UrMo Digital - Traffic Area Map (TAM) - Brunswick, Germany

This inventory of traffic areas in the city of Brunswick, Germany, is based on image sequences acquired during six flight campaigns at different times of the day and year in 2019 and 2020. Each aerial image is segmented by a neural network into the classes (1) Parking area, (2) Road, and (3) Access way, with the latter two classes differing in terms of their primary transportation function (mobility versus access). The individual segmentations are subsequently merged, since in addition to dedicated parking areas, those traffic areas that are regularly used for parking a motorized vehicle (e.g., at the curbside) are also to be classified as such. Furthermore, the multitemporal fusion enhances the robustness and completeness of the traffic area map (TAM). Potential applications include: urban planning, traffic modeling, and parking management.

For more information about the project, the reader is referred to: https://elib.dlr.de/191145/1/Hellekes_et_al_2022_Parking_space_inventory_from_above.pdf

Date (Creation): 2022-08-01T00:00:00

Citation identifier: https://geoservice.dlr.de/catalogue/srv/metadata/d47a2d18-8443-4428-837f-b079d171a7e7

Presentation form: Digital map

Purpose: To provide an inventory of traffic areas in the city of Brunswick, Germany. The resulting map serves applications like urban planning, transport modeling, and traffic management.

Status: Completed

Point of contact

German Aerospace Center (DLR)

Distributor

German Aerospace Center (DLR) - ( )

Author

German Aerospace Center (DLR) - Jens Hellekes

Maintenance and update frequency: Not planned

Keywords

DLR
EOC
Aerial Imagery
Image Segmentation
Traffic Area Map
Parking Space Detection
Multitemporal Fusion
Brunswick
Germany

GEMET - INSPIRE themes, version 1.0

Transport networks

Spatial scope

local

Use limitation: Nutzungseinschränkungen: Das DLR ist nicht haftbar für Schäden, die sich aus der Nutzung ergeben. / Use Limitations: DLR not liable for damage resulting from use.

Access constraints: Other restrictions

Other constraints: Es gelten keine Zugriffsbeschränkungen

Use constraints: Other restrictions

Other constraints: Nutzungsbedingungen: Lizenz, https://creativecommons.org/licenses/by-nc/4.0 / Terms of use: License, https://creativecommons.org/licenses/by-nc/4.0

Other constraints: {"id": "cc-by-nc-4.0",

"name": "Creative Commons Namensnennung - Nicht kommerziell 4.0 International (CC BY-NC 4.0)",

"url": " http://dcat-ap.de/def/licenses/cc-by-nc/4.0 ",

"quelle": "Copyright DLR (year of production)"}

Spatial representation type: Grid

Denominator: 200

Language: Deutsch

Character set: UTF8

Topic category

Transportation

Begin date: 2019-04-25

End date: 2020-06-24

Unique resource identifier: EPSG:3035

Number of dimensions: 2

Dimension name: Column

Dimension size: 90000

Resolution: 0.1 m

Dimension name: Row

Dimension size: 56000

Resolution: 0.1 m

Cell geometry: Area

Transformation parameter availability: No

Distribution format

Cloud Optimized GeoTIFF ( )

OnLine resource

URMO_TAM_3K_BRUNSWICK ( OGC:WMS )

WMS Access: inventory of traffic areas in the city of Brunswick, Germany

OnLine resource

3K_MOS_BRUNSWICK ( OGC:WMS )

WMS Access: aerial imagery mosaic for the city of Brunswick, Germany

OnLine resource

UrMo Digital - Forschen für die städtische Mobilität der Zukunft ( WWW:LINK-1.0-http--link )

Webpage with links and description for accessing more information about the project

OnLine resource

HTTP download ( WWW:LINK-1.0-http--link )

HTTP download (UrMo Digital)

Hierarchy level: Dataset

Domain consistency

Measure identification: INSPIRE / Conformity_001

Conformance result

Date (Publication): 2010-12-08

Explanation: See the referenced specification

Pass: Yes

Statement: The traffic are map for Brunswick, Germany is based on aerial images acquired with the DLR 3K camera system at varying times of the day and year between 2019 and 2020, covering about 36 km² with a spatial resolution of 0.1 m.

Description: UrMo Digital - Traffic Area Map Processing

Data:

The classification is based on image sequences acquired during six flight campaigns at different times of the day and year in 2019 and 2020. Imagery was acquired with the 3K camera system at 10 cm ground sampling distance

Processing:

Each aerial image is segmented by a neural network, multi-temporal fusion is used to improve robustness and detect curbside parking areas.