A new formulation of the image partitioning problem is presented: construct a complete and stable description of an image, in terms of a specified descriptive language, that is simplest in the sense of being shortest. We show that a descriptive language limited to a low-order polynomial description of the intensity variation within each region and a chain-code-like description of the region boundaries yields intuitively satisfying partitions for a wide class of images. The advantage of this formulation is that it can be extended to deal with subsequent steps of the image-understanding problem (or to deal with other image attributes, such as texture) in a natural way by augmenting the descriptive language. Experiments performed on a variety of both real and synthetic images demonstrate the superior performance of this approach over partitioning techniques based on clustering vectors of local image attributes and standard edge-detection techniques. 1 Introduction The partitioning proble...

Abstract—The standard approach to edge detection is based on a model of edges as large step changes in intensity. This approach fails to reliably detect and localize edges in natural images where blur scale and contrast can vary over a broad range. The main problem is that the appropriate spatial scale for local estimation depends upon the local structure of the edge, and thus varies unpredictably over the image. Here we show that knowledge of sensor properties and operator norms can be exploited to define a unique, locally computable minimum reliable scale for local estimation at each point in the image. This method for local scale control is applied to the problem of detecting and localizing edges in images with shallow depth of field and shadows. We show that edges spanning a broad range of blur scales and contrasts can be recovered accurately by a single system with no input parameters other than the second moment of the sensor noise. A natural dividend of this approach is a measure of the thickness of contours which can be used to estimate focal and penumbral blur. Local scale control is shown to be important for the estimation of blur in complex images, where the potential for interference between nearby edges of very different blur scale requires that estimates be made at the minimum reliable scale.

We propose a language for designing image measurement operators suitable for early vision. We refer to them as logical/linear (L/L) operators, since they unify aspects of linear operator theory and boolean logic. A family of these operators appropriate for measuring the low-order differential structure of image curves is developed. These L/L operators are derived by decomposing a linear model into logical components to ensure that certain structural preconditions for the existence of an image curve are upheld. Tangential conditions guarantee continuity, while normal conditions select and categorize contrast profiles. The resulting operators allow for coarse measurement of curvilinear differential structure (orientation and curvature) while successfully segregating edge- and line-like features. By thus reducing the incidence of false-positive responses, these operators are a substantial improvement over (thresholded) linear operators which attempt to resolve the same class of features. ...

We propose a unified approach to solve low, intermediate and high level computer vision problems for 3D object recognition from range images. All three levels of computation are cast in an optimization framework and can be implemented on neural network style architecture. In the low level computation, the tasks are to estimate curvature images from the input range data. Subsequent processing at the intermediate level is concerned with segmenting these curvature images into coherent curvature sign maps. In the high level, image features are matched against model features based on an object description called attributed relational graph (ARG). We show that the above computational tasks at each of the three different levels can all be formulated as optimizing a two-term energy function. The first term encodes unary constraints while the second term binary ones. These energy functions are minimized using parallel and distributed relaxation-based algorithms which are well suited for neural...

The objective of this paper is to contribute to the methodology available for dealing with the detection and the estimation of the location of discontinuities in one dimensional piecewise smooth regression functions observed in white Gaussian noise over an interval. Our approach is nonparametric in nature because the unknown function is not assumed to have any specific form. Our method relies upon a wavelet analysis of the observed signal and belongs to the class of "indirect" methods, where one detects and locates the change points prior to fitting the curve, and then uses one's favorite function estimation technique on each segment to recover the curve. We show that, provided discontinuities can be detected and located with sufficient accuracy, detection followed by wavelet smoothing enjoys optimal rates of convergence. 1 Introduction Wavelet based nonparametric regression has become a well known and mathematically founded technique for estimating smooth functions adaptively. Optima...

Abstract—The problem of identifying and counting rolling leukocytes within intravital microscopy is of both theoretical and practical interest. Currently, methods exist for tracking rolling leukocytes in vivo, but these methods rely on manual detection of the cells. In this paper we propose a technique for accurately detecting rolling leukocytes based on Bayesian classification. The classification depends on a feature score, the gradient inverse coefficient of variation (GICOV), which serves to discriminate rolling leukocytes from a cluttered environment. The leukocyte detection process consists of three sequential steps: the first step utilizes an ellipse matching algorithm to coarsely identify the leukocytes by finding the ellipses with a locally maximal GICOV. In the second step, starting from each of the ellipses found in the first step, a B-spline snake is evolved to refine the leukocytes boundaries by maximizing the associated GICOV score. The third and final step retains only the extracted contours that have a GICOV score above the analytically determined threshold. Experimental results using 327 rolling leukocytes were compared to those of human experts and currently used methods. The proposed GICOV method achieves 78.6 % leukocyte detection accuracy with 13.1 % false alarm rate. Index Terms—Active contours, boundary extraction, classification, leukocyte detection, microscopy. I.

Scattered data modeling is useful in many scientific fields and industrial applications to reveal the properties and relationships in empirically acquired data sets. If the data contain discontinuities, the data analysts must manually mark the segmenting boundaries before using the current software packages. Here, we automatically detect discontinuities from noisy sparse scattered data and use triangular NURBS surfaces to model and visualize the data. We use Guy and Medioni's global voting method to interpolate from sparse data three dense potential fields for surfaces, edges, and junctions. The global voting interpolants encode several human perceptual grouping principles such as co-surfacity, proximity, and constancy of curvature. The inferred potential fields are stored in three volumetric grids, giving each voxel the probability of being a surface point, an edge point, and a junction point. Then we use a new model called "winged B-snakes", which are deformable triangular NURBS surf...

to 20 meters). Previous work on scene modelling for indoor mobile robotics applications was done using vision based methods such as depth from stereo or motion [2]. This paper presents a new scene analysis system that automatically reconstructs the 3D geometric model of real-world scenes from multiple range images. The reconstruction is achieved through a fully comprehensive procedure that includes range data acquisition, geometrical feature extraction, registration and integration of multiple views. A new hybrid algorithm for the segmentation of range images has been developed to overcome the specific problems specific of this kind of images. This algorithm combines edge and region detection approaches to build a high-level 3D description of a real scene described by a noisy range image. Another relevant issue is the registration/integration of range images from different viewpoints into a consistent 3D model. The integration part combines registered and partially overlapping data set...

AbstractÐFor over 30 years researchers in computer vision have been proposing new methods for performing low-level vision tasks such as detecting edges and corners. One key element shared by most methods is that they represent local image neighborhoods as constant in color or intensity with deviations modeled as noise. Due to computational considerations that encourage the use of small neighborhoods where this assumption holds, these methods remain popular. This research models a neighborhood as a distribution of colors. Our goal is to show that the increase in accuracy of this representation translates into higher-quality results for low-level vision tasks on difficult, natural images, especially as neighborhood size increases. We emphasize large neighborhoods because small ones often do not contain enough information. We emphasize color because it subsumes gray scale as an image range and because it is the dominant form of human perception. We discuss distributions in the context of detecting edges, corners, and junctions, and we show results for each. Index TermsÐEdge detection, junction detection, corner detection, earth mover's distance, color distributions, perceptual color distance.

This paper presents an active scheme for the localization of a mobile robot based on the detection of natural landmarks. Assuming that a partial 3D model of the environment is known a priori, an optimal and active choice of the landmark is supported on a new strategy for 3D map partition, yielding high updating rates of the location estimates. Good localization accuracy and robustness are achieved by combining laser range data with odometry, using Kalman filtering schemes. 1 Introduction Accurate localization is a fundamental issue in mobile robots navigation. Various factors may incurring the mobile robot in error during operation [3], and hence, reliable localization is a difficult and not yet completely solved problem. In one hand, complex environments present serious difficulties to overcome, such as dynamic and/or static unmodeled obstacles, human beings presence as well as coordination with other robots. On the other hand, inaccuracies on sensor measurements or inappropriate sen...