26 resultados para computer vision,machine learning,centernet,volleyball,sports
Resumo:
La familia de algoritmos de Boosting son un tipo de técnicas de clasificación y regresión que han demostrado ser muy eficaces en problemas de Visión Computacional. Tal es el caso de los problemas de detección, de seguimiento o bien de reconocimiento de caras, personas, objetos deformables y acciones. El primer y más popular algoritmo de Boosting, AdaBoost, fue concebido para problemas binarios. Desde entonces, muchas han sido las propuestas que han aparecido con objeto de trasladarlo a otros dominios más generales: multiclase, multilabel, con costes, etc. Nuestro interés se centra en extender AdaBoost al terreno de la clasificación multiclase, considerándolo como un primer paso para posteriores ampliaciones. En la presente tesis proponemos dos algoritmos de Boosting para problemas multiclase basados en nuevas derivaciones del concepto margen. El primero de ellos, PIBoost, está concebido para abordar el problema descomponiéndolo en subproblemas binarios. Por un lado, usamos una codificación vectorial para representar etiquetas y, por otro, utilizamos la función de pérdida exponencial multiclase para evaluar las respuestas. Esta codificación produce un conjunto de valores margen que conllevan un rango de penalizaciones en caso de fallo y recompensas en caso de acierto. La optimización iterativa del modelo genera un proceso de Boosting asimétrico cuyos costes dependen del número de etiquetas separadas por cada clasificador débil. De este modo nuestro algoritmo de Boosting tiene en cuenta el desbalanceo debido a las clases a la hora de construir el clasificador. El resultado es un método bien fundamentado que extiende de manera canónica al AdaBoost original. El segundo algoritmo propuesto, BAdaCost, está concebido para problemas multiclase dotados de una matriz de costes. Motivados por los escasos trabajos dedicados a generalizar AdaBoost al terreno multiclase con costes, hemos propuesto un nuevo concepto de margen que, a su vez, permite derivar una función de pérdida adecuada para evaluar costes. Consideramos nuestro algoritmo como la extensión más canónica de AdaBoost para este tipo de problemas, ya que generaliza a los algoritmos SAMME, Cost-Sensitive AdaBoost y PIBoost. Por otro lado, sugerimos un simple procedimiento para calcular matrices de coste adecuadas para mejorar el rendimiento de Boosting a la hora de abordar problemas estándar y problemas con datos desbalanceados. Una serie de experimentos nos sirven para demostrar la efectividad de ambos métodos frente a otros conocidos algoritmos de Boosting multiclase en sus respectivas áreas. En dichos experimentos se usan bases de datos de referencia en el área de Machine Learning, en primer lugar para minimizar errores y en segundo lugar para minimizar costes. Además, hemos podido aplicar BAdaCost con éxito a un proceso de segmentación, un caso particular de problema con datos desbalanceados. Concluimos justificando el horizonte de futuro que encierra el marco de trabajo que presentamos, tanto por su aplicabilidad como por su flexibilidad teórica. Abstract The family of Boosting algorithms represents a type of classification and regression approach that has shown to be very effective in Computer Vision problems. Such is the case of detection, tracking and recognition of faces, people, deformable objects and actions. The first and most popular algorithm, AdaBoost, was introduced in the context of binary classification. Since then, many works have been proposed to extend it to the more general multi-class, multi-label, costsensitive, etc... domains. Our interest is centered in extending AdaBoost to two problems in the multi-class field, considering it a first step for upcoming generalizations. In this dissertation we propose two Boosting algorithms for multi-class classification based on new generalizations of the concept of margin. The first of them, PIBoost, is conceived to tackle the multi-class problem by solving many binary sub-problems. We use a vectorial codification to represent class labels and a multi-class exponential loss function to evaluate classifier responses. This representation produces a set of margin values that provide a range of penalties for failures and rewards for successes. The stagewise optimization of this model introduces an asymmetric Boosting procedure whose costs depend on the number of classes separated by each weak-learner. In this way the Boosting procedure takes into account class imbalances when building the ensemble. The resulting algorithm is a well grounded method that canonically extends the original AdaBoost. The second algorithm proposed, BAdaCost, is conceived for multi-class problems endowed with a cost matrix. Motivated by the few cost-sensitive extensions of AdaBoost to the multi-class field, we propose a new margin that, in turn, yields a new loss function appropriate for evaluating costs. Since BAdaCost generalizes SAMME, Cost-Sensitive AdaBoost and PIBoost algorithms, we consider our algorithm as a canonical extension of AdaBoost to this kind of problems. We additionally suggest a simple procedure to compute cost matrices that improve the performance of Boosting in standard and unbalanced problems. A set of experiments is carried out to demonstrate the effectiveness of both methods against other relevant Boosting algorithms in their respective areas. In the experiments we resort to benchmark data sets used in the Machine Learning community, firstly for minimizing classification errors and secondly for minimizing costs. In addition, we successfully applied BAdaCost to a segmentation task, a particular problem in presence of imbalanced data. We conclude the thesis justifying the horizon of future improvements encompassed in our framework, due to its applicability and theoretical flexibility.
Resumo:
A more natural, intuitive, user-friendly, and less intrusive Human–Computer interface for controlling an application by executing hand gestures is presented. For this purpose, a robust vision-based hand-gesture recognition system has been developed, and a new database has been created to test it. The system is divided into three stages: detection, tracking, and recognition. The detection stage searches in every frame of a video sequence potential hand poses using a binary Support Vector Machine classifier and Local Binary Patterns as feature vectors. These detections are employed as input of a tracker to generate a spatio-temporal trajectory of hand poses. Finally, the recognition stage segments a spatio-temporal volume of data using the obtained trajectories, and compute a video descriptor called Volumetric Spatiograms of Local Binary Patterns (VS-LBP), which is delivered to a bank of SVM classifiers to perform the gesture recognition. The VS-LBP is a novel video descriptor that constitutes one of the most important contributions of the paper, which is able to provide much richer spatio-temporal information than other existing approaches in the state of the art with a manageable computational cost. Excellent results have been obtained outperforming other approaches of the state of the art.
Resumo:
The aim of this Master Thesis is the analysis, design and development of a robust and reliable Human-Computer Interaction interface, based on visual hand-gesture recognition. The implementation of the required functions is oriented to the simulation of a classical hardware interaction device: the mouse, by recognizing a specific hand-gesture vocabulary in color video sequences. For this purpose, a prototype of a hand-gesture recognition system has been designed and implemented, which is composed of three stages: detection, tracking and recognition. This system is based on machine learning methods and pattern recognition techniques, which have been integrated together with other image processing approaches to get a high recognition accuracy and a low computational cost. Regarding pattern recongition techniques, several algorithms and strategies have been designed and implemented, which are applicable to color images and video sequences. The design of these algorithms has the purpose of extracting spatial and spatio-temporal features from static and dynamic hand gestures, in order to identify them in a robust and reliable way. Finally, a visual database containing the necessary vocabulary of gestures for interacting with the computer has been created.
Resumo:
OntoTag - A Linguistic and Ontological Annotation Model Suitable for the Semantic Web
1. INTRODUCTION. LINGUISTIC TOOLS AND ANNOTATIONS: THEIR LIGHTS AND SHADOWS
Computational Linguistics is already a consolidated research area. It builds upon the results of other two major ones, namely Linguistics and Computer Science and Engineering, and it aims at developing computational models of human language (or natural language, as it is termed in this area). Possibly, its most well-known applications are the different tools developed so far for processing human language, such as machine translation systems and speech recognizers or dictation programs.
These tools for processing human language are commonly referred to as linguistic tools. Apart from the examples mentioned above, there are also other types of linguistic tools that perhaps are not so well-known, but on which most of the other applications of Computational Linguistics are built. These other types of linguistic tools comprise POS taggers, natural language parsers and semantic taggers, amongst others. All of them can be termed linguistic annotation tools.
Linguistic annotation tools are important assets. In fact, POS and semantic taggers (and, to a lesser extent, also natural language parsers) have become critical resources for the computer applications that process natural language. Hence, any computer application that has to analyse a text automatically and ‘intelligently’ will include at least a module for POS tagging. The more an application needs to ‘understand’ the meaning of the text it processes, the more linguistic tools and/or modules it will incorporate and integrate.
However, linguistic annotation tools have still some limitations, which can be summarised as follows:
1. Normally, they perform annotations only at a certain linguistic level (that is, Morphology, Syntax, Semantics, etc.).
2. They usually introduce a certain rate of errors and ambiguities when tagging. This error rate ranges from 10 percent up to 50 percent of the units annotated for unrestricted, general texts.
3. Their annotations are most frequently formulated in terms of an annotation schema designed and implemented ad hoc.
A priori, it seems that the interoperation and the integration of several linguistic tools into an appropriate software architecture could most likely solve the limitations stated in (1). Besides, integrating several linguistic annotation tools and making them interoperate could also minimise the limitation stated in (2). Nevertheless, in the latter case, all these tools should produce annotations for a common level, which would have to be combined in order to correct their corresponding errors and inaccuracies. Yet, the limitation stated in (3) prevents both types of integration and interoperation from being easily achieved.
In addition, most high-level annotation tools rely on other lower-level annotation tools and their outputs to generate their own ones. For example, sense-tagging tools (operating at the semantic level) often use POS taggers (operating at a lower level, i.e., the morphosyntactic) to identify the grammatical category of the word or lexical unit they are annotating. Accordingly, if a faulty or inaccurate low-level annotation tool is to be used by other higher-level one in its process, the errors and inaccuracies of the former should be minimised in advance. Otherwise, these errors and inaccuracies would be transferred to (and even magnified in) the annotations of the high-level annotation tool.
Therefore, it would be quite useful to find a way to
(i) correct or, at least, reduce the errors and the inaccuracies of lower-level linguistic tools;
(ii) unify the annotation schemas of different linguistic annotation tools or, more generally speaking, make these tools (as well as their annotations) interoperate.
Clearly, solving (i) and (ii) should ease the automatic annotation of web pages by means of linguistic tools, and their transformation into Semantic Web pages (Berners-Lee, Hendler and Lassila, 2001). Yet, as stated above, (ii) is a type of interoperability problem. There again, ontologies (Gruber, 1993; Borst, 1997) have been successfully applied thus far to solve several interoperability problems. Hence, ontologies should help solve also the problems and limitations of linguistic annotation tools aforementioned.
Thus, to summarise, the main aim of the present work was to combine somehow these separated approaches, mechanisms and tools for annotation from Linguistics and Ontological Engineering (and the Semantic Web) in a sort of hybrid (linguistic and ontological) annotation model, suitable for both areas. This hybrid (semantic) annotation model should (a) benefit from the advances, models, techniques, mechanisms and tools of these two areas; (b) minimise (and even solve, when possible) some of the problems found in each of them; and (c) be suitable for the Semantic Web. The concrete goals that helped attain this aim are presented in the following section.
2. GOALS OF THE PRESENT WORK
As mentioned above, the main goal of this work was to specify a hybrid (that is, linguistically-motivated and ontology-based) model of annotation suitable for the Semantic Web (i.e. it had to produce a semantic annotation of web page contents). This entailed that the tags included in the annotations of the model had to (1) represent linguistic concepts (or linguistic categories, as they are termed in ISO/DCR (2008)), in order for this model to be linguistically-motivated; (2) be ontological terms (i.e., use an ontological vocabulary), in order for the model to be ontology-based; and (3) be structured (linked) as a collection of ontology-based
Resumo:
Detecting user affect automatically during real-time conversation is the main challenge towards our greater aim of infusing social intelligence into a natural-language mixed-initiative High-Fidelity (Hi-Fi) audio control spoken dialog agent. In recent years, studies on affect detection from voice have moved on to using realistic, non-acted data, which is subtler. However, it is more challenging to perceive subtler emotions and this is demonstrated in tasks such as labelling and machine prediction. This paper attempts to address part of this challenge by considering the role of user satisfaction ratings and also conversational/dialog features in discriminating contentment and frustration, two types of emotions that are known to be prevalent within spoken human-computer interaction. However, given the laboratory constraints, users might be positively biased when rating the system, indirectly making the reliability of the satisfaction data questionable. Machine learning experiments were conducted on two datasets, users and annotators, which were then compared in order to assess the reliability of these datasets. Our results indicated that standard classifiers were significantly more successful in discriminating the abovementioned emotions and their intensities (reflected by user satisfaction ratings) from annotator data than from user data. These results corroborated that: first, satisfaction data could be used directly as an alternative target variable to model affect, and that they could be predicted exclusively by dialog features. Second, these were only true when trying to predict the abovementioned emotions using annotator?s data, suggesting that user bias does exist in a laboratory-led evaluation.
Resumo:
Purely data-driven approaches for machine learning present difficulties when data are scarce relative to the complexity of the model or when the model is forced to extrapolate. On the other hand, purely mechanistic approaches need to identify and specify all the interactions in the problem at hand (which may not be feasible) and still leave the issue of how to parameterize the system. In this paper, we present a hybrid approach using Gaussian processes and differential equations to combine data-driven modeling with a physical model of the system. We show how different, physically inspired, kernel functions can be developed through sensible, simple, mechanistic assumptions about the underlying system. The versatility of our approach is illustrated with three case studies from motion capture, computational biology, and geostatistics.
Resumo:
An important part of human intelligence, both historically and operationally, is our ability to communicate. We learn how to communicate, and maintain our communicative skills, in a society of communicators – a highly effective way to reach and maintain proficiency in this complex skill. Principles that might allow artificial agents to learn language this way are in completely known at present – the multi-dimensional nature of socio-communicative skills are beyond every machine learning framework so far proposed. Our work begins to address the challenge of proposing a way for observation-based machine learning of natural language and communication. Our framework can learn complex communicative skills with minimal up-front knowledge. The system learns by incrementally producing predictive models of causal relationships in observed data, guided by goal-inference and reasoning using forward-inverse models. We present results from two experiments where our S1 agent learns human communication by observing two humans interacting in a realtime TV-style interview, using multimodal communicative gesture and situated language to talk about recycling of various materials and objects. S1 can learn multimodal complex language and multimodal communicative acts, a vocabulary of 100 words forming natural sentences with relatively complex sentence structure, including manual deictic reference and anaphora. S1 is seeded only with high-level information about goals of the interviewer and interviewee, and a small ontology; no grammar or other information is provided to S1 a priori. The agent learns the pragmatics, semantics, and syntax of complex utterances spoken and gestures from scratch, by observing the humans compare and contrast the cost and pollution related to recycling aluminum cans, glass bottles, newspaper, plastic, and wood. After 20 hours of observation S1 can perform an unscripted TV interview with a human, in the same style, without making mistakes.
Resumo:
An automatic machine learning strategy for computing the 3D structure of monocular images from a single image query using Local Binary Patterns is presented. The 3D structure is inferred through a training set composed by a repository of color and depth images, assuming that images with similar structure present similar depth maps. Local Binary Patterns are used to characterize the structure of the color images. The depth maps of those color images with a similar structure to the query image are adaptively combined and filtered to estimate the final depth map. Using public databases, promising results have been obtained outperforming other state-of-the-art algorithms and with a computational cost similar to the most efficient 2D-to-3D algorithms.
Resumo:
El principal objetivo de este trabajo es proporcionar una solución en tiempo real basada en visión estéreo o monocular precisa y robusta para que un vehículo aéreo no tripulado (UAV) sea autónomo en varios tipos de aplicaciones UAV, especialmente en entornos abarrotados sin señal GPS. Este trabajo principalmente consiste en tres temas de investigación de UAV basados en técnicas de visión por computador: (I) visual tracking, proporciona soluciones efectivas para localizar visualmente objetos de interés estáticos o en movimiento durante el tiempo que dura el vuelo del UAV mediante una aproximación adaptativa online y una estrategia de múltiple resolución, de este modo superamos los problemas generados por las diferentes situaciones desafiantes, tales como cambios significativos de aspecto, iluminación del entorno variante, fondo del tracking embarullado, oclusión parcial o total de objetos, variaciones rápidas de posición y vibraciones mecánicas a bordo. La solución ha sido utilizada en aterrizajes autónomos, inspección de plataformas mar adentro o tracking de aviones en pleno vuelo para su detección y evasión; (II) odometría visual: proporciona una solución eficiente al UAV para estimar la posición con 6 grados de libertad (6D) usando únicamente la entrada de una cámara estéreo a bordo del UAV. Un método Semi-Global Blocking Matching (SGBM) eficiente basado en una estrategia grueso-a-fino ha sido implementada para una rápida y profunda estimación del plano. Además, la solución toma provecho eficazmente de la información 2D y 3D para estimar la posición 6D, resolviendo de esta manera la limitación de un punto de referencia fijo en la cámara estéreo. Una robusta aproximación volumétrica de mapping basada en el framework Octomap ha sido utilizada para reconstruir entornos cerrados y al aire libre bastante abarrotados en 3D con memoria y errores correlacionados espacialmente o temporalmente; (III) visual control, ofrece soluciones de control prácticas para la navegación de un UAV usando Fuzzy Logic Controller (FLC) con la estimación visual. Y el framework de Cross-Entropy Optimization (CEO) ha sido usado para optimizar el factor de escala y la función de pertenencia en FLC. Todas las soluciones basadas en visión en este trabajo han sido probadas en test reales. Y los conjuntos de datos de imágenes reales grabados en estos test o disponibles para la comunidad pública han sido utilizados para evaluar el rendimiento de estas soluciones basadas en visión con ground truth. Además, las soluciones de visión presentadas han sido comparadas con algoritmos de visión del estado del arte. Los test reales y los resultados de evaluación muestran que las soluciones basadas en visión proporcionadas han obtenido rendimientos en tiempo real precisos y robustos, o han alcanzado un mejor rendimiento que aquellos algoritmos del estado del arte. La estimación basada en visión ha ganado un rol muy importante en controlar un UAV típico para alcanzar autonomía en aplicaciones UAV. ABSTRACT The main objective of this dissertation is providing real-time accurate robust monocular or stereo vision-based solution for Unmanned Aerial Vehicle (UAV) to achieve the autonomy in various types of UAV applications, especially in GPS-denied dynamic cluttered environments. This dissertation mainly consists of three UAV research topics based on computer vision technique: (I) visual tracking, it supplys effective solutions to visually locate interesting static or moving object over time during UAV flight with on-line adaptivity approach and multiple-resolution strategy, thereby overcoming the problems generated by the different challenging situations, such as significant appearance change, variant surrounding illumination, cluttered tracking background, partial or full object occlusion, rapid pose variation and onboard mechanical vibration. The solutions have been utilized in autonomous landing, offshore floating platform inspection and midair aircraft tracking for sense-and-avoid; (II) visual odometry: it provides the efficient solution for UAV to estimate the 6 Degree-of-freedom (6D) pose using only the input of stereo camera onboard UAV. An efficient Semi-Global Blocking Matching (SGBM) method based on a coarse-to-fine strategy has been implemented for fast depth map estimation. In addition, the solution effectively takes advantage of both 2D and 3D information to estimate the 6D pose, thereby solving the limitation of a fixed small baseline in the stereo camera. A robust volumetric occupancy mapping approach based on the Octomap framework has been utilized to reconstruct indoor and outdoor large-scale cluttered environments in 3D with less temporally or spatially correlated measurement errors and memory; (III) visual control, it offers practical control solutions to navigate UAV using Fuzzy Logic Controller (FLC) with the visual estimation. And the Cross-Entropy Optimization (CEO) framework has been used to optimize the scaling factor and the membership function in FLC. All the vision-based solutions in this dissertation have been tested in real tests. And the real image datasets recorded from these tests or available from public community have been utilized to evaluate the performance of these vision-based solutions with ground truth. Additionally, the presented vision solutions have compared with the state-of-art visual algorithms. Real tests and evaluation results show that the provided vision-based solutions have obtained real-time accurate robust performances, or gained better performance than those state-of-art visual algorithms. The vision-based estimation has played a critically important role for controlling a typical UAV to achieve autonomy in the UAV application.
Resumo:
Uno de los mayores retos para la comunidad científica es conseguir que las máquinas posean en un futuro la capacidad del sistema visual y cognitivo humanos, de forma que, por ejemplo, en entornos de video vigilancia, puedan llegar a proporcionar de manera automática una descripción fiable de lo que está ocurriendo en la escena. En la presente tesis, mediante la propuesta de un marco de trabajo de referencia, se discuten y plantean los pasos necesarios para el desarrollo de sistemas más inteligentes capaces de extraer y analizar, a diferentes niveles de abstracción y mediante distintos módulos de procesamiento independientes, la información necesaria para comprender qué está sucediendo en un conjunto amplio de escenarios de distinta naturaleza. Se parte de un análisis de requisitos y se identifican los retos para este tipo de sistemas en la actualidad, lo que constituye en sí mismo los objetivos de esta tesis, contribuyendo así a un modelo de datos basado en el conocimiento que permitirá analizar distintas situaciones en las que personas y vehículos son los actores principales, dejando no obstante la puerta abierta a la adaptación a otros dominios. Así mismo, se estudian los distintos procesos que se pueden lanzar a nivel interno así como la necesidad de integrar mecanismos de realimentación a distintos niveles que permitan al sistema adaptarse mejor a cambios en el entorno. Como resultado, se propone un marco de referencia jerárquico que integra las capacidades de percepción, interpretación y aprendizaje para superar los retos identificados en este ámbito; y así poder desarrollar sistemas de vigilancia más robustos, flexibles e inteligentes, capaces de operar en una variedad de entornos. Resultados experimentales ejecutados sobre distintas muestras de datos (secuencias de vídeo principalmente) demuestran la efectividad del marco de trabajo propuesto respecto a otros propuestos en el pasado. Un primer caso de estudio, permite demostrar la creación de un sistema de monitorización de entornos de parking en exteriores para la detección de vehículos y el análisis de plazas libres de aparcamiento. Un segundo caso de estudio, permite demostrar la flexibilidad del marco de referencia propuesto para adaptarse a los requisitos de un entorno de vigilancia completamente distinto, como es un hogar inteligente donde el análisis automático de actividades de la vida cotidiana centra la atención del estudio. ABSTRACT One of the most ambitious objectives for the Computer Vision and Pattern Recognition research community is that machines can achieve similar capacities to the human's visual and cognitive system, and thus provide a trustworthy description of what is happening in the scene under surveillance. Thus, a number of well-established scenario understanding architectural frameworks to develop applications working on a variety of environments can be found in the literature. In this Thesis, a highly descriptive methodology for the development of scene understanding applications is presented. It consists of a set of formal guidelines to let machines extract and analyse, at different levels of abstraction and by means of independent processing modules that interact with each other, the necessary information to understand a broad set of different real World surveillance scenarios. Taking into account the challenges that working at both low and high levels offer, we contribute with a highly descriptive knowledge-based data model for the analysis of different situations in which people and vehicles are the main actors, leaving the door open for the development of interesting applications in diverse smart domains. Recommendations to let systems achieve high-level behaviour understanding will be also provided. Furthermore, feedback mechanisms are proposed to be integrated in order to let any system to understand better the environment and the logical context around, reducing thus the uncertainty and noise, and increasing its robustness and precision in front of low-level or high-level errors. As a result, a hierarchical cognitive architecture of reference which integrates the necessary perception, interpretation, attention and learning capabilities to overcome main challenges identified in this area of research is proposed; thus allowing to develop more robust, flexible and smart surveillance systems to cope with the different requirements of a variety of environments. Once crucial issues that should be treated explicitly in the design of this kind of systems have been formulated and discussed, experimental results shows the effectiveness of the proposed framework compared with other proposed in the past. Two case studies were implemented to test the capabilities of the framework. The first case study presents how the proposed framework can be used to create intelligent parking monitoring systems. The second case study demonstrates the flexibility of the system to cope with the requirements of a completely different environment, a smart home where activities of daily living are performed. Finally, general conclusions and future work lines to further enhancing the capabilities of the proposed framework are presented.
Resumo:
The emergence of new horizons in the field of travel assistant management leads to the development of cutting-edge systems focused on improving the existing ones. Moreover, new opportunities are being also presented since systems trend to be more reliable and autonomous. In this paper, a self-learning embedded system for object identification based on adaptive-cooperative dynamic approaches is presented for intelligent sensor’s infrastructures. The proposed system is able to detect and identify moving objects using a dynamic decision tree. Consequently, it combines machine learning algorithms and cooperative strategies in order to make the system more adaptive to changing environments. Therefore, the proposed system may be very useful for many applications like shadow tolls since several types of vehicles may be distinguished, parking optimization systems, improved traffic conditions systems, etc.
