Rebalancing urban mobility: a tale of four cities

The key of mobility in urban planning is not in dispute. Integrated strategies that take into account the interrelations among land use, transport supply and demand and the different transportation modes are more necessary than ever. In Europe, regulatory tools such as local mobility plans or traffic plans have been enforced for a long time, evolving into so-called sustainable urban transport plans (SUTP) ? that is, plans thatmerge urban planning,mobility governance, social awareness and environmental safeguards to develop a vision based on sustainability and equity. Indeed, SUTP are aimed at solving typical problems in current land use, such as urban sprawl, which make clear the need for a paradigm shift from transport (or mobility) planning to land use (or city) planning, thereby producing urban mobility plans that are fully aligned with integrated urban development plans. This paper describes how SUTP are articulated across Europe according to four case studies: Peterborough (UK), Chambe¿ry (France), Ferrara (Italy) and Pinto (Spain), to highlight variations and commonalities, both among the four national legal frameworks and the actual planning processes at the local level. Objectives, measures and indicators used in the monitoring and evaluation phases have been analysed and the results assessed. The main conclusion of the paper is that, as seen in these real-life examples, the lack of integration between spatial planning and transport strategies results in the unsustainability of urban areas and, therefore, in a significant loss of competitiveness.

Super-Resolution in Respiratory Synchronized Positron Emission Tomography

Respiratory motion is a major source of reduced quality in positron emission tomography (PET). In order to minimize its effects, the use of respiratory synchronized acquisitions, leading to gated frames, has been suggested. Such frames, however, are of low signal-to-noise ratio (SNR) as they contain reduced statistics. Super-resolution (SR) techniques make use of the motion in a sequence of images in order to improve their quality. They aim at enhancing a low-resolution image belonging to a sequence of images representing different views of the same scene. In this work, a maximum a posteriori (MAP) super-resolution algorithm has been implemented and applied to respiratory gated PET images for motion compensation. An edge preserving Huber regularization term was used to ensure convergence. Motion fields were recovered using a B-spline based elastic registration algorithm. The performance of the SR algorithm was evaluated through the use of both simulated and clinical datasets by assessing image SNR, as well as the contrast, position and extent of the different lesions. Results were compared to summing the registered synchronized frames on both simulated and clinical datasets. The super-resolution image had higher SNR (by a factor of over 4 on average) and lesion contrast (by a factor of 2) than the single respiratory synchronized frame using the same reconstruction matrix size. In comparison to the motion corrected or the motion free images a similar SNR was obtained, while improvements of up to 20% in the recovered lesion size and contrast were measured. Finally, the recovered lesion locations on the SR images were systematically closer to the true simulated lesion positions. These observations concerning the SNR, lesion contrast and size were confirmed on two clinical datasets included in the study. In conclusion, the use of SR techniques applied to respiratory motion synchronized images lead to motion compensation combined with improved image SNR and contrast, without any increase in the overall acquisition times.

Surface velocity and ice discharge of the ice cap on King George Island, Antarctica

Glaciers on King George Island, Antarctica, have shown retreat and surface lowering in recent decades, concurrent with increasing air temperatures. A large portion of the glacier perimeter is ocean-terminating, suggesting possible large mass losses due to calving and submarine melting. Here we estimate the ice discharge into the ocean for the King George Island ice cap. L-band synthetic aperture radar images covering the time-span January 2008 to January 2011 over King George Island are processed using an intensity-tracking algorithm to obtain surface velocity measurements. Pixel offsets from 40 pairs of radar images are analysed and inverted to estimate a weighted average surface velocity field. Ice thicknesses are derived from simple principles of ice flow mechanics using the computed surface velocity fields and in situ thickness data. The maximum ice surface speeds reach mayor que 225 m/yr, and the total ice discharge for the analysed flux gates of King George Island is estimated to be 0.720+/-0.428 Gt/yr, corresponding to a specific mass loss of 0.64+/-0.38 m w.e./yr over the area of the entire ice cap (1127 km2).

Estudio numérico de flujo turbulento cargado con partículas sólidas a través de canales y tuberías de sección variable

La presente Tesis Doctoral tiene como objetivo el estudio de flujo turbulento cargado con partículas sólidas a través de canales y tuberías de sección constante usando un enfoque Euleriano-Lagrangiano. El campo de flujo de la fase de transporte (aire) se resuelve usando simulación de grandes escalas (LES), implementada en un programa de volúmenes finitos mientras que las ecuaciones gobernantes de la fase dispersa son resueltas por medio de un algoritmo de seguimiento Lagrangiano de partículas que ha sido desarrollado y acoplado al programa que resuelve el flujo. Se estudia de manera sistemática y progresiva la interacción fluido→partícula (one-way coupling), a través de diferentes configuraciones geométricas en coordenadas cartesianas (canales de sección constante y variable) y en coordenadas cilíndricas (tuberías de sección constante y sección variable) abarcando diferentes números de Reynolds y diferentes tamaños de partículas; todos los resultados obtenidos han sido comparados con datos publicados previamente. El estudio de flujo multifásico a través de, tuberías de sección variable, ha sido abordada en otras investigaciones mayoritariamente de forma experimental o mediante simulación usando modelos de turbulencia menos complejos y no mediante LES. El patrón de flujo que se verifica en una tubería con expansión es muy complejo y dicha configuración geométrica se halla en múltiples aplicaciones industriales que involucran el transporte de partículas sólidas, por ello es de gran interés su estudio. Como hecho innovador, en esta tesis no solo se resuelven las estadísticas de velocidad del fluido y las partículas en tuberías con diferentes tamaños de expansión y diferentes regímenes de flujo sino que se caracteriza, usando diversas formulaciones del número de Stokes y el parámetro de arrastre, el ingreso y acumulación de partículas dentro de la zona de recirculación, obteniéndose resultados coincidentes con datos experimentales. ABSTRACT The objective of this Thesis research is to study the turbulent flow laden with solid particles through channels and pipes with using Eulerian-Lagrangian approach. The flow field of the transport phase (air ) is solved using large eddy simulation ( LES ) implemented in a program of finite volume while the governing equations of the dispersed phase are resolved by means of a particle Lagrangian tracking algorithm which was developed and coupled to principal program flow solver . We studied systematically and progressively the fluid interaction → particle ( one- way coupling ) , through different geometric configurations in Cartesian coordinates ( channel with constant and variable section) and in cylindrical coordinates ( pipes with constant section and variable section ) covering different Reynolds numbers and different particle sizes, all results have been compared with previously published data . The study of multiphase flow through, pipes with variable section has been addressed in other investigations predominantly experimentally or by simulation using less complex models and no turbulence by LES. The flow pattern is verified in a pipe expansion is very complex and this geometry is found in many industrial applications involving the transport of solid particles, so it is of great interest to study. As an innovator fact , in this Thesis not only finds fluid velocity statistics and particles with different sizes of pipe expansion and different flow regimes but characterized, using various formulations of the Stokes number and the drag parameter are resolved, the entry and accumulation of particles within the recirculation zone , matching results obtained with experimental data.

Foreground segmentation in depth imagery using depth and spatial dynamic models for video surveillance applications

Low-cost systems that can obtain a high-quality foreground segmentation almostindependently of the existing illumination conditions for indoor environments are verydesirable, especially for security and surveillance applications. In this paper, a novelforeground segmentation algorithm that uses only a Kinect depth sensor is proposedto satisfy the aforementioned system characteristics. This is achieved by combininga mixture of Gaussians-based background subtraction algorithm with a new Bayesiannetwork that robustly predicts the foreground/background regions between consecutivetime steps. The Bayesian network explicitly exploits the intrinsic characteristics ofthe depth data by means of two dynamic models that estimate the spatial and depthevolution of the foreground/background regions. The most remarkable contribution is thedepth-based dynamic model that predicts the changes in the foreground depth distributionbetween consecutive time steps. This is a key difference with regard to visible imagery,where the color/gray distribution of the foreground is typically assumed to be constant.Experiments carried out on two different depth-based databases demonstrate that theproposed combination of algorithms is able to obtain a more accurate segmentation of theforeground/background than other state-of-the art approaches.

Teoría y práctica de la restauración de la Mezquita-Catedral de Córdoba durante el siglo XX

La Mezquita-Catedral de Córdoba es un edificio vivo. Un edificio que ha sido transformado sucesivamente por hombres de razas, culturas y religiones distintas durante sus más de 1.200 años de vida y que, a pesar de ello, no ha dejado de estar en uso ni uno solo de esos días de esa larga vida. De esta forma, el edificio se muestra ante el visitante como un complejo objeto arquitectónico, resultado de una continua transformación. La capacidad de la transformación de los edificios es algo inherente a su propia condición arquitectónica, no es un hecho exclusivo de la Mezquita-Catedral. Sin embargo, en este edificio esa transformación se produce con una gran intensidad y sin pérdida de su autenticidad. Tradicionalmente, los edificios se han adaptado a los nuevos requerimientos de cada época en un proceso que ha buscado en el propio edificio las leyes o principios que habían de regir la intervención. De esta forma, tanto las sucesivas ampliaciones de la Mezquita de Abd al-Rahman I como las siguientes intervenciones cristianas debieron asumir lo preexistente como material de trabajo. Así, los arquitectos del califa al-Hakam II dialogaron con sus antecesores complejizando el espacio que recibieron, así como los Hernán Ruiz consiguieron un nuevo organismo resultante de la introducción de su arquitectura luminosa en la trama hispanomusulmana. El siglo XIX confirmó el deseo por descubrir las huellas de un pasado esplendoroso que la intervención barroca había silenciado bajo un tratamiento homogéneo del espacio. La recuperación de esas huellas supuso, hace exactamente dos siglos, el inicio de la última gran etapa en la transformación del edificio, la de la restauración. La fábrica es considerada como objeto a conservar y los esfuerzos desde ese momento se centraron en la recuperación de la arquitectura omeya latente. De este modo, la práctica de la restauración como disciplina se encontró absolutamente influenciada por la Arqueología como única fuente de conocimiento. Las intervenciones buscaban lo original como modo de recuperar espacial y formalmente aquel pasado, concentrándose en los lugares del edificio considerados como esenciales. La declaración del edificio como monumento nacional en 1882 propició que el Estado se hiciera cargo de su mantenimiento y conservación, sustituyendo en esa tarea a los Obispos y Cabildos del siglo XIX, que tuvieron un entendimiento muy avanzado para su época. La llegada del arquitecto Velázquez Bosco en las últimas décadas del siglo XIX supuso un cambio trascendental en la historia del edificio, puesto que recibió un edificio con importantes deterioros y consiguió poner las bases del edificio que hoy contemplamos. El empeño por la recuperación material y espacial devolvió a la Mezquita-Catedral buena parte de su imagen original, reproduciendo con exactitud los modelos hallados en las exploraciones arqueológicas. La llegada de Antonio Flórez tras la muerte de Velázquez Bosco supuso la traslación al edificio del debate disciplinar que se desarrolló en las dos primeras décadas del siglo XX. Flórez procuró un nuevo entendimiento de la intervención, considerando la conservación como actuación prioritaria. En 1926 el Estado reformó la manera en que se atendía al patrimonio con la creación de un sistema de zonas y unos arquitectos a cargo de ellas. La existencia de un nuevo marco legislativo apuntaló esa nueva visión conservativa, avalada por la Carta de Atenas de 1931. Este modelo restauración científica huía de la intervención en estilo y valoraba la necesidad de intervenir de la manera más escueta posible y con un lenguaje diferenciado, basándose en los datos que ofrecía la Arqueología. Por tanto, se continuaba con la valoración del edificio como documento histórico, buscando en este caso una imagen diferenciada de la intervención frente a la actitud mimética de Velázquez. Resulta destacable la manera en la que el historiador Manuel Gómez-Moreno influyó en varias generaciones de arquitectos, arqueólogos e historiadores, tanto en el entendimiento científico de la restauración como en la propia estructura administrativa. La labor desarrollada en el edificio por José Mª Rodríguez Cano primero y Félix Hernández a continuación estuvo influida de manera teórica por el método de Gómez-Moreno, aunque en muchos aspectos su labor no representó una gran diferencia con lo hecho por Velázquez Bosco. La búsqueda de lo original volvió a ser recurrente, pero la carga económica del mantenimiento de un edificio tan extenso conllevó la no realización de muchos de los proyectos más ambiciosos. Esta obsesiva búsqueda de la imagen original del edificio tuvo su última y anacrónica etapa con la intervención de la Dirección General de Arquitectura en los 70. Sin embargo, el agotamiento del modelo científico ya había propiciado un nuevo escenario a nivel europeo, que cristalizó en la Carta de Venecia de 1964 y en una nueva definición del objeto a preservar, más allá del valor como documento histórico. Esta nueva posición teórica tuvo su traslación al modelo restaurador español en el último cuarto de siglo XX, coincidiendo con la Transición. El arquitecto Dionisio Hernández Gil defendió una interpretación distinta a la de los arqueólogos y de los historiadores, que había prevalecido durante todo el siglo. En opinión de Hernández Gil, los problemas de intervención debían enfocarse fundamentalmente como problemas de Arquitectura, abandonando la idea de que solamente podían ser resueltos por especialistas. Esta convicción teórica fue defendida desde la nueva Administración y deparó la utilización de unos criterios de intervención particularizados, provenientes del análisis multifocal de cada situación y no sólo desde el valor de los edificios como documentos históricos. Y este cambio tuvo su traslación a la Mezquita-Catedral con la práctica de Gabriel Ruiz Cabrero y Gabriel Rebollo. En consecuencia con esa nueva perspectiva, aceptaron el edificio que recibieron, sustituyendo la búsqueda de aquella página original por la aceptación de cada una de las páginas de su historia y el respeto a las técnicas constructivas del pasado. La búsqueda de soluciones específicas desde el propio objeto arquitectónico significó la renovada atención a la potente estructura formal-constructiva como origen de toda reflexión. Considerar la Mezquita-Catedral en primer lugar como Arquitectura implicaba la atención a todo tipo de factores además de los históricos, como medio para preservar su autenticidad. Esta tesis pretende demostrar que la práctica de la restauración realizada en la Mezquita-Catedral a lo largo del siglo XX ha evolucionado desde la búsqueda de lo original hasta la búsqueda de lo auténtico, como reflejo de una visión basada en lo arqueológico frente a una renovada visión arquitectónica más completa, que incluye a la anterior. La consideración de la intervención en este edificio como otra página más de su historia y no como la última, significa la reedición de un mecanismo recurrente en la vida del edificio y un nuevo impulso en ese proceso de continua transformación. ABSTRACT The Mosque-Cathedral of Cordoba is a living building. A building transformed by men of different races, cultures and religions during more than 1.200 years old and that, nevertheless, it has continued to be in use all days in that long life. Thus, the building shows to the visitor as a complex architectural object, the result of continuous transformation. This transformation capacity of the buildings is inherent in their own architectural condition, it’s not an exclusive fact of the Mosque-Cathedral. However, in this building that transformation happens with a great intensity, without losing their authenticity. Traditionally, buildings have been adapted to the new requirements of times in a process that looked for laws or principles in order to guide the intervention. Thus, both the successive enlargements of the Mosque of Abd al-Rahman and Christian interventions must assume the preexistence as a working material. So, the architects of the caliph al-Hakam II spoke to their predecessors, complexing the receiving space, as well as Hernan Ruiz got a new organism as result the introduction of his luminous architecture into hispanic-muslim weft. The nineteenth century confirmed the desire to discover the traces of a glorious past that Baroque intervention had silenced, under a uniform space treatment. Exactly two centuries ago, the recovery of these traces meant the start of the last major phase in the transformation of the building: the restoration. The building was considered subject to conserve and since then, efforts focused on the recovery of latent Umayyad architecture. Thus, the practice of restoration as a discipline was absolutely influenced by Archaeology as the only source of knowledge. Interventions were seeking the original as the way to recover that past in a space and formal way, concentrating on essential sites of the building. The statement as a national monument in 1882 prompted the State take charge of its maintenance and preservation, replacing to the nineteenth century Bishops and Cabildos, which had a very advanced understanding for that time. The arrival of the architect Velazquez Bosco in the last decades of the nineteenth century involved a momentous change in the history of the building, since he received a building with significant damage and he achieved the foundations of the building that we can see today. Efforts to a material and space recover returned the Mosque-Cathedral to its original image, accurately reproducing the models found in archaeological explorations. The arrival of Antonio Florez after Velazquez’s death involved the translation of discipline debate, which was developed in the first two decades of the twentieth century. Florez tried a new understanding of the intervention, considering conservation as a priority action. In 1926, the State reformed the way in which heritage was attended, creating a zones system with a few architects in charge of them. The existence of a new legislative framework, underpinned this new conservative vision, supported by the Athens Charter of 1931. This scientific restoration model fleeing from intervention in style and it appreciated the need to intervene in the most concise way, with a distinct language based on the data offered by Archaeology. Therefore, it continued with the appraisement of the building as a historical document, seeking in this case a differentiated image of intervention, against Velazquez mimetic attitude. It is remarkable the way in which the historian Manuel Gomez-Moreno influenced several generations of architects, archaeologists and historians, both in the scientific understanding of the restoration and the administrative structure. The work of Jose Maria Rodriguez Cano first and then Felix Hernandez was theoretically influenced by the Gomez-Moreno’s method, although in many respects their work did not represent a great difference to Velazquez Bosco. The search of the original returned to recur, but the economic charge of maintaining such a large building led to the non-realization of many of the most ambitious projects. This obsessive search for the original image of the building had its last and anachronistic stage with the intervention of the Department of Architecture at 70’s. However, the exhaustion of the scientific model had already led to a new scenario at European level, which crystallized in the Venice Charter of 1964 and a new definition of the object to be preserved beyond the value as a historical document. This new theoretical position had its translation to Spanish restaurateur model in the last quarter of the twentieth century, coinciding with the Transition. The architect Dionisio Hernandez Gil defended a different interpretation from archaeologists and historians, that had prevailed throughout the century. According to Hernandez Gil, the problems of intervention should focus primarily as architectural issues, abandoning the idea that they could only be determined by specialist. This theoretical conviction was defended from the new administration and led to the use of particularized criteria, from a multifocal analysis of each situation. And this change had its translation to the Mosque with the practice of Gabriel Ruiz Cabrero and Gabriel Rebollo. Consistent with this new perspective, they accepted the receiving building, replacing the search on original page for acceptance of all historical pages and respecting the constructive techniques of the past. The search for specific solutions from the architectural object meant the renewed attention to the powerful formal-constructive structure as the origin of all thought. Consider the Mosque-Cathedral as Architecture, involved the attention to all kinds of factors in addition to the historical, as a means to preserve its authenticity. This thesis aims to demonstrate that the practice of restoration in the Mosque-Cathedral throughout the twentieth century has evolved from the search of the original to the search for the authentic, reflecting a vision based on the archaeological against a renewed more complete architectural vision, including the above. Consideration of intervention in this building as another page in its history and not the last one, means the reissue of an own mechanism and a new impetus in that continuous transformation process.

Multi-resolution model-based traffic sign detection and tracking

In this paper we propose an innovative approach to tackle the problem of traffic sign detection using a computer vision algorithm and taking into account real-time operation constraints, trying to establish intelligent strategies to simplify as much as possible the algorithm complexity and to speed up the process. Firstly, a set of candidates is generated according to a color segmentation stage, followed by a region analysis strategy, where spatial characteristic of previously detected objects are taken into account. Finally, temporal coherence is introduced by means of a tracking scheme, performed using a Kalman filter for each potential candidate. Taking into consideration time constraints, efficiency is achieved two-fold: on the one side, a multi-resolution strategy is adopted for segmentation, where global operation will be applied only to low-resolution images, increasing the resolution to the maximum only when a potential road sign is being tracked. On the other side, we take advantage of the expected spacing between traffic signs. Namely, the tracking of objects of interest allows to generate inhibition areas, which are those ones where no new traffic signs are expected to appear due to the existence of a TS in the neighborhood. The proposed solution has been tested with real sequences in both urban areas and highways, and proved to achieve higher computational efficiency, especially as a result of the multi-resolution approach.

Image Segmentation Using Ant System-based Clustering Algorithm

Industrial applications of computer vision sometimes require detection of atypical objects that occur as small groups of pixels in digital images. These objects are difficult to single out because they are small and randomly distributed. In this work we propose an image segmentation method using the novel Ant System-based Clustering Algorithm (ASCA). ASCA models the foraging behaviour of ants, which move through the data space searching for high data-density regions, and leave pheromone trails on their path. The pheromone map is used to identify the exact number of clusters, and assign the pixels to these clusters using the pheromone gradient. We applied ASCA to detection of microcalcifications in digital mammograms and compared its performance with state-of-the-art clustering algorithms such as 1D Self-Organizing Map, k-Means, Fuzzy c-Means and Possibilistic Fuzzy c-Means. The main advantage of ASCA is that the number of clusters needs not to be known a priori. The experimental results show that ASCA is more efficient than the other algorithms in detecting small clusters of atypical data.

EVA: Laparoscopic instrument tracking based on endoscopic video analysis for psychomotor skills assessment

INTRODUCTION: The EVA (Endoscopic Video Analysis) tracking system a new tracking system for extracting motions of laparoscopic instruments based on non-obtrusive video tracking was developed. The feasibility of using EVA in laparoscopic settings has been tested in a box trainer setup. METHODS: EVA makes use of an algorithm that employs information of the laparoscopic instrument's shaft edges in the image, the instrument's insertion point, and the camera's optical centre to track the 3D position of the instrument tip. A validation study of EVA comprised a comparison of the measurements achieved with EVA and the TrEndo tracking system. To this end, 42 participants (16 novices, 22 residents, and 4 experts) were asked to perform a peg transfer task in a box trainer. Ten motion-based metrics were used to assess their performance. RESULTS: Construct validation of the EVA has been obtained for seven motion-based metrics. Concurrent validation revealed that there is a strong correlation between the results obtained by EVA and the TrEndo for metrics such as path length (p=0,97), average speed (p=0,94) or economy of volume (p=0,85), proving the viability of EVA. CONCLUSIONS: EVA has been successfully used in the training setup showing potential of endoscopic video analysis to assess laparoscopic psychomotor skills. The results encourage further implementation of video tracking in training setups and in image guided surgery.

Detection and Tracking of Dynamic Objects. A MultiRobot approach to Critical Infrastructures Surveillance.

Despite that Critical Infrastructures (CIs) security and surveillance are a growing concern for many countries and companies, Multi Robot Systems (MRSs) have not been yet broadly used in this type of facilities. This dissertation presents a novel study of the challenges arisen by the implementation of this type of systems and proposes solutions to specific problems. First, a comprehensive analysis of different types of CIs has been carried out, emphasizing the influence of the different characteristics of the facilities in the design of a security and surveillance MRS. One of the most important needs for the surveillance of a CI is the detection of intruders. From a technical point of view this problem can be abstracted as equivalent to the Detection and Tracking of Mobile Objects (DATMO). This dissertation proposes algorithms to solve this specific problem in a CI environment. Using 3D range images of the environment as input data, two detection algorithms for ground robots have been developed. These detection algorithms provide a list of moving objects in the robot detection area. Direct image differentiation and computer vision techniques are used when the robot is static. Alternatively, multi-layer ground reconstructions are compared to detect the dynamic objects when the robot is moving. Since CIs usually spread over large areas, it is very useful to incorporate aerial vehicles in the surveillance MRS. Therefore, a moving object detection algorithm for aerial vehicles has been also developed. This algorithm compares the real optical flow obtained from a down-face oriented camera with an artificial optical flow computed using a RANSAC based homography matrix. Two tracking algorithms have been developed to follow the moving objects trajectories. These algorithms can efficiently handle occlusions and crossings, as well as exchange information among robots. The multirobot tracking can be applied to any type of communication structure: centralized, decentralized or a combination of both. Even more, the developed tracking algorithms are independent of the detection algorithms and could be potentially used with other detection procedures or even with static sensors, such as cameras. In addition, using the 3D point clouds available to the robots, a relative localization algorithm has been developed to improve the position estimation of a given robot with observations from other robots. All the developed algorithms have been extensively tested in different simulated CIs using the Webots robotics simulator. Furthermore, the algorithms have also been validated with real robots operating in real scenarios. In conclusion, this dissertation presents a multirobot approach to Critical Infrastructure Surveillance, mainly focusing on Detecting and Tracking Dynamic Objects.

Efficient hybrid monocular-stereo approach to on-board, video-based traffic sign detection and tracking

In this paper we propose an innovative method for the automatic detection and tracking of road traffic signs using an onboard stereo camera. It involves a combination of monocular and stereo analysis strategies to increase the reliability of the detections such that it can boost the performance of any traffic sign recognition scheme. Firstly, an adaptive color and appearance based detection is applied at single camera level to generate a set of traffic sign hypotheses. In turn, stereo information allows for sparse 3D reconstruction of potential traffic signs through a SURF-based matching strategy. Namely, the plane that best fits the cloud of 3D points traced back from feature matches is estimated using a RANSAC based approach to improve robustness to outliers. Temporal consistency of the 3D information is ensured through a Kalman-based tracking stage. This also allows for the generation of a predicted 3D traffic sign model, which is in turn used to enhance the previously mentioned color-based detector through a feedback loop, thus improving detection accuracy. The proposed solution has been tested with real sequences under several illumination conditions and in both urban areas and highways, achieving very high detection rates in challenging environments, including rapid motion and significant perspective distortion

Automatic expert system based on images for accuracy crop row detection in maize fields

This paper proposes an automatic expert system for accuracy crop row detection in maize fields based on images acquired from a vision system. Different applications in maize, particularly those based on site specific treatments, require the identification of the crop rows. The vision system is designed with a defined geometry and installed onboard a mobile agricultural vehicle, i.e. submitted to vibrations, gyros or uncontrolled movements. Crop rows can be estimated by applying geometrical parameters under image perspective projection. Because of the above undesired effects, most often, the estimation results inaccurate as compared to the real crop rows. The proposed expert system exploits the human knowledge which is mapped into two modules based on image processing techniques. The first one is intended for separating green plants (crops and weeds) from the rest (soil, stones and others). The second one is based on the system geometry where the expected crop lines are mapped onto the image and then a correction is applied through the well-tested and robust Theil–Sen estimator in order to adjust them to the real ones. Its performance is favorably compared against the classical Pearson product–moment correlation coefficient.

Video analysis based vehicle detection and tracking using an MCMC sampling framework

This article presents a probabilistic method for vehicle detection and tracking through the analysis of monocular images obtained from a vehicle-mounted camera. The method is designed to address the main shortcomings of traditional particle filtering approaches, namely Bayesian methods based on importance sampling, for use in traffic environments. These methods do not scale well when the dimensionality of the feature space grows, which creates significant limitations when tracking multiple objects. Alternatively, the proposed method is based on a Markov chain Monte Carlo (MCMC) approach, which allows efficient sampling of the feature space. The method involves important contributions in both the motion and the observation models of the tracker. Indeed, as opposed to particle filter-based tracking methods in the literature, which typically resort to observation models based on appearance or template matching, in this study a likelihood model that combines appearance analysis with information from motion parallax is introduced. Regarding the motion model, a new interaction treatment is defined based on Markov random fields (MRF) that allows for the handling of possible inter-dependencies in vehicle trajectories. As for vehicle detection, the method relies on a supervised classification stage using support vector machines (SVM). The contribution in this field is twofold. First, a new descriptor based on the analysis of gradient orientations in concentric rectangles is dened. This descriptor involves a much smaller feature space compared to traditional descriptors, which are too costly for real-time applications. Second, a new vehicle image database is generated to train the SVM and made public. The proposed vehicle detection and tracking method is proven to outperform existing methods and to successfully handle challenging situations in the test sequences.

A new DSATUR-based algorithm for exact vertex coloring

This paper describes a new exact algorithm PASS for the vertex coloring problem based on the well known DSATUR algorithm. At each step DSATUR maximizes saturation degree to select a new candidate vertex to color, breaking ties by maximum degree w.r.t. uncolored vertices. Later Sewell introduced a new tiebreaking strategy, which evaluated available colors for each vertex explicitly. PASS differs from Sewell in that it restricts its application to a particular set of vertices. Overall performance is improved when the new strategy is applied selectively instead of at every step. The paper also reports systematic experiments over 1500 random graphs and a subset of the DIMACS color benchmark.

3D Object following based on visual information for Unmanned Aerial Vehicles

This article presents a novel system and a control strategy for visual following of a 3D moving object by an Unmanned Aerial Vehicle UAV. The presented strategy is based only on the visual information given by an adaptive tracking method based on the color information, which jointly with the dynamics of a camera fixed to a rotary wind UAV are used to develop an Image-based visual servoing IBVS system. This system is focused on continuously following a 3D moving target object, maintaining it with a fixed distance and centered on the image plane. The algorithm is validated on real flights on outdoors scenarios, showing the robustness of the proposed systems against winds perturbations, illumination and weather changes among others. The obtained results indicate that the proposed algorithms is suitable for complex controls task, such object following and pursuit, flying in formation, as well as their use for indoor navigation