Детайли за публикацията
(Publication details)

Autors: Christoff, N. V., Manolova, A. H.
Title: Feature extraction and classification using minimal curvature of 3D mesh for automatic crater detection
Keywords: Mars Orbiter Laser Altimeter, 3D mesh, automatic

Abstract: In this paper is examined the significance of tree classes of feature selection algorithms, extracted from 3D mesh data, generated from the Mars Orbiter Laser Altimeter (MOLA) for a classification task to automatically detect craters, while at the same time testing four classifiers. The key idea of this study is to study the discriminative power of the original values, hereafter called “pure” values, of a minimal curvature by only converting them to grey scale image. The experimental results with four different classifiers show that better accuracy results are obtained over the features selected from the grey scale image. It is employed technique from computer vision used for face detection in the task of crater detection.

References

  1. Barlow, N. G., 1988, Crater size-frequency distributions and a revised Martian relative chronology, Icarus, Volume 5 (2), pp. pp.285–305
  2. K. Di, W. Li, Z. Yue, Y. Sun, Y. Lui, 2014, A machine learning ap-proach to crater detection from topographic data, Advances in Space Research, Volume 54 (11), pp. pp. 2419-2429
  3. G. T. Vamshi, T. R. Martha, K. V. Kumar, 2016, An object-based classification method for automatic detection of lunar impact craters from topographic data, Advances in Space Research, Volume 57, pp. pp. 1978–1988
  4. J.R. Kim, J.Muller, S. van Gasselt, J.G. Morley, G. Neukum, 2005, Automated crater detection, a new tool for Mars cartography and chronology, Photogramm. Eng. Remote Sens., Volume 71(10), pp. pp.1205–1217

Issue
52nd International Scientific Conference on Information, Communication and Energy Systems and Technologies, 2017, Serbia,

Full text of the publication

Вид: пленарен доклад в международен форум, публикация в реферирано издание

Въведена от: доц. д-р Агата Христова Манолова