Search

An unmanned aerial vehicle (UAV) is a robotic aircraft that can fly with either a remote input from a ground-based operator, or autonomously without human intervention based on pre-programmed flight plans (How et al., 2004). UAVs offer advantages over conventional manned vehicles in many applications because they can be used in situations otherwise too dangerous for manned vehicles and without being weighed down by the systems required by a pilot. UAVs are currently receiving much attention in research because they can be used in a wide variety of fields, both civil and military, such as reconnaissance, geophysical survey, environmental and meteorological monitoring, aerial photography, and search-and-rescue tasks. Most of these missions are usually carried out in threatened environments, and then it is very important to fly along a route which keeps the UAV away from known threats. Detection radars are one of the main threats for an UAV, but there are others that should also be avoided, such as fires, electric storms, radio shadowing zones, no flight zones, and so on. One of the main goals in many UAV’s projects has been to establish the route that maximizes the likelihood of successful mission completion taking into account all known information about technological constraints, obstacles and threat zones on a static environment (Richards & How, 2002). Some papers that investigate path planning for UAVs presume that the location of the threats and their presence are deterministically known at planning-time, and interpret a path which avoids possible threat regions as an optimal path (Borto, 2000). However more recent projects are examining the possibilities of UAVs as realistic autonomous agents working on dynamic environments where threat zones called pop-up are present (Zengin & Dogan, 2004). The true presence of these types of zones is only known at flying-time, but the location and knowledge about the probability of appearance can be known at planning-time. In this chapter we will present an approach to trajectory optimization for UAV in presence of obstacles, waypoints, and risk zones. The approach has been implemented on SPASAS (System for Planning And Simulation of Aerial Strategy), an integrated system for definition of flight scenarios, flight planning, simulation and graphic representation of the results developed at Complutense University of Madrid. The system uses two alternative methods for trajectory generation: mixed integer linear programming (MILP) and a modification of the A* algorithm, depending on the characteristics of the scenario between two waypoints.

SUMMARYRobotic surface planetary exploration is a challenging endeavor, with critical safety requirements and severe communication constraints. Autonomous navigation is one of the most crucial and yet risky aspects of these operations. Therefore, a certain level of local autonomy for onboard robots is an essential feature, so that they can make their own decisions independently of ground control, reducing operational costs and maximizing the scientific return of the mission. In addition, existing tools to support research in this domain are usually proprietary to space agencies, and out of reach of most researchers. This paper presents a framework developed to support research in this field, a modular onboard software architecture design and a series of algorithms that implement a visual-based autonomous navigation approach for robotic space exploration. It allows analysis of algorithms' performance and functional validation of approaches and autonomy strategies, data monitoring and the creation of simulation models to replicate the vehicle, sensors, terrain and operational conditions. The framework and algorithms are partly supported by open-source packages and tools. A set of experiments and field testing with a physical robot and hardware are described as well, detailing results and algorithms' processing time, which experience an incremented of one order of magnitude when executed in space-certified like hardware, with constrained resources, in comparison to using general purpose hardware.

This paper proposes an automatic expert system for 3D terrain reconstruction and automatic intensity correction in stereo pairs of images based on histogram matching. Different applications in robotics, particularly those based on autonomous navigation in rough and natural environments, require a high-quality reconstruction of the surface. The stereo vision system is designed with a defined geometry and installed onboard a mobile robot, together with other sensors such as an Inertial Measurement Unit (IMU), necessary for sensor fusion. It is generally assumed the intensities of corresponding points in two images of a stereo pair are equal. However, this assumption is often false, even though they are acquired from a vision system composed of two identical cameras. We have also found this issue in our dataset. Because of the above undesired effects the stereo matching process is significantly affected, as many correspondence algorithms are very sensitive to these deviations in the brightness pattern, resulting in an inaccurate terrain reconstruction. The proposed expert system exploits the human knowledge which is mapped into three modules based on image processing techniques. The first one is intended for correcting intensities of the stereo pair coordinately, adjusting one as a function of the other. The second one is based in computing disparity, obtaining a set of correspondences. The last one computes a reconstruction of the terrain by reprojecting the computed points to 2D and applying a series of geometrical transformations. The performance of this method is verified favorably.

[ES] En este trabajo se aborda la problemática del proceso de correspondencia de imágenes estéreo procedentes de terrenos reales obtenidas con el sistema estereoscópico Videre STH-DCSG 9 mm. Se utilizan una serie de algoritmos de correspondencia, que forman parte del proceso estereoscópico global, cuya finalidad es realizar una reconstrucción 3D para navegación de robots autónomos en entornos naturales y no estructurados. En primer lugar, se realiza un estudio acerca del efecto que tiene la aplicación del filtrado homomórfico sobre las imágenes de entrada como paso previo a la correspondencia. Mediante dicho filtrado se consigue mejorar considerablemente el mapa de disparidad, logrando un mayor número de correspondencias verdaderas en relación a los procesos de correspondencia sin filtrado. Después, se realiza un filtrado del mapa de disparidad dirigido por clusters y basado en el principio de continuidad espacial con el que se consigue la eliminación de falsos positivos o correspondencias erróneas. Ambos filtrados constituyen la principal aportación del trabajo., [EN] In this work we deal with the matching process problem using stereo images from real world terrains taken with a Videre STH- DCSG 9 mm stereoscopic system. A series of matching algorithms are used, as part of the global stereoscopic process, with the purpose of creating a 3D reconstruction for robotic autonomous navigation in natural and non-structured environments. First, a study about the effects of applying homomorphic filtering to the input images previous to the matching process is carried out. Using this method, a significant enhancement in the disparity map is achieved, obtaining a greater number of true correspondences in relation to applying no filtering at all. Then, a filtering process over the disparities map driven by clusters and based in a spatial continuity premise dismisses false positives or wrong correspondences. Both filtering processes are the main contribution of this work.

Stereo matching is a heavily researched area with a prolific published literature and a broad spectrum of heterogeneous algorithms available in diverse programming languages. This paper presents a Matlab-based testbed that aims to centralize and standardize this variety of both current and prospective stereo matching approaches. The proposed testbed aims to facilitate the application of stereo-based methods to real situations. It allows for configuring and executing algorithms, as well as comparing results, in a fast, easy and friendly setting. Algorithms can be combined so that a series of processes can be chained and executed consecutively, using the output of a process as input for the next; some additional filtering and image processing techniques have been included within the testbed for this purpose. A use case is included to illustrate how these processes are sequenced and its effect on the results for real applications. The testbed has been conceived as a collaborative and incremental open-source project, where its code is accessible and modifiable, with the objective of receiving contributions and releasing future versions to include new algorithms and features. It is currently available online for the research community.

This paper proposes an automatic method based on the deterministic simulated annealing (DSA) approach for solving the image change detection problem between two images where one of them is the reference image. Each pixel in the reference image is considered as a node with a state value in a network of nodes. This state determines the magnitude of the change. The DSA optimization approach tries to achieve the most network stable configuration based on the minimization of an energy function. The DSA scheme allows the mapping of interpixel contextual dependencies which has been used favorably in some existing image change detection strategies. The main contribution of the DSA is exactly its ability for avoiding local minima during the optimization process thanks to the annealing scheme. Local minima have been detected when using some optimization strategies, such as Hopfield neural networks, in images with large amount of changes, greater than the 20%. The DSA performs better than other optimization strategies for images with a large amount of changes and obtain similar results for images where the changes are small. Hence, the DSA approach appears to be a general method for image change detection independently of the amount of changes. Its performance is compared against some recent image change detection methods.

[EN] The trajectory generation and its replanning in hostile environments for UAVs (Unmanned Aerial Vehicles) is a discipline in expansion. The hostile environments contains threats, modelled here as radars. Initially a route is planned. Then, if during the fly arise pop-up threats, a replanning is carried out. In both cases the routes are obtained via the A* algorithm. When replanning, the UAV makes a decision about whether to continue the initial plan or to follow the replanned route. The multiattribute decision making theory is a suitable strategy., [ES] La generación de trayectorias y la replanificación de las mismas en entornos hostiles para UAVs (Unmanned Aerial Vehicles) es una disciplina en auge. Los entornos hostiles se caracterizan por la presencia de amenazas, modeladas aquí como radares. Inicialmente se planifica una ruta. Si en vuelo surgen nuevas amenazas, la ruta inicial se replanifica. En ambos casos las rutas se obtienen mediante el algoritmo A*. Ante una replanificación el UAV toma una decisión sobre si continuar por la ruta inicial o por la replanificada. La teoría de la decisión multiatributo proporciona en este caso el mecanismo adecuado., La investigación realizada ha sido financiada por el proyecto “COSICOLOGI” S-0505/DPI-0391 de la Comunidad Autónoma de Madrid, así como por el Ministerio de Educación y Ciencia bajo el proyecto “Planificación, simulación y control para cooperación de múltiples UAVs”. También ha sido desarrollada al amparo del proyecto 353/2005 titulado Evaluación de Técnicas de Inteligencia Artificial para toma de Decisiones y Optimización de Estrategias entre la Universidad Complutense de Madrid y la empresa EADS-Casa.

This paper proposes a Bayesian approach for minimizing the time of finding an object of uncertain location and dynamics using several moving sensing agents with constrained dynamics. The approach exploits twice the Bayesian theory: on one hand, it uses a Bayesian formulation of the objective functions that compare the constrained paths of the agents and on the other hand, a Bayesian optimization algorithm to solve the problem. By combining both elements, our approach handles successfully this complex problem, as illustrated by the results over different scenarios presented and statistically analyzed in the paper. Finally, the paper also discusses other formulations of the problem and compares the properties of our approach with others closely related.

This paper proposes a new method, oriented to crop row detection in images from maize fields with high weed pressure. The vision system is designed to be installed onboard a mobile agricultural vehicle, i.e. submitted to gyros, vibrations and undesired movements. The images are captured under image perspective, being affected by the above undesired effects. The image processing consists of three main processes: image segmentation, double thresholding, based on the Otsu's method, and crop row detection. Image segmentation is based on the application of a vegetation index, the double thresholding achieves the separation between weeds and crops and the crop row detection applies least squares linear regression for line adjustment. Crop and weed separation becomes effective and the crop row detection can be favorably compared against the classical approach based on the Hough transform. Both gain effectiveness and accuracy thanks to the double thresholding that makes the main finding of the paper.

This paper formulates and proposes a discrete solution for the problem of finding a lost target under uncertainty in minimum time (Minimum Time Search). Given a searching region where some information about the target is known but uncertain (i.e. location and dynamics), and a searching agent with constrained dynamics, we provide two decision making algorithms that optimizes the agent actions to find the target in a minimum time. The problem is faced as a discrete optimization: the actions and the sensor are discrete, and the target probabilistic model is described over a graph, where each vertex contains the target's location probability information and each edge defines the agent possible actions. We revisit the mathematical model of the optimal search problem and we propose a novel approach to include the time into the decision making by reinterpreting it as a maximum discounted time reward problem. The optimal decision plan for the agent is obtained by solving this non convex discrete problem using the cross entropy method. By performing statistical simulations we show how the target is found in minimum time.

Stereoscopic vision systems have been used manually for decades to capture threedimensional information of the environment in different applications. With the growth experienced in recent years by the techniques of computer image processing, stereoscopic vision has been increasingly incorporating automated systems of different nature. The central problem in the automation of a stereoscopic vision system is the determination of the correspondence between pixels of the pair of stereoscopic images that come from the same point in three-dimensional scene. The research undertaken in this work comprises the design of a global strategy to solve the stereoscopic correspondence problem for a specific kind of hemispherical image from forest environments. The images are obtained through an optical system based on the lens known as fisheye because this optic system can recover 3D information in a large field-of-view around the camera; in our system it is 183o×360o. This is an important advantage because it allows one to image the trees in the 3D scene close to the system from the base to the top, unlike in systems equipped with conventional lenses where close objects are partially mapped (Abraham & Forstner, 2005). The focus is on obtaining this information from tree trunks using stereoscopic images. The technicians carry out forest inventories which include studies on wood volume and tree density as well as the evolution and growth of the trees with the measurements obtained. Because the trees appear completely imaged, the stereoscopic system allows the calculation of distances from the device to significant points into the trees in the 3D scene, including diameters along the stem, heights and crown dimensions to be measured, as well as determining the position of the trees. These data may be used to obtain precise taper equations, leaf area or volume estimations (Montes et al., 2009). As the distance from the device to each tree can be calculated, the density of trees within a determined area can be also surveyed and growing stock; tree density, basal area (the section of stems at 1.30 m height in a hectare) and other interesting variables may be estimated at forest stand level using statistical inference (Gregoire, 1998).

We present a novel strategy for computing disparity maps from omni-directional stereo images obtained with fish-eye lenses in forest environments. At a first segmentation stage, the method identifies textures of interest to be either matched or discarded. Two of them are identified by applying the powerful Support Vector Machines approach. At a second stage, a stereovision matching process is designed based on the application of four stereovision matching constraints: epipolarity, similarity, uniqueness and smoothness. The epipolarity guides the process. The similarity and uniqueness are mapped once again through the Support Vector Machines, but under a different way to the previous case; after this an initial disparity map is obtained. This map is later filtered by applying the Discrete Simulated Annealing framework where the smoothness constraint is conveniently mapped. The combination of the segmentation and stereovision matching approaches makes the main contribution. The method is compared against the usage of simple features and combined similarity matching strategies. (C) 2011 Elsevier Ltd. All rights reserved.

We present a novel strategy for computing disparity maps from hemispherical stereo images obtained with fish-eye lenses in forest environments. At a first segmentation stage, the method identifies textures of interest to be either matched or discarded. This is achieved by applying a pattern recognition strategy based on the combination of two classifiers: Fuzzy Clustering and Bayesian. At a second stage, a stereovision matching process is performed based on the application of four stereovision matching constraints: epipolar, similarity, uniqueness and smoothness. The epipolar constraint guides the process. The similarity and uniqueness are mapped through a decision making strategy based on a weighted fuzzy similarity approach, obtaining a disparity map. This map is later filtered through the Hopfield Neural Network framework by considering the smoothness constraint. The combination of the segmentation and stereovision matching approaches makes the main contribution. The method is compared against the usage of simple features and combined similarity matching strategies.

This paper describes a device, based on stereovision, which is designed for forest inventories purposes. It captures pairs of omni-directional stereoscopic images through a fish-eye lens, from which different tri-dimensional measures can be obtained by applying a stereovision process, including image acquisition, feature and attribute extraction, feature matching and depth determination. This paper explains and summarizes two specific methods for solving the matching problem, as the key step in stereovision. They are pixel-based and region-based, applied in two kinds of forests environments, the first one highly illuminated and the second one with poor illumination. The performance achieved validates both designs.

Computer vision is an emerging area which is demanding solutions for solving different problems. The data to be processed are bi-dimensional (2D) images captured from the tri-dimensional (3D) scene. The objects in 3D are generally composed of related parts that joined form the whole object. Fortunately, the relations in 3D are preserved in 2D. Hence, we can exploit this fact by considering specific and basic elements which are related to other elements in the 2D images. The relations with other elements allow establishing a link among them. Hence, we have the necessary ingredients to build a structure under the Fuzzy Cognitive Maps (FCMs) paradigm. FCMs have been satisfactorily used in several areas of computer vision including: pattern recognition, image change detection or stereo vision matching. In this chapter we establish the general framework of fuzzy cognitive maps in the context of 2D images and describe three applications in the three mentioned areas of computer vision. We also give some details about the performance of this paradigm in these applications.

This work presents a strategy to track and describe the boundary of an environmental surface using a sequence of incomplete boundary images coming from an UAV with a camera onboard. The algorithm uses all captured images to feed the trajectory, which drives the UAV towards the next point to take the next shot, until the identification is completed. The multiple patterns of the input image make the problem difficult. Our approach orders the points of the image to identify the existent edges, and computes the trajectory as a minimization problem using a multi-objective function that gathers information about the boundary and the polynomial that fit in these edges.

This paper describes a novel stereovision matching approach based on omni-directional images obtained with fish-eye lenses in forest environments. The goal is to obtain a disparity map as a previous step for determining the volume of wood in the imaged area. The interest is focused on the trunks of the trees. Due to the irregular distribution of the trunks, the most suitable features are the pixels. A set of six attributes is used for establishing the matching between the pixels in both images of each stereo pair analysed. The final decision about the matched pixels is taken based on a well tested Fuzzy Multi-Criteria Decision Making approach, where the attributes determine the criteria and the potential matches in one image of the stereo pair for a given pixel in the other one determine the alternatives. The application of this decision making approach makes the main finding of the paper. The full procedure is based on the application of three well known matching constraints. The proposed approach is compared favourably against the usage of simple features.

This paper describes a novel stereovision matching approach by combining several attributes at the pixel level for omni-directional images obtained with fish-eye lenses in forest environments. The goal is to obtain a disparity map as a previous step for determining distances to the trees and then the volume of wood in the imaged area. The interest is focused on the trunks of the trees. Because of the irregular distribution of the trunks, the most suitable features are the pixels. A set of six attributes is used for establishing the matching between the pixels in both images of the stereo pair. The final decision about the matched pixels is taken by combining the attributes. Two combined strategies are proposed: the Sugeno Fuzzy Integral and the Dempster-Shafer theory. The combined strategies, applied to our specific stereo vision matching problem, make the main finding of the paper. In both, the combination is based on the application of three well known matching constraints. The proposed approaches are compared among them and favourably against the usage of simple features.

This paper describes a novel stereovision matching approach based on omni-directional images obtained with fish-eye lenses in forest environments. The goal is to obtain a disparity map as a previous step for determining the volume of wood in the imaged area. The interest is focused on the trunks of the trees, due to the irregular distribution of the trunks; the most suitable features are the pixels. A set of six attributes is used for establishing the matching between the pixels in both images of the stereo pair. The final decision about the matched pixel is taken based on the Choquet Fuzzy Integral paradigm, which is a technique well tested for combining classifiers. The use and adjusting of this decision approach to our specific stereo vision matching problem makes the main finding of the paper. The procedure is based on the application of three well known matching constraints. The proposed approach is compared favourably against the usage of simple features and other fuzzy strategy that combines the simple ones.

This paper describes a novel feature-based stereovision matching process based on a pair of omnidirectional images in forest stands acquired with a stereovision sensor equipped with fish-eye lenses. The stereo analysis problem consists of the following steps image acquisition, camera modelling, feature extraction, image matching and depth determination. Once the depths of significant points on the trees are obtained, the growing stock volume can be estimated by considering the geometrical camera modelling, which is the final goal. The key steps are feature extraction and image matching. This paper is devoted solely to these two steps. At a first stage a segmentation process extracts the trunks, which are the regions used as features, where each feature is identified through a set of attributes of properties useful for matching. In the second step the features are matched based on the application of the following four well known matching constraints, epipolar, similarity, ordering and uniqueness. The combination of the segmentation and matching processes for this specific kind of sensors make the main contribution of the paper. The method is tested with satisfactory results and compared against the human expert criterion. © 2009 by the authors.

This paper presents an approach to trajectory generation for unmanned aerial vehicles (UAV) by using mixed integer linear programming (MILP) and a modification of the A* algorithm to optimize paths in dynamic environments, particularly having pop-ups with a known future probability of appearance. Each pop-up leads to one or several possible evasion maneuvers, characterized with a set of values used as decision making parameters in an integer linear programming (ILP) model that optimizes the final route by choosing the most suitable alternative trajectories, according to the imposed constrains such as maximum fuel consumption and spent time. The model of the system in MILP and A* algorithms is presented, as well as the ILP formulation for decision making. Results and discussions are given to promote future real time implementations.

This paper outlines a neural network model based on the Fuzzy Cognitive Maps (FCM) framework for solving the automatic image change detection problem. Each pixel in the reference image is assumed to be a node in the network. Each node has associated a fuzzy value, which determines the magnitude of the change. Each fuzzy value is updated by a trade-off between the influences received from the fuzzy values from other neurons and its own fuzzy value. Classical approaches in the literature have been designed assuming that the mutual influences between two nodes are symmetric. The main finding of this paper is the assumption that mutual influences could not be symmetric. This non symmetric relationship can be embedded by the FCM paradigm. The performance of the proposed method is illustrated by comparative analysis against some recent image change detection methods.

This paper presents an approach to trajectories optimization for unmanned aerial vehicle (UAV) in presence of obstacles, waypoints, and threat zones such as radar detection regions, using mixed integer linear programming (MILP). The main result is the linear approximation of a nonlinear radar detection risk function with integer constraints and indicator 0-1 variables. Several results are presented to show that the approach can yields trajectories depending on the acceptable risk of detection.

Under illumination variations image change detection becomes a difficult task. Some existing image change detection methods try to compensate this effect. It is assumed that an image can be expressed in terms of its illumination and reflectance components. Detection of changes in the reflectance component is directly related to scene changes. In general, scene illumination varies slowly over space, whereas the reflectance component contains mainly spatially high frequency details. The intention is to apply the image change detection algorithm to the reflectance component only. The aim of this work is to analyze the performance of different homomorphic pre-filtering schemes for extracting the reflectance component so that the image change detection algorithm is applied only to this component. This scheme is not suitable for scenes without spatial high frequency details.

A system is presented for exploiting restricted-and-parallelism (RAP) in logic programs on a distributed (nonshared memory) architecture. The system uses global compilation techniques and is designed using the new generation of transputers (H1/C104). Externally, the system behaves as a sequential one, in which, the solutions are always produced according to the depth-first strategy. >

Many problems from artificial intelligence can be described as constraint satisfaction problems over finite domains (CSP(FD)), that is, a solution is an assignment of a value to each problem variable such that a set of constraints is satisfied. Arc-consistency algorithms remove inconsistent values from the set of values that can be assigned to a variable (its domain), thus reducing the search space. We have developed a parallelisation scheme of arc-consistency to be run on MIMD multiprocessor. The set of constraints is divided into N partitions, which are executed in parallel on N processors. The parallelisation scheme has been implemented on a CRAY T3E multiprocessor with up to thirty-four processors. Empirical results on speedup and behaviour are reported and discussed.

This paper describes a parallel model for a distributed memory architecture of a non traditional evolutionary computation method, which integrates constraint propagation and evolution programs. This integration provides a problem-independent optimisation strategy for large scale constrained combinatorial problems over finite integer domains. We have adopted a global parallelisation approach which preserves the properties, behaviour, and theoretical studies of the sequential algorithm. Moreover, high speedup is achieved since genetic operators are coarsegrained, as they perform a search in a discrete space carrying out constraint propagation. A global parallelisation implies a single population but, as we focus on distributed memory architectures, the single virtual population is physically distributed among the processors. Selection and mating consider all the individuals in the population, but the application of genetic operators is performed in parallel. The implementation of the model has been tested on a CRAY T3E multiprocessor using two complex constrained optimisation problems. Experiments have proved the efficiency of this approach since linear speedups have been obtained.

The paper describes a multimicrocomputer system for hotel automation. The system picks up hotel-generated data in order to provide the actual status at any moment, and performs status-dependent operations to provide: a) service to guest, b) security in the hotel, and c) statistical and accounting information for management purposes.