Statistic tests aided multi-source DEM fusion

C. Y. Fu, Jaan-Rong Tsay

Research output: Contribution to journalConference article

1 Citation (Scopus)

Abstract

Since the land surface has been changing naturally or manually, DEMs have to be updated continually to satisfy applications using the latest DEM at present. However, the cost of wide-area DEM production is too high. DEMs, which cover the same area but have different quality, grid sizes, generation time or production methods, are called as multi-source DEMs. It provides a solution to fuse multi-source DEMs for low cost DEM updating. The coverage of DEM has to be classified according to slope and visibility in advance, because the precisions of DEM grid points in different areas with different slopes and visibilities are not the same. Next, difference DEM (dDEM) is computed by subtracting two DEMs. It is assumed that dDEM, which only contains random error, obeys normal distribution. Therefore, student test is implemented for blunder detection and three kinds of rejected grid points are generated. First kind of rejected grid points is blunder points and has to be eliminated. Another one is the ones in change areas, where the latest data are regarded as their fusion result. Moreover, the DEM grid points of type I error are correct data and have to be reserved for fusion. The experiment result shows that using DEMs with terrain classification can obtain better blunder detection result. A proper setting of significant levels (a) can detect real blunders without creating too many type I errors. Weighting averaging is chosen as DEM fusion algorithm. The priori precisions estimated by our national DEM production guideline are applied to define weights. Fisher's test is implemented to prove that the priori precisions correspond to the RMSEs of blunder detection result.

Original languageEnglish
Pages (from-to)227-233
Number of pages7
JournalInternational Archives of the Photogrammetry, Remote Sensing and Spatial Information Sciences - ISPRS Archives
Volume41
DOIs
Publication statusPublished - 2016 Jan 1
Event23rd International Archives of the Photogrammetry, Remote Sensing and Spatial Information Sciences Congress, ISPRS 2016 - Prague, Czech Republic
Duration: 2016 Jul 122016 Jul 19

Fingerprint

digital elevation model
Fusion reactions
statistics
Statistics
Visibility
Random errors
Electric fuses
Normal distribution
production method
Costs
visibility
costs
weighting
Students
coverage
generation time
test
present
experiment
cost

All Science Journal Classification (ASJC) codes

  • Information Systems
  • Geography, Planning and Development

Cite this

@article{37317e406f754eb7aa0fd602c91f1916,
title = "Statistic tests aided multi-source DEM fusion",
abstract = "Since the land surface has been changing naturally or manually, DEMs have to be updated continually to satisfy applications using the latest DEM at present. However, the cost of wide-area DEM production is too high. DEMs, which cover the same area but have different quality, grid sizes, generation time or production methods, are called as multi-source DEMs. It provides a solution to fuse multi-source DEMs for low cost DEM updating. The coverage of DEM has to be classified according to slope and visibility in advance, because the precisions of DEM grid points in different areas with different slopes and visibilities are not the same. Next, difference DEM (dDEM) is computed by subtracting two DEMs. It is assumed that dDEM, which only contains random error, obeys normal distribution. Therefore, student test is implemented for blunder detection and three kinds of rejected grid points are generated. First kind of rejected grid points is blunder points and has to be eliminated. Another one is the ones in change areas, where the latest data are regarded as their fusion result. Moreover, the DEM grid points of type I error are correct data and have to be reserved for fusion. The experiment result shows that using DEMs with terrain classification can obtain better blunder detection result. A proper setting of significant levels (a) can detect real blunders without creating too many type I errors. Weighting averaging is chosen as DEM fusion algorithm. The priori precisions estimated by our national DEM production guideline are applied to define weights. Fisher's test is implemented to prove that the priori precisions correspond to the RMSEs of blunder detection result.",
author = "Fu, {C. Y.} and Jaan-Rong Tsay",
year = "2016",
month = "1",
day = "1",
doi = "10.5194/isprsarchives-XLI-B6-227-2016",
language = "English",
volume = "41",
pages = "227--233",
journal = "International Archives of the Photogrammetry, Remote Sensing and Spatial Information Sciences - ISPRS Archives",
issn = "1682-1750",

}

TY - JOUR

T1 - Statistic tests aided multi-source DEM fusion

AU - Fu, C. Y.

AU - Tsay, Jaan-Rong

PY - 2016/1/1

Y1 - 2016/1/1

N2 - Since the land surface has been changing naturally or manually, DEMs have to be updated continually to satisfy applications using the latest DEM at present. However, the cost of wide-area DEM production is too high. DEMs, which cover the same area but have different quality, grid sizes, generation time or production methods, are called as multi-source DEMs. It provides a solution to fuse multi-source DEMs for low cost DEM updating. The coverage of DEM has to be classified according to slope and visibility in advance, because the precisions of DEM grid points in different areas with different slopes and visibilities are not the same. Next, difference DEM (dDEM) is computed by subtracting two DEMs. It is assumed that dDEM, which only contains random error, obeys normal distribution. Therefore, student test is implemented for blunder detection and three kinds of rejected grid points are generated. First kind of rejected grid points is blunder points and has to be eliminated. Another one is the ones in change areas, where the latest data are regarded as their fusion result. Moreover, the DEM grid points of type I error are correct data and have to be reserved for fusion. The experiment result shows that using DEMs with terrain classification can obtain better blunder detection result. A proper setting of significant levels (a) can detect real blunders without creating too many type I errors. Weighting averaging is chosen as DEM fusion algorithm. The priori precisions estimated by our national DEM production guideline are applied to define weights. Fisher's test is implemented to prove that the priori precisions correspond to the RMSEs of blunder detection result.

AB - Since the land surface has been changing naturally or manually, DEMs have to be updated continually to satisfy applications using the latest DEM at present. However, the cost of wide-area DEM production is too high. DEMs, which cover the same area but have different quality, grid sizes, generation time or production methods, are called as multi-source DEMs. It provides a solution to fuse multi-source DEMs for low cost DEM updating. The coverage of DEM has to be classified according to slope and visibility in advance, because the precisions of DEM grid points in different areas with different slopes and visibilities are not the same. Next, difference DEM (dDEM) is computed by subtracting two DEMs. It is assumed that dDEM, which only contains random error, obeys normal distribution. Therefore, student test is implemented for blunder detection and three kinds of rejected grid points are generated. First kind of rejected grid points is blunder points and has to be eliminated. Another one is the ones in change areas, where the latest data are regarded as their fusion result. Moreover, the DEM grid points of type I error are correct data and have to be reserved for fusion. The experiment result shows that using DEMs with terrain classification can obtain better blunder detection result. A proper setting of significant levels (a) can detect real blunders without creating too many type I errors. Weighting averaging is chosen as DEM fusion algorithm. The priori precisions estimated by our national DEM production guideline are applied to define weights. Fisher's test is implemented to prove that the priori precisions correspond to the RMSEs of blunder detection result.

UR - http://www.scopus.com/inward/record.url?scp=84979555755&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=84979555755&partnerID=8YFLogxK

U2 - 10.5194/isprsarchives-XLI-B6-227-2016

DO - 10.5194/isprsarchives-XLI-B6-227-2016

M3 - Conference article

AN - SCOPUS:84979555755

VL - 41

SP - 227

EP - 233

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

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

SN - 1682-1750

ER -