Deep learning-based extraction of building contours for large-scale 3D urban reconstruction

Tripodi, Sébastien; Duan, Liuyun; Trastour, Frederic; Poujade, V.; Laurore, L.; Tarabalka, Yuliya

doi:10.1117/12.2533149

Cited by 4 publications

(5 citation statements)

References 9 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…AI-based procedures were recently used to infer buildings' features and characteristics. Machine and deep learning methods were increasingly employed for predicting 3D urban geometries and semantics [29][30][31][32], for energy performances [33][34][35], for models generalisation [36], or to infer some missing information, such as buildings' age [37][38][39][40] and height [28,[41][42][43][44]. Prediction algorithms are generally trained using satellite or aerial images [43,44], LiDAR data [37,42], or 2D data (such as photographs, maps, footprints, and attributes) available from historical archives, cadastre datasets, or volunteered geographic information databases [28,38,39,45].…”

Section: Related Workmentioning

confidence: 99%

4D Building Reconstruction with Machine Learning and Historical Maps

2021

View full text Add to dashboard Cite

The increasing importance of three-dimensional (3D) city modelling is linked to these data’s different applications and advantages in many domains. Images and Light Detection and Ranging (LiDAR) data availability are now an evident and unavoidable prerequisite, not always verified for past scenarios. Indeed, historical maps are often the only source of information when dealing with historical scenarios or multi-temporal (4D) digital representations. The paper presents a methodology to derive 4D building models in the level of detail 1 (LoD1), inferring missing height information through machine learning techniques. The aim is to realise 4D LoD1 buildings for geospatial analyses and visualisation, valorising historical data, and urban studies. Several machine learning regression techniques are analysed and employed for deriving missing height data from digitised multi-temporal maps. The implemented method relies on geometric, neighbours, and categorical attributes for height prediction. Derived elevation data are then used for 4D building reconstructions, offering multi-temporal versions of the considered urban scenarios. Various evaluation metrics are also presented for tackling the common issue of lack of ground-truth information within historical data.

show abstract

Section: Related Workmentioning

confidence: 99%

4D Building Reconstruction with Machine Learning and Historical Maps

2021

View full text Add to dashboard Cite

show abstract

“…For this task, we have adopted a U-net convolutional neural network architecture, which has exhibited the highest performance in several benchmarks involving building rooftop labeling [10,4]. A detailed description of the designed model and the Luxcarta database used for its training in given in [11]. We have shown in [11] that a careful design of the model together with an appropriate loss function (we have used a combination of cross-entropy and intersection over union losses) allows to train a generic model, which performs well on different types of urban areas, such as residential, industrial and very dense areas.…”

Section: Rooftop Extractionmentioning

confidence: 99%

“…We have designed a solution to polygonize building contours, which performs a naive polygonization of the mask of every building, followed by a polygon simplification, which searches for a compressed polygon with the best quality/complexity ratio, i.e. with the minimum number of vertices within a specified tolerance of an error [11].…”

Section: Rooftop Extractionmentioning

confidence: 99%

“…The proposed chain has been applied on a stereo pair of Pléiades satellite images at 50 cm spatial resolution over Marseille, France, with a theoretical elevation precision of 3.06 m. This precision is computed from the satellite azimuth and elevation for each image of the stereo pair. In our previous work [11], we have reported the accuracy of our rooftop extraction algorithm, yielding the mean intersection over union of 0.77, with 93% of detected buildings. Here we evaluate our chain by comparing the estimated footprint positions with the ground-truth footprints: 88146 building footprint contours have been manually drawn.…”

Section: Experiments and Conclusionmentioning

confidence: 99%

See 1 more Smart Citation

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

Tripodi¹,

Duan²,

Poujade³

et al. 2020

IGARSS 2020 - 2020 IEEE International Geoscience and Remote Sensing Symposium

Self Cite

View full text Add to dashboard Cite

Automatic 3D reconstruction of urban scenes from stereo pairs of satellite images remains a popular yet challenging research topic, driven by numerous applications such as telecommunications and defense. The quality of reconstruction results depends particularly on the quality of the available stereo pair. In this paper, we propose an operational pipeline for large-scale 3D reconstruction of buildings from stereo satellite images. The proposed chain uses U-net to extract contour polygons of buildings, and the combination of optimization and computational geometry techniques to reconstruct a digital terrain model and a digital height model, and to correctly estimate the position of building footprints. The pipeline has proven to be efficient for 3D building reconstruction, even if the close-to-nadir image is not available.

show abstract

“…3D outdoor scene reconstruction, a process that entails the reconstruction of the three-dimensional geometric structure of a scene based on one or more 2D images, has the capability to accurately capture the intricate details and textures of the 3D environment [1] . In recent years, the demand for 3D data has surged in various domains, including urban digital modeling [2,3] , the creation of immersive virtual reality environments within the metaverse [4] , and addressing public safety concerns in smart cities [5] . This increasing, demand has fueled extensive research and development efforts in the field of outdoor 3D scene reconstruction.…”

Section: Introductionmentioning

confidence: 99%

Global Soft Pooling Adaptive Attention Network for Single Aerial Image-Based 3D Outdoor Scene Reconstruction

Wang,

Li,

Yan

2023

Preprint

View full text Add to dashboard Cite

In the realm of outdoor scene 3D reconstruction from a solitary RGB aerial image, a persistent challenge pertains to the issue of inadequate reconstruction accuracy. In this article, we introduce a novel approach, namely, the Global Soft Pooling Adaptive Attention Network, designed to facilitate high-precision 3D scene reconstruction in outdoor environments. This network primarily comprises two distinct attention network modules: the Global Soft Pooling Dynamic Convolutional Attention and the Three-Head Adaptive Graph Attention. The Global Soft Pooling Attention Network employs a stem_conv and four MBdyconv components for the extraction of multi-scale image features. It harnesses global soft pooling techniques, integrating both channels fusion and spatial attention mechanisms, thereby enabling the precise acquisition of composite features. These features are subsequently assigned to initialize mesh vertices. The Three-Head Adaptive Graph Attention Network leverages three sets of adaptive 1D convolutions to derive 3D vertex features, taking into account the weights of neighboring vertices. A linear layer is employed to compute the vertex coordinate offsets (denoted as "ΔV"), which are then utilized to refine the initial mesh vertices, ultimately achieving an enhanced mesh model. When evaluated on the publicly available SensatUrban dataset, our proposed method demonstrates impressive performance metrics, achieving a reconstruction performance index of 0.96 for l2 and 1.68 for l3. Experimental results unequivocally demonstrate that our approach outperforms existing deep learning methodologies, establishing itself as the state-of-the-art solution for outdoor 3D scene reconstruction.

show abstract

Deep learning-based extraction of building contours for large-scale 3D urban reconstruction

Cited by 4 publications

References 9 publications

4D Building Reconstruction with Machine Learning and Historical Maps

4D Building Reconstruction with Machine Learning and Historical Maps

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

Global Soft Pooling Adaptive Attention Network for Single Aerial Image-Based 3D Outdoor Scene Reconstruction

Contact Info

Product

Resources

About