Statistical modelling for enhanced outlier detection (bibtex)

by N. Piotto, G. Cordara

Abstract:

Matching of local features is an uncertain process which may provide wrong associations due to several reasons that include, among other factors, the uncertainty in locating the keypoint position. Since the statistics of the Log Distance Ratio (LDR) for pairs of incorrect matches are significantly different from those of correct matches, we propose a noniterative scheme for outlier detection that includes in the distance calculation the location uncertainty of the keypoint, specifically modeled by a covariance matrix: the LDR is then evaluated relying on Mahalanobis distance. By statistically modeling the wrong associations, inlier matches can thus be rapidly identified by solving an eigenvalue problem. The method is general enough to be applied both in 2D (i.e., texture) and 3D (i.e., texture + depth) scenarios. The effectiveness of the proposed method is assessed in the field of RGB-D SLAM, showing significant improvements with respect to state of the art methods.

Reference:

N. Piotto, G. Cordara, "Statistical modelling for enhanced outlier detection", In Image Processing (ICIP), 2014 IEEE International Conference on, pp. 4280-4284, 2014.

Bibtex Entry:

@INPROCEEDINGS{2014-10-7025869, author={Piotto, N. and Cordara, G.}, booktitle={Image Processing (ICIP), 2014 IEEE International Conference on}, title={Statistical modelling for enhanced outlier detection}, year={2014}, month={Oct}, pages={4280-4284}, abstract={Matching of local features is an uncertain process which may provide wrong associations due to several reasons that include, among other factors, the uncertainty in locating the keypoint position. Since the statistics of the Log Distance Ratio (LDR) for pairs of incorrect matches are significantly different from those of correct matches, we propose a noniterative scheme for outlier detection that includes in the distance calculation the location uncertainty of the keypoint, specifically modeled by a covariance matrix: the LDR is then evaluated relying on Mahalanobis distance. By statistically modeling the wrong associations, inlier matches can thus be rapidly identified by solving an eigenvalue problem. The method is general enough to be applied both in 2D (i.e., texture) and 3D (i.e., texture + depth) scenarios. The effectiveness of the proposed method is assessed in the field of RGB-D SLAM, showing significant improvements with respect to state of the art methods.}, keywords={SLAM (robots);covariance matrices;eigenvalues and eigenfunctions;feature extraction;image matching;image texture;statistical analysis;2D scenario;3D scenario;LDR statistics;Mahalanobis distance;RGB-D SLAM;covariance matrix;distance calculation;eigenvalue problem;enhanced outlier detection;keypoint location uncertainty;local feature matching;log distance ratio statistics;noniterative scheme;simultaneous localization and mapping;statistical modelling;Covariance matrices;Estimation;Feature extraction;Simultaneous localization and mapping;Three-dimensional displays;Uncertainty;Visualization;RGB-D SLAM;feature matching;outlier detection;pose estimation}, doi={10.1109/ICIP.2014.7025869}, }