3D City Reconstruction: A Novel Method for Semantic Segmentation and Building Monomer Construction Using Oblique Photography

Xu, Wenqiang; Zeng, Yongnian; Yin, Changlin

doi:10.3390/app13158795

Cited by 6 publications

(3 citation statements)

References 32 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…3D surface models are models (e.g., oblique aerial photography models) that depict external contours through topological grids. 28 3D surface models lack component information, making it challenging to directly ascertain exterior non-structural components. Therefore, this study proposes an algorithm for constructing exterior non-structural component models based on grid of building model.…”

Section: Voxelization Algorithmmentioning

confidence: 99%

An integrated simulation method for large‐scale earthquake‐induced falling debris in building groups

Xu,

Zhu,

et al. 2024

Earthq Engng Struct Dyn

View full text Add to dashboard Cite

When building groups are subjected to earthquakes, the potential hazard of exterior falling debris poses a significant risk of causing severe injuries and fatalities. In this study, an integrated simulation method of the large‐scale earthquake‐induced exterior falling debris for building groups is proposed, which includes modeling, calculation, and visualization. Firstly, a modeling algorithm is established for falling debris models of building groups. This algorithm employs the Octree algorithm to support the transformation of the three‐dimensional (3D) building surface model into falling debris models. Subsequently, the generated falling debris models are aggregated using a density clustering algorithm, and their motion is efficiently calculated based on the physics engine and time history analysis. Finally, a cooperative visualization algorithm is developed to effectively present a 3D scene that incorporates both structural displacement and the motion of falling debris in building groups. The actual distribution of exterior falling debris during the earthquake in Turkey validates the proposed simulation method, which is then integrally applied to the Beijing central business district. This integrated simulation method has the capability to provide a large‐scale 3D scene of falling debris for the virtual safety drills of earthquake evacuation and rescue within urban building groups.

show abstract

Section: Voxelization Algorithmmentioning

confidence: 99%

An integrated simulation method for large‐scale earthquake‐induced falling debris in building groups

Xu,

Zhu,

et al. 2024

Earthq Engng Struct Dyn

View full text Add to dashboard Cite

show abstract

“…Performing semantic reconstruction concurrently with 3D reconstruction could leverage prior knowledge (such as walls being smooth planes that are perpendicular to the ground) to enhance reconstruction accuracy [23]. The incorporation of semantic information can enhance the accuracy of mesh reconstruction in individual models [24].…”

Section: Introductionmentioning

confidence: 99%

A Semantically Aware Multi-View 3D Reconstruction Method for Urban Applications

Wei,

Pei,

et al. 2024

Applied Sciences

View full text Add to dashboard Cite

The task of 3D reconstruction of urban targets holds pivotal importance for various applications, including autonomous driving, digital twin technology, and urban planning and development. The intricate nature of urban landscapes presents substantial challenges in attaining 3D reconstructions with high precision. In this paper, we propose a semantically aware multi-view 3D reconstruction method for urban applications which incorporates semantic information into the technical 3D reconstruction. Our research primarily focuses on two major components: sparse reconstruction and dense reconstruction. For the sparse reconstruction process, we present a semantic consistency-based error filtering approach for feature matching. To address the challenge of errors introduced by the presence of numerous dynamic objects in an urban scene, which affects the Structure-from-Motion (SfM) process, we propose a computation strategy based on dynamic–static separation to effectively eliminate mismatches. For the dense reconstruction process, we present a semantic-based Semi-Global Matching (sSGM) method. This method leverages semantic consistency to assess depth continuity, thereby enhancing the cost function during depth estimation. The improved sSGM method not only significantly enhances the accuracy of reconstructing the edges of the targets but also yields a dense point cloud containing semantic information. Through validation using architectural datasets, the proposed method was found to increase the reconstruction accuracy by 32.79% compared to the original SGM, and by 63.06% compared to the PatchMatch method. Therefore, the proposed reconstruction method holds significant potential in urban applications.

show abstract

“…Thus, the basic GIS capabilities, such as query attributes, topical expressions, and spatial queries, are challenging to operate on oblique photographic modeling data. Resolving the problem of building monomer construction using oblique photography has become a hurdle for oblique photographic modeling data used in 3D GIS applications [17]. The traditional method to select a singular building from oblique photography is to separate individual objects by a cutting algorithm [18].…”

Section: Introductionmentioning

confidence: 99%

A Single Data Extraction Algorithm for Oblique Photographic Data Based on the U-Net

Wang,

Li,

Lin

et al. 2024

Remote Sensing

View full text Add to dashboard Cite

In the automated modeling generated by oblique photography, various terrains cannot be physically distinguished individually within the triangulated irregular network (TIN). To utilize the data representing individual features, such as a single building, a process of building monomer construction is required to identify and extract these distinct parts. This approach aids subsequent analyses by focusing on specific entities, mitigating interference from complex scenes. A deep convolutional neural network is constructed, combining U-Net and ResNeXt architectures. The network takes as input both digital orthophoto map (DOM) and oblique photography data, effectively extracting the polygonal footprints of buildings. Extraction accuracy among different algorithms is compared, with results indicating that the ResNeXt-based network achieves the highest intersection over union (IOU) for building segmentation, reaching 0.8255. The proposed “dynamic virtual monomer” technique binds the extracted vector footprints dynamically to the original oblique photography surface through rendering. This enables the selective representation and querying of individual buildings. Empirical evidence demonstrates the effectiveness of this technique in interactive queries and spatial analysis. The high level of automation and excellent accuracy of this method can further advance the application of oblique photography data in 3D urban modeling and geographic information system (GIS) analysis.

show abstract

3D City Reconstruction: A Novel Method for Semantic Segmentation and Building Monomer Construction Using Oblique Photography

Cited by 6 publications

References 32 publications

An integrated simulation method for large‐scale earthquake‐induced falling debris in building groups

An integrated simulation method for large‐scale earthquake‐induced falling debris in building groups

A Semantically Aware Multi-View 3D Reconstruction Method for Urban Applications

A Single Data Extraction Algorithm for Oblique Photographic Data Based on the U-Net

Contact Info

Product

Resources

About