalized difference NDVI index provides an even higher statistical dependency; (4) bands/indices' sensitivity to yellow rust changes over time and decreases in later Heading stage until being very low in Ripening stage (61 days after inoculation). This experimental study provides a crucial guidance for future early spatio-temporal yellow rust monitoring at farmland scales.

Item Type: Article
Uncontrolled Keywords: Multispectral image; Spatio-temporal analysis; Statistical dependency; UAV remote sensing; Yellow rust
Divisions: Faculty of Science and Health
Faculty of Science and Health > Computer Science and Electronic Engineering, School of
SWORD Depositor: Elements
Depositing User: Elements
Date Deposited: 02 Oct 2019 14:25
Last Modified: 18 Aug 2022 10:29

Actions (login required)

View Item View Item