Although plastic pollution is one of the most noteworthy environmental issues nowadays, there is still a knowledge gap in terms of monitoring the spatial distribution of plastics, which is needed to prevent its negative effects and to plan mitigation actions. Unmanned Aerial Vehicles (UAVs) can provide suitable data for mapping floating plastic, but most of the methods require visual interpretation and manual labeling. The main goals of this paper are to determine the suitability of deep learning algorithms for automatic floating plastic extraction from UAV orthophotos, testing the possibility of differentiating plastic types, and exploring the relationship between spatial resolution and detectable plastic size, in order to define a methodology for UAV surveys to map floating plastic. Two study areas and three datasets were used to train and validate the models. An end-to-end semantic segmentation algorithm based on U-Net architecture using the ResUNet50 provided the highest accuracy to map different plastic materials (F1-score: Oriented Polystyrene (OPS): 0.86; Nylon: 0.88; Polyethylene terephthalate (PET): 0.92; plastic (in general): 0.78), showing its ability to identify plastic types. The classification accuracy decreased with the decrease in spatial resolution, performing best on 4 mm resolution images for all kinds of plastic. The model provided reliable estimates of the area and volume of the plastics, which is crucial information for a cleaning campaign.

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.

Digital elevation model (DEM) has been frequently used for the reduction and management of flood risk. Various classification methods have been developed to extract DEM from point clouds. However, the accuracy and computational efficiency need to be improved. The objectives of this study were as follows: (1) to determine the suitability of a new method to produce DEM from unmanned aerial vehicle (UAV) and light detection and ranging (LiDAR) data, using a raw point cloud classification and ground point filtering based on deep learning and neural networks (NN); (2) to test the convenience of rebalancing datasets for point cloud classification; (3) to evaluate the effect of the land cover class on the algorithm performance and the elevation accuracy; and (4) to assess the usability of the LiDAR and UAV structure from motion (SfM) DEM in flood risk mapping. In this paper, a new method of raw point cloud classification and ground point filtering based on deep learning using NN is proposed and tested on LiDAR and UAV data. The NN was trained on approximately 6 million points from which local and global geometric features and intensity data were extracted. Pixel-by-pixel accuracy assessment and visual inspection confirmed that filtering point clouds based on deep learning using NN is an appropriate technique for ground classification and producing DEM, as for the test and validation areas, both ground and non-ground classes achieved high recall (>0.70) and high precision values (>0.85), which showed that the two classes were well handled by the model. The type of method used for balancing the original dataset did not have a significant influence in the algorithm accuracy, and it was suggested not to use any of them unless the distribution of the generated and real data set will remain the same. Furthermore, the comparisons between true data and LiDAR and a UAV structure from motion (UAV SfM) point clouds were analyzed, as well as the derived DEM. The root mean square error (RMSE) and the mean average error (MAE) of the DEM were 0.25 m and 0.05 m, respectively, for LiDAR data, and 0.59 m and –0.28 m, respectively, for UAV data. For all land cover classes, the UAV DEM overestimated the elevation, whereas the LIDAR DEM underestimated it. The accuracy was not significantly different in the LiDAR DEM for the different vegetation classes, while for the UAV DEM, the RMSE increased with the height of the vegetation class. The comparison of the inundation areas derived from true LiDAR and UAV data for different water levels showed that in all cases, the largest differences were obtained for the lowest water level tested, while they performed best for very high water levels. Overall, the approach presented in this work produced DEM from LiDAR and UAV data with the required accuracy for flood mapping according to European Flood Directive standards. Although LiDAR is the recommended technology for point cloud acquisition, a suitable alternative is also UAV SfM in hilly areas.

Surface water maps are essential for many environmental applications. Waterbody delineation from satellite images remains a challenging task due to sensor limitations, the presence of clouds, the low albedo surfaces in urban areas, topographic, and atmospheric conditions. In this paper, a model based on the Supported Vector Machine (SVM) classifier was adopted for waterbody extraction from Sentinel-2, Landsat 8 Operational Land Imager (OLI) and RapidEye satellite images. As well, the accuracy of two other sources (OpenStreetMapping (OSM) and Military Geographic Institute (MGI)) was tested. The free images from Sentinel-2 and Landsat 8 OLI were more accurate (Kappa (KHAT):0.89, 0.88) data sources than commercial RapidEye images (KHAT: 0.79). Regarding the performance between Sentinel-2 and Landsat 8 OLI, Sentinel-2 obtained the most accurate results (overall accuracy 94.49 vs. 94.17, commission error 1.34 vs. 1.87). Due to the variable spatial resolution of OSM and MGI data, it was not possible to detect small waterbodies with these sources, and therefore high values of omission error and a strong underestimation of the area of surface water were obtained. This study demonstrates the suitability of free images for mapping and monitoring of surface waterbodies, including small water bodies.