Search

Extracting buildings in urban scenes from remote sensing images is crucial for the construction of digital cities, urban monitoring, urban planning, and autonomous driving. Traditional methods generally rely on shadow detection or stereo matching from multi-view high-resolution remote sensing images, which is cost-intensive. Recently, machine learning has provided solutions for the estimation of building heights from remote sensing images, but challenges remain due to the limited observation angles and image quality. The inherent lack of information in a single modality greatly limits the extraction precision. This article proposes an advanced method using multi-source remote sensing images for urban building height estimation, which is characterized by multi-level cross-fusion, the multi-task joint learning of footprint extraction and height estimation, and semantic information to refine the height estimation results. The complementary and effective features of synthetic aperture radar (SAR) and electro-optical (EO) images are transferred through multi-level cross-fusion. We use the semantic information of the footprint extraction branch to refine the height estimation results, enhancing the height results from coarse to fine. Finally, We evaluate our model on the SpaceNet 6 dataset and achieve 0.3849 and 0.7231 in the height estimation metric δ 1 and footprint extraction metric D i c e , respectively, which indicate effective improvements in the results compared to other methods. [ABSTRACT FROM AUTHOR]

Interferometric synthetic aperture radar (InSAR) is a remote sensing tool used for monitoring urban areas affected by geological hazards. Here we analysed the effectiveness of stabilization works on a slow-moving landslide in Arcos de La Frontera (Cádiz, Spain) using a persistent scatterer interferometric approach. The works consisted on jet grouting of cement-based injections and were applied locally to stabilize the most damaged neighbourhood. We processed a large stack of Sentinel-1 SAR satellite acquisitions covering the period January, 2016, to March, 2023, and obtained surface velocity and displacement trends measured along the line of sight (LOS) of the satellite on both ascending and descending orbits. The results show a clear deceleration of the landslide head after mid-2018, suggesting the local stabilization works were effective after that time. Prior to mid-2018, the maximum LOS velocity of the landslide head was 2.2 cm/year in ascending orbit and 1.3 cm/year in the descending orbit, decreasing to 0.43 cm/year and 0.23 cm/year, respectively. The InSAR results were compared to in-situ monitoring data and revealed that the extent of the stabilization has influenced a much larger area beyond the zone of the local interventions. Overall, InSAR has proved a powerful and versatile tool to be implemented in operational geotechnical monitoring. [ABSTRACT FROM AUTHOR]

In the capitalist rush to attract more visitors, cities are committing significant resources to heritage conservation, driven by the substantial economic benefits generated by the tourism industry. However, less famous or less well-resourced cities, often with smaller populations, also known as intermediary cities, find it difficult to allocate funds to protect their most significant heritage sites. In this conservation context, intermediary cities, often on the periphery or 'at the margins', can fill the gaps and needs of urbanism through a better strategic understanding of the challenges of global touristification, thus this research provides urban planning tools for local governments with limited resources to preserve their architectural heritage through remote sensing, for its advantages in terms of lower economic cost, as a valuable monitoring tool to effectively identify high-vulnerability sites that require priority attention in the conservation of architectural heritage. In other words, it allows for a reduction in the territory of those areas located 'at the margins' in terms of urban planning and management, by approaching the territorial, urban, architectural and tourism problems from a transdisciplinary perspective in the preservation of the architectural heritage. This study explores the application of optical (Sentinel-2) using neural networks for classifying the land cover and radar (Sentinel-1 and PAZ) satellite images to obtain the ground motion as a geotechnical risk study, together with geospatial data, for the monitoring of architectural heritage in intermediate cities. Focusing on the districts of Bragança and Guarda in Portugal, the approach allows the direct identification of vulnerable architectural heritage, identifying 9 highly-vulnerable areas using PAZ data and 7 areas using Sentinel-1 data. Furthermore, this work provides an understanding of the potential and limitations of these technologies in heritage preservation because compares the processing results of freely accessible medium-resolution Sentinel-1 radar imagery with the high-resolution radar images from the innovative PAZ satellite. [ABSTRACT FROM AUTHOR]