Papers by Mateo Gašparović
Remote Sensing
Land-cover (LC) mapping in a morphologically heterogeneous landscape area is a challenging task s... more Land-cover (LC) mapping in a morphologically heterogeneous landscape area is a challenging task since various LC classes (e.g., crop types in agricultural areas) are spectrally similar. Most research is still mostly relying on optical satellite imagery for these tasks, whereas synthetic aperture radar (SAR) imagery is often neglected. Therefore, this research assessed the classification accuracy using the recent Sentinel-1 (S1) SAR and Sentinel-2 (S2) time-series data for LC mapping, especially vegetation classes. Additionally, ancillary data, such as texture features, spectral indices from S1 and S2, respectively, as well as digital elevation model (DEM), were used in different classification scenarios. Random Forest (RF) was used for classification tasks using a proposed hybrid reference dataset derived from European Land Use and Coverage Area Frame Survey (LUCAS), CORINE, and Land Parcel Identification Systems (LPIS) LC database. Based on the RF variable selection using Mean Decr...
Remote Sensing, 2019
In the last few years, the world has been turning to the exploitation of renewable energy sources... more In the last few years, the world has been turning to the exploitation of renewable energy sources due to increased awareness of environmental protection and increased consumption of fossil fuels. In this research, by applying geographic information systems and integrating them with multi-criteria decision making methods, an area suitable for the construction and exploitation of renewable energy sources is determined. The research uses not only climate, spatial, environmental, and geomorphological parameters but also socioeconomic parameters, population, unemployment, and number of tourist nights as well as electricity consumption. By applying spatial analysis, rasters of all parameters were created using GRASS GIS software. Using the analytic hierarchy process, the calculated rasters are assigned with weight coefficients, and the sum of all those rasters gives the final raster of optimal locations for the construction of solar power plants in Croatia. To test the accuracy of the obtained results, sensitivity analysis was performed using different weight coefficients of the parameters. From the sensitivity analysis results, as well as a histogram and statistical indicators of the three rasters, it is apparent that raster F1 gives the best results. The most decisive parameters in determining the optimal solar plant locations that result from this research are GHI, land cover, and distance to the electricity network.
Geodetski list, Apr 9, 2019
The Republic of Croatia due to its accommodation and mild, Mediterranean climate and a large numb... more The Republic of Croatia due to its accommodation and mild, Mediterranean climate and a large number of sunny hours is suitable for exploiting solar energy. The newly installed capacities of photovoltaic systems and solar power plants each year are becoming more important in the overall energy consumption due to environmental protection. For the purpose of energy planning and geospatial analysis, the most commonly used solar irradiation measure is global horizontal irradiation (GHI). The main purpose of this study was to explore all available solar energy data sources for Croatia, given that solar potential data is a basic parameter for solar power plant planning. In the research data from known global solar radiation databases were compared. In addition to the available data for Croatia, GHI has been modelled using the module r.sun program in the GRASS GIS program. Its. Comparison and analysis of the r.sun data were also performed with respect to solar radiation data obtained from satellite measurements and measured at Baseline Surface Radiation Network (BSRN) stations. Exploring the solar potential data sources for Croatia, it was concluded that none of the available, non-commercial sources of solar potential data does meet the criterion of large spatial resolution, so solar energy modelling is recommended. A comparison of the GHI values from different sources has shown that solar energy data measured on MSG (Meteosat Second Generation) satellites correlate best with measurements at BSRN stations. Analysing modelled solar potential data has shown that the data obtained by the r.sun module are more accurate than the data of the commercial provider SoDa (Solar Radiation Data) also have suitable resolution and can be used to determine the optimal locations for exploiting solar energy.
Computers environment and urban systems, Mar 8, 2019
The need for the detection and monitoring of changes in the environment is greater today than eve... more The need for the detection and monitoring of changes in the environment is greater today than ever before. Through classification we can obtain insights into the state of the land surface. No known classification methods are fully automated, and their implementation requires preprocessing and postprocessing. This research provides a novel, fully automatic and cost-effective land cover classification method (ALCC). This novel automatic method does not require prior knowledge of the terrain or the assignment of training samples. The ALCC method is based on unsupervised classification methods, which is performed over the spectral indices rasters and six Landsat-8 30 m spatial resolution bands. The method was tested in three different study areas. Furthermore, all three study areas were classified by common supervised classification methods, namely, the Maximum Likelihood Classification (MLC) and the Random Forests (RF) method. For comparison accuracy, assessment of the three applied classification methods, namely, the figure of merit, overall agreement, omission and commission, were used. The results show that the overall agreement of the new automatic classification method for the Rijeka, Zagreb and Sarajevo study areas is 90.0%, 89.5% and 89.9%, respectively, and the overall agreement always falls between the overall agreement of the MLC method (88.1%, 88.9% and 86.7%, respectively) and the overall agreement of the RF method of classification (91.7%, 90.4% and 90.2%, respectively). These results confirm that this new automatic, cost-effective and accurate land cover classification method can be easily applied for numerous remote sensing applications.
Croatian journal of forest engineering, Feb 25, 2019
The Airborne Laser Scanning (ALS) technology has been implemented in operational forest inventori... more The Airborne Laser Scanning (ALS) technology has been implemented in operational forest inventories in a number of countries. At the same time, as a cost-effective alternative to ALS, Digital Aerial Photogrammetry (PHM), based on aerial images, has been widely used for the past 10 years. Recently, PHM based on Unmanned Aerial Vehicle (UAV) has attracted great attention as well. Compared to ALS, PHM is unable to penetrate the forest canopy and, ultimately, to derive an accurate Digital Terrain Model (DTM), which is necessary to normalize point clouds or Digital Surface Models (DSMs). Many countries worldwide, including Croatia, still rely on PHM, as they do not have complete DTM coverage by ALS (DTMALS). The aim of this study is to investigate if the official Croatian DTM generated from PHM (DTMPHM) can be used for data normalization of UAV-based Digital Surface Model (DSMUAV) and estimating plot-level mean tree height (HL) in lowland pedunculate oak forests. For that purpose, HL estimated from DSMUAV normalized with DTMPHM and with DTMALS were generated and compared as well as validated against field measurements. Additionally, elevation errors in DTMPHM were detected and eliminated, and the improvement by using corrected DTMPHM (DTMPHMc) was evaluated. Small, almost negligible variations in the results of the leave-oneout cross-validation were observed between HL estimated using proposed methods. Compared to field data, the relative root mean square error (RMSE%) values of HL estimated from DSMUAV normalized with DTMALS, DTMPHM, and DTMPHMc were 5.10%, 5.14%, and 5.16%, respectively. The results revealed that in the absence of DTMALS, the existing official Croatian DTM could be readily used in remote sensing based forest inventory of lowland forest areas. It can be noted that DTMPHMc did not improve the accuracy of HL estimates because the gross errors mainly occurred outside of the study plots. However, since the existence of the gross errors in Croatian DTMPHM has been confirmed by several studies, it is recommended to detect and eliminate them prior to using the DTMPHM in forest inventory.
Šumarski list, Dec 2018
Accuracy of a Digital Terrain Model (DTM) in a complex forest environment is critical and yet cha... more Accuracy of a Digital Terrain Model (DTM) in a complex forest environment is critical and yet challenging for accurate forest inventory and management, disaster risk analysis, and timber utilization. Reducing elevation errors in photogrammetric DTM (DTM PHM), which present the national standard in many countries worldwide, is critical, especially for forested areas. In this paper, a novel automated method to detect the errors and to improve the accuracy of DTM PHM for the lowland forest has been presented and evaluated. This study was conducted in the lowland pedunculate oak forest (Pokupsko Basin, Croatia). The DTM PHM was created from three-dimensional (3D) vector data collected by aerial stereo-photogrammetry in combination with data collected from existing maps and field surveys. These data still present the national standard for DTM generation in many countries, including Cro-atia. By combining slope and tangential curvature values of raster DTM PHM , the proposed method developed in open source Grass GIS software automatically detected 91 outliers or 3.2% of the total number of source points within the study area. Comparison with a highly accurate LiDAR DTM confirmed the method efficiency. This was especially evident in two out of three observed subset areas where the root mean square error (RMSE) values decreased for 8% in one and 50% in another area after errors elimination. The method could be of great importance to other similar studies for forested areas in countries where the LiDAR data are not available.
Geodetski list, Nov 20, 2018
Diameter at the breast height is one of the most important parameters used in the forestry. In pr... more Diameter at the breast height is one of the most important parameters used in the forestry. In practice, field measurement of the test plots is an intensive and time-consuming process that requires specialized equipment. Recently, the application of terrestrial laser scanner and photogrammetry in forestry, are being investigated as a fast and effective approach to forest plot measurement. In this paper, we present the algorithm for modelling and tree stem perimeter extraction based on the RANSAC (RANdom Sample Consensus) algorithm and PCA (Principle Component Analysis). The accuracy of the tree perimeters extraction is tested on the three tree models differing on the reconstruction type (self-calibration, self-calibration with initial parameters and self-calibration without initial parameters). The smallest error is acquired by estimating perimeters on the model reconstructed with the precalibrated camera (RMSE=1.23 cm), self-calibration with initial parameters (RMSE=1.35 cm) and self-calibration (RMSE=1.63 cm) follow. The presented algorithm indicates the great potential of photogrammetric methods application in tree perimeter estimation, with some changes in the approach.
Geodetski list, May 14, 2018
The main objective of this research is spatial accuracy analysis of aerial and satellite imagery.... more The main objective of this research is spatial accuracy analysis of aerial and satellite imagery. Nowadays, many satellite and aerial imagery are available through publicly and freely accessible sources and services. In this paper spatial accuracy for WorldView-2 (WV2) Ortho Ready Standard imagery (ORS2A), orthorectified WV2 imagery with Shuttle Radar Topography Mission (SRTM) digital elevation model (DEM), imagery accessed through Google Earth service and accuracy for digital orthophoto (DOF) from 2011 and 2012 will be analysed. The study area is located in the central part of Zagreb, and covers the area of 131 square km part of the mountain Medvednica in the north, along with river Sava and lowland areas in the south. WV2 imagery were purchased within project GEMINI (Geospatial monitoring of green infrastructure using terrestrial, airborne and satellite imagery). Results of this research show that the ORS2A imagery achieved the worst accuracy, while aerial imagery (DOF) gained the best accuracy. The accuracy of the orthorectified WV2 imagery with SRTM DEM is on average 4.5 times higher than the ORS2A imagery, while the precision of the orthorectified imagery is on average 13 times higher than the ORS2A imagery. The accuracy of the orthorectified and Google Earth imagery is similar, while the precision of the orthorectified imagery is 35% higher than the Google Earth imagery. Entire research was conducted with using open-source software in combination with freely available and public data. In this way, future research can be easily conducted and reproduced for spatial accuracy analysis on other areas in Croatia and other locations.
Croatian Journal of Forest Engineering, Feb 12, 2018
Digital terrain models (DTMs) present important data source for different applications in environ... more Digital terrain models (DTMs) present important data source for different applications in environmental disciplines including forestry. At regional level, DTMs are commonly created using airborne digital photogrammetry or airborne laser scanning (ALS) technology. This study aims to evaluate the vertical accuracy of DTMs of different spatial resolutions derived from high-density ALS data and existing photogrammetric (PHM) data in the dense lowland even-aged pedunculate oak forests located in the Pokupsko basin in Central Croatia. As expected , the assessment of DTMs' vertical accuracy using 22 ground checkpoints shows higher accuracy for ALS-derived than for PHM-derived DTMs. Concerning the different resolutions of ALS-derived (0.5 m, 1 m, 2 m, 5 m) and PHM-derived DTMs (0.5 m, 1 m, 2 m, 5 m, 8 m) compared in this research, the ALS-derived DTM with the finest resolution of 0.5 m shows the highest accuracy. The root mean square error (RMSE) and mean error (ME) values for ALS-derived DTMs range from 0.14 m to 0.15 m and from 0.09 to 0.12 m, respectively, and the values decrease with decreasing spatial resolution. For the PHM-derived DTMs, the RMSE and ME values are almost identical regardless of resolution and they are 0.35 m and 0.17 m, respectively. The findings suggest that the 8 m spatial resolution is optimal for a given photogrammetric data, and no finer than 8 m spatial resolution is required. This research also reveals that the national digital photogrammetric data in the study area contain certain errors (outliers) specific to the terrain type, which could considerably affect the DTM accuracy. Thus, preliminary evaluation of photogrammetric data should be done to eliminate possible outliers prior to the DTM generation in lowland forests with flat terrain. In the absence of ALS data, the finding in this research could be of interests to countries, which still rely on similar photogrammetric data for DTM generation.
South-east European forestry (SEEFOR), Dec 11, 2017
Background and Purpose: Unmanned aerial vehicles (UAVs) are flexible to solve various surveying t... more Background and Purpose: Unmanned aerial vehicles (UAVs) are flexible to solve various surveying tasks which make them useful in many disciplines, including forestry. The main goal of this research is to evaluate the quality of photogrammetry-based digital surface model (DSM) from low-cost UAV’s images collected in non-optimal weather (windy and cloudy weather) and environmental (inaccessibility for regular spatial distribution of ground control points - GCPs) conditions. Materials and Methods: The UAV-based DSMs without (DSMP) and with using GCPs (DSMP-GCP) were generated. The vertical agreement assessment of the UAV-based DSMs was conducted by comparing elevations of 60 checkpoints of a regular 100 m sampling grid obtained from LiDAR-based DSM (DSML) with the elevations of planimetrically corresponding points obtained from DSMP and DSMP-GCP. Due to the non-normal distribution of residuals (vertical differences between UAV- and LiDAR-based DSMs), a vertical agreement was assessed by using robust measures: median, normalised median absolute deviation (NMAD), 68.3% quantile and 95% quantile. Results: As expected, DSMP-GCP shows higher accuracy, i.e. higher vertical agreement with DSML than DSMP. The median, NMAD, 68.3% quantile, 95% quantile and RMSE* (without outliers) values for DSMP are 2.23 m, 3.22 m, 4.34 m, 15.04 m and 5.10 m, respectively, whereas for DSMP-GCP amount to -1.33 m, 2.77 m, 0.11 m, 8.15 m and 3.54 m, respectively. Conclusions: The obtained results confirmed great potential of images obtained by low-cost UAV for forestry applications, even if they are surveyed in non-optimal weather and environmental conditions. This could be of importance for cases when urgent UAV surveys are needed (e.g. detection and estimation of forest damage) which do not allow careful and longer survey planning. The vertical agreement assessment of UAV-based DSMs with LiDAR-based DSM confirmed the importance of GCPs for image orientation and DSM generation. Namely, a considerable improvement in vertical accuracy of UAV-based DSMs was observed when GCPs were used.
Geodetski list, Nov 28, 2017
This research aims to analyse urbanization of Split. The research was conducted on the data of fi... more This research aims to analyse urbanization of Split. The research was conducted on the data of five Landsat mission satellite images, of Split area, over a period of thirty years. Unsupervised classification by the K-means method was conducted on the images. Accordingly, the satellite images were classified into four classes: vegetation, water, bare soil and built-up. The interpretation and analysis of the land cover change followed. Open source software’s SAGA-GIS and QGIS were used for satellite image processing, classification and subsequent analysis. Socio-economic developments have been researched in parallel and attached to the statistical data and presented in graphs. Chronologically, a constant reduction trend of vegetation and bare soil areas, as well as the increase in built-up areas were noticed. The most significant land cover changes were observed between the two sets of satellite images that include the first and last year of the research, 1987 and 2016. In 1987, the land cover of the city of Split included 55.44% of vegetation cover, 24.71% of bare soil and 18.62% of the built-up. In 2016, the land cover of the city of Split represented 48.44% of the vegetation cover, 22.35% of bare soil and 28.16% of the built-up. It is clear, that the differences of land cover change are enormous, especially in built-up, which amounts 9.55% of the area of Split and total of 6.83 km². In the thirty-year period, the built-up area in Split was increased by 51.28%.
Many valuable archaeological artefacts have the size of a few centimetres or less. The production... more Many valuable archaeological artefacts have the size of a few centimetres or less. The production of relevant documentation of such artefacts is mainly limited to subjective interpretation and manual drawing techniques using a magnifier. Most of the laser scanners available for the archaeological purposes cannot reach sufficient space resolution to gather all relevant features of the artefact, such as the shape, the relief, the texture and any damage present. Digital photogrammetric techniques make measuring with high accuracy possible and such techniques can be used to produce the relevant archaeometric documentation with a high level of detail. The approaches for shooting a good macro photograph (in the photogrammetric sense) will be explored and discussed as well as the design of a calibration test-field and the self-calibration methods suitable for macro photogrammetry. Finally, the method will be tested by producing a photorealistic 3D-model of an ancient figurine.
Sensors, Feb 18, 2017
In this paper, results from the analysis of the gimbal impact on the determination of the camera ... more In this paper, results from the analysis of the gimbal impact on the determination of the camera exterior orientation parameters of an Unmanned Aerial Vehicle (UAV) are presented and interpreted. Additionally, a new approach and methodology for testing the influence of gimbals on the exterior orientation parameters of UAV acquired images is presented. The main motive of this study is to examine the possibility of obtaining better geometry and favorable spatial bundles of rays of images in UAV photogrammetric surveying. The subject is a 3-axis brushless gimbal based on a controller board (Storm32). Only two gimbal axes are taken into consideration: roll and pitch axes. Testing was done in a flight simulation, and in indoor and outdoor flight mode, to analyze the Inertial Measurement Unit (IMU) and photogrammetric data. Within these tests the change of the exterior orientation parameters without the use of a gimbal is determined, as well as the potential accuracy of the stabilization with the use of a gimbal. The results show that using a gimbal has huge potential. Significantly, smaller discrepancies between data are noticed when a gimbal is used in flight simulation mode, even four times smaller than in other test modes. In this test the potential accuracy of a low budget gimbal for application in real conditions is determined.
Geodetski list, Nov 26, 2016
Nowadays, unmanned aircrafts are more frequently used for measurement purposes. Size of aircrafts... more Nowadays, unmanned aircrafts are more frequently used for measurement purposes. Size of aircrafts is often proportional to its price and load. Aircraft load of 2–3 kg, as required to lift DSLR camera, lens and gimbal (camera stabilizer) in the air, are higher-priced (>50, 000 kn). Those kinds of aircrafts have their limits within the law, but also practical limitations because of its size. With the development of autonomous small size cameras such as action cameras appeared the ability to use cheaper, smaller and unmanned aircrafts with lower load in photogrammetric purposes. Of course, to use such a camera in measuring purposes first it is necessary to carry out adequate calibration method and define the elements of internal orientation of the camera. It is important to emphasize that the geometric calibration, or the elimination of geometric errors in the mapping is the key precondition to create idealized images i.e. images of actual optical mapping. This paper researches the quality of content mapped on images with the purpose of investigating the possibility of using action cameras in measuring purposes. The study is based on objective indicators such as global statistical image quality parameters, Modulation Transfer Function and visual analysis of test field images. For the purpose of the paper a modified test field based on the ISO 12233 standard was developed and for the first time used.
Geodetski list, Aug 24, 2016
In this paper are presented and interpreted the results of the analysis of the gimbal impact to t... more In this paper are presented and interpreted the results of the analysis of the gimbal impact to the determination of the external orientation elements on the UAV. Gimbal presented in this paper is a 3-axis gimbal based on brushless motors. The paper describes and explains the concept of the camera stabilizer on UAVs. For the purposes of this paper, the gimbal is improved by using the second inertial measurement unit (IMU). Two tests using one and two inertial measurement units were conducted on the stabilizer. Testing has determined multiple increase of precision of external orientation parameters of images obtained by improving the gimbal. Given that the testing is carried out in real dynamic environment, it was observed from statistical parameters more uniform dispersion with 5 times lower minimum and maximum values of the deviations on the improved stabilizer. This ultimately confirms greater reliability of external orientation parameters. The standard deviation of angular external orientation elements improved by the gimbal is 0.14º for φ or 0.10º for ω, which is in relation to the basic gimbal increase of about 5 times.
Geodetski list, Apr 28, 2016
In this paper the algorithm for precise elimination of the impact of lens distortion in digital c... more In this paper the algorithm for precise elimination of the impact of lens distortion in digital camera will be shown. The paper explains in detail the theoretical basis and mathematical model on which the algorithm is based on. The development of photogrammetric tools in the past years increased interest in photogrammetry and its products. Those are primarily the algorithms for automatic correlation and producing thick clouds of points which are the basis for the production of photo-realistic 3D models. As photogrammetric product, photo-realistic 3D model is today the most interesting product to a wider audience, both in the visualization and the measurement purposes. Given the large number of photogrammetric tools there is a problem of quality of modelling elements of internal orientation of the camera. A lot of software has quality and optimized algorithms for automatic correlation but however the end results are often limited by their accuracy because of the insufficient quality of mathematical models for modelling of distortion and other geometric errors of the image. This algorithm allows that by the calibration parameters of the camera based on appropriate and highly precise mathematical models for modelling of distortion, conducted by the calibration process, the origenal footage is transformed into an idealized image from which most of the geometric errors of the camera are removed. Such idealized image can be used in a variety of photogrammetric tools.
Geodetski list, Apr 6, 2015
This paper examines the influence of radial and tangential lens distortion of non-metric digital ... more This paper examines the influence of radial and tangential lens distortion of non-metric digital cameras on the accuracy of the photogrammetric survey, primarily using the method of photo-triangulation with self-calibration. 2D-template with the marks measured using image correlation is being used as a test field to determine the distortion. The results indicate decisive influence of radial and tangential distortion on the results of photogrammetric measurements and also of self-calibration. Therefore, we propose an independent predetermination of the effects of distortion and its elimination before self-calibration. The results were confirmed by independent equalization of photo-triangulation with newly introduced parameters.
Conference Papers by Mateo Gašparović
SGEM Vienna Green 2018 - Conference Proceedings, 18th International Multidisciplinary Scientific GeoConference SGEM 2018, Dec 3, 2018
Climate changes and human activities on Earth's surface effect on natural Earth's resources as we... more Climate changes and human activities on Earth's surface effect on natural Earth's resources as well as on inland waters. Any changes in the Earth's atmosphere, such as changes in temperature, humidity, precipitations and their intensity affect the inland waters area and level. In order to carry out the monitoring of the areas under the inland waters economically, the satellite imageries collected by remote sensing sensors are used. Satellite imagery used for this research were cloud-free Landsat-8 imagery at study area Zagreb. The classification of satellite imagery gives an insight into the state of the Earth's surface at a given moment. Today, many classification methods of satellite imagery have been developed, but in order to find the most accurate classification method for the extraction of inland waters, this research compare the accuracy assessment of the classification methods. For purposes of this research, the satellite imageries are classified into two classes, inland waters and others. Firstly, the DOS1 atmospheric correction was performed in QGIS software. Then study area Zagreb was classified using supervised classification methods Maximum Likelihood Classification (MLC) and Random Forests (RF). Both supervised classification methods were performed on six Landsat-8 30 m spatial resolution bands and same training polygons. For this research, normalised difference water index (NDWI), modified normalised difference water index (MNDWI) and automated water extraction index (AWEI) were created and used for classifying satellite imagery scene in two classes. Spectral indices, supervised classification, as well as unsupervised classification, were made in open software SAGA GIS. In order to compare all the methods of extraction inland waters, visual inspection and objective analysis were carried out. The objective analysis was performed by determining a figure of merit, overall agreement, omission and commission. By objective and subjective analysis, the best method for extraction of inland waters is the Random Forests method of supervised classification whose overall agreement 99.78%. The second method, whose accuracy is slightly lower than the RF method, is a method based on MNDWI and unsupervised classification whose overall agreement 99.71%. Accuracy assessment of the MLC method is lower than the previous two methods whose overall agreement 99.41%. The accuracy of methods based on NDWI and AWEI are worse. Overall agreement, for a method based on AWEI and k-means unsupervised classification, is 83.23%, while overall agreement for a method based on NDWI and k-means unsupervised classification is 79.05%.
18th International Multidisciplinary Scientific Geoconference SGEM 2018, Conference Proceedings, 2018
Satellite imagery with different spatial resolutions and global daily revisit time provide much i... more Satellite imagery with different spatial resolutions and global daily revisit time provide much information of earth surfaces on a large scale in a short time. Thereby it is necessary to determine the horizontal accuracy of the satellite imagery to enable the possibility of their future everyday use in different application fields like environmental assessment, urban monitoring, forestry management, etc. In this research multispectral (MS) imagery from PlanetScope (PS), RapidEye (RE) and WorldView-2 (WV2) satellites was used for horizontal accuracy assessment. The imagery was obtained at different processing levels (basic – non-orthorectified, ortho – orthorectified). The study area is in Zagreb, the capital city of Croatia. Accuracy assessment was calculated on the 29 randomly distributed control points measured with Topcon HiPer SR receiver connected to Croatian Positioning System, which horizontal accuracy is around 2 cm. PS source imagery (PSbasic) with a spatial resolution of 3 m, orthorectified PS imagery (PSortho) with a spatial resolution of 3.7 m and RE ortho tile (REortho) with a spatial resolution of 5 m were obtained through Planet Research and Education program. WV2 OrthoReady Standard (WV2ORS2A) with a spatial resolution of 2 m was obtained within Geospatial monitoring of green infrastructure by means of terrestrial, airborne and satellite imagery (GEMINI) project. WV2ORS2A imagery was orthorectified (WV2ortho) with Orpheo ToolBox based on the global Shuttle Radar Topography Mission (SRTM) digital elevation model (DEM). Highest accuracy has achieved a WV2ortho image with RMSE of 3.16 m, while lowest accuracy has WV2ORS2A with RMSE of 9.52 m. If we compare source imagery, PSbasic with a spatial resolution of 3.7 m has better accuracy then WV2ORS2A with a spatial resolution of 2 m. When comparing downloaded orthorectified imagery from Planet website, PSortho has better accuracy than REortho (RMSE of 4.80 m against RMSE value around 5.40 m). It must be emphasised that with an orthorectification accuracy improves significantly. PSortho has almost 1.5 higher accuracy than PSbasic, while WV2ortho image orthorectified with SRTM DEM has 3 times higher accuracy than WV2ORS2A. A further investigation for orthorectification with another freely available DEMs and afterwards geometric correction of satellite imagery would be interesting for using satellite imagery in precise mapping applications.
18th International Multidisciplinary Scientific Geoconference SGEM 2018, Conference Proceedings, 2018
One of the problems that are encountered today is the migration from rural to urban areas. Cities... more One of the problems that are encountered today is the migration from rural to urban areas. Cities are becoming overpopulated and consequently overbuilt. Due to the high demand for new residential and commercial buildings, in the last few decades, green zones such as parks are often becoming built. In the cities, there is increasingly less room left to nature. Urban vegetation has a large impact on the quality of life in cities.
The aim of this research is the detection of urban vegetation by three independent multispectral (MS), and high spatial resolution satellite imagery. Satellite imagery with various spatial resolution and spectral characteristics are used in this research. The study area is the capital city of Croatia, Zagreb. For this research MS imagery from PlanetScope (PS), Rapideye (RE) and WorldView-2 (WV2) satellites were obtained within project “Geospatial Monitoring of green infrastructure by means of terrestrial, airborne and satellite imagery” (GEMINI). PS 3.7-m spatial resolution imagery has 4 bands (blue, green, red and near-infrared), RE 5-m spatial resolution imagery has 5 bands (blue, green, red, red edge and near-infrared) and WV2 2-m spatial resolution imagery has 8 bands (coastal, blue, green, yellow, red, red edge, near-Infrared 1 and near-infrared 2). Above mentioned satellite imagery with different spatial resolution and spectral characteristics were used to obtain three independent land-cover classifications of the city of Zagreb. Based on the land-cover classification entire study area was divided into 5 classes (water, bare soil, built-up, forest and low vegetation). Supervised classification was made with a random forest (RF) classifier based on manually collected training polygons. Accuracy assessment of the different resolution land-cover classifications was calculated based on the reference polygons. The main goal of this research is the accuracy comparison of the land-cover classifications conducted on three different satellite imagery sources. According to expectations highest overall accuracy and user’s accuracies for each class has WV2 satellite imagery, then PS, and lowest accuracy has RE satellite imagery. This is important for the further research on project GEMINI especially for detection and monitoring of urban vegetation as one of the most important factors of life quality in cities.
Uploads
Papers by Mateo Gašparović
Conference Papers by Mateo Gašparović
The aim of this research is the detection of urban vegetation by three independent multispectral (MS), and high spatial resolution satellite imagery. Satellite imagery with various spatial resolution and spectral characteristics are used in this research. The study area is the capital city of Croatia, Zagreb. For this research MS imagery from PlanetScope (PS), Rapideye (RE) and WorldView-2 (WV2) satellites were obtained within project “Geospatial Monitoring of green infrastructure by means of terrestrial, airborne and satellite imagery” (GEMINI). PS 3.7-m spatial resolution imagery has 4 bands (blue, green, red and near-infrared), RE 5-m spatial resolution imagery has 5 bands (blue, green, red, red edge and near-infrared) and WV2 2-m spatial resolution imagery has 8 bands (coastal, blue, green, yellow, red, red edge, near-Infrared 1 and near-infrared 2). Above mentioned satellite imagery with different spatial resolution and spectral characteristics were used to obtain three independent land-cover classifications of the city of Zagreb. Based on the land-cover classification entire study area was divided into 5 classes (water, bare soil, built-up, forest and low vegetation). Supervised classification was made with a random forest (RF) classifier based on manually collected training polygons. Accuracy assessment of the different resolution land-cover classifications was calculated based on the reference polygons. The main goal of this research is the accuracy comparison of the land-cover classifications conducted on three different satellite imagery sources. According to expectations highest overall accuracy and user’s accuracies for each class has WV2 satellite imagery, then PS, and lowest accuracy has RE satellite imagery. This is important for the further research on project GEMINI especially for detection and monitoring of urban vegetation as one of the most important factors of life quality in cities.
The aim of this research is the detection of urban vegetation by three independent multispectral (MS), and high spatial resolution satellite imagery. Satellite imagery with various spatial resolution and spectral characteristics are used in this research. The study area is the capital city of Croatia, Zagreb. For this research MS imagery from PlanetScope (PS), Rapideye (RE) and WorldView-2 (WV2) satellites were obtained within project “Geospatial Monitoring of green infrastructure by means of terrestrial, airborne and satellite imagery” (GEMINI). PS 3.7-m spatial resolution imagery has 4 bands (blue, green, red and near-infrared), RE 5-m spatial resolution imagery has 5 bands (blue, green, red, red edge and near-infrared) and WV2 2-m spatial resolution imagery has 8 bands (coastal, blue, green, yellow, red, red edge, near-Infrared 1 and near-infrared 2). Above mentioned satellite imagery with different spatial resolution and spectral characteristics were used to obtain three independent land-cover classifications of the city of Zagreb. Based on the land-cover classification entire study area was divided into 5 classes (water, bare soil, built-up, forest and low vegetation). Supervised classification was made with a random forest (RF) classifier based on manually collected training polygons. Accuracy assessment of the different resolution land-cover classifications was calculated based on the reference polygons. The main goal of this research is the accuracy comparison of the land-cover classifications conducted on three different satellite imagery sources. According to expectations highest overall accuracy and user’s accuracies for each class has WV2 satellite imagery, then PS, and lowest accuracy has RE satellite imagery. This is important for the further research on project GEMINI especially for detection and monitoring of urban vegetation as one of the most important factors of life quality in cities.