Social Sensing Technology Suite based on Object Mining for Large-Scale Video Archives

2016 Fiscal Year Final Research Report

• Project/Area Number: 26240016
• Research Category: Grant-in-Aid for Scientific Research (A)
• Allocation Type: Single-year Grants
• Section: 一般
• Research Field: Multimedia database
• Research Institution: National Institute of Informatics
• Principal Investigator: SATOH Shin'ichi 国立情報学研究所, コンテンツ科学研究系, 教授 (90249938)
• Co-Investigator(Renkei-kenkyūsha): KATAYAMA Norio 国立情報学研究所, コンテンツ科学研究系, 准教授 (60280559) ; LE Duy-Dinh 国立情報学研究所, コンテンツ科学研究系, 准教授 (80450170) ; MO Hiroshi 国立情報学研究所, コンテンツ科学研究系, 助教 (60312203)
• Project Period (FY): 2014-06-27 – 2017-03-31
• Keywords: 大規模放送映像アーカイブ / 社会センシング / 物体マイニング / 映像マイニング

Outline of Final Research Achievements

We study and develop technology suite for social sensing to evaluate events in our society (financial situation, sports events, disasters, accidents, etc.) by analyzing temporal exploration and frequencies of objects (person, location, products, file footage, etc.) in broadcast video archives. In concrete, we study object mining technique to detect and identify objects in large-scale broadcast video archives, and social sensing technology suite to accomplish multi-facet analysis of the occurrences of the objects in the space of broadcast video archives. Especially, object mining is a challenging topic, and we address significant performance and efficiency boost by global consistency checking.

Free Research Field

マルチメディア検索