Geometric Object Based Building Reconstruction From Satellite Imagery Derived Point Clouds

Li, Z.; Xu, Bo; Shan, Jie

doi:10.5194/isprs-archives-xlii-2-w13-73-2019

Cited by 5 publications

(5 citation statements)

References 14 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Some research has been carried out on building footprint regularization. Most relevant to this paper are two works: The first one is that of Li et al (2019), which inspired us to utilizing the primary orientation angle together with their simple yet effective rectilinearization algorithm. However, the way they compute the primary orientation angle is not robust.…”

Section: Related Workmentioning

confidence: 99%

“…This allows to obtain regular polygons, even in complex cases. However, frame field learning does not guarantee rectilinearity, as Li et al (2019) does.…”

Section: Related Workmentioning

confidence: 99%

“…The baseline method is that of Li et al (2019). The main difference to our approach is that the baseline uses a learning free procedure to obtain the primary orientation angle.…”

Section: Baselinementioning

confidence: 99%

See 2 more Smart Citations

Rectilinear Building Footprint Regularization Using Deep Learning

Schuegraf,

Li,

Tian

et al. 2024

ISPRS Ann. Photogramm. Remote Sens. Spatial Inf. Sci.

View full text Add to dashboard Cite

Abstract. Nowadays, deep learning allows to automatically learn features from data. Buildings are one of the most important objects in urban environments. They are used in applications such as inputs to building reconstruction, disaster monitoring, city planing and environment modelling for autonomous driving. However, it is not enough to represent them in raster format, since applications require buildings as polygons. We use an existing, learning based approach to extract building footprints from ortho imagery and digital surface model (DSM) and propose a pipeline for building polygon extraction, which we call primary orientation learning (POL). The first step is to extract initial polygons, that contain a vertex for each pixel in the boundary of the footprint. Afterwards, the two primary orientation angles are regressed continuously. Using these orientation, we insert vertices such that all consecutive edges are perpendicular. To the best of our knowledge, our approach is the first to predict a continuous orientation angle for building boundary regularization. Furthermore, the proposed method is highly efficient with an average processing time of 2.879 ms for a single building.

show abstract

Section: Related Workmentioning

confidence: 99%

“…This allows to obtain regular polygons, even in complex cases. However, frame field learning does not guarantee rectilinearity, as Li et al (2019) does.…”

Section: Related Workmentioning

confidence: 99%

See 1 more Smart Citation

Rectilinear Building Footprint Regularization Using Deep Learning

Schuegraf,

Li,

Tian

et al. 2024

ISPRS Ann. Photogramm. Remote Sens. Spatial Inf. Sci.

View full text Add to dashboard Cite

show abstract

“…The single-image building reconstruction network proposed by Alidoost et al [32] used an optimized multi-scale convolution-deconvolution network to extract the height information and roof profile information of the buildings in the image. The large complex building is divided into multiple primitives [33], and the original building model is obtained through information combination and model splicing, which also require higher primitive processing. Partovi et al [7,34] proposed to reconstruct 3D building models with LoD2 in the vector format using DSM and VHR optical satellite imagery, which allows for reconstructing buildings higher than 3 m and larger than 75 m 2 , Sirmacek et al [35] also solved the problem where steep walls could not be generated.…”

Section: Related Workmentioning

confidence: 99%

A 3D Reconstruction Framework of Buildings Using Single Off-Nadir Satellite Image

et al. 2021

View full text Add to dashboard Cite

A novel framework for 3D reconstruction of buildings based on a single off-nadir satellite image is proposed in this paper. Compared with the traditional methods of reconstruction using multiple images in remote sensing, recovering 3D information that utilizes the single image can reduce the demands of reconstruction tasks from the perspective of input data. It solves the problem that multiple images suitable for traditional reconstruction methods cannot be acquired in some regions, where remote sensing resources are scarce. However, it is difficult to reconstruct a 3D model containing a complete shape and accurate scale from a single image. The geometric constraints are not sufficient as the view-angle, size of buildings, and spatial resolution of images are different among remote sensing images. To solve this problem, the reconstruction framework proposed consists of two convolutional neural networks: Scale-Occupancy-Network (Scale-ONet) and model scale optimization network (Optim-Net). Through reconstruction using the single off-nadir satellite image, Scale-Onet can generate water-tight mesh models with the exact shape and rough scale of buildings. Meanwhile, the Optim-Net can reduce the error of scale for these mesh models. Finally, the complete reconstructed scene is recovered by Model-Image matching. Profiting from well-designed networks, our framework has good robustness for different input images, with different view-angle, size of buildings, and spatial resolution. Experimental results show that an ideal reconstruction accuracy can be obtained both on the model shape and scale of buildings.

show abstract

“…The aforementioned segmentation approaches have limitations, such as poor robustness and sensitivity to noise. To address the problem, recent progresses including B-spline fitting [26], Gestalt laws [27], structural regularity [28], regular object-based [29] and complex 3D family-based model fitting [30] are proposed and reported to have better performance. When the model is segmented, the feature recognition step, specifically the rooftop primitives recognition, determines the common borders with a predefined roof types.…”

Section: Introductionmentioning

confidence: 99%

Curved Buildings Reconstruction From Airborne LiDAR Data by Matching and Deforming Geometric Primitives

Song

Xia

Wang

et al. 2021

IEEE Trans. Geosci. Remote Sensing

View full text Add to dashboard Cite

irborneirborneA LiDAR (Light Detection and Ranging) data is widely applied in building reconstruction, with studies reporting success in typical buildings. However, the reconstruction of curved buildings remains an open research problem. To this end, we propose a new framework for curved building reconstruction via assembling and deforming geometric primitives. The input LiDAR point cloud are first converted into contours where individual buildings are identified. After recognizing geometric units (primitives) from building contours, we get initial models by matching basic geometric primitives to these primitives. To polish assembly models, we employ a warping field for model refinements. Specifically, an embedded deformation (ED) graph is constructed via downsampling the initial model. Then, the point-to-model displacements are minimized by adjusting node parameters in the ED graph based on our objective function. The presented framework is validated on several highly curved buildings collected by various LiDAR in different cities. The experimental results, as well as accuracy comparison, demonstrate the advantage and effectiveness of our method. The new insight attributes to an efficient reconstruction manner. Moreover, we prove that the primitive-based framework significantly reduces the data storage to 10-20 percent of classical mesh models.

show abstract

Geometric Object Based Building Reconstruction From Satellite Imagery Derived Point Clouds

Cited by 5 publications

References 14 publications

Rectilinear Building Footprint Regularization Using Deep Learning

Rectilinear Building Footprint Regularization Using Deep Learning

A 3D Reconstruction Framework of Buildings Using Single Off-Nadir Satellite Image

Curved Buildings Reconstruction From Airborne LiDAR Data by Matching and Deforming Geometric Primitives

Contact Info

Product

Resources

About