of inaccurate segmentation, 2) helps to clarify the semantics of a particular region, and 3) enables a simple querying interface for region-based image retrieval systems. The application of SIMPLIcity to several databases, including a database of about 200,000 general-purpose images, has demonstrated that our

Abstract. Background subtraction is a method typically used to seg-ment moving regions in image sequences taken from a static camera by comparing each new frame to a model of the scene background. We present a novel non-parametric background model and a background subtraction approach. The model

information is shown to affect cognitive processes only if the instructions require verbalization of information that would not otherwise be attended to. From an analysis of what would be in STM at the time of report, the model predicts what can reliably be reported. The inaccurate reports found by other

We describe a system for representing moving images with sets of overlapping layers. Each layer contains an intensity map that defines the additive values of each pixel, along with an alpha map that serves as a mask indicating the transparency. The layers are ordered in depth and they occlude each other in accord with the rules of compositing. Velocity maps define how the layers are to be warped over time. The layered representation is more flexible than standard image transforms and can capture many important properties of natural image sequences. We describe some methods for decomposing image sequences into layers using motion analysis, and we discuss how the representation may be used for image coding and other applications.

... is a benchmark in visual object category recognition and detection, providing the vision and machine learning communities with a standard dataset of images and annotation, and standard evaluation procedures. Organised annually from 2005 to present, the challenge and its associated dataset has become accepted as the benchmark for object detection. This paper describes the dataset and evaluation procedure. We review the state-of-the-art in evaluated methods for both classification and detection, analyse whether the methods are statistically different, what they are learning from the images (e.g. the object or its context), and what the methods find easy or confuse. The paper concludes with lessons learnt in the three year history of the challenge, and proposes directions for future improvement and extension.

The BLAST programs are widely used tools for searching protein and DNA databases for sequence similarities. For protein comparisons, a variety of definitional, algorithmic and statistical refinements described here permits the execution time of the BLAST programs to be decreased substantially while enhancing their sensitivity to weak similarities. A new criterion for triggering the extension of word hits, combined with a new heuristic for generating gapped alignments, yields a gapped BLAST program that runs at approximately three times the speed of the original. In addition, a method is introduced for automatically combining statistically significant alignments produced by BLAST into a position-specific score matrix, and searching the database using this matrix. The resulting Position-Specific Iterated BLAST (PSIBLAST) program runs at approximately the same speed per iteration as gapped BLAST, but in many cases is much more sensitive to weak but biologically relevant sequence similarities. PSI-BLAST is used to uncover several new and interesting members of the BRCT superfamily.

This article describes the semantics of the language of statecharts as implenented in the STATEMATE system [Harel et al. 1990; Harel and Politi 1996]. The initial version of this semantics was developed by a team about.10 years ago. With the added experience of the users of the system it has since been extended and modified. This executable semantics has been in operation in driving the simulation, dynamic tests, and code generation tDols of STATEMATE since 1987, and a technical report describing it has been available from i-Logix, Inc. since 1989. We have now decided to revise and publish the report so as to make it more widely accessible, to alleviate some of the confusion about the "official semantics of the language, and to counter a number of incorrect comments made in the literature about the way statecharts have been implemented. For example, the survey [yon der Beek 1994] does not mention the STATEMATE implementation of statecharts or the semantics adopted for it at all, although this semantics is different from the ones surveyed therein (and was developed earlier than all of them except for Harel et al. [1987]). As another example, Leveson et al. [1995] describe a case that exhibits an unacceptable kind of behavior in a statechart, which they say is what the "semantics of statecharts" leads to (pp. 695-697). Unfortunately, they base their discussion of statechart semantics on one of the many semantics proposed by various authors (that of Pnueli and Shalev [1991]) and give the reader the impression that this is the official semantics of the language

Abstract not found

This paper aims to present a review of recent as well as classic image registration methods. Image registration is the process of overlaying images (two or more) of the same scene taken at different times, from different viewpoints, and/or by different sensors. The registration geometrically align two images (the reference and sensed images). The reviewed approaches are classified according to their nature (areabased and feature-based) and according to four basic steps of image registration procedure: feature detection, feature matching, mapping function design, and image transformation and resampling. Main contributions, advantages, and drawbacks of the methods are mentioned in the paper. Problematic issues of image registration and outlook for the future research are discussed too. The major goal of the paper is to provide a comprehensive reference source for the researchers involved in image registration, regardless of particular application areas.

Optical flow cannot be computed locally, since only one independent measurement is available from the image sequence at a point, while the flow velocity has two components. A second constraint is needed. A method for finding the optical flow pattern is presented which assumes that the apparent velocity of the brightness pattern varies smoothly almost everywhere in the image. An iterative implementation is shown which successfully computes the optical flow for a number of synthetic image sequences. The algorithm is robust in that it can handle image sequences that are quantized rather coarsely in space and time. It is also insensitive to quantization of brightness levels and additive noise. Examples are included where the assumption of smoothness is violated at singular points or along lines in the image.