Abstract

In this paper we present a practical approach for generating an occlusion-free textured 3D map of urban facades by the synergistic use of terrestrial images, 3D point clouds and area-based information. Particularly in dense urban environments, the high presence of urban objects in front of the facades causes significant difficulties for several stages in computational building modeling. Major challenges lie on the one hand in extracting complete 3D facade quadrilateral delimitations and on the other hand in generating occlusion-free facade textures. For these reasons, we describe a straightforward approach for completing and recovering facade geometry and textures by exploiting the data complementarity of terrestrial multi-source imagery and area-based information.

Highlights

  • Nowadays, developments of Mobile Mapping Systems equipped with direct georeferencing devices are revolutionising the mapping world (e.g., [1, 2])

  • These 3D building models are usually textured at roof level by using aerial images and sometimes textured at facade level by exploiting oblique aerial images (e.g., [4])

  • For solving part of these problems that are common in dense urban environments, we propose a synergistic approach in which heterogeneous cartographic data greatly take advantage of each-others strengths for generating accurate 3D facade quadrilaterals (e.g., [1]) as well as occlusion-free facade textures that correctly match at this level of representation

Read more

Summary

Introduction

Developments of Mobile Mapping Systems equipped with direct georeferencing devices are revolutionising the mapping world (e.g., [1, 2]). Resulting terrestrial-based facade textures can be non-representative of true facades (e.g., partial representation of facade walls or representation of external objects such as roof portions) due to ill-fitting aerial-based delimitations These problems strongly appear in textured building models that are semi-manually generated by designers or architects (high consumers of building models) and where demonstrative virtual platforms are created for presenting urban planning projects. A critical and widespread problem of these urban facade textures lies in the presence of strong occlusions caused by the urban street objects (unpredictable occlusions) In many cases, this problem is not addressed and acquired frontal facade images are directly mapped onto the generated or created models in spite of the presence of wide visible occlusions (e.g., [5]). This results in a positioning system that is only based on images (e.g., [10])

Operating Mobile Mapping System
Primary Street Point Cloud Segmentation
Map-based Segmentation into Vertical and Surface Clusters
Focusing on Facade Regions by Exploiting Existing Digital Cadastral Maps
Extracting Disjoint Facade Clusters by Fusing Amap and
Delimiting Vertices of Facade Quadrilateral in Planimetry and Altimetry
Recovering Quasi-real Occlusion-free Facade Textures
Detecting Occluding Objects of Urban Facades
Generating Masks Hiding the Occluding Objects
Enhancing rendering of reconstructed textures
Conclusion and Future Works
Full Text
Paper version not known

Talk to us

Join us for a 30 min session where you can share your feedback and ask us any queries you have

Schedule a call

Disclaimer: All third-party content on this website/platform is and will remain the property of their respective owners and is provided on "as is" basis without any warranties, express or implied. Use of third-party content does not indicate any affiliation, sponsorship with or endorsement by them. Any references to third-party content is to identify the corresponding services and shall be considered fair use under The CopyrightLaw.