Presentation 2018-03-08
Hierarchical Single Person Re-identification based on Group Detection and Re-identification
Shingo Inami, Daisuke Sugimura, Takayuki Hamamoto,
PDF Download Page PDF download Page Link
Abstract(in Japanese) (See Japanese page)
Abstract(in English) In this paper, we propose a method for hierarchical single person re-identification based on group re-identification. We first estimate groups from videos taken with each camera. We extract features from local patches obtained from group images, and apply graph matching to estimate correspondeces between two group images. Using the estimated correspondences, we perform group re-identification. With the responses from group re-identification, we then perform single person re-identification. Because group re-identification allows us to reduce the size of candidates of pedestrian to be identified, the accuracy of single person re-identification can be improved. Experiment using public dataset demonstrates the effectiveness of the proposed method.
Keyword(in Japanese) (See Japanese page)
Keyword(in English) Single Person Re-identification / Group Re-identification / Group Detection / Graph Matching
Paper # IMQ2017-44,IE2017-136,MVE2017-86
Date of Issue 2018-03-01 (IMQ, IE, MVE)

Conference Information
Committee CQ / MVE / IE / IMQ
Conference Date 2018/3/8(2days)
Place (in Japanese) (See Japanese page)
Place (in English) Okinawa Industry Support Center
Topics (in Japanese) (See Japanese page)
Topics (in English) Five Senses Media, Cooking and Eating Activities Media, Multimedia, Media Experience, Video Encoding, Image Media Quality, Network Quality and Reliability, etc. (Co-sponsor: Technical Committee on Multimedia on Cooking and Eating Activities (CEA))
Chair Takanori Hayashi(Hiroshima Inst. of Tech.) / Yoshinari Kameda(Univ. of Tsukuba) / Takayuki Hamamoto(Tokyo Univ. of Science) / Kenji Sugiyama(Seikei Univ.)
Vice Chair Hideyuki Shimonishi(NEC) / Jun Okamoto(NTT) / Kenji Mase(Nagoya Univ.) / Kazuya Kodama(NII) / Hideaki Kimata(NTT) / Toshiya Nakaguchi(Chiba Univ.) / Mitsuru Maeda(Canon)
Secretary Hideyuki Shimonishi(NTT) / Jun Okamoto(Keio Univ.) / Kenji Mase(Kyoto Univ.) / Kazuya Kodama(NTT) / Hideaki Kimata(Kyushu Univ.) / Toshiya Nakaguchi(Nagoya Univ.) / Mitsuru Maeda(KDDI Research)
Assistant Kenko Ota(Nippon Inst. of Tech.) / Norihiro Fukumoto(KDDI Research Inc.) / Ryo Yamamoto(UEC) / Takatsugu Hirayama(Nagoya Univ.) / Ryosuke Aoki(NTT) / Yasutaka Matsuo(NHK) / Kazuya Hayase(NTT) / Masaru Tsuchida(NTT) / Gosuke Ohashi(Shizuoka Univ.)

Paper Information
Registration To Technical Committee on Communication Quality / Technical Committee on Media Experience and Virtual Environment / Technical Committee on Image Engineering / Technical Committee on Image Media Quality
Language JPN
Title (in Japanese) (See Japanese page)
Sub Title (in Japanese) (See Japanese page)
Title (in English) Hierarchical Single Person Re-identification based on Group Detection and Re-identification
Sub Title (in English)
Keyword(1) Single Person Re-identification
Keyword(2) Group Re-identification
Keyword(3) Group Detection
Keyword(4) Graph Matching
1st Author's Name Shingo Inami
1st Author's Affiliation Tokyo University of Science(Tokyo Univ. of Science)
2nd Author's Name Daisuke Sugimura
2nd Author's Affiliation Tokyo University of Science(Tokyo Univ. of Science)
3rd Author's Name Takayuki Hamamoto
3rd Author's Affiliation Tokyo University of Science(Tokyo Univ. of Science)
Date 2018-03-08
Paper # IMQ2017-44,IE2017-136,MVE2017-86
Volume (vol) vol.117
Number (no) IMQ-483,IE-484,MVE-485
Page pp.pp.107-110(IMQ), pp.107-110(IE), pp.107-110(MVE),
#Pages 4
Date of Issue 2018-03-01 (IMQ, IE, MVE)