Dense flow field algorithm using binary descriptor and modified energy function

Dong Sung Pae, Hyeon Chan Oh, Sang Kyoo Park, Tae Koo Kang, Myo Taeg Lim

Research output: Chapter in Book/Report/Conference proceedingConference contribution

Abstract

In this paper, we describe a Dense Flow-Field algorithm for moving detection of an object using a binary descriptor and a modified energy function. Among the moving detection algorithms, a Dense SIFT-Flow algorithm is recently introduced. In the conventional Dense SIFT-Flow, a SIFT descriptor and an energy function are employed to make the flow vectors containing the movement information of each pixel at entire image. The matching process in the conventional SIFT-Flow algorithm uses descriptor information and a message-passing method in a coarse-to-fine scheme. Although the matching performance of the Dense SIFT-Flow is good for detecting the movement of each pixel, large computational time is needed. To reduce the complexity of the description part, the proposed method employs a binary descriptor. The process of the binary descriptor is simple enough to reduce the complexity. In addition, the energy function in the conventional Dense Flow-Field must be modified for the binary descriptor as replacing the unfair displacement term of the conventional energy function with a fair displacement term. From the experimental results, we can know that the proposed method is faster than the conventional method with respect to making flow field and more robust with respect to diagonal movements.

Original languageEnglish
Title of host publicationSII 2017 - 2017 IEEE/SICE International Symposium on System Integration
PublisherInstitute of Electrical and Electronics Engineers Inc.
Pages1016-1021
Number of pages6
Volume2018-January
ISBN (Electronic)9781538622636
DOIs
Publication statusPublished - 2018 Feb 1
Event2017 IEEE/SICE International Symposium on System Integration, SII 2017 - Taipei, Taiwan, Province of China
Duration: 2017 Dec 112017 Dec 14

Other

Other2017 IEEE/SICE International Symposium on System Integration, SII 2017
CountryTaiwan, Province of China
CityTaipei
Period17/12/1117/12/14

Fingerprint

Energy Function
Scale Invariant Feature Transform
Descriptors
Flow Field
Flow fields
flow distribution
Binary
Pixels
pixels
energy
Message passing
Pixel
Unfair
messages
Term
Message Passing
Entire
Experimental Results
Movement

ASJC Scopus subject areas

  • Modelling and Simulation
  • Instrumentation
  • Artificial Intelligence
  • Computer Science Applications
  • Engineering (miscellaneous)
  • Materials Science (miscellaneous)
  • Control and Optimization

Cite this

Pae, D. S., Oh, H. C., Park, S. K., Kang, T. K., & Lim, M. T. (2018). Dense flow field algorithm using binary descriptor and modified energy function. In SII 2017 - 2017 IEEE/SICE International Symposium on System Integration (Vol. 2018-January, pp. 1016-1021). Institute of Electrical and Electronics Engineers Inc.. https://doi.org/10.1109/SII.2017.8279356

Dense flow field algorithm using binary descriptor and modified energy function. / Pae, Dong Sung; Oh, Hyeon Chan; Park, Sang Kyoo; Kang, Tae Koo; Lim, Myo Taeg.

SII 2017 - 2017 IEEE/SICE International Symposium on System Integration. Vol. 2018-January Institute of Electrical and Electronics Engineers Inc., 2018. p. 1016-1021.

Research output: Chapter in Book/Report/Conference proceedingConference contribution

Pae, DS, Oh, HC, Park, SK, Kang, TK & Lim, MT 2018, Dense flow field algorithm using binary descriptor and modified energy function. in SII 2017 - 2017 IEEE/SICE International Symposium on System Integration. vol. 2018-January, Institute of Electrical and Electronics Engineers Inc., pp. 1016-1021, 2017 IEEE/SICE International Symposium on System Integration, SII 2017, Taipei, Taiwan, Province of China, 17/12/11. https://doi.org/10.1109/SII.2017.8279356
Pae DS, Oh HC, Park SK, Kang TK, Lim MT. Dense flow field algorithm using binary descriptor and modified energy function. In SII 2017 - 2017 IEEE/SICE International Symposium on System Integration. Vol. 2018-January. Institute of Electrical and Electronics Engineers Inc. 2018. p. 1016-1021 https://doi.org/10.1109/SII.2017.8279356
Pae, Dong Sung ; Oh, Hyeon Chan ; Park, Sang Kyoo ; Kang, Tae Koo ; Lim, Myo Taeg. / Dense flow field algorithm using binary descriptor and modified energy function. SII 2017 - 2017 IEEE/SICE International Symposium on System Integration. Vol. 2018-January Institute of Electrical and Electronics Engineers Inc., 2018. pp. 1016-1021
@inproceedings{8eb6cb44d47a421490b3e21c46615262,
title = "Dense flow field algorithm using binary descriptor and modified energy function",
abstract = "In this paper, we describe a Dense Flow-Field algorithm for moving detection of an object using a binary descriptor and a modified energy function. Among the moving detection algorithms, a Dense SIFT-Flow algorithm is recently introduced. In the conventional Dense SIFT-Flow, a SIFT descriptor and an energy function are employed to make the flow vectors containing the movement information of each pixel at entire image. The matching process in the conventional SIFT-Flow algorithm uses descriptor information and a message-passing method in a coarse-to-fine scheme. Although the matching performance of the Dense SIFT-Flow is good for detecting the movement of each pixel, large computational time is needed. To reduce the complexity of the description part, the proposed method employs a binary descriptor. The process of the binary descriptor is simple enough to reduce the complexity. In addition, the energy function in the conventional Dense Flow-Field must be modified for the binary descriptor as replacing the unfair displacement term of the conventional energy function with a fair displacement term. From the experimental results, we can know that the proposed method is faster than the conventional method with respect to making flow field and more robust with respect to diagonal movements.",
author = "Pae, {Dong Sung} and Oh, {Hyeon Chan} and Park, {Sang Kyoo} and Kang, {Tae Koo} and Lim, {Myo Taeg}",
year = "2018",
month = "2",
day = "1",
doi = "10.1109/SII.2017.8279356",
language = "English",
volume = "2018-January",
pages = "1016--1021",
booktitle = "SII 2017 - 2017 IEEE/SICE International Symposium on System Integration",
publisher = "Institute of Electrical and Electronics Engineers Inc.",

}

TY - GEN

T1 - Dense flow field algorithm using binary descriptor and modified energy function

AU - Pae, Dong Sung

AU - Oh, Hyeon Chan

AU - Park, Sang Kyoo

AU - Kang, Tae Koo

AU - Lim, Myo Taeg

PY - 2018/2/1

Y1 - 2018/2/1

N2 - In this paper, we describe a Dense Flow-Field algorithm for moving detection of an object using a binary descriptor and a modified energy function. Among the moving detection algorithms, a Dense SIFT-Flow algorithm is recently introduced. In the conventional Dense SIFT-Flow, a SIFT descriptor and an energy function are employed to make the flow vectors containing the movement information of each pixel at entire image. The matching process in the conventional SIFT-Flow algorithm uses descriptor information and a message-passing method in a coarse-to-fine scheme. Although the matching performance of the Dense SIFT-Flow is good for detecting the movement of each pixel, large computational time is needed. To reduce the complexity of the description part, the proposed method employs a binary descriptor. The process of the binary descriptor is simple enough to reduce the complexity. In addition, the energy function in the conventional Dense Flow-Field must be modified for the binary descriptor as replacing the unfair displacement term of the conventional energy function with a fair displacement term. From the experimental results, we can know that the proposed method is faster than the conventional method with respect to making flow field and more robust with respect to diagonal movements.

AB - In this paper, we describe a Dense Flow-Field algorithm for moving detection of an object using a binary descriptor and a modified energy function. Among the moving detection algorithms, a Dense SIFT-Flow algorithm is recently introduced. In the conventional Dense SIFT-Flow, a SIFT descriptor and an energy function are employed to make the flow vectors containing the movement information of each pixel at entire image. The matching process in the conventional SIFT-Flow algorithm uses descriptor information and a message-passing method in a coarse-to-fine scheme. Although the matching performance of the Dense SIFT-Flow is good for detecting the movement of each pixel, large computational time is needed. To reduce the complexity of the description part, the proposed method employs a binary descriptor. The process of the binary descriptor is simple enough to reduce the complexity. In addition, the energy function in the conventional Dense Flow-Field must be modified for the binary descriptor as replacing the unfair displacement term of the conventional energy function with a fair displacement term. From the experimental results, we can know that the proposed method is faster than the conventional method with respect to making flow field and more robust with respect to diagonal movements.

UR - http://www.scopus.com/inward/record.url?scp=85050850102&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=85050850102&partnerID=8YFLogxK

U2 - 10.1109/SII.2017.8279356

DO - 10.1109/SII.2017.8279356

M3 - Conference contribution

AN - SCOPUS:85050850102

VL - 2018-January

SP - 1016

EP - 1021

BT - SII 2017 - 2017 IEEE/SICE International Symposium on System Integration

PB - Institute of Electrical and Electronics Engineers Inc.

ER -