Abstract-The popularity of using hyperspectral imaging systems in studying and monitoring plant properties and conditions has increased lately. This increase has been driven by both financial and environmental advantages of such systems. Using a nondestructive hyperspectral imaging system improves the breeding process, increases profit, and reduces the usage of herbicide, thus reducing side effects to plants and environment. This paper is concerned with the use of hyperspectral image analysis for differentiating different plant species as well as their conditions. The main contribution of the work lies in the use of feature selection for choosing relevant, discriminant spectral information as the input to the classifier (e.g. SVM), as compared to the use of empirical spectral indices. Two independent hyperspectral datasets, captured by different instrumentations, were used in evaluation. Experimental results show significant improvements in classification accuracy with several feature selection algorithms compared to with the spectral vegetation and disease indices. The study shows that systematically selection of wavelength features can shed light on attributes that differentiate plants and their conditions.
Abstract-Recently, there has been a significant increase in the use of proximal or remote hyperspectral imaging systems to study plant properties, types, and conditions. Numerous financial and environmental benefits of using such systems have been the driving force behind this growth. This paper is concerned with the analysis of hyperspectral data for detecting plant diseases and stress conditions and classifying crop types by means of advanced machine learning techniques. Main contribution of the work lies in the use of an innovative classification framework for the analysis, in which adaptive feature selection, novelty detection, and ensemble learning are integrated. Three hyperspectral datasets and a nonimaging hyperspectral dataset were used in the evaluation of the proposed framework. Experimental results show significant improvements achieved by the proposed method compared to the use of empirical spectral indices and existing classification methods.Index Terms-Ensemble learning, feature selection, hyperspectral imaging (HSI), novelty detection (ND), plant monitoring, remote sensing, support vector machine (SVM).
BackgroundThe use of spectral imaging within the plant phenotyping and breeding community has been increasing due its utility as a non-invasive diagnostic tool. However, there is a lack of imaging systems targeted specifically at plant science duties, resulting in low precision for canopy-scale measurements. This study trials a prototype multispectral system designed specifically for plant studies and looks at its use as an early detection system for visually asymptomatic disease phases, in this case Pyrenopeziza brassicae in Brassica napus. The analysis takes advantage of machine learning in the form of feature selection and novelty detection to facilitate the classification. An initial study into recording the morphology of the samples is also included to allow for further improvement to the system performance.ResultsThe proposed method was able to detect light leaf spot infection with 92% accuracy when imaging entire oilseed rape plants from above, 12 days after inoculation and 13 days before the appearance of visible symptoms. False colour mapping of spectral vegetation indices was used to quantify disease severity and its distribution within the plant canopy. In addition, the structure of the plant was recorded using photometric stereo, with the output influencing regions used for diagnosis. The shape of the plants was also recorded using photometric stereo, which allowed for reconstruction of the leaf angle and surface texture, although further work is needed to improve the fidelity due to uneven lighting distributions, to allow for reflectance compensation.ConclusionsThe ability of active multispectral imaging has been demonstrated along with the improvement in time taken to detect light leaf spot at a high accuracy. The importance of capturing structural information is outlined, with its effect on reflectance and thus classification illustrated. The system could be used in plant breeding to enhance the selection of resistant cultivars, with its early and quantitative capability.
Abstract-Numerous environmental and financial benefits of using hyperspectral imaging have driven its increased applications on studying plant conditions. This paper is concerned with the analysis of hyperspectral images for plant discrimination by means of spectral and texture analysis approaches. The main contribution of the work lies in the use of a spectral-texture analysis based on both feature selection and Markov random field model to enhance prediction performance, as compared to conventional approaches. A hyperspectral dataset on control and stressed Arabidopsis plant leaves captured by a proximal hyperspectral imaging system was used in the experiment. Texture parameters with different orders were estimated from the MRF model and two SVM settings were used in the evaluation. Experimental results showed significant improvements in classification performance of the proposed spectral-texture approach over the conventional methods.
A texture enhanced spectral analysis framework is proposed for classifying hyperspectral images of plants of different conditions. Differentiating different plant conditions is important to precision agriculture as it helps detect diseases and stresses and optimise growth control. Advanced machine learning techniques are used to identify distinctive features in the spectral domain of hyperspectral images. In addition, texture properties are explored in the subband images. The framework integrates these two levels of properties at both feature extraction and classifying decision stages. The main crux of the work lies in the use of the significant spectral and texture features and a decision fusion mechanism to enhance the image properties, thus improving classification accuracy. Two hyperspectral datasets, originated from proximal hyperspectral systems, were used in the evaluation and significant improvements in classification accuracy achieved.
scite is a Brooklyn-based organization that helps researchers better discover and understand research articles through Smart Citations–citations that display the context of the citation and describe whether the article provides supporting or contrasting evidence. scite is used by students and researchers from around the world and is funded in part by the National Science Foundation and the National Institute on Drug Abuse of the National Institutes of Health.
hi@scite.ai
10624 S. Eastern Ave., Ste. A-614
Henderson, NV 89052, USA
Copyright © 2024 scite LLC. All rights reserved.
Made with 💙 for researchers
Part of the Research Solutions Family.