Tadahiro Kitahashi

Generating Semantic Descriptions of Broadcasted Sports Videos Based on Structures of Sports Games and TV Programs

This paper presents a model to represent a broadcasted sports video in a semantic way and proposes a method of automatically generating semantic descriptions of significant scenes. Representation of a video should clarify the semantic content of the video as accurately as possible. Our model structurizes the video and specifies suitable semantic descriptions for video segments paying attention to the structure of both a sports game and a sports TV program. As the elements of these semantic descriptions, the proposed method tries to obtain the information about the plays and their related players from the closed-caption stream by searching key phrases. Finding the corresponding segments of the video by means of template matching for the image stream attaches these textual descriptions to the proper portion of the video. In this paper, we discuss some experimental results of our method and the potentiality for integrating these results into the standardized MPEG-7 description tools.

A cooperative recognition of human movements and related objects guided by functional model of objects

We propose a new type of object models that includes functional attributes like edible, portable and supportable, instead of or in addition to the conventional appearance based ones like color, texture, shape and so forth. It leads to not conventional recognition of objects one by one individually and separately but understanding a scene where humans are interacting with objects. The detection of the functional attributes defined newly in a proposed model requires recognition of humans actions that actually exhibit interactions with mainly an object, and in some cases interaction between objects each other. This has ever been ignored in the traditional object recognition, since a dominant situation for recognition of objects is set up as a stationary circumstance without human activities

A Dynamic Recognition of Human Actions and Related Objects

In the field of image understanding, it is becoming popular to recognize human actions and objects in a scene to improve human-computer interaction. Recently, various methods for scene recognition have been proposed, and most of them focus on recognizing human actions and objects separately. We consider, however, it is important to recognize them complementary, because human actions are closely related with objects. The relationship between actions and objects are represented by hierarchical models. First, movement of human head and hands are tracked by stereo vision. Features of actions such as position and direction of the head and hands are extracted and input to dynamic Bayesian networks to classify actions roughly. Then the actions and related objects are refined by using conceptual models of human actions and objects. Finally, detailed actions and objects are recognized by referring each models cooperatively

Virtual change of illumination color in image based rendering

An extension of the ability of the image based rendering (IBR) is described by presenting a method of generating images corresponding to the virtual change of the lighting color. It is an additional ability to the previous proposal that allows generating images by virtually changing the lighting orientation. It is also suggested that the basic idea developed in this paper might be applicable to the virtual varying object material.