Abstract
Environment understanding in real-world scenarios has gained an increased interest in research and industry. The advances in data capture and processing allow a high-detailed reconstruction from a set of multi-view images by generating meshes and point clouds. Likewise, deep learning architectures along with the broad availability of image datasets bring new opportunities for the segmentation of 3D models into several classes. Among the areas that can benefit from 3D semantic segmentation is the automotive industry. However, there is a lack of labeled 3D models that can be useful for training and use as ground truth in deep learning-based methods. In this work, we propose an automatic procedure for the generation and semantic segmentation of 3D cars that were obtained from the photogrammetric processing of UAV-based imagery. Therefore, sixteen car parts are identified in the point cloud. To this end, a convolutional neural network based on the U-Net architecture combined with an Inception V3 encoder was trained in a publicly available dataset of car parts. Then, the trained model is applied to the UAV-based images and these are mapped on the photogrammetric point clouds. According to the preliminary image-based segmentation, an optimization method is developed to get a full labeled point cloud, taking advantage of the geometric and spatial features of the 3D model. The results demonstrate the method's capabilities for the semantic segmentation of car models. Moreover, the proposed methodology has the potential to be extended or adapted to other applications that benefit from 3D segmented models.

Abstract
Monitoring invasive plant species is a crucial task to assess their presence in affected ecosystems. However, it is a laborious and complex task as it requires vast surface areas, with difficult access, to be surveyed. Remotely sensed data can be a great contribution to such operations, especially for clearly visible and predominant species. In the scope of this study, water hyacinth (Eichhornia crassipes) was monitored in the Lower Mondego region (Portugal). For this purpose, Sentinel-2 satellite data were explored enabling us to follow spatial patterns in three water channels from 2018 to 2021. By applying a straightforward and effective methodology, it was possible to estimate areas that could contain water hyacinth and to obtain the total surface area occupied by this invasive species. The normalized difference vegetation index (NDVI) was used for this purpose. It was verified that the occupation of this invasive species over the study area exponentially increases from May to October. However, this increase was not verified in 2021, which could be a consequence of the adopted mitigation measures. To provide the results of this study, the methodology was applied through a semi-automatic geographic information system (GIS) application. This tool enables researchers and ecologists to apply the same approach in monitoring water hyacinth or any other invasive plant species in similar or different contexts. This methodology proved to be more effective than machine learning approaches when applied to multispectral data acquired with an unmanned aerial vehicle. In fact, a global accuracy greater than 97% was achieved using the NDVI-based approach, versus 93% when using the machine learning approach (above 93%).

Abstract

Abstract

Abstract

Abstract
SAR Interferometry (InSAR) techniques are for detecting and monitoring ground deformation all over the planet. Natural disasters such as volcanoes and earthquakes deformations are among the main applications, and the great developments that we have witnessed in recent years suggests that near real-time monitoring will soon be possible. InSAR is developing fast - space agencies are launching more satellites, leading to exponential data growth. Consequently, conventional techniques cannot process all the acquired data. Modern deep learning methods can be a solution since they reach high accuracy in automatically detecting patterns in images and are fast to operate. In this work, we explore the contribution of deep learning vision transformer models to automatically detect seismic deformation in SAR interferograms. A VGG19 model is trained as baseline and ViT model uses 256x256 pixels patches and the full interferogram. The ViT model outperforms the state-of-the-art both for patch and full interferogram approaches, achieving 0.88 and 0.92 F1-score, respectively.