Operational Pipeline for Large-Scale 3D Reconstruction of Buildings From Satellite Images

Tripodi, Sébastien; Duan, Liuyun; Poujade, V.; Trastour, Frederic; Bauchet, Jean-Philippe; Laurore, L.; Tarabalka, Yuliya

doi:10.1109/igarss39084.2020.9324213

Cited by 11 publications

(6 citation statements)

References 10 publications

(16 reference statements)

Supporting

Mentioning

Contrasting

Order By: Relevance

“…7.3.1 Stereo matching using semi-global matching From the input stereo pair of orthoimages, we apply epipolar rectification as described in 7.1, then, we use a modified version of SGM algorithm (Tripodi et al, 2020) to enable solving certain conditions such as large displacements and textureless regions. The used method is a buildup of the original algorithm as it is a 1) Pyramidal approach: since SGM is executed at different scales ([8,4,2,1]) thus removing noise by incorporating disparities at all levels, 2) Usage of the census as a cost function being more robust to radiometric difference, 3) Runtime enhancement as the algorithm is implemented in GPU.…”

Section: Procedural Alignment Through Image Matching Techniquesmentioning

confidence: 99%

“…The first step consists of applying epipolar rectification of the optical images that will be used by the next alignment methods. As the first disparity estimation method, we employ the modified SGM algorithm from (Tripodi et al, 2020) to compute the pixel-wise disparity map. As shown in Figure 9, disparity values are assigned to feature pixels of the reference image, i.e., disparity values are assigned to pixels of buildings' rooftops.…”

Section: Template Matchingmentioning

confidence: 99%

See 1 more Smart Citation

Novel Approaches for Aligning Geospatial Vector Maps

Cherif,

Tripodi,

Tarabalka

et al. 2024

Int. Arch. Photogramm. Remote Sens. Spatial Inf. Sci.

View full text Add to dashboard Cite

Abstract. The surge in data across diverse fields presents an essential need for advanced techniques to merge and interpret this information. With a special emphasis on compiling geospatial data, this integration is crucial for unlocking new insights from geographic data, enhancing our ability to map and analyze trends that span across different locations and environments with more authenticity and reliability. Existing techniques have made progress in addressing data fusion; however, challenges persist in fusing and harmonizing data from different sources, scales, and modalities. This research presents a comprehensive investigation into the challenges and solutions in vector map alignment, focusing on developing methods that enhance the precision and usability of geospatial data. We explored and developed three distinct methodologies for polygonal vector map alignment: ProximityAlign, which excels in precision within urban layouts but faces computational challenges; the Optical Flow Deep Learning-Based Alignment, noted for its efficiency and adaptability; and the Epipolar Geometry-Based Alignment, effective in data-rich contexts but sensitive to data quality. In practice, the proposed approaches serve as tools to benefit from as much as possible from existing datasets while respecting a spatial reference source. It also serves as a paramount step for the data fusion task to reduce its complexity.

show abstract

Section: Procedural Alignment Through Image Matching Techniquesmentioning

confidence: 99%

Section: Template Matchingmentioning

confidence: 99%

Novel Approaches for Aligning Geospatial Vector Maps

Cherif,

Tripodi,

Tarabalka

et al. 2024

Int. Arch. Photogramm. Remote Sens. Spatial Inf. Sci.

View full text Add to dashboard Cite

show abstract

“…Regarding the process of 3D building reconstruction based on VHR satellite images, the state of the art has quite a few scientific papers. The potential of stereo and tri-stereo Pléiades satellite images was tested in the last decade for obtaining DEMs [13][14][15][16][17][18][19], DSMs [5,13,[20][21][22][23] or automatic building extraction at LOD1 or LOD2 [24][25][26]. In [24], the buildings are reconstructed in 3D at LOD1, the building footprints and the rooftop polygons are automatically extracted, and the height information of every building is obtained by subtracting the DTM from the DSM and retaining the median or the majority values.…”

Section: Related Workmentioning

confidence: 99%

“…The potential of stereo and tri-stereo Pléiades satellite images was tested in the last decade for obtaining DEMs [13][14][15][16][17][18][19], DSMs [5,13,[20][21][22][23] or automatic building extraction at LOD1 or LOD2 [24][25][26]. In [24], the buildings are reconstructed in 3D at LOD1, the building footprints and the rooftop polygons are automatically extracted, and the height information of every building is obtained by subtracting the DTM from the DSM and retaining the median or the majority values. However, the quantitative evaluation of the DSM or the building heights was not performed using other data sources, such as an ALS point cloud.…”

Section: Related Workmentioning

confidence: 99%

Proposed Methodology for Accuracy Improvement of LOD1 3D Building Models Created Based on Stereo Pléiades Satellite Imagery

Breaban

Oniga²,

Chirila³

et al. 2022

Remote Sensing

View full text Add to dashboard Cite

Three-dimensional city models play an important role for a large number of applications in urban environments, and thus it is of high interest to create them automatically, accurately and in a cost-effective manner. This paper presents a new methodology for point cloud accuracy improvement to generate terrain topographic models and 3D building modeling with the Open Geospatial Consortium (OGC) CityGML standard, level of detail 1 (LOD1), using very high-resolution (VHR) satellite images. In that context, a number of steps are given attention (which are often (in the literature) not considered in detail), including the local geoid and the role of the digital terrain model (DTM) in the dense image matching process. The quality of the resulting models is analyzed thoroughly. For this objective, two stereo Pléiades 1 satellite images over Iasi city were acquired in September 2016, and 142 points were measured in situ by global navigation satellite system real-time kinematic positioning (GNSS-RTK) technology. First, the quasigeoid surface resulting from EGG2008 regional gravimetric model was corrected based on data from GNSS and leveling measurements using a four-parameter transformation, and the ellipsoidal heights of the 142 GNSS-RTK points were corrected based on the local quasigeoid surface. The DTM of the study area was created based on low-resolution airborne laser scanner (LR ALS) point clouds that have been filtered using the robust filter algorithm and a mask for buildings, and the ellipsoidal heights were also corrected with the local quasigeoid surface, resulting in a standard deviation of 37.3 cm for 50 levelling points and 28.1 cm for the 142 GNSS-RTK points. For the point cloud generation, two scenarios were considered: (1) no DTM and ground control points (GCPs) with uncorrected ellipsoidal heights resulting in an RMS difference (Z) for the 64 GCPs and 78 ChPs of 69.8 cm and (2) with LR ALS-DTM and GCPs with corrected ellipsoidal height values resulting in an RMS difference (Z) of 60.9 cm. The LOD1 models of 1550 buildings from the Iasi city center were created based on Pléiades-DSM point clouds (corrected and not corrected) and existing building sub-footprints, with four methods for the derivation of the building roof elevations, resulting in a standard deviation of 1.6 m against high-resolution (HR) ALS point cloud in the case of the best scenario. The proposed method for height extraction and reconstruction of the city structure performed the best compared with other studies on multiple satellite stereo imagery.

show abstract

“…Combining these two data sources enables the automated BIM reconstruction of buildings. This process eliminates the need for costly ground surveys or direct physical contact, significantly improving the efficiency of data collection and reducing acquisition costs [6].…”

Section: Introductionmentioning

confidence: 99%

Deep-Learning-Based Automated Building Information Modeling Reconstruction Using Orthophotos with Digital Surface Models

Wang,

Jiang,

Liu

2024

Buildings

View full text Add to dashboard Cite

In the field of building information modeling (BIM), converting existing buildings into BIM by using orthophotos with digital surface models (DSMs) is a critical technical challenge. Currently, the BIM reconstruction process is hampered by the inadequate accuracy of building boundary extraction when carried out using existing technology, leading to insufficient correctness in the final BIM reconstruction. To address this issue, this study proposes a novel deep-learning- and postprocessing-based approach to automating reconstruction in BIM by using orthophotos with DSMs. This approach aims to improve the efficiency and correctness of the reconstruction of existing buildings in BIM. The experimental results in the publicly available Tianjin and Urban 3D reconstruction datasets showed that this method was able to extract accurate and regularized building boundaries, and the correctness of the reconstructed BIM was 85.61% and 82.93%, respectively. This study improved the technique of extracting regularized building boundaries from orthophotos and DSMs and achieved significant results in enhancing the correctness of BIM reconstruction. These improvements are helpful for the reconstruction of existing buildings in BIM, and this study provides a solid foundation for future improvements to the algorithm.

show abstract

Operational Pipeline for Large-Scale 3D Reconstruction of Buildings From Satellite Images

Cited by 11 publications

References 10 publications

Novel Approaches for Aligning Geospatial Vector Maps

Novel Approaches for Aligning Geospatial Vector Maps

Proposed Methodology for Accuracy Improvement of LOD1 3D Building Models Created Based on Stereo Pléiades Satellite Imagery

Deep-Learning-Based Automated Building Information Modeling Reconstruction Using Orthophotos with Digital Surface Models

Contact Info

Product

Resources

About