Computer vision is embracing a new research focus in which the aim is to develop visual skills for robots that allow them to interact with a dynamic, realistic environment. To achieve this aim, new kinds of vision algorithms need to be developed which run in real time and subserve the robot's goals. Two fundamental goals are determin-ing the location of a known object. Color can be successfully used for both tasks. This article demonstrates that color histograms of multicolored objects provide a robust, efficient cue for index-ing into a large database of models. It shows that color histograms are stable object representations in the presence of occlusion and over change in view, and that they can differentiate among a large number of objects. For solving the identification problem, it introduces a technique called Histogram Intersection, which matches model and im-age histograms and a fast incremental version of Histogram Intersection, which allows real-time indexing into a large database of stored models. For solving the location problem it introduces an algorithm called Histogram Backprojection, which performs this task efficiently in crowded scenes. 1

Early vision algorithms often have a first stage of linear-filtering that `extracts' from the image information at multiple scales of resolution and multiple orientations. A common difficulty in the design and implementation of such schemes is that one feels compelled to discretize coarsely the space of scales and orientations in order to reduce computation and storage costs. This discretization produces anisotropies due to a loss of traslation-, rotation-, scaling-invariance that makes early vision algorithms less precise and more difficult to design. This need not be so: one can compute and store efficiently the response of families of linear filters defined on a continuum of orientations and scales. A technique is presented that allows (1) to compute the best approximation of a given family using linear combinations of a small number of `basis' functions; (2) to describe all finite-dimensional families, i.e. the families of filters for which a finite dimensional representation is p...

Families of kernels that are useful in a variety of early vision algorithms may be obtained by rotating and scaling in a continuum a `template' kernel. These multi-scale multi-orientation family may be approximated by linear interpolation of a discrete finite set of appropriate `basis' kernels. A scheme for generating such a basis together with the appropriate interpolation weights is described. Unlike previous schemes by Perona, and Simoncelli et al. it is guaranteed to generate the most parsimonious one. Additionally, it is shown how to exploit two symmetries in edge-detection kernels for reducing storage and computational costs and generating simultaneously endstop- and junction-tuned filters for free.

This paper presents a novel, parameter-free technique for the segmentation and local description of line structures on multiple scales, both in 2-D and 3-D. The algorithm is based on a nonlinear combination of linear filters and searches for elongated, symmetric line structures, while suppressing the response to edges. The filtering process creates one sharp maximum across the line-feature profile and across scalespace. The multiscale response reflects local contrast and is independent of the local width.

In the past several years, the speed of standard processors has reached the point where interesting problems requiring visual tracking can be carried out on standard workstations. However, relatively little attention has been devoted to developing visual tracking technology in its own right. In this article, we describe X Vision, a modular, portable framework for visual tracking. X Vision is designed to be a programming environment for real-time vision which provides high performance on standard workstations outfitted with a simple digitizer. X Vision consists of a small set of image-level tracking primitives, and a framework for combining tracking primitives to form complex tracking systems. Efficiency and robustness are achieved by propagating geometric and temporal constraints to the feature detection level, where image warping and specialized image processing are combined to perform feature detection quickly and robustly. Over the past several years, we have used X Vision to constr...

We describe a technique for displaying patterns that appear to move continuously without changing their positions. The method uses a quadrature pair of oriented filters to vary the local phase, giving the sensation of motion. We have used this technique in various computer graphic and scientific visualization applications.

Shape modeling is an important constituent of computer vision as well as computer graphics research. Shape models aid the tasks of object representation and recognition. This paper presents a new approach to shape modeling which retains the most attractive features of existing methods, and overcomes their prominent limitations. Our technique can be applied to model arbitrarily complex shapes, which include shapes with significant protrusions, and to situations where no a priori assumption about the object's topology is made. A single instance of our model, when presented with an image having more than one object of interest, has the ability to split freely to represent each object. This method is based on the ideas developed by Osher & Sethian to model propagating solid/liquid interfaces with curvature-dependent speeds. The interface (front) is a closed, nonintersecting, hypersurface flowing along its gradient field with constant speed or a speed that depends on the curvature...

In some types of digital color cameras only a single value is provided for each pixel: either, red, green, or blue. The reconstruction of the three color values for each pixel is known as the "demosaicing" problem. This report suggests a solution to this problem based on the steerable wavelet decomposition. The reconstructed images present a faithful interpolation of missing data while preserving edges and textures.

RE 1. a: An image of a vase moving to the right. b: A sequence of frames may be piled up to form a flip book; time is the third dimension. c: A skeleton view of the (x,y,t) volume helps suggest its structure. d: The space-time volume may be sliced to illustrate the fact that the motion is equivalent to spatio-temporal orientation. e: In the case of continuous motion, the volume is densely filled. The moving vase traces out an extruded shape that is sheared due to the motion. O (a) (b) (c) (d) (e) x t y x t y x t y x To get a better understanding of the structure of the spacetime volume, we can cut a slice through it in an (x,t) plane, as illustrated in Figure 1d. The vase traces out an extruded shape that is sheared due to the motion. In the case of continuous motion, the spatio-temporal volume is densely filled, as shown in Figure 1e. The (x,t) slice is slanted as a result of the rightward motion. Figure 2a shows an (x,y,t) volume taken from a video sequence showing a

The focus of this project was to modify the image feature extraction subsystem of the ImageRover system[11]. The subsystem was extended to use color and texture measures which more closely correspond to the human perception. The feature implemented for color is the color histogram in L u v color space. The texture measure implemented is 2D Wold decomposition, which incorporates the three most important for human perception measures, "directionality", "periodicity" and "randomness." Texture module performance was evaluated on the Brodatz texture album. The resulting modules are now part of the ImageRover system. 1 Introduction In the last several years, as more and more information became available on the Internet (especially on World Wide Web), the main problem of the users shifted from existence of needed information to the ability to find it. One of the solutions for this problem is the creation of a comprehensive index of all the available documents. Manual creation of ...