Dušan Jovanović | University of Novi Sad, Faculty of Technical Sciences (original) (raw)

Papers by Dušan Jovanović

Remote Sensing, 2024

Precision viticulture systems are essential for enhancing traditional intensive viticulture, achi... more Precision viticulture systems are essential for enhancing traditional intensive viticulture, achieving high-quality results, and minimizing costs. This study explores the integration of Unmanned Aerial Vehicles (UAVs) and artificial intelligence in precision viticulture, focusing on vine detection and vineyard zoning. Vine detection employs the YOLO (You Only Look Once) deep learning algorithm, achieving a remarkable 90% accuracy by analysing UAV imagery with various spectral ranges from various phenological stages. Vineyard zoning, achieved through the application of the K-means algorithm, incorporates geospatial data such as the Normalized Difference Vegetation Index (NDVI) and the assessment of nitrogen, phosphorus, and potassium content in leaf blades and petioles. This approach enables efficient resource management tailored to each zone’s specific needs. The research aims to develop a decision-support model for precision viticulture. The proposed model demonstrates a high vine detection accuracy and defines management zones with variable weighting factors assigned to each variable while preserving location information, revealing significant differences in variables. The model’s advantages lie in its rapid results and minimal data requirements, offering profound insights into the benefits of UAV application for precise vineyard management. This approach has the potential to expedite decision making, allowing for adaptive strategies based on the unique conditions of each zone.

Informacioni sistem zemljišnih parcela (LPIS) i kontrola daljinskom detekcijom igraju važnu ulogu... more Informacioni sistem zemljišnih parcela (LPIS) i kontrola daljinskom detekcijom igraju važnu ulogu u sistemu direktnih isplata za potrebe poljoprivrede u zemljama članicama Evropske Unije (EU). EU odobrava subvencijе poljoprivrednicima koji uzgajaju određene vrste biljnih kultura. S ciljem upravljanja i kontrole zahteva, EU je donela odluku da osnuje Integrisani Sistem Administracije i Kontrole-Integrated Administration and Control System (IACS), 1992. godine. Tokom godina, otkriveno je da površine za koje se zahteva subvencija često ne reprezentuju realnost. Shodno tome, trebalo je unaprediti proces deklaracije uspostavljanjem Informacionog sistema zemljišnih parcela-Land Parcel Identification System (LPIS), po mogućnosti zasnovanog na ortofoto snimcima. LPIS sistem je ključna komponenta IACS sistema. Takođe je jedan od najkompleksnijih IACS podsistema, posebno zbog grafičke prirode podataka i raznovrsnosti tipova podataka koji su prisutni. U radu je diskutovana je upotrebljivost najčešće korišćenih komercijalnih satelitskih sitema, na osnovu principa daljinske detekcije i tehnike objektno orijentisane klasifikacije upotrebom Erdas softverskog okruženja. Analizirane su prednosti automatske klasifikacije pri izradi jednog ovako kompleksnog sistema. Specificirani su aspekti primene i dat je predlog implementacije LPIS u našem okruženju. Procesiranjem satelitskih snimaka pilot područja okoline Pančeva, upotrebom Erdas programskog paketa analizirani su mogući pristupi u kreiranju i uspostavljanju Informacionog sistema zemljišnih parcela. KLJUČNE REČI: Geoinformacioni sitemi, Informacioni sistem zemljišnih parcela LPIS (Land Parcel Identification System), daljinska detekcija, objektno-orijentisana klasifikacija, Erdas. ABSTRACT: Land Parcel Identification System and Control with Remote Sensing (CwRS) play an important role in the system of the direct agricultural area-based payments in the EU Member States. The European Union (EU) grants financial aid to farmers, growing a certain kind of crops. In order to administrate and to control the farmer's declarations, the EU decided to establish an Integrated Administration and Control System (IACS) in 1992. Over the years it was found, that the declared areas often do not represent the reality. As a result, the process of declaration should be improved by the establishment of a Land Parcel Identification System (LPIS), preferably based on orthophotos. The LPIS system is the key component of an IACS. It is also possibly one of the most complex IACS subsystems , mostly due to the graphical nature of the data and the variety of different data formats involved. In order to create a pilot LPIS sistem the usefulness of the most common commercial highresolution satellite systems is discussed based on remote sensing, change detection and image classification. Classification was performed in principles of object-oriented classification, using Erdas software tool. The benefits of automatic classification process in the preparation of such a complex system are analysed together with aspects of application and implementation of LPIS in analised area of Pancevo.

Info M, 2011

Research Journal of Agricultural Science, 2015

A land-parcel identification system (LPIS) is a system to identify land use for a given country. ... more A land-parcel identification system (LPIS) is a system to identify land use for a given country. The goal of LPIS is to get a clear picture of how the land is used for agricultural production, regardless of the crop that is grown on them. Such a regulated and transparent system is a prerequisite for obtaining EU subsidies for agricultural production. LPIS core conceptual model defines entities in agriculture like agricultural parcels and blocks. ISO 19152 defines a reference Land Administration Domain Model (LADM) covering basic information-related components of land administration including parties (people and organizations), basic administrative units, rights, responsibilities, and restrictions (ownership rights), spatial units (parcels, and the legal space of buildings and utility networks), spatial sources(surveying) and spatial representations (geometry and topology). This paper describes the possibilities of integration of these two models for Serbia. Cadastral data for Serbia are given in country domain profile based on LADM. Extended LPIS domain model for Serbia based on collaboration with LADM is proposed together with case study example. The proposal has been given for the implementation of LPIS based on open-source GIS solutions. Data on the cadastral parcel and agricultural parcel are under the jurisdiction of two different organizations. Both models are based on the same key abstractionthe parcel, which raises the possibility of the occurrence of redundant data. By integrating the two models, the connection of one model with another can be provided. The introduction of the service architecture will enable that the data in both systems are up to date, which would reduce redundancy.

ISPRS international journal of geo-information, Jul 30, 2020

The Smart Cities data and applications need to replicate, as faithfully as possible, the state of... more The Smart Cities data and applications need to replicate, as faithfully as possible, the state of the city and to simulate possible alternative futures. In order to do this, the modelling of the city should cover all aspects of the city that are relevant to the problems that require smart solutions. In this context, 2D and 3D spatial data play a key role, in particular 3D city models. One of the methods for collecting data that can be used for developing such 3D city models is Light Detection and Ranging (LiDAR), a technology that has provided opportunities to generate large-scale 3D city models at relatively low cost. The collected data is further processed to obtain fully developed photorealistic virtual 3D city models. The goal of this research is to develop virtual 3D city model based on airborne LiDAR surveying and to analyze its applicability toward Smart Cities applications. It this paper, we present workflow that goes from data collection by LiDAR, through extract, transform, load (ETL) transformations and data processing to developing 3D virtual city model and finally discuss its future potential usage scenarios in various fields of application such as modern ICT-based urban planning and 3D cadaster. The results are presented on the case study of campus area of the University of Novi Sad.

Savremena teorija i praksa u graditeljstvu, Jun 10, 2020

Phenology modeling of the most common agricultural cultures based on time series of high spatial ... more Phenology modeling of the most common agricultural cultures based on time series of high spatial resolution satellite imagery and vegetation indices was conducted for several crop types. This data was used as an indicator of crops state in the multivariable correlation model as dependent variables. The influence of climate factors (temperature, air pressure, precipitation, insolation, cloudiness and humidity) on crops state was determined using multivariable correlation. This model allows prediction of delayed influence of climate factors on plant health and state through the values of NDVI.

Proceedings of SPIE, Aug 12, 2016

The aim of our study was to verify the impact that pansharpening (PS) methods produce on vegetati... more The aim of our study was to verify the impact that pansharpening (PS) methods produce on vegetation indices. We used images with both moderate (Landsat 7, Landsat 8) and high (World View2, Ikonos) spatial resolution on which we performed three methods of PS (Brovey transform, Gram-Schmidt and Principal component). The study is based on the differences of vegetation indices (VI) values before and after the pansharpening method is applied. The difference is quantified as an root mean square error. Vegetation indices used in this study were: NDVI, MSAVI2, EVI2, GNDVI, OSAVI and SAVI. Statistical analysis is carried out by calculating coefficients of correlation, root mean square errors and bias calculations for every vegetation index before and after pansharpening procedure is done. The results imply that the BT gave the most diverse results between original VI values and the PS VI values, while the GS and PC methods preserved the values of pixel bands, and that the effect of any PS method is most evident when using Ikonos bands.

IOP conference series, Dec 1, 2017

3D models of urban areas have found use in modern world such as navigation, cartography, urban pl... more 3D models of urban areas have found use in modern world such as navigation, cartography, urban planning visualization, construction, tourism and even in new applications of mobile navigations. With the advancement of technology there are much better solutions for mapping earth's surface and spatial objects. 3D city model enables exploration, analysis, management tasks and presentation of a city. Urban areas consist of terrain surfaces, buildings, vegetation and other parts of city infrastructure such as city furniture. Nowadays there are a lot of different methods for collecting, processing and publishing 3D models of area of interest. LIDAR technology is one of the most effective methods for collecting data due the large amount data that can be obtained with high density and geometrical accuracy. CityGML is open standard data model for storing alphanumeric and geometry attributes of city. There are 5 levels of display (LoD0, LoD1, LoD2, LoD3, LoD4). In this study, main aim is to represent part of urban area of Novi Sad using LIDAR technology, for data collecting, and different methods for extraction of information's using CityGML as a standard for 3D representation. By using series of programs, it is possible to process collected data, transform it to CityGML and store it in spatial database. Final product is CityGML 3D model which can display textures and colours in order to give a better insight of the cities. This paper shows results of the first three levels of display. They consist of digital terrain model and buildings with differentiated rooftops and differentiated boundary surfaces. Complete model gives us a realistic view of 3D objects.

Šumarski list

Poznavanje točnih i ažurnih geoprostornih podataka o šumama i šumskim površinama dobivenih interp... more Poznavanje točnih i ažurnih geoprostornih podataka o šumama i šumskim površinama dobivenih interpretiranjem podataka metodama daljinskih istraživanja, ima veliko značenje na pravovremenu intervenciju i upravljanje šumskim površinama, dok odluke temeljene na zastarjelim i nedovoljno preciznim podacima mogu imati vrlo negativne posljedice. U ovome radu prezentirana je metoda analize radarskih Sentinel 1 SAR satelitskih snimaka, zajedno s kombinacijom multispektralnih Sentinel 2 snimaka, s ciljem identifikacije nestalih i novo nastalih šumskih površina, kao i ocjenom uporabljivosti besplatnih, svima dostupnih radarskih satelitskih snimaka za promatranje šumskih površina. Klasifikacija radarskih snimaka obavljena je pomoću Random Forest klasifikacijskog algoritma na Cloud platformi. Provedena studija pokazala je da je u svakom analiziranom periodu od 2016. do 2019. godine veća površina pod nestalom šumom u odnosu na novonastalu površinu pod šumama. Procjena točnosti klasifikacije za sva...

Remote Sensing

Based on a newly adopted “Rulebook on the records of identified changes on buildings in Serbia” (... more Based on a newly adopted “Rulebook on the records of identified changes on buildings in Serbia” (2020) that regulates the content, establishment, maintenance and use of records on identified changes on buildings, it is expected that the geodetic-cadastral information system will be extended with these records. The records contain data on determined changes of buildings in relation to the reference epoch of aerial or satellite imagery, namely data on buildings: (1) that are not registered in the real estate cadastre; (2) which are registered in the real estate cadastre, and have been changed in terms of the dimensions in relation to the data registered in the real estate cadastre; (3) which are registered in the real estate cadastre, but are removed on the ground. For this purpose, the LADM-based cadastral data model for Serbia is extended to include records on identified changes on buildings. In the year 2020, Republic Geodetic Authority commenced a new satellite acquisition for the...

Tehnicki vjesnik - Technical Gazette, 2019

In this paper several well-known filtering techniques were compared in the purpose of automatic l... more In this paper several well-known filtering techniques were compared in the purpose of automatic line generalization. The used methods for line simplification are digital first order low-pass filter, Savitzky-Golay (SG) filter and Whittaker filter. Two versions of the algorithm for line feature generalization were tested, from source scale 1:25 000 towards target scale of 1:100 000 and from source scale 1:25 000 towards scale of 1:50 000. Also, GPS data filtering for the target scale 1:50 000 was tested. The first version of the algorithm considers that there are no control data, and the filtering parameter is dictated by the desired accuracy for the target scale. The second version involves control data in the target scale. This means that the optimal value for the filtering parameter is the value for which the difference between input and control data is the smallest. Analysis showed that the SG filter yielded the best results in general. The proposed filters can be considered as a new solution for automated cartographic line simplification.

Zbornik radova Departmana za geografiju, turizam i hotelijerstvo, 2017

Satellite images have a wide application for detection and identification of objects, phenomena a... more Satellite images have a wide application for detection and identification of objects, phenomena and changes on the surface of the Earth. In this paper are presented methods for arable land identification based on Sentinel-2 satellite imagery and distribution of the obtained data. The images were atmospherically corrected, resulting in the true reflection values from the ground. The identification procedure is based on known annual crops land cover variation rules during seasons. The vegetation signal in the images was enhanced using the SAVI vegetation index, after which the detection of arable land was carried out by raster subtraction. As a result, data on the spatial distribution of 5 arable land classes were obtained: summer crops, winter crops, pastures, vineyards and orchards and unclassified land. In order to complete the final result, inhabited places and water surfaces were detected and mapped. The resulting data were vectorized and displayed through a three-layer GIS (Geographic information system) service-based architecture in accordance with OGC specification.

Zbornik radova Departmana za geografiju, turizam i hotelijerstvo, 2018

Open Geosciences, 2016

The aim of the paper is to compare Moderate Resolution Imaging Spectroradiometer (MODIS) Normaliz... more The aim of the paper is to compare Moderate Resolution Imaging Spectroradiometer (MODIS) Normalized Difference Vegetation Index (

Geographica Pannonica, 2015

Change detection is a process of detecting differences with the objects or phenomena which are ob... more Change detection is a process of detecting differences with the objects or phenomena which are observed in the different time intervals. In this study different methods of analyzing satellite images are presented, with the aim to identify changes in land cover in a certain period of time (1985-2013). The area observed in this study is the region of mountain Zlatibor (Serbia) with its surroundings. The methods represented in this study are vegetation indices differencing, Supervised classification and Object based classification. These methods gave different results in term of land cover area, and it is generally concluded that supervised classification gave the most accurate results with the images of medium spatial resolution. The results of this study can be used for urban and environmental planning. All information lead to conclusion that the surface under the forests is reduced for about 4% (or about 1000 ha) while the built up area has doubled (grown about 600 ha) during the examined period. The results also highlights the importance of change detection techniques in land cover for the areas that are developing rapidly, such as Zlatibor study area.

ISPRS International Journal of Geo-Information, 2019

The utility network cadastre in Serbia is the main register of utility lines and the rights to th... more The utility network cadastre in Serbia is the main register of utility lines and the rights to them. The Law on State Survey and Cadastre states the necessity for implementing a unified information system of both a real estate and utility network cadastre, but this has not been achieved in practice. The reasons for such a unified information system are to ensure easier maintenance of the rights of both the utilities and properties located above or below them, to ensure more efficient procedures for obtaining the consent for placement, repair, or removal of the utility line, to prevent procedures being executed based on outdated data, to build an information system as the law prescribes, and to facilitate the business processes in the Serbian geodetic authority, since it is responsible for both registers. Therefore, an already-developed LADM (Land Administration Domain Model)-based country profile for Serbia should be extended to include information from the utility network cadastre....

Geocarto International, 2014

ABSTRACT Main objective of this study was to establish a relationship between land cover and land... more ABSTRACT Main objective of this study was to establish a relationship between land cover and land surface temperature (LST) in urban and rural areas. The research was conducted using Landsat, WorldView-2 (WV-2) and Digital Mapping Camera. Normalised difference vegetation index and normalised difference built-up index were used for establishing the relation between built-up area, vegetation cover and LST for spatial resolution of 30 m. Impervious surface and vegetation area generated from Digital Mapping Camera from Intergraph and WV-2 were used to establish the relation between built-up area, vegetation cover and LST for spatial resolutions of 0.1, 0.5 and 30 m. Linear regression models were used to determine the relationship between LST and indicators. Main contribution of this research is to establish the use of combining remote sensing sensors with different spectral and spatial resolution for two typical settlements in Vojvodina. Correlation coefficients between LST and LST indicators ranged from 0.602 to 0.768.

SGEM2011 11th International Multidisciplinary Scientific GeoConference, 2011

ABSTRACT

This paper describes concepts related to facade modeling based on laser scanning. The City Hall o... more This paper describes concepts related to facade modeling based on laser scanning. The City Hall of Novi Sad was chosen as object of interest. City Hall's facade scanning was performed using Leica ScanStation scanner. Scans were taken from three different locations to acquire all pieces of the facade. A GPS receiver was used to measure coordinates of three different points on the facade, so that the scans may be georeferenced later in the process. At the end of scanning process there were three point clouds which represented front, the west and east parts of the City Hall's facade. Further, Leica Cyclone 5.7 was used to process point clouds. The point clouds were processed to remove all the points that did not belong to the facade. Refined point clouds were exported in DXF and 3DS formats and visualized in Leica Virtual Explorer Architect.

Ratarstvo i povrtarstvo, 2014

Running title: Jovanović D et al. Crop yield estimation using methods of remote sensing Summary: ... more Running title: Jovanović D et al. Crop yield estimation using methods of remote sensing Summary: Monitoring phenology of crops and yield estimate based on vegetation indice as well as other parameters such as temperature or amount of rainfall were largely reported in literature. In this research, MODIS Normalized Difference Vegetation Index (NDVI) was used as an indicator of specific crop condition, the other parameter was Land Surface Temperature (LST), which can indicate the amount of crop moisture. Training years were 2011, 2012 and year 2013.