Hyperspectral NIR image regression part I: calibration and correction

Burger, James; Geladi, Paul

doi:10.1002/cem.938

Cited by 107 publications

(66 citation statements)

References 18 publications

(19 reference statements)

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The pre-flight reference calibration with one calibration panel represents a one-point calibration. Burger and Geladi (2006) mentioned the beneficial effect of calibration targets with different grayscale intensities (multi-point calibration). Measuring multiple targets before the flight would add complexity to the pre-flight procedures and eventually reduce flight time due to battery consumption.…”

Section: Oktoxl With Gimbalmentioning

confidence: 99%

Introduction and preliminary results of a calibration for full-frame hyperspectral cameras to monitor agricultural crops with UAVs

Aasen

Bendig

Bolten

et al. 2014

Int. Arch. Photogramm. Remote Sens. Spatial Inf. Sci.

View full text Add to dashboard Cite

ABSTRACT:Hyperspectral remote sensing helps to acquire information about the status of agricultural crops to allow optimized management practices in the context of precision agriculture. Due to technological innovations small and lightweight hyperspectral sensors have become available which may be carried by unmanned aerial vehicles (UAVs). In this paper we give a brief overview over existing hyperspectral sensors for UAVs. We focus on a new type of full-frame sensors which capture hyperspectral information in two dimensional image frames. We then develop a calibration procedure for these sensors and identify challenges in remote sensing of vegetation. The calibration is evaluate by in-field data acquired during a flight campaign. The spectral calibration shows good results with less than three percent difference in reflection for 110 of the 125 bands (458 to 886 nm).

show abstract

Section: Oktoxl With Gimbalmentioning

confidence: 99%

Introduction and preliminary results of a calibration for full-frame hyperspectral cameras to monitor agricultural crops with UAVs

Aasen

Bendig

Bolten

et al. 2014

Int. Arch. Photogramm. Remote Sens. Spatial Inf. Sci.

View full text Add to dashboard Cite

show abstract

“…These standards permitted additional corrections or instrument standardization. A detailed description of these external and internal standards, and their modeling algorithms has been given in a previous publication [1]. Figure 1(a) shows a typical image at one wavelength, including the internal standard gray scale.…”

Section: Hyperspectral Imagesmentioning

confidence: 99%

“…In a previous paper [1] it was explained how to convert hyperspectral images usually collected as A/D converter counts into corrected diffuse reflectance values. For this correction purpose, external (between-image) and internal (within-image) Spectralon [2] UV-Vis-NIR standard reflectance materials were used together with two-point, linear and nonlinear correction equations.…”

Section: Introductionmentioning

confidence: 99%

Hyperspectral NIR image regression part II: dataset preprocessing diagnostics

Burger

Geladi

2006

Journal of Chemometrics

Self Cite

View full text Add to dashboard Cite

When known reference values such as concentrations are available, the spectra from near infrared (NIR) hyperspectral images can be used for building regression models. The sets of spectra must be corrected for errors, transformed to reflectance or absorbance values, and trimmed of bad pixel outliers in order to build robust models and minimize prediction errors. Calibration models can be computed from small (<100) sets of spectra, where each spectrum summarizes an individual image or spatial region of interest (ROI), and used to predict large (>20 000) test sets of spectra. When the distributions of these large populations of predicted values are viewed as histograms they provide mean sample concentrations (peak centers) as well as uniformity (peak widths) and purity (peak shape) information. The same predicted values can also be viewed as concentration maps or images adding spatial information to the uniformity or purity presentations. Estimates of large population statistics enable a new metric for determining the optimal number of model components, based on a combination of global bias and pooled standard deviation values computed from multiple test images or ROIs. Two example datasets are presented: an artificial mixture design of three chemicals with distinct NIR spectra and samples of different cheeses. In some cases it was found that baseline correction by taking first derivatives gave more useful prediction results by reducing optical problems. Other data pretreatments resulted in negligible changes in prediction errors, overshadowed by the variance associated with sample preparation or presentation and other physical phenomena.

show abstract

“…These spikes are related to dead pixels that are due to a few elements in the detector responding with an unusually high or low value. 27 All spectra with absorbance higher than 1.5 at 1740 nm, corresponding to conveyor belt absorbance, were also removed. Due to noise at the beginning and the end of spectra, only the 150 wavelengths between 1432 and 2368 nm were maintained.…”

Section: Methodsmentioning

confidence: 99%

NIR hyperspectral imaging spectroscopy and chemometrics for the discrimination of roots and crop residues extracted from soil samples

Eylenbosch

Bodson

Baeten

et al. 2017

Journal of Chemometrics

View full text Add to dashboard Cite

Roots play a major role in plant development. Their study in field conditions is important to identify suitable soil management practices for sustainable crop productions. Soil coring, which is a common method in root production measurement, is limited in sampling frequency due to the hand-sorting step. This step, needed to sort roots from other elements extracted from soil cores like crop residues, is time consuming, tedious, and vulnerable to operator ability and subjectivity. To get rid of the cumbersome hand-sorting step, avoid confusion between these elements, and reduce the time needed to quantify roots, a new procedure, based on near-infrared hyperspectral imaging spectroscopy and chemometrics, has been proposed. It was tested to discriminate roots of winter wheat (Triticum aestivum L.) from crop residues and soil particles.Two algorithms (support vector machine and partial least squares discriminant analysis) have been compared for discrimination analysis. Models constructed with both algorithms allowed the discrimination of roots from other elements, but the best results were reached with models based on support vector machine. The ways to validate models, with selected spectra or with hyperspectral images, provided different kinds of information but were complementary. This new procedure of root discrimination is a first step before root quantification in soil samples with near-infrared hyperspectral imaging. The results indicate that the methodology could be an interesting tool to improve the understanding of the effect of tillage or fertilization, for example, on root system development. conditions. The potential of plants to obtain water and mineral nutrients from the soil is primarily attributed to their capacity to develop extensive root systems.2 Studies on root development are important for a better understanding of the interaction between crop root systems and the growing environment to identify suitable soil management practices for sustainable crop productions. 4 The time taken by roots to colonize the deep soil profile and the root system biomass production during the whole crop development cycle are therefore good indicators to interpret crop behavior in various management modes and in a given soilclimate context. Nevertheless, roots are rarely directly evaluated in field experiments because soil limits accessibility for their observation. 1,5 Therefore, they need to be extracted from soil before any measurement can be made.Soil coring is a commonly used method to sample roots in field experiments and measure their production. 6 This technique is not expensive and allows repeated measurements during crop growth at several soil depths. After soil coring, cores need to be washed to extract roots from soil. Others elements, mainly crop residues buried in crop soils, are also extracted during the washing step and need to be separated from roots, commonly by hand-sorting, before any analysis or quantification of roots. 1,4,5,[7][8][9][10] This sorting step is time-consuming, tedious, an...

show abstract

Hyperspectral NIR image regression part I: calibration and correction

Cited by 107 publications

References 18 publications

Introduction and preliminary results of a calibration for full-frame hyperspectral cameras to monitor agricultural crops with UAVs

Introduction and preliminary results of a calibration for full-frame hyperspectral cameras to monitor agricultural crops with UAVs

Hyperspectral NIR image regression part II: dataset preprocessing diagnostics

NIR hyperspectral imaging spectroscopy and chemometrics for the discrimination of roots and crop residues extracted from soil samples

Contact Info

Product

Resources

About