Journal: PFG – Journal of Photogrammetry, Remote Sensing and Geoinformation Science

Abbreviation

PFG

Publisher

Springer

Journal Volumes

ISSN

2512-2819
2512-2789

Description

Filters

2022 - 20233
Reset filters

Search Results

Publications 1 - 3 of 3
  • Urban Change Forecasting from Satellite Images
    Item type: Journal Article
    Metzger, Nando; Türkoglu, Mehmet Özgür; Caye Daudt, Rodrigo; et al. (2023)
    PFG – Journal of Photogrammetry, Remote Sensing and Geoinformation Science
    Forecasting where and when new buildings will emerge is a rather unexplored topic, but one that is very useful in many disciplines such as urban planning, agriculture, resource management, and even autonomous flying. In the present work, we present a method that accomplishes this task with a deep neural network and a custom pretraining procedure. In Stage 1, a U-Net backbone is pretrained within a Siamese network architecture that aims to solve a (building) change detection task. In Stage 2, the backbone is repurposed to forecast the emergence of new buildings based solely on one image acquired before its construction. Furthermore, we also present a model that forecasts the time range within which the change will occur. We validate our approach using the SpaceNet7 dataset, which covers an area of 960 km² at 24 points in time across 2 years. In our experiments, we found that our proposed pretraining method consistently outperforms the traditional pretraining using the ImageNet dataset. We also show that it is to some degree possible to predict in advance when building changes will occur.
  • Geometric Feedback System for Robotic Spraying
    Item type: Journal Article
    Frangez, Valens; Taha, Nizar; Feihl, Nicolas; et al. (2022)
    PFG – Journal of Photogrammetry, Remote Sensing and Geoinformation Science
    In this paper, we tackle the task of replacing labor intensive and repetitive manual inspection of sprayed concrete elements with a sensor-based and automated alternative. We present a geometric feedback system that is integrated within a robotic setup and includes a set of depth cameras used for acquiring data on sprayed concrete structures, during and after fabrication. The acquired data are analyzed in terms of thickness and surface quality, with both sets of information then used within the adaptive fabrication process. The thickness evaluation is based on the comparison of the as-built state to a previous as-built state or to the design model. The surface quality evaluation is based on the local analysis of 3D geometric and intensity features. These features are used by a random forest classifier trained using data manually labelled by a skilled professional. With this approach, we are able to achieve a prediction accuracy of 87 % or better when distinguishing different surface quality types on flat specimens, and 75 % when applied in a full production setting with wet and non-planar surfaces. The presented approach is a contribution towards in-line material thickness and surface quality inspection within digital fabrication.
  • Recent Ice Trends in Swiss Mountain Lakes: 20-year Analysis of MODIS Imagery
    Item type: Journal Article
    Tom, Manu; Wu, Tianyu; Baltsavias, Emmanuel; et al. (2022)
    PFG – Journal of Photogrammetry, Remote Sensing and Geoinformation Science
    Depleting lake ice is a climate change indicator, just like sea-level rise or glacial retreat. Monitoring Lake Ice Phenology (LIP) is useful because long-term freezing and thawing patterns serve as sentinels to understand regional and global climate change. We report a study for the Oberengadin region of Switzerland, where several small- and medium-sized mountain lakes are located. We observe the LIP events, such as freeze-up, break-up and ice cover duration, across two decades (2000-2020) from optical satellite images. We analyse the time series of MODIS imagery by estimating spatially resolved maps of lake ice for these Alpine lakes with supervised machine learning. To train the classifier we rely on reference data annotated manually based on webcam images. From the ice maps, we derive long-term LIP trends. Since the webcam data are only available for two winters, we cross-check our results against the operational MODIS and VIIRS snow products. We find a change in complete freeze duration of - 0.76 and - 0.89 days per annum for lakes Sils and Silvaplana, respectively. Furthermore, we observe plausible correlations of the LIP trends with climate data measured at nearby meteorological stations. We notice that mean winter air temperature has a negative correlation with the freeze duration and break-up events and a positive correlation with the freeze-up events. Additionally, we observe a strong negative correlation of sunshine during the winter months with the freeze duration and break-up events.
Publications 1 - 3 of 3