@article{oai:nagoya.repo.nii.ac.jp:00021685,
 author = {熊谷, はるか and 道満, 恵介 and 出口, 大輔 and 井手, 一郎 and 村瀬, 洋 and KUMAGAI, Haruka and DOMAN, Keisuke and DEGUCHI, Daisuke and IDE, Ichiro and MURASE, Hiroshi},
 issue = {479},
 journal = {電子情報通信学会技術研究報告. MVE, マルチメディア・仮想環境基礎},
 month = {Mar},
 note = {本稿では,同一のイベントを異なる視点で撮影した同一シーンを検出するための領域別照合手法の検討結果について報告する.近年では,大量に蓄積されたニュース映像を内容に基づいて扱う技術が必要となっている.本稿ではその中でも,同一シーン検出手法に注目する.本手法では,映像を人物領域と背景領域に分割し,それぞれの領域同士を独立に照合し,その結果を統合する.撮影視点の違いに対応するため,領域同士の照合では,それぞれの領域の性質に応じて,撮影視点の違いに頑健な特徴を用いる.人物領域の照合には,特徴点の不均一性パターンを用い,背景領域の照合には,色ヒストグラム特徴を用いる.実際に放送されたニュース映像で同一シーン検出実験を行い,提案手法の有効性を確認した., In this paper, we report a study on region-based matching for detecting scene duplicates from news videos. Scene duplicates are videos taking the same event from different perspectives. Recently, technology to deal with the large amount of news videos based on their contents is needed. Among them, we are focusing on the scene duplicate detection problem. The proposed method first segments a video into the background and the person region, and then each region is matched independently, and finally the results are integrated. In order to deal with the different perspectives, the regions are matched with the features that are robust against the different perspectives according to the nature of each region. To match the person regions, the proposed method uses the pattern non-uniformity of the feature points. Meanwhile, to match the background region, the proposed method uses the color histogram feature. We conducted scene duplicate detection experiments using actual news videos. Prom the results, we confirmed the effectiveness of the proposed method., IEICE Technical Report;IE2011-146,IEICE Technical Report;MVE2011-108},
 pages = {75--80},
 title = {ニュース映像中の同一シーン検出のための領域別照合手法の検討},
 volume = {111},
 year = {2012}
}