Reconeixement i seguiment d’objectes en vídeo a partir del seu moviment

L’objectiu d’aquest PFC és estudiar la branca de la detecció d’objectes en vídeos segons el seu moviment. Per fer-ho es crearà un algorisme que sigui capaç de tractar un vídeo, calculant el nombre d’objectes de l’escena i quina és la posició de cada un d’aquests. L’algorisme ha de ser capaç de trobar un conjunt de regions útils i a partir d’aquest, separar-lo en diferents grups, cada un representant un objecte en moviment. La finalitat d’aquest projecte és l’estudi de la detecció d’objectes en vídeo. Intentarem crear un algorisme que ens permeti dur a terme aquest estudi i treure’n conclusions. Pretenem fer un algorisme, o un conjunt d’algorismes, en Matlab que sigui capaç de donat qualsevol vídeo, pugui retornar un conjunt de imatges, o un vídeo, amb els diferents objectes de l’escena destacats. Es faran proves en diferents situacions, des de objectes sintètics amb un moviment clarament definit, fins a proves en seqüències reals extretes de diferents pel•lícules. Per últim es pretén comprovar l’eficiència d’aquest. Ja que el projecte s’emmarca en la línia de recerca de robòtica i visió per computador, la tasca principal serà la manipulació d’imatges. Per tant farem servir el Matlab, ja que les imatges no son res més que matrius i aquest programa permet el càlcul vectorial i matricial d’una manera senzilla i realment eficient

Estudi i implementació d’un mètode de reconstrucció 3D basat en SfM i registre de vistes 3D parcials

Aquest projecte es basarà en reconstruir una imatge 3D gran a partir d’una seqüència d’imatges 2D capturades per una càmera. Ens centrem en l’estudi de les bases matemàtiques de la visió per computador així com en diferents mètodes emprats en la reconstrucció 3D d’imatges. Per portar a terme aquest estudi s’utilitza la plataforma de desenvolupament MatLab ja que permet tractar operacions matemàtiques, imatges i matrius de gran tamany amb molta senzillesa, rapidesa i eficiència, per aquesta raó s’usa en moltes recerques sobre aquest tema. El projecte aprofundeix en el tema descrit anteriorment estudiant i implementant un mètode que consisteix en aplicar Structure From Motion (SFM) a pocs frames seguits obtinguts d’una seqüència d’imatges 2D per crear una reconstrucció 3D. Quan s’han creat dues reconstruccions 3D consecutives i fent servir un frame com a mínim en comú entre elles, s’aplica un mètode de registre d’estructures 3D, l’Iterative Closest Point (ICP), per crear una reconstrucció 3D més gran a través d’unir les diferents reconstruccions obtingudes a partir de SfM. El mètode consisteix en anar repetint aquestes operacions fins al final dels frames per poder aconseguir una reconstrucció 3D més gran que les petites imatges que s’aconsegueixen a través de SfM. A la Figura 1 es pot veure un esquema del procés que es segueix. Per avaluar el comportament del mètode, utilitzem un conjunt de seqüències sintètiques i un conjunt de seqüències reals obtingudes a partir d’una càmera. L’objectiu final d’aquest projecte és construir una nova toolbox de MatLab amb tots els mètodes per crear reconstruccions 3D grans per tal que sigui possible tractar amb facilitat aquest problema i seguir-lo desenvolupant en un futur

Reconeixement de cd-roms musicals mitjançant visió per computador

Dissenyar, implementar i testejar un sistema per classificar imatges: disseny d’un sistema que primer aprèn com són les imatges d’una classe a partir d’un conjunt d’imatges d’entrenament i després és capaç de classificar noves imatges assignant-les-hi l’ etiqueta corresponent a una de les classes “apreses”. Concretament s’analitzen caràtules de cd-roms, les quals s’han de reconèixer per després reproduir automàticament la música del seu àlbum associat

Local map update for large scale SLAM

A technique for simultaneous localisation and mapping (SLAM) for large scale scenarios is presented. This solution is based on the use of independent submaps of a limited size to map large areas. In addition, a global stochastic map, containing the links between adjacent submaps, is built. The information in both levels is corrected every time a loop is closed: local maps are updated with the information from overlapping maps, and the global stochastic map is optimised by means of constrained minimisation

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

Modeling and Classifying Breast Tissue Density in Mammograms

We present a new approach to model and classify breast parenchymal tissue. Given a mammogram, first, we will discover the distribution of the different tissue densities in an unsupervised manner, and second, we will use this tissue distribution to perform the classification. We achieve this using a classifier based on local descriptors and probabilistic Latent Semantic Analysis (pLSA), a generative model from the statistical text literature. We studied the influence of different descriptors like texture and SIFT features at the classification stage showing that textons outperform SIFT in all cases. Moreover we demonstrate that pLSA automatically extracts meaningful latent aspects generating a compact tissue representation based on their densities, useful for discriminating on mammogram classification. We show the results of tissue classification over the MIAS and DDSM datasets. We compare our method with approaches that classified these same datasets showing a better performance of our proposal

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 method to obtain the integrated contour image in colour scenes

This paper describes a method to achieve the most relevant contours of an image. The presented method proposes to integrate the information of the local contours from chromatic components such as H, S and I, taking into account the criteria of coherence of the local contour orientation values obtained from each of these components. The process is based on parametrizing pixel by pixel the local contours (magnitude and orientation values) from the H, S and I images. This process is carried out individually for each chromatic component. If the criterion of dispersion of the obtained orientation values is high, this chromatic component will lose relevance. A final processing integrates the extracted contours of the three chromatic components, generating the so-called integrated contours image

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

Use of decision trees in colour feature selection: application to object recognition in outdoor scenes

A new method for the automated selection of colour features is described. The algorithm consists of two stages of processing. In the first, a complete set of colour features is calculated for every object of interest in an image. In the second stage, each object is mapped into several n-dimensional feature spaces in order to select the feature set with the smallest variables able to discriminate the remaining objects. The evaluation of the discrimination power for each concrete subset of features is performed by means of decision trees composed of linear discrimination functions. This method can provide valuable help in outdoor scene analysis where no colour space has been demonstrated as being the most suitable. Experiment results recognizing objects in outdoor scenes are reported

On the way to solve lighting problems in underwater imaging

A major obstacle to processing images of the ocean floor comes from the absorption and scattering effects of the light in the aquatic environment. Due to the absorption of the natural light, underwater vehicles often require artificial light sources attached to them to provide the adequate illumination. Unfortunately, these flashlights tend to illuminate the scene in a nonuniform fashion, and, as the vehicle moves, induce shadows in the scene. For this reason, the first step towards application of standard computer vision techniques to underwater imaging requires dealing first with these lighting problems. This paper analyses and compares existing methodologies to deal with low-contrast, nonuniform illumination in underwater image sequences. The reviewed techniques include: (i) study of the illumination-reflectance model, (ii) local histogram equalization, (iii) homomorphic filtering, and, (iv) subtraction of the illumination field. Several experiments on real data have been conducted to compare the different approaches

Detection of matchings in a sequence of underwater images through texture analysis

This paper presents an approach to ameliorate the reliability of the correspondence points relating two consecutive images of a sequence. The images are especially difficult to handle, since they have been acquired by a camera looking at the sea floor while carried by an underwater robot. Underwater images are usually difficult to process due to light absorption, changing image radiance and lack of well-defined features. A new approach based on gray-level region matching and selective texture analysis significantly improves the matching reliability

Proposal of a parallel architecture for a motion detection algorithm

This paper proposes a parallel architecture for estimation of the motion of an underwater robot. It is well known that image processing requires a huge amount of computation, mainly at low-level processing where the algorithms are dealing with a great number of data. In a motion estimation algorithm, correspondences between two images have to be solved at the low level. In the underwater imaging, normalised correlation can be a solution in the presence of non-uniform illumination. Due to its regular processing scheme, parallel implementation of the correspondence problem can be an adequate approach to reduce the computation time. Taking into consideration the complexity of the normalised correlation criteria, a new approach using parallel organisation of every processor from the architecture is proposed

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