Presentation 2017-06-01
Feasibility Study of a Simple Scheme for Multi-Target Object Tracking
Hiro Yokokawa, Takuro Oki, Ryusuke Miyamoto,
PDF Download Page PDF download Page Link
Abstract(in Japanese) (See Japanese page)
Abstract(in English) Multiple object tracking is one of the most challenging problems in the field of the image recognition. This paper proposes a simple tracking scheme that uses only estimated locations generated from 2 frames just before the current frame and detection results obtained at every frame. The tracking accuracy of the proposed scheme was compared with KCF, MedianFlow, MIL, Boosting, and TLD that are implemented in the OpenCV library using a 3DCG-based dataset. In the experiment, seven kinds of metrics that are used in MOT challenge benchmark were adopted. The experimental results showed that our scheme shows the best accuracies in these metrics except for ID switches.
Keyword(in Japanese) (See Japanese page)
Keyword(in English) multiple object tracking / human tracking / object detection
Paper # SIS2017-8
Date of Issue 2017-05-25 (SIS)

Conference Information
Committee SIS
Conference Date 2017/6/1(2days)
Place (in Japanese) (See Japanese page)
Place (in English) Housen-Sou (Beppu)
Topics (in Japanese) (See Japanese page)
Topics (in English) Smart Personal Systems, etc.
Chair Hirokazu Tanaka(Hiroshima City Univ.)
Vice Chair Takayuki Nakachi(NTT) / Noriaki Suetake(Yamaguchi Univ.)
Secretary Takayuki Nakachi(Kanagawa Inst. of Tech.) / Noriaki Suetake(Kyushu Inst. of Tech.)
Assistant Masaaki Fujiyoshi(Tokyo Metropolitan Univ.) / Takanori Koga(TCT)

Paper Information
Registration To Technical Committee on Smart Info-Media Systems
Language JPN
Title (in Japanese) (See Japanese page)
Sub Title (in Japanese) (See Japanese page)
Title (in English) Feasibility Study of a Simple Scheme for Multi-Target Object Tracking
Sub Title (in English)
Keyword(1) multiple object tracking
Keyword(2) human tracking
Keyword(3) object detection
1st Author's Name Hiro Yokokawa
1st Author's Affiliation Meiji University(Meiji Univ.)
2nd Author's Name Takuro Oki
2nd Author's Affiliation Meiji University(Meiji Univ.)
3rd Author's Name Ryusuke Miyamoto
3rd Author's Affiliation Meiji University(Meiji Univ.)
Date 2017-06-01
Paper # SIS2017-8
Volume (vol) vol.117
Number (no) SIS-70
Page pp.pp.41-46(SIS),
#Pages 6
Date of Issue 2017-05-25 (SIS)