Moving object proposal by grouping with motion feature

Teppei Suzuki, Shota Takayama, Sho Isobe, Makoto Masuda, Yoshimitsu Aoki

Research output: Contribution to journalArticle

Abstract

Recently, Object Recognition Is Improved Accuracy By Convolutional Neural Network(Cnn) And Growing Object Recognition Demand For Automatic Driving System And Security And So On. However, One Of The Problem Of Object Recognition Is To Extract Object Region Which Have Various Size, Scale And Form. This Paper Propose Moving Object Proposal For Object Recognition. Using Region Grouping And Scoring With Optical Flow, We Can Propose Object Proposal For Moving Objects. The Object Proposal Experiments Show Effective Results Compared With Previous Method On The Ucf Crowd Dataset.

Original languageEnglish
Pages (from-to)151-157
Number of pages7
JournalSeimitsu Kogaku Kaishi/Journal of the Japan Society for Precision Engineering
Volume83
Issue number2
Publication statusPublished - 2017

Fingerprint

Object recognition
Optical flows
Neural networks
Experiments

Keywords

  • Dense crowd
  • Object Proposal
  • Object Recognition
  • Optical Flow
  • Segmentation

ASJC Scopus subject areas

  • Mechanical Engineering

Cite this

Moving object proposal by grouping with motion feature. / Suzuki, Teppei; Takayama, Shota; Isobe, Sho; Masuda, Makoto; Aoki, Yoshimitsu.

In: Seimitsu Kogaku Kaishi/Journal of the Japan Society for Precision Engineering, Vol. 83, No. 2, 2017, p. 151-157.

Research output: Contribution to journalArticle

Suzuki, Teppei ; Takayama, Shota ; Isobe, Sho ; Masuda, Makoto ; Aoki, Yoshimitsu. / Moving object proposal by grouping with motion feature. In: Seimitsu Kogaku Kaishi/Journal of the Japan Society for Precision Engineering. 2017 ; Vol. 83, No. 2. pp. 151-157.
@article{576ab20a40f245b89b1f9e98ba136743,
title = "Moving object proposal by grouping with motion feature",
abstract = "Recently, Object Recognition Is Improved Accuracy By Convolutional Neural Network(Cnn) And Growing Object Recognition Demand For Automatic Driving System And Security And So On. However, One Of The Problem Of Object Recognition Is To Extract Object Region Which Have Various Size, Scale And Form. This Paper Propose Moving Object Proposal For Object Recognition. Using Region Grouping And Scoring With Optical Flow, We Can Propose Object Proposal For Moving Objects. The Object Proposal Experiments Show Effective Results Compared With Previous Method On The Ucf Crowd Dataset.",
keywords = "Dense crowd, Object Proposal, Object Recognition, Optical Flow, Segmentation",
author = "Teppei Suzuki and Shota Takayama and Sho Isobe and Makoto Masuda and Yoshimitsu Aoki",
year = "2017",
language = "English",
volume = "83",
pages = "151--157",
journal = "Seimitsu Kogaku Kaishi/Journal of the Japan Society for Precision Engineering",
issn = "0912-0289",
publisher = "Japan Society for Precision Engineering",
number = "2",

}

TY - JOUR

T1 - Moving object proposal by grouping with motion feature

AU - Suzuki, Teppei

AU - Takayama, Shota

AU - Isobe, Sho

AU - Masuda, Makoto

AU - Aoki, Yoshimitsu

PY - 2017

Y1 - 2017

N2 - Recently, Object Recognition Is Improved Accuracy By Convolutional Neural Network(Cnn) And Growing Object Recognition Demand For Automatic Driving System And Security And So On. However, One Of The Problem Of Object Recognition Is To Extract Object Region Which Have Various Size, Scale And Form. This Paper Propose Moving Object Proposal For Object Recognition. Using Region Grouping And Scoring With Optical Flow, We Can Propose Object Proposal For Moving Objects. The Object Proposal Experiments Show Effective Results Compared With Previous Method On The Ucf Crowd Dataset.

AB - Recently, Object Recognition Is Improved Accuracy By Convolutional Neural Network(Cnn) And Growing Object Recognition Demand For Automatic Driving System And Security And So On. However, One Of The Problem Of Object Recognition Is To Extract Object Region Which Have Various Size, Scale And Form. This Paper Propose Moving Object Proposal For Object Recognition. Using Region Grouping And Scoring With Optical Flow, We Can Propose Object Proposal For Moving Objects. The Object Proposal Experiments Show Effective Results Compared With Previous Method On The Ucf Crowd Dataset.

KW - Dense crowd

KW - Object Proposal

KW - Object Recognition

KW - Optical Flow

KW - Segmentation

UR - http://www.scopus.com/inward/record.url?scp=85013849244&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=85013849244&partnerID=8YFLogxK

M3 - Article

AN - SCOPUS:85013849244

VL - 83

SP - 151

EP - 157

JO - Seimitsu Kogaku Kaishi/Journal of the Japan Society for Precision Engineering

JF - Seimitsu Kogaku Kaishi/Journal of the Japan Society for Precision Engineering

SN - 0912-0289

IS - 2

ER -