Video Vectorization between Two Keyframes (情報センシング メディア工学)

スポンサーリンク

概要

• 論文の詳細を見る

• We propose a technique to generate a vectorized representation of video data from raster video. Multiple frames from the input video are vectorized and used as keyframes and vector-based time data is automatically generated between pairs of keyframes. First, each keyframe is converted into a mesh constructed of triangular Bezier patches. Mesh vertices' are then tracked and approximated using Bezier spline curves. Vertices that were not successfully tracked were interpolated using a linear combination of nearby, successfully tracked vertices. We present the results of applying our method and discuss the validity and possible applications of the method.

• 2012-06-04

著者

• Taniguchi Yukinobu

  Ntt Cyber Solution Laboratories

• Tsutsuguchi Ken

  NTT Cyber Solutions Laboratories

• Mclean Nathan

  Ntt Cyber Space Laboratories:university Of Victoria

• Taniguchi Yukinobu

  Ntt Cyber Space Laboratories

• Tsutsuguchi Ken

  NTT Cyber Space Laboratories

関連論文

• ウェブ画像に対する領域ベースのセマンティックマイニングによるビジュアルコンセプトのモデリングに関する検討
• A-16-10 A new video editing interface based on the automatic extraction of emphasized speech and laughter scenes
• A new video editing interface based on the automatic extraction of emphasized speech and "laughter" scenes (画像工学)
• A new video editing interface based on the automatic extraction of emphasized speech and "laughter" scenes
• D-12-117 Semantic Concept Modeling by Integrating Multiple Sub-concepts from Images
• PanoramaExcerpts : Video Cataloging by Automatic Synthesis and Layout of Panoramic Images(Excellent Paper Originally Published in Japanese)
• Image vectorization and object-based editing system (メディア工学)
• Video Vectorization between Two Keyframes (情報センシング メディア工学)
• Video Vectorization between Two Keyframes
• Visual Concept Modeling Scheme Using Early Learning of Region-based Semantics for Web Images

スポンサーリンク