Based on the information gathered within the technologies review performed in the previous article, the authors analyse if the deferent technologies could efficiently (or not) support the excavation work to be performed for the remediation of industrial disasters. At first sight, some technologies reach the requested accuracy. But after considering the error propagation when the technologies are applied in the condition of the fieldwork, it turned out that none of the remote sensing techniques we have reviewed finally offers sufficient accuracy to reach the 2.5 cm relative vertical accuracy target that was set. The final conclusion is a direct realtime measurement in the field, and the development of an appropriate apparatus for the real-time control of the blade may be the appropriate solution to reach the targeted accuracy in the field. This approach should be examined and developed in a next research work.

In the last 10 years, the technological developments have changed the paradigm in remote sensing science. Nowadays, very diverse technologies can be employed to capture and/or extract very accurate terrain elevation data and prepare digital elevation models. This article aims at reviewing the existing remote sensing technologies which could support disaster remediation (by excavation of the soil) with very accurate elevation data acquisition. Ground based technologies (like terrestrial laser scanning, InSAR and SfM) and airborne technologies (airborne laser scanning [ALS], UAV photogrammetric approach, UAV with LiDAR) are reviewed. Their capacities are examined according to the following technical criteria: spatial efficiency, point density, accuracy and applicability in disaster situation.

In this study high spatial resolution (1 m) hyperspectral images and LiDAR data (8p/m(2)) was applied to discriminate among tree species of mixed forest. The main objective of this study was to apply machine learning methods using crown segments for image classification. A watershed segmentation algorithm was used to delineate individual crowns from a filtered CHM model. The image classification was applied on the original spectral bands and transformed (MNF) dataset. A binary tree SVM classifier was developed in accordance with the principle of SVM, based on the Jeffries-Matusita (JM) separability measure of selected classes. The ABTSVM on MNF-transformed dataset provided more accurate results than applied multiclass SVM methods. The addition of crown segments resulted in an increase in classification accuracy of 14.51 percentage points over pixel-based classification alone.

In this work, we propose a spectral assignment analysis (SAA) oriented partial least squares regression (PLS-R) modeling approach, designed to provide descriptive spectral assignments of proxy models. We applied this method on airborne HSR data of asphalt roads combined with the dynamic friction coefficient (m) that were measured independently. Accordingly, the method automatically subgroups the data into high and low values clusters under an iterative segmentation process. A PLS-R model is fitted to each group, followed by the extraction of the B Coefficient spectrum. A spectral angle (SA) value is calculated in each iteration between the two spectra to find the most pronounced difference between the two segments, pointing on a significant group separation. Hyperspectral data was acquired using the AisaFenix 1k hyperspectral imaging system over several asphalt roads in central Israel. This method provided insights regarding the physical and chemical processes occurring to asphalt pavement due to aging effects, and the different assignments for different friction levels.

In our paper we examined the opportunities of a classification based on descriptive statistics of NDVIthroughout a year’s time series dataset. We used NDVI layers derived from cloud-free Sentinel-2 imagesin 2018. The NDVI layers were processed by object-based image analysis and classified into 5 classes, inaccordance with Corine Land Cover (CLC) nomenclature. The result of classification had a 76.2% overallaccuracy. We described the reasons for the disagreement in case of the most remarkable errors. .

Munkánk során egy szikes táj vegetációtípusainak osztályozását végeztük el, légi hiperspektrális adatok felhasználásával. A munka célja a hiperspektrális adatok alkalmazhatóságának vizsgálata volt e komplex társulásoknál, eltérő képosztályozási módszerek alkalmazásával. Vizsgálatunkban hagyományos osztályozó eljárások (Maximum Likelihood Classifier – MLC, Random Forest – RF és Support Vector Machine – SVM) eredményességét teszteltük 10 és 30 pixeles tanítóterületek felhasználásával. A mozaikolt hiperspektrális felvételen a zajszűrés és az információnyerés céljából MNF transzformációt alkalmaztunk. A légi hiperspektrális felvétel AISA EAGLE II szenzorral készült 1m terepi felbontásban. Társulástani besorolás és felszínborítás alapján összesen 20 vegetációosztályt alakítottunk ki. Az osztályokat további négy főbb élőhelykategóriába soroltuk: sztyeppék, nyílt szikes gyepek, szikes rétek, szikes és nem szikes mocsarak. Az SVM és az RF osztályozó eljárások, a pixelek számától függetlenül, majdnem minden vegetációosztálynál megbízhatóan működtek, nagy osztályozási pontosságot adtak. Az MLC bár nagy mintaszámnál nagy pontosságú osztályozást eredményezett, kis mintaszámnál számos osztály esetében alacsony megbízhatósággal működött. Az eredmények alapján elmondható, hogy a komplex fátlan táji környezetben a vegetáció osztályozásra az SVM megfelelő osztályozó lehet, mivel nagyobb pontosságot nyújt, mint az RF és az MLC. Az SVM bizonyult a legkevésbé érzékenynek a tanító területek mintáinak méretére, így alkalmas lehet azokban az esetekben, amikor néhány osztálynál az elérhető pixelek száma korlátozottan áll rendelkezésre.

An important part of wheat harvest planning is to have good understanding of the field where harvesting operation is to be conducted. Terrain characteristics influence biomass product. This information has been challenging to view of the area to be worked. Precision agriculture is about collecting timely geospatial information on soil-plant relations and prescribing an applying site-specific treatments to increase agricultural production and protect the environment. Precision farming should be applied in order to achieve sustainable agriculture. The development and implementation of site-specific farming has been made possible by combining geographic information systems (GIS) and hyperspectral remote sensing. In this research we introduce one existing problem that could be solved based on application of hyperspectral remote sensing. Digital images were taken by an Aisa EAGLE II hyperspectral sensor, which produced images with 253 contiguous bands (400-1000 nm), a spectral sampling of 2.5nm bandwidth, and a ground pixel size of 1m. In our work narrowband vegetation indices (VI) were calculated from high resolution aerial hyperspectral images for estimating the biomass of winter wheat in an agricultural area. Narrow band’s NDVI were computed for each combination of NIR and Red bands. Regression model was computed between NDVI’s and field samples, where 625nm and 720nm bands produced the strongest relationship with biomass values (n=9, R2=0.762, p<0.05). -------------------------------------------------------------------- A szantofoldi gabonatermesztes tervezesenek fontos resze a gazdalkodasi terulet megismerese. A teruleti jellemzők befolyasoljak a biomassza produktumot. Ez az informacio kihivast jelent a gazdalkodas teruleti tervezeseben. A precizios novenytermesztes osszegyűjti az aktualis terinformatikai informaciokat a talaj-noveny kapcsolatrendszereről es meghatarozza az alkalmazhato helyspecifikus kezeleseket, amelyek novelik a mezőgazdasagi termeles merteket es a kornyezetet is vedi. A precizios gazdalkodas alkalmazhato a fenntarthato mezőgazdasagi fejlődes elerese erdekeben. A helyspecifikus gazdalkodasi modszer kidolgozasa es vegrehajtasa lehetőve tette a geoinformacios rendszerek (GIS) es a hiperspektralis taverzekeles otvozeset. Jelen kutatasban szeretnenk bemutatni egy olyan gyakorlati peldat, amely megoldasara taverzekelesből nyert informaciok segitsegevel kezelhetők. A felvetelek AISA EAGLE II tipusu hiperspektralis szenzorral keszultek lathato es kozeli infravoros tartomanyban (400-1000 nm), 2,5 nm-es spektralis mintavetelezessel es 1 meter terepi felbontassal, az igy elkeszult felvetelek 253 db spektralis csatornat tartalmaztak. Munkank soran nagy felbontasu legi hiperspektralis felvetelekből szamitott keskenysavu vegetacios indexek (VI) segitsegevel kovetkeztettunk az őszi buza biomassza mennyisegere egy mezőgazdasagi teruleten. A keskenysavu NDVI szamitasahoz a voros-el szamitast es az osszes csatornakombinaciot teszteltuk a voros es a kozeli infravoros tartomanyokban a nedves biomassza-hozam becslesere. A legszorosabb regressziot a nedves biomassza es a mintaterulet hiperspektralis felvetel pixelei kozott a 625nm voros es a 720nm-es kozeli infravoros csatornakbol szamitott keskeny savu NDVI alkalmazasaval kaptuk.

This paper investigates whether the combination of airborne hyperspectral imagery (Aisa EAGLE II) and image classification methods (MLC, SVM) using feature extraction can discriminate among species and clones of energy trees. The trees examined have similar morphological traits due to limitation of detection. The image classification was applied on a spectrally selected and transformed (PCA, MNF) dataset. A binary tree SVM classifier was developed in accordance with the principle of SVM, based on the Jeffries-Matusita (JM) separability measure of selected classes. The adaptive binary tree SVM on MNF-transformed dataset provided more accurate results than applied MLC and multiclass SVM methods. The primary outcome of this study was a comparison of support vector machines (SVM) classification methods to evaluate species or clones of energy plants. In this paper, an adaptive binary tree SVM classifier (ABTSVM) is proposed to increase the accuracy of subspecies level.

This article aims at exploring the potential of hyperspectral imaging in order to develop further the Hungarian aerial nuclear reconnaissance system. First a description about the theoretical basis of ionizing radiations is provided. The different types of radiations, their characteristics, penetration range and effect on matter are presented. Then a critical analysis is done on the Hungarian nuclear reconnaissance system based on the detection capacities and operational implementation criteria. The last part explores the potential of hyperspectral imaging technology, its added values and the different possibilities envisaged for its application.

One of the largest industrial disasters in Europe took place in the village of Kolontar (Hungary) on October 4th, 2010. Due to a ruptured dam more than 1 million m3 of red sludge flooded the nearby small towns along the Torna river. The spilled material containing a highly alkaline solution (>12 pH) resulted in a complex environmental disaster, requiring a multi-disciplinary approach regarding the assessment and the remediation of the site.The Karoly Robert College has developed a remote sensing protocol, which greatly assists both the domestic and international disaster management (forecast, damage surveying and control). In case of the Hungarian red sludge disaster the primary objective of the hyperspectral remote sensing mission was to estimate the environmental damage, the precise size of the polluted area, the rating of substance concentration in the sludge. For quick assessment and remediation purposes, it was deemed important to estimate the thickness of the red mud, particularly the areas where it...

One of the largest industrial spills in Europe occurred in the village of Kolontar (Hungary) on October 4, 2010. The primary objective of the hyperspectral remote sensing mission was to monitor that is necessary in order to estimate the environmental damage, the precise size of the polluted area, the rating of substance concentration in the mud, and the overall condition of the flooded district as soon as possible. The secondary objective was to provide geodetic data necessary for the high-resolution visual information from the data of an additional Lidar survey, and for the coherent modeling of the event. For quick assessment and remediation purposes, it was deemed important to estimate the thickness of the red mud, particularly the areas where it was deposited in a thick layer. The results showed that some of the existing tools can be easily modified and implemented to get the most out of the available advanced remote sensing data.

The village of Kolontár, Hungary had became the site of one of the largest industrial spills in Europe on October 4th, 2010. The primary objective of the hyperspectral remote sensing mission was monitoring needed to estimate environmental damage, the precise size of the polluted area, the rating of substance concentration in the mud, and the overall condition of the flooded district. The secondary objective was aimed to provide geodetic data necessary for the high-resolution visual information from the data obtained with an additional Lidar survey, and for coherent modelling of the event. For quick assessment and remediation purposes, it was deemed important to estimate the thickness of the red mud, particularly the areas where the depths of the layer were more than 3cm. The results showed that some of the existing tools can be readily modified and implemented to get the most out of the available advanced remotely sensed data.

Rapid development in remote sensing technologies provides more and more reliable methods for environmental assessment. For most wetlands, it is difficult to walk-in without disturbing the endangered species living there; therefore, application of opportunities provided by remote sensing has a great importance in population-mapping. One effective tool of vegetation pattern estimation is hyperspectral remote sensing, which can be used for association and species level mapping as well, due to high ground resolution. The Rakamaz-Tiszanagyfalui Nagy-morotva is an oxbow lake, located in the north-eastern part of Hungary. For this study, a wetland area of 1.17 km 2 containing the original water bad and shoreline was selected. For the image analysis, images taken by an AISA DUAL system hyperspectral sensor were used. At the same time, 7 main vegetation classes were separated, which are typical for the sample plot designated on the test site. Classification was performed by the master areas signed by the most common associations of the Rakamaz-Tiszanagyfalui Nagy-morotva with determined spectrums. During the image analysis, SAM classification method was used, where radian values were optimized by the results of classification performed at the control area.

This study examines the use of high spatial resolution hyperspectral imagery in combination with light detection and ranging (LiDAR) data and digital aerial imagery for vegetation management of utility corridors. Two different classification methods, i.e. the support vector machines (SVM) and the spectral angle mapper (SAM) were applied on the datasets to test their ability for discrimination of various vegetation species. The SVM classifier performed best with an overall accuracy of 83% applied on the hyperspectral imagery. With inclusion of the LiDAR data the accuracy could be increased to 92%. Power lines were extracted from the LiDAR data and the conductor clearance was calculated. The results were merged with the SVM classification and a species map of vegetation that could cause potential damage to the power lines was generated. The results of this study show that an improved approach for vegetation management of utility corridors can be achieved by combining the spatial and spectral information of multi-source datasets.

Nowadays, hyperspectral remote sensing is increasingly widely used, which makes possible several precision applications. In particular, actual status as well as change in status of objects on ground surface can be evaluated, providing useful information for e. g. agriculture, and environmental management, and thematic information can also be obtained, such as landuse pattern for a given area. In our study, effect of adverse soil processes on plants at an arable land was investigated by processing airborne remotely sensed data. Hyperspectral images were taken by using an AISA Dual hyperspectral sensor detecting between 400 and 1.000 nm in parallel with field measurement of certain biomass parameters, including plant height, cover, leaf area index, etc. and sampling at points determined by GPS, for laboratory analysis of chlorophyll a content. After radiometric and geometric corrections, channel selecting methods were applied to improve the information content. In addition to the traditionally used vegetation indices, channels potentially useful to estimate biomass and chlorophyll were selected. After evaluating point data, spatial distribution of chlorophyll a content was also examined, and as a result, a vegetation stress map was generated. In addition, based on calculations from field measurement data for coverage, and selection and processing of certain spectra, a coverage map was also generated for the studied area.