ITR Collaborative Research: Indexing, Retrieval, and Use of Large Motion Databases

ITR 协作研究：大型运动数据库的索引、检索和使用

• 批准号: 0326322
• 负责人: Christos Faloutsos
• 金额: $ 140万
• 依托单位: Carnegie-Mellon University
• 依托单位国家: 美国
• 项目类别: Continuing Grant
• 财政年份: 2004
• 资助国家: 美国
• 起止时间: 2004-03-15 至 2009-02-28
• 项目状态: 已结题
• 来源: https://www.nsf.gov/awardsearch/showAward?AWD_ID=0326322&HistoricalAwards=false
• 关键词: ITR; Collaborative; Research; Indexing; Retrieval

The project will attempt to develop techniques for indexing and retrieving motion data. The PIs have already developed a substantial library of motion data. Motion databases are being used in the film and entertainment industry. However efficient access to such data is still a major challenge. The indexing algorithms to be developed will enable efficient access to the data. The retrieval algorithms will enable the retrieval of motion data. The project will also develop clustering techniques so that similar motions may be grouped together for efficient retrieval. The proposal has strong intellectual merit and will make contributions to advancing the state-of-the-art in motion databases. While the main application area at present is the entertainment and film industry, the results of the project may be applied to defense, intelligence and transportation applications. One can expect this project to have broader impact in homeland security applications.

该项目将尝试开发索引和检索运动数据的技术。 PI 已经开发了一个庞大的运动数据库。运动数据库正在电影和娱乐行业中使用。然而，有效访问此类数据仍然是一个重大挑战。待开发的索引算法将能够有效地访问数据。检索算法将能够检索运动数据。该项目还将开发聚类技术，以便将相似的动作分组在一起以进行有效的检索。 该提案具有很强的智力价值，将为推进最先进的运动数据库做出贡献。虽然目前主要应用领域是娱乐和电影行业，但该项目的成果可能应用于国防、情报和交通应用。人们可以预期这一项目将对国土安全应用产生更广泛的影响。