dc.contributor.author |
Αθανασάς, Κωνσταντίνος
|
el |
dc.contributor.author |
Athanasas, Konstantinos
|
en |
dc.date.accessioned |
2016-09-19T11:04:57Z |
|
dc.date.available |
2016-09-19T11:04:57Z |
|
dc.date.issued |
2016-09-19 |
|
dc.identifier.uri |
https://dspace.lib.ntua.gr/xmlui/handle/123456789/43583 |
|
dc.identifier.uri |
http://dx.doi.org/10.26240/heal.ntua.5835 |
|
dc.description |
Εθνικό Μετσόβιο Πολυτεχνείο--Μεταπτυχιακή Εργασία. Διεπιστημονικό-Διατμηματικό Πρόγραμμα Μεταπτυχιακών Σπουδών (Δ.Π.Μ.Σ.) “Γεωπληροφορική” |
el |
dc.rights |
Default License |
|
dc.subject |
Impact craters |
en |
dc.subject |
Circular Hough transform |
en |
dc.subject |
Determinant of Hessian |
en |
dc.subject |
Spacescale |
en |
dc.subject |
Μετεωρητικοί κρατήρες |
el |
dc.subject |
Ανίχνευση ακμών |
el |
dc.subject |
Ανίχνευση περιοχών |
el |
dc.subject |
Ορίζουσα του Εσσιανού πίνακα |
el |
dc.title |
Probing the potential of conventional computer vision operators for the detection of meteor craters on a Martian digital terrain model |
en |
heal.type |
masterThesis |
|
heal.secondaryTitle |
Διερεύνηση της δυνατότητας τελεστών τεχνητής όρασης για την
ανίχνευση μετεωρητικών κρατήρων σε ψηφιακό μοντέλο εδάφους του πλανήτη Άρη |
el |
heal.classification |
Γεωπληροφορική |
el |
heal.classificationURI |
http://data.seab.gr/concepts/0470dde7ed974578bbc4961549816f7b254efcb2 |
|
heal.language |
en |
|
heal.access |
free |
|
heal.recordProvider |
ntua |
el |
heal.publicationDate |
2016-03-30 |
|
heal.abstract |
This study explores the performance of two different computer-vision approaches,namely the circular Hough transform (CHT) and the determinant of Hessian (DoH), to crater detection on a digital terrain model of planet Mars. CHT exploits the edges of
circular features such as craters, revealed after several steps of image processing.
However, the performance of the standard version of CHT on the Martian digital terrain model generated poor results as the interference of noise from irrelevant features
persistent in the processed DTM generated numerous false responses. On the other hand,published adaptations of CHT engaging additional labor to isolate much of the influence
of noise were deemed as impractical for routine crater detection.
As a substitute, DoH was successful in detecting the overwhelming majority of the
craters appearing on a horizontal Martian terrain. The percentage of success deteriorated
as topographically more complex surfaces were encompassed. Even though, DoH scored
higher than CHT despite the perplexity because DoH proved to be less sensitive to the
noise than CHT. Current results, although not optimal, encourage future research to
improving the performance of DoH for routine crater detection undertakings. |
en |
heal.advisorName |
Αργιαλάς, Δημήτριος |
el |
heal.committeeMemberName |
Αργιαλάς, Δημήτριος |
el |
heal.committeeMemberName |
Καράντζαλος, Κωνσταντίνος |
el |
heal.committeeMemberName |
Σακελλαρίου, Μιχαήλ |
el |
heal.academicPublisher |
Εθνικό Μετσόβιο Πολυτεχνείο. Σχολή Αγρονόμων και Τοπογράφων Μηχανικών |
el |
heal.academicPublisherID |
ntua |
|
heal.numberOfPages |
64 σ. |
el |
heal.fullTextAvailability |
true |
|