Presentation 2013-06-11
Spotting Recognition of Motions from a Video Captured by a Moving Camera
Syunpei TORII, Yuki NITSUMA, Yuichi YAGUCHI, Ryuichi OKA,
PDF Download Page PDF download Page Link
Abstract(in Japanese) (See Japanese page)
Abstract(in English) In the technology of first person vision, recognition of human motions is an important function as well as recognition of static objects from a video captured by a moving camera. We apply a segmentation-free recognition algorithm called time-space continuous dynamic programming (TSCDP) for recognizing human motions from a video captured by a moving camera with ten typical and different camera motions. The features of camera motions are also extracted by the difference pattern between the point trajectory of a reference pattern and the trajectory extracted by TSCDP from an input video. We report experimental results of motion recognition and feature extraction of camera motions.
Keyword(in Japanese) (See Japanese page)
Keyword(in English) first person vision / moving camera / trajectory / DP / motion recognition / feature extraction
Paper # PRMU2013-31
Date of Issue

Conference Information
Committee PRMU
Conference Date 2013/6/3(1days)
Place (in Japanese) (See Japanese page)
Place (in English)
Topics (in Japanese) (See Japanese page)
Topics (in English)
Chair
Vice Chair
Secretary
Assistant

Paper Information
Registration To Pattern Recognition and Media Understanding (PRMU)
Language JPN
Title (in Japanese) (See Japanese page)
Sub Title (in Japanese) (See Japanese page)
Title (in English) Spotting Recognition of Motions from a Video Captured by a Moving Camera
Sub Title (in English)
Keyword(1) first person vision
Keyword(2) moving camera
Keyword(3) trajectory
Keyword(4) DP
Keyword(5) motion recognition
Keyword(6) feature extraction
1st Author's Name Syunpei TORII
1st Author's Affiliation University of Aizu()
2nd Author's Name Yuki NITSUMA
2nd Author's Affiliation University of Aizu
3rd Author's Name Yuichi YAGUCHI
3rd Author's Affiliation University of Aizu
4th Author's Name Ryuichi OKA
4th Author's Affiliation University of Aizu
Date 2013-06-11
Paper # PRMU2013-31
Volume (vol) vol.113
Number (no) 75
Page pp.pp.-
#Pages 6
Date of Issue