Monitoring the Recovery after 2016 Hurricane Matthew in Haiti via Markovian Multitemporal Region-Based Modeling

The aim of this paper is to address the monitoring of the recovery phase in the aftermath of Hurricane Matthew (28 September–10 October 2016) in the town of Jérémie, southwestern Haiti. This is accomplished via a novel change detection method that has been formulated, in a data fusion perspective, in terms of multitemporal supervised classification. The availability of very high resolution images provided by last-generation satellite synthetic aperture radar (SAR) and optical sensors makes this analysis promising from an application perspective and simultaneously challenging from a processing viewpoint. Indeed, pursuing such a goal requires the development of novel methodologies able to exploit the large amount of detailed information provided by this type of data. To take advantage of the temporal and spatial information associated with such images, the proposed method integrates multisensor, multisource, and contextual information. Markov random field modeling is adopted here to integrate the spatial context and the temporal correlation associated with images acquired at different dates. Moreover, the adoption of a region-based approach allows for the characterization of the geometrical structures in the images through multiple segmentation maps at different scales and times. The performances of the proposed approach are evaluated on multisensor pairs of COSMO-SkyMed SAR and Pléiades optical images acquired over Jérémie, in the aftermath of and during the three years after Hurricane Matthew. The effectiveness of the change detection results is analyzed both quantitatively, through the computation of accuracy measures on a test set, and qualitatively, by visual inspection of the classification maps. The robustness of the proposed method with respect to different algorithmic choices is also assessed, and the detected changes are discussed in relation to the recovery endeavors in the area and ground-truth data collected in the field in April 2019.

Download Full-text

Change Detection in Hyperspectral Images Using Recurrent 3D Fully Convolutional Networks

Remote Sensing ◽

10.3390/rs10111827 ◽

2018 ◽

Vol 10 (11) ◽

pp. 1827 ◽

Cited By ~ 24

Author(s):

Ahram Song ◽

Jaewan Choi ◽

Youkyung Han ◽

Yongil Kim

Keyword(s):

Deep Learning ◽

Change Detection ◽

Spatial Information ◽

Short Term Memory ◽

Hyperspectral Images ◽

Convolutional Network ◽

Ground Truth Data ◽

Fully Convolutional Network ◽

Training Samples ◽

Multi Temporal

Hyperspectral change detection (CD) can be effectively performed using deep-learning networks. Although these approaches require qualified training samples, it is difficult to obtain ground-truth data in the real world. Preserving spatial information during training is difficult due to structural limitations. To solve such problems, our study proposed a novel CD method for hyperspectral images (HSIs), including sample generation and a deep-learning network, called the recurrent three-dimensional (3D) fully convolutional network (Re3FCN), which merged the advantages of a 3D fully convolutional network (FCN) and a convolutional long short-term memory (ConvLSTM). Principal component analysis (PCA) and the spectral correlation angle (SCA) were used to generate training samples with high probabilities of being changed or unchanged. The strategy assisted in training fewer samples of representative feature expression. The Re3FCN was mainly comprised of spectral–spatial and temporal modules. Particularly, a spectral–spatial module with a 3D convolutional layer extracts the spectral–spatial features from the HSIs simultaneously, whilst a temporal module with ConvLSTM records and analyzes the multi-temporal HSI change information. The study first proposed a simple and effective method to generate samples for network training. This method can be applied effectively to cases with no training samples. Re3FCN can perform end-to-end detection for binary and multiple changes. Moreover, Re3FCN can receive multi-temporal HSIs directly as input without learning the characteristics of multiple changes. Finally, the network could extract joint spectral–spatial–temporal features and it preserved the spatial structure during the learning process through the fully convolutional structure. This study was the first to use a 3D FCN and a ConvLSTM for the remote-sensing CD. To demonstrate the effectiveness of the proposed CD method, we performed binary and multi-class CD experiments. Results revealed that the Re3FCN outperformed the other conventional methods, such as change vector analysis, iteratively reweighted multivariate alteration detection, PCA-SCA, FCN, and the combination of 2D convolutional layers-fully connected LSTM.

Download Full-text

Mapping of ImageNet and Wikidata for Knowledge Graphs Enabled Computer Vision

Business Information Systems ◽

10.52825/bis.v1i.65 ◽

2021 ◽

pp. 151-161

Author(s):

Dominik Filipiak ◽

Anna Fensel ◽

Agata Filipowska

Keyword(s):

Computer Vision ◽

Performance Metrics ◽

Contextual Information ◽

Ground Truth ◽

Knowledge Graph ◽

Graph Structure ◽

Exact Match ◽

Ground Truth Data ◽

Final Performance ◽

Knowledge Graphs

Knowledge graphs are used as a source of prior knowledge in numerous computer vision tasks. However, such an approach requires to have a mapping between ground truth data labels and the target knowledge graph. We linked the ILSVRC 2012 dataset (often simply referred to as ImageNet) labels to Wikidata entities. This enables using rich knowledge graph structure and contextual information for several computer vision tasks, traditionally benchmarked with ImageNet and its variations. For instance, in few-shot learning classification scenarios with neural networks, this mapping can be leveraged for weight initialisation, which can improve the final performance metrics value. We mapped all 1000 ImageNet labels – 461 were already directly linked with the exact match property (P2888), 467 have exact match candidates, and 72 cannot be matched directly. For these 72 labels, we discuss different problem categories stemming from the inability of finding an exact match. Semantically close non-exact match candidates are presented as well. The mapping is publicly available athttps://github.com/DominikFilipiak/imagenet-to-wikidata-mapping.

Download Full-text

An Urban Flooding Index for Unsupervised Inundated Urban Area Detection Using Sentinel-1 Polarimetric SAR Images

Remote Sensing ◽

10.3390/rs13224511 ◽

2021 ◽

Vol 13 (22) ◽

pp. 4511

Author(s):

Hui Zhang ◽

Zhixin Qi ◽

Xia Li ◽

Yimin Chen ◽

Xianwei Wang ◽

...

Keyword(s):

Urban Area ◽

Urban Areas ◽

Ground Truth ◽

Detection Accuracy ◽

Urban Flooding ◽

Polarimetric Sar ◽

Sar Images ◽

Ground Truth Data ◽

Optical Images ◽

Coefficient Increase

Urban flooding causes a variation in radar return from urban areas. However, such variation has not been thoroughly examined for different polarizations because of the lack of polarimetric SAR (PolSAR) images and ground truth data simultaneously collected over flooded urban areas. This condition hinders not only the understanding of the effect mechanism of urban flooding under different polarizations but also the development of advanced methods that could improve the accuracy of inundated urban area detection. Using Sentinel-1 PolSAR and Jilin-1 high-resolution optical images acquired on the same day over flooded urban areas in Golestan, Iran, this study investigated the characteristics and mechanisms of the radar return changes induced by urban flooding under different polarizations and proposed a new method for unsupervised inundated urban area detection. This study found that urban flooding caused a backscattering coefficient increase (BCI) and interferometric coherence decrease (ICD) in VV and VH polarizations. Furthermore, VV polarization was more sensitive to the BCI and ICD than VH polarization. In light of these findings, the ratio between the BCI and ICD was defined as an urban flooding index (UFI), and the UFI in VV polarization was used for the unsupervised detection of flooded urban areas. The overall accuracy, detection accuracy, and false alarm rate attained by the UFI-based method were 96.93%, 91.09%, and 0.95%, respectively. Compared with the conventional unsupervised method based on the ICD and that based on the fusion of backscattering coefficients and interferometric coherences (FBI), the UFI-based method achieved higher overall accuracy. The performance of VV was evaluated and compared to that of VH in the flooded urban area detection using the UFI-, ICD-, and FBI-based methods, respectively. VV polarization produced higher overall accuracy than VH polarization in all the methods, especially in the UFI-based method. By using VV instead of VH polarization, the UFI-based method improved the detection accuracy by 38.16%. These results indicated that the UFI-based method improved flooded urban area detection by synergizing the BCI and ICD in VV polarization.

Download Full-text

ASSESSMENT OF LAND USE AND LAND COVER CHANGE DETECTION BY USING REMOTE SENSING AND GIS TECHNIQUES IN THE COASTAL DESERTS, SOUTH OF IRAN

ISPRS - International Archives of the Photogrammetry, Remote Sensing and Spatial Information Sciences ◽

10.5194/isprs-archives-xlii-4-w18-489-2019 ◽

2019 ◽

Vol XLII-4/W18 ◽

pp. 489-492

Author(s):

S. A. R. Hosseini ◽

H. Gholami ◽

Y. Esmaeilpoor

Keyword(s):

Remote Sensing ◽

Land Use ◽

Land Cover ◽

Change Detection ◽

Urban Areas ◽

Ground Truth ◽

Landsat Images ◽

Ground Truth Data ◽

Sensing Technology ◽

Time Period

Abstract. Land use/land cover (LULC) changes have become a central issue in current global change and sustainability research. Due to the large expanse of land change detection by the traditional methods is not sufficient and efficient; therefore, using of new methods such as remote sensing technology is necessary and vital This study evaluates LULC change in chabahar and konarak Coastal deserts, located in south of sistan and baluchestan province from 1988 to 2018 using Landsat images. Maximum likelihood classification were used to develop LULC maps. The change detection was executed using post-classification comparison and GIS. Then, taking ground truth data, the classified maps accuracy were assessed by calculating the Kappa coefficient and overall accuracy. The results for the time period of 1988–2018 are presented. Based on the results of the 30-year time period, vegetation has been decreased in area while urban areas have been developed. The area of saline and sandy lands has also increased.

Download Full-text

Copernicus Sentinel imagery for more risk-resilient historic cities in coastal zones: contribution to the monitoring of Albenga archaeological site and delta of river Centa

Applied Geomatics ◽

10.1007/s12518-020-00340-5 ◽

2020 ◽

Author(s):

Branka Cuca

Keyword(s):

Risk Assessment ◽

Change Detection ◽

Ground Truth ◽

Archaeological Site ◽

Coastal Zones ◽

Ground Truth Data ◽

Heritage Sites ◽

Flooding Hazard ◽

Medieval Church ◽

Extreme Flooding

Abstract Earth observation (EO) technologies and products are traditionally providing an extremely important contribution to a more efficient management of built areas and people during emergencies. Their employment could be extremely useful in monitoring and risk assessment of protected monument and sites situated in potentially vulnerable areas such as costal zones. Change detection has a crucial role in such activities, especially in case of hazardous events—on one side, this method can provide inputs in the phases of risk assessment and rapid mapping for immediate response; on the other side, over prolonged periods of time after the event, change detection can be used for purposes of option analysis of technical solutions and for overall recovery planning of the site. Workflow proposed is based on the use of Copernicus Sentinel-2 data to provide the comparison of changes occurring during extreme flooding events of river Centa, Liguria. Firstly, an investigation of NDVI and NDWI of the extreme flooding event occurring in November 2019 was conducted. The event was then put in correlation with another previously studied flooding hazard occurring in 2016 in the same area that has caused severe damages to the archaeological remains of the medieval church of San Clemente, situated within the Centa riverbed. In conclusion, the results from both years have been compared with ground truth data of topographic database in order to observe the extension of the flooded area and to provide contribution to the monitoring activities. The aim of the research was to offer some novel insight for a more informed decision-making during the risk assessment, risk management and resilience phases regarding the vulnerable built heritage sites found in coastal areas.

Download Full-text

Assessment of Forest above Ground Biomass Estimation Using Multi-Temporal C-band Sentinel-1 and Polarimetric L-band PALSAR-2 Data

Remote Sensing ◽

10.3390/rs10091424 ◽

2018 ◽

Vol 10 (9) ◽

pp. 1424 ◽

Cited By ~ 16

Author(s):

Xiaodong Huang ◽

Beth Ziniti ◽

Nathan Torbick ◽

Mark Ducey

Keyword(s):

Optical Sensors ◽

Forest Canopy ◽

Alpha Angle ◽

Ground Truth ◽

Biomass Estimation ◽

Above Ground Biomass ◽

Ground Truth Data ◽

Ground Biomass ◽

Multi Temporal ◽

L Band

Synthetic Aperture Radar (SAR), as an active sensor transmitting long wavelengths, has the advantages of working day and night and without rain or cloud disturbance. It is further able to sense the geometric structure of forests more than passive optical sensors, making it a valuable tool for mapping forest Above Ground Biomass (AGB). This paper studies the ability of the single- and multi-temporal C-band Sentinel-1 and polarimetric L-band PALSAR-2 data to estimate live AGB based on ground truth data collected in New England, USA in 2017. Comparisons of results using the Simple Water Cloud Model (SWCM) on both VH and VV polarizations show that C-band reaches saturation much faster than the L-band due to its limited forest canopy penetration. The exhaustive search multiple linear regression model over the many polarimetric parameters from PALSAR-2 data shows that the combination of polarimetric parameters could slightly improve the AGB estimation, with an adjusted R2 as high as 0.43 and RMSE of around 70 Mg/ha when decomposed Pv component and Alpha angle are used. Additionally, the single- and multi-temporal C-band Sentinel-1 data are compared, which demonstrates that the multi-temporal Sentinel-1 significantly improves the AGB estimation, but still has a much lower adjusted R2 due to the limitations of the short wavelength. Finally, a site-level comparison between paired control and treatment sites shows that the L-band aligns better with the ground truth than the C-band, showing the high potential of the models to be applied to relative biomass change detection.

Download Full-text

Earthquake-Induced Landslide Mapping for the 2018 Hokkaido Eastern Iburi Earthquake Using PALSAR-2 Data

Remote Sensing ◽

10.3390/rs11202351 ◽

2019 ◽

Vol 11 (20) ◽

pp. 2351 ◽

Cited By ~ 3

Author(s):

Yusupujiang Aimaiti ◽

Wen Liu ◽

Fumio Yamazaki ◽

Yoshihisa Maruyama

Keyword(s):

Synthetic Aperture Radar ◽

Ground Truth ◽

Weather Conditions ◽

Synthetic Aperture ◽

Ground Truth Data ◽

Active Sensor ◽

Optical Images ◽

Comparison Results ◽

Landslide Mapping ◽

Aperture Radar

Timely information about landslides during or immediately after an event is an invaluable source for emergency response and management. Using an active sensor, synthetic aperture radar (SAR) can capture images of the earth’s surface regardless of weather conditions and may provide a solution to the problem of mapping landslides when clouds obstruct optical imaging. The 2018 Hokkaido Eastern Iburi earthquake (Mw 6.6) and its aftershocks not only caused major damage with severe loss of life and property but also induced many landslides across the area. To gain a better understanding of the landslides induced by this earthquake, we proposed a method of landslide mapping using pre- and post-event Advanced Land Observation Satellite 2 Phased Array L-band Synthetic Aperture Radar 2 (ALOS-2 PALSAR-2) images acquired from both descending and ascending orbits. Moreover, the accuracy of the classification results was verified by comparisons with high-resolution optical images, and ground truth data (provided by GSI, Japan). The detected landslides show a good match with the reference optical images by visual comparison. The quantitative comparison results showed that a combination of the descending and ascending intensity-based landslide classification had the best accuracy with an overall accuracy and kappa coefficient of 80.1% and 0.45, respectively.

Download Full-text

Individual Building Rooftop and Tree Crown Segmentation from High-Resolution Urban Aerial Optical Images

Journal of Sensors ◽

10.1155/2016/1795205 ◽

2016 ◽

Vol 2016 ◽

pp. 1-13 ◽

Cited By ~ 1

Author(s):

Jichao Jiao ◽

Zhongliang Deng

Keyword(s):

Cost Function ◽

Tree Height ◽

Salient Feature ◽

Ground Truth ◽

Aerial Photographs ◽

Ground Truth Data ◽

Optical Images ◽

Trained Classifier ◽

The Cost ◽

Good Agreement

We segment buildings and trees from aerial photographs by using superpixels, and we estimate the tree’s parameters by using a cost function proposed in this paper. A method based on image complexity is proposed to refine superpixels boundaries. In order to classify buildings from ground and classify trees from grass, the salient feature vectors that include colors, Features from Accelerated Segment Test (FAST) corners, and Gabor edges are extracted from refined superpixels. The vectors are used to train the classifier based on Naive Bayes classifier. The trained classifier is used to classify refined superpixels as object or nonobject. The properties of a tree, including its locations and radius, are estimated by minimizing the cost function. The shadow is used to calculate the tree height using sun angle and the time when the image was taken. Our segmentation algorithm is compared with other two state-of-the-art segmentation algorithms, and the tree parameters obtained in this paper are compared to the ground truth data. Experiments show that the proposed method can segment trees and buildings appropriately, yielding higher precision and better recall rates, and the tree parameters are in good agreement with the ground truth data.

Download Full-text

SENTINEL-1 BASED FLOOD MAPPING USING INTERFEROMETRIC COHERENCE AND INTENSITY CHANGE DETECTION APPROACH

ISPRS - International Archives of the Photogrammetry, Remote Sensing and Spatial Information Sciences ◽

10.5194/isprs-archives-xliii-b3-2020-1697-2020 ◽

2020 ◽

Vol XLIII-B3-2020 ◽

pp. 1697-1703

Author(s):

I. Papila ◽

U. Alganci ◽

E. Sertel

Keyword(s):

Change Detection ◽

Urban Areas ◽

Satellite Image ◽

Region Growing ◽

Ground Truth ◽

Intensity Change ◽

Flood Mapping ◽

Satellite Mission ◽

Ground Truth Data ◽

Sar Data

Abstract. This study presents a semi-automatic algorithm for mapping floods. Both Optical and Synthetic Aperture Radar (SAR) data are used to observe the flood that hit the Cukurova region of Adana (Turkey) in 2019. The performance of the interferometric coherence in complementing intensity component of SAR data is investigated for mapping the floods occurred in agricultural and urban environments. There was no ground truth data available from the flooded area, thus classification result of optical satellite image is used as a seed for the region growing algorithm that defines the classes according to a threshold value. The advantage of using both intensity and coherence change detection is verified with the results. The results have been evaluated through very high-resolution SPOT-6 optical image which acquired simultaneously with Sentinel-1B SAR image. The comparison with the SPOT-6 data results shows that the proposed approach can map flooded areas with acceptable accuracy using the SAR data from Sentinel-1 satellite mission. Highly affected agricultural areas along with the river line could be mapped both by optical and SAR analysis. Comparison of results from VV and VH polarization provided that cross-polarization VH has a very little effect on flood mapping. The proposed algorithm successfully distinguishes the classes among the affected region, especially in urban areas.

Download Full-text

Vegetation cover change detection and assessment in arid environment using multi-temporal remote sensing images and ecosystem management approach

Solid Earth ◽

10.5194/se-7-713-2016 ◽

2016 ◽

Vol 7 (2) ◽

pp. 713-725 ◽

Cited By ~ 17

Author(s):

Anwar Abdelrahman Aly ◽

Abdulrasoul Mosa Al-Omran ◽

Abdulazeam Shahwan Sallam ◽

Mohammad Ibrahim Al-Wabel ◽

Mohammad Shayaa Al-Shayaa

Keyword(s):

Remote Sensing ◽

Change Detection ◽

Ecosystem Management ◽

Vegetation Cover ◽

Secondary Data ◽

Ground Truth ◽

Management Approach ◽

Landsat Images ◽

Ground Truth Data ◽

Multi Temporal

Abstract. Vegetation cover (VC) change detection is essential for a better understanding of the interactions and interrelationships between humans and their ecosystem. Remote sensing (RS) technology is one of the most beneficial tools to study spatial and temporal changes of VC. A case study has been conducted in the agro-ecosystem (AE) of Al-Kharj, in the center of Saudi Arabia. Characteristics and dynamics of total VC changes during a period of 26 years (1987–2013) were investigated. A multi-temporal set of images was processed using Landsat images from Landsat4 TM 1987, Landsat7 ETM+2000, and Landsat8 to investigate the drivers responsible for the total VC pattern and changes, which are linked to both natural and social processes. The analyses of the three satellite images concluded that the surface area of the total VC increased by 107.4 % between 1987 and 2000 and decreased by 27.5 % between years 2000 and 2013. The field study, review of secondary data, and community problem diagnosis using the participatory rural appraisal (PRA) method suggested that the drivers for this change are the deterioration and salinization of both soil and water resources. Ground truth data indicated that the deteriorated soils in the eastern part of the Al-Kharj AE are frequently subjected to sand dune encroachment, while the southwestern part is frequently subjected to soil and groundwater salinization. The groundwater in the western part of the ecosystem is highly saline, with a salinity ≥ 6 dS m−1. The ecosystem management approach applied in this study can be used to alike AE worldwide.

Download Full-text