研究者詳細 - 馬場口　登

論文 - 馬場口　登

分割表示 251 件中 121 - 140 件目／全件表示 >>

番組紹介テキストの特徴に基づく番組紹介スポットの自動生成査読

河合吉彦, 住吉英樹, 柴田正啓, 八木伸行, 馬場口登

映像情報メディア学会誌 64 ( 1 ) 85 - 93 2010年1月

［解説］マルチメディア検索の技術動向

馬場口登

映像情報メディア学会誌, 講座：マルチメディア検索の最前線（第１回） 64 ( 1 ) 58 - 63 2010年1月

Automatically protecting privacy in consumer generated videos using intended human object detector 査読

Yuta Nakashima, Noboru Babaguchi, Jianping Fan

MM'10 - Proceedings of the ACM Multimedia 2010 International Conference 1135 - 1138 2010年

The growing popularity of video sharing services such as YouTube enables us to upload and share consumer generated videos (CGVs) easily, resulting in disclosure of the privacy sensitive information (PSI) of persons, i.e., their appearances. Therefore, we need a technique for automatically protecting the privacy in CGVs
however, the main problem is how to determine PSI regions automatically. In this paper, we propose a novel system for automatically protecting the privacy in CGVs. The proposed system tackles the problem of determining PSI regions by using an intended human object detector that detects human objects which the camera person wanted to capture to achieve his/her capture intention. In addition, the proposed system adopts several PSI obscuring methods such as blocking out, blurring and seam carving. We present the results of subjective evaluations of a privacy protected video in terms of the visual quality and acceptability of PSI disclosure, as well as the performance of the intended human object detector. © 2010 ACM.

Hierarchical anomality detection based on situation 査読

Shuichi Nishio, Hiromi Okamoto, Noboru Babaguchi

Proceedings - International Conference on Pattern Recognition 1108 - 1111 2010年

In this paper, we propose a novel anomality detection method based on external situational information and hierarchical analysis of behaviors. Past studies model normal behaviors to detect anomality as outliers. However, normal behaviors tend to differ by situations. Our method combines a set of simple classifiers with pedestrian trajectories as inputs. As mere path information is not sufficient for detecting anomality, trajectories are first decomposed into hierarchical features of different abstract levels and then applied to appropriate classifiers corresponding to the situation it belongs to. Effects of the methods are tested using real environment data. © 2010 IEEE.

Face Image Retrieval across Age Variation Using Relevance Feedback 査読

Naoko Nitta, Atsushi Usui, Noboru Babaguchi

ADVANCES IN MULTIMEDIA MODELING, PROCEEDINGS 5916 152 - 162 2010年

Given a single face image of a specific person as a query, it is very difficult to retrieve all of his/her images from a personal image collection stored for a long term clue to age-related changes in facial appearances. This paper proposes to apply relevance feedback to enhance the performance of image retrieval from the image collections with age variation. Specifically, we propose two types of update schemes: i) query expansion and ii) weight updating and show the effects of each scheme by experiments with two actual image collections. For an image collection, the recall rate improved from 40.8% to 72.5% after five iterations of relevance feedback.

EVENT TACTIC ANALYSIS IN SPORTS VIDEO USING SPATIO-TEMPORAL PATTERN 査読

Minh-Son Dao, Keita Masui, Noboru Babaguchi

2010 IEEE INTERNATIONAL CONFERENCE ON IMAGE PROCESSING 1497 - 1500 2010年

Recently, event detection in sports videos has been gaining some remarkable results. Unfortunately, there is a lack of useful tools for users to explore and exploit these event clips on their own demands. In this paper, a novel method using spatio-temporal patterns to analyze event tactics in sports videos is introduced. The proposed method aims to understand tactics of events such as distributions and speeds of players, or attacking/defensive formations throughout a time when such events happen without tracking objects. The major contribution of the proposed method is to model event tactics by using sequence of symbols. Each symbol represents a distribution of players in a certain period of time. Therefore, a sequence of symbols intrinsically is concerned as spatio-temporal patterns. By using these patterns, an event tactic is detected, explained, and integrated into an event video to create a visualizing abstract. This visualizing abstract is very useful to help users understand an event tactic without watching whole clip. Moreover, users could query by an example or by a text to find all events sharing the same tactic. Thorough testing with over 100 goal clips in soccer domain demonstrate the superiority of the proposed method in terms of precision recall ratios.

Discriminating intended human objects in consumer videos 査読

Hiroshi Uegaki, Yuta Nakashima, Noboru Babaguchi

Proceedings - International Conference on Pattern Recognition 4380 - 4383 2010年

In a consumer video, there are not only intended objects, which are intentionally captured by the camcorder user, but also unintended objects, which are accidentally framed-in. Since the intended objects are essential to present what the camcorder user wants to express in the video, discriminating the intended objects from the unintended objects are beneficial for many applications, e.g., video summarization, privacy protection, and so forth. In this paper, focusing on human objects, we propose a method for discriminating the intended human objects from the unintended human objects. We evaluated the proposed method using 10 videos captured by 3 camcorder users. The results demonstrate that the proposed method successfully discriminates the intended human objects with 0.45 of recall and 0.80 of precision. © 2010 IEEE.

Digital diorama: Sensing-based real-world visualization 査読

Takumi Takehara, Yuta Nakashima, Naoko Nitta, Noboru Babaguchi

Communications in Computer and Information Science 81 663 - 672 2010年

Many sensors around the world are consistently collecting the real-time real-world data. The data streams captured by these sensors can give us an idea of what is going on in a specific area
however, it is not easy for humans to understand their spatial and temporal relationships by just looking at them independently. This paper proposes to construct Digital Diorama, a three-dimensional view where viewers can see at a glance how people are moving around the monitored space without violating their privacy, by integrating multiple data streams captured by stationary cameras and RFID readers in real time. Digital Diorama realizes such real-world visualization with the following features: 1) view control, 2) real-time camera image superimposition, and 3) privacy control. We have demonstrated that Digital Diorama for a shopping center was able to present the current positions of persons and real-time camera images in approximately 1 frame per second. © Springer-Verlag Berlin Heidelberg 2010.

Detecting intended human objects in human-captured videos 査読

Yuta Nakashima, Noboru Babaguchi, Jianping Fan

2010 IEEE Computer Society Conference on Computer Vision and Pattern Recognition - Workshops, CVPRW 2010 33 - 40 2010年

When people take videos, they always want to capture intended objects, which are essential for presenting what they want to express in their videos, and to share the intended objects with others. The concept of intended objects provide a novel perspective for video content analysis, and detecting intended objects may be beneficial for wide range of applications such as video understanding and semantics interpretation, video summarization, video adaptation, video privacy protection, and so on. In this paper, we focus on a particular type of intended objects, i.e., intended human objects, and an interesting method is developed for detecting intended human objects automatically from human-captured videos. We also investigate the correlation between intended human objects and visual attention. Our experimental results indicate that our method can successfully detect the intended human objects. © 2010 IEEE.

Modeling visual information by spatio-temporal patterns to analyze event tactic in sports video 査読

Keita Masui, Minh-Son Dao, Noboru Babaguchi

2010 2nd European Workshop on Visual Information Processing, EUVIP2010 198 - 203 2010年

Although event detection in sports videos has been gaining some remarkable results, tools for exploring and exploiting these event clips on their own demands are far from user's expectation. In this paper, a novel method using spatio-temporal patterns to model visual information tailored to analyze event tactics in sports videos without tracking objects is introduced. The major contribution of the proposed method is to represent visual information by using a sequence of symbols. Each symbol represents a distribution of players in a certain period of time. By using these sequences, event tactics are detected, explained, and visualized to help users understand event tactics without watching whole clips. Moreover, users could query by an example or by a text to find all events sharing the same tactic. Thorough testing with over 100 goal clips in soccer domain demonstrates the superiority of the proposed method in terms of precision recall ratios. ©2010 IEEE.

Real-time user position estimation in indoor environments using digital watermarking for audio signals 査読

Ryosuke Kaneto, Yuta Nakashima, Noboru Babaguchi

Proceedings - International Conference on Pattern Recognition 97 - 100 2010年

In this paper, we propose a method for estimating the user position where a user is holding a microphone in an indoor environment using digital watermarking for audio signals. The proposed method utilizes detection strengths, which are calculated while detecting spread-spectrum-based watermarks. Taking into account delays and attenuation of the watermarked signals emitted from multiple loudspeakers and other factors, we construct a model of detection strengths. The user position is estimated in real-time using the model. The experimental results indicate that the user positions are estimated with 1.3 m of root mean squared error on average for the case where the user is static. We demonstrate that the proposed method successfully estimates the user position even when the user moves. © 2010 IEEE.

［解説］グランドチャレンジ

馬場口登

映像情報メディア学会誌, ふぉーかす 63 ( 12 ) 2009年12月

NHK STRL at TRECVID 2009: Surveillance Event Detection and High-Level Feature Extraction 査読

M. Takahashi, Y. Kawai, M. Fujii, M. Shibata, N. Babaguchi, S. Satoh

Proc. of TREC Video Retrieval Evaluation (TRECVID) Workshop 2009年11月

Digital Diorama: Real-Time Adaptive Visualization of Public Spaces 査読

T. Takehara, Y. Nakashima, N. Nitta, N. Babaguchi

Proc. of 1st International Conference on Security Camera Network, Privacy Protection and Community Safety (SPC2009) 2009年10月

Security Analysis of Anonymous Communication System 3-Mode Net Against Collaborating Nodes 査読

K. Kono, S. Nakano, Y. Ito, N. Babaguchi

Proc. of 2009 APSIPA Annual Summit Conference(APSIPA ASC 2009) 105 - 110 2009年10月

［招待講演］映像サーベイランスとプライバシ保護招待

馬場口登

2009年9月

［解説］パターン認識・メディア理解の10大チャレンジテーマ

鷲見和彦, 内田誠一, 佐藤真一, 佐藤洋一, 日浦慎作, 福井和広, 馬場口登

電子情報通信学会誌 92 ( 8 ) 665 - 675 2009年8月

［解説］今なぜグランドチャレンジか

馬場口登, 鷲見和彦

電子情報通信学会誌 92 ( 8 ) 640 - 642 2009年8月

User and Device Adaptation in Summarizing Sports Videos 査読

Naoko Nitta, Noboru Babaguchi

IEICE TRANSACTIONS ON INFORMATION AND SYSTEMS E92D ( 6 ) 1280 - 1288 2009年6月

Video summarization is defined as creating a video summary which includes only important scenes in the original video streams. In order to realize automatic video summarization, the significance of each scene needs to be determined. When targeted especially on broadcast sports videos, a play scene, which corresponds to a play, can be considered as a scene unit. The significance of every play scene can generally be determined based on the importance of the play in the game. Furthermore, the following two issues should be considered: 1) what is important depends on each user's preferences, and 2) the summaries should be tailored for media devices that each user has. Considering the above issues, this paper proposes a unified framework for user and device adaptation in summarizing broadcast sports videos. The proposed framework summarizes sports videos by selecting play scenes based on not only the importance of each play itself but also the users' preferences by using the metadata, which describes the semantic content of videos with keywords, and user profiles, which describe users' preference degrees for the keywords. The selected scenes are then presented in a proper way using various types of media such as video, image, or text according to device profiles which describe the device type. We experimentally verified the effectiveness of user adaptation by examining how the generated summaries are changed by different preference degrees and by comparing our results with/without using user profiles. The validity of device adaptation is also evaluated by conducting questionnaires using PCs and mobile phones as the media devices.

［招待講演］センシングウェブにおける観測型実世界コンテンツ招待

馬場口登

2009年6月

　前のページ - 次のページ　

<馬場口 登>

論文 - 馬場口 登

<馬場口　登>

論文 - 馬場口　登