Detecting Infected Cucumber Plants with Close-Range Multispectral Imagery
Autor: | Keri Wang, Brigitte Leblon, Ata Haddadi, Claudio Ignacio Fernández, Jinfei Wang |
---|---|
Jazyk: | angličtina |
Rok vydání: | 2021 |
Předmět: |
0106 biological sciences
Science Multispectral image 0211 other engineering and technologies Image registration 02 engineering and technology 01 natural sciences support vector machines SURF features 021101 geological & geomatics engineering Mathematics speeded-up robust features image alignment powdery mildew Pixel business.industry Pattern recognition Support vector machine Data set Feature (computer vision) General Earth and Planetary Sciences RGB color model Affine transformation Artificial intelligence business 010606 plant biology & botany |
Zdroj: | Remote Sensing, Vol 13, Iss 2948, p 2948 (2021) Remote Sensing; Volume 13; Issue 15; Pages: 2948 |
ISSN: | 2072-4292 |
Popis: | This study used close-range multispectral imagery over cucumber plants inside a commercial greenhouse to detect powdery mildew due to Podosphaera xanthii. It was collected using a MicaSense® RedEdge camera at 1.5 m over the top of the plant. Image registration was performed using Speeded-Up Robust Features (SURF) with an affine geometric transformation. The image background was removed using a binary mask created with the aligned NIR band of each image, and the illumination was corrected using Cheng et al.’s algorithm. Different features were computed, including RGB, image reflectance values, and several vegetation indices. For each feature, a fine Gaussian Support Vector Machines algorithm was trained and validated to classify healthy and infected pixels. The data set to train and validate the SVM was composed of 1000 healthy and 1000 infected pixels, split 70–30% into training and validation datasets, respectively. The overall validation accuracy was 89, 73, 82, 51, and 48%, respectively, for blue, green, red, red-edge, and NIR band image. With the RGB images, we obtained an overall validation accuracy of 89%, while the best vegetation index image was the PMVI-2 image which produced an overall accuracy of 81%. Using the five bands together, overall accuracy dropped from 99% in the training to 57% in the validation dataset. While the results of this work are promising, further research should be considered to increase the number of images to achieve better training and validation datasets. |
Databáze: | OpenAIRE |
Externí odkaz: |