Automated Endmember Extraction Research Articles

Spectral mixture analysis of AVIRIS-NG hyperspectral data for material identification and classification for the part of Kolkata city

Identification and extraction of material in the urban scenario are always challenging due to the presence of different heterogeneous materials. Airborne hyperspectral sensors with the advantage of both high spectral and spatial resolution can be used in such areas for the identification and mapping of urban materials. Manual extraction of the endmembers in highly dense heterogeneous urban regions is a very difficult task to achieve, but with automated extraction techniques, it yields promising results. To counter the mixed pixels problem in heterogeneous urban areas automated endmember extraction techniques like Endmember Average RMS (EAR), Minimum Average Spectral Angle (MASA), and Count Based Endmember Selection (CoB) was used for pure endmember identification in the densely populated urban area of Kolkata region using AVIRIS NG imagery. Spectral Unmixing Multiple Endmember Spectral Mixture Analysis (MESMA), Linear Spectral Unmixing (LSU), and Mixture Tuned Matched Filtering (MTMF) was performed on AVIRIS NG data using the extracted endmembers of different urban materials. The rule-based classification was performed on abundance images obtained from MESMA, MTMF, and LSU techniques for comparative analysis. Classification using MESMA abundance images outperformed in mapping mixed urban environments with an overall accuracy (OA) of 88.6 % followed by the rule-based classified output of MTMF and LSU with OA of 75.27% and 72.45% respectively.

Evaluating automated endmember extraction for classifying hyperspectral data and deriving spectral parameters for monitoring forest vegetation health.

The hyperspectral remote sensing datasets possess high capability in differentiating the spectrally similar features, and thus, they are immensely important in various forestry activities, especially vegetation classifications. But extracting endmembers for data training is a challenging task. The present study is focused on the use of automated endmember extraction technique for deriving endmembers during the unavailability of ground spectra. We used the Sequential Maximum Angle Convex Cone (SMACC) method on EO-1 Hyperion data for endmember extraction in the Barkot forest range of Dehradun district, Uttarakhand which were used for classification of the study area using support vector machine (SVM). Further, we estimated the vegetation health of the region by assigning the threshold weights for various derived environmental variables such as NDVI (Normalised Difference Vegetation Index), CRI (Carotenoid Reflectance Index), Anthocyanin Reflectance Index (ARI), Modified Simple Ratio (MSR), Modified Chlorophyll Absorption Ratio Index (MCARI) and WBI (Water Band Index). Then, to further validate the health of the forest types, we correlated it with the Land Surface Temperature (LST) from LANDSAT 5 ETM + data. The results showed a high classification accuracy of 89.13%. The healthy vegetation area coverage of the area was about 78.6% with most healthy class as Tectona grandis and Shorea robusta and its correlation with LST showed lower temperature range in healthy vegetation areas and vice versa. The study was useful in determining the superiority of SMACC automated endmember extraction and estimating the vegetation health.

An assessment of background removal approaches for improved estimation of rice leaf nitrogen concentration with unmanned aerial vehicle multispectral imagery at various observation times

Background effect is a crucial limitation for the monitoring of leaf nitrogen concentration (LNC) in crops with unmanned aerial vehicle (UAV) multispectral imagery. Some background removal approaches have been developed for improve the estimation of LNC, but their performances are not compared in one study and it is unclear whether they are sensitive to the observation time of UAV imagery. This study evaluated three background removal approaches, i.e., the soil-adjusted vegetation index (SAVI) approach, the green pixel vegetation index approach (GPVI) and abundance adjusted vegetation index (AAVI), for estimating rice LNC from UAV-based multispectral imagery at individual and across growth stages as well as different observation times of the day. The red edge chlorophyll index (CIre) was chosen as the common basis for the last two approaches. In particular, the AAVI approach was refined with a higher number of endmembers and automated endmember extraction, and further evaluated for assessing the effect of separating sunlit components from shaded components of the canopy. Our results demonstrated that the vegetation indices (VIs) for off-noon observation times showed better relationships with LNC than those for noon at individual and across growth stages. Compared to both SAVI and CIre-green, the AACIre for all pixels (AACIre-all) exhibited the weakest sensitivity to observation time and yielded the best relationships for single-stage (jointing: r2=0.70, booting: r2=0.76, heading: r2=0.70) and across-stage (r2=0.66) models. Among the AAVIs derived from three categories of pixels, the AACIre-sunlit (R2 =0.90, RMSE=0.17%, Bias=0.03%) outperformed AACIre-all (R2 =0.85, RMSE=0.23%, Bias=0.08%) and then AACIre-shaded (R2 =0.38, RMSE=0.49%, Bias=0.40%) remarkably for the estimation accuracy of LNC. This study suggests that the refined AAVI approach has great value in reducing the background effect for more accurate monitoring of growth parameters and could be extended to other crops and regions for improved precision crop management and field-based high-throughput phenotyping.

Snow Cover Estimation From Image Time Series Based on Spectral Unmixing

A method based on spectral unmixing (SU) for snow cover estimation from a time series of optical images is proposed in this letter. Specifically, we have developed an endmember estimation procedure that exploits the temporal continuity of a scene. Consecutive dates are jointly processed for a more precise description of background materials improving the estimation of a fractional snow cover map. The proposed workflow relies on up to three consecutive acquisitions over the same area to extract an appropriate set of background spectra to be considered as endmembers. In greater details, multiple sets of endmembers are extracted from different images in the time series by a geometrical automated endmember extraction algorithm and the most relevant one is selected in terms of reconstruction error. Snow cover maps are then estimated by SU considering as endmembers the snow spectra coming from a spectral library and those associated with the background materials as estimated by the proposed procedure. The proposed technique is quantitatively validated considering Moderate-Resolution Imaging Spectroradiometer Terra data over the French Alps and Moroccan High Atlas image time series and comparing the estimated snow cover maps with high-resolution reference data. The experiment clearly demonstrates the effectiveness of the generated set of endmembers using three different approaches to abundance estimation.

Feasibility for detection of autofluorescent signatures in rat organs using a novel excitation-scanning hyperspectral imaging system.

The natural fluorescence (autofluorescence) of tissues has been noted as a biomarker for cancer for several decades. Autofluorescence contrast between tumors and healthy tissues has been of significant interest in endoscopy, leading to development of autofluorescence endoscopes capable of visualizing 2-3 fluorescence emission wavelengths to achieve maximal contrast. However, tumor detection with autofluorescence endoscopes is hindered by low fluorescence signal and limited quantitative information, resulting in prolonged endoscopic procedures, prohibitive acquisition times, and reduced specificity of detection. Our lab has designed a novel excitation-scanning hyperspectral imaging system with high fluorescence signal detection, low acquisition time, and enhanced spectral discrimination. In this study, we surveyed a comprehensive set of excised tissues to assess the feasibility of detecting tissue-specific pathologies using excitation-scanning. Fresh, untreated tissue specimens were imaged from 360 to 550 nm on an inverted fluorescence microscope equipped with a set of thin-film tunable filters (Semrock, A Unit of IDEX). Images were subdivided into training and test sets. Automated endmember extraction (ENVI 5.1, Exelis) with PCA identified endmembers within training images of autofluorescence. A spectral library was created from 9 endmembers. The library was used for identification of endmembers in test images. Our results suggest (1) spectral differentiation of multiple tissue types is possible using excitation scanning; (2) shared spectra between tissue types; and (3) the ability to identify unique morphological features in disparate tissues from shared autofluorescent components. Future work will focus on isolating specific molecular signatures present in tissue spectra, and elucidating the contribution of these signatures in pathologies.

Automated Extraction of Image-Based Endmember Bundles for Improved Spectral Unmixing

Spectral unmixing is an important task in hyperspectral data exploitation. It amounts to estimating the abundance of pure spectral constituents (endmembers) in each (possibly mixed) observation collected by the imaging instrument. In recent years, several endmember extraction algorithms (EEAs) have been proposed for automated endmember extraction from hyperspectral data sets. Traditionally, EEAs extract/select only one single standard endmember spectrum for each of the presented endmember classes or scene components. The use of fixed endmember spectra, however, is a simplification since in many cases the conditions of the scene components are spatially and temporally variable. As a result, variation in endmember spectral signatures is not always accounted for and, hence, spectral unmixing can lead to poor accuracy of the estimated endmember fractions. Here, we address this issue by developing a simple strategy to adapt available EEAs to select multiple endmembers (or bundles) per scene component. We run the EEAs in randomly selected subsets of the original hyperspectral image, and group the extracted samples of pure materials in a bundle using a clustering technique. The output is a spectral library of pure materials, extracted automatically from the input scene. The proposed technique is applied to several common EEAs and combined with an endmember variability reduction technique for unmixing purposes. Experiments with both simulated and real hyperspectral data sets indicate that the proposed strategy can significantly improve fractional abundance estimations by accounting for endmember variability in the original hyperspectral data.

Spectral unmixing of normalized reflectance data for the deconvolution of lichen and rock mixtures

In subarctic regions the ubiquitous presence of rock encrusting lichens compromises the ability to map the reflectance signatures of minerals from imaging spectrometer data. The use of lichen as an endmember in spectral mixture analysis (SMA) may overcome these limitations. Because lichens rarely completely occupy the Instantaneous Field of View (IFOV), it is difficult to define a lichen endmember from an image using visual or automated endmember extraction tools. Spectral similarity of various crustose/foliose lichen species in the short wave infrared (SWIR) suggests that spectral unmixing of rock and lichens may be successfully accomplished using a single lichen endmember for this spectral range. We report the use of a spectral normalization method to minimize differences in SWIR reflectance between five lichen species ( U. torrefacta, R. bolanderi, R. geminatum, R. geographicum, A. cinerea). When the normalization is applied to reflectance spectra from 2000–2400 nm acquired for a lichen encrusted quartzite rock sample we show that only a single lichen endmember is required to account for the lichen contribution in the observed mixtures. In contrast, two such endmembers are required when the normalization is not applied to the reflectance data. We illustrate this point using examples where endmembers are extracted manually and automatically, and compare the SMA results against abundances estimated from digital photography. For both the reflectance and normalized reflectance data, SMA results correlate well ( R 2>0.9) with abundances estimated from digital photography. The use of normalized reflectance implies that any field/laboratory lichen spectrum can be selected as the lichen endmember for SMA of airborne/spaceborne imagery.