Arturo Espinosa-Romero

A robust Graph Transformation Matching for non-rigid registration

In this paper, we propose a simple and highly robust point-matching method named Graph Transformation Matching (GTM) relying on finding a consensus nearest-neighbour graph emerging from candidate matches. The method iteratively eliminates dubious matches in order to obtain the consensus graph. The proposed technique is compared against both the Softassign algorithm and a combination of RANSAC and epipolar constraint. Among these three techniques, GTM demonstrates to yield the best results in terms of elimination of outliers. The algorithm is shown to be able to deal with difficult cases such as duplication of patterns and non-rigid deformations of objects. An execution time comparison is also presented, where GTM shows to be also superior to RANSAC for high outlier rates. In order to improve the performance of GTM for lower outlier rates, we present an optimised version of the algorithm. Lastly, GTM is successfully applied in the context of constructing mosaics of retinal images, where feature points are extracted from properly segmented binary images. Similarly, the proposed method could be applied to a number of other important applications.

Graph-based methods for retinal mosaicing and vascular characterization

In this paper, we propose a highly robust point-matching method (Graph Transformation Matching - GTM) relying on finding the consensus graph emerging from putative matches. Such method is a two-phased one in the sense that after finding the consensus graph it tries to complete it as much as possible. We successfully apply GTM to image registration in the context of finding mosaics from retinal images. Feature points are obtained after properly segmenting such images. In addition, we also introduce a novel topological descriptor for quantifying disease by characterizing the arterial/venular trees. Such descriptor relies on diffusion kernels on graphs. Our experiments have showed only statistical significance for the case of arterial trees, which is consistent with previous findings.

Wavefront reconstruction using multiple directional derivatives and Fourier transform

We present a Fourier-based regularized method for reconstructing the wavefront from multiple directional derivatives. This method is robust to noise, and is specially suited for deflectometry measurement.

Dynamical image-based PID uncalibrated visual servoing with fixed camera for tracking of planar robots with a heuristical predictor

Based on a recent state-of-the-art image-based visual feedback control scheme in fixed uncalibrated camera proposed by the authors, the experimental verification is presented. However, image acquisition and processing for closed-loop control introduces technological challenges through the time delay induced by the CCD camera itself. Thus, to preserve the time domain algorithm and to avoid discretization of our nonlinear controller, a practical predictor is introduced to obtain rough estimates of the image at the bandwidth of the robot. The nonlinear dynamics of the planar robot is considered for the stability analysis. Exponential tracking arises due to a chattering-free visual sliding mode using PID controller based on image error trajectories. The experimental setup describes details of the implementation of our previous theoretical results using a fire wire fixed camera, and a direct drive robot for desired image trajectories. All camera and robot parameters are unknown, and experimental results confirm the theoretical results

GPU based real-time quadrature transform method for 3-D surface measurement and visualization

In this article, we propose a massively parallel, real-time algorithm for the estimation of the dynamic phase map of a vibrating object. The algorithm implements a Fourier-based quadrature transform and temporal phase unwrapping technique. CUDA, a graphic processing unit programming architecture was used to implement the algorithm. It was tested on a fringe pattern sequence using three devices with different capabilities, achieving a processing rate greater than 1600 frames per second (fps).

Dynamic 3-D shape measurement method based on quadrature transform.

In this work, it is presented a combination of temporal phase unwrapping technique and Fourier-based quadrature transform to obtain the dynamic phase map from a vibrating object. The proposed combination results on a very simple algorithm which allows an accurate and versatile 3D reconstruction of the object under analysis.

Adaptive sliding mode uncalibrated visual servoing for finite-time tracking of 2D robot

A globally convergent visual feedback control scheme is proposed for the dynamic model of uncertain planar robot manipulators with uncalibrated camera. Additionally, a time-varying feedback gain induces a terminal attractor in the visual error manifold to guarantee finite-time convergence of image-based tracking errors. Simulations results of a two degrees-of-freedom manipulator with uncalibrated CCD camera are presented to illustrate the dynamic closed-loop performance.

Total variation regularization cost function for demodulating phase discontinuities

We introduce a method based on the minimization of a total variation regularization cost function for computing discontinuous phase maps from fringe patterns. The performance of the method is demonstrated by numerical experiments with both synthetic and real data.

Global Uncalibrated Visual Servoing for Constrained Robots Working on an Uncalibrated Environments

This paper studies the open problem of uncalibrated visual servoing for constrained robots with parametric uncertainties, interacting with unknown environments. A new theoretical framework and its experimental validation are given. This approach produces global exponential convergence of the constrained visual position and the contact force between the end-effector and the unknown constrain surface. This approach is based on the formulation of the visual orthogonalization principle (VOP), which, under the framework of passivity, yields a closed-loop system that fuses camera, encoder and force sensor signals. An experimental system running on Linux-RTAI OS is implemented to visually drive a constrained direct-drive robot manipulator, equipped with six axis JR3 force sensor and a FireWire CCD digital camera posed in fixed configuration. This experimental system proves the effectiveness of the proposed approach even when the robot, camera and restriction surface parameters are assumed as unknown

Three-dimensional reconstruction of blood vessels extracted from retinal fundus images

We present a 3D reconstruction of retinal blood vessel trees using two views of fundus images. The problem is addressed by using well known computer vision techniques which consider: 1) The recovery of camera-eyeball model parameters by an auto-calibration method. The camera parameters are found via the solution of simplified Kruppa equations, based on correspondences found by a LMedS optimisation correlation between pairs of eight different views. 2) The extraction of blood vessels and skeletons from two fundus images. 3) The matching of corresponding points of the two skeleton trees. The trees are previously labelled during the analysis of 2D binary images. Finally, 4) the lineal triangulation of matched correspondence points and the surface modelling via generalised cylinders using diameter measurements extracted from the 2D binary images. The method is nearly automatic and it is tested with 2 sets of 10 fundus retinal images, each one taken from different subjects. Results of 3D vein and artery trees reconstructions are shown.