Fusing Georeferenced and Stereoscopic Image Data for 3D Building Façade Reconstruction

Bacharidis, Konstantinos; Sarri, Froso; Paravolidakis, V.; Ragia, Lemonia; Zervakis, Michalis

doi:10.3390/ijgi7040151

Cited by 8 publications

(14 citation statements)

References 32 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The present work is considered to be an extension to our previous work, with the goal of refining and strengthening the framework design. We begin with an overview of the overall approach introduced in [20], presenting its advantages, limitations and highlighting the parts of the methodology that the present work aims to improve. The contributions of the present paper lie in eliminating the limitations of our previous approach.…”

Section: Proposed Methodsmentioning

confidence: 99%

3D Building Façade Reconstruction Using Deep Learning

Bacharidis

Sarri

Ragia

2020

IJGI

Self Cite

View full text Add to dashboard Cite

In recent years, advances in computer hardware, graphics rendering algorithms and computer vision have enabled the utilization of 3D building reconstructions in the fields of archeological structure restoration and urban planning. This paper deals with the reconstruction of realistic 3D models of buildings façades, in the urban environment for cultural heritage. The proposed approach is an extension of our previous work in this research topic, which introduced a methodology for accurate 3D realistic façade reconstruction by defining and exploiting a relation between stereoscopic image and tacheometry data. In this work, we re-purpose well known deep neural network architectures in the fields of image segmentation and single image depth prediction, for the tasks of façade structural element detection, depth point-cloud generation and protrusion estimation, with the goal of alleviating drawbacks in our previous design, resulting in a more light-weight, robust, flexible and cost-effective design.

show abstract

Section: Proposed Methodsmentioning

confidence: 99%

3D Building Façade Reconstruction Using Deep Learning

Bacharidis

Sarri

Ragia

2020

IJGI

Self Cite

View full text Add to dashboard Cite

show abstract

“…The structures have been documented combining oblique and zenithal images manually acquired according to a non-stereoscopic scheme [12], approximately 5 m off the evidence.…”

Section: Architectural Survey: Wall Elevationsmentioning

confidence: 99%

Combined Methodologies for the Survey and Documentation of Historical Buildings: The Castle of Scalea (CS, Italy)

Donato

Giuffrida

2019

Heritage

View full text Add to dashboard Cite

In the last few years, new technologies have become indispensable tools for specialists in the field of cultural heritage for the analysis, reconstruction and interpretation of data but also for promotion of artefacts or buildings sometimes inaccessible or in a bad state of conservation. The discipline of geomatics offer many opportunities and solutions for integrated digital surveys and the documentation of heritage (point-based methods, image-based photogrammetry and their combination): These data can be processed in order to derive metric information and share them using databases or GIS (geographic information system) tools. This paper is focused on the description of combined survey methodologies adopted for the geometric and architectural documentation of the site and surviving structures of the Castel of Scalea (Cosenza, Italy). It is a typical context where traditional survey procedures do not fully succeed or require a longer amount of time and great effort if a high level of accuracy is requested: For this reason, aerial close-range digital photogrammetry enhanced by the GNSS (global navigation satellite system), and total station positioning systems have been used at various levels of detail for the production of a detailed 3D model and 2D thematic maps with an excellent level of in the positioning of the structures and in the architectural drawing. Thanks to the collected dataset, it was possible to better identify the building units (CF), to digitize the limits of the masonry stratigraphic units (USM), and to draw up a first constructive diachronic sequence hypothesis on which to base chronology. Moreover, some particular masonry techniques have been sampled and compared at the regional level with the aim to better dating of constructive expedients. It was finally demonstrated how the use of integrated methodologies allows us to obtain a complete and detailed documentation including information regarding not only architectural and geometrical features but also archaeological and historical elements, building materials and decay evidences—all useful as support of the interpretation of data.

show abstract

“…Emerging sophisticated tools allow either partial or complete automation of the modelling process, so it is possible to obtain a 3D reconstructions based on satellite data [ 9 ], stereoscopic images [ 10 ], or light detection and ranging (LiDAR) data [ 11 , 12 , 13 , 14 ]. Photogrammetric reconstruction is also widely used (e.g., [ 2 , 15 , 16 , 17 , 18 ]).…”

Section: Introductionmentioning

confidence: 99%

Accuracy Verification of Surface Models of Architectural Objects from the iPad LiDAR in the Context of Photogrammetry Methods

Łabędź

Skabek

Ozimek

et al. 2022

Sensors

View full text Add to dashboard Cite

The creation of accurate three-dimensional models has been radically simplified in recent years by developing photogrammetric methods. However, the photogrammetric procedure requires complex data processing and does not provide an immediate 3D model, so its use during field (in situ) surveys is infeasible. This paper presents the mapping of fragments of built structures at different scales (finest detail, garden sculpture, architectural interior, building facade) by using a LiDAR sensor from the Apple iPad Pro mobile device. The resulting iPad LiDAR and photogrammetric models were compared with reference models derived from laser scanning and point measurements. For small objects with complex geometries acquired by iPad LiDAR, up to 50% of points were unaligned with the reference models, which is much more than for photogrammetric models. This was primarily due to much less frequent sampling and, consequently, a sparser grid. This simplification of object surfaces is highly beneficial in the case of walls and building facades as it smooths out their surfaces. The application potential of the IPad LiDAR Pro is severely constrained by its range cap being 5 m, which greatly limits the size of objects that can be recorded, and excludes most buildings.

show abstract

Fusing Georeferenced and Stereoscopic Image Data for 3D Building Façade Reconstruction

Cited by 8 publications

References 32 publications

3D Building Façade Reconstruction Using Deep Learning

3D Building Façade Reconstruction Using Deep Learning

Combined Methodologies for the Survey and Documentation of Historical Buildings: The Castle of Scalea (CS, Italy)

Accuracy Verification of Surface Models of Architectural Objects from the iPad LiDAR in the Context of Photogrammetry Methods

Contact Info

Product

Resources

About