3D Virtual Urban Scene Reconstruction From a Single Optical Remote Sensing Image

Li, Suo; Zhu, Zhanyu; Wang, Haipeng; Xu, Feng

doi:10.1109/access.2019.2915932

Cited by 10 publications

(8 citation statements)

References 9 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…A CPU + GPU heterogeneous parallel technique was used to implement deep learning algorithms for applications based on multisource data. The paper in [115] presented a 3-D virtual urban scene reconstruction method based on CNNs by combining maps, satellite optical images, and digital terrain models (DTMs). The CNN model was trained on a GPU.…”

Section: B Multisource Remote Sensing Data and Auxiliary Datamentioning

confidence: 99%

Distributed Fusion of Heterogeneous Remote Sensing and Social Media Data: A Review and New Developments

Liu

Lei

et al. 2021

Proc. IEEE

View full text Add to dashboard Cite

Despite the wide availability of remote sensing big data from numerous different Earth Observation (EO) instruments, the limitations in the spatial and temporal resolution of such EO sensors (as well as atmospheric opacity and other kinds of interferers) have led to many situations in which using only remote sensing data cannot fully meet the requirements of applications in which a (near) real-time response is needed. Examples of these applications include floods, earthquakes, and other kinds of natural disasters, such as typhoons. To address this issue, social media data have gradually been adopted to fill possible gaps in the analysis when remote sensing data are lacking or incomplete. In this case, the fusion of heterogeneous big data streams from multiple data sources introduces significant demands from a computational viewpoint. In order to meet these challenges,

show abstract

Section: B Multisource Remote Sensing Data and Auxiliary Datamentioning

confidence: 99%

Distributed Fusion of Heterogeneous Remote Sensing and Social Media Data: A Review and New Developments

Liu

Lei

et al. 2021

Proc. IEEE

View full text Add to dashboard Cite

show abstract

“…In photogrammetry and remote sensing, CNNs can be employed to extract height information such as DSMs from single aerial or satellite-based images (Amini Amirkolaee and Ghamisi and Yokoya, 2018), as well as building detection and footprints extraction (Aamir et al, 2019;Wu et al, 2018;Xu et al, 2018;Yang et al, 2018). (Li et al, 2019) used two independent CNNs for land cover classification and building height estimation from single satellite images. The CNN for height estimation task is a fully connected network and estimates a fixed height value for each building block for 3D reconstruction in LoD1.…”

Section: Related Workmentioning

confidence: 99%

Y-Shaped Convolutional Neural Network for 3d Roof Elements Extraction to Reconstruct Building Models From a Single Aerial Image

Alidoost

Arefi

Hahn

2020

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

View full text Add to dashboard Cite

Abstract. Fast and efficient detection and reconstruction of buildings have become essential in real-time applications such as navigation, 3D rendering, augmented reality, and 3D smart cities. In this study, a modern Deep Learning (DL)-based framework is proposed for automatic detection, localization, and height estimation of buildings, simultaneously, from a single aerial image. The proposed framework is based on a Y-shaped Convolutional Neural Network (Y-Net) which includes one encoder and two decoders. The input of the network is a single RGB image, while the outputs are predicted height information of buildings as well as the rooflines in three classes of eave, ridge, and hip lines. The extracted knowledge by the Y-Net (i.e. buildings’ heights and rooflines) is utilized for 3D reconstruction of buildings based on the third Level of Detail (LoD2). The main steps of the proposed approach are data preparation, CNNs training, and 3D reconstruction. For the experimental investigations airborne data from Potsdam are used, which were provided by ISPRS. For the predicted heights, the results show an average Root Mean Square Error (RMSE) and a Normalized Median Absolute Deviation (NMAD) of about 3.8 m and 1.3 m, respectively. Moreover, the overall accuracy of the extracted rooflines is about 86%.

show abstract

“…In order to simulate SRAL raw signal of actual terrain surface, 3‐D geometry reconstruction is an important step for terrain surface modeling. In this paper, the geometric reconstruction method of terrain surface is introduced with the usage of the global map and global DEM (Li et al, ). The land surface types are derived from the global map, which are used to match the corresponding scattering coefficient models.…”

Section: Terrain Surface Model and Scattering Computationmentioning

confidence: 99%

“…With the digital map, a color clustering recognition method (Li et al, ) is performed to extract the terrain types. After the clustering, the targets are classified into different types as shown in Figure b.…”

Section: Terrain Surface Model and Scattering Computationmentioning

confidence: 99%

Raw Signal Simulation of Synthetic Aperture Radar Altimeter Over Complex Terrain Surfaces

Zhu

Zhang

2020

Radio Science

Self Cite

View full text Add to dashboard Cite

In comparison with the conventional radar altimeter, synthetic aperture radar altimeter (SRAL) is developed with better along‐track spatial resolution and height precision. When SRAL improves the performance of height measurement, it also complicates the radar system designing, signal processing, data analyzing, and system testing. The SRAL raw signal is the result of the interaction between the transmitted signal and the complex terrain surfaces. Generally, the SRAL is used in ocean applications since the PDF can be derived from different ocean surfaces. However, the actual acquired SRAL waveforms can be from complex and variable surface, which may include mountains, cities, forests, lakes, and other types of terrain surfaces. These waveforms contain information about the surfaces of the Earth although difficult to analyze. This paper focuses on the study of the raw signal simulation of SRAL for complex terrain surfaces including land surfaces. The principle of radar altimeter, the electromagnetic characteristics of land targets, and the SRAL signal processing are analyzed. The geometric models are extracted from digital elevation model, and the scattering characteristics of the terrain surface are established with three scattering models. Finally, three cases of terrain surfaces, namely, ice surface, mountain area, and urban area, are simulated and validated against actual SRAL signals measured by the Sentinel‐3 SRAL sensor.

show abstract

3D Virtual Urban Scene Reconstruction From a Single Optical Remote Sensing Image

Cited by 10 publications

References 9 publications

Distributed Fusion of Heterogeneous Remote Sensing and Social Media Data: A Review and New Developments

Distributed Fusion of Heterogeneous Remote Sensing and Social Media Data: A Review and New Developments

Y-Shaped Convolutional Neural Network for 3d Roof Elements Extraction to Reconstruct Building Models From a Single Aerial Image

Raw Signal Simulation of Synthetic Aperture Radar Altimeter Over Complex Terrain Surfaces

Contact Info

Product

Resources

About