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.

Phenology modeling of the most common agricultural cultures based on time series of high spatialresolution satellite imagery and vegetation indices was conducted for several crop types. This datawas 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 andhumidity) on crops state was determined using multivariable correlation. This model allowsprediction of delayed influence of climate factors on plant health and state through the values ofNDVI.

Automatic extraction of footprints of buildings from orthophotos is a challenge in the field of remote sensing data processing. The combination of image classification and object localization tasks in this research aims to develop a new model based on ResUNet and the YOLO algorithm. By applying the proposed model and publicly available data, a high level of building extraction success of 89% is achieved. Although there is potential to improve the results by introducing other types of data, the integration of these models represents a significant step towards improving the technology of automatic extraction of buildings from orthophotos.

Land use/Land cover (LULC) is crucial for land management. This study shows the spatiotemporal dynamics of LULC for a wide area of Novi Sad with the emphasis on the urban area analysis. Results presented in this study aim to estimate LULC changes and predict future trends of urban area expansion in Novi Sad. Conducted study shows that in the years to come there will be a decrease in the urban area expansion compared to last 35 years.

This paper presents the process of creating and analyzing the accuracy of the Scan to BIM model of the building of the Department of Civil Engineering and Geodesy, Faculty of Technical Sciences, University of Novi Sad based on data collected by terrestrial laser scanning. The point cloud was used to model the object in the BIM environment, while the accuracy of the model was evaluated using Cloud to Model analysis. In order to remove extreme values and noises, cloud filtering methods were applied, after which a statistical analysis of deviations was performed. The results show that most of the point cloud is within a small deviation interval, which confirms the good geometric fit of the BIM model and the point cloud.