Hyperspectral Classification of Cyperus esculentus Clones and Morphologically Similar Weeds
| Autor: | Benny De Cauwer, Jan Pieters, David Nuyttens, Marlies Lauwers, Simon Cool |
|---|---|
| Jazyk: | angličtina |
| Rok vydání: | 2020 |
| Předmět: |
Agriculture and Food Sciences
reflectance Multispectral image 0211 other engineering and technologies Early detection weed classification YELLOW NUTSEDGE GLYPHOSATE 02 engineering and technology lcsh:Chemical technology Biochemistry Analytical Chemistry Hyperspectral reflectance Cyperus partial least squares–discriminant analysis Crop production SCATTERING lcsh:TP1-1185 Electrical and Electronic Engineering ROTUNDUS Instrumentation 021101 geological & geomatics engineering biology RANDOM FOREST TUBER PRODUCTION business.industry logistic regression Hyperspectral imaging Pattern recognition PURPLE 04 agricultural and veterinary sciences Spectral bands HERBICIDES EFFICACY biology.organism_classification Atomic and Molecular Physics and Optics Random forest yellow nutsedge 040103 agronomy & agriculture GROWTH 0401 agriculture forestry and fisheries Artificial intelligence business random forest |
| Zdroj: | Sensors, Vol 20, Iss 2504, p 2504 (2020) SENSORS Sensors Volume 20 Issue 9 |
| ISSN: | 1424-8220 |
| Popis: | Cyperus esculentus (yellow nutsedge) is one of the world&rsquo s worst weeds as it can cause great damage to crops and crop production. To eradicate C. esculentus, early detection is key&mdash a challenging task as it is often confused with other Cyperaceae and displays wide genetic variability. In this study, the objective was to classify C. esculentus clones and morphologically similar weeds. Hyperspectral reflectance between 500 and 800 nm was tested as a measure to discriminate between (I) C. esculentus and morphologically similar Cyperaceae weeds, and between (II) different clonal populations of C. esculentus using three classification models: random forest (RF), regularized logistic regression (RLR) and partial least squares&ndash discriminant analysis (PLS&ndash DA). RLR performed better than RF and PLS&ndash DA, and was able to adequately classify the samples. The possibility of creating an affordable multispectral sensing tool, for precise in-field recognition of C. esculentus plants based on fewer spectral bands, was tested. Results of this study were compared against simulated results from a commercially available multispectral camera with four spectral bands. The model created with customized bands performed almost equally well as the original PLS&ndash DA or RLR model, and much better than the model describing multispectral image data from a commercially available camera. These results open up the opportunity to develop a dedicated robust tool for C. esculentus recognition based on four spectral bands and an appropriate classification model. |
| Databáze: | OpenAIRE |
| Externí odkaz: |
|