Post Disaster Mapping With Semantic Change Detection in Satellite Imagery

Gupta, Ananya; Welburn, Elisabeth; Watson, Simon; Yin, Hujun

doi:10.1109/cvprw.2019.00062

Cited by 28 publications

(26 citation statements)

References 9 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Once again, several precedents demonstrate the benefits of shared datasets for science and humanitarian monitoring. Among them are OpenStreetMap, a collaborative, editable geospatial database of roads, buildings, and infrastructure (Herfort et al, 2021); xBD, a large-scale training and validation data set for remote sensing-based building damage assessment (Gupta et al, 2019); and the Humanitarian Data Exchange (https://data.humdata.org), funded by the UN Office for the Coordination of Human Affairs. Using Ukraine as an example, a time series of VHR mosaics across the country-ideally spanning cross-border regions, too-could be generated at weekly or monthly timesteps to guide a multi-date analysis of conflict effects.…”

Section: Produce Nationwide Analysis-ready Vhr Mosaics To Harmonize W...mentioning

confidence: 99%

Improving Satellite Monitoring of Armed Conflicts

2022

View full text Add to dashboard Cite

Very‐high resolution (VHR) satellite imagery is increasingly used to visualize the effects of armed conflicts in near‐real time. Yet these data, typically commercial, are generally released selectively or for a fee, impeding scientific and humanitarian applications. Such images also tend to focus on cities or infrastructure, obscuring the effects of war in rural or sparsely populated areas such as forests. To leverage VHR imagery for improved and more holistic conflict monitoring, we call for (a) archiving VHR images for scientific and humanitarian use; (b) producing analysis‐ready, conflict‐wide VHR mosaics to harmonize monitoring; and (c) forming a sustainably funded public VHR satellite program. International coordination on such a satellite could also support the transformation of VHR Earth observation (EO) data into a public good. Taking these three steps promises to revolutionize conflict monitoring, much in the way that opening access to lower‐resolution EO data has stimulated new discoveries about the planet's ecosystems and human impacts. Broadening and standardizing access to and analysis of archived VHR imagery may improve understandings of war, empower and refine responses, and potentially, mitigate future conflicts.

show abstract

Section: Produce Nationwide Analysis-ready Vhr Mosaics To Harmonize W...mentioning

confidence: 99%

Improving Satellite Monitoring of Armed Conflicts

2022

View full text Add to dashboard Cite

show abstract

“…Automated road identification in post-disaster scenarios is a nascent topic with concurrent research [14]. Some work is based on identifying road obstacles such as fallen trees and standing water using vehicle trajectory data [7].…”

Section: Disaster Analysismentioning

confidence: 99%

CNN-Based Semantic Change Detection in Satellite Imagery

Gupta,

Welburn,

Watson

et al. 2020

Preprint

Self Cite

View full text Add to dashboard Cite

Timely disaster risk management requires accurate road maps and prompt damage assessment. Currently, this is done by volunteers manually marking satellite imagery of affected areas but this process is slow and often errorprone. Segmentation algorithms can be applied to satellite images to detect road networks. However, existing methods are unsuitable for disaster-struck areas as they make assumptions about the road network topology which may no longer be valid in these scenarios. Herein, we propose a CNN-based framework for identifying accessible roads in post-disaster imagery by detecting changes from predisaster imagery. Graph theory is combined with the CNN output for detecting semantic changes in road networks with OpenStreetMap data. Our results are validated with data of a tsunami-affected region in Palu, Indonesia acquired from DigitalGlobe.

show abstract

“…R EMOTE sensing image change detection targets finding the variable pixel-level regions between given two images, such as optical, multispectral, infrared, and synthetic aperture radar (SAR) images captured at long intervals [1]. It is one of the most important research topics in the pattern recognition and computer vision communities and has been widely used in many applications [2]- [5]. Although significant developments have been achieved, remote sensing change detection is still a challenging and difficult task due to the following two issues.…”

Section: Introductionmentioning

confidence: 99%

Partitioning and Migration of Trace Elements during Coal Combustion in Two Coal-Fired Power Plants in Hefei City, Anhui Province, Eastern China

Jiang

Chen

et al. 2023

Minerals

View full text Add to dashboard Cite

Coal-fired thermal power plants that meet the huge energy demand of China largely contribute to carbon emissions, environmental pollution, and human health issues. To investigate the impact of coal-fired power plants on the environment in the most developed region of eastern China, samples of feed coal, limestone, slag, fly ash, and flue gas desulfurization (FGD) gypsum were collected from two coal-fired power plants in Hefei City, Anhui Province, China. The concentrations of trace elements in these samples were determined using inductively coupled plasma mass spectrometry (ICP-MS). The results show that the feed coal was slightly rich in V, Cr, Se, In, Sb, Pb, and Ga compared to common Chinese coal. Most trace elements were concentrated in fly ash, especially in the fine particles. Only Sc, Cr, Rb, and Ba were enriched in slag. The smaller the particle size of the fly ash, the higher the fraction of volatile trace elements. The elemental concentrations of old fly ash, which was precipitated in the well of the flue gas pipeline, did not show noticeable differences from fresh fly ash. In addition, the short-time storage of fly ash did not influence the trace elements. To understand the possibility of recovering rare earth elements from coal combustion by-products, the outlook coefficients (Coutl) of coal combustion by-products for the Wanneng (WN) and Tianyuan (TY) power plants were calculated, and they were found to be promising for rare earth elements plus yttrium (REY) recovery. However, as per the evaluation diagram of cut-off grade and Coutl values, all feed coal and its by-products from these two coal-fired power plants are projected to be ‘unpromising’. Therefore, the coal combustion by-products from the WN and TY coal-fired power plants were not candidates for REY recovery.

show abstract

Post Disaster Mapping With Semantic Change Detection in Satellite Imagery

Cited by 28 publications

References 9 publications

Improving Satellite Monitoring of Armed Conflicts

Improving Satellite Monitoring of Armed Conflicts

CNN-Based Semantic Change Detection in Satellite Imagery

Partitioning and Migration of Trace Elements during Coal Combustion in Two Coal-Fired Power Plants in Hefei City, Anhui Province, Eastern China

Contact Info

Product

Resources

About