J. Apolinar Muñoz Rodríguez's research while affiliated with Centro de Investigaciones en Optica and other places

Publications (22)

Chapter
A technique to represent object surface via NURBS and genetic algorithms is presented. In this technique, the surface is generated based on control points. Then, the control points and the weights are optimized via genetic algorithms to find the NURBS, which represents the object surface. The genetic algorithm is constructed through an objective fu...
Article
An accurate technique to perform NURBS surface fitting via genetic algorithms is presented. In this technique, the initial NURBS surface is generated by using object points as control points. Then, the genetic algorithm computes the weights and control points to obtain the NURBS surface fitting. The genetic algorithm is implemented through an objec...
Article
An accurate technique to perform binocular self-calibration by means of an adaptive genetic algorithm based on a laser line is presented. In this calibration, the genetic algorithm computes the vision parameters through simulated binary crossover (SBX). To carry it out, the genetic algorithm constructs an objective function from the binocular geome...
Article
A self-calibration technique based on genetic algorithms (GAs) with simulated binary crossover (SBX) and laser line imaging is presented. In this technique, the GA determines the vision parameters based on perspective projection geometry. The GA is constructed by means of an objective function, which is deduced from the equations of the laser line...
Article
An automatic technique to improve the plantar surface model via Bezier networks is presented. This technique generates the foot sole model via Bezier networks based on surface points, which are retrieved via line projection. The surface model is defined by means of network weights and the control points, which are measured via line position by a Be...
Article
An automatic technique to perform surface modeling via Bezier networks and line projection is presented. In this technique, the surface model is generated via Bezier networks based on surface points, which are retrieved via laser line scanning. Thus, the surface model is defined by means of network weights, which are multiplied by the control point...
Article
An automatic technique to improve the surface model of the shoe-last bottom via Bezier networks is presented. In this technique, the surface model is generated via Bezier networks based on surface points, which are measured via line projection. The measurement procedure is performed by a Bezier network based on the line position. Thus, the model pr...
Article
A three-dimensional model to perform measurements of variable range is presented. This model is performed by a Bezier network via projection of a laser line and an adaptive focal length. The variation of the measurement range is provided by the adjustment of the camera placement and the focal length. The modifications of these parameters are determ...
Article
An encoding system based on a damped triangular function is presented. The image encoding is implemented by a computational algorithm, which transforms the image intensity to a triangular function. This procedure generates a random pattern from the original image. Thus, a secret image is obtained to perform the electronic transmission. The decoding...
Article
An online self-camera orientation for mobile vision is presented. In this technique, the camera orientation is determined during the vision task. This procedure is carried out by Bezier networks of a laser line. Here, the camera orientation is calibrated when the camera is turned during the vision task. Also, the networks perform the three-dimensio...
Article
An automatic re-calibration for mobile vision is presented. In this technique, the vision parameters are determined by means of a Bezier network. This procedure is carried out by image processing of a laser line. From the network structure, the initial calibration and the online re-calibration are performed. The proposed technique avoids calibrated...
Article
Full-text available
An automatic technique for tomato classification is presented based on size and color. The size is determined based on surface contouring by laser line scanning. Here, a Bezier network computes the tomato height based on the line position. The tomato color is determined by CIELCH color space and the components red and green. Thus, the tomato size i...
Article
A self-calibration technique for mobile three-dimensional vision is presented. This technique determines the vision parameters during the vision task based on computer algorithms and image processing. The three-dimensional vision is performed by a Bezier network based on laser line projection. This network provides the data to perform the online se...
Article
An automatic calibration technique for three-dimensional vision is presented. This technique determines the vision parameters by means of approximation networks and image processing of a laser line. Also, the network performs the three-dimensional vision based on laser scanning and a mobile camera. The network is built based on the behavior of a la...
Article
A mobile calibration technique for three-dimensional vision is presented. In this technique, the parameters of mobile vision are computed automatically by approximation networks and image processing of a laser line. Also, the three-dimensional vision is performed by the networks. The proposed vision system provides online geometric modifications fr...
Article
An automatic technique for gear reconstruction is presented. In this technique, the gear modeling is performed by means of an approximation network. To carry it out, a vision system is implemented based on laser metrology. The approximation network is performed based on the gear pattern. To perform the contouring, the gear is scanned by a laser lin...
Article
Se presenta una técnica de visión tridimensional basada en metrología láser y algoritmos de inteligencia artificial. En esta técnica, la visión se efectúa mediante proyección de una línea láser y procesamiento de imágenes. Mediante un arreglo óptico móvil, la línea láser barre la superficie bajo estudio. En base al comportamiento de la línea láser,...
Article
An automatic technique for shape modelling is presented. The approach of this technique is the object representation by means of a mathematical model. To carry it out, a neural network is implemented to perform the object modelling. The model provided by the neural network is performed based on the surface data. To detect the surface data, the obje...
Article
An automatic technique for the representation of the object shape is presented. The main aim of this technique is the extraction of the topography and the shape of articles by networks. Based on laser stripe projection, the topography is obtained automatically using Bezier approximation networks. Using the topographic dimension, a two-dimensional B...
Article
A technique for measuring the objects shape is presented. In this technique, the object is scanned using a light line. From the scanning a set of images is captured by a CCD camera. By processing these images, the object surface is recovered. To determine the surface dimensions, a regression neural network is applied. This network is built using da...
Article
A simple, fast and accurate technique for direct detection of 3-D shape of rotated objects based on light line projection is presented. This technique is proved by simulation and experimentally verified. To obtain the surface shape, the object is rotated at an angle with an electromechanical device. In each rotation, the object is scanned by a ligh...

Citations

... J. Apolinar Mu Muñoz Rodr Rodríguez et al. and Xiaoqiang Tian et al. used a genetic algorithm and BP neural network-based on particle swarm optimization to optimize the control point and knot sequence of the NURBS surface, respectively. There is improved accuracy and speed of fitting NURBS surfaces [26,27]. Jinho Song et al. divide unorganized points into boundary points and internal points using a deep neural network, in order to facilitate more explicit parameterization of boundary points during NURBS modeling [28]. ...
... The precise calibration of a large-base stereovision system is complex and may cause a large positioning uncertainty [74]. Therefore, our future work will focus on an autonomous in situ calibration of the system. ...
... In terrain studies it follows that a digital terrain model (DTM) is required [8][9][10][11][12]. The DTM is a surface z = z(x, y), where x and y belong to a planar grid (generally a regular grid, but in some cases DTMs based on irregular grids are used). ...
... In view of the defects of traditional NSGA-II gene recombination operators, in order to improve the global search speed and optimization accuracy of the algorithm, gene recombination operators can be divided into two categories according to the spatial distribution characteristics of the offspring generated by gene recombination operators [12] : 1) Gene recombination operators whose offspring are distributed along the axis centered on the parent; 2) The gene recombination operator of the progeny spreading around with the parent as the center. ...
... Three-dimensional measurement of micro structure is an area with growing needs and interest since it can always have a significant influence on the performance of micro products. In the past few years, various methods have been proposed to obtain the surface topography such as atomic force microscopy (AFM), scanning tunnel microscopy (STM), stage profiler and confocal scanning microscopy [6][7][8][9]. Some of them could achieve a high precision while it may destroy the measured structure because of the contacting methods. ...
... The second kind of profile measurement methods is active vision, which generates the third dimensional information by the structured light. The light pattern in the active vision includes points 21 , lines 22 and gratings 23,24 . Xu G. 25 outlines a model to reconstruct the 3D laser projection point on the measured object. ...
... Although nonlinear ADRC (NLADRC) is excellent for nonlinear problems, it is difficult to tune the parameters [21,24,25]. Consequently, LADRC consisting of a tracking differentiator (TD), a linear ESO (LESO), and a linear state error feedback (LSEF) law was employed [26]. ...
... Equation (14) shows that the coordinates of the epipole on π c are independent of z c , demonstrating that this epipole is fixed and unique, at which the fringe does not distort as the object depth varies. ...
... In previous works there are mainly two groups of methods for extracting the light stripe centre, one is in pixel level [5,6], and the other is in the subpixel level [7][8][9][10][11][12][13][14][15]. Pixel level methods are usually used for the measurements being of not high accuracy. ...