USING PIXEL-BASED AND OBJECT-BASED METHODS TO CLASSIFY URBAN HYPERSPECTRAL FEATURES

Integrated management of forest ecosystems requires an accurate and all-sided mastery of the forest information, of which forest ecosystem cover especially at tree species level is the most basic and important component. The study investigated and demonstrated the mapping potential of the forest ecosystem at tree species level from high spatial resolution hyperspectral images. The mapping performances of eight conventional classification methods including Maximum Likelihood (ML), Mahalanobis Distance (MaD), Minimum Distance (MD), Parallelepiped (P), Binary Encoding (BE), Spectral Angle Mapper (SAM), Spectral Information Divergence (SID) and Support Vector Machine (SVM), were verified based on two noise treatments (noise fraction and noise removal) and three leaf growth periods (tender leaf period, young leaf period and adult leaf period). It could be confirmed that noise removal obviously contributed to improving the classification agreement and young leaf period was most suitable for mapping forest ecosystem at tree species level from high spatial resolution hyperspectral images. ML, P, BE and SID were not considered appropriate according to good results with overall accuracy and kappa coefficient exceeding 85% and 0.80 respectively. Though MD also produced a very high classification agreement, it could not cover up its poor potential to identify tree species by spectral features. Even if SVML, SVMP, SVMR and SVMS performed the stablest and could generate good results across three periods, the best result was obtained by SAM. Except that the difference was significant between MD and SVMS at the 5% significance level in tender leaf period, the comparative tests did not provide more proof to show the significant difference between the methods considered appropriate.

The authors propose an information theoretic criterion, called spectral information divergence (SID) for spectral similarity and discriminability. It is derived from the concept of divergence arising in information theory and can be used to describe the statistics of a spectrum. Unlike spectral angle mapper (SAM) which extracts geometric features between two spectra, SID views each pixel spectrum as a random variable and then measures the discrepancy of probabilistic behaviors between two spectra. In order to evaluate SID, SAM is used for comparison via hyperspectral data. Experimental results show that SID can characterise spectral similarity and variability more effectively than SAM.

Remote sensing detection of gold related alteration zones in Um Rus area, Central Eastern Desert of Egypt

This paper uses simulated annealing and focus on the spectral angle mapper (SAM), to demonstrate how the separability of two mean spectra from different species can be increased by choosing the bands that maximize the metric. It is known that classification performance is enhanced when the differences in mean spectra for each end-member species are maximized. Comparison was made using the selected bands derived from the proposed method, to all bands in the electromagnetic spectrum (EMS), only the bands in the visible, near infrared and short wave infrared regions of the EMS and selected bands using stepwise discriminant analysis. The bands from the proposed method often indicates a better choice of band selection as viewed by the summary statistics for (a) the SAM measurements, (b) the correlations between bands and (c) the spectral information divergence (SID), for each pair of species; and the classification accuracy of SAM and SID.

A hyperspectral image can be considered as an image cube where the third dimension is the spectral domain represented by hundreds of spectral wavelengths. As a result, a hyperspectral image pixel is actually a column vector with dimension equal to the number of spectral bands and contains valuable spectral information that can be used to account for pixel variability, similarity and discrimination. We present a new hyperspectral measure, the spectral information measure (SIM), to describe spectral variability and two criteria, spectral information divergence and spectral discriminatory probability for spectral similarity and discrimination, respectively. The spectral information measure is an information-theoretic measure which treats each pixel as a random variable using its spectral signature histogram as the desired probability distribution. Spectral information divergence (SID) compares the similarity between two pixels by measuring the probabilistic discrepancy between two corresponding spectral signatures. The spectral discriminatory probability calculates spectral probabilities of a spectral database (library) relative to a pixel to be identified so as to achieve material identification. In order to compare the discriminatory power of one spectral measure relative to another, a criterion is also introduced for performance evaluation, which is based on the power of discriminating one pixel from another relative to a reference pixel. The experimental results demonstrate that the new hyperspectral measure can characterize spectral variability more effectively than the commonly used spectral angle mapper (SAM).

In this paper, we evaluate the capability of the high spatial resolution airborne Digital Airborne Imaging System (DAIS) imagery for detailed vegetation classification at the alliance level with the aid of ancillary topographic data. Image objects as minimum classification units were generated through the Fractal Net Evolution Approach (FNEA) segmentation using eCognition software. For each object, 52 features were calculated including spectral features, textures, topographic features, and geometric features. After statistically ranking the importance of these features with the classification and regression tree algorithm (CART), the most effective features for classification were used to classify the vegetation. Due to the uneven sample size for each class, we chose a non-parametric (nearest neighbor) classifier. We built a hierarchical classification scheme and selected features for each of the broadest categories to carry out the detailed classification, which significantly improved the accuracy. Pixel-based maximum likelihood classification (MLC) with comparable features was used as a benchmark in evaluating our approach. The objectbased classification approach overcame the problem of saltand-pepper effects found in classification results from traditional pixel-based approaches. The method takes advantage of the rich amount of local spatial information present in the irregularly shaped objects in an image. This classification approach was successfully tested at Point Reyes National Seashore in Northern California to create a comprehensive vegetation inventory. Computer-assisted classification of high spatial resolution remotely sensed imagery has good potential to substitute or augment the present ground-based inventory of National Park lands.

The successful implementation of Spectral Matching Measures (SMMs) often plays a crucial role in material discrimination and classification using hyperspectral dataset. The commonly exploited SMMs, such as Spectral Angle Mapper (SAM), Spectral Information Divergence (SID), and their hybrid, i.e., SIDSAMtan, show limited discrimination ability while discriminating spectrally similar materials. This study presents three new effective SMMs named Dice Spectral Similarity Coefficient (DSSC), Kumar–Johnson Spectral Similarity Coefficient (KJSSC), and a hybrid of DSSC and KJSSC, i.e., KJDSSCtan, for accurate discrimination of spectrally similar materials. A wide range of hyperspectral datasets of minerals and vegetation acquired under laboratory and real atmospheric conditions were used to compare and evaluate the performance of newly proposed and existing SMMs using Relative Spectral Discrimination Power (RSDPW) statistics. We also assessed the discrimination ability of the proposed and existing SMMs using spectra of selected minerals and vegetation species with an added component of random noise and linearly synthesized mixed spectra. An in-depth comparison and evaluation of different SMMs demonstrated that the discrimination power of the proposed SMMs is significantly higher than existing SMMs. The proposed SMMs also outperform existing SMMs when discriminating noisy and linearly synthesized mixed counterparts. The KJSSC and DSSC show similar efficacy in discriminating spectra of minerals and vegetation, whereas their hybrid measure, i.e., KJDSSCtan shows significantly higher spectral discrimination ability. Therefore, the newly proposed hybrid measure, i.e., KJDSSCtan is recommended over existing SMMs for successful material discrimination and classification using hyperspectral data.

We propose a new spectral-spatial method for hyperspectral image classification based on a graph cut. The classification task is formulated as an energy minimization problem on the graph of image pixels, and is solved by using the graph-cut α-expansion approach. The energy to optimize is computed as a sum of data and interaction energy terms, respectively. The data energy term is computed using the outputs of the probabilistic support vector machines classification. The second energy term, which expresses the interaction between spatially adjacent pixels, is computed by using dissimilarity measures between spectral vectors, such as vector norms, spectral angle mapper and spectral information divergence. Experimental results on hyperspectral images captured by the RO-SIS and the AVIRIS sensors reveal that the proposed method yields higher classification accuracies when compared to the recent state-of-the-art approaches.

Abstract. In this paper a new classification technique for hyperspectral data based on synergetics theory is presented. Synergetics – originally introduced by the physicist H. Haken – is an interdisciplinary theory to find general rules for pattern formation through selforganization and has been successfully applied in fields ranging from biology to ecology, chemistry, cosmology, and thermodynamics up to sociology. Although this theory describes general rules for pattern formation it was linked also to pattern recognition. Pattern recognition algorithms based on synergetics theory have been applied to images in the spatial domain with limited success in the past, given their dependence on the rotation, shifting, and scaling of the images. These drawbacks can be discarded if such methods are applied to data acquired by a hyperspectral sensor in the spectral domain, as each single spectrum, related to an image element in the hyperspectral scene, can be analysed independently. The classification scheme based on synergetics introduces also methods for spatial regularization to get rid of "salt and pepper" classification results and for iterative parameter tuning to optimize class weights. The paper reports an experiment on a benchmark data set frequently used for method comparisons. This data set consists of a hyperspectral scene acquired by the Airborne Visible Infrared Imaging Spectrometer AVIRIS sensor of the Jet Propulsion Laboratory acquired over the Salinas Valley in CA, USA, with 15 vegetation classes. The results are compared to state-of-the-art methodologies like Support Vector Machines (SVM), Spectral Information Divergence (SID), Neural Networks, Logistic Regression, Factor Graphs or Spectral Angle Mapper (SAM). The outcomes are promising and often outperform state-of-the-art classification methodologies.

In volatile, conflict-affected regions, rapidly mapping asbestos-cement rooftops is critical to mitigate health risks from airborne fibres. Over a 4-month field campaign (Nov 2023–Apr 2024), we partnered with the Israel Space Agency and Ministry of Environmental Protection to acquire disturbance-free field spectra at multiple Kibbutzim, Moshavim and cities, using an ASD FieldSpec 4 High-Res with both the SoilPro® apparatus and contact probe to build a comprehensive spectral library (Sup Figs. 5–14). Leveraging EnMAP Level 2A hyperspectral imagery (17 May 2024), we applied MNF noise reduction, precise co-registration, and cloud/shadow masking before executing eight supervised classifiers; Linear Spectral Unmixing, Support Vector Machine, Spectral Angle Mapper, Adaptive Coherence Estimator, Mahalanobis Distance, Maximum Likelihood, Spectral Information Divergence, and Matched Filtering, in an iterative filtering cascade. Exhaustive ground-truth surveys across villages and cities achieved an 86% positive match rate despite urban complexity and security-driven coordinate restrictions. This integrative workflow combining rigorous field calibration, multi-algorithm spectral filtering, and exhaustive validation, demonstrates that orbit-based hyperspectral data can reliably map asbestos hazards at scale, guiding timely emergency response and long-term remediation in high-risk settings.

Today, water quality and water pollution can be detected using remote sensing and its terrestrial components. Remote sensing does not only provide a quick solution to detect water quality and pollution, but it could also be low cost. Within the scope of the study, the water quality of the İmranlı area of the Kızılırmak River, one of the most important water resources of the Sivas region and the İmranlı dam on the river, was investigated by spectral classification methods. Water samples were taken from various points on the river and dam and their chemical oxygen demands were determined in the laboratory. In addition, the reflectance values of the water samples taken by the local spectral measurements were examined in order to use as end members for spectral classification. CHRIS Proba is used as satellite image. Match filtering (MF), spectral angle mapping (SAM) and spectral information divergence (SID) methods have been used as the spectral classification methods and it has been examined which method gives better results in determining water quality. According to the results, it is understood that SAM method provides better classification accuracy than other methods.

The high spectral resolution of hyperspectral images (HSI) requires a heavy processing load. Assigning each pixel to a group in the image, which is called superpixel, and processing the superpixels instead of the pixels is resorted as a means to overcome this challenge in the hyperspectral literature. In this paper, we propose an algorithm to segment a hyperspectral image into superpixels by means of iteratively updating the boundary pixels of superpixels. We first explore the optimal similarity metric for the boundary pixel updates with the contraint of keeping the superpixel boundaries aligned with the object boundaries in the image. We investigate two approaches for similarity detection between pixels during this update, first comparing the hyperspectral pixels individually, and second, comparing the pixels by using also their neigborhood. The spectral similarity metrics used for investigation are selected as spectral angle mapping (SAM) [1], spectral information divergence (SID) [2] and spatial coherence distance [3] due to their common usage. The proposed approach is compared with a pioneer state-of-the-art superpixel algorithm, SLIC [4], and its superiority is verified in terms of the superpixelization performance metrics, namely boundary recall and undersegmentation error [5].

Abstract. Polarimetric and Interferometric Airborne SAR in L-band 2 (PiSAR-L2) program is an experimental program of PALSAR-2 sensor in ALOS-2 satellite. Japan Aerospace Exploration Agency (JAXA) and Indonesian National Institute of Aeronautics and Space (LAPAN) have a research collaboration to explore the utilization of PiSAR-L2 data for forestry, agriculture, and disaster applications in Indonesia. The research explored the utilization of PiSAR-L2 data for land cover classification in forest area using the pixel-based and object-based methods. The PiSAR-L2 data in the 2.1 level with full polarization bands were selected over part of forest area in Riau Province. Field data collected by JAXA team was used for both training samples and verification data. Preprocessing data was carried out by backscatter (Sigma naught) conversion and Lee filtering. Beside full polarization images (HH, HV, VV), texture imagess (HH deviation, HV deviation, and VV deviation) were also added as the input bands for the classification processes. These processes were conducted for 2.5 meter and 10 meter spatial resolution data applying two methods of the maximum likelihood classifier for pixel-based classification and the support vector machine classifier for the object-based classification. Moreover, the average overall accuracy was calculated for each classification result. The results show that the use of texture images could improve the accuracy of land cover classification, particularly to differentiate between forest and acacia plantation. The pixelbased method showed a more detail information of the objects, but has “salt and pepper”. In the other hand, the object-based method showed a good accuracy and clearer border line among objects, but has often some misinterpretations in object identification.

Este trabalho utilizou dados multiespectrais (ETM+/Landsat 7), de radar de abertura sintética (RADARSAT-1 e MAPSAR simulado) e aerogeofísicos para caracterização geológica e geração de alvos exploratórios para mineralizações de ferro no bloco Serra Leste, porção oriental da Serra de Carajás (PA). A técnica Minimun Noise Fraction (MNF) foi aplicada às seis bandas do sensor ETM+/Landsat 7, produzindo-se o realce de coberturas ricas em ferro. Dados SAR permitiram a observação da macrotopografia e lineamentos que foram também interpretados com base em dados aerogeofísicos e multiespectrais. As imagens geofísicas e SAR do RADARSAT-1 foram integradas por meio da técnica IHS (intensidade-matiz-saturação), e os produtos gerados foram usados para uma melhor delimitação de unidades geológicas e para definição de alvos para prospecção de ferro. O método de classificação supervisionada Spectral Angle Mapper (SAM) foi aplicado a um conjunto de imagens geofísicas selecionadas a partir da determinação do modelo descritivo das mineralizações de ferro e das assinaturas geofísicas verificadas no alvo Serra Leste. Utilizando-se a ocorrência documentada de ferro na região como ponto de treinamento, um mapa de favorabilidade foi produzido. Os resultados da classificação SAM mostraram-se equivalentes ou superiores quanto a sua acurácia quando comparados ao mapa geológico e produtos de realce espectral produzidos neste artigo.

Sentinel-2A remote sensing satellite system was recently launched, providing free global remote sensing data similar to Landsat systems. Although the mission enables the acquisition of 10 m spatial resolution global data, the assessment of Sentinel-2A data performance for mapping in Malaysia is still limited. This study aimed to investigate and assess the capability of Sentinel-2A imagery in mapping urban areas in Malaysia by comparing its performance against the established Landsat-8 data as well as the fusion datasets from combining Landsat-8 and Sentinel-2A datasets and using Wavelet transform (WT), Brovey transform (BT) and principal component analysis. Pixel-based and object-based image analysis (OBIA) classification approaches combined with support vector machine (SVM) and decision tree (DT) algorithms were utilized in this assessment, and the accuracy generated was analysed. The Sentinel-2A data provided superior urban mapping output over the use of Landsat-8 alone, and the fusion datasets do not yield advantages for single-scene urban mapping. The highest overall accuracy (OA) for pixel-based classification of Sentinel-2A images is 84.77 % by SVM, followed by 65.27 % using DT. BT produced the highest OA for the fusion images of 78.40 % with SVM and 52.21 % with DT. For the object-based classification of Sentinel-2A images, the highest OA is 71.33 % by SVM, followed by 76.38 % using DT. Similarly, the highest OA of fusion images is obtained by BT of 50.35 % with SVM, followed by 65.66 % with DT. From the analysis, the use of SVM pixel-based classification for medium spatial resolution Sentinel-2A data is effective for urban mapping in Malaysia and useful for future long-term mapping applications. HIGHLIGHTS An accurate mapping of urban land is still challenging and requires high image quality of spectral and spatial aspects to identify features Single and fusion image analysis conducted in order to investigate and assess the most performing interpretation result by grouping out the features classes Statistical performance and image classification comparison is relevant to prove the most effective result among the images GRAPHICAL ABSTRACT