Search

Telerobotics is the area of robotics concerned with the control of robots from a distance, mainly using wireless connections or the Internet. It is a combination of two major subfields, teleoperation and telepresence. The work presented in this chapter belongs to the field of teleoperated robots, where a remote centre sets commands to the robot and supervises the performed motion by receiving feedback from its sensors. In teleoperated robots the control algorithm can be balanced between the remote host and the local host in the robot, which yields to several kind of possible control schemas. The key components needed to develop telerobotics applications are the following: control (algorithm and real time implementation), sensors (world sensing and information processing) and wireless communication (generally using standard wireless technologies, i.e. IEEE 802.11) [Angelo, 2003], [Anvari, 2007], [Gumaste, 2007], [Mehani, 2007], [Chumsamutr, 2003], [Hespanha, 2007], [Bambang, 2007]. This chapter is outlined within both educational and research fields in telerobotics, and so its aim is to offer a reliable and low cost architecture to be implemented in research labs. The robotic platform consists of the Pioneer 3DX (P3-DX) from the company MobileRobots (see Figure 1). It is made of an aluminium body (44x38x22cm) with 16.5cm diameter drive wheels. The two DC motors use 38.3:1 gear ratios and contain 500-tick encoders. The differential drive platform is highly holonomic and can rotate in place moving both wheels, or it can swing around a stationery wheel in a circle of 32cm radius. A rear caster is included for balancing the robot. On flat floor, the P3-DX can move at speeds of 1.6 mps. At slower speeds it can carry payloads up to 23 kg. In addition to motor encoders, the P3DX base includes eight ultrasonic transducer (range-finding sonar) sensors arranged to provide 180degree forward coverage. This robot includes a 32-bit RISC-based controller, with 8 digital inputs and 8 digital outputs plus 1 dedicated A/D port; 4 of the outputs can be reconfigured to PWM outputs [P3-DX, 2009]. The P3-DX can be ordered with a complete electronic hardware [MobileRobots, 2009], which include wide range sensors, an on-board PC and Wireless Ethernet communication device. However, the authors propose to start from a basic structure that allows to be customized depending on the final application. This decision offers the opportunity of working with open platforms which is specially suitable for educational labs in engineering schools. On 1

International audience; A major research area in Computer Assisted Intervention (CAI) is to aid laparoscopic surgery teams with Augmented Reality (AR) guidance. This involves registering data from other modalities such as MR and fusing it with the laparoscopic video in real-time, to reveal the location of hidden critical structures. We present the first system for AR guided laparoscopic surgery of the uterus. This works with pre-operative MR or CT data and monocular laparoscopes, without requiring any additional interventional hardware such as optical trackers. We present novel and robust solutions to two main sub-problems: the initial registration, which is solved using a short exploratory video, and update registration, which is solved with real-time tracking-by-detection. These problems are challenging for the uterus because it is a weakly-textured, highly mobile organ that moves independently of surrounding structures. In the broader context, our system is the first that has successfully performed markerless real-time registration and AR of a mobile human organ with monocular laparoscopes in the OR.

This paper proposes a deep learning-based method to detect multiple people from a single overhead depth image with high precision. Our neural network, called DPDnet , is composed by two fully-convolutional encoder-decoder blocks built with residual layers. The main block takes a depth image as input and generates a pixel-wise confidence map, where each detected person in the image is represented by a Gaussian-like distribution, The refinement block combines the depth image and the output from the main block, to refine the confidence map. Both blocks are simultaneously trained end-to-end using depth images and ground truth head position labels. The paper provides a rigorous experimental comparison with some of the best methods of the state-of-the-art, being exhaustively evaluated in different publicly available datasets. DPDnet proves to outperform all the evaluated methods with statistically significant differences, and with accuracies that exceed 99%. The system was trained on one of the datasets (generated by the authors and available to the scientific community) and evaluated in the others without retraining, proving also to achieve high accuracy with varying datasets and experimental conditions. Additionally, we made a comparison of our proposal with other CNN-based alternatives that have been very recently proposed in the literature, obtaining again very high performance. Finally, the computational complexity of our proposal is shown to be independent of the number of users in the scene and runs in real time using conventional GPUs.

This paper studies the 3D reconstruction of a deformable surface from a single image and a reference surface, known as the template. This problem is known as Shape-from-Template and has been recently shown to be well-posed for isometric deformations, for which the surface bends without altering geodesics. This paper studies the case of equiareal deformations. They are elastic deformations where the local area is preserved and thus include isometry as a special case. Elastic deformations have been studied before in Shape-from-Template, yet no theoretical results were given on the existence or uniqueness of solutions. The equiareal model is much more widely applicable than isometry. This paper brings Monge’s theory, widely used for studying the solutions of nonlinear first-order PDEs, to the field of 3D reconstruction. It uses this theory to establish a theoretical framework for equiareal Shape-from-Template and answers the important question of whether it is possible to reconstruct a surface exactly with a much weaker prior than isometry. We prove that equiareal Shape-from-Template has a maximum of two local solutions sufficiently near an initial curve that lies on the surface. In addition, we propose an analytical reconstruction algorithm that can recover the multiple solutions. Our algorithm uses standard numerical tools for ODEs. We use the perspective camera model and give reconstruction results with both synthetic and real examples.

Purpose:To compare rotational stability, centration and visual outcomes provided by three trifocal lens models that have the same optical zone design but different material, composition, and/or toricity.Methods:The study included 78 patients with symmetric bilateral intraocular lens implantation. The lenses under evaluation were trifocal intraocular lenses made of hydrophilic acrylic material: a spherical lens 26% hydrophilic acrylic (POD FineVision), a similar lens but having a toric design (POD Toric FineVision), and a trifocal lens 25% hydrophilic acrylic material (FineVision/MicroF). Moreover, the lenses share the same optical zone design. The lenses’ rotational stability and centration were measured by means of the PIOLET software, which relies on recording and image processing techniques to determine lens rotation and centration based on slit-lamp images. We also assessed patients’ visual quality by means of 25, 40, and 80 cm VA tests.Results:The best centration results were achieved with the POD Toric FineVision model, although the differences were not statistically significant. As for lens rotation, it was below 5° in all cases under study. Regarding VA, all subjects attained at least 0.3 logMAR for far distance uncorrected VA, at 80 cm VA was about 0.2 logMAR, at 40 cm it was above 0.15 logMAR, and at 25 cm it was about 0.3 logMAR for both lens types.Conclusion:All three intraocular lens models yield excellent visual results at far, near as well as intermediate distances. The POD FineVision and POD Toric FineVision models, with double C-loop design, yielded the best results centration-wise and rotation-wise. Differences had no clinical relevance.

This paper describes a novel DNN-based system, named PD3net , that detects multiple people from a single depth image, in real time. The proposed neural network processes a depth image and outputs a likelihood map in image coordinates, where each detection corresponds to a Gaussian-shaped local distribution, centered at each person’s head. This likelihood map encodes both the number of detected people as well as their position in the image, from which the 3D position can be computed. The proposed DNN includes spatially separated convolutions to increase performance, and runs in real-time with low budget GPUs. We use synthetic data for initially training the network, followed by fine tuning with a small amount of real data. This allows adapting the network to different scenarios without needing large and manually labeled image datasets. Due to that, the people detection system presented in this paper has numerous potential applications in different fields, such as capacity control, automatic video-surveillance, people or groups behavior analysis, healthcare or monitoring and assistance of elderly people in ambient assisted living environments. In addition, the use of depth information does not allow recognizing the identity of people in the scene, thus enabling their detection while preserving their privacy. The proposed DNN has been experimentally evaluated and compared with other state-of-the-art approaches, including both classical and DNN-based solutions, under a wide range of experimental conditions. The achieved results allows concluding that the proposed architecture and the training strategy are effective, and the network generalize to work with scenes different from those used during training. We also demonstrate that our proposal outperforms existing methods and can accurately detect people in scenes with significant occlusions.

Time delay estimation is essential in Acoustic Source Localization (ASL) systems. One of the most used techniques for this purpose is the Generalized Cross Correlation (GCC) between a pair of signals and its use in Steered Response Power (SRP) techniques, which estimate the acoustic power at a specific location. Nowadays, Deep Learning strategies may outperform these methods. However, they are generally dependent on the geometric and sensor configuration conditions that are available during the training phases, thus having limited generalization capabilities when facing new environments if no re-training nor adaptation is applied. In this work, we propose a method based on an encoder-decoder CNN architecture capable of outperforming the well known SRP-PHAT algorithm, and also other Deep Learning strategies when working in mismatched training-testing conditions without requiring a model re-training. Our proposal aims to estimate a smoothed version of the correlation signals, that is then used to generate a refined acoustic power map, which leads to better performance on the ASL task. Our experimental evaluation uses three publicly available realistic datasets and provides a comparison with the SRP-PHAT algorithm and other recent proposals based on Deep Learning.

The International Personality Item Pool (IPIP) five-factor model inventories are widely used for personality research and have been translated into multiple languages. However, the extent of the psychometric assessment of translated scales is variable, often minimal. The lack of psychometric scrutiny is particularly problematic because translation is an inherently complex process. Here, we present a structural analysis of one Spanish translation of the 50-item IPIP five-factor inventory in a sample of Peruvian, non-university educated, working adults (n = 778). A global confirmatory factor analytic (CFA) model of the a priori five factors failed to fit. So too did single factor models for four of the five factors, the exception being Neuroticism. Fit was improved via use of an exploratory structural equation measurement model, but the resultant solution showed very poor theoretical coherence. So, we explored the data for systematic measurement artefacts and sought to model them to improve the psychometric properties of the scale. Specifically, the pattern of factor loadings suggested that the lack of coherence might be due to the effects of the valence of item wording (i.e., positively or negatively worded items). CFA models including five substantive factors and a series of method factors modelling shared covariance based on item wording, improved fit and coherence. This investigation suggests that unless method factors are explicitly modelled the tested Spanish translation may not be suitable for use in certain Spanish-speaking countries or samples composed of non-university educated participants. More broadly, the study has implications for many translated scales, especially when used without thorough psychometric evaluation.

This work proposes a new method for face and mouth tracking using video cameras. This method has been proposed to be used in intelligent spaces as an initial stage to provide information to higher level applications. The method incorporates the classifiers of the Viola and Jones detection method, modified to provide a probabilistic output previously proposed by the authors, useful for tracking with particle filter. The method combines classifiers trained to detect specific poses (frontal and side face views), building an independent likelihood model of pose changes. We also propose to combine the model in several cameras to allow the mouth tracking in a three-dimensional space. The system has been evaluated on the AV16.3 database sequences showing good results in both precision and recall when using a single camera (in a bidimensional space), and an error below 3cm when using three cameras (in a three-dimensional space).

A method for infrared and cameras sensor fusion, applied to indoor positioning in intelligent spaces, is proposed in this work. The fused position is obtained with a maximum likelihood estimator from infrared and camera independent observations. Specific models are proposed for variance propagation from infrared and camera observations (phase shifts and image respectively) to their respective position estimates and to the final fused estimation. Model simulations are compared with real measurements in a setup designed to validate the system. The difference between theoretical prediction and real measurements is between 0.4 cm (fusion) and 2.5 cm (camera), within a 95% confidence margin. The positioning precision is in the cm level (sub-cm level can be achieved at most tested positions) in a 4 &times, 3 m locating cell with 5 infrared detectors on the ceiling and one single camera, at distances from target up to 5 m and 7 m respectively. Due to the low cost system design and the results observed, the system is expected to be feasible and scalable to large real spaces.

Image warps -or just warps- capture the geometric deformation existing between two images of a deforming surface. The current approach to enforce a warp's smoothness is to penalize its second order partial derivatives (Bookstein in IEEE Trans Pattern Anal Mach Intell 11:567---585, 1989; Rueckert et al. in IEEE Trans Med Imaging 18:712---721, 1999). Because this favors locally affine warps, this fails to capture the local projective component of the image deformation. This may have a negative impact on applications such as image registration and deformable 3D reconstruction. We propose a novel penalty designed to smooth the warp while capturing the deformation's local projective structure. Our penalty is based on equivalents to the Schwarzian derivatives, which are projective differential invariants exactly preserved by homographies. We propose a methodology to derive a set of partial differential equations with only homographies as solutions. We call this system the Schwarzian equations and we explicitly derive them for 2D functions using differential properties of homographies. We name as Schwarp a warp which is estimated by penalizing the residual of Schwarzian equations. Experimental evaluation shows that Schwarps outperform existing warps in modeling and extrapolation power, and lead to better results in three deformable reconstruction methods, namely, shape reconstruction in shape-from-template, camera calibration in Shape-from-Template and Non-Rigid Structure-from-Motion.

The algorithms for acoustic source localization based on PHAT filtering have been profusely used with good results in reverberant and noisy environments. However, there are very few studies that give a formal explanation of their robustness, most of them providing just an empirical validation or showing results on simulated data. In this work we present a novel analytical model for predicting the behavior of both the SRP-PHAT power maps and the GCC-PHAT functions. The results show that they are only affected by the signal bandwidth, the microphone array topology, and the room geometry, being independent of the spectral content of the received signal. The proposed model is shown to be valid in reverberant environments and under far and near field conditions. Using this result, an analysis study on how the aforementioned factors affect the SRP-PHAT power maps is presented providing well supported theoretical and practical considerations. The model validation is based on both synthetic and real data, obtaining in all cases a high accuracy of the model to reproduce the SRP-PHAT power maps, both in anechoic and non-anechoic scenarios, becoming thus an excellent tool to be exploited for the improvement of real world relevant applications related to acoustic localization. HighlightsA novel parametric analytical model to predict SRP-PHAT power maps is formulated.An exhaustive evaluation is done on both synthetic and real data.Results show high accuracy for very different acoustical and geometrical conditions.The paper also addresses practical issues in the model implementation.

The International Personality Item Pool (IPIP) five-factor model inventories are a widely used resource for personality research and have been translated into multiple languages. However, the extent of the psychometric assessment of translated scales is variable. Here we present a structural analysis of one Spanish translation of the 50-item IPIP five-factor inventory in a sample of Peruvian non-university educated working adults (n=778). A global confirmatory factor analytic (CFA) model of the a priori five factors failed to fit. So too did single factor models for four of the five factors, the exception being Neuroticism. Fit was improved via use of an exploratory structural equation measurement model, but the resultant solution showed very poor theoretical coherence. The pattern of factor loadings suggested that the lack of coherence might be due to the effects of the valence of item wording. CFA models including five substantive factors and a series of method factors modelling shared covariance based on item wording, improved fit and coherence. This investigation suggests that the tested Spanish translation, without explicitly modelling method factors, may not be suitable for use in certain Spanish-speaking countries or samples composed of non-university educated participants.

Employment interviews are relevant scenarios for the study of social interaction. In this setting, social skills play an important role, even though the interactions between potential employers and candidates are often limited. One fundamental aspect of social interaction is the use of nonverbal communication , which affects how we are socially perceived. We present a method to automatically extract body communicative cues from one-on-one conversations recorded with Kinect devices. First, we find the three-dimensional position of hands and head of the subject, and, aided by training data, we infer the upper body pose. Then, we use the inferred poses to perform action recognition and build person-specific activity descriptors. We evaluate our system with both domain-specific and public, generic datasets, and show competitive performance.

We study a problem that we call Shape-from-Template , which is the problem of reconstructing the shape of a deformable surface from a single image and a 3D template. Current methods in the literature address the case of isometric deformations, and relax the isometry constraint to the convex inextensibility constraint, solved using the so-called maximum depth heuristic. We call these methods zeroth-order since they use image point locations (the zeroth-order differential structure) to solve the shape inference problem from a perspective image. We propose a novel class of methods that we call first-order. The key idea is to use both image point locations and their first-order differential structure. The latter can be easily extracted from a warp between the template and the input image. We give a unified problem formulation as a system of PDEs for isometric and conformal surfaces that we solve analytically . This has important consequences. First, it gives the first analytical algorithms to solve this type of reconstruction problems. Second, it gives the first algorithms to solve for the exact constraints . Third, it allows us to study the well-posedness of this type of reconstruction: we establish that isometric surfaces can be reconstructed unambiguously and that conformal surfaces can be reconstructed up to a few discrete ambiguities and a global scale. In the latter case, the candidate solution surfaces are obtained analytically. Experimental results on simulated and real data show that our isometric methods generally perform as well as or outperform state of the art approaches in terms of reconstruction accuracy, while our conformal methods largely outperform all isometric methods for extensible deformations.

When many users consult service desks simultaneously, these typically saturate. This causes the customer attention to be delayed more than usual. To increase the amount of human agents is a costly process for organizations. All this has motivated the design of a knowledge-based system that automatically assists both customers and human agents at the service desk. Web technology was used to enable clients to communicate with a software agent via chat. Techniques of Natural Language Processing were used for the software agent to understand the customer requests. The domain knowledge used by the software agent to understand customer requests has been codified in an ontology. A rule-based expert system (ES) was designed to perform the diagnostic task. This paper presents a knowledge-based system allowing client to communicate with the service desk through a chat system using free text. Evaluations conducted with users have shown an improvement in the attention of service desks when the software developed is used.

This paper presents a sequential non-rigid reconstruction method that recovers the 3D shape and the camera pose of a deforming object from a video sequence and a previous shape model of the object. We take PTAM (Parallel Mapping and Tracking), a state-of-the-art sequential real-time SfM (Structure-from-Motion) engine, and we upgrade it to solve non-rigid reconstruction. Our method provides a good trade-off between processing time and reconstruction error without the need for specific processing hardware, such as GPUs. We improve the original PTAM matching by using descriptor-based features, as well as smoothness priors to better constrain the 3D error. This paper works with perspective projection and deals with outliers and missing data. We evaluate the tracking algorithm performance through different tests over several datasets of non-rigid deforming objects. Our method achieves state-of-the-art accuracy and can be used as a real-time method suitable for being embedded in portable devices., Ministerio de Economía y Competitividad, Comunidad de Madrid, Agencia Estatal de Investigación

We present a global and convex formulation for the template-less 3D reconstruction of a deforming object with the perspective camera. We show for the first time how to construct a Second-Order Cone Programming (SOCP) problem for Non-Rigid Structure-from-Motion (NRSfM) using the Maximum-Depth Heuristic (MDH). In this regard, we deviate strongly from the general trend of using affine cameras and factorization-based methods to solve NRSfM, which do not perform well with complex nonlinear deformations. In MDH, the points' depths are maximized so that the distance between neighbouring points in camera space are upper bounded by the geodesic distance. In NRSfM both geodesic and camera space distances are unknown. We show that, nonetheless, given point correspondences and the camera's intrinsics the whole problem can be solved with SOCP. This is the first convex formulation for NRSfM with physical constraints. We further present how robustness and temporal continuity can be included in the formulation to handle outliers and decrease the problem size, respectively. We show with extensive experiments that our methods accurately reconstruct quasi-isometric objects from partial views under articulated and strong deformations. Compared to the previous methods, our approach gives better or similar accuracy. It naturally handles missing correspondences, non-smooth objects and is very simple to implement compared to previous methods, with only one free parameter (the neighbourhood size).

We study Isometric Non-Rigid Shape-from-Motion (Iso-NRSfM): given multiple intrinsically calibrated monocular images, we want to reconstruct the time-varying 3D shape of a thin-shell object undergoing isometric deformations. We show that Iso-NRSfM is solvable from local warps, the inter-image geometric transformations. We propose a new theoretical framework based on the Riemmanian manifold to represent the unknown 3D surfaces as embeddings of the camera's retinal plane. This allows us to use the manifold's metric tensor and Christoffel Symbol (CS) fields. These are expressed in terms of the first and second order derivatives of the inverse-depth of the 3D surfaces, which are the unknowns for Iso-NRSfM. We prove that the metric tensor and the CS are related across images by simple rules depending only on the warps. This forms a set of important theoretical results. We show that current solvers cannot solve for the first and second order derivatives of the inverse-depth simultaneously. We thus propose an iterative solution in two steps. 1) We solve for the first order derivatives assuming that the second order derivatives are known. We initialise the second order derivatives to zero, which is an infinitesimal planarity assumption. We derive a system of two cubics in two variables for each image pair. The sum-of-squares of these polynomials is independent of the number of images and can be solved globally, forming a well-posed problem for $N\geq 3$ images. 2) We solve for the second order derivatives by initialising the first order derivatives from the previous step. We solve a linear system of $4N-4$ equations in three variables. We iterate until the first order derivatives converge. The solution for the first order derivatives gives the surfaces’ normal fields which we integrate to recover the 3D surfaces. The proposed method outperforms existing work in terms of accuracy and computation cost on synthetic and real datasets.

Objective To report the use of augmented reality (AR) in gynecology. Design AR is a surgical guidance technology that enables important hidden surface structures to be visualized in endoscopic images. AR has been used for other organs, but never in gynecology and never with a very mobile organ like the uterus. We have developed a new AR approach specifically for uterine surgery and demonstrated its use for myomectomy. Setting Tertiary university hospital. Patient(s) Three patients with one, two, and multiple myomas, respectively. Intervention(s) AR was used during laparoscopy to localize the myomas. Main Outcome Measure(s) Three-dimensional (3D) models of the patient's uterus and myomas were constructed before surgery from T2-weighted magnetic resonance imaging. The intraoperative 3D shape of the uterus was determined. These models were automatically aligned and "fused" with the laparoscopic video in real time. Result(s) The live fused video made the uterus appear semitransparent, and the surgeon can see the location of the myoma in real time while moving the laparoscope and the uterus. With this information, the surgeon can easily and quickly decide on how best to access the myoma. Conclusion(s) We developed an AR system for gynecologic surgery and have used it to improve laparoscopic myomectomy. Technically, the software we developed is very different to approaches tried for other organs, and it can handle significant challenges, including image blur, fast motion, and partial views of the organ.

Multipath interference of light is the cause of important errors in Time of Flight (ToF) depth estimation. This paper proposes an algorithm that removes multipath distortion from a single depth map obtained by a ToF camera. Our approach does not require information about the scene, apart from ToF measurements. The method is based on fitting ToF measurements with a radiometric model. Model inputs are depth values free from multipath interference whereas model outputs consist of synthesized ToF measurements. We propose an iterative optimization algorithm that obtains model parameters that best reproduce ToF measurements, recovering the depth of the scene without distortion. We show results with both synthetic and real scenes captured by commercial ToF sensors. In all cases, our algorithm accurately corrects the multipath distortion, obtaining depth maps that are very close to ground truth data.

Augmented Reality (AR) is a technology that can allow a surgeon to see subsurface structures. This works by overlaying information from another modality, such as MRI and fusing it in real time with the endoscopic images. AR has never been developed for a very mobile organ like the uterus and has never been performed for gynecology. Myomas are not always easy to localize in laparoscopic surgery when they do not significantly change the surface of the uterus, or are at multiple locations. To study the accuracy of myoma localization using a new AR system compared to MRI-only localization. Ten residents were asked to localize six myomas (on a uterine model into a laparoscopic box) when either using AR or in conditions that simulate a standard method (only the MRI was available). Myomas were randomly divided in two groups: the control group (MRI only, AR not activated) and the AR group (AR activated). Software was used to automatically measure the distance between the point of contact on the uterine surface and the myoma. We compared these distances to the true shortest distance to obtain accuracy measures. The time taken to perform the task was measured, and an assessment of the complexity was performed. The mean accuracy in the control group was 16.80 mm [0.1–52.2] versus 0.64 mm [0.01–4.71] with AR. In the control group, the mean time to perform the task was 18.68 [6.4–47.1] s compared to 19.6 [3.9–77.5] s with AR. The mean score of difficulty (evaluated for each myoma) was 2.36 [1–4] versus 0.87 [0–4], respectively, for the control and the AR group. We developed an AR system for a very mobile organ. This is the first user study to quantitatively evaluate an AR system for improving a surgical task. In our model, AR improves localization accuracy.

International audience; We have developed a technique to study how good computers can be at diagnosing gastrointestinal lesions from regular (white light and narrow banded) colonoscopic videos compared to two levels of clinical knowledge (expert and beginner). Our technique includes a novel tissue classification approach which may save clinician's time by avoiding chromoendoscopy, a time-consuming staining procedure using indigo carmine. Our technique also discriminates the severity of individual lesions in patients with many polyps, so that the gastroenterologist can directly focus on those requiring polypectomy. Technically, we have designed and developed a framework combining machine learning and computer vision algorithms, which performs a virtual biopsy of hyperplastic lesions, serrated adenomas and adenomas. Serrated adenomas are very difficult to classify due to their mixed/hybrid nature and recent studies indicate that they can lead to colorectal cancer through the alternate serrated pathway. Our approach is the first step to avoid systematic biopsy for suspected hyperplastic tissues. We also propose a database of colonoscopic videos showing gastrointestinal lesions with ground truth collected from both expert image inspection and histology. We not only compare our system with the expert predictions, but we also study if the use of 3D shape features improves classification accuracy, and compare our technique's performance with three competitor methods.

Aim To describe a simple and efficacious monitoring system for patients presenting with severe dengue with severe plasma leakage. Method: We reviewed sixty-one out of 110 records of patients presenting with dengue in August and September of 1999 at the Hospital Tony Facio, Limón province, Costa Rica. Results: Dengue virus 3 was the cause of the epidemic. Thirty one (51%) patients presented with warning sings, and thirty (49%) had severe dengue with severe plasma leakage. Those patients presenting with hypotension (low mean arterial blood pressure) were treated with an intravenous polyelectrolyte solution in order to maintain the mean arterial pressure between the lower and mean range. When the mean arterial pressure presented a tendency to rise over the normal range, the infusion was withdrawn. The hematocrit was not the parameter used to monitor the treatment of the patients. There were no deaths. Conclusions: Monitoring the mean arterial blood pressure instead of the hematocrit values in patients with severe dengue with severe plasma leakage represents an easier and more efficacious way of treating this patient population. Resumen: Objetivo: Describir un sistema de monitoreo más simple y eficiente para pacientes con dengue grave con extravasación de plasma severa. Método: Se revisaron 61 de 110 expedientes de pacientes que presentaban dengue, entre agosto y setiembre de 1999, en el Hospital Tony Facio de la provincia de Limón en Costa Rica. Resultados: El virus de dengue tipo 3 causó la epidemia. Treinta y uno (51%) de los pacientes presentaron signos de alarma, treinta (49%) presentaron dengue grave con extravasación de plasma severa. Los pacientes que presentaban hipotensión (baja presión sanguínea media) fueron tratados con solución de polielectrolitos intravenosa para mantener la presión arterial media entre el rango inferior y la media. En cuanto la presión arterial media presentaba una tendencia a incrementar sobre el rango normal, la infusión era retirada. El hematocrito no fue un parámetro para monitorear el manejo de los pacientes. No hubo muertes. Conclusiones: El monitorear la presión arterial media, en lugar de los valores de hematocritos, en pacientes con dengue grave con extravasación severa representa una manera más fácil y eficiente de tratar a esta población de pacientes.

This paper describes an algorithm based on the 2D approach of Allard and Fraley that uses Voronoi tessellation and a non-parametric maximum likelihood estimator. We have designed a 3D version of this algorithm which detects multiple clusters of points immersed in background noise; its application to the detection of galaxy clusters in redshift space, using the astronomical database of the 2-degree Field Galaxy Redshift Survey, is presented and discussed. Adopting as a benchmark a particular set of catalogued clusters of galaxies, we find that the proposed algorithm recognizes the location of ∼ 67% of the clusters. Three variants of the algorithm were assessed to deal with the elongation of the clusters in the radial direction of observation introduced by the astronomical distance indicator; their merits and limitations are discussed. We address separately the detection of the galaxy cluster location and the detection of galaxy cluster members, both of them having an anisotropic space as their search domain. In the case of detection of galaxy cluster members, a second stage of detection was incorporated in order to improve the results. © 2006 IEEE.

We present a global and convex formulation for template-less 3D reconstruction of a deforming object with the perspective camera. We show for the first time how to construct a Second-Order Cone Programming (SOCP) problem for Non-Rigid Shape-from-Motion (NRSfM) using the Maximum-Depth Heuristic (MDH). In this regard, we deviate strongly from the general trend of using affine cameras and factorization-based methods to solve NRSfM. In MDH, the points' depths are maximized so that the distance between neighbouring points in camera space are upper bounded by the geodesic distance. In NRSfM both geodesic and camera space distances are unknown. We show that, nonetheless, given point correspondences and the camera's intrinsics the whole problem is convex and solvable with SOCP. We show with extensive experiments that our method accurately reconstructs quasi-isometric surfaces from partial views under articulated and strong deformations. It naturally handles missing correspondences, non-smooth objects and is very simple to implement compared to previous methods, with only one free parameter (the neighbourhood size).

Shape-from-Template (SfT) reconstructs the shape of a deforming surface from a single image, a 3D template and a deformation prior. For isometric deformations, this is a well-posed problem. However, previous methods which require no initialization break down when the perspective effects are small, which happens when the object is small or viewed from larger distances. That is, they do not handle all projection geometries. We propose stable SfT methods that accurately reconstruct the 3D shape for all projection geometries. We follow the existing approach of using first-order differential constraints and obtain local analytical solutions for depth and the first-order quantities: the depth-gradient or the surface normal. Previous methods use the depth solution directly to obtain the 3D shape. We prove that the depth solution is unstable when the projection geometry tends to affine, while the solution for the first-order quantities remain stable for all projection geometries. We therefore propose to solve SfT by first estimating the first-order quantities (either depth-gradient or surface normal) and integrating them to obtain shape. We validate our approach with extensive synthetic and real-world experiments and obtain significantly more accurate results compared to previous initialization-free methods. Our approach does not require any optimization, which makes it very fast.

This paper presents a current control scheme for a voltage-source converter connected to the grid through an LCL filter. The proposed current control is based on the linear quadratic (LQ) Gaussian (LQG) servo controller technique, which combines the LQ regulator and the Kalman filter (KF). The use of the KF instead of a Luenberger estimator improves the quality of the estimation of state variables in noisy environments, increasing the noise immunity of the control loop. This paper focuses on giving some criteria and practical hints to choose both the KF and LQ design parameters to achieve null steady-state tracking error, channel decoupling, and noise immunity. Furthermore, this paper analyzes the steady-state KF approximation that allows a significant decrement in the computational complexity of the algorithm at nearly no cost in accuracy. Simulation and experimental results prove the correct operation of the proposed LQG current control and the possible advantages of using KF to estimate the state vector.

Generalized procrustes analysis computes the best set of transformations that relate matched shape data. In shape analysis the transformations are usually chosen as similarities, while in general statistical data analysis other types of transformation groups such as the affine group may be used. Generalized procrustes analysis has a nonlinear and nonconvex formulation. The classical approach alternates the computation of a so-called reference shape and the computation of transformations relating this reference shape to each shape datum in turn. We propose the stratified approach to generalized procrustes analysis. It first uses the affine transformation group to analyze the data and then upgrades the solution to the sought after group, whether Euclidean or similarity. We derive a convex formulation for each of these two steps, and efficient practical algorithms that gracefully handle missing data (incomplete shapes). Extensive experimental results show that our approaches perform well on simulated and real data. In particular our closed-form solution gives very accurate results for generalized procrustes analysis of Euclidean data.

This paper presents a method for detecting a textured deformed surface in an image. It uses (wide-baseline) point matches between a template and the input image. The main contribution of the paper is twofold. First, we propose a robust method based on local surface smoothness capable of discarding outliers from the set of point matches. Our method handles large proportions of outliers (beyond 70% with less than 15% of false positives) even when the surface self-occludes. Second, we propose a method to estimate a self-occlusion resistant warp from point matches. Our method allows us to realistically retexture the input image. A pixel-based (direct) registration approach is also proposed. Bootstrapped by our robust point-based method, it finely tunes the warp parameters using the value (intensity or color) of all the visible surface pixels. The proposed framework was tested with simulated and real data. Convincing results are shown for the detection and retexturing of deformed surfaces in challenging images.

We identify 1901 galaxy clusters (N g ≥ 2) with the VoML+G algorithm (Paper I) on the Two-Degree Field Galaxy Redshift Survey. We present the 341 clusters with at least 10 galaxies that are within 0.009 < z < 0.14 (the Catalog), of which 254 (~75%) have counterparts in the literature (NED), with the remainder (87) plausibly "new" because of incompleteness of previous searches or unusual galaxy contents. The 207 clusters within z = 0.04–0.09 are used to study the properties of the galaxy systems in the nearby universe, including their galaxy contents parameterized by the late-type galaxy fractions (f L ). For this nearly complete cluster subsample, we find the following: (i) 63% are dominated by early-type galaxies (i.e., the late-type-poor clusters, f L < 0.5) with corresponding mean multiplicity and logarithmic virial mass (in units of M ⊙) of 22 ± 1 and 12.91 ± 0.04, respectively; and (ii) 37% are dominated by late-type galaxies (i.e., the late-type-rich clusters, f L ≥ 0.5) with corresponding mean multiplicity and logarithmic virial mass (in units of M ⊙) of 15.7 ± 0.9 and 12.66 ± 0.07, respectively. The statistical analysis of the late-type fraction distribution supports, with a 3σ confidence level, the presence of two population components. It is suggested that the late-type-poor galaxy systems reflect and extend the class of Abell-APM-EDCC clusters and that the late-type-rich systems (~one-third of the total) belong to a new, previously unappreciated class. The late-type-rich clusters, on average high mass-to-light ratio systems, appear to be more clustered on large scales than the late-type-poor clusters. A class of late-type-rich clusters is not predicted by current theory.

This paper presents a sensor system for robot localization based on the information obtained from a single camera attached in a fixed place external to the robot. Our approach firstly obtains the 3D geometrical model of the robot based on the projection of its natural appearance in the camera while the robot performs an initialization trajectory. This paper proposes a structure-from-motion solution that uses the odometry sensors inside the robot as a metric reference. Secondly, an online localization method based on a sequential Bayesian inference is proposed, which uses the geometrical model of the robot as a link between image measurements and pose estimation. The online approach is resistant to hard occlusions and the experimental setup proposed in this paper shows its effectiveness in real situations. The proposed approach has many applications in both the industrial and service robot fields.

This paper addresses the design and presents the experimental results of an aperiodic remote-controlled mechatronic plant using a MiniDK2 electronic development board. We compare the classic periodic control solution with our self-triggered approach. The triggering mechanism consists of evaluating if the measurement error exceeds a predefined value. This measurement error is defined as the difference between the output signal of a model with and without a sample-and-hold that is activated only at the triggering instants. The minimum inter-execution time is the reference period and the maximum time is set by the designer, guaranteeing the stability of the closed loop system. At each new triggering instant, the remote controller receives a new measurement of the system and sends the actuation signal to the mechatronic plant.

This paper is the first in a series, presenting a new galaxy cluster finder based on a three-dimensional Voronoi Tesselation plus a maximum likelihood estimator, followed by gapping-filtering in radial velocity(VoML+G). The scientific aim of the series is a reassessment of the diversity of optical clusters in the local universe. A mock galaxy database mimicking the southern strip of the magnitude(blue)-limited 2dF Galaxy Redshift Survey (2dFGRS), for the redshift range 0.009 < z < 0.22, is built on the basis of the Millennium Simulation of the LCDM cosmology and a reference catalog of "Millennium clusters," spannning across the 1.0 × 1012–1.0 × 1015 M ⊙ h −1 dark matter (DM) halo mass range, is recorded. The validation of VoML+G is performed through its application to the mock data and the ensuing determination of the completeness and purity of the cluster detections by comparison with the reference catalog. The execution of VoML+G over the 2dFGRS mock data identified 1614 clusters, 22% with N g ≥ 10, 64 percent with 10 > N g ≥ 5, and 14% with N g < 5. The ensemble of VoML+G clusters has a ~59% completeness and a ~66% purity, whereas the subsample with N g ≥ 10, to z ~ 0.14, has greatly improved mean rates of ~75% and ~90%, respectively. The VoML+G cluster velocity dispersions are found to be compatible with those corresponding to "Millennium clusters" over the 300–1000 km s−1 interval, i.e., for cluster halo masses in excess of ~3.0 × 1013 M ⊙ h −1.

An active research objective in Computer Assisted Intervention (CAI) is to develop guidance systems to aid surgical teams in la-paroscopic Minimal Invasive Surgery (MIS) using Augmented Reality (AR). This involves registering and fusing additional data from other modalities and overlaying it onto the laparoscopic video in realtime. We present the first AR-based image guidance system for assisted myoma localisation in uterine laparosurgery. This involves a framework for semi-automatically registering a pre-operative Magnetic Resonance Image (MRI) to the laparoscopic video with a deformable model. Although there has been several previous works involving other organs, this is the first to tackle the uterus. Furthermore, whereas previous works perform registration between one or two laparoscopic images (which come from a stereo laparoscope) we show how to solve the problem using many images (e.g. 20 or more), and show that this can dramatically improve registration. Also unlike previous works, we show how to integrate occluding contours as registration cues. These cues provide powerful registration constraints and should be used wherever possible. We present retrospective qualitative results on a patient with two myomas and quantitative semi-synthetic results. Our multi-image framework is quite general and could be adapted to improve registration in other organs with other modalities such as CT.

This paper proposes a general framework to solve Non-Rigid Shape-from-Motion (NRSfM) with the perspective camera under isometric deformations. Contrary to the usual low-rank linear shape basis, isometry allows us to recover complex shape deformations from a sparse set of images. Existing methods suffer from ambiguities and may be very expensive to solve. We bring four main contributions. First, we formulate isometric NRSfM as a system of first-order Partial Differential Equations (PDE) involving the shape’s depth and normal field and an unknown template. Second, we show this system cannot be locally resolved. Third, we introduce the concept of infinitesimal planarity and show that it makes the system locally solvable for at least three views. Fourth, we derive an analytic solution which involves convex, linear least-squares optimization only, and outperforms existing works.

It has been recently shown that reconstructing an isometric surface from a single 2D input image matched to a 3D template was a well-posed problem. This however does not tell us how reconstruction algorithms will behave in practical conditions, where the amount of perspective is generally small and the projection thus behaves like weak-perspective or orthography. We here bring answers to what is theoretically recoverable in such imaging conditions, and explain why existing convex numerical solutions and analytical solutions to 3D reconstruction may be unstable. We then propose a new algorithm which works under all imaging conditions, from strong to loose perspective. We empirically show that the gain in stability is tremendous, bringing our results close to the iterative minimization of a statisticallyoptimal cost. Our algorithm has a low complexity, is simple and uses only one round of linear least-squares.

[ES] Se presenta un método general para la detección, de forma no invasiva, de la postura corporal de varias personas a partir de la información capturada por múltiples cámaras. Se sigue una filosofía basada en el entrenamiento previo de un modelo articulado y posterior seguimiento. La principal aportación es la posibilidad de detectar varias personas simultáneamente. Se utiliza un modelo articulado para definir las posturas que puede adoptar una persona. Mediante bases de datos de captura de movimiento se selecciona un conjunto de clases o actividades predefinidas. El entrenamiento reduce la complejidad del modelo articulado a partir de técnicas no lineales de reducción de dimensionalidad. Así, las diferentes actividades de una persona quedan definidas de manera compacta por un conjunto de valores de baja dimensionalidad. Posteriormente, un filtro de partículas mixto (estados discretos y continuos) es utilizado para detectar la postura y el tipo de movimiento simultáneamente. Las hipótesis resultantes, seleccionadas automáticamente a partir de la distribución de partículas, son refinadas usando un optimizador no lineal que hace uso de funciones ‘a priori’ del tipo de movimiento entrenado. La propuesta se ha evaluado con un método simple pero estándar, basado en la comparación de volúmenes cilíndricos articulados con volúmenes del cuerpo humano, extraidos automáticamente a partir de las imágenes. Se consigue una precisión cercana a trabajos del estado del arte que no tienen en cuenta a más de una persona y ofrece un marco de trabajo flexible para futuras investigaciones., [EN] This work presents a general framework for tracking simultaneously the body posturas of multiple people from nonintrusive visual sensors. The method is based on a trainingthen-tracking philosophy, with the main addition of being able to handle more than just one person. We train the body postura from labelled motion capture datasets. The training process is based on popular non-linear dimensionality reduction techniques. Then, a mixed, discrete and continuous state particle filter is used to simultaneously detect the postura and the kind of motion performed by each of the human bodies. The resulting hypotheses, automatically selected from the particle distribution, are then refined using non-linear optimization methods with statistical priors. The whole framework is tested using a simple but standard method based on comparing articulated cylindrical models with SfS volumes, taken from several cameras. Our accuracy in public available datasets is near to the state-ofthe-art works that do not take into account multiple people in the problem., Este trabajo ha sido parcialmente respaldado por el Ministerio de Ciencia e Innovacion Español bajo los proyectos VISNU (ref. TIN2009-08984) y SDTEAM-UAH (ref. TIN2008-06856-C05-05).

This paper describes the development of innovative software and hardware technologies in order to design a system capable of obtaining the pose of robotic wheelchairs through the use of cameras in fixed positions in the environment. Our intelligent space is able of obtaining information from the observed world using its sensors. Robot localization in the intelligent spaces is an essential task to provide a service to users while simplifying the technology embedded on the robot, moving the individual robot intelligence to the environment. The intelligent space is composed of two labs and the corridor between them, simulating a house. Eleven cameras are installed in the intelligent space with USB technology connected onto 11 TCP/IP servers. The identification of the robotic wheelchair in the intelligent space is done by localizing the beacons built with infrared LEDs and positioned on the robot. Thus, the localization algorithm can be simpler and faster. With the points obtained from the location, it is possible to reconstruct the 3D pose of the robotic wheelchair in the environment.

Nonverbal communication plays an important role in many aspects of our lives, such as in job interviews, where vis-α-vis conversations take place. This paper proposes a method to automatically detect body communicative cues by using video sequences of the upper body of individuals in a conversational context. To our knowledge, our work brings novelty by explicitly addressing the recognition of visual activity in a seated, conversational setting from monocular video, compared to most existing work in video-based motion capture, which targets full-body with lower limb activities. We first detect the person hands in the sequence by searching for the higher speed parts along the whole video. Then, aided by training a set of typical conversational movements, we infer the approximate 3D upper body pose, that we transfer to a low-dimensionality space in order to perform action recognition. We test our system in the context of job interviews, with several new databases that we make publicly available.

This paper presents an algorithm that automatically corrects the distortion caused by multipath interference (MpI) in depth measurements obtained with time of flight cameras (ToF cameras). A radiometric model that explains, under some mild simplifications, the working principle of a ToF camera including a model for MpI is proposed. Using this model we demonstrate that all the information needed for compensating the influence of MpI on the scene captured by the camera is self-contained in the measurements (depth and amplitude of infrared signal). We propose an iterative optimization method that, based on the measurements contaminated with MpI, gives depth correction for each pixel. Results are shown in artificially generated time of flight scenes using the radiometric model. In addition, the system has been validated in real scenes using a commercial ToF camera providing good results.

We present a method to automatically select the regularization parameter in the two-term compound cost function used in image registration. Our method is called CFS (Constant Flow Sampling). It samples the regularization parameter using the constraint that the warp-induced image flow be of constant magnitude on average. Compared to other methods, CFS provably provides a global solution at a specified precision and within a finite number of steps. CFS can be embedded within any algorithm minimizing a two-term compound cost function depending on a regularization parameter. We report experimental results on the registration of several datasets of laparoscopic images.

This paper proposes the development of innovative software and hardware technologies in order to design a system capable of obtaining the pose of a robotic wheelchairs through the use of cameras in fixed positions in the environment. The intelligent space is able of obtaining information from the observed world using its sensors. Robot localization in the intelligent spaces is an essential task to provide a service to users while simplifying the technology embedded on the robot, moving the individual robot intelligence to the environment. The intelligent space is composed of two labs and the corridor between them, simulating a house. Eleven cameras are installed in the intelligent space with USB technology connected onto 11 TCP/IP servers. The identification of the robotic wheelchair in the intelligent space is done by beacons built with infrared LEDs positioned on the top of the robot. Thus, the localization algorithm can be simpler and faster. With the points obtained from the location, it is possible to reconstruct 3-D pose of the robotic wheelchair in the environment.

Através do presente estudo objetivou-se realizar uma avaliação da arborização existente em cinco praças de Cachoeira do Sul, onde foram observadas variáveis relativas às espécies arbóreas, tais como: diagnóstico da fitossanidade, riqueza de espécies, análise do CAP (circunferência à altura do peito) e altura, e quanto a presença ou ausência de áreas livres adequadas. Os dados foram coletados em planilha específica, transferidos e analisados no software Excel. O total de indivíduos encontrados foi de 832, distribuídos em 36 famílias botânicas. As cinco espécies de maior ocorrência foram Jacaranda mimosifolia, Ligustrum lucidum, Tipuana tipu, Lagerstroemia indica e Parapiptadenia rigida, representando 35,94% do total. A análise da fitossanidade mostrou que 62,59% das árvores encontram-se saudáveis, 26% estão sendo atacadas por pragas e 11% sofreram injúria mecânica. Na avaliação da altura dos indivíduos, 53% apresentaram alturas maiores que 9 m, observou-se também que 65,75% dessas árvores apresentaram CAP maiores que 55 cm. É possível observar, nas cinco praças, a existência de um mesmo número de espécies exóticas e nativas. Os resultados encontrados para a análise de área livre mostram que 451 indivíduos não possuem espaço adequado para seu bom desenvolvimento, enquanto que 381 possuem esses espaços.

This paper presents a complete implementation of the Principal Component Analysis (PCA) algorithm in Field Programmable Gate Array (FPGA) devices applied to high rate background segmentation of images. The classical sequential execution of different parts of the PCA algorithm has been parallelized. This parallelization has led to the specific development and implementation in hardware of the different stages of PCA, such as computation of the correlation matrix, matrix diagonalization using the Jacobi method and subspace projections of images. On the application side, the paper presents a motion detection algorithm, also entirely implemented on the FPGA, and based on the developed PCA core. This consists of dynamically thresholding the differences between the input image and the one obtained by expressing the input image using the PCA linear subspace previously obtained as a background model. The proposal achieves a high ratio of processed images (up to 120 frames per second) and high quality segmentation results, with a completely embedded and reliable hardware architecture based on commercial CMOS sensors and FPGA devices.