Yoneharu Fujita

Semi-automatic program construction from specifications using library modules

A method of semiautomatic specification refinement and program generation using library modules, is described. Users write their specifications and modify and rearrange them so that they can be refined with the aid of the library modules. When a specification is given, a refinement system, called MAPS (module-aided program construction system) searches for library modules applicable to the given specification, replaces the specification with a more detailed description written in the operation part of the modules, and converts the refined specification into a program written in a programming language designated by the user. Case-like expressions or pseudo-natural language expressions are used for describing users specifications and specifications for library modules. >

A comparison with covariance features on player uniform number recognition

Broadcast sports video report is expected be the generated player data in real time. Therefore, uniform number recognition need to fast computing. Covariance feature has possibilities to do it in real time. We present a method for uniform number recognition using the covariance feature as a region descriptor. The covariance feature is represented by the covariance matrix of image features such as spatial position, intensity, higher order derivatives, etc. Thus, the covariance feature vary by used image features. Feature matching is a simple nearest neighbor search under a distance measure [1]. In the experiments, the six covariances compared. The recognition rate is 79% in a multiple player game.

Normalization of Titles and Their Retrieval.

Abstract This paper presents a method of normalizations of English titles and their retrieval. The title expressed by a noun phrase or a noun clause is converted to a function-expression by parsing. For the retrieval with a reasonable recall rate as well as a high precision rate, the function-expression is transformed to a predicate-governor form, and then normalized to a standard form. Therefrom, various items are extracted and recorded in a hierarchical tree-like inverted file. In order to keep the recall rate in a reasonable value, several retrieval stages are implemented based on the key-term and case-label matching. The retrieval is controlled by the preciseness of the specification of case-labels for each key-term.

Digital scorebook: football logging and visualization using image processing support

We propose a digital scorebook for football game which digitizes a football game video and presents it as an animation. The proposed system consists of player position estimation from the game video, event selection interface and player movement animation. Player position estimation allows for flexible movements and angles of the cameras including zoom in and out, pan, tilt, and yaw. This reliable and robust estimation of the player movement is based on image analysis by synthesis and Generalized Hough Transform(GHT). The operator can annotate game scenes based on player movement data using event selection interface. The player movement is represented by the animation whose characters have number or letter figures to emphasize the data. We demonstrate the applicability of player position estimation and play annotation scheme via the character behaviors in animation.