研究者詳細 - 馬場口　登

論文 - 馬場口　登

分割表示 251 件中 141 - 160 件目／全件表示 >>

［解説］特集「センシングウェブ」にあたって

馬場口登, 美濃導彦

人工知能学会誌 24 ( 2 ) 177 - 178 2009年3月

［招待講演］超大規模ヘテロセンサネットワーキング技術の応用－センシングWebプロジェクト－招待

馬場口登

2009年2月

［招待講演］映像サーベイランスとプライバシー保護

馬場口登

2009年1月

A New Linguistic-Perceptual Event Model for Spatio-Temporal Event Detection and Personalized Retrieval of Sports Video 査読

Minh-Son Dao, Sharma Ishan Nath, Noboru Babaguichi

IMAGE ANALYSIS AND PROCESSING - ICIAP 2009, PROCEEDINGS 5716 594 - 603 2009年

This paper proposes a new linguistic-perceptual event model tailoring to spatio-temporal event detection and conceptual-visual personalized retrieval of sports video sequences. The major contributions of the proposed model are hierarchical structure, independence between linguistic and perceptual part, and ability of capturing temporal information of sports events. Thanks to these advanced contributions, it is very easy to upgrade model events from simple to complex levels either by self-studying from inner knowledge or by being taught from plug-in additional knowledge. Thus, the proposed model not only can work well in unwell structured environments but also is able to adapt itself to new domains without the need (or with a few modification) for external reprogramming, re-configuring and re-adjusting. Thorough experimental results demonstrate that events are modeled and detected with high accuracy and automation, and users' expectation of personalized retrieval is highly satisfied.

Matrix-based algorithm for integrating inheritance relations of access rights for policy generation 査読

Kazuhiro Kono, Yoshimichi Ito, Akihito Aoyama, Hiroaki Kamoda, Noboru Babaguchi

Journal of Information Processing 17 318 - 327 2009年

This paper presents a matrix-based algorithm for integrating inheritance relations of access rights for generating integrated access control policies which unify management of various access control systems. Inheritance relations of access rights are found in subject, resource, and action categories. Our algorithm first integrates inheritance relations in each category, and next, integrates inheritance relations of all categories. It is shown that these operations can be carried out by basic matrix operations. This enables us to implement the integration algorithm very easily.

Psychological study for designing privacy protected video surveillance system: PriSurv 査読

Noboru Babaguchi, Takashi Koshimizu, Ichiro Umata, Tomoji Toriyama

Protecting Privacy in Video Surveillance 147 - 164 2009年

Abstract As video surveillance systems are widely deployed, concerns continue to grow about invasion of privacy. We have built a privacy protected video surveillance system called PriSurv. Although PriSurv protects subject privacy using image processing, criteria of controlling the subject's visual information that is privacy-sensitive should be clarified. Visual information must be disclosed by considering the trade-off between privacy and security. The level of privacy-sensitive visual information that could be disclosed to a viewer is simply called disclosable privacy in this chapter. Disclosable privacy, which deeply involves the personal sense, is affected by many factors. A sense of privacy is individual, but in some cases it might have common factors. A sense of privacy is individual, but in some cases it might have common factors. In this chapter, we analyze what factors determine and affect disclosable privacy by applying statistical analysis to questionnaire-based experimental results. These results indicate that disclosable privacy is concerned with how much a subject has feeling of closeness to a viewer and expects the viewer's responsibility. They also show that disclosable privacy differs greatly by individuals. Reflecting the obtained findings in PriSurv's design, we adapt PriSurv to reflect a personal sense of privacy. © 2009 Springer London.

Preserving topological information in sub-trajectories-based representation for spatio-temporal trajectories indexing and retrieval 査読

Minh-Son Dao, Ishan Nath Sharma, Noboru Babaguchi

MM'09 - Proceedings of the 2009 ACM Multimedia Conference, with Co-located Workshops and Symposiums 641 - 644 2009年

Trajectories of moving objects are known as one of the most important cues for understanding semantics in video data. Although there are a lot of significant researches dealing with trajectory analysis tailored to indexing and retrieval, several problems still remain. One of them is a trade-off between whole trajectory- and sub-trajectories- based methods. The former problem is that representing a trajectory as a whole is not appropriate for detecting similar patterns of the trajectory. In contrast, the latter is that even though some key portion of two trajectories share similar patterns, the whole trajectories may be totally different. Therefore, this paper proposes a novel method to optimize such trade-off. By representing a trajectory as a combination of sequence of "word" - each word's character represents one distinct feature extracted from sub-trajectories (i.e. segments), and a topological graph of trajectory's segments, the proposed method is shift and scale invariant, can handle occlusion and distortion, and can discover similar patterns among trajectories. Thorough comparisons with well-known methods demonstrate the superiority of the proposed method in terms of precision recall ratios. Copyright 2009 ACM.

Performance Analysis of Anonymous Communication System 3-Mode Net 査読

Kazuhiro Kono, Shinnosuke Nakano, Yoshimichi Ito, Noboru Babaguchi

FIFTH INTERNATIONAL CONFERENCE ON INFORMATION ASSURANCE AND SECURITY, VOL 2, PROCEEDINGS 593 - 596 2009年

This paper analyzes the performance of 3-Mode Net (3MN), which is a new anonymous communication system proposed in [1]. In particular, we give the probability distributions of the number of relay nodes as well as the number of encryption required for communications. The expectations and variances of these two numbers are also given. These results enable us to grasp the influence of the probabilities of mode selections in 3MN. Numerical examples are also presented to illustrate these results.

Breaking the YASS Algorithm via Pixels and DCT Coefficients Analysis 査読

X. Yu, N. Babaguchi

Proc. of International Conference on Pattern Recognition (ICPR2008) 2008年12月

Digital Diorama: Adaptive 3D Visualization System for Indoor Environment 査読

R. Yamaguchi, Y. Yamamoto, N. Nitta, Y. Ito, N. Babaguchi

Proc. of International Workshop on Sensig Web 17 - 24 2008年12月

NHK STRL at TRECVID 2008: High-Level Feature Extraction and Surveillance Event Detection 査読

Y. Kawai, M. Takahashi, M. Sano, M. Fujii, M. Shibata, N. Yagi, N. Babaguchi

Proc. of TREC Video Retrieval Evaluation (TRECVID) Workshop 1 358 - 365 2008年11月

［解説］個人的選好獲得システムの構築：興味区間抽出・興味度推定・プロファイル作成招待

新田直子, 馬場口登

画像ラボ vol.19 ( no.11 ) 58 - 64 2008年11月

Mining Temporal Information and Web-Casting Text for Automatic Sports Event Detection 査読

M. S. Dao, N. Babaguchi

Proc. of IEEE International Workshop on Multimedia Signal Processing (MMSP2008) 616 - 621 2008年10月

多重暗号化と確率的動作選択に基づく双方向通信可能な匿名通信方式:3-Mode Net 査読

三宅直貴, 伊藤義道, 馬場口登

電子情報通信学会論文誌A J91-A ( 10 ) 949 - 956 2008年10月

部分映像挿入による時間軸上の映像補完査読

庄司竜太, 新田直子, 馬場口登

映像情報メディア学会誌 62 ( 10 ) 1633 - 1640 2008年10月

［招待講演］映像サーベイランスとプライバシー招待

馬場口登

2008年9月

［解説］テレビ視聴者の好みを推定しよう

馬場口登, 新田直子

放送文化基金報 ( no.71 ) 28 - 29 2008年9月

Sensing Web Project - How to handle privacy information in sensor data - 査読

M. Minoh, K. Kakusho, N. Babaguchi

Proc. of 12th Intl. Conf. Information Processing and Management of Uncertainty in Knowledge-based Systems(IPMU08) 863 - 869 2008年6月

［解説］ネットワークロボットのセンシングとプライバシー保護技術

馬場口登, 西尾修一

電子情報通信学会誌 91 ( 5 ) 380 - 386 2008年5月

_Privacy Protected Video Surveillance System Using Adaptive visual Abstraction 査読

K. Chinomi, N. Nitta, Y. Ito, N. Babaguchi

Proc. of Multimedia Modeling Conference (MMM2008) 144 - 154 2008年1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