Herbert Bay

SURF: speeded up robust features

In this paper, we present a novel scale- and rotation-invariant interest point detector and descriptor, coined SURF (Speeded Up Robust Features). It approximates or even outperforms previously proposed schemes with respect to repeatability, distinctiveness, and robustness, yet can be computed and compared much faster. This is achieved by relying on integral images for image convolutions; by building on the strengths of the leading existing detectors and descriptors (in casu, using a Hessian matrix-based measure for the detector, and a distribution-based descriptor); and by simplifying these methods to the essential. This leads to a combination of novel detection, description, and matching steps. The paper presents experimental results on a standard evaluation set, as well as on imagery obtained in the context of a real-life object recognition application. Both show SURFs strong performance.

Speeded-Up Robust Features (SURF)

This article presents a novel scale- and rotation-invariant detector and descriptor, coined SURF (Speeded-Up Robust Features). SURF approximates or even outperforms previously proposed schemes with respect to repeatability, distinctiveness, and robustness, yet can be computed and compared much faster. This is achieved by relying on integral images for image convolutions; by building on the strengths of the leading existing detectors and descriptors (specifically, using a Hessian matrix-based measure for the detector, and a distribution-based descriptor); and by simplifying these methods to the essential. This leads to a combination of novel detection, description, and matching steps. The paper encompasses a detailed description of the detector and descriptor and then explores the effects of the most important parameters. We conclude the article with SURFs application to two challenging, yet converse goals: camera calibration as a special case of image registration, and object recognition. Our experiments underline SURFs usefulness in a broad range of topics in computer vision.

Wide-baseline stereo matching with line segments

We present a new method for matching line segments between two uncalibrated wide-baseline images. Most current techniques for wide-baseline matching are based on viewpoint invariant regions. Those methods work well with highly textured scenes, but fail with poorly textured ones. We show that such scenes can be successfully matched using line segments. Moreover, since line segments and regions provide complementary information, their combined matching allows to deal with a broader range of scenes. We generate an initial set of line segment correspondences, and then iteratively increase their number by adding matches consistent with the topological structure of the current ones. Finally, a coplanar grouping stage allows to estimate the fundamental matrix even from line segments only.

Retina mosaicing using local features

Laser photocoagulation is a proven procedure to treat various pathologies of the retina. Challenges such as motion compensation, correct energy dosage, and avoiding incidental damage are responsible for the still low success rate. They can be overcome with improved instrumentation, such as a fully automatic laser photocoagulation system. In this paper, we present a core image processing element of such a system, namely a novel approach for retina mosaicing. Our method relies on recent developments in region detection and feature description to automatically fuse retina images. In contrast to the state-of-the-art the proposed approach works even for retina images with no discernable vascularity. Moreover, an efficient scheme to determine the blending masks of arbitrarily overlapping images for multi-band blending is presented.

3D from Line Segments in Two Poorly-Textured, Uncalibrated Images

This paper addresses the problem of camera self-calibration, bundle adjustment and 3D reconstruction from line segments in two images of poorly-textured indoor scenes. First, we generate line segment correspondences, using an extended version of our previously proposed matching scheme. The first main contribution is a new method to identify polyhedral junctions resulting from the intersections of the line segments. At the same time, the images are segmented into planar polygons. This is done using an algorithm based on a binary space partitioning (BSP) tree. The junctions are matched end points of the detected line segments and hence can be used to obtain the epipolar geometry. The essential matrix is considered for metric camera calibration. For better stability, the second main contribution consists in a bundle adjustment on the line segments and the camera parameters that reduces the number of unknowns by a maximum flow algorithm. Finally, a piecewise-planar 3D reconstruction is computed based on the segmentation of the BSP tree. The systems performance is tested on some challenging examples.

Dense stereo by triangular meshing and cross validation

Dense depth maps can be estimated in a Bayesian sense from multiple calibrated still images of a rigid scene relative to a reference view [1]. This well-established probabilistic framework is extended by adaptively refining a triangular meshing procedure and by automatic cross-validation of model parameters. The adaptive refinement strategy locally adjusts the triangular meshing according to the measured image data. The new method substantially outperforms the competing techniques both in terms of robustness and accuracy.