Scene classifier for real time road detection

L’objectiu principal del projecte és el de classificar escenes de carretera en funció del contingut de les imatges per així poder fer un desglossament sobre quin tipus de situació tenim en el moment. És important que fixem els paràmetres necessaris en funció de l’escenari en què ens trobem per tal de treure el màxim rendiment possible a cada un dels algoritmes. La seva funcionalitat doncs, ha de ser la d’avís i suport davant els diferents escenaris de conducció. És a dir, el resultat final ha de contenir un algoritme o aplicació capaç de classificar les imatges d’entrada en diferents tipus amb la màxima eficiència espacial i temporal possible. L’algoritme haurà de classificar les imatges en diferents escenaris. Els algoritmes hauran de ser parametritzables i fàcilment manejables per l’usuari. L’eina utilitzada per aconseguir aquests objectius serà el MATLAB amb les toolboxs de visió i xarxes neuronals instal·lades.

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

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

Identification of geometrically consistent interest points for 3D scene reconstruction

We propose an algorithm that extracts image features that are consistent with the 3D structure of the scene. The features can be robustly tracked over multiple views and serve as vertices of planar patches that suitably represent scene surfaces, while reducing the redundancy in the description of 3D shapes. In other words, the extracted features will off er good tracking properties while providing the basis for 3D reconstruction with minimum model complexity

Hand detection in cluttered scene images using Fourier-Mellin invariant features

This paper proposes an automatic hand detection system that combines the Fourier-Mellin Transform along with other computer vision techniques to achieve hand detection in cluttered scene color images. The proposed system uses the Fourier-Mellin Transform as an invariant feature extractor to perform RST invariant hand detection. In a first stage of the system a simple non-adaptive skin color-based image segmentation and an interest point detector based on corners are used in order to identify regions of interest that contains possible matches. A sliding window algorithm is then used to scan the image at different scales performing the FMT calculations only in the previously detected regions of interest and comparing the extracted FM descriptor of the windows with a hand descriptors database obtained from a train image set. The results of the performed experiments suggest the use of Fourier-Mellin invariant features as a promising approach for automatic hand detection.

Hand detection in cluttered scene images using Fourier-Mellin invariant features

This paper proposes an automatic hand detection system that combines the Fourier-Mellin Transform along with other computer vision techniques to achieve hand detection in cluttered scene color images. The proposed system uses the Fourier-Mellin Transform as an invariant feature extractor to perform RST invariant hand detection. In a first stage of the system a simple non-adaptive skin color-based image segmentation and an interest point detector based on corners are used in order to identify regions of interest that contains possible matches. A sliding window algorithm is then used to scan the image at different scales performing the FMT calculations only in the previously detected regions of interest and comparing the extracted FM descriptor of the windows with a hand descriptors database obtained from a train image set. The results of the performed experiments suggest the use of Fourier-Mellin invariant features as a promising approach for automatic hand detection.

Scene representation for object monitoring

In robotics, having a 3D representation of the environment where a robot is working can be very useful. In real-life scenarios, this environment is constantly changing for example by human interaction, external agents or by the robot itself. Thus, the representation needs to be constantly updated and extended to account for these dynamic scene changes. In this work we face the problem of representing the scene where a robot is acting. Moreover, we ought to improve this representation by reusing the information obtained in previous scenes. Our goal is to build a method to represent a scene and to update it while changes are produced. In order to achieve that, different aspects of computer vision such as space representation or feature tracking are discussed

Using appearance and context for outdoor scene object classification

We propose a probabilistic object classifier for outdoor scene analysis as a first step in solving the problem of scene context generation. The method begins with a top-down control, which uses the previously learned models (appearance and absolute location) to obtain an initial pixel-level classification. This information provides us the core of objects, which is used to acquire a more accurate object model. Therefore, their growing by specific active regions allows us to obtain an accurate recognition of known regions. Next, a stage of general segmentation provides the segmentation of unknown regions by a bottom-strategy. Finally, the last stage tries to perform a region fusion of known and unknown segmented objects. The result is both a segmentation of the image and a recognition of each segment as a given object class or as an unknown segmented object. Furthermore, experimental results are shown and evaluated to prove the validity of our proposal

View-dependent information theory quality measures for pixel sampling and scene discretization in flatland

In this paper, we present view-dependent information theory quality measures for pixel sampling and scene discretization in flatland. The measures are based on a definition for the mutual information of a line, and have a purely geometrical basis. Several algorithms exploiting them are presented and compare well with an existing one based on depth differences

Generic object classification for autonomous robots

Un dels principals problemes de la interacció dels robots autònoms és el coneixement de l'escena. El reconeixement és fonamental per a solucionar aquest problema i permetre als robots interactuar en un escenari no controlat. En aquest document presentem una aplicació pràctica de la captura d'objectes, de la normalització i de la classificació de senyals triangulars i circulars. El sistema s'introdueix en el robot Aibo de Sony per a millorar-ne la interacció. La metodologia presentada s'ha comprobat en simulacions i problemes de categorització reals, com ara la classificació de senyals de trànsit, amb resultats molt prometedors.

Object recognition for autonomous objects: comparison of two approaches

Report for the scientific sojourn at the Swiss Federal Institute of Technology Zurich, Switzerland, between September and December 2007. In order to make robots useful assistants for our everyday life, the ability to learn and recognize objects is of essential importance. However, object recognition in real scenes is one of the most challenging problems in computer vision, as it is necessary to deal with difficulties. Furthermore, in mobile robotics a new challenge is added to the list: computational complexity. In a dynamic world, information about the objects in the scene can become obsolete before it is ready to be used if the detection algorithm is not fast enough. Two recent object recognition techniques have achieved notable results: the constellation approach proposed by Lowe and the bag of words approach proposed by Nistér and Stewénius. The Lowe constellation approach is the one currently being used in the robot localization project of the COGNIRON project. This report is divided in two main sections. The first section is devoted to briefly review the currently used object recognition system, the Lowe approach, and bring to light the drawbacks found for object recognition in the context of indoor mobile robot navigation. Additionally the proposed improvements for the algorithm are described. In the second section the alternative bag of words method is reviewed, as well as several experiments conducted to evaluate its performance with our own object databases. Furthermore, some modifications to the original algorithm to make it suitable for object detection in unsegmented images are proposed.

Diseño cooperativo de un sistema de comunicaciones por satélite basado en diversidad espacial

En este proyecto se han presentado los modelos de distribución de canal más comunes que se puede encontrar una señal en una transmisión. Seguidamente se ha presentado el concepto de diversidad en comunicaciones inalámbricas terrestres y se ha trasladado el escenario a comunicaciones por satélite. Para analizar la calidad de los enlaces con diversidad se ha realizado un simulador, con Matlab, que modele la estructura básica de un sistema de comunicaciones (emisor, canal y receptor). Simulando las comunicaciones entre los diferentes sistemas de diversidad se ha podido comparar la calidad de cada enlace. El modelo Alamouti ha presentado una robustez y una baja probabilidad de error que hacen que sea la mejor elección a la hora de diseñar un sistema de diversidad para comunicaciones por satélite. Utiliza la diversidad de canal para aprovechar cada pizca de señal que recibe y así poder descifrar el mensaje enviado.

Pessebre virtual: disseny i exportació

Aquest projecte és una part d’un projecte més ampli consistent en estudiar un format gràfic que permeti exportar una escena modelada en Blender i importar aquesta mateixa escena en un entorn interactiu basat en Visual C++ amb OpenGL. D’aquesta forma, disposem de la capacitat de modelat de Blender i de la interacció i visualització de la llibreria OpenGL. Aquest format ha de representar geometria i textures imprescindiblement, i si és possible, d’altres factors importants com il·luminació, visualització i moviment. La part del projecte explicada en aquesta memòria consisteix en estudiar el format gràfic més adient per representar els diferents factors de realisme de l’escena (geometria, textura, etc.) havent triat el format OBJ per la seva capacitat de representació i fàcil edició. Per a provar el format, s’ha dissenyat un diorama de pessebre utilitzant les capacitats de modelatge de Blender. Pel que respecta les figures, aspecte important per a considerar l’escena com a pessebre, s’ha utilitzat un escàner 3D que ha obtingut representacions de malla 3D, a partir de figures reals de pessebre, que posteriorment han estat texturades. S’ha generat un vídeo del diorama de pessebre que permet veure’n tots els detalls navegant amb el punt de vista per l’escena. Aquest vídeo s’ha exposat en la mostra de pessebres de la Associació Pessebrista de Sabadell el Nadal del 2008.

Plataforma de adquisición de imágenes en escenarios virtuales para uso en sistemas de visión

En aquest projecte presentem un mètode per generar bases de imatges de vianants, requerides per a l'entrenament o validació de sistemes d'aprenentatge basats en exemples, en un entorn virtual. S'ha desenvolupat una plataforma que permet simular una navegació d'una càmara en una escena virtual i recuperar el fluxe de vídeo amb el seu groundtruth. Amb l'ús d'aquesta plataforma es suprimeix el procés d'anotació, necesari per obtenir el groundtruth en entorns reals, i es redueixen els costos al treballar en un entorn virtual.

Programa de introducción a la investigación y al desarrollo de las destrezas comunicativas (hablar y escribir correctamente): aplicación, desarrollo y resultados

Ante el nuevo reto que supone la adaptación al Espacio Europeo de Educación Superior (EEES) con una acción política que propone introducir importantes modificaciones en la concepción del proceso de enseñanza-aprendizaje entre las que se encuentran el replanteamiento del papel del profesor y del alumno, y el proceder metodológico en la acción docente, todos los agentes educativos deben aunar esfuerzos para articular medidas que posibiliten la adaptación a este nuevo escenario de manera óptima. Las universidades están ofreciendo a los docentes herramientas que puedan facilitar el acceso a los procesos de innovación educativa que exige el nuevo espacio de formación. En este marco es donde nace el proyecto titulado 'Programa de Introducción a la Investigación y al Desarrollo de las Destrezas Comunicativas (hablar y escribir correctamente)' que, valiéndose de los recursos tecnológicos que nos ofrece el Servicio de Innovación Educativa de la Universidad de Málaga, busca mejorar las competencias de expresión oral y escrita de los alumnos, así como la capacidad para organizar sus trabajos de investigación de manera rigurosa y ordenada, siguiendo una secuenciación razonada y científica. En la presente comunicación se detallan los objetivos del proyecto, la descripción del mismo, el modo de proceder en su desarrollo, las partes de las que ha constado y las conclusiones a las que se ha llegado.