The rapid growth of outdoor digital twin data sets and advancements in 3D data acquisition technology have sparked interest in improving segmentation performance using deep learning. This research aims to analyze and evaluate different sampling strategies and optimization techniques while exploring the intensity information of outdoor point cloud data. Two sampling strategies, random and stratified sampling, are employed to divide a limited data set. Additionally, the data set is divided into point cloud data with and without intensity. The PointNet++ model is used to segment the point cloud data into two classes, vegetation and structure. The results indicate that stratified sampling outperforms random sampling, yielding a considerable improvement in mean intersection over union scores of up to 10%. Interestingly, the inclusion of intensity information in the data set does not universally enhance performance. Although the use of intensity improves the performance of random sampling, it does not benefit stratified sampling. This research provides insights into the effectiveness of different sampling strategies for outdoor point cloud data segmentation. The findings can contribute to the development of optimized approaches to improving segmentation accuracy in outdoor digital twin applications using deep learning techniques.
The latest Digital Terrain Model (DTM) is seen as an upgradable DTM that is fitted to the latest combination of DTM master and its displacement. The latest DTM can be used to overcome the problem of static DTM weaknesses in displaying the latest topographic changes. DTM masters are obtained from InSAR and Digital Surface Model (DSM) ALOS PALSAR conversions. Meanwhile, the displacement is obtained from Sentinel-1 images, which can be updated every 6–12 days or at least every month. ALOS PALSAR data were the images acquired in 2008 and 2017, while Sentinel-1 data used were images acquired in 2018 and 2020. This study aims to reveal the importance of an upgradable DTM so called latest DTM which is combination of DTM master and its displacement in order to show the latest condition of study area. The case study is the dynamics analyze of the Semangko fault specifically in the Sianok and Sumani segments situated in Indonesia. The vertical accuracy assessment was done to evaluate the DSM to DTM conversion with a tolerance of 1.96σ. The result obtained is the latest DTM. It is derived from the integration of the DTM master with displacement. The latest DTM can be used to detect the dynamics of Semangko fault. The study area has vertical deformation at a value of –50 cm to 30 cm. The Semangko fault area is dominated by –25 to 5 cm deformation. In general, this region has decreased. The decline in this region ranges from 7.5 cm to 10 cm per year. The latest DTM vertical accuracy is 2.158 m (95% confidence level) with a scale of 1: 10,000 to 1: 20,000.
1 October 2019 in The International Archives of the Photogrammetry, Remote Sensing and Spatial Information Sciences
DTM is a digital model that visualizes height topography. DTM can be used for various survey mapping applications. DTM can be derived from DSM. Currently DSM is widely available but the availability of DTM is still rare, especially in Indonesia. In this study, DSM was obtained from a combination of DSM X SAR, SRTM, and TanDEM-X with the integration method. This DSM integration made height error correction and height reference field to the EGM 2008. This DSM integration has fulfilled the tolerance of vertical accuracy in 1.96σ (95%). This study aims to convert DSM to DTM and discuss some of the DTM applications. The study area of this study is Rote Islands (north and east side), especially in the Dead Sea Lake Area which includes Lake Oemasapoka to Oesu Island. DSM can be converted into DTM by considering several things, namely the canopy tilt angle to topography, the height of the vegetation approach, and the radius defined around the canopy. One way to get this parameter is to make contours on the vegetation in the DSM. After conversion of DSM to DTM, DTM is obtained at ground level. The DTM that has been produced needs to be done a height difference test and the making of longitudinal profile. This longitudinal profile will visualize the conditions of DSM and DTM so that the vegetation height will appear along the profile. The resulting DTM can be used for several applications such as topographic contours, watersheds, water levels, flow accumulation, slope, slope direction, and others.
Land subsidence is a phenomenon that occurs in many parts of the world, particularly in coastal plains and river delta areas, including the north coast of Java, commonly known as ‘pantura’. By utilizing satellite time series data, land subsidence along the north coast of Java was detected using The Small Baseline Subset (SBAS) method. Additionally, combining data from different Sentinel-1 orbit directions (ascending-descending) enables the production of a more accurate 2.5D model. This research aims to calculate the rate of land subsidence on the north coast of Java from 2020 to 2023 using the 2.5D model, and to compare the results with CORS processing results. Recent identification of land subsidence highlights that residential areas and rice fields are highly vulnerable to potential subsidence. The 2.5D model in the up-down (UD) direction shows the highest land subsidence occurred in Demak Regency at 146.45 mm/year, Semarang City at 144.34 mm/year, and Pekalongan Regency at 137.94 mm/year. An accuracy assessment was performed using twelve CORS stations, showing RMSE values ranging from millimeters to centimeters: vertical ascending at 16.5 mm, vertical descending at 18.6 mm, UD at 8.8 mm, and East ̶ West (EW) at 26.3 mm.