Automated Damage Indication for Rapid Geospatial Reporting

Tiede, Dirk; Lang, Stefan; Füreder, Petra; Hölbling, Daniel; Hoffmann, Christian; Zeil, Peter

doi:10.14358/pers.77.9.933

Cited by 44 publications

(17 citation statements)

References 17 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Speed and accuracy are important factors when dealing with big remote sensing data or time conditioned events (e.g., earthquakes, tsunamis, landslides, refugees, tornados, oil spills etc.) for damage, disaster, risk and crisis-management support [2,[41][42][43]. If a satellite image is increasing in landscape complexity, number of bands and extent, a high amount of time and computational resources are needed in order to automatically extract or classify features of interest.…”

Section: Introductionmentioning

confidence: 99%

Fast Segmentation and Classification of Very High Resolution Remote Sensing Data Using SLIC Superpixels

Csillik

2017

Remote Sensing

105

View full text Add to dashboard Cite

Speed and accuracy are important factors when dealing with time-constraint events for disaster, risk, and crisis-management support. Object-based image analysis can be a time consuming task in extracting information from large images because most of the segmentation algorithms use the pixel-grid for the initial object representation. It would be more natural and efficient to work with perceptually meaningful entities that are derived from pixels using a low-level grouping process (superpixels). Firstly, we tested a new workflow for image segmentation of remote sensing data, starting the multiresolution segmentation (MRS, using ESP2 tool) from the superpixel level and aiming at reducing the amount of time needed to automatically partition relatively large datasets of very high resolution remote sensing data. Secondly, we examined whether a Random Forest classification based on an oversegmentation produced by a Simple Linear Iterative Clustering (SLIC) superpixel algorithm performs similarly with reference to a traditional object-based classification regarding accuracy. Tests were applied on QuickBird and WorldView-2 data with different extents, scene content complexities, and number of bands to assess how the computational time and classification accuracy are affected by these factors. The proposed segmentation approach is compared with the traditional one, starting the MRS from the pixel level, regarding geometric accuracy of the objects and the computational time. The computational time was reduced in all cases, the biggest improvement being from 5 h 35 min to 13 min, for a WorldView-2 scene with eight bands and an extent of 12.2 million pixels, while the geometric accuracy is kept similar or slightly better. SLIC superpixel-based classification had similar or better overall accuracy values when compared to MRS-based classification, but the results were obtained in a fast manner and avoiding the parameterization of the MRS. These two approaches have the potential to enhance the automation of big remote sensing data analysis and processing, especially when time is an important constraint.

show abstract

Section: Introductionmentioning

confidence: 99%

Fast Segmentation and Classification of Very High Resolution Remote Sensing Data Using SLIC Superpixels

Csillik

2017

Remote Sensing

105

View full text Add to dashboard Cite

show abstract

“…Besides many advantages, this also comes with shortcomings, like the limited computational capabilities and a lack of powerful tools to handle the complexity of the data, especially when time is an important constrain in delivering of high quality geospatial information (e.g. Tiede et al, 2011).…”

Section: Introductionmentioning

confidence: 99%

Superpixels: the end of pixels in OBIA: A comparison of state-of-the-art superpixel methods for remote sensing data

Csillik¹

2016

GEOBIA 2016: Solutions and Synergies

View full text Add to dashboard Cite

ABSTRACT:In computer vision, using superpixels or perceptually meaningful atomic regions to speed up later-stage processing are becoming increasingly popular in many applications. Superpixels are used as a pre-processing stage to organize an image into a low-level grouping process through oversegmentation, thus simplifying the computation in later stages. However, in remote sensing domain few studies use superpixels. Even so, there is no comparison between superpixel methods and their suitability for remote sensing images. In this study, we compare four state-of-the-art superpixel methods: Simple Linear Iterative Clustering (SLIC and SLICO), Superpixels Extracted via Energy-Driven Sampling (SEEDS) and Linear Spectral Clustering (LSC). We applied them to very high resolution remote sensing data of different characteristics (extent, spatial resolution and landscape complexity) in order to see how superpixels are affected by these factors. The four algorithms were compared regarding their computational time, ability to adhere to image boundaries and the accuracy of the resulted superpixels. Furthermore, we discuss the individual strengths and weaknesses of each algorithm and draw further applications of superpixels in OBIA.

show abstract

“…As such, the method may be able to provide useful accuracy information for key Digital Earth applications such as building damage mapping to inform post-disaster response activities. It must be stressed that no criticism of the different maps or their producer's is intended, the maps have value beyond the issue considered here and may well be of different quality in other parts of the affected area (Hisada, Shibaya, and Ghayamghamian 2004;Tiede et al 2011). The key concern is that on the one specific issue considered, the detection of severely damaged buildings, there was a marked difference in the accuracy with which the maps represented the sample of cases.…”

Section: Resultsmentioning

confidence: 98%

“…Here, five building damage maps focused on Port-au-Prince were used and compared against the results of a ground-based survey that visited 98 buildings in the city to provide a reference data-set. A detailed description of each map is beyond the scope of this article, but the key details and an indicative reference for each of the five maps used are: (map a) a map derived from oblique, multi-perspective airborne imagery (Gerke and Kerle 2011; the data used here were downloaded from http://www.istructe.org/resources-centre/ technical-topic-areas/eefit/haiti-photo-archive); (map b) a map derived through the activities of the Global Earth Observation -Catastrophe Assessment Network which used inputs from over 600 people in 23 countries (van Aardt et al 2011; the specific data used were downloaded from http://www.istructe.org/resources-centre/technical-topic-areas/ eefit/haiti-photo-archive); (map c) a map produced by the Centre for Satellite based Crisis Information (ZKI) by a team using visual interpretation of satellite sensor images (Voigt et al 2011; the specific data used were downloaded from http://www.zki.dlr.de/ article/1262); (map d) a map produced through the Global Monitoring for Environment and Security (GMES) Services for the Management of Operations, Situation Awareness and Intelligence for Regional Crisis (Tiede et al 2011; the specific data used were downloaded from http://spatial.telespazio.it/gmosaic_haiti/); and (map e) a map produced from WorldView-2 satellite and aerial survey imagery by the United Nations Institute for Training and Research's (UNITAR) Operational Satellite Applications Programme (UNOSAT) (Duda and Jones 2011; the specific data used were downloaded from http:// www.unitar.org/unosat/node/44/1424). The ground reference data for 98 buildings arises from a survey undertaken by The Earthquake Engineering Field Investigation Team (Booth, Saito, and Madabhushi 2010).…”

Section: Real Datamentioning

confidence: 99%

Rating crowdsourced annotations: evaluating contributions of variable quality and completeness

Foody

2013

International Journal of Digital Earth

View full text Add to dashboard Cite

Crowdsourcing has become a popular means to acquire data about the Earth and its environment inexpensively, but the data-sets obtained are typically imperfect and of unknown quality. Two common imperfections with crowdsourced data are the contributions from cheats or spammers and missing cases. The effect of the latter two imperfections on a method to evaluate the accuracy of crowdsourced data via a latent class model was explored. Using simulated and real data-sets, it was shown that the method is able to derive useful information on the accuracy of crowdsourced data even when the degree of imperfection was very high. The practical potential of this ability to obtain accuracy information within the geospatial sciences and the realm of Digital Earth applications was indicated with reference to an evaluation of building damage maps produced by multiple bodies after the 2010 earthquake in Haiti. Critically, the method allowed data-sets to be ranked in approximately the correct order of accuracy and this could help ensure that the most appropriate data-sets are used.

show abstract

Automated Damage Indication for Rapid Geospatial Reporting

Cited by 44 publications

References 17 publications

Fast Segmentation and Classification of Very High Resolution Remote Sensing Data Using SLIC Superpixels

Fast Segmentation and Classification of Very High Resolution Remote Sensing Data Using SLIC Superpixels

Superpixels: the end of pixels in OBIA: A comparison of state-of-the-art superpixel methods for remote sensing data

Rating crowdsourced annotations: evaluating contributions of variable quality and completeness

Contact Info

Product

Resources

About