Optimal Wavebands Research Articles

Crop Discrimination Using Field Hyper Spectral Remotely Sensed Data

Crop discrimination through satellite imagery is still problematic. Accuracy of crop classification for high spatial resolution satellite imagery in the intensively cultivated lands of the Egyptian Nile delta is still low. Therefore, the main objective of this research is to determine the optimal hyperspectral wavebands in the spectral range of (400 - 2500 nm) to discriminate between two winter crops (Wheat and Clover) and two summer crops (Maize and Rice). This is considered as a first step to improve crop classification through satellite imagery in the intensively cultivated areas in Egypt. Hyperspectral ground measurements of ASD field Spec3 spectroradiometer was used to monitor the spectral reflectance profile during the period of the maximum growth stage of the four crops. 1-nm-wide was aggregated to 10-nm-wide bandwidths. After accounting for atmospheric windows and/or areas of significant noise, a total of 2150 narrow bands in 400 - 2500 nm were used in the analysis. Spectral reflectance was divided into six spectral zones: blue, green, red, near-infrared, shortwave infrared-I and shortwave infrared-II. One Way ANOVA and Tukey’s HSD post hoc analysis was performed to choose the optimal spectral zone that could be used to differentiate the different crops. Then, linear regression discrimination (LDA) was used to identify the specific optimal wavebands in the spectral zones in which each crop could be spectrally identified. The results of Tukey’s HSD showed that blue, NIR, SWIR-1 and SWIR-2 spectral zones are more sufficient in the discrimination between wheat and clover than green and red spectral zones. At the same time, all spectral zones were quite sufficient to discriminate between rice and maize. The results of (LDA) showed that the wavelength zone (727:1299 nm) was the optimal to identify clover crop while three zones (350:712, 1451:1562, 1951:2349 nm) could be used to identify wheat crop. The spectral zone (730:1299 nm) was the optimal to identify maize crop while three spectral zones were the best to identify rice crop (350:713, 1451:1532, 1951:2349 nm). An average of thirty measurements for each crop was considered in the process. These results will be used in machine learning process to improve the performance of the existing remote sensing software’s to isolate the different crops in intensive cultivated lands. The study was carried out in Damietta governorate of Egypt.

Rapid determination of preliminary thalassaemia screening indicators based on near-infrared spectroscopy with wavelength selection stability

A rapid determination method for the preliminary thalassaemia screening indicators—haemoglobin (Hb), mean corpuscular Hb (MCH) and mean corpuscular volume (MCV)—based on near-infrared (NIR) spectroscopy was developed. Wavelength selections were accomplished using the improved moving window partial least squares (MWPLS) method for stability. Each model was established using an approach based on randomness, similarity and stability to obtain objective, stable and practical models. The optimal wavebands screened using MWPLS were 1538 nm to 1756 nm for Hb and 968 nm to 1028 nm for MCH and MCV, which were within the NIR overtone region. The validation root mean square error, validation correlation coefficients and relative validation root mean square error of prediction were 3.9 g L−1, 0.972 and 2.9% for Hb; 1.41 pg, 0.958 and 4.8% for MCH; and 4.09 fL, 0.929 and 4.9% for MCV, respectively. The three models achieved high validation accuracy, and the Hb, MCH and MCV prediction values were close to the clinical measured values. Based on the cut-off values (MCH = 27.0 pg, MCV = 80.0 fL) for the routine method, the sensitivity and specificity both reached 100% based on the spectral-predicted MCH and MCV values in the validation set. The spectral prediction was highly accurate for determining negative and positive samples in preliminary thalassaemia screening. The proposed method is rapid and simple compared with the conventional method. This technique is a promising tool for preliminary thalassaemia screening in population prevention and control programmes. This study provides valuable references for designing specialised spectrometers.

Assessing biophysical variable parameters of bean crop with hyperspectral measurements

Recently high spectral resolution sensors have been developed, which allow new and more advanced applications in agriculture. Motivated by the increasing importance of hyperspectral remote sensing data, the need for research is important to define optimal wavebands to estimate biophysical parameters of crop. The use of narrow band vegetation indices (VI) derived from hyperspectral measurements acquired by a field spectrometer was evaluated to estimate bean (Phaseolus vulgaris L.) grain yield, plant height and leaf area index (LAI). Field canopy reflectance measurements were acquired at six bean growth stages over 48 plots with four water levels (179.5; 256.5; 357.5 and 406.2 mm) and tree nitrogen rates (0; 80 and 160 kg ha-1) and four replicates. The following VI was analyzed: OSNBR (optimum simple narrow-band reflectivity); NB_NDVI (narrow-band normalized difference vegetation index) and NDVI (normalized difference index). The vegetation indices investigated (OSNBR, NB_NDVI and NDVI) were efficient to estimate LAI, plant height and grain yield. During all crop development, the best correlations between biophysical variables and spectral variables were observed on V4 (the third trifoliolate leaves were unfolded in 50 % of plants) and R6 (plants developed first flowers in 50 % of plants) stages, according to the variable analyzed.

Vis/NIR hyperspectral imaging for detection of hidden bruises on kiwifruits

It is necessary to develop a non-destructive technique for kiwifruit quality analysis because the machine injury could lower the quality of fruit and incur economic losses. Bruises are not visible externally owing to the special physical properties of kiwifruit peel.We proposed the hyperspectral imaging technique to inspect the hidden bruises on kiwifruit. The Vis/NIR (408–1117 nm) hyperspectral image data was collected. Multiple optimal wavelength (682, 723, 744, 810, and 852 nm) images were obtained using principal component analysis on the high dimension spectral image data (wavelength range from 600 nm to 900 nm). The bruise regions were extracted from the component images of the five waveband images using RBF-SVM classification. The experimental results showed that the error of hidden bruises detection on fruits by means of hyperspectral imaging was 12.5%. It was concluded that the multiple optimal waveband images could be used to constructs a multispectral detection system for hidden bruises on kiwifruits.

Spectral Discrimination of Opium Poppy Using Field Spectrometry

Opium is a narcotic obtained from opium poppy and is the raw material of heroin for the illegal drug trade. Monitoring the illegal concentrated cultivation of opium poppy in major regions is critical for the understanding by governments and international communities of the scale of illegal drug trade. This paper investigates whether opium poppy can be discriminated from its coexisting plants using analytical-spectral-device field spectrometer data in the visible to short-wave infrared spectral range. Canopy spectral measurements were conducted during three different growth periods of opium poppy. A synthetic method with three analysis levels was applied to discriminate opium poppy from other species and to select optimal bands for opium poppy discrimination. First, the Mann-Whitney U-test method was used to test the spectral reflectance difference between opium poppy and coexisting crops at each wavelength. Then, the Jeffries-Matusita distance and band correlation analysis were conducted to select the optimal wavebands for discriminating opium poppy using the significant wavebands from the test results. Finally, classification and regression tree analysis was employed to validate the classification accuracy based on the selected optimal wavebands. The results indicated that the spectral reflectance of opium poppy was significantly different from that of coexisting crops in many surveyed wavebands, and opium poppy could be discriminated using a field survey spectrum at canopy level. The best time for discriminating opium poppy from coexisting crops was around flowering time. This paper provided the prerequisite for monitoring opium poppy using satellite remote sensing data in some regions of concern.

Waveband selection for NIR spectroscopy analysis of soil organic matter based on SG smoothing and MWPLS methods

Savitzky–Golay (SG) smoothing and moving window partial least square (MWPLS) methods were applied to the model optimization and the waveband selection for near-infrared (NIR) spectroscopy analysis of soil organic matter. The optimal single wavelength prediction bias (OSWPB) was used to evaluate the similarity of calibration set and prediction set, and a new division method for calibration set and prediction set was proposed. SG smoothing modes were expanded to 540 kinds. The specific computer algorithm platforms for optimization of SG smoothing mode combined with PLS factor and for MWPLS method with changeable parameters were built up. The optimal waveband for soil organic matter was 1926–2032 nm, the optimal smoothing mode was the 2nd order derivative, 6th degree polynomial, 45 smoothing points, the PLS factor, RMSEP and R P were 8, 0.260 (%) and 0.877 respectively. The prediction effect was obviously better than that in the whole spectral collecting region. To get stable results, all the optimization processes were based on the average prediction effect on 50 different divisions of calibration set and prediction set.

Waveband Selection of NIR Spectroscopy Analysis for Glucose Aqueous Solution Based on Savitzky-Golay Smoothing

The high accurate partial least squares (PLS) models of near-infrared (NIR) spectroscopy analysis for glucose aqueous solution were established by large-scale simultaneous optimization of Savitzky-Golay (SG) smoothing mode and PLS factor. A total of 6 wavebands were used for modelling respectively. The model prediction effect with SG smoothing was obviously better than ones without SG smoothing for each waveband, it indicated that the large-scale simultaneous optimization of SG smoothing mode and PLS factor could obviously improve model prediction effect. The optimal waveband was the combination of 400-1880 and 2082-2350 nm, the optimal SG smoothing mode was 1st order derivative smoothing, 2nd degree polynomial, 63 smoothing points, and the corresponding PLS factor, RMSEP and RP were 14, 0.289 mmol/L and 0.9996 respectively. The combination of 1100-1880 and 2082-2350 nm was also a waveband with high signal to noise ratio for glucose, could replace the whole spectral collecting region and get very good prediction effect, which could provide valuable references for designing spectrophotometer system in special NIR spectrometer. To get the stable prediction results, all models and results were obtained based on the average data on 30 different divisions of calibration set and prediction set.

Classification of sugar beet and volunteer potato reflection spectra with a neural network and statistical discriminant analysis to select discriminative wavelengths

The objectives of this study were to determine the reflectance properties of volunteer potato and sugar beet and to assess the potential of separating sugar beet and volunteer potato at different fields and in different years, using spectral reflectance characteristics. With the ImspectorMobile, vegetation reflection spectra were successfully repeatedly gathered in two fields, on seven days in 2 years that resulted in 11 datasets. Both in the visible and in the near-infrared reflection region, combinations of wavelengths were responsible for discrimination between sugar beet and volunteer potato plants. Two feature selection methods, discriminant analysis (DA) and neural network (NN), succeeded in selecting sets of discriminative wavebands, both for the range of 450–900 and 900–1650 nm. First, 10 optimal wavebands were selected for each of the 11 available datasets individually. Second, by calculating the discriminative power of each selected waveband, 10 fixed wavebands were selected for all 11 datasets analyses. Third, 3 fixed wavebands were determined for all 11 datasets. These three wavebands were chosen because these had been selected by both DA and NN and were for sensor 1: 450, 765, and 855 nm and for sensor 2: 900, 1440, and 1530 nm. With the resulting three sets of wavebands, classifications were performed with a DA, a neural network with 1 hidden neuron (NN1) and a neural network with two hidden neurons (NN2). The maximum classification performance was obtained with the near-infrared sensor coupled to the NN2 method with an optimal adapted set of 10 wavebands, where the percentages were 100 ± 0.1 and 1 ± 1.3% for true negative (TN) classified volunteer potato plants and false negative (FN) classified sugar beet plants respectively. In general the NN2 method gave the best classification results, followed by DA and finally the NN1 method. When the optimal adapted waveband sets were generalized to a set of 10 fixed wavebands, the classification results were still at a reasonable level of a performance at 87% TN and 1% FN for the NN2 classification method. However, when a further reduction and generalization was made to 3 fixed wavebands, the classification results were poor with a minimum performance of 69% TN and 3% FN for the NN2 classification method. So, these results indicate that for the best classification results it is required that the sensor and classification system adapt to the specific field situation, to optimally discriminate between volunteer potato and sugar beet pixel spectra.

Optimal waveband identification for estimation of leaf area index of paddy rice

The objectives of the study were to select suitable wavebands for rice leaf area index (LAI) estimation using the data acquired over a whole growing season, and to test the efficiency of the selected wavebands by comparing them with feature positions of rice canopy spectra. In this study, the field experiment in 2002 growing season was conducted at the experimental farm of Zhejiang University, Hangzhou, China. Measurements of hyperspectral reflectance (350 approximately 2500 nm) and corresponding LAI were made for a paddy rice canopy throughout the growing season. And three methods were employed to identify the optimal wavebands for paddy rice LAI estimation: correlation coefficient-based method, vegetation index-based method, and stepwise regression method. This research selected 15 wavebands in the region of 350~2 500 nm, which appeared to be the optimal wavebands for the paddy rice LAI estimation. Of the selected wavebands, the most frequently occurring wavebands were centered around 554, 675, 723, and 1 633 nm. They were followed by 444, 524, 576, 594, 804, 849, 974, 1 074, 1 219, 1 510, and 2 194 nm. Most of them made physical sense and had their counterparts in spectral known feature positions, which indicates the promising potential of the 15 selected wavebands for the retrieval of paddy rice LAI.

Determining optimal wavebands using genetic algorithm for detection of internal insect infestation in tart cherry

This paper reports the results of waveband selection for detecting internal insect infestation in tart cherries as a precursor to development of a dedicated multispectral vision system. A genetic algorithm (GA) approach was applied on hyperspectral transmittance images (580–980 nm) and reflectance spectral data (590–1,550 nm) acquired from both intact and infested tart cherries. The GA analysis indicates that the ability of using transmittance imaging approach for detecting internal insect infestation in tart cherries would be limited. According to the GA analysis on the reflectance spectra, visible wavelengths were of less importance than NIR wavelengths for the purpose of distinguishing intact cherries from infested ones. The PLSDA results indicate that models built with three or four GA selected wavelength regions gave similar classification accuracy to the model built with full wavelength region, which demonstrates the efficiency of the GA variable selection procedure. However, due to the stochastic nature of the GA, the efficiency of using these wavebands in a multispectral vision system needs to be verified in future work.

ASSESSING THEHYPERSPECTRAL REMOTE SENSING DATA TO DIAGNOSIS CROP VARIABLES MODEL IN TROPICAL IRRIGATED WETLAND RICE

Canopy spectral measureme~t using ground-based hyperspectral r;levice and rice crop variables such as leaf area index (LAI), leaf dry weight (LDW) and SPAD values were done periodically during growth season with involving three rice cultivars (Pandanwangi, Ciherang and IR Jumbo) ahd four nitrogen application levels (NO,N80, N92 and NI03 kg/ha). Thestudy is directed to explore all possible waveband combinations tested in reflectance of vegetation indices (VIs) and to develop a predictive model of relation between hyperspectral-based vegetation indiceswith rice crop variables. . Analysis of all possible two-pair waveband combinations used in VIs was investigated with 6,786 combinations to gain optimal waveband attributed to crop variables. To develop.efficient and accurate model, various multivariate regression models were examined with ten-fold cross validations. Accuracy validation of predicted model was performed using reflectance and FDR, NDVI, RVI, RDVI and SA VI data. Validation of predictive model using flJR implied better accuracy to estimate LAI using whole season data (R2=0.856). Meanwhile, the model using SA VI denoted highest values (R2=0.852)for predicting LAI While the validation of predictive model using RVI implied the highest values (K=O. 797) for predicting LDW. Moreover, the test of predictive model using SAVI indicated the highest value (R2=0.658) for predicting SPAD values. According to overall validation using VIs, it seems that RVI has the best accuracy to validate the predictive model of LAI than those of LDW or SPAD values. Meanwhile, the most significant of K to validate the predictive model was obtained on FDR data with R2=0.859for LAl

Hyperspectral field reflectance measurements to estimate wheat grain yield and plant height

Hyperspectral crop reflectance data are useful for several remote sensing applications in agriculture, but there is still a need for studies to define optimal wavebands to estimate crop biophysical parameters. The objective of this work is to analyze the use of narrow and broad band vegetation indices (VI) derived from hyperspectral field reflectance measurements to estimate wheat (Triticum aestivum L.) grain yield and plant height. A field study was conducted during the winter growing season of 2003 in Campinas, São Paulo State, Brazil. Field canopy reflectance measurements were acquired at six wheat growth stages over 80 plots with four wheat cultivars (IAC-362, IAC-364, IAC-370, and IAC-373), five levels of nitrogen fertilizer (0, 30, 60, 90, and 120 kg of N ha-1) and four replicates. The following VI were analyzed: a) hyperspectral or narrow-band VI (1. optimum multiple narrow-band reflectance, OMNBR; 2. narrow-band normalized difference vegetation index, NB_NDVI; 3. first- and second-order derivative of reflectance; and 4. four derivative green vegetation index); and b) broad band VI (simple ratio, SR; normalized difference vegetation index, NDVI; and soil-adjusted vegetation index, SAVI). Hyperspectral indices provided an overall better estimate of biophysical variables when compared to broad band VI. The OMNBR with four bands presented the highest R² values to estimate both grain yield (R² = 0.74; Booting and Heading stages) and plant height (R² = 0.68; Heading stage). Best results to estimate biophysical variables were observed for spectral measurements acquired between Tillering II and Heading stages.

Nitrogen detection with hyperspectral normalized ratio indices across multiple plant species

The main focus of recent studies relating vegetation leaf chemistry with remotely sensed data is the prediction of chlorophyll and nitrogen content using indices based on a combination of bands from the red and infrared wavelengths. The use of high spectral resolution data offers the opportunity to select the optimal wavebands for predicting plant chemical properties. In order to test the optimal band combinations for predicting nitrogen content, normalized ratio indices were calculated for all wavebands between 350 and 2200 nm for five different species. The correlation between these indices and the nitrogen content of the samples was calculated and compared between species. The results show a strong correlation between individual normalized ratio indices and the nitrogen content for different species. The spectral regions that are most effective for predicting nitrogen content are, for each individual species, different from the normalized difference vegetation index (NDVI) spectral region. By combining the areas of maximum correlation it was possible to determine the optimal spectral regions for predicting leaf nitrogen content across species. In a cross‐species situation, normalized ratio indices using the combination of reflectance at 1770 nm and at 693 nm may give the best relation to nitrogen content for individual species.

Uses of Hyperspectral and Multispectral Laser Induced Fluorescence Imaging Techniques for Food Safety Inspection

Spectral imaging including machine vision and multispectral imaging can provide a rapid, nondestructive means to assess agricultural commodities for their quality and safety for human consumption. These nondestructive techniques generally rely on reflectance measurements; the most commonly used spectral regions range through the visible (Vis) to the near infrared (NIR). Another optical sensing technique is based on fluorescence that is generally regarded as more sensitive optical sensing tools compared to reflectance techniques. Recently, we developed two imaging systems for food safety research; a laboratory-based hyperspectral imaging system capable of both reflectance and fluorescence measurements and a multispectral laser induced fluorescence imaging system. Because many contiguous spectral bands are acquired with each hyperspectral image pixel, the resulting data quantity makes uses of hyperspectral imaging spectrometer for on-line food safety inspection impractical. Instead, the spectral and spatial information is used to determine several optimal wavebands that can be implemented to a multispectral imaging system. We present a systematic method for using hyperspectral image data to identify few wavebands to be used in multispectral detection systems. Also presented is a two-band ratio as a multispectral fusion method along with automated detection for animal feces contamination on apples. The fluorescence imaging techniques demonstrated that even minute animal feces, not clearly visible to human eye, could be detected. Practical considerations for development of multispectral fluorescence imaging systems for on-line uses are also discussed.