3D Reconstruction of Building Based on High-Resolution SAR and Optical Images

2006 ◽  
Author(s):  
Z. Junjie ◽  
D. Chibiao ◽  
Y. Hongjian ◽  
X. Minghong
Keyword(s):  
High Resolution ◽  
3D Reconstruction ◽  
Optical Images

scholarly journals High‐resolution MRI of the human palatine tonsil and its schematic anatomic 3D reconstruction

2021 ◽  
Author(s):  
Karl‐Heinz Herrmann ◽  
Franziska Hoffmann ◽  
Günther Ernst ◽  
David Pertzborn ◽  
Daniela Pelzel ◽  
...  
Keyword(s):  
High Resolution ◽  
3D Reconstruction ◽  
Palatine Tonsil ◽  
High Resolution Mri

scholarly journals Ultra-High-Resolution 1 m/pixel CaSSIS DTM Using Super-Resolution Restoration and Shape-from-Shading: Demonstration over Oxia Planum on Mars

2021 ◽  
Vol 13 (11) ◽  
pp. 2185
Author(s):  
Yu Tao ◽  
Sylvain Douté ◽  
Jan-Peter Muller ◽  
Susan J. Conway ◽  
Nicolas Thomas ◽  
...  
Keyword(s):  
High Resolution ◽  
3D Reconstruction ◽  
Imaging System ◽  
Processing System ◽  
Digital Terrain Model ◽  
Super Resolution ◽  
Landing Site ◽  
Shape From Shading ◽  
Stereo Pair ◽  
Terrain Model

We introduce a novel ultra-high-resolution Digital Terrain Model (DTM) processing system using a combination of photogrammetric 3D reconstruction, image co-registration, image super-resolution restoration, shape-from-shading DTM refinement, and 3D co-alignment methods. Technical details of the method are described, and results are demonstrated using a 4 m/pixel Trace Gas Orbiter Colour and Stereo Surface Imaging System (CaSSIS) panchromatic image and an overlapping 6 m/pixel Mars Reconnaissance Orbiter Context Camera (CTX) stereo pair to produce a 1 m/pixel CaSSIS Super-Resolution Restoration (SRR) DTM for different areas over Oxia Planum on Mars—the future ESA ExoMars 2022 Rosalind Franklin rover’s landing site. Quantitative assessments are made using profile measurements and the counting of resolvable craters, in comparison with the publicly available 1 m/pixel High-Resolution Imaging Experiment (HiRISE) DTM. These assessments demonstrate that the final resultant 1 m/pixel CaSSIS DTM from the proposed processing system has achieved comparable and sometimes more detailed 3D reconstruction compared to the overlapping HiRISE DTM.

scholarly journals Development of High-Throughput, High-Resolution 3D Reconstruction of Large-Volume Biological Tissue Using Automated Tape Collection Ultramicrotomy and Scanning Electron Microscopy

2011 ◽  
Vol 17 (S2) ◽  
pp. 966-967 ◽  
Author(s):  
R Schalek ◽  
N Kasthuri ◽  
K Hayworth ◽  
D Berger ◽  
J Tapia ◽  
...  
Keyword(s):  
Electron Microscopy ◽  
Scanning Electron Microscopy ◽  
High Resolution ◽  
3D Reconstruction ◽  
High Throughput ◽  
Large Volume ◽  
Biological Tissue ◽  
Scanning Electron

Extended abstract of a paper presented at Microscopy and Microanalysis 2011 in Nashville, Tennessee, USA, August 7–August 11, 2011.

scholarly journals SAR AND OBLIQUE AERIAL OPTICAL IMAGE FUSION FOR URBAN AREA IMAGE SEGMENTATION

2017 ◽  
Vol XLII-1/W1 ◽  
pp. 639-642 ◽  
Author(s):  
J. Fagir ◽  
A. Schubert ◽  
M. Frioud ◽  
D. Henke
Keyword(s):  
Image Segmentation ◽  
High Resolution ◽  
Single Channel ◽  
Research Area ◽  
Synthetic Aperture ◽  
Optical Data ◽  
Surface Model ◽  
Digital Surface Model ◽  
Oblique View ◽  
Optical Images

The fusion of synthetic aperture radar (SAR) and optical data is a dynamic research area, but image segmentation is rarely treated. While a few studies use low-resolution nadir-view optical images, we approached the segmentation of SAR and optical images acquired from the same airborne platform – leading to an oblique view with high resolution and thus increased complexity. To overcome the geometric differences, we generated a digital surface model (DSM) from adjacent optical images and used it to project both the DSM and SAR data into the optical camera frame, followed by segmentation with each channel. The fused segmentation algorithm was found to out-perform the single-channel version.

scholarly journals DCN-Based Spatial Features for Improving Parcel-Based Crop Classification Using High-Resolution Optical Images and Multi-Temporal SAR Data

2019 ◽  
Vol 11 (13) ◽  
pp. 1619 ◽  
Author(s):  
Zhou Ya’nan ◽  
Luo Jiancheng ◽  
Feng Li ◽  
Zhou Xiaocheng
Keyword(s):  
Time Series ◽  
High Resolution ◽  
Short Term Memory ◽  
Multivariate Time Series ◽  
Hunan Province ◽  
Spatial Features ◽  
Optical Images ◽  
Multi Temporal ◽  
Crop Classification ◽  
Sar Data

Spatial features retrieved from satellite data play an important role for improving crop classification. In this study, we proposed a deep-learning-based time-series analysis method to extract and organize spatial features to improve parcel-based crop classification using high-resolution optical images and multi-temporal synthetic aperture radar (SAR) data. Central to this method is the use of multiple deep convolutional networks (DCNs) to extract spatial features and to use the long short-term memory (LSTM) network to organize spatial features. First, a precise farmland parcel map was delineated from optical images. Second, hundreds of spatial features were retrieved using multiple DCNs from preprocessed SAR images and overlaid onto the parcel map to construct multivariate time-series of crop growth for parcels. Third, LSTM-based network structures for organizing these time-series features were constructed to produce a final parcel-based classification map. The method was applied to a dataset of high-resolution ZY-3 optical images and multi-temporal Sentinel-1A SAR data to classify crop types in the Hunan Province of China. The classification results, showing an improvement of greater than 5.0% in overall accuracy relative to methods without spatial features, demonstrated the effectiveness of the proposed method in extracting and organizing spatial features for improving parcel-based crop classification.

Classifications of High Resolution Optical Images using Supervised Algorithms

2018 ◽  
Author(s):  
Balnarsaiah Battula ◽  
Laxminarayana Parayitam ◽  
T. S. Prasad ◽  
Penta Balakrishna ◽  
Chandrasekhar Patibandla
Keyword(s):  
High Resolution ◽  
Optical Images

A Novel Method for Automated Acquisition of Tilt Series for Electron Tomography Based on Pre-Calibration of the Specimen Stage

2000 ◽  
Vol 6 (S2) ◽  
pp. 1148-1149
Author(s):  
U. Ziese ◽  
A.H. Janssen ◽  
T.P. van der Krift ◽  
A.G. van Balen ◽  
W.J. de Ruijter ◽  
...  
Keyword(s):  
High Resolution ◽  
3D Reconstruction ◽  
Cell Biology ◽  
Electron Tomography ◽  
Three Dimensional ◽  
Imaging Method ◽  
3D Images ◽  
Tilt Series ◽  
3D Information ◽  
Structural Arrangements

Electron tomography is a three-dimensional (3D) imaging method with transmission electron microscopy (TEM) that provides high-resolution 3D images of structural arrangements. Conventional TEM images are in first approximation mere 2D-projections of a 3D sample under investigation. With electron tomographya series of images is acquired of a sample that is tilted over a large angular range (±70°) with small angular tilt increments (so called tilt-series). For the subsequent 3D-reconstruction, the images of the tilt series are aligned relative to each other and the 3D-reconstruction is computed. Electron tomography is the only technique that can provide true 3D information with nm-scale resolution of individual and unique samples. For (cell) biology and material science applications the availability of high-resolution 3D images of structural arrangements within individual samples provides unique architectural information that cannot be obtained otherwise. Routine application of electron tomography will comprise a major revolutionary step forward in the characterization of complex materials and cellular arrangements.

scholarly journals Extracting Building Boundaries from High Resolution Optical Images and LiDAR Data by Integrating the Convolutional Neural Network and the Active Contour Model

2018 ◽  
Vol 10 (9) ◽  
pp. 1459 ◽  
Author(s):  
Ying Sun ◽  
Xinchang Zhang ◽  
Xiaoyang Zhao ◽  
Qinchuan Xin
Keyword(s):  
High Resolution ◽  
Active Contour ◽  
Active Contour Model ◽  
Remote Sensing Data ◽  
Lidar Data ◽  
Boundary Extraction ◽  
Contour Model ◽  
Optical Images ◽  
Building Footprint ◽  
Salt And Pepper

Identifying and extracting building boundaries from remote sensing data has been one of the hot topics in photogrammetry for decades. The active contour model (ACM) is a robust segmentation method that has been widely used in building boundary extraction, but which often results in biased building boundary extraction due to tree and background mixtures. Although the classification methods can improve this efficiently by separating buildings from other objects, there are often ineluctable salt and pepper artifacts. In this paper, we combine the robust classification convolutional neural networks (CNN) and ACM to overcome the current limitations in algorithms for building boundary extraction. We conduct two types of experiments: the first integrates ACM into the CNN construction progress, whereas the second starts building footprint detection with a CNN and then uses ACM for post processing. Three level assessments conducted demonstrate that the proposed methods could efficiently extract building boundaries in five test scenes from two datasets. The achieved mean accuracies in terms of the F1 score for the first type (and the second type) of the experiment are 96.43 ± 3.34% (95.68 ± 3.22%), 88.60 ± 3.99% (89.06 ± 3.96%), and 91.62 ±1.61% (91.47 ± 2.58%) at the scene, object, and pixel levels, respectively. The combined CNN and ACM solutions were shown to be effective at extracting building boundaries from high-resolution optical images and LiDAR data.

Sign in / Sign up

Export Citation Format

Share Document