Regularization and Completion of TomoSAR Point Clouds in a Projected Height Map Domain

Ley, Andreas; D'Hondt, O.; Hellwich, Olaf

doi:10.1109/jstars.2018.2814219

Cited by 18 publications

(8 citation statements)

References 23 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…For quantitative evaluation, we defined the regularization precision to be the deviation from the regularization result to the ground truth. For every scatterer in the point cloud, we computed its absolute distance to the nearest ground truth surface [18]. The distance is illustrated in Figure 14.…”

Section: Resultsmentioning

confidence: 99%

“…For simplicity, in the following analysis, we assumed that the input point clouds of our method were projected from the slant range domain to the ground range domain by using the method described in [18]. The schematic geometry of one single target building is illustrated in Figure 3.…”

Section: Methodsmentioning

confidence: 99%

“…The schematic geometry of one single target building is illustrated in Figure 3. Considering the side-look imaging principle of TomoSAR, we made a simplifying assumption that the radar did not penetrate the building and ground, so that the surface scatterers can be “seen” only from one side of the building [18]. Then, we directly used these surface scatterers to represent the building structure.…”

Section: Methodsmentioning

confidence: 99%

“…Thus, methods of height estimation are of great concern when processing TomoSAR point clouds. References [17,18] processed the point clouds efficiently by estimating the heights of the principal building planes and segmented the data into several parts and did the plane fitting of the roof and ground by part. The processing performance depends on the segmentation of the raw data and the precision of the plane fitting to a large extent.…”

Section: Introductionmentioning

confidence: 99%

See 3 more Smart Citations

Automatic Regularization of TomoSAR Point Clouds for Buildings Using Neural Networks

Zhou

Zhang

et al. 2019

Sensors

View full text Add to dashboard Cite

Tomographic SAR (TomoSAR) is a remote sensing technique that extends the conventional two-dimensional (2-D) synthetic aperture radar (SAR) imaging principle to three-dimensional (3-D) imaging. It produces 3-D point clouds with unavoidable noise that seriously deteriorates the quality of 3-D imaging and the reconstruction of buildings over urban areas. However, existing methods for TomoSAR point cloud processing notably rely on data segmentation, which influences the processing efficiency and denoising performance to a large extent. Inspired by regression analysis, in this paper, we propose an automatic method using neural networks to regularize the 3-D building structures from TomoSAR point clouds. By changing the point heights, the surface points of a building are refined. The method has commendable performance on smoothening the building surface, and keeps a precise preservation of the building structure. Due to the regression mechanism, the method works in a high automation level, which avoids data segmentation and complex parameter adjustment. The experimental results demonstrate the effectiveness of our method to denoise and regularize TomoSAR point clouds for urban buildings.

show abstract

Section: Resultsmentioning

confidence: 99%

Section: Methodsmentioning

confidence: 99%

Section: Methodsmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

See 2 more Smart Citations

Automatic Regularization of TomoSAR Point Clouds for Buildings Using Neural Networks

Zhou

Zhang

et al. 2019

Sensors

View full text Add to dashboard Cite

show abstract

“…Previous completion methods usually focus on filling in small parts, where the basic structure is relatively complete. A. Ley et al [7] propose a simple convex optimization formulation that exploits geometric constraint, which has been demonstrated in denoising point clouds and filling in small holes on E-SAR data. Z. Cai et al [8] come up with an occluded boundary detection method based on the last-echo information, but is only fit for on small-footprint LIDAR point clouds [9].…”

Section: Introductionmentioning

confidence: 99%

Data-Driven Point Cloud Objects Completion

Zhang

Zang

2019

Sensors

View full text Add to dashboard Cite

With the development of the laser scanning technique, it is easier to obtain 3D large-scale scene rapidly. However, many scanned objects may suffer serious incompletion caused by the scanning angles or occlusion, which has severely impacted their future usage for the 3D perception and modeling, while traditional point cloud completion methods often fails to provide satisfactory results due to the large missing parts. In this paper, by utilising 2D single-view images to infer 3D structures, we propose a data-driven Point Cloud Completion Network ( P C C N e t ), which is an image-guided deep-learning-based object completion framework. With the input of incomplete point clouds and the corresponding scanned image, the network can acquire enough completion rules through an encoder-decoder architecture. Based on an attention-based 2D-3D fusion module, the network is able to integrate 2D and 3D features adaptively according to their information integrity. We also propose a projection loss as an additional supervisor to have a consistent spatial distribution from multi-view observations. To demonstrate the effectiveness, first, the proposed P C C N e t is compared to recent generative networks and has shown more powerful 3D reconstruction abilities. Then, P C C N e t is compared to a recent point cloud completion methods, which has demonstrate that the proposed P C C N e t is able to provide satisfied completion results for objects with large missing parts.

show abstract

Urban surface reconstruction in SAR tomography by graph-cuts

Rambour

Denis

Tupin

et al. 2019

Computer Vision and Image Understanding

View full text Add to dashboard Cite

SAR (Synthetic Aperture Radar) tomography reconstructs 3-D volumes from stacks of SAR images. High resolution satellites such as TerraSAR-X provide images that can be combined to produce 3-D models. In urban areas, sparsity priors are generally enforced during the tomographic inversion process in order to retrieve the location of scatterers seen within a given radar resolution cell. However, such priors often miss parts of the urban surfaces. Those missing parts are typically regions of flat areas such as ground or rooftops. This paper introduces a surface segmentation algorithm based on the computation of the optimal cut in a flow n etwork. This segmentation process can be included within the 3-D reconstruction framework in order to improve the recovery of urban surfaces. Illustrations on a TerraSAR-X tomographic dataset demonstrate the potential of the approach to produce a 3-D model of urban surfaces such as ground, façades and rooftops.

show abstract

Regularization and Completion of TomoSAR Point Clouds in a Projected Height Map Domain

Cited by 18 publications

References 23 publications

Automatic Regularization of TomoSAR Point Clouds for Buildings Using Neural Networks

Automatic Regularization of TomoSAR Point Clouds for Buildings Using Neural Networks

Data-Driven Point Cloud Objects Completion

Urban surface reconstruction in SAR tomography by graph-cuts

Contact Info

Product

Resources

About