Changes between Version 8 and Version 9 of project/project/subproj/wps52


Ignore:
Timestamp:
May 5, 2021 11:40:00 AM (17 months ago)
Author:
hettrich
Comment:

--

Legend:

Unmodified
Added
Removed
Modified
  • project/project/subproj/wps52

    v8 v9  
    77=== Project Tasks:
    88||
    9 The work in MOSAIK Phase 1 showed the importance of automated generation of surface input parameters, as well as the provision of open-source data. As not all municipalities have the same data available at the same level of detail, it is useful to have a base layer available that consistently provides a minimum amount of spatial input parameters and which can be supplementary, if necessary, with local parameters. This basic data-set should only consist of open-source data, if possible, to allow their use for everyone, who intends to test PALM-4U. Many open-source data not only exist for Germany, but also for Europe and globally. Therefore, it would allow the transferability of PALM-4U to cities outside of Germany.
    109
    11 Additionally to the need for a basic data-set, the demand for further spatial input parameters, which will be developed in this work package, has been identified during the development of PALM in MOSAIK-1. Therefore, the goal of work package WP-S5.2 is to improve the surface input parameters for PALM-4U in two different ways:
     10'''I) Development of analysis-ready surface data sets'''
     11||
     12The work in MOSAIK Phase 1 showed the importance of an automated generation of surface input parameters, as well as the provisioning of analysis-ready data. As not all municipalities have the same data available at the same level of detail, it was deemed important to provide base-layers that consistently provide a minimum amount of spatial input parameters, which can be supplemented, if necessary, with local parameters. This basic data-set should only consist of freely accessible data, if possible, to allow their use for everyone intending to test PALM-4U. Many open-source data not only exist for Germany, but also for Europe and globally. Therefore, such base-layers allow the transferability of PALM-4U to cities outside of Germany.
     13In addition to deriving and providing the data layers themselves, work is performed to create and document stand-alone data retrieval software, which could then be distributed with PALM-4U allowing input data retrieval and preparation also on the user side.
     14||
     15'''II) Development of methods to integrate new high-resolution input data.'''
     16||
     17In addition to the need for a consistent base-layer data-set, the demand for further spatial input parameters has been identified during the development of PALM in MOSAIK-1. Therefore, the second goal of this work package is to explore new methods of deriving information not readily available in other published data-sets. In particular, we are looking to improve the description of building characteristics from aerial imagery using novel machine learning approaches.
    1218
    13 1) Development of an open-source surface data set(s) from which the input parameters can be derived automatically.
     19||
     20=== Project structure
     21||
     22This project is conducted at the German Aerospace Centre in Oberpfaffenhofen.
    1423
    15 2) Development of methods to integrate new high-resolution input data.
     24PI: Julian Zeidler
     25 
     26Projektmitarbeiter: Dr. Benjamin Leutner
     27||
     28=== Progress so far:
     29||
     30'''Base-layer data retrieval and preparation '''
    1631
    17 
     32Data sets have been curated from open-access data-sources and distributed to the project partners. This includes layers such as vegetation heights, surface materials or elevation (Figure 1).
    1833
    1934{{{
     
    2540'''Figure 1:''' Examples of input parameter (parts of) the study area of Berlin, Germany, for PALM-4U. Created by DLR. Data sources: FIS Broker Berlin (LiDAR, CIR imagery, CityGML),  Open Street Map (OSM) and SRTM
    2641
    27 ||
    28 === Project structure
    29 ||
    30 This project is conducted at the German Aerospace Centre in Oberpfaffenhofen.
     42'''AI based building information extraction from aerial imagery.'''
    3143
    32 PI: Dr. Wieke Heldens
    33 ||
    34 === Deliverables:
    35 ||
    36 ||
    37 === Progress so far:
    38 ||
     44Recent developments in the realm of artificial intelligence allow for increasingly detailed information retrieval from very high-resolution imagery. In this task we explore the potential of oblique aerial imagery to retrieve detailed building façade information.
     45To this end, we implemented and trained a deep-learning based classifier, which performs instance segmentation on two-dimensional images. In particular it maps facade window area, an important component of building heat exchange, based on texture images from a 3D city model of Berlin (LOD2 CityGML).  Training data, sourced from publicly available data-sets, were used in a first iteration to train a Mask-RCNN model. In a second, transfer-learning step the model was fine-tuned to manually labelled 2d images extracted from the LOD2 data. This final model was the validated and used to annotate all unlabeled textures from the LOD2 data, hence creating a map of façade window fractions.
     46
     47{{{
     48#!div style="align:center; width: 800px; border: 0px solid"
     49[[Image(WP-S52-figure2.png,nolink,800px,center)]]
     50}}}
     51
     52
     53'''Figure 2:''' Model-based extraction of façade window area from oblique aerial imagery (provided in CityGML LOD2 format) by means of an instance segmentation algorithm.
     54
    3955||
    4056=== References
     
    4864=== Contact:
    4965||
    50 Dr. Wieke Heldens
     66Julian Zeidler
    5167
    52 Wieke.Heldens[at]dlr.de
     68Julian.Zeidler[at]dlr.de
    5369
    5470Deutsches Zentrum für Luft u. Raumfahrt e.V. (DLR)
                                                                                                                                                                                                                                                                                                                                                                               
  | Impressum | ©Leibniz Universität Hannover |