Search

Suspected Hazardous Area extent is a very important task. It can be done by using advanced computer vision methods and artificial intelligence algorithms on airborne and space imagery in order to extract new information of SHA and to detect indicators of mine presence. We introduce the concept and describe a procedure of strong mine presence indicators detection by using convolutional neural networks and rule-based inference. Also, we propose a recommender system that improves detection quality with interactive relevance feedback. Such a system may also assist in post-processing procedures and classification of indicators after their detection.

U radu se analiziraju Land Administration Domain Model (LADM) -ISO 19152 norma, INSPIRE direktiva i tehničke specifikacije za zgrade i katastarske čestice te njihova primjenjivost za razvoj i uspostavu 3D katastra. Usporedbom LADM norme i INSPIRE specifikacija prikazano je pojmovno podudaranje i kompatibilne definicije zajedničkih koncepata za katastarske čestice uz isticanje njihovih razlika u opsegu i ciljanim područjima primjene. S obzirom da je LADM primarno orijentiran na sustave za upravljanje zemljištem pokazao se kao bolja osnova za uspostavu 3D katastra. Također, u radu se razmatra primjenjivost LADM-a i INSPIRE-a u sustavu upravljanja zemljištem u Hrvatskoj. Zaključeno je, na temelju dosadašnjih radova, da direktna implementacija 3D katastra nije moguća zbog trenutnog stanja povezanih upisnika i načina strukturiranosti postojećih podataka te se predlaže postepeni prelazak u 3D katastar uz paralelno rješavanje zakonodavnih i institucionalnih pitanja.

This paper presents the analysis of two types of remote sensing data ; hyperspectral Hyperion (EC-1) and multispectral LANDSAT 8 (OLI). The main aim is to assess the influences of atsensor radiometric re-calibration and atmospheric correction on Vegetation Indices (VI) performances by estimating its values and credibility. The proposed examination is corresponding to different spectral resolution, as well as bands wavelengths and its distance between the band center and the edge of the band (FWHM). On the selected data sets preprocessing and processing procedures were applied. In the preprocessing stage, the Hyperion at-sensor DN data is first radiometrically calibrated by a standard protocol EO-1 User Guide v. 2.3 (Beck, 2003). Next stage is radiometric recalibration and atmospheric correction via Supervised Vicarious Calibration (SVC) method (Brook and Ben-Dor, 2011). The SVC method is based on a mission-by-mission approach of the data of interest. Data quality is evaluated before and during the calibration procedure and involves multiple stages of correction depending on the quality of the analyzed data. While for LANDSAT imagery a simpler calibration procedure was applied using coefficients reported in its inherent MTL file. Following processing procedures included calculation of the three commonly used VIs ; Enhanced Vegetation Index (EVI), Normalized Difference Vegetation Index (NDVI) and Simple Ration Index (SRI). Aforementioned VIs were calculated for every correction stage of both calibration procedures. The VIs values were normalized for further comparison. Determining how much different data type VIs results are affected by the atmosphere and sensors radiometric performance was done by applying spatial correlation analysis. Also, for comparison, structural similarity index (SSIM) was applied. The procedure was done for all normalized VIs that were derived in all calibration stages in order to assess in what scope the calibration procedures and steps are needed to have reliable results. Beck, R., 2003. EO-1 user guide v. 2.3. Department of Geography University of Cincinnati. Brook, A. and Dor, E.B., 2011. Supervised vicarious calibration (SVC) of hyperspectral remote-sensing data. Remote Sensing of Environment, 115(6), pp.1543- 1555.

The main topic discussed in this paper is the research, development, and implementation of hyperspectral remote sensing technology in humanitarian mine action (HMA), mainly for non- technical survey (NTS) from aerial platforms. NTS should be conducted to determine whether landmines or unexploded ordnance (UXO) exist in considered areas and whether clearance is needed and if so, in what scope. The availability of the hyperspectral sensors (2011–2012) that are suitable for use with multi-engine unmanned aerial vehicles (UAV) enabled the development of systems for HMA. While large and costly airborne hyperspectral systems have been available for over two decades, they had little to no impact on HMA. Optical spectroscopy brought out interest in the relationship between vegetation and explosives, and this relationship is considered herein. Therefore, we briefly analyzed the state of landmine detection via hyperspectral technology, particularly the efforts to detect the mines due to the influence of explosives on vegetation reflectance spectra.

U okviru EU FP7 projekta TIRAMISU (2012.2015.) za potrebe humanitarnog razminiranja, razvijeno je nekoliko alata.1 Ovi alati namijenjeni su za izviđanje i detekciju minski sumnjive površine, njezinih indikatora, neeksplodiranih ubojnih sredstava te za uredsku rekonstrukciju bojišnice korištenjem podataka prikupljenih iz zračnih i zemaljskih platformi senzorima s različitim valnim područjima. U tom procesu korišten je vrlo širok spektar metoda obrade i interpretacije prikupljenih podataka, analiza terena, znanja, kontekstualnih i drugih informacija, itd. [1]. U periodu provođenja TIRAMISU projekta dolazi do rapidno rastućih sigurnosnih prijetnji u Europi te intenziviranja terorističkih napada s upotrebom improviziranih eksplozivnih naprava (IED). Ovo stavlja područje sigurnosti visoko na listu prioriteta kao i potrebu za pronalaskom i razvojem alata kojima bi se odgovorilo na ovu vrstu ugroza. U članku se, stoga, kratko komentiraju odabrani primjeri rješenja koji su razvijeni tijekom projekta [1] za potrebe protuminskog djelovanja i diskutira se njihov mogući prijenos u domenu borbe protiv IED-a. Osim toga, komentira se koncept jednog odabranog sustava za borbu protiv IED-a kao i nužna unapređenja i modifikacije kako bi se postigla njegova funkcionalnost za planiranu namjenu.

The potentials of hyperspectral remote sensing are widely used in many domains, e.g. in the geology, agriculture, forestry, vegetables and fruit industry, protection of the environment, sea and land pollution monitoring, forensics. Our attention is aimed on the application of potentials of hyperspectral remote sensing for humanitarian demining, unexploded ordnance survey (UXO), on detection of improvised explosive devices (IED). The start was in European Commission FP6 project ARC (2001) for humanitarian mine action, continued with monitoring of sea pollution (Croatian Ministry of Science project 2008), finished in FP7 project TIRAMISU (2012-2015) with mine action and UXO detection. In these cases was used hyperspectral line scanner V9 (Specim) integrated in push-broom mode acquisition system. In 2015 we introduced full frame hyperspectral sensor, UHD-185 (Cubert). Both types of sensors (line scanner and full frame sensor) were integrated into aerial acquisition and navigation systems on board of multiengine UAV and a light helicopter and applied in very intensive data collecting campaigns over the mine fields. Also the radio controlled blimp and a large helicopter were tested and evaluated as platforms for line scanner. Main results of the research and development, testing and evaluation of this new technology for mine action are presented.

A remote sensing method for assessment of spatial-temporal distribution of bees, was derived from 2003 to 2006 while its first operational application started in 2013 in the framework of the TIRAMISU Project. The method derives spatial-temporal distribution of the preconditioned (trained) honeybees above an area that is contaminated by explosive or landmines. For this purpose, a long-wave infrared cameras and high-resolution digital cameras were used. Direct detection of honeybees on an image is limited by the resolution of the electro-optical sensor, so for detection and assessment of spatial-temporal distribution of honeybees the principal components analysis (PCA) is crucial. The key feature of the method is an indirect detection of bees, by detecting their signatures in the principal component raster, obtained by processing the images of the time sequence. Within this project we have tested a several platforms for data acquisition: radio controlled blimp (2013), remotely piloted aircraft system (2014, 2015) and a mast (2013, 2015). The greatest challenge was to find an appropriate airborne platform and operational parameters for visible wavelength data acquisition since it is much harder to detect honeybees in this wavelength range, regarding lower contrast of honeybees to ground surface. Finally, in 2015, successful results were achieved with an RPAS and color camera with these parameters: 4096x2160 pixels, 24 bits and 25 frames/s. The 25 frames per second enables fine temporal resolution and estimation of spatial-temporal density.

In this paper, we present a case study report on how novel robotics technologies like the Unmanned Aerial System (UAS) and data processing methodologies could be used in order to support the traditional mine action procedures and be directly applied onto the terrain while increasing the operational efficiency, supporting mine action workers and minimizing human suffering in case of natural disaster with impact to mine action. Our case study is focusing on the region Olovo (Central Bosnia and Herzegovina) in response to massive flooding, landslides and sediment torrents in spring- summer of 2014. Such destructive impact of the natural disaster on the mine action situation resulted with a re-localizing of many explosive remnants of war which have been moved due to the flooding and landslides with significant negative environmental and security consequences increasing new potentially suspected hazardous areas. What will be elaborated in this paper is the following: problem definition with a statement of needs, data acquisition procedures with UAS, data processing and quality assessment and usability in further mine action procedures.

After the destructive impact of flooding on minefields in Bosnia and Herzegovina in 2014 the goal was to: (I) Provide reliable high- resolution spatial data and information by aerial surveillance and reconnaissance. (II) Develop initial models for spatial estimation of new hazardous risk caused by the shifting of landmines and unexploded ordnance (UXO) to areas which had not been mine suspected before the disaster. (III) Develop and validate Recommendations and Standard Operating Procedures for mine action after natural disasters.

In this paper, we present results of UAV applicability level for Hyperspectral Line Scanner survey of mine suspected areas, in particular for the purpose of vegetation analysis in and outside of mine-contaminated areas. The emphasis is placed on testing different UAVs with predefined platform requirements measures for specific purpose and sensor system.

The use of the unmanned aircraft systems (UAS) for humanitarian mine action is comming technology. There is a large discrepancy between very simplified offering of UAS industry and the needs of the mine action. The misunderstanding between the potentials and operational needs is a main obstacle for deployment of UAS in mine action. The own experience of the application of UAS in a large mine suspected areas, influenced by severe natural disaster in 2014 motivated us to consider this topic deeper. In considered cases UAS were exposed to the variety of extreme requirements, the situations, terrain, relief, vegetation, hazard level, acces, GPS satelite availability. Our goal is to derive situation spatial statistical models and explain impact of majority of the mentioned variables. Aerial mapping of the affected mine suspected area damaged by landslides, torrents and floods was conducted with two different UAS, we use only one data set. Once obtained, the data acquired from the UAS were processed and new digital orthomosaic and digital surface terrain models of affected mine suspected areas were produced. When the initial evaluation of spatial accuracy was done it was found that the value of spatial positional error varies, considerably from 1m to 45m, regardless of the uniform processing procedure. Due to various factors that could affect the data to oscillate in positional accuracy so greatly it is clear that simply understanding of this phenomenon is not possible and it is necessary conduct deeper analysis of the data. For further analysis one data set of 11 recorded locations was selected. In this paper will be presented different statistical models of the various factors influence on the realization of spatial accuracy.

Devastating floods swept through Bosnia and Herzegovina, Croatia, and Serbia in May 2014. The destructiveness of the floods, landslides and sediment torrents on minefields resulted in significant environmental and security issues. These three countries’ mine action centers launched a joint project cofunded by the Republic of Croatia’s Ministry of Foreign and European Affairs to develop effective and efficient methods and technologies that might improve the situation. Their research seeks to provide reliable assessments of the flood damage to minefields and generate accurate implications for potential hazardous areas.

Non-technical survey of Suspected Hazardous Area (SHA) is a very complex procedure that is additionally hindered when the area is under destructive impact of landslides and sediment torrents. Employment of Remotely Piloted Aircraft Systems (RPAS) in non-techical survey can be of great significance in such circumstances when, due to inaccessibility of the location and high risks connected to it, it is impossible to define the destructive impact of landslides and sediment torrents. Aerial survey of such area can provide substantial information on the impact of these destructive phenomena, its elements, placement and indication of its status, and sometimes also provide information of the MSA indicators (bunkers, trenches, roads and landmarks of the minefield records, etc.). In the case study of the location Krsno polje (municipality Maglaj), there will be presented a complete integrated operating procedure: problem definition with a statement of needs, data acquisition procedures applied with such systems, data processing and quality assessment and usablity in further mine action procedures. At this location, greatly affected by a natural disaster that has befallen upon B&H in May of 2014., both mine endangerment and backfilling of civilian houses ocurred, including the potential risk of spreading onto the road between Maglaj and Zavidovići resulting in possible cut-offs in regional road communication. Demining activities were undertaken at the location, as well as the removal of deposited material that struck residential buildings and yards ; however not the landslide that of which a significant part is situated in the MSA. The area has not been remediated and is still a threat endandgering the region with possible reactivation, expansion and mine displacement.

The module of T-AI DSS for data acquisition should provide the stability and reliability of (aerial) data acquisition on each platform. Subsystems (system configurations are different for different platforms) for aerial data acquisition will be examined on multiple platforms (Mi-8, blimp, Bell-206) and should have stable operation, without cancellation, on every platform. A new system for aerial hyperspectral survey: TIRAMISU light hyperspectral imaging system (T-LHSIS), was conceptualized by CTDT, designed, constructed and manufactured by FGUNIZ. T-LHSIS was tested on two platforms: blimp and Bell-206 helicopter by CTDT and FGUNIZ. The features of the system shown in the following text. T-LHSIS is a new tool, which can be used as stand alone equipment or in T-AIDSS. The helicopter Bell- 206 is a new platform which can be used within T-AI DSS. The continuous and stable electricity supply for the aerial acquisition multisensor subsystem is re- designed, developed and built up in T-AI DSS. It is necessary to provide the independence of the power supply for the aerial acquisition system of AI DSS. This module is used for the collection of additional data from the depths of SHA. The requirements (general and specific) for the collection of additional data on SHA-in are the result of work in the module for the analytical assessment of the data in MIS.

The airborne and space borne hyper spectral remote sensing is new challenge for the application in humanitarian mine action. The basic knowledge and the understanding of the demands, needs and requirements to this technology in the domain of humanitarian mine action starts from the available knowledge in the agriculture, forestry, ecology, land use, land cover, military surveillance and reconnaissance etc. The research of the basic behavior of hyper spectral features, potentially relevant for the humanitarian mine action, was conducted on several minefields using the ground vehicle based system. The development of the ground vehicle based system started in 2012, its advancement continued in 2013 and 2014, in the frame of EU FP7 project TIRAMISU. The experience collected during research phase leaded to development of the model of a ground vehicle based hyper spectral remote sensing system which can be applied for technical survey.

The general survey of the unexploded ordnance (UXO) scattered around the ammunition depot after its unplanned explosion and the ground based measurements of the hyper spectral samples (end members) of UXO have been done in order to create initial spectral library of UXO. The methods, technique and collected data are presented and evaluated. The Johnson’s criterion was used for detection, classification, recognition and identification of UXO in the airborne images (visible and near infrared wavelengths) of the surrounding of the ammunition depot. The test site near Benkovac contains 1000 landmines and 524 metal debris buried in the year 2001 in squares 1x1 m, at depths from 5 to 20 cm below the surface. The locations of 885 landmines and debris are not public and the blind tests are possible. The sparse vegetation covers some squares since the soil is meager. The hyper spectral data have been collected of the 1x1 m squares by the ground based mechanic scanner. The spectral samples of the vegetation inside and outside of the test site have been collected and total Nitrogen contents were measured.

In this paper, we address the problem of spatial accuracy of the hyperspectral cubes of mountainous and hilly terrain. Achievable spatial accuracy and precision of the hyperspectral images at the mountainous and hilly terrain are influenced by different parameters. In the paper is reported the main achievement for the used survey system with hyperspectral line scanner, the increased spatial accuracy, and precision based on the GCP’s derived from the digital orthophoto map.