Contextual Priming for Object Detection

There is general consensus that context can be a rich source of information about an object's identity, location and scale. In fact, the structure of many real-world scenes is governed by strong configurational rules akin to those that apply to a single object. Here we introduce a simple probabilistic framework for modeling the relationship between context and object properties based on the correlation between the statistics of low-level features across the entire scene and the objects that it contains. The resulting scheme serves as an effective procedure for object priming, context driven focus of attention and automatic scale-selection on real-world scenes.

Rotation Invariant Object Recognition from One Training Example

Local descriptors are increasingly used for the task of object recognition because of their perceived robustness with respect to occlusions and to global geometrical deformations. Such a descriptor--based on a set of oriented Gaussian derivative filters-- is used in our recognition system. We report here an evaluation of several techniques for orientation estimation to achieve rotation invariance of the descriptor. We also describe feature selection based on a single training image. Virtual images are generated by rotating and rescaling the image and robust features are selected. The results confirm robust performance in cluttered scenes, in the presence of partial occlusions, and when the object is embedded in different backgrounds.

Object Detection in Images by Components

In this paper we present a component based person detection system that is capable of detecting frontal, rear and near side views of people, and partially occluded persons in cluttered scenes. The framework that is described here for people is easily applied to other objects as well. The motivation for developing a component based approach is two fold: first, to enhance the performance of person detection systems on frontal and rear views of people and second, to develop a framework that directly addresses the problem of detecting people who are partially occluded or whose body parts blend in with the background. The data classification is handled by several support vector machine classifiers arranged in two layers. This architecture is known as Adaptive Combination of Classifiers (ACC). The system performs very well and is capable of detecting people even when all components of a person are not found. The performance of the system is significantly better than a full body person detector designed along similar lines. This suggests that the improved performance is due to the components based approach and the ACC data classification structure.

Geometric Aspects of Visual Object Recognition

This thesis presents there important results in visual object recognition based on shape. (1) A new algorithm (RAST; Recognition by Adaptive Sudivisions of Tranformation space) is presented that has lower average-case complexity than any known recognition algorithm. (2) It is shown, both theoretically and empirically, that representing 3D objects as collections of 2D views (the "View-Based Approximation") is feasible and affects the reliability of 3D recognition systems no more than other commonly made approximations. (3) The problem of recognition in cluttered scenes is considered from a Bayesian perspective; the commonly-used "bounded-error errorsmeasure" is demonstrated to correspond to an independence assumption. It is shown that by modeling the statistical properties of real-scenes better, objects can be recognized more reliably.

Object and Scene Classification: what does a Supervised Approach Provide us?

Given a set of images of scenes containing different object categories (e.g. grass, roads) our objective is to discover these objects in each image, and to use this object occurrences to perform a scene classification (e.g. beach scene, mountain scene). We achieve this by using a supervised learning algorithm able to learn with few images to facilitate the user task. We use a probabilistic model to recognise the objects and further we classify the scene based on their object occurrences. Experimental results are shown and evaluated to prove the validity of our proposal. Object recognition performance is compared to the approaches of He et al. (2004) and Marti et al. (2001) using their own datasets. Furthermore an unsupervised method is implemented in order to evaluate the advantages and disadvantages of our supervised classification approach versus an unsupervised one

Scene Classification Using a Hybrid Generative/Discriminative Approach

We investigate whether dimensionality reduction using a latent generative model is beneficial for the task of weakly supervised scene classification. In detail, we are given a set of labeled images of scenes (for example, coast, forest, city, river, etc.), and our objective is to classify a new image into one of these categories. Our approach consists of first discovering latent ";topics"; using probabilistic Latent Semantic Analysis (pLSA), a generative model from the statistical text literature here applied to a bag of visual words representation for each image, and subsequently, training a multiway classifier on the topic distribution vector for each image. We compare this approach to that of representing each image by a bag of visual words vector directly and training a multiway classifier on these vectors. To this end, we introduce a novel vocabulary using dense color SIFT descriptors and then investigate the classification performance under changes in the size of the visual vocabulary, the number of latent topics learned, and the type of discriminative classifier used (k-nearest neighbor or SVM). We achieve superior classification performance to recent publications that have used a bag of visual word representation, in all cases, using the authors' own data sets and testing protocols. We also investigate the gain in adding spatial information. We show applications to image retrieval with relevance feedback and to scene classification in videos

A concurrent region growing algorithm guided by circumscribed contours

Image segmentation of natural scenes constitutes a major problem in machine vision. This paper presents a new proposal for the image segmentation problem which has been based on the integration of edge and region information. This approach begins by detecting the main contours of the scene which are later used to guide a concurrent set of growing processes. A previous analysis of the seed pixels permits adjustment of the homogeneity criterion to the region's characteristics during the growing process. Since the high variability of regions representing outdoor scenes makes the classical homogeneity criteria useless, a new homogeneity criterion based on clustering analysis and convex hull construction is proposed. Experimental results have proven the reliability of the proposed approach

A new approach to segmentation based on fusing circumscribed contours, region growing and clustering

One of the major problems in machine vision is the segmentation of images of natural scenes. This paper presents a new proposal for the image segmentation problem which has been based on the integration of edge and region information. The main contours of the scene are detected and used to guide the posterior region growing process. The algorithm places a number of seeds at both sides of a contour allowing stating a set of concurrent growing processes. A previous analysis of the seeds permits to adjust the homogeneity criterion to the regions's characteristics. A new homogeneity criterion based on clustering analysis and convex hull construction is proposed

Estado actual del sector estratégico textil-confecciones e identificación de los escenarios de desarrollo alternativos

El desarrollo del presente trabajo constituye, la aplicación del modelo del Análisis Estructural de los Sectores Estratégicos y la identificación de los escenarios de desarrollo alternativos para las empresas del Sector Textil-Confecciones de Bogota, en donde se describe el estado actual de las empresas en aspectos macroeconómicos y macroeconómicos; a continuación, se identifican los estados actuales, logros, alcances, y trazabilidad del sector. Dicha investigación se efectuó en dos etapas: la primera, corresponde al desarrollo del AESE, está compuesto por cuatro fases: en la primera, se evalúan los estados financieros de las empresas y las variables estratégicas para determinar el grado de convergencia estratégica dentro del sector; en la segunda, se lleva a cabo el levantamiento del panorama competitivo para identificar los espacios de mercado no atendidos que representan oportunidad de crecimiento. En la tercera, se realiza un diagnóstico de las Fuerzas del Mercado y en la última fase se realiza el Estudio de Competidores; en la segunda etapa de la investigación se realizo el análisis prospectivo, está compuesto por tres pasos: en el primero, a partir del desarrollo del AESE, se extrajeron las variables claves del sector y su nivel de impacto interno y externo; en el segundo, se determina la influencia que ejercen los actores presentes en el sector y por ultimo mediante una visión gerencial que contempla aspectos sociales, políticos , económicos y tecnológicos se proyectan futuros escenarios cada uno con probabilidad de ocurrencia.

Análisis de la política exterior de Brasil y Venezuela en materia energética. Periodo 2003 – 2008

El dinamismo de las políticas exteriores de Brasil y Venezuela ha sido particularmente activo en la última década. Brasil porque con su manifiesta ambición de potencia regional, se ha encargado de ejercer una fuerte influencia sobre América del Sur al mismo tiempo que toma la iniciativa en escenarios multilaterales con la grandes potencias y potencias emergentes, destacándose mundialmente. Y Venezuela porque desde la llegada al poder del presidente Hugo Chávez ha desarrollado una política exterior agresiva con los Estados Unidos y sus aliados en el continente, y extremadamente benévola con sus socios comerciales e ideológicos, usando como principal herramienta sus recursos petroleros y los dividendos que su venta le generan.

Estudio de prefactibilidad del cultivo de lombrices para la producción y comercialización de humus en Acacías Meta

El proyecto comprende una descripción de los aspectos generales que hacen referencia al sector de los abonos orgánicos en Colombia, abarcando temas como: su comportamiento, volúmenes históricos de producción a nivel nacional y los resultados de encuesta aplicada al mercado objetivo del proyecto. Después viene el desarrollo de los estudios que componen la formulación del proyecto como: Mercado (determinación del mercado objetivo, descripción del producto, el precio y estrategias de comercialización), Técnico (descripción del proceso productivo, proyección de costos, plan de inversiones, etc.), Administrativos (determinación de personal, tipo de contrato y remuneración del trabajo), Legal (se menciona el marco regulatorio de los abonos orgánicos, beneficios fiscales), Ambiental (licencias, permisos para el desarrollo del proyecto) y Financiero (supuestos, flujo de caja, escenarios y los resultados derivados de estos).

Estudio prospectivo del municipio de San Bernardo al 2016

The following one is a Prospective Plan that is focused on the development of San Bernardo's community, in which we based on the methodology and software of the French school LIPSTOR EPITA, wh ich support us to identify all the characteristics of the system by the identific ation of key variables and trough that, the identification of the objectives of the different actors, which very generously collaborated us in the development of the work. Once we analyze the information, there is created a series of hypothesis and that get scenes in the future to develop the objectives and strategic plans for the grow and develop of the study object, that is the San Bernardo town.

Estudio de prospectiva del sector asegurador

Conoc iendo la impor tancia del sector asegurador como parte de la base de l sistema financiero de un país, consideram os de gran importancia realizar un estudio que permita establecer la situac ión actual y que posic ión debe tomar el sector asegurador, para enfrent ar escenarios futuros en el corto, mediano y lar go plazo, delimitando las tendencias del me rcado y del entorno, para así crear posibles es trategias encaminadas a tornar a favor las si tuaciones adversas. Con el transcurso de los años ha evolucionado el concepto de riesgo para las Personas y a que estas han tomado conciencia de la inherencia de éste en la vida cotidiana, esto denot a el surgim iento de empresas preocupadas por satisfacer las necesidades y exigenc ias de este sector.

Interdisciplinary Pedagogical Experience for Health Human Resources Focused on the Holistic Promotion of Health and the Prevention of the Disease

The object of this experience is to offer the students the opportunity to take part in the construction of a pedagogic strategy centred on the ludic, for the promotion of the integral health and the prevention of the disease with an educational community; directed to supporting and qualifying the well-being so much individually as group. The project is designed to five years, about interdisciplinary character (Speech Therapy, Medicine, Psychology, Nursery, Occupational Therapy), interinstitutional (Universidad del Rosario, Universidad de San Buenaventura y Universidad de Cundinamarca) and intersectorial (Education and Health). It considers the different actors of the educational community and school and the home as propitious scenes for the strengthening potential, beside being the fundamental spaces for the construction of knowledges and learnings concerning the integral health. To achieve the target, one has come constructing from the second semester of 2003, one pedagogic strategy centred on the ludic and the creativity, from which they are planned, they develop and evaluate the actions of promotion of skills, values, behaviors and attitudes in the care of the health and the prevention of disease, orientated to the early, opportune and effective detection of risk factors and problematic of the development that they affect the integral health. The above mentioned strategy raises a so called scene Bienestarópolis: A healthy world for conquering, centred on prominent figures, spaces and elements that alternate between the fantasy and the reality to facilitate the approximation, the interiorización and the appropriation of the integral health. Across this one, the children motivated by the adults enter an imaginary world in that theirs desires, knowledges and attitudes are the axis of his development. Since Vigotsky raises it, in the game the child realizes actions in order to adapt to the world that surrounds it acquiring skills for the learning. The actions of the project have involved 410 children and 25 teachers, of the degrees Zero, The First and The Second of basic primary; 90 parents of family, and an average of 40 students and 8 teachers of the already mentioned disciplines.

Rol del terapeuta ocupacional que trabaja en las administradoras de riesgos profesionales de Bogotá D.C.

El Propósito de la investigación es contextualizar la acción profesional de los terapeutas Ocupacionales dentro de nuevos escenarios de desempeño siendo las Administradoras de Riesgos Profesionales un claro ejemplo de ello. Esta investigación aproxima al lector a conocer las áreas de participación descritas en dos grandes grupos como son Promoción y Prevención y Comercial, los cuales se caracterizan por el tipo de funciones que se realizan y son claramente descritas en el trabajo.