Fabio Bellavia

Robust Selective Stereo SLAM without Loop Closure and Bundle Adjustment

This paper presents a novel stereo SLAM framework, where a robust loop chain matching scheme for tracking keypoints is combined with an effective frame selection strategy. The proposed approach, referred to as selective SLAM (SSLAM), relies on the observation that the error in the pose estimation propagates from the uncertainty of the three-dimensional points. This is higher for distant points, corresponding to matches with low temporal flow disparity in the images. Comparative results based on the reference KITTI evaluation framework show that SSLAM is effective and can be implemented efficiently, as it does not require any loop closure or bundle adjustment.

Improving SIFT-based Descriptors Stability to Rotations

Image descriptors are widely adopted structures to match image features. SIFT-based descriptors are collections of gradient orientation histograms computed on different feature regions, commonly divided by using a regular Cartesian grid or a log-polar grid. In order to achieve rotation invariance, feature patches have to be generally rotated in the direction of the dominant gradient orientation. In this paper we present a modification of the GLOH descriptor, a SIFT-based descriptor based on a log-polar grid, which avoids to rotate the feature patch before computing the descriptor since predefined discrete orientations can be easily derived by shifting the descriptor vector. The proposed descriptors, called sGLOH and sGLOH+, have been compared with the SIFT descriptor on the Oxford image dataset, with good results which point out its robustness and stability.

Keypoint descriptor matching with context-based orientation estimation ☆

Abstract This paper presents a matching strategy to improve the discriminative power of histogram-based keypoint descriptors by constraining the range of allowable dominant orientations according to the context of the scene under observation. This can be done when the descriptor uses a circular grid and quantized orientation steps, by computing or providing a global reference orientation based on the feature matches. The proposed matching strategy is compared with the standard approaches used with the SIFT and GLOH descriptors and the recent rotation invariant MROGH and LIOP descriptors. A new evaluation protocol based on an approximated overlap error is presented to provide an effective analysis in the case of non-planar scenes, thus extending the current state-of-the-art results.

Selective visual odometry for accurate AUV localization

In this paper we present a stereo visual odometry system developed for autonomous underwater vehicle localization tasks. The main idea is to make use of only highly reliable data in the estimation process, employing a robust keypoint tracking approach and an effective keyframe selection strategy, so that camera movements are estimated with high accuracy even for long paths. Furthermore, in order to limit the drift error, camera pose estimation is referred to the last keyframe, selected by analyzing the feature temporal flow. The proposed system was tested on the KITTI evaluation framework and on the New Tsukuba stereo dataset to assess its effectiveness on long tracks and different illumination conditions. Results of a live archaeological campaign in the Mediterranean Sea, on an AUV equipped with a stereo camera pair, show that our solution can effectively work in underwater environments.

A non-parametric segmentation methodology for oral videocapillaroscopic images

We aim to describe a new non-parametric methodology to support the clinician during the diagnostic process of oral videocapillaroscopy to evaluate peripheral microcirculation. Our methodology, mainly based on wavelet analysis and mathematical morphology to preprocess the images, segments them by minimizing the within-class luminosity variance of both capillaries and background. Experiments were carried out on a set of real microphotographs to validate this approach versus handmade segmentations provided by physicians. By using a leave-one-patient-out approach, we pointed out that our methodology is robust, according to precision-recall criteria (average precision and recall are equal to 0.924 and 0.923, respectively) and it acts as a physician in terms of the Jaccard index (mean and standard deviation equal to 0.858 and 0.064, respectively).

A non-parametric scale-based corner detector

This paper introduces a new Harris-affine corner detector algorithm, that does not need parameters to locate corners in images, given an observation scale. Standard detectors require to fine tune the values of parameters which strictly depend on the particular input image. A quantitative comparison between our implementation and a standard Harris-affine implementation provides good results, showing that the proposed methodology is robust and accurate. The benchmark consists of public images used in literature for feature detection.

Semi-automatic registration of retinal images based on line matching approach

Accurate retinal image registration is essential to track the evolution of eye-related diseases. We propose a semiautomatic method based on features relying upon retinal graphs for temporal registration of retinal images. The features represent straight lines connecting vascular landmarks on the retina vascular tree: bifurcations, branchings, crossings, end points. In the built retinal graph, one straight line between two vascular landmarks indicates that they are connected by a vascular segment in the original retinal image. The locations of the landmarks are manually extracted to avoid the information loss due to errors in a retinal vessels segmentation algorithms. A straight line model is designed to compute a similarity measure to quantify the line matching between images. From the set of matching lines, corresponding points are extracted and a global transformation is computed. The performance of the registration method is evaluated in the absence of ground truth using the cumulative inverse consistency error (CICE).

noRANSAC for fundamental matrix estimation

The estimation of the fundamental matrix from a set of corresponding points is a relevant topic in epipolar stereo geometry [10]. Due to the high amount of outliers between the matches, RANSAC-based approaches [7, 13, 29] have been used to obtain the fundamental matrix. In this paper two new contributes are presented: a new normalized epipolar error measure which takes into account the shape of the features used as matches [17] and a new strategy to compare fundamental matrices. The proposed error measure gives good results and it does not depend on the image scale. Moreover, the new evaluation strategy describes a valid tool to compare diffe rent RANSAC-based methods because it does not rely on the inlier ratio, which could not c orrespond to the best allowable fundamental matrix estimated model, but it makes use of a reference ground truth fundamental matrix obtained by a set of corresponding points given by the user.

Accurate keyframe selection and keypoint tracking for robust visual odometry

This paper presents a novel stereo visual odometry (VO) framework based on structure from motion, where a robust keypoint tracking and matching is combined with an effective keyframe selection strategy. In order to track and find correct feature correspondences a robust loop chain matching scheme on two consecutive stereo pairs is introduced. Keyframe selection is based on the proportion of features with high temporal disparity. This criterion relies on the observation that the error in the pose estimation propagates from the uncertainty of 3D points—higher for distant points, that have low 2D motion. Comparative results based on three VO datasets show that the proposed solution is remarkably effective and robust even for very long path lengths.

Estimating the Best Reference Homography for Planar Mosaics From Videos

This paper proposes a novel strategy to find the best reference homography in mosaics from video sequences. The reference homography globally minimizes the distortions induced on each image frame by the mosaic homography itself. This method is designed for planar mosaics on which a bad choice of the first reference image frame can lead to severe distortions after concatenating several successive homographies. This often happens in the case of underwater mosaics with non-flat seabed and no georeferential information available. Given a video sequence of an almost planar surface, sub-mosaics with low distortions of temporally close image frames are computed and successively merged according to a hierarchical clustering procedure. A robust and effective feature tracker using an approximated global position map between image frames allows us to build the mosaic also between locally close but not temporally consecutive frames. Sub-mosaics are successively merged by concatenating their relative homographies with another reference homography which minimizes the distortion on each frame of the fused image. Experimental results on challenging real underwater videos show the validity of the proposed method.