Presentation 2015-07-02
[Invited Talk] Object Recognition with Depth Image by Machine Learning
Hironobu Fujiyoshi,
PDF Download Page PDF download Page Link
Abstract(in Japanese) (See Japanese page)
Abstract(in English) This paper presents object recognition with point cloud and depth images, and its trends. There have been many various researches with depth information for detecting human, analyzing human flow, and recognizing action. In this paper, we report that machine learning with depth images obtains better performance than that with gray-scale images. We also present a human pose estimation method used for practical application such as gesture interaction, and discuss trends in depth image processing.
Keyword(in Japanese) (See Japanese page)
Keyword(in English) depth image / point cloud / machine learning / object detection / action recognition / human pose estimation
Paper # ICD2015-17
Date of Issue 2015-06-25 (ICD)

Conference Information
Committee ICD / ITE-IST
Conference Date 2015/7/2(2days)
Place (in Japanese) (See Japanese page)
Place (in English) National Defense Academy
Topics (in Japanese) (See Japanese page)
Topics (in English) Analog, Mixed Analog and Digital, RF, and Sensor Interface Circuitry
Chair Minoru Fujishima(Hiroshima Univ.) / Shigetoshi Sugawa(Tohoku Univ.)
Vice Chair Hideto Hidaka(Renesas)
Secretary Hideto Hidaka(Hiroshima Univ.) / (Hokkaido Univ.)
Assistant Makoto Takamiya(Univ. of Tokyo) / Hiroe Iwasaki(NTT) / Takashi Hashimoto(Panasonic) / Hiroyuki Ito(Tokyo Inst. of Tech.) / Pham Konkuha(Univ. of Electro-Comm.)

Paper Information
Registration To Technical Committee on Integrated Circuits and Devices / Technical Group on Information Sensing Technologies
Language JPN
Title (in Japanese) (See Japanese page)
Sub Title (in Japanese) (See Japanese page)
Title (in English) [Invited Talk] Object Recognition with Depth Image by Machine Learning
Sub Title (in English)
Keyword(1) depth image
Keyword(2) point cloud
Keyword(3) machine learning
Keyword(4) object detection
Keyword(5) action recognition
Keyword(6) human pose estimation
1st Author's Name Hironobu Fujiyoshi
1st Author's Affiliation Chubu University(Chubu Univ.)
Date 2015-07-02
Paper # ICD2015-17
Volume (vol) vol.115
Number (no) ICD-124
Page pp.pp.13-18(ICD),
#Pages 6
Date of Issue 2015-06-25 (ICD)