scholarly journals Use of the SAR Shadowing Effect for Deforestation Detection with Sentinel-1 Time Series

2018 ◽  
Vol 10 (8) ◽  
pp. 1250 ◽  
Author(s):  
Alexandre Bouvet ◽  
Stéphane Mermoz ◽  
Marie Ballère ◽  
Thierry Koleck ◽  
Thuy Le Toan
Keyword(s):  
Time Series ◽  
Detection Rate ◽  
Large Scale ◽  
Detection Method ◽  
Earth Observation ◽  
Synthetic Aperture ◽  
Sar Images ◽  
Shadowing Effect ◽  
Potential Exploitation ◽  
Better Than

To detect deforestation using Earth Observation (EO) data, widely used methods are based on the detection of temporal changes in the EO measurements within the deforested patches. In this paper, we introduce a new indicator of deforestation obtained from synthetic aperture radar (SAR) images, which relies on a geometric artifact that appears when deforestation happens, in the form of a shadow at the border of the deforested patch. The conditions for the appearance of these shadows are analyzed, as well as the methods that can be employed to exploit them to detect deforestation. The approach involves two steps: (1) detection of new shadows; (2) reconstruction of the deforested patch around the shadows. The launch of Sentinel-1 in 2014 has opened up opportunities for a potential exploitation of this approach in large-scale applications. A deforestation detection method based on this approach was tested in a 600,000 ha site in Peru. A detection rate of more than 95% is obtained for samples larger than 0.4 ha, and the method was found to perform better than the optical-based UMD-GLAD Forest Alert dataset both in terms of spatial and temporal detection. Further work needed to exploit this approach at operational levels is discussed.

scholarly journals FLOOD DETECTION IN TIME SERIES OF OPTICAL AND SAR IMAGES

2020 ◽  
Vol XLIII-B2-2020 ◽  
pp. 1343-1346
Author(s):  
C. Rambour ◽  
N. Audebert ◽  
E. Koeniguer ◽  
B. Le Saux ◽  
M. Crucianu ◽  
...  
Keyword(s):  
Neural Network ◽  
Time Series ◽  
Remote Sensing Data ◽  
Earth Observation ◽  
Synthetic Aperture ◽  
Flood Events ◽  
Sar Images ◽  
Optical Images ◽  
Flood Detection ◽  
Network Approaches

Abstract. These last decades, Earth Observation brought a number of new perspectives from geosciences to human activity monitoring. As more data became available, Artificial Intelligence (AI) techniques led to very successful results for understanding remote sensing data. Moreover, various acquisition techniques such as Synthetic Aperture Radar (SAR) can also be used for problems that could not be tackled only through optical images. This is the case for weather-related disasters such as floods or hurricanes, which are generally associated with large clouds cover. Yet, machine learning on SAR data is still considered challenging due to the lack of available labeled data. To help the community go forward, we introduce a new dataset composed of co-registered optical and SAR images time series for the detection of flood events and new neural network approaches to leverage these two modalities.

scholarly journals Patch-Based Change Detection Method for SAR Images with Label Updating Strategy

2021 ◽  
Vol 13 (7) ◽  
pp. 1236
Author(s):  
Yuanjun Shu ◽  
Wei Li ◽  
Menglong Yang ◽  
Peng Cheng ◽  
Songchen Han
Keyword(s):  
Neural Networks ◽  
Deep Learning ◽  
Change Detection ◽  
Detection Method ◽  
Training Data ◽  
Synthetic Aperture ◽  
Learning Method ◽  
Sar Images ◽  
Two Stage ◽  
Second Stage

Convolutional neural networks (CNNs) have been widely used in change detection of synthetic aperture radar (SAR) images and have been proven to have better precision than traditional methods. A two-stage patch-based deep learning method with a label updating strategy is proposed in this paper. The initial label and mask are generated at the pre-classification stage. Then a two-stage updating strategy is applied to gradually recover changed areas. At the first stage, diversity of training data is gradually restored. The output of the designed CNN network is further processed to generate a new label and a new mask for the following learning iteration. As the diversity of data is ensured after the first stage, pixels within uncertain areas can be easily classified at the second stage. Experiment results on several representative datasets show the effectiveness of our proposed method compared with several existing competitive methods.

scholarly journals On the Use of Single-, Dual-, and Quad-Polarimetric SAR Observation for Landslide Detection

2019 ◽  
Vol 8 (9) ◽  
pp. 384 ◽  
Author(s):  
Park ◽  
Lee
Keyword(s):  
Remote Sensing ◽  
Detection Rate ◽  
Detection Method ◽  
Incidence Angle ◽  
Accuracy Assessment ◽  
Temporal Variations ◽  
The Other ◽  
Synthetic Aperture ◽  
False Alarms ◽  
Simple Change

Remote sensing technologies, particularly with Synthetic Aperture Radar (SAR) system, can provide timely and critical information to assess landslide distributions over large areas. Most space-borne SAR systems have been operating in different polarimetric modes to meet various operational requirements. This study aims to discuss how much detectability can be expected in the landslide map produced from the single-, dual-, and quad-polarization modes of observation. The experimental analysis of the characteristic changes of PALSAR-2 signals showed that quad-polarization parameters indicating signal depolarization properties revealed noticeable landslide-induced temporal changes for all local incidence angle ranges. To produce a landslide map, a simple change detection method based on characteristic scattering properties of landslide areas was proposed. The accuracy assessment results showed that the depolarization parameters, such as the co-pol coherence and polarizing contribution, can identify areas affected by landslides with a detection rate of 60%, and a false-alarm rate of 5%. On the other hand, the single- or dual-pol parameters can only be expected to provide half the accuracy with significant false-alarms in areas with temporal variations independent of landslides.

scholarly journals Ship Classification and Detection Based on CNN Using GF-3 SAR Images

2018 ◽  
Vol 10 (12) ◽  
pp. 2043 ◽  
Author(s):  
Mengyuan Ma ◽  
Jie Chen ◽  
Wei Liu ◽  
Wei Yang
Keyword(s):  
Large Scale ◽  
Weather Conditions ◽  
Synthetic Aperture ◽  
Feature Analysis ◽  
Single Shot ◽  
Target Classification ◽  
Sar Images ◽  
Different Types ◽  
Ship Classification ◽  
Fully Connected

Ocean surveillance via high-resolution Synthetic Aperture Radar (SAR) imageries has been a hot issue because SAR is able to work in all-day and all-weather conditions. The launch of Chinese Gaofen-3 (GF-3) satellite has provided a large number of SAR imageries, making it possible to marine targets monitoring. However, it is difficult for traditional methods to extract effective features to classify and detect different types of marine targets in SAR images. This paper proposes a convolutional neutral network (CNN) model for marine target classification at patch level and an overall scheme for marine target detection in large-scale SAR images. First, eight types of marine targets in GF-3 SAR images are labelled based on feature analysis, building the datasets for further experiments. As for the classification task at patch level, a novel CNN model with six convolutional layers, three pooling layers, and two fully connected layers has been designed. With respect to the detection part, a Single Shot Multi-box Detector with a multi-resolution input (MR-SSD) is developed, which can extract more features at different resolution versions. In order to detect different targets in large-scale SAR images, a whole workflow including sea-land segmentation, cropping with overlapping, detection with MR-SSD model, coordinates mapping, and predicted boxes consolidation is developed. Experiments based on the GF-3 dataset demonstrate the merits of the proposed methods for marine target classification and detection.

scholarly journals SodSAR: A Tower-Based 1–10 GHz SAR System for Snow, Soil and Vegetation Studies

Sensors ◽  
2020 ◽  
Vol 20 (22) ◽  
pp. 6702
Author(s):  
Jorge Jorge Ruiz ◽  
Risto Vehmas ◽  
Juha Lemmetyinen ◽  
Josu Uusitalo ◽  
Janne Lahtinen ◽  
...  
Keyword(s):  
Synthetic Aperture ◽  
The Arctic ◽  
Target Range ◽  
Network Analyzer ◽  
Sar Images ◽  
Finnish Meteorological Institute ◽  
Radar Calibration ◽  
Loss Of Coherence ◽  
Better Than ◽  
Meteorological Institute

We introduce SodSAR, a fully polarimetric tower-based wide frequency (1–10 GHz) range Synthetic Aperture Radar (SAR) aimed at snow, soil and vegetation studies. The instrument is located in the Arctic Space Centre of the Finnish Meteorological Institute in Sodankylä, Finland. The system is based on a Vector Network Analyzer (VNA)-operated scatterometer mounted on a rail allowing the formation of SAR images, including interferometric pairs separated by a temporal baseline. We present the description of the radar, the applied SAR focusing technique, the radar calibration and measurement stability analysis. Measured stability of the backscattering intensity over a three-month period was observed to be better than 0.5 dB, when measuring a target with a known radar cross section. Deviations of the estimated target range were in the order of a few cm over the same period, indicating also good stability of the measured phase. Interforometric SAR (InSAR) capabilities are also discussed, and as a example, the coherence of subsequent SAR acquisitions over the observed boreal forest stand are analyzed over increasing temporal baselines. The analysis shows good conservation of coherence in particular at L-band, while higher frequencies are susceptible to loss of coherence in particular for dense vegetation. The potential of the instrument for satellite calibration and validation activities is also discussed.

scholarly journals Adjacent-Track InSAR Processing for Large-Scale Land Subsidence Monitoring in the Hebei Plain

2021 ◽  
Vol 13 (4) ◽  
pp. 795
Author(s):  
Xi Li ◽  
Li Yan ◽  
Lijun Lu ◽  
Guoman Huang ◽  
Zheng Zhao ◽  
...  
Keyword(s):  
Time Series ◽  
Synthetic Aperture Radar ◽  
Land Subsidence ◽  
Large Scale ◽  
Synthetic Aperture ◽  
Hebei Plain ◽  
Deformation Velocity ◽  
Large Scale Land ◽  
Subsidence Monitoring ◽  
Aperture Radar

Large-scale land subsidence has threatened the safety of the Hebei Plain in China. For tens of thousands of square kilometers of the Hebei Plain, large-scale subsidence monitoring is still one of the most difficult problems to be solved. In this paper, we employed the small baseline subset (SBAS) and NSBAS technique to monitor the land subsidence in the Hebei Plain (45,000 km2). The 166 Sentinel-1A data of adjacent-track 40 and 142 collected from May 2017 to May 2019 were used to generate the average deformation velocity and deformation time-series. A novel data fusion flow for the generation of land subsidence velocity of adjacent-track is presented and tested, named as the fusion of time-series interferometric synthetic aperture radar (TS-InSAR) results of adjacent-track using synthetic aperture radar amplitude images (FTASA). A cross-comparison analysis between the two tracks results and two TS-InSAR results was carried out. In addition, the deformation results were validated by leveling measurements and benchmarks on bedrock results, reaching a precision 9 mm/year. Twenty-six typical subsidence bowls were identified in Handan, Xingtai, Shijiazhuang, Hengshui, Cangzhou, and Baoding. An average annual subsidence velocity over −79 mm/year was observed in Gaoyang County of Baoding City. Through the cause analysis of the typical subsidence bowls, the results showed that the shallow and deep groundwater funnels, three different land use types over the building construction, industrial area, and dense residential area, and faults had high spatial correlation related to land subsidence bowls.

scholarly journals N-YOLO: A SAR Ship Detection Using Noise-Classifying and Complete-Target Extraction

2021 ◽  
Vol 13 (5) ◽  
pp. 871
Author(s):  
Gang Tang ◽  
Yichao Zhuge ◽  
Christophe Claramunt ◽  
Shaoyang Men
Keyword(s):  
Noise Level ◽  
Detection Method ◽  
Synthetic Aperture ◽  
Target Area ◽  
Original Image ◽  
Sar Images ◽  
Ship Detection ◽  
Target Extraction ◽  
High Resolution Images ◽  
Potential Area

High-resolution images provided by synthetic aperture radar (SAR) play an increasingly important role in the field of ship detection. Numerous algorithms have been so far proposed and relative competitive results have been achieved in detecting different targets. However, ship detection using SAR images is still challenging because these images are still affected by different degrees of noise while inshore ships are affected by shore image contrasts. To solve these problems, this paper introduces a ship detection method called N-YOLO, which based on You Only Look Once (YOLO). The N-YOLO includes a noise level classifier (NLC), a SAR target potential area extraction module (STPAE) and a YOLOv5-based detection module. First, NLC derives and classifies the noise level of SAR images. Secondly, the STPAE module is composed by a CA-CFAR and expansion operation, which is used to extract the complete region of potential targets. Thirdly, the YOLOv5-based detection module combines the potential target area with the original image to get a new image. To evaluate the effectiveness of the N-YOLO, experiments are conducted using a reference GaoFen-3 dataset. The detection results show that competitive performance has been achieved by N-YOLO in comparison with several CNN-based algorithms.

scholarly journals Accurate detection method of moving target based on sequential SAR images with multiple azimuth squint angles

2021 ◽  
Vol 2083 (3) ◽  
pp. 032051
Author(s):  
Shiqi Yang ◽  
Yang Liu ◽  
Peili Xi ◽  
Chunsheng Li ◽  
Wei Yang ◽  
...  
Keyword(s):  
False Alarm ◽  
Detection Method ◽  
Synthetic Aperture ◽  
Moving Target ◽  
Constant False Alarm Rate ◽  
Moving Targets ◽  
Sar Images ◽  
Block Level ◽  
Detection Block ◽  
Motion Characteristics

Abstract In this paper, a novel moving target detection method for sequential Synthetic Aperture Radar (SAR) images with different azimuth-squint angles is proposed. In sequential SAR images, due to the movement of the target, the imaging position of moving targets among different frames differs. The method proposed in this paper uses this kind of motion characteristics to achieve the detection of moving targets in multi-frame SAR images. This algorithm can be divided into two parts: block-level detection and pixel-level detection. Block-level detection is achieved by stacked denoising autoencoders to extract the high-dimensional features of the moving target. Pixel-level detection consists of Local Binary Similarity Patterns (LBSP) coding as well as grayscale background subtraction. Pixel-level detection only needs to consider the pixels of foreground image pieces which contain moving targets. This method can not only increase the detection speed, but also suppress the false alarm problem caused by clutter. Experiments are carried out for verifying the validation of the method and the comparison are made between the proposed method and the traditional Constant False Alarm Rate (CFAR) algorithm.

Synthetic aperture radar coherence as a proxy for geomorphic activity

2020 ◽  
Author(s):  
Stephanie Olen ◽  
Bodo Bookhagen
Keyword(s):  
Time Series ◽  
Synthetic Aperture Radar ◽  
Surface Sediment ◽  
Coherence Time ◽  
Synthetic Aperture ◽  
Sar Images ◽  
Sediment Movement ◽  
Denudation Rates ◽  
Geomorphic Processes ◽  
Aperture Radar

<p>Mountain landscapes are shaped by hillslope and fluvial processes that remove and transport material and sediment. Developing proxies to map these processes through space and time is a key element in better understanding their distribution and drivers. Remotely sensed and satellite observations of Earth’s surface are greatly expanding the reach of geomorphologists and presenting a myriad of new opportunities to explore and quantify Earth surface processes. Synthetic aperture radar (SAR), in particular, promises to be a powerful tool for mapping and quantifying geomorphic processes. Here, we exploit a time series of coherence estimates between SAR images from the Copernicus Sentinel-1 mission. Coherence is the spatial correlation between two SAR images and is sensitive to changes in both the phase (elevation) and amplitude (surface backscatter) of the received radar signal. Geomorphic processes such as landsliding, hillslope slump, cobble movement, or alluvial sediment transport can result in loss of SAR coherence. In regions without significant vegetation or anthropomorphic input, we therefore propose that coherence loss is a proxy for surface sediment movement and geomorphic activity. We constructed time series of Sentinel-1 coherence images spanning three to five years for arid and semi-arid regions of the Argentinian Central Andes and the north-western Himalaya. Both regions are characterized by active tectonics and seasonal climatic gradients. The relatively short revisit time of the Sentinel-1 satellites (~2-4 weeks in our regions of interest) mean that we can not only map geomorphic activity averaged over multiple years, but observe intra-annual and seasonal differences throughout a given year. We are also able to compare interannual geomorphic responses during years with, e.g.,  relatively strong or weak monsoon seasons.</p><p> </p><p>We couple our Sentinel-1 coherence time series with a compilation of published 10-Berrylium terrestrial cosmogenic nuclide basin-wide denudation rates from the Open Cosmogenic isoTOPe and lUmineScence (OCTOPUS) database. For basins with cosmogenic data, we derive temporal and spatial statistics of our coherence time series. Across regional gradients, the range of coherence within basins positively correlates to millennial denudation rates and to topographic metrics used to indicate long-term uplift (e.g., channel steepness). Outlying basins include those in which erosion is driven by large, deep-seeded landslides that occur over repeat times longer than our multi-year observation period. Our study suggests that a dense time series of interferometric coherence can be used as a proxy for surface sediment movement and landscape stability in vegetation-free settings at event to decadal timescales.</p>

scholarly journals An Adaptive Hierarchical Detection Method for Ship Targets in High-Resolution SAR Images

2020 ◽  
Vol 12 (2) ◽  
pp. 303 ◽  
Author(s):  
Yi Liang ◽  
Kun Sun ◽  
Yugui Zeng ◽  
Guofei Li ◽  
Mengdao Xing
Keyword(s):  
Detection Method ◽  
Estimation Method ◽  
Kernel Density ◽  
Image Resolution ◽  
Synthetic Aperture ◽  
Sar Images ◽  
Airborne Sar ◽  
Visual Attention Mechanism ◽  
Synthetic Aperture Radars ◽  
Coarse To Fine

With the improvement of image resolution in synthetic aperture radars (SARs), sea clutter characteristics become more complex, which poses new challenges to traditional ship target detection missions. In this paper, to detect ship targets quickly and efficiently in a complex background, we propose an adaptive hierarchical detection method based on a coarse-to-fine mechanism. This method constructs a new visual attention mechanism to strengthen ship targets and obtain the candidate targets adaptively by the means dichotomy method. On this basis, the precise detection results of the targets are obtained using the speed block kernel density estimation method, which maintains constant false alarm characteristics. Compared with existing methods, the adaptive hierarchical detection method has simple, fast, and accurate characteristics. Experiments based on GF-III satellite and airborne SAR datasets are presented to demonstrate the effectiveness of the proposed method.

Sign in / Sign up

Export Citation Format

Share Document