Home // GEOProcessing 2022, The Fourteenth International Conference on Advanced Geographic Information Systems, Applications, and Services // View article

Use of UAV-Based RGB Imagery and Vegetation Index for Early Detection of the Rabies of Chickpeas

Authors:
Lorena Parra
Barbara Stefanutti
David Mostaza-Colado
Jose F. Marin
Jaime Lloret
Pedro V. Mauri

Keywords: plant disease; aggregation; image processing; legume; biotic stress; crop

Abstract:
Rainfed crops rarely include the application of phytosanitary products due to the high cost of their application and the reduced rentability of crops. Nonetheless, if diseases are early detected, phytosanitary application costs are heavily reduced. This paper presents a method of detecting rabies in chickpeas based on true-colour images gathered from drones. The methodology consists of applying a series of vegetation indexes and filters. In the proposed method, applied to several images, we include the detection of areas affected by rabies of chickpea but also their differentiation from other areas with lower vigour. The developed approach is tested with images obtained in different soil types and gathered at diverse flying heights. As vegetation indexes, we used well-known vegetation indexes and specific vegetation indexes developed for chickpeas. To evaluate the accuracy of the proposed methodology, the number and percentage of true positives and false positives are assessed. Moreover, a verification is done using a different picture in order to evaluate if the methodology might be applied in other scenarios. The results of the initial test and the verification test offer a number of true positives higher than 85%. Thus, we can affirm that the proposed methodology can be useful for the differentiation between areas affected by rabies of chickpea and areas with low vigour due to the passing of machinery.

Pages: 68 to 74

Copyright: Copyright (c) IARIA, 2022

Publication date: June 26, 2022

Published in: conference

ISSN: 2308-393X

ISBN: 978-1-61208-983-6

Location: Porto, Portugal

Dates: from June 26, 2022 to June 30, 2022