A de-texturing and spatially constrained K-means approach for image segmentation

This paper presents a new and simple segmentation method based on the K-means clustering procedure and a two-step process. The first step relies on an original de-texturing procedure which aims at converting the input natural textured color image into a color image, without texture, that will be easier to segment. Once, this de-textured (color) image is estimated, a final segmentation is achieved by a spatially-constrained K-means segmentation. These spatial constraints help the iterative K-means labeling process to succeed in finding an accurate segmentation by taking into account the inherent spatial relationships and the presence of pre-estimated homogeneous textural regions in the input image. This procedure has been successfully applied on the Berkeley image database. The experiments reported in this paper demonstrate that the proposed method is efficient (in terms of visual evaluation and quantitative performance measures) and performs competitively compared to the best existing state-of-the-art segmentation methods recently proposed in the literature.     

A Vector-based Representation for Image Warping

A method for image analysis, representation and re-synthesis is introduced. Unlike other schemes it is not pixel based but rather represents a picture as vector data, from which an altered version of the original image can be rendered. Representing an image as vector data allows performing operations such as zooming, retouching or colourising, avoiding common problems associated with pixel image manipulation. This paper brings together methods from the areas of computer vision, image compositing and image based rendering to prove that this type of image representation is a step towards accurate and efficient image manipulation.     

Progressive Transmission of Vector Map Data over the World Wide Web

Within distributed computing environments, access to very large geospatial datasets often suffers from slow or unreliable network connections. To allow users to start working with a partially delivered dataset, progressive transmission methods are a viable solution. While incremental and progressive methods have been applied successfully to the transmission of raster images over the World Wide Web, and, in the form of prototypes, of triangular meshes, the transmission of vector map datasets has lacked a similar attention. This paper introduces a solution to the progressive transmission of vector map data that allows users to apply analytical GIS methods to partially transmitted data sets. The architecture follows a client-server model with multiple map representations at the server side, and a thin client that compiles transmitted increments into a topologically consistent format. This paper describes the concepts, develops an architecture, and discusses implementation concerns.     

Localization of shapes using statistical models and stochastic optimization

In this paper, we present a new model for deformations of shapes. A pseudo-likelihood is based on the statistical distribution of the gradient vector field of the gray level. The prior distribution is based on the Probabilistic Principal Component Analysis (PPCA). We also propose a new model based on mixtures of PPCA that is useful in the case of greater variability in the shape. A criterion of global or local object specificity based on a preliminary color segmentation of the image, is included into the model. The localization of a shape in an image is then viewed as minimizing the corresponding Gibbs field. We use the Exploration/Selection (E/S) stochastic algorithm in order to find the optimal deformation. This yields a new unsupervised statistical method for localization of shapes. In order to estimate the statistical parameters for the gradient vector field of the gray level, we use an Iterative Conditional Estimation (ICE) procedure. The color segmentation of the image can be computed with an Exploration/Selection/Estimation (ESE) procedure.     

Approximate inference in Boltzmann machines

Inference in Boltzmann machines is NP-hard in general. As a result approximations are often necessary. We discuss first order mean field and second order Onsager truncations of the Plefka expansion of the Gibbs free energy. The Bethe free energy is introduced and rewritten as a Gibbs free energy. From there a convergent belief optimization algorithm is derived to minimize the Bethe free energy. An analytic expression for the linear response estimate of the covariances is found which is exact on Boltzmann trees. Finally, a number of theorems is proven concerning the Plefka expansion, relating the first order mean field and the second order Onsager approximation to the Bethe approximation. Experiments compare mean field approximation, Onsager approximation, belief propagation and belief optimization.     

Data Communications for Internet Robots

For Internet robots, the most challenging and distinct difficulties are well recognized to be associated with Internet transmission delays, delay jitter and not-guaranteed bandwidth, which might degrade system performance dramatically or even lead to instability. Current approaches to data communication between the remote robot and the human operator employ directly one of the two currently available protocols, i.e. TCP and UPD. In this paper, a teleoperation-oriented data transmission mechanism is implemented. Compared to TCP, the presented scheme provides minimized transmission delays and delay jitter; in the steady state, its transmission rate is much smoother; when available network bandwidth changes, it adapts to the variation quickly without large overshoot. Compared to UDP, it is inter-protocol fairness convergent, intro-protocol convergent, and efficient convergent. The presented mechanism is deployed in a mobile robot teleoperation system developed. In the experiments, users successfully guided a Pioneer-2 mobile robot through a laboratory environment remotely over the Internet via a web browser.