Study of different image features used for recognizing unknown person's activity based on tensor decomposition approach (ヒューマン情報処理)
スポンサーリンク
概要
- 論文の詳細を見る
This paper proposes a method for recognizing an unknown person' action from a video sequence, where the unknown person is defined as a person who is not included in the database (tensor) used for the recognition process. We have developed a tensor decomposition based method, but that method used only motion capture data. The main motivation of this paper is to replace the motion capture data by image feature data and clarify which image features are useful. This paper tests three image features as well as their combinations. Experimental results using synthesized image sequences present the effectiveness of the method and clarify the useful image features.
- 社団法人電子情報通信学会の論文
- 2007-08-27
著者
関連論文
- Parallel forward projection of large voxel-volumes on the GPU (放送技術)
- Parallel forward projection of large voxel-volumes on the GPU (オーディオビジュアル複合情報処理)
- Parallel forward projection of large voxel-volumes on the GPU (通信方式)
- Parallel forward projection of large voxel-volumes on the GPU (画像工学)
- Stakeholder system and analysis of extended producer responsibility based on game theory (情報システムと社会環境)
- A Proposal on Active Extensible Stereo Camera Array For High Speed Moving Object Detection
- Study of different image features used for recognizing unknown person's activity based on tensor decomposition approach (コンピュータビジョンとイメージメディア)
- Study of different image features used for recognizing unknown person's activity based on tensor decomposition approach (ヒューマン情報処理)
- Study of different image features used for recognizing unknown person's activity based on tensor decomposition approach (パターン認識・メディア理解)
- J-024 Tensor Decomposition Framework For Recognizing an Unknown Person's Action From A Video Sequence Using Image Features
- D-12-122 Implementation of a Video Sequence Based System for Recognizing an Unknown Person's Gesture by a Tensor Decomposition Based Approach
- Comparative study of segmentation in monochrome facial images: snake pedals and template matching (コンピュータビジョンとイメージメディア)
- Comparative study of segmentation in monochrome facial images: snake pedals and template matching (ヒューマン情報処理)
- Comparative study of segmentation in monochrome facial images: snake pedals and template matching (パターン認識・メディア理解)
- D-12-100 Study of Motion Segmentation from Dynamic Stereo Images Acquired by Active Stereo Cameras
- A modified RANSAC based method for extracting primitive shapes from image (コンピュータビジョンとイメージメディア)
- Staff removal for square musical notation manuscripts OCR: an experiment on the binarization and staff detection stage (パターン認識・メディア理解)
- D-4-6 Analysis-based Participant Selection Scheme in Workflow Management System(D-4. データ工学, 情報・システム1)
- D-12-49 Local Adaptive Thresholding Study for Early Musical Manuscripts OMR
- A Modified RANSAC mechanism : Multiple models extraction algorithm
- A Modified RANSAC mechanism : Multiple models extraction algorithm
- G-013 Incorporating Zoom Motion Estimation in Video Compression : A More General Approach for Motion Compensated Predictive Coding