Budget Amount *help |
¥18,980,000 (Direct Cost: ¥14,600,000、Indirect Cost: ¥4,380,000)
Fiscal Year 2010: ¥5,070,000 (Direct Cost: ¥3,900,000、Indirect Cost: ¥1,170,000)
Fiscal Year 2009: ¥6,630,000 (Direct Cost: ¥5,100,000、Indirect Cost: ¥1,530,000)
Fiscal Year 2008: ¥7,280,000 (Direct Cost: ¥5,600,000、Indirect Cost: ¥1,680,000)
|
Research Abstract |
This project addressed a new technology for video semantic analysis and video archive structuring based on the analysis of semantic relation graph composed of video near-duplicate relation obtained from large-scale and diverse broadcast video archive, thus independent from standard image semantic analysis. In concrete, (1) Implementation of near-duplicate detection applicable to large-scale broadcast video archive (2) Classification of near-duplicate relation and extraction of semantic relation (3) Graph structure representation composed of extracted semantic relation and its analysis (4) Revealing potential of semantic analysis of broadcast video archive based of video near-duplicate detection
|