Presentation 2015-12-04
Image Shrinking Based Computational Cost Reduction of Moving Area Extraction Using Global Motion Estimation with KLT Tracker and Background Subtraction
Shingo Kokami, Takashi Imagawa, Hiroshi Tsutsui, Yoshikazu Miyanaga,
PDF Download Page PDF download Page Link
Abstract(in Japanese) (See Japanese page)
Abstract(in English) This paper proposes a computational cost reduction method for moving areaextraction using global motion estimation with KLT tracker and backgroundsubtraction. The proposed method utilizes image shrinking to reduce thecomputational cost. However, the accuracy of estimated global motion mightbe degraded since the number of good feature points for tracking reduces dueto image shrinking. This degraded motion estimation increase the amount ofnoise included in background subtracted images. To alleviate this, theproposed method utilizes median filter on background subtracted binaryimages to reduce noise and also utilizes labeling to remove small regions. For the evaluation of the proposed method, we extract moving areas usingthree video sequences each of which has different camera movement. Inaddition, we analyze the accuracy of the proposed moving area extractionusing F-measure by changing parameters of the proposed method such as thesize of median filter and the threshold area size for small region removal.
Keyword(in Japanese) (See Japanese page)
Keyword(in English) Moving area detection / Background subtraction / KLT tracker / Global motion estimation
Paper # SIS2015-46
Date of Issue 2015-11-26 (SIS)

Conference Information
Committee SIS
Conference Date 2015/12/3(2days)
Place (in Japanese) (See Japanese page)
Place (in English) Matsuya-sensen (Awara city, Fukui)
Topics (in Japanese) (See Japanese page)
Topics (in English) SoC, Related to RFID, etc.
Chair Mitsuji Muneyasu(Kansai Univ.)
Vice Chair Hirokazu Tanaka(Hiroshima City Univ.) / Takayuki Nakachi(NTT)
Secretary Hirokazu Tanaka(Nagoya City Univ.) / Takayuki Nakachi(Toshiba)
Assistant Hiroyuki Tsuji(Kanagawa Inst. of Tech.) / Hakaru Tamukoh(Kyushu Inst. of Tech.)

Paper Information
Registration To Technical Committee on Smart Info-Media System
Language JPN
Title (in Japanese) (See Japanese page)
Sub Title (in Japanese) (See Japanese page)
Title (in English) Image Shrinking Based Computational Cost Reduction of Moving Area Extraction Using Global Motion Estimation with KLT Tracker and Background Subtraction
Sub Title (in English)
Keyword(1) Moving area detection
Keyword(2) Background subtraction
Keyword(3) KLT tracker
Keyword(4) Global motion estimation
1st Author's Name Shingo Kokami
1st Author's Affiliation Hokkaido University(Hokkaido Univ.)
2nd Author's Name Takashi Imagawa
2nd Author's Affiliation Hokkaido University(Hokkaido Univ.)
3rd Author's Name Hiroshi Tsutsui
3rd Author's Affiliation Hokkaido University(Hokkaido Univ.)
4th Author's Name Yoshikazu Miyanaga
4th Author's Affiliation Hokkaido University(Hokkaido Univ.)
Date 2015-12-04
Paper # SIS2015-46
Volume (vol) vol.115
Number (no) SIS-348
Page pp.pp.95-98(SIS),
#Pages 4
Date of Issue 2015-11-26 (SIS)