Home Video Summarization by Shot Characteiristics
スポンサーリンク
概要
- 論文の詳細を見る
Digital video (DV) cameras are popularly used to capture events. These recorded videos are easily summed up to many hours of the video data. Search for one particular record is a time consuming and boring task. Therefore, it is more desirable to edit or summarize the entire records for guide scanning. We propose a home video summarization using shot importance. Shot importance is defined by the shot duration and motion activity. The more important the shot is, the more number of Representative frames (R-frames) is retrieved. When the events of all shots are unrelated, it is desired to retrieve more information from more shots. Our algorithm allows user to select the number of shot to be appeared in the summarized video. In the experiment, videos are summarized by different summarization rate. All the summarized videos are evaluated. We further evaluate our result with an existing algorithm. The experiment shows that our algorithm gives an acceptable summarized result.
- 一般社団法人電子情報通信学会の論文
- 2003-06-06
著者
-
Aizawa Kiyoharu
Department Of Elec. Eng. Department Of Frontier Informatics Tuh University Of Tokyo
-
Aizawa Kiyoharu
Department Of Electrical Engineering And Frontier Informatics University Of Tokyo
-
Cooharojananone Nagul
Department Of Electrical Engineering And Frontier Informatics University Of Tokyo
-
AUETHAVIKIAT Supatana
Institute of Industrial Science, University of Tokyo
-
Auethavikiat Supatana
Institute Of Industrial Science University Of Tokyo
関連論文
- ITERATIVE RECONSTRUCTION OF VIRTUAL VIEW FROM MULTIPLE IMAGES CAPTURED WITH AN UNSTRUCTURED CAMERA ARRAY(International Workshop on Advanced Image Technology 2005)
- ウェアラブルビデオの環境移動変化シーン検出
- Robust Object-Based Watermarking Using Feature Matching
- A Novel Technique for Improving Compressed Image by Mapping a Reference Image
- Vision Chip for Very Fast Detection of Motion Vectors: Design and Implementation (Special Issue on Integrated Electronics and New System Paradigms)
- Color Indexing by Weighted Cumulative Angular Distance (映像メディア処理と一般--映像コンテンツの製作編集)
- ライフログの取得と検索のためのシステム構築
- LIFE LOG PLATFORM FOR CONTINUOUS AND DISCRETE RECORDING AND RETRIEVAL OF PERSONAL MEDIA(International Workshop on Advanced Image Technology 2007)
- LIFE LOG PLATFORM FOR CONTINUOUS AND DISCRETE RECORDING AND RETRIEVAL OF PERSONAL MEDIA
- Retrieval of Images Captured by Car Cameras Using Its Front and Side Views and GPS Data(Advanced Image Technology)
- A-16-21 Hierarchical Approach for Personal Life Media Retrieval
- Car Location Matching Using Front & Side-View and GPS Data(International Workshop on Advanced Image Technology 2006)
- A-16-14 Audio Segmentation using a Large Number of Microphones for Multimedia Retrieval in a Ubiquitous Environment
- ショット特徴を用いたホームビデオ要約
- Image Acquisition by Pixel-Based Random-Access Image Sensor for a Real-Time IBR System(Special Issue on Signals, Systems and Electronics Technology)
- 23-1 Cumulative Angular distance measure and its improvement for color indexing
- ロバスト異方性領域成長による2段階画像セグメンテーション
- D-12-71 Shot importance based for home video summarization
- A-15-15 Retrieval of Locomotion Patterns Using Sketch Based Spatial Queries
- D-12-7 Shot-adaptive sampling for video summarization
- Ubiquitous Display Controlled by Mobile Terminals(Special Issue on Mobile Multimedia Communications)
- A-20-12 Interactive Multimedia Retrieval Based on Illumination Changes in a Multi Camera Ubiquitous Environment
- A Basic Framework for Event-Based Monitoring by Networked Smart Image Sensors (特集 画像の認識と理解)
- Computational Sensors : Vision VLSI (Surveys on Image Processing Technologies : Algorithms, Sensors and Applications)
- Home Video Summarization by Shot Characteiristics
- 10-12 Video Summarization for a Large Number of Cameras Using Floor Sensors in a Ubiquitous Environment
- 9-2 Key Frame Extraction Based on Content and Context in Life Log Video
- SIFT-Based Non-blind Watermarking Robust to Non-linear Geometrical Distortions