Label placement in 3D georeferenced and oriented digital photographs using GIS technology

he increasing availability of digital camera devices and camera phones enable users to capture and upload digital photos at any a time and any place. Online image collections face the problem organizing increasing photo collections. Because users experience adding qualitative photo annotations as a time-consuming and tedious task, they omit to do it. However, good photo annotation is very important for fast and reliable photo retrieval. The integration of positioning devices (e.g. GPS) with digital camera enables to capture position along with the photo and this location metadata has been applied in previous research to automatically caption digital photos. The disadvantage of describing a photo using location metadata only is that it only enables to add information about its surrounding and not about the actual objects pictured. This research carried out in the framework of the EU research project Tripod assumes in the near future camera devices integrated with GPS and digital compass will be available. Using this full spatial metadata, it is possible to exactly identify and localize objects inside the pictured scene. Digital photos with 3D position and view direction are collected on the Market Square in Delft (The Netherlands) using a Topcon imaging total station and Nikon D100 camera mounted with digital 3-axis compass and GPS to carry out a proof-of-concept. Using the output of a perspective viewer service, a tool that renders an three-dimensional model, a virtual abstraction that matches the digital photo is created to be able to identify and localize visible objects in order to place a label next to it. The three-dimensional models applied for this research are created from conventional GIS datasets (e.g. TOP10NL and GBKN) and a digital elevation model (AHN) by extruding the building footprints. The best possible for a label is defined at the empty areas and constraints and rules are added to ESRI ArcGIS label Engine Maplex to carry out the label placement inside the digital photo in a GIS environment. Misidentification and misplacement due to lens distortions, and GPS and compass inaccuracies are evaluated. A demo-application is developed in ESRI ArcGIS using Visual Basic for Applications (VBA) programming and system architecture is proposed for implementation of a photo labelling service. It is concluded that the virtual scenes as output of perspective viewer services are appropriate to apply for object identification and localization. In doing so, the problem of label placement in three-dimensional geographic environments is reduced to a two-dimensional map-labelling problem. The best location of label placement is determined using constraints and rules to be applied to the virtual scene and the reclassified-to-binary image of the input photo, and the depth map enables to vary in label font size depending on the object distance.

Subject

photo annotation
label placement
object identification
extrusion models
geographic information systems

To reference this document use:

http://resolver.tudelft.nl/uuid:b130806f-58be-466c-8890-a1534df3ff00

Publisher

TU Delft, OTB, Geo-Database Management Center

Part of collection

Student theses

Document type

master thesis

Rights

Files

PDF

otb_boer_2007.pdf

9.42 MB

Close viewer