Papers by Francisco José Madrid Cuevas
Journal of Visual Communication and Image Representation, 2016
Direction changes cause difficulties for most of the gait recognition systems, due to appearance ... more Direction changes cause difficulties for most of the gait recognition systems, due to appearance changes. We propose a new approach for multi-view gait recognition, which focuses on recognizing people walking on unconstrained (curved and straight) paths. To this effect, we present a new rotation invariant gait descriptor which is based on 3D angular analysis of the movement of the subject. Our method does not require the sequence to be split into gait cycles, and is able to provide a response before processing the whole sequence. A Support Vector Machine is used for classifying, and a sliding temporal window with majority vote policy is used to reinforce the classification results. The proposed approach has been experimentally validated on "AVA Multi-View Dataset" and "Kyushu University 4D Gait Database" and compared with related state-of-art work. Experimental results demonstrate the effectiveness of this approach in the problem of gait recognition on unconstrained paths.
Journal of Visual Communication and Image Representation, 2016
The present paper proposes a new algorithm for automatic generation of polygonal approximations o... more The present paper proposes a new algorithm for automatic generation of polygonal approximations of 2D closed contours based on a new thresholding method. The new proposal computes the significance level of the contour points using a new symmetric version of the well-known Ramer, Douglas-Peucker method, and then a new Adaptive method is applied to threshold the normalized significance level of the contour points to generate the polygonal approximation. The experiments have shown that the new algorithm has good performance for generating polygonal approximations of 2D closed contours. Futhermore, the new algorithm does not require any parameter to be tuned.
Machine Vision and Applications, 2015
In this paper, we consider the problem of 2D human pose estimation on stereo image pairs. In part... more In this paper, we consider the problem of 2D human pose estimation on stereo image pairs. In particular, we aim at estimating the location, orientation and scale of upper-body parts of people detected in stereo image pairs from realistic stereo videos that can be found in the Internet. To address this task, we propose a novel pictorial structure model to exploit the stereo information included in such stereo image pairs: the Stereo Pictorial Structure (SPS). To validate our proposed model, we contribute a new annotated dataset of stereo image pairs, the Stereo Human Pose Estimation Dataset (SHPED), obtained from YouTube stereoscopic video sequences, depicting people in challenging poses and diverse indoor and outdoor scenarios. The experimental results on SHPED indicates that SPS improves on state-ofthe-art monocular models thanks to the appropriate use of the stereo information.
Proceedings of the 9th International Conference on Distributed Smart Cameras, 2015
Appearance changes due to viewing angle changes cause difficulties for most of the gait recogniti... more Appearance changes due to viewing angle changes cause difficulties for most of the gait recognition methods. In this paper, we propose a new approach for multi-view recognition, which allows to recognize people walking on curved paths. The recognition is based on 3D angular analysis of the movement of the walking human. A coarse-to-fine gait signature represents local variations on the angular measurements along time. A Support Vector Machine is used for classifying, and a sliding temporal window for majority vote policy is used to smooth and reinforce the classification results. The proposed approach has been experimentally validated on the publicly available "Kyushu University 4D Gait Database". The results show that this new approach achieves promising results in the problem of gait recognition on curved paths.
Machine Vision and Applications, 2015
Gait as biometrics has been widely used for human identification. However, direction changes caus... more Gait as biometrics has been widely used for human identification. However, direction changes cause difficulties for most of the gait recognition systems, due to appearance changes. This study presents an efficient multi-view gait recognition method that allows curved trajectories on completely unconstrained paths for indoor environments. Our method is based on volumetric reconstructions of humans, aligned along their way. A new gait descriptor, termed as Gait Entropy Volume (GEnV), is also proposed. GEnV focuses on capturing 3D dynamical information of walking humans through the concept of entropy. Our approach does not require the sequence to be split into gait cycles. A GEnV based signature is computed on the basis of the previous 3D gait volumes. Each signature is classified by a Support Vector Machine, and a majority voting policy is used to smooth and reinforce the classifications results. The proposed approach is experimentally validated on the "AVA Multi-View Gait Dataset (AVAMVG)" and on the "Kyushu University 4D Gait Database (KY4D)". The results show that this new approach achieves promising results in the problem of gait recognition on unconstrained paths.
Activity Monitoring by Multiple Distributed Sensing, 2014
In this paper, we introduce a new multi-view dataset for gait recognition. The dataset was record... more In this paper, we introduce a new multi-view dataset for gait recognition. The dataset was recorded in an indoor scenario, using six convergent cameras setup to produce multi-view videos, where each video depicts a walking human. Each sequence contains at least 3 complete gait cycles. The dataset contains videos of 20 walking persons with a large variety of body size, who walk along straight and curved paths. The multi-view videos have been processed to produce foreground silhouettes. To validate our dataset, we have extended some appearance-based 2D gait recognition methods to work with 3D data, obtaining very encouraging results. The dataset, as well as camera calibration information, is freely available for research purposes.
Pattern Recognition, 2014
This paper presents a fiducial marker system specially appropriated for camera pose estimation in... more This paper presents a fiducial marker system specially appropriated for camera pose estimation in applications such as augmented reality, robot localization, etc. Three main contributions are presented. First, we propose an algorithm for generating configurable marker dictionaries (in size and number of bits) following a criterion to maximize the inter-marker distance and the number of bit transitions. In the process, we derive the maximum theoretical inter-marker distance that dictionaries of square binary markers can have. Second, a method for automatically detecting the markers and correcting possible errors is proposed. Third, a solution to the occlusion problem in augmented reality applications is shown. To that aim, multiple markers are combined with an occlusion mask calculated by color segmentation. The experiments conducted show that our proposal obtains dictionaries with higher inter-marker distances and lower false negative rates than state-of-the-art systems, and provides an effective solution to the occlusion problem.
Method for Polygonal Approximation through Dominant Points Deletion
A method for polygonal approximation of digital planar curves is proposed. This method is relied ... more A method for polygonal approximation of digital planar curves is proposed. This method is relied on the supression of dominant points. Initially, the method uses the set of all breakpoints as dominant points. The method eliminates dominant points until a final condition is satisfied. The residuary dominant points are the polygonal approximation. This aproximation is compared with other classical algorithms. The experimental results show that this method works well for digital planar curves with features of several sizes.
Dominant Points Detection Using Phase Congruence
This paper proposes a new method for simplifying a 2d shape boundary based on its phase congruenc... more This paper proposes a new method for simplifying a 2d shape boundary based on its phase congruence and the optimisation of a function criterion. The phase congruence is a dimensionless feature that stands out boundary salient structures over different scales allowing a hierarchical fast optimisation process over the detected structures. The proposed method has been compared with other two well-known methods using an objective measure of the quality of the generated approximation. The experimental results have shown that the the proposed method is superior in performance to those reviewed in our study.
Method for Polygonal Approximation through Dominant Points Deletion
A method for polygonal approximation of digital planar curves is proposed. This method is relied ... more A method for polygonal approximation of digital planar curves is proposed. This method is relied on the supression of dominant points. Initially, the method uses the set of all breakpoints as dominant points. The method eliminates dominant points until a final condition is satisfied. The residuary dominant points are the polygonal approximation. This aproximation is compared with other classical algorithms. The experimental results show that this method works well for digital planar curves with features of several sizes.
Pattern Recognition, 2008
In this paper a novel non-parametric method is proposed for unimodal thresholding in an edge dete... more In this paper a novel non-parametric method is proposed for unimodal thresholding in an edge detection context. The proposed method assigns a point in a ROC (receiver operating characteristic) space to each possible threshold without the need of a reference binary image. The optimal point and the required corresponding threshold is then determined in the ROC graph. The Berkeley Segmentation Dataset has been used to evaluate the performance of the proposed method, which is compared with another two recent proposals and Otsu method. ᭧ he has been working with the Department of Computing and Numerical Analysis of Cordoba University, and currently he is an assistant professor. His research is focused mainly on image segmentation, 2-D object recognition and evaluation of computer vision algorithms.
Pattern Recognition, 2011
This paper presents a novel method for assessing the accuracy of unsupervised polygonal approxima... more This paper presents a novel method for assessing the accuracy of unsupervised polygonal approximation algorithms. This measurement relies on a polygonal approximation called the ''reference approximation''. The reference approximation is obtained using the method of Perez and Vidal [11] by an iterative method that optimizes an objective function. Then, the proposed measurement is calculated by comparing the reference approximation with the approximation to be evaluated, taking into account the similarity between the polygonal approximation and the original contour, and penalizing polygonal approximations with an excessive number of points. A comparative experiment by using polygonal approximations obtained with commonly used algorithms showed that the proposed measurement is more efficient than other proposed measurements at comparing polygonal approximations with different number of points.
Image and Vision Computing, 2008
This paper proposes a new method for simplifying contours based on the multi-scale analysis of th... more This paper proposes a new method for simplifying contours based on the multi-scale analysis of the local phase. The main advantages of the proposed method are: (i) it does not use any curvature measure approximation to stand out the characteristic points. (ii) The symmetry/asymmetry points can be considered as dominant points of the contour and (iii) it provides a robust approach to suppress the contour noise. The method has been compared with a representative number of other methods using an objective measure of the quality of the generated approximation. The experimental results have shown that the proposed method is superior to those reviewed in our study.
Automatic generation of consensus ground truth for the comparison of edge detection techniques
Image and Vision Computing, 2008
Two new methods are proposed to automatically generate consensus ground truth for real images: Mi... more Two new methods are proposed to automatically generate consensus ground truth for real images: Minimean and Minimax methods. These methods and a version of the Yitzhaky and Peli method have been used to provide ground truth for the comparison of edge detection ...
Pattern Recognition Letters, 2004
Bacterial translocation is currently considered the main pathogenic mechanism leading to spontane... more Bacterial translocation is currently considered the main pathogenic mechanism leading to spontaneous bacterial peritonitis in patients with advanced cirrhosis and ascites. However, to the authors' knowledge there is no information regarding the characteristics of this process in humans. The goals of the current study were to pursue partially identified bacterial DNA in blood (what the authors consider molecular evidence of bacterial translocation) through its relative quantification in a 72-hour study period by using real-time polymerase chain reaction (PCR). A consecutive series of 17 patients with advanced cirrhosis and culture-negative, nonneutrocytic ascites were studied. Therapeutic paracentesis was performed at the time of admission, and blood samples were obtained at baseline and every 8 hours in a 3-day period. Bacterial DNA was detected by a PCR-based method, relatively quantified by real-time PCR, and identified by automated nucleotide sequencing. Seven of 17 patients demonstrated the simultaneous presence of bacterial DNA in blood and ascitic fluid at the time of admission. After therapeutic paracentesis was performed, bacterial DNA persisted in the blood for a minimum of 24 hours, and was reported to last as long as 72 hours in some patients. In addition, different patterns of bacterial DNA appearance and clearance from the blood were identified. The nucleotide sequencing process demonstrated that bacteria detected in the first sample were identical to those noted in subsequent detections over time. In conclusion, bacterial translocation is a single-species, dynamic process that appears to develop in a subgroup of patients with advanced cirrhosis. (HEPATOLOGY 2004;39:484 -491.) S pontaneous bacterial peritonitis (SBP) is a severe infection developing in patients with advanced cirrhosis, in the absence of any intraabdominal, surgically treatable source of infection. 1 It is considered to be the final consequence of repeated episodes of bacterial translocation (BT) from the intestinal lumen and eventual arrival of bacteria in the ascitic fluid (AF). However, the predisposition to develop a SBP episode is related to its intrinsic bactericidal properties. BT is an incompletely understood process by which intestinal bacteria can cross the epithelial wall, thereby reaching mesenteric lymph nodes and other organs. 5 BT has been studied extensively in cirrhotic rats, 6,7 but for obvious reasons it is difficult to study its incidence in patients with cirrhosis. We recently reported the presence of bacterial DNA (BactDNA) in blood and AF in roughly 40% of patients with cirrhosis and culture-negative, nonneutrocytic ascites 9 and, although more experimental work is needed to confirm our hypothesis, the data available to date may represent molecular evidence of BT. This method allows the study of BT in patients without clinical evidence of infection, thus becoming a useful tool with which to investigate the steps preceding a fully developed infection.
Pattern Recognition, 2010
This work proposes a novel particle filter for tracking multiple people using multiple and hetero... more This work proposes a novel particle filter for tracking multiple people using multiple and heterogeneous cameras, namely monocular and stereo cameras. Our approach is to define confidence models and observation models for each type of camera. Particles are evaluated independently in each camera, and then the data are fused in accordance with the confidence. Confidence models take into account several sources of information. On the one hand, they consider occlusion information from an occlusion map calculated using a depth-ordered particle evaluation. On the other hand, the relative precision of sensors is considered so that the contribution of a sensor in the final data fusion step is proportional to its precision. We have defined confidence and observation models for monocular and stereo cameras and have designed tests to validate our proposal. The experiments show that our method is able to operate with each type individually and in combination. Two other remarkable properties of our method are that it is highly parallelizable and that it does not impose restrictions on the cameras' positions or orientations.
Determining Hysteresis Thresholds for Edge Detection by Combining the Advantages and Disadvantages of Thresholding Methods
IEEE Transactions on Image Processing, 2010
Hysteresis is an important technique for edge detection, but the unsupervised determination of it... more Hysteresis is an important technique for edge detection, but the unsupervised determination of its parameters is not an easy problem. In this paper, we propose a method for unsupervised determination of hysteresis thresholds using the advantages and disadvantages of two thresholding methods. The basic idea of our method is to look for the best hysteresis thresholds in a set of candidates. First, the method finds a subset and a overset of the unknown edge points set. Then, it determines the best edge map with the measure chi(2). Compared with a general method to determine the parameters of an edge detector, our method performs well and is less computationally complex. The basic idea of our method can be generalized to other pattern recognition problems.
Pattern Recognition, 2010
Hysteresis is an important edge detection technique, but the unsupervised determination of hyster... more Hysteresis is an important edge detection technique, but the unsupervised determination of hysteresis thresholds is a difficult problem. Thus, hysteresis has limited practical applicability. Unimodal thresholding techniques are another edge detection method. They are useful, because the histogram of a feature image (usually the feature image is an approximation of the gradient image) is unimodal, and there are many unsupervised methods to solve this problem. But such techniques do not use spatial information to detect edge points, so their performance is worse than that of the hysteresis.
Simplified Texture Unit: A~New Descriptor of the Local Texture in Gray-Level Images
In this work we propose a new descriptor of the local texture in gray-level images, named Simplif... more In this work we propose a new descriptor of the local texture in gray-level images, named Simplified Texture Unit (STU). This descriptor is a version, with a smaller computational cost as much in its obtaining as in its later use, of the well-known Texture Unit descriptor (TU) 6. We have carried out a comparative study of the capacity to describe the texture of a region with the capacity provided by the TU descriptor and two other versions of the same one, known as Local Binary Pattern (LBP) and Local Binary Pattern with Contrast (LBP/C) 11. The results of the experiment allow to affirm that the new descriptor has a greater performance with small region sizes, what makes it suitable for unsupervised texture segmentation since it could allow a greater accuracy in the localization of the frontiers between textured regions.
Journal of Visual Communication and Image Representation, 2009
In this work, a novel approach for people detection and tracking using multiple stereo cameras is... more In this work, a novel approach for people detection and tracking using multiple stereo cameras is proposed. Our proposal consists in combining information from all the available cameras using three different plan-view maps. Occupancy and height maps register the volume and height of the objects that are visible in the stereo cameras, respectively. We also propose the use of a novel map, named confidence map, which registers the confidence of the information projected in each cell. The proposed confidence map is employed to fuse the information captured by each camera so that the most reliable information is kept in each cell. We then propose a particle filter algorithm for tracking people in the fused plan-view maps. The observation model employed considers height, occupancy and confidence information so that information from the most reliable camera is employed at each time instant. The experiments conducted show the validity of our proposal.
Uploads
Papers by Francisco José Madrid Cuevas