scholarly journals Accuracy Evaluation of DEM generated from Satellite Images Using Automated Geo-positioning Approach

2017 ◽  
Vol 33 (1) ◽  
pp. 69-77 ◽  
Author(s):  
Kwan-Young Oh ◽  
Hyung-Sup Jung ◽  
Moung-Jin Lee
Keyword(s):  
Satellite Images ◽  
Accuracy Evaluation

scholarly journals Geometric Accuracy Evaluation of High-Resolution Satellite Images Based on Xianning Test Field

Sensors ◽  
2018 ◽  
Vol 18 (7) ◽  
pp. 2121 ◽  
Author(s):  
Xiongwei Zheng ◽  
Qi Huang ◽  
Jingjing Wang ◽  
Taoyang Wang ◽  
Guo Zhang
Keyword(s):  
High Resolution ◽  
Satellite Images ◽  
Accuracy Evaluation ◽  
Test Field ◽  
Geometric Accuracy ◽  
High Resolution Satellite Images

scholarly journals FSRSS-Net: High-Resolution Mapping of Buildings from Middle-Resolution Satellite Images Using a Super-Resolution Semantic Segmentation Network

2021 ◽  
Vol 13 (12) ◽  
pp. 2290
Author(s):  
Tao Zhang ◽  
Hong Tang ◽  
Yi Ding ◽  
Penglong Li ◽  
Chao Ji ◽  
...  
Keyword(s):  
High Resolution ◽  
Spatial Resolution ◽  
Satellite Images ◽  
Super Resolution ◽  
Semantic Segmentation ◽  
Image Features ◽  
Accuracy Evaluation ◽  
Building Recognition ◽  
Semantic Maps ◽  
Sentinel 2A

Satellite mapping of buildings and built-up areas used to be delineated from high spatial resolution (e.g., meters or sub-meters) and middle spatial resolution (e.g., tens of meters or hundreds of meters) satellite images, respectively. To the best of our knowledge, it is important to explore a deep-learning approach to delineate high-resolution semantic maps of buildings from middle-resolution satellite images. The approach is termed as super-resolution semantic segmentation in this paper. Specifically, we design a neural network with integrated low-level image features of super-resolution and high-level semantic features of super-resolution, which is trained with Sentinel-2A images (i.e., 10 m) and higher-resolution semantic maps (i.e., 2.5 m). The network, based on super-resolution semantic segmentation features is called FSRSS-Net. In China, the 35 cities are partitioned into three groups, i.e., 19 cities for model training, four cities for quantitative testing and the other 12 cities for qualitative generalization ability analysis of the learned networks. A large-scale sample dataset is created and utilized to train and validate the performance of the FSRSS-Net, which includes 8597 training samples and 766 quantitative accuracy evaluation samples. Quantitative evaluation results show that: (1) based on the 10 m Sentinel-2A image, the FSRSS-Net can achieve super-resolution semantic segmentation and produce 2.5 m building recognition results, and there is little difference between the accuracy of 2.5 m results by FSRSS-Net and 10 m results by U-Net. More importantly, the 2.5 m building recognition results by FSRSS-Net have higher accuracy than the 2.5 m results by U-Net 10 m building recognition results interpolation up-sampling; (2) from the spatial visualization of the results, the building recognition results of 2.5 m are more precise than those of 10 m, and the outline of the building is better depicted. Qualitative analysis shows that: (1) the learned FSRSS-Net can be also well generalized to other cities that are far from training regions; (2) the FSRSS-Net can still achieve comparable results to the U-Net 2 m building recognition results, even when the U-Net is directly trained using both 2-meter resolution GF2 satellite images and corresponding semantic labels.

scholarly journals DSM Accuracy Evaluation for the ISPRS Commission I Image Matching Benchmark

2014 ◽  
Vol XL-1 ◽  
pp. 195-200 ◽  
Author(s):  
G. Kuschk ◽  
P. d'Angelo ◽  
R. Qin ◽  
D. Poli ◽  
P. Reinartz ◽  
...  
Keyword(s):  
Satellite Images ◽  
Ground Truth ◽  
Automatic Generation ◽  
Reference Points ◽  
Real Surface ◽  
Accuracy Evaluation ◽  
Camera Model ◽  
Ground Truth Data ◽  
Advantages And Disadvantages ◽  
Stereo Reconstruction

To improve the quality of algorithms for automatic generation of Digital Surface Models (DSM) from optical stereo data in the remote sensing community, the Working Group 4 of Commission I: Geometric and Radiometric Modeling of Optical Airborne and Spaceborne Sensors provides on its website <a href="http://www2.isprs.org/commissions/comm1/wg4/benchmark-test.html"target="_blank">http://www2.isprs.org/commissions/comm1/wg4/benchmark-test.html</a> a benchmark dataset for measuring and comparing the accuracy of dense stereo algorithms. The data provided consists of several optical spaceborne stereo images together with ground truth data produced by aerial laser scanning. In this paper we present our latest work on this benchmark, based upon previous work. <br><br> As a first point, we noticed that providing the abovementioned test data as geo-referenced satellite images together with their corresponding RPC camera model seems too high a burden for being used widely by other researchers, as a considerable effort still has to be made to integrate the test datas camera model into the researchers local stereo reconstruction framework. To bypass this problem, we now also provide additional rectified input images, which enable stereo algorithms to work out of the box without the need for implementing special camera models. Care was taken to minimize the errors resulting from the rectification transformation and the involved image resampling. <br><br> We further improved the robustness of the evaluation method against errors in the orientation of the satellite images (with respect to the LiDAR ground truth). To this end we implemented a point cloud alignment of the DSM and the LiDAR reference points using an Iterative Closest Point (ICP) algorithm and an estimation of the best fitting transformation. This way, we concentrate on the errors from the stereo reconstruction and make sure that the result is not biased by errors in the absolute orientation of the satellite images. The evaluation of the stereo algorithms is done by triangulating the resulting (filled) DSMs and computing for each LiDAR point the nearest Euclidean distance to the DSM surface. We implemented an adaptive triangulation method minimizing the second order derivative of the surface in a local neighborhood, which captures the real surface more accurate than a fixed triangulation. As a further advantage, using our point-to-surface evaluation, we are also able to evaluate non-uniformly sampled DSMs or triangulated 3D models in general. The latter is for example needed when evaluating building extraction and data reduction algorithms. <br><br> As practical example we compare results from three different matching methods applied to the data available within the benchmark data sets. These results are analyzed using the above mentioned methodology and show advantages and disadvantages of the different methods, also depending on the land cover classes.

The machine training in problems of satellite images’s processing

Metrologiya ◽  
2020 ◽  
pp. 15-37
Author(s):  
L. P. Bass ◽  
Yu. A. Plastinin ◽  
I. Yu. Skryabysheva
Keyword(s):  
Remote Sensing ◽  
Neural Networks ◽  
Computer Vision ◽  
Satellite Images ◽  
Vision Systems ◽  
Earth Remote Sensing ◽  
Practical Applications ◽  
Convolution Neural Networks ◽  
Computer Vision Systems ◽  
Trained Neural Network

Use of the technical (computer) vision systems for Earth remote sensing is considered. An overview of software and hardware used in computer vision systems for processing satellite images is submitted. Algorithmic methods of the data processing with use of the trained neural network are described. Examples of the algorithmic processing of satellite images by means of artificial convolution neural networks are given. Ways of accuracy increase of satellite images recognition are defined. Practical applications of convolution neural networks onboard microsatellites for Earth remote sensing are presented.

Multitemporal distribution analysis of Dodonaea viscosa (L.) Jacq. by remote sensing in Durango, Mexico

2020 ◽  
Vol 13 (8) ◽  
Author(s):  
Marco, A. Márquez-Linares ◽  
Jonathan G. Escobar--Flores ◽  
Sarahi Sandoval- Espinosa ◽  
Gustavo Pérez-Verdín
Keyword(s):  
Neural Network ◽  
Artificial Neural Network ◽  
Design Methodology ◽  
Supervised Classification ◽  
Satellite Images ◽  
Ground Cover ◽  
Distribution Analysis ◽  
Dodonaea Viscosa ◽  
Artificial Neural ◽  
Landsat Satellite

Objective: to determine the distribution of D. viscosa in the vicinity of the Guadalupe Victoria Dam in Durango, Mexico, for the years 1990, 2010 and 2017.Design/Methodology/Approach: Landsat satellite images were processed in order to carry out supervised classifications using an artificial neural network. Images from the years 1990, 2010 and 2017 were used to estimate ground cover of D. viscosa, pastures, crops, shrubs, and oak forest. This data was used to calculate the expansion of D. viscosa in the study area.Results/Study Limitations/Implications: the supervised classification with the artificial neural network was optimal after 400 iterations, obtaining the best overall precision of 84.5 % for 2017. This contrasted with the year 1990, when overall accuracy was low at 45 % due to less training sites (fewer than 100) recorded for each of the land cover classes.Findings/Conclusions: in 1990, D. viscosa was found on only five hectares, while by 2017 it had increased to 147 hectares. If the disturbance caused by overgrazing continues, and based on the distribution of D. viscosa, it is likely that in a few years it will have the ability to invade half the study area, occupying agricultural, forested, and shrub areas

Designing a coherent land registration system for rural Portugal

2019 ◽  
Vol 2 (1) ◽  
Author(s):  
Tiago NUNES ◽  
Miguel COUTINHO
Keyword(s):  
Satellite Images ◽  
Field Research ◽  
Digital Native ◽  
Web Based ◽  
Registration System ◽  
Land Registration ◽  
Daily Rate ◽  
Property Owners ◽  
Property Identification

After almost a century of several attempts to establish a coherent land registration system across the whole country, in 2017 the Portuguese government decided to try a new, digital native approach to the problem. Thus, a web-based platform was created, where property owners from 10 pilot municipalities could manually identify their lands’ properties using a map based on satellite images. After the first month of submissions, it became clear that at the current daily rate, it would take years to achieve the goal of 100% rural property identification across just the 10 municipalities. Field research during the first month after launch enabled us to understand landowners’ relationships with their land, map their struggles with the platform, and prototype ways to improve the whole service. Understanding that these improvements would still not be enough to get to the necessary daily rate, we designed, tested and validated an algorithm that allows us to identify a rural property shape and location without coordinates. Today, we are able to help both Government and landowners identify a rural property location with the click of a button.

A Novel Change Detection Method for Unregistered Optical Satellite Images

2012 ◽  
Vol E95.B (5) ◽  
pp. 1890-1893
Author(s):  
Wang LUO ◽  
Hongliang LI ◽  
Guanghui LIU ◽  
Guan GUI
Keyword(s):  
Change Detection ◽  
Satellite Images ◽  
Detection Method ◽  
Optical Satellite Images
Sign in / Sign up

Export Citation Format

Share Document