Presentation 2004-12-17
Pitch by pitch event detection using impulse sound detection and moving image clustering.
Dan MIKAMI, Seiichi KONYA, Masashi MORIMOTO,
PDF Download Page PDF download Page Link
Abstract(in Japanese) (See Japanese page)
Abstract(in English) In this paper, we propose a pitching event detection method from baseball videos. The method, at first, detects candidates of pitching event using hitting or catching sound analysis which is expected stable regardless of video capture environment. Then, each candidate is clustered by its motion. The motion template of the pitching event is then generated from the cluster which has the most elements. Final, pitching events are extracted agein using the motion template. Experiments with broadcasted baseball videos and private baseball video, confirm effectiveness of the proposed method.
Keyword(in Japanese) (See Japanese page)
Keyword(in English) baseball video / indexing / multi-modal / MHI / clustering
Paper # PRMU2004-139
Date of Issue

Conference Information
Committee PRMU
Conference Date 2004/12/10(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) Pitch by pitch event detection using impulse sound detection and moving image clustering.
Sub Title (in English)
Keyword(1) baseball video
Keyword(2) indexing
Keyword(3) multi-modal
Keyword(4) MHI
Keyword(5) clustering
1st Author's Name Dan MIKAMI
1st Author's Affiliation ()
2nd Author's Name Seiichi KONYA
2nd Author's Affiliation
3rd Author's Name Masashi MORIMOTO
3rd Author's Affiliation
Date 2004-12-17
Paper # PRMU2004-139
Volume (vol) vol.104
Number (no) 524
Page pp.pp.-
#Pages 6
Date of Issue