scholarly journals A New Set of Tools for the Generation of InSAR Visibility Maps Over Wide Areas

Geosciences ◽  
2021 ◽  
Vol 11 (6) ◽  
pp. 229
Author(s):  
Matteo Del Soldato ◽  
Lorenzo Solari ◽  
Alessandro Novellino ◽  
Oriol Monserrat ◽  
Federico Raspini
Keyword(s):  
Land Cover ◽  
Ground Motion ◽  
Large Scale ◽  
Good Practice ◽  
Technical Note ◽  
Target Area ◽  
Reliable Technique ◽  
Precise Tool ◽  
Challenging Environment ◽  
Multi Temporal

Multi-temporal Interferometric Synthetic Aperture Radar (MTInSAR) is a solid and reliable technique used to measure ground motion in many different environments. Today, the scientific community and a wide variety of users and stakeholders consider MTInSAR a precise tool for ground motion-related applications. The standard product of a MTInSAR analysis is a deformation map containing a high number of point-like measurement points (MP) which carry information on ground motion. The density of MPs is uneven, and they cannot be extracted continuously at large scale due to geometrical distortions and unfavourable landcover. It is a good practice to assess the feasibility of the interferometric analysis ahead of data processing. This technical note proposes a ready-to-use set of tools aimed at updating existing methods for modelling the effects of local topography and land cover on MTInSAR approaches. The goal of the tools is to provide InSAR experts and non-experts with a fast and automatic way to derive visibility maps, useful for pre-processing screening of a target area, and to forecast the expected density of MP over a specified area. Moreover, the visibility maps are a valid support for users to better understand the available standard and advanced interferometric results. Two workflows are proposed: the first generates the so-called Rindex map (Ri_m) to estimate the influence of topography on MP detection, the second is used to derive a land cover-calibrated Ri_m seen as a probabilistic model for MP detection (MPD_m). The proposed set of tools was applied in the context of the Alpine arc, whose climatic, morphological, and land cover characteristics represent a challenging environment for any interferometric approach.

scholarly journals Domain-Adversarial Training of Self-Attention-Based Networks for Land Cover Classification Using Multi-Temporal Sentinel-2 Satellite Imagery

2021 ◽  
Vol 13 (13) ◽  
pp. 2564
Author(s):  
Mauro Martini ◽  
Vittorio Mazzia ◽  
Aleem Khaliq ◽  
Marcello Chiaberge
Keyword(s):  
Land Cover ◽  
Large Scale ◽  
Domain Adaptation ◽  
Learning Approaches ◽  
Atmospheric Conditions ◽  
Practical Applications ◽  
Area Of Interest ◽  
Multi Temporal ◽  
Significant Performance ◽  
Adversarial Training

The increasing availability of large-scale remote sensing labeled data has prompted researchers to develop increasingly precise and accurate data-driven models for land cover and crop classification (LC&CC). Moreover, with the introduction of self-attention and introspection mechanisms, deep learning approaches have shown promising results in processing long temporal sequences in the multi-spectral domain with a contained computational request. Nevertheless, most practical applications cannot rely on labeled data, and in the field, surveys are a time-consuming solution that pose strict limitations to the number of collected samples. Moreover, atmospheric conditions and specific geographical region characteristics constitute a relevant domain gap that does not allow direct applicability of a trained model on the available dataset to the area of interest. In this paper, we investigate adversarial training of deep neural networks to bridge the domain discrepancy between distinct geographical zones. In particular, we perform a thorough analysis of domain adaptation applied to challenging multi-spectral, multi-temporal data, accurately highlighting the advantages of adapting state-of-the-art self-attention-based models for LC&CC to different target zones where labeled data are not available. Extensive experimentation demonstrated significant performance and generalization gain in applying domain-adversarial training to source and target regions with marked dissimilarities between the distribution of extracted features.

Land Use and Land Cover Change Based on Remote Sensing and GIS in Changping, Beijing, China and Lake Velence Watershed, Hungary

2011 ◽  
Vol 403-408 ◽  
pp. 1543-1547
Author(s):  
Gai Ying Chen ◽  
Da Zhi Guo ◽  
Malgorzata Verőné Wojtaszek ◽  
Béla Márkus
Keyword(s):  
Remote Sensing ◽  
Land Use ◽  
Information System ◽  
Land Cover ◽  
Land Cover Change ◽  
Large Scale ◽  
Remote Sensing And Gis ◽  
The Past ◽  
Multi Temporal ◽  
Beijing China

Because of the rapid economy development and the enormous society evolution, large scale changes of land use and land cover had occurred in areas of Beijing and Hungary in the past two decades. This paper focused on monitoring on LUCC(land use and land cover change) in Changping，Beijing, China and Lake Velence watershed area in Szekesfehervar, Hungary based on Multi-Temporal, Multi-Spatial and multi-source remotely sensed images and Geographic Information System( GIS).

scholarly journals Classification of Large-Scale High-Resolution SAR Images with Deep Transfer Learning

2020 ◽  
Author(s):  
Zhongling Huang
Keyword(s):  
High Resolution ◽  
Land Cover ◽  
Transfer Learning ◽  
Large Scale ◽  
Target Area ◽  
Sar Images ◽  
Label Noise ◽  
Deep Model ◽  
Imbalanced Classes

<div> <div> <div> <p>The classification of large-scale high-resolution SAR land cover images acquired by satellites is a challenging task, facing several difficulties such as semantic annotation with expertise, changing data characteristics due to varying imaging parameters or regional target area differences, and complex scattering mechanisms being different from optical imaging. Given a large-scale SAR land cover dataset collected from TerraSAR-X images with a hierarchical three-level annotation of 150 categories and comprising more than 100,000 patches, three main challenges in automatically interpreting SAR images of highly imbalanced classes, geographic diversity, and label noise are addressed. In this letter, a deep transfer learning method is proposed based on a similarly annotated optical land cover dataset (NWPU-RESISC45). Besides, a top-2 smooth loss function with cost-sensitive parameters was introduced to tackle the label noise and imbalanced classes’ problems. The proposed method shows high efficiency in transferring information from a similarly annotated remote sensing dataset, a robust performance on highly imbalanced classes, and is alleviating the over-fitting problem caused by label noise. What’s more, the learned deep model has a good generalization for other SAR-specific tasks, such as MSTAR target recognition with a state-of-the-art classification accuracy of 99.46%. </p> </div> </div> </div>

scholarly journals Classification of Large-Scale High-Resolution SAR Images with Deep Transfer Learning

2020 ◽  
Author(s):  
Zhongling Huang
Keyword(s):  
High Resolution ◽  
Land Cover ◽  
Transfer Learning ◽  
Large Scale ◽  
Target Area ◽  
Sar Images ◽  
Label Noise ◽  
Deep Model ◽  
Imbalanced Classes

<div> <div> <div> <p>The classification of large-scale high-resolution SAR land cover images acquired by satellites is a challenging task, facing several difficulties such as semantic annotation with expertise, changing data characteristics due to varying imaging parameters or regional target area differences, and complex scattering mechanisms being different from optical imaging. Given a large-scale SAR land cover dataset collected from TerraSAR-X images with a hierarchical three-level annotation of 150 categories and comprising more than 100,000 patches, three main challenges in automatically interpreting SAR images of highly imbalanced classes, geographic diversity, and label noise are addressed. In this letter, a deep transfer learning method is proposed based on a similarly annotated optical land cover dataset (NWPU-RESISC45). Besides, a top-2 smooth loss function with cost-sensitive parameters was introduced to tackle the label noise and imbalanced classes’ problems. The proposed method shows high efficiency in transferring information from a similarly annotated remote sensing dataset, a robust performance on highly imbalanced classes, and is alleviating the over-fitting problem caused by label noise. What’s more, the learned deep model has a good generalization for other SAR-specific tasks, such as MSTAR target recognition with a state-of-the-art classification accuracy of 99.46%. </p> </div> </div> </div>

Application of Scan Based FA and Advanced Passive Voltage Contrast Technique in Defect Isolation

2003 ◽  
Author(s):  
Michael B. Schmidt ◽  
Noor Jehan Saujauddin
Keyword(s):  
Failure Analysis ◽  
Large Scale ◽  
Fault Isolation ◽  
Electronic Information ◽  
Scan Testing ◽  
Challenging Environment ◽  
Contrast Technique ◽  
Defect Isolation ◽  
Voltage Contrast ◽  
Higher Sensitivity

Abstract Scan testing and passive voltage contrast (PVC) techniques have been widely used as failure analysis fault isolation tools. Scan diagnosis can narrow a failure to a given net and passive voltage contrast can give real-time, large-scale electronic information about a sample at various stages of deprocessing. In the highly competitive and challenging environment of today, failure analysis cycle time is very important. By combining scan FA with a much higher sensitivity passive voltage contrast technique, one can quickly find defects that have traditionally posed a great challenge.

scholarly journals Cropland Abandonment in Slovakia: Analysis and Comparison of Different Data Sources

Land ◽  
2021 ◽  
Vol 10 (4) ◽  
pp. 334
Author(s):  
Juraj Lieskovský ◽  
Dana Lieskovská
Keyword(s):  
Land Use ◽  
Land Cover ◽  
Spatial Data ◽  
Data Sources ◽  
Communist Regime ◽  
Corine Land Cover ◽  
Cropland Area ◽  
Cropland Abandonment ◽  
Multi Temporal

This study compares different nationwide multi-temporal spatial data sources and analyzes the cropland area, cropland abandonment rates and transformation of cropland to other land cover/land use categories in Slovakia. Four multi-temporal land cover/land use data sources were used: The Historic Land Dynamics Assessment (HILDA), the Carpathian Historical Land Use Dataset (CHLUD), CORINE Land Cover (CLC) data and Landsat images classification. We hypothesized that because of the different spatial, temporal and thematic resolution of the datasets, there would be differences in the resulting cropland abandonment rates. We validated the datasets, compared the differences, interpreted the results and combined the information from the different datasets to form an overall picture of long-term cropland abandonment in Slovakia. The cropland area increased until the Second World War, but then decreased after transition to the communist regime and sharply declined following the 1989 transition to an open market economy. A total of 49% of cropland area has been transformed to grassland, 34% to forest and 15% to urban areas. The Historical Carpathian dataset is the more reliable long-term dataset, and it records 19.65 km2/year average cropland abandonment for 1836–1937, 154.44 km2/year for 1938–1955 and 140.21 km2/year for 1956–2012. In comparison, the Landsat, as a recent data source, records 142.02 km2/year abandonment for 1985–2000 and 89.42 km2/year for 2000–2010. These rates, however, would be higher if the dataset contained urbanisation data and more precise information on afforestation. The CORINE Land Cover reflects changes larger than 5 ha, and therefore the reported cropland abandonment rates are lower.

SateLoc: A Virtual Fingerprinting Approach to Outdoor LoRa Localization Using Satellite Images

2021 ◽  
Vol 17 (4) ◽  
pp. 1-28
Author(s):  
Yuxiang Lin ◽  
Wei Dong ◽  
Yi Gao ◽  
Tao Gu
Keyword(s):  
Land Cover ◽  
Large Scale ◽  
Satellite Images ◽  
Low Cost ◽  
Tracking Error ◽  
Location Based Services ◽  
Distance Constraint ◽  
Combination Strategy ◽  
Land Cover Types ◽  
High Resolution Satellite Images

With the increasing relevance of the Internet of Things and large-scale location-based services, LoRa localization has been attractive due to its low-cost, low-power, and long-range properties. However, existing localization approaches based on received signal strength indicators are either easily affected by signal fading of different land-cover types or labor intensive. In this work, we propose SateLoc, a LoRa localization system that utilizes satellite images to generate virtual fingerprints. Specifically, SateLoc first uses high-resolution satellite images to identify land-cover types. With the path loss parameters of each land-cover type, SateLoc can automatically generate a virtual fingerprinting map for each gateway. We then propose a novel multi-gateway combination strategy, which is weighted by the environmental interference of each gateway, to produce a joint likelihood distribution for localization and tracking. We implement SateLoc with commercial LoRa devices without any hardware modification, and evaluate its performance in a 227,500-m urban area. Experimental results show that SateLoc achieves a median localization error of 43.5 m, improving more than 50% compared to state-of-the-art model-based approaches. Moreover, SateLoc can achieve a median tracking error of 37.9 m with the distance constraint of adjacent estimated locations. More importantly, compared to fingerprinting-based approaches, SateLoc does not require the labor-intensive fingerprint acquisition process.

scholarly journals Classification of Very-High-Spatial-Resolution Aerial Images Based on Multiscale Features with Limited Semantic Information

2021 ◽  
Vol 13 (3) ◽  
pp. 364
Author(s):  
Han Gao ◽  
Jinhui Guo ◽  
Peng Guo ◽  
Xiuwan Chen
Keyword(s):  
Deep Learning ◽  
Land Cover ◽  
Spatial Resolution ◽  
Large Scale ◽  
High Spatial Resolution ◽  
Training Data ◽  
Aerial Images ◽  
Rural Landscapes ◽  
Feature Representations ◽  
Object Based

Recently, deep learning has become the most innovative trend for a variety of high-spatial-resolution remote sensing imaging applications. However, large-scale land cover classification via traditional convolutional neural networks (CNNs) with sliding windows is computationally expensive and produces coarse results. Additionally, although such supervised learning approaches have performed well, collecting and annotating datasets for every task are extremely laborious, especially for those fully supervised cases where the pixel-level ground-truth labels are dense. In this work, we propose a new object-oriented deep learning framework that leverages residual networks with different depths to learn adjacent feature representations by embedding a multibranch architecture in the deep learning pipeline. The idea is to exploit limited training data at different neighboring scales to make a tradeoff between weak semantics and strong feature representations for operational land cover mapping tasks. We draw from established geographic object-based image analysis (GEOBIA) as an auxiliary module to reduce the computational burden of spatial reasoning and optimize the classification boundaries. We evaluated the proposed approach on two subdecimeter-resolution datasets involving both urban and rural landscapes. It presented better classification accuracy (88.9%) compared to traditional object-based deep learning methods and achieves an excellent inference time (11.3 s/ha).

Sign in / Sign up

Export Citation Format

Share Document