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

. The satisfiability (SAT) problem is a core problem in mathematical logic and computing theory. In practice, SAT is fundamental in solving many problems in automated reasoning, computer-aided design, computeraided manufacturing, machine vision, database, robotics, integrated circuit design, computer architecture design, and computer network design. Traditional methods treat SAT as a discrete, constrained decision problem. In recent years, many optimization methods, parallel algorithms, and practical techniques have been developed for solving SAT. In this survey, we present a general framework (an algorithm space) that integrates existing SAT algorithms into a unified perspective. We describe sequential and parallel SAT algorithms including variable splitting, resolution, local search, global optimization, mathematical programming, and practical SAT algorithms. We give performance evaluation of some existing SAT algorithms. Finally, we provide a set of practical applications of the sat...

Although game-tree search works well in perfectinformation games, there are problems in trying to use it for imperfect-information games such as bridge. The lack of knowledge about the opponents ' possible moves gives the game tree a very large branching factor, making the tree so immense that game-tree searching is infeasible. In this paper, we describe our approach for overcoming this problem. We develop a model of imperfect-information games, and describe how to represent information about the game using a modified version of a task network that is extended to represent multi-agency and uncertainty. We present a game-playing procedure that uses this approach to generate game trees in which the set of alternative choices is determined not by the set of possible actions, but by the set of available tactical and strategic schemes. In our tests of this approach on the game of bridge, we found that it generated trees having a much smaller branching factor than would have been generated b...

ly, we will consider the current state S (or any other state) to be a collection of ground atoms (that is, completely instantiated predicates) of some function- A Planning Approach to Declarer Play in Contract Bridge 5 free first-order language L that is generated by finitely many constant symbols and predicate symbols. We do not care whether this is how S would actually be represented in an implementation of a game-playing program. Among other things, S will contain information about who the players are, and whose turn it is to move. To represent this information, we will consider S to include a ground atom Agent(x) for each player x, and a ground atom Turn(y) for the player y whose turn it is to move. For example, in the game of bridge, S would include the ground atoms Agent(North), Agent(South), Agent(East), and Agent(West). If it were South's turn to move, then S would include the ground atom Turn(South). We will be considering S from the point of view of a particular player P ...

This article introduces a new indexing technique based on boundary histograms. For multicolored objects boundary histograms record estimates of the boundary lengths between different discrete colors in an image. Boundary histograms are small and insensitive to noise. To identify images we apply a match function to their boundary histograms. The match function that we derive handles occlusions and distracting pixels in the background of an object gracefully. The robustness and the low complexity of the match function together with its ability to distinguish many objects allow us to use boundary histograms as an index for large image databases. Test results illustrate the above mentioned features of boundary histograms and the match function. Keywords: Object recognition, color indexing, image signature, boundary length estimates. 1 Introduction Recent advances in data storage and data compression will allow image databases to explode in size. However, currently there exist only very ...

We propose and evaluate a class of objective functions that rank hypotheses for feature labels. Our approach takes into account the representation cost and quality of the shapes themselves, and balances the geometric requirements against the photometric evidence This balance is essential for any system using underconstrained or generic feature models. We introduce examples of specific models allowing the actual computation of the terms in the objective function, and show how this framework leads naturally to control parameters that have a clear semantic meaning. We illustrate the properties of our objective functions on synthetic and real images. 1

This article proposes a technique to animate a Chinese style painting given its image. We first extract descriptions of the brush strokes that hypothetically produced it. The key to the extraction process is the use of a brush stroke library, which is obtained by digitizing single brush strokes drawn by an experienced artist. The steps in our extraction technique are first to segment the input image, then to find the best set of brush strokes that fit the regions, and, finally, to refine these strokes to account for local appearance. We model a single brush stroke using its skeleton and contour, and we characterize texture variation within each stroke by sampling perpendicularly along its skeleton. Once these brush descriptions have been obtained, the painting can be animated at the brush stroke level. In this article, we focus on Chinese paintings with relatively sparse strokes. The animation is produced using a graphical application we developed. We present several animations of real paintings using our technique.

Abstract—Synthetic aperture radar (SAR) has been intensively used for sea-ice monitoring in polar regions. A computer-assisted analysis of SAR sea-ice imagery is extremely difficult due to numerous imaging parameters and environmental factors. This paper presents a system which, with some limited information provided, is able to perform an automated segmentation and classification for the SAR sea-ice imagery. In the system, both the segmentation and classification processes are based on a Markov random-field theory and are formulated in a joint manner under the Bayesian framework. Solutions to the formulation are obtained by a region-growing technique which keeps refining the segmentation and producing semantic class labels at the same time in an iterative manner. The algorithm is a general-segmentation approach named iterative region growing using semantics, which, in this paper, is dedicated to the problem of classifying the operational SAR sea-ice imagery provided by the Canadian Ice Service (CIS). The classified image results have been validated by the CIS personnel, and the resulting classifications are quite successful using the same algorithm applied to diverse data sets. Index Terms—Expert system, image segmentation, Markov random field (MRF), region growing, sea ice, synthetic aperture radar (SAR). I.

This paper describes issues surrounding the application of automated planning in computer vision. It includes a literature survey covering the major areas of automated planning from a historical perspective. Beginning with STRIPS we examine the major innovations in computerized planning and the problems that required those innovations. We then discuss the motivation for using planners as a part of a vision system. Computer vision fits into the planning paradigm well because of its task oriented nature. The large number of tasks and the complexities of using them give us reason to believe that users of a vision system will gain some benefit from access to a planning systems. We then introduce a new way of using planners in computer vision. We have implemented this idea using a planning system developed at NASA's Ames research center called COLLAGE. COLLAGE is a non-linear, hierarchical planner which utilizes multiple plan creation and control methods. With this planner we will show that...

: The efficient computation of region parameters in image understanding by a SIMD array requires that those regions be processed simultaneously. The difficulty lies in orchestrating non-uniform data-dependent communication using only a single thread of control. We introduce a novel new technique we call coterie structures for the simultaneous parallel processing of connected components on reconfigurable broadcast meshes. Our technique differs fundamentally from those previously used for this class of networks in that each region is processed using only those PEs to which that region is mapped. Simultaneous and efficient region processing is thereby effected without remapping. The primary theoretical result is that techniques similar to those used in PRAM graph contraction algorithms can be used to create an optimal randomized reduction algorithm and near optimal deterministic algorithms for reduction and parallel prefix in all regions simultaneously. The primary practical result is a r...