Development of Robust Hyperspectral Indices for Detection of Deviations of Normal Plant State
نویسندگان
چکیده
This research was conducted to assess the potential of hyperspectral indices to detect iron deficiency in capital-intensive multi-annual crop systems. A well-defined hyperspectral multi-layer dataset was constructed for a peach orchard in Zaragoza, Spain, consisting of hyperspectral measurements at various monitoring levels (leaf, crown, airborne). Trees were subjected to four different treatments of iron application (0 g / tree, 60 g / tree, 90 g / tree, and 120 g / tree). Groundbased measurements were used to characterise the on-site peach (Prunus persica L.) orchard in terms of chlorophyll, dry matter, water content, and leaf area index (LAI). Indices were extracted from the spectral profiles by means of band reduction techniques based on logistic regression and narrow-waveband ratioing involving all possible two-band combinations. Physiological interpretations extracted from leaf-level experiments were extrapolated to crownand airborne level. It was concluded from leaf level measurements that a decrease in leaf chlorophyll concentration resulted due to iron deficiency. The results suggested that spectral bands and narrow waveband ratio vegetation indices, selected via multivariate logistic regression classification, were able to distinguish iron untreated and iron treated trees (C-values>0.8). Moreover, the most appropriate indices obtained in this manner fulfilled the expectations by being highly correlated (R>0.6) to the measured chlorophyll concentrations. The visible part of the spectrum, mostly dominated by the amount of pigments (e.g. chlorophyll, carotenoids), provided the most discriminative spectral region (505 740 nm) in this study. The discriminatory performance of a combined chlorophyll and soil-adjusted vegetation index was compared to the results of the selected vegetation indices to estimate the effects of soil background and LAI on those indices.
منابع مشابه
3D Gabor Based Hyperspectral Anomaly Detection
Hyperspectral anomaly detection is one of the main challenging topics in both military and civilian fields. The spectral information contained in a hyperspectral cube provides a high ability for anomaly detection. In addition, the costly spatial information of adjacent pixels such as texture can also improve the discrimination between anomalous targets and background. Most studies miss the wort...
متن کاملDevelopment of a Robust Observer for General Form Nonlinear System: Theory, Design and Implementation
The problem of observer design for nonlinear systems has got great attention in the recent literature. The nonlinear observer has been a topic of interest in control theory. In this research, a modified robust sliding-mode observer (SMO) is designed to accurately estimate the state variables of nonlinear systems in the presence of disturbances and model uncertainties. The observer has a simple ...
متن کاملImproving the RX Anomaly Detection Algorithm for Hyperspectral Images using FFT
Anomaly Detection (AD) has recently become an important application of target detection in hyperspectral images. The Reed-Xialoi (RX) is the most widely used AD algorithm that suffers from “small sample size” problem. The best solution for this problem is to use Dimensionality Reduction (DR) techniques as a pre-processing step for RX detector. Using this method not only improves the detection p...
متن کاملFeature extraction of hyperspectral images using boundary semi-labeled samples and hybrid criterion
Feature extraction is a very important preprocessing step for classification of hyperspectral images. The linear discriminant analysis (LDA) method fails to work in small sample size situations. Moreover, LDA has poor efficiency for non-Gaussian data. LDA is optimized by a global criterion. Thus, it is not sufficiently flexible to cope with the multi-modal distributed data. We propose a new fea...
متن کاملTarget Detection Improvements in Hyperspectral Images by Adjusting Band Weights and Identifying end-members in Feature Space Clusters
Spectral target detection could be regarded as one of the strategic applications of hyperspectral data analysis. The presence of targets in an area smaller than a pixel’s ground coverage has led to the development of spectral un-mixing methods to detect these types of targets. Usually, in the spectral un-mixing algorithms, the similar weights have been assumed for spectral bands. Howe...
متن کامل