論文 - 馬場口　登

Towards abstracting sports video by highlights 査読

N Babaguchi

2000 IEEE INTERNATIONAL CONFERENCE ON MULTIMEDIA AND EXPO, PROCEEDINGS VOLS I-III   1519 - 1522   2000年

　詳細を見る

Recently, video abstraction has become a demanding application in multimedia computing. It is defined as creating shorter video clips or video posters from the original video stream. In this paper, we present a basic approach towards abstracting sports video by highlights, dealing with American football games, Using event based indexing, we create an abstracted video clip automatically. To select the appropriate highlights of the game, an impact factor reflecting on the importance of the event is newly introduced. It was possible to make an about 5-minute clip from the 3-hour original video.

［特別講演］メディア理解による映像メディアの構造化 招待

馬場口登

電子情報通信学会技術研究報告   PRMU99-42/IE99-18/MVE99-38   39 - 46   1999年7月

Detecting events from continuous media by intermodal collaboration and knowledge use 査読

N Babaguchi, S Sasamori, T Kitahashi, R Jain

IEEE INTERNATIONAL CONFERENCE ON MULTIMEDIA COMPUTING AND SYSTEMS, PROCEEDINGS VOL 1   782 - 786   1999年

　詳細を見る

In this paper, we propose an event network, which is a structured representation oriented for the contents of continuous media, as well as present two methods of detecting events as the first step to construct the network. We here deal with sports TV programs, considering American football as a case study. The first method is simple intermodal collaboration: linking between visual and linguistic (closed caption) streams. Using domain knowledge about state transitions of football games, the second method attempts to extract specific visual objects including the information about contents. The experimental results indicate that the both methods are effective for event detection.

Solving contradiction in knowledge-base without interaction 査読

K Katsurada, M Koyama, K Ohara, N Babaguchi, T Kitahashi

1998 IEEE INTERNATIONAL CONFERENCE ON SYSTEMS, MAN, AND CYBERNETICS, VOLS 1-5   1546 - 1551   1998年

　詳細を見る

We propose a non-interactive method for solving the contradictions caused by exceptions to ordinary rules. It is realized by 1) detecting the ordinary rules which have the instances in their bodies, and 2) converting them into the default; rules. To reduce the default rules which need much time in reasoning, we convert the minimal sets of ordinary rules to solve contradictions. Since the proposed method is executed without interaction with human, it contributes to automatic rule-base maintenance.

［解説］文書画像の記号化と表現メディアの変換－グラフ領域への応用－ 招待

北橋忠宏, 馬場口登, 角所考

画像ラボ   7 ( 9 )   21 - 24   1996年9月

Generation of sketch map image and its instructions to support the understanding of geographical information 査読

Noboru Babaguchi, Seiichiro Dan, Tadahiro Kitahashi

Proceedings - International Conference on Pattern Recognition   3   274 - 278   1996年

　詳細を見る

In this paper, we propose a method of generating a sketch map drawing and its instructions in order to support the route understanding of a human. Both are given from a structured data, called the road network, which is a graph augmented by the attributes of roads and crossings. In generating a sketch map drawing, the pictorial information about the shape and the direction of roads is modified. The sketch map drawing can be generated at any simplification level by controlling a parameter called simpleness. The instructions corresponding to the sketch map are produced by assigning appropriate terms into sentence templates. We verified that favorable results are obtained by this method. © 1996 IEEE.

［解説］地図理解支援のための略地図生成について－地図デフォルメのシステム化－ 招待

馬場口登, 上田俊弘, 淡誠一郎, 北橋忠宏

画像ラボ   6 ( 7 )   23 - 26   1995年7月

REPRESENTING, UTILIZING AND ACQUIRING KNOWLEDGE FOR DOCUMENT IMAGE UNDERSTANDING 査読

K KISE, N BABAGUCHI

IEICE TRANSACTIONS ON INFORMATION AND SYSTEMS   E77D ( 7 )   770 - 777   1994年7月

　詳細を見る

This paper discusses the role of knowledge in document image understanding from the viewpoints of representation, utilization and acquisition. For the representation of knowledge, we propose two models, a layout model and a content model, which represent knowledge about the layout structure and content of a document, respectively. For the utilization of knowledge, we implement layout analysis and content analysis which utilize a layout model and a content model, respectively. The strategy of hypothesis generation and verification is introduced in order to integrate these two kinds of analysis. For the acquisition of knowledge, we propose a method of incremental acquisition of a layout model from a stream of example documents. From the experimental results of document image understanding and knowledge acquisition using 50 samples of visiting cards, we verified the effectiveness of the proposed method.

GENERATION OF SKETCH MAP DRAWING FROM VECTORIZED IMAGE 査読

N BABAGUCHI, K TANAKA, T KITAHASHI

ICIP-94 - PROCEEDINGS, VOL III   207 - 211   1994年

非単調推論 招待

馬場口登

日本ファジィ学会誌   4 ( 4 )   608 - 619   1992年8月

Curvedness of a line picture 査読

Noboru Babaguchi, Tsunehiro Aibara

Pattern Recognition   20 ( 3 )   273 - 280   1987年

　詳細を見る

The shape analysis of a binary picture is of great importance for pictorial pattern recognition. In this paper, we propose a useful geometric feature parameter called curvedness. Curvedness represents which lines are dominant in a binary picture, straight or curved. Our algorithm for measuring curvedness is based on the relationship between the distance to a boundary point on each black point along each quantized direction and the mean width of a binary picture. We investigate the fundamental property of curvedness. The experimental results for Japanese Hiragana and Kanji characters show the validity of curvedness. © 1987.