SoftPOSIT: Simultaneous Pose and Correspondence Determination
International Journal of Computer Vision
Distinctive Image Features from Scale-Invariant Keypoints
International Journal of Computer Vision
Pyramid segmentation algorithms revisited
Pattern Recognition
Journal of Field Robotics - Special Issue on Space Robotics, Part III
Image Matching for Geomorphic Measurement Based on SIFT and RANSAC Methods
CSSE '08 Proceedings of the 2008 International Conference on Computer Science and Software Engineering - Volume 02
Colour image segmentation using homogeneity method and data fusion techniques
EURASIP Journal on Advances in Signal Processing - Image processing and analysis in biomechanics
Hi-index | 0.00 |
In this paper we present a vision-based algorithm for estimating the absolute position of a lander, during the descent phase of a planetary exploration mission. A precise position estimation is required in order to avoid obstacles or to get close to scientifically interesting areas assessed on the basis of orbiter images. Lander position is estimated with respect to visual landmarks on planetary surface. The core of the algorithm is a novel technique for identifying candidate landmarks using a local homogeneity analysis. This analysis can identify fast homogeneity changes or wide-range texture similarities and exhibits a computational cost that is invariant with respect to the size of the window where the measure is computed. Moreover, homogeneity analysis offers a way for simultaneously taking into account heterogeneous features. The second contribution of this article is a general framework for position estimation based on landmarks, encoded by means of SURF descriptors. The relevance of the extracted features is increased in order to reduce the number of superfluous keypoints.