Разработка алгоритма отслеживания лица человека на основе применения оптического потока

Translated title of the contribution: Development of the human face tracking algorithm based on the optical flow application

A. A. Druki, V. G. Spitsyn, Y. A. Bolotova, D. Oliva, A. V. Gelginberg

Division for Information Technology

Research output: Contribution to journal › Article › peer-review

Abstract

The article is devoted to the development of algorithms and software to increase the efficiency of detection and tracking of human faces on video sequences. The review of existing methods of objects detection and tracking on video sequences indicates their advantages and disadvantages. A human face tracking algorithm based on the application of an optical flow is developed, which uses the Viola-Jones detector to objects localization. The preprocessing of the frame is carried out using the Gaussian filter, flow calculation by the pyramidal Lucas-Kanade method. The article presents the results of the algorithm software implementation with description of the main functions and classes. The developed algorithm was tested and comparison of work results with analogues was carried out.

Translated title of the contribution	Development of the human face tracking algorithm based on the optical flow application
Original language	Russian
Pages (from-to)	86-101
Number of pages	16
Journal	Scientific Visualization
Volume	10
Issue number	5
DOIs	https://doi.org/10.26583/sv.10.5.06
Publication status	Published - 2018

ASJC Scopus subject areas

Software
Computer Vision and Pattern Recognition

Access to Document

10.26583/sv.10.5.06

Fingerprint Dive into the research topics of 'Development of the human face tracking algorithm based on the optical flow application'. Together they form a unique fingerprint.

Cite this

Разработка алгоритма отслеживания лица человека на основе применения оптического потока. / Druki, A. A.; Spitsyn, V. G.; Bolotova, Y. A.; Oliva, D.; Gelginberg, A. V.

In: Scientific Visualization, Vol. 10, No. 5, 2018, p. 86-101.

Research output: Contribution to journal › Article › peer-review

@article{70006e2d996042f5a5f8c296198c7338,

title = "Разработка алгоритма отслеживания лица человека на основе применения оптического потока",

abstract = "The article is devoted to the development of algorithms and software to increase the efficiency of detection and tracking of human faces on video sequences. The review of existing methods of objects detection and tracking on video sequences indicates their advantages and disadvantages. A human face tracking algorithm based on the application of an optical flow is developed, which uses the Viola-Jones detector to objects localization. The preprocessing of the frame is carried out using the Gaussian filter, flow calculation by the pyramidal Lucas-Kanade method. The article presents the results of the algorithm software implementation with description of the main functions and classes. The developed algorithm was tested and comparison of work results with analogues was carried out.",

keywords = "Computer vision, Face detection, Image classification, Object tracking, Optical flow",

author = "Druki, {A. A.} and Spitsyn, {V. G.} and Bolotova, {Y. A.} and D. Oliva and Gelginberg, {A. V.}",

year = "2018",

doi = "10.26583/sv.10.5.06",

language = "Русский",

volume = "10",

pages = "86--101",

journal = "Scientific Visualization",

issn = "2079-3537",

publisher = "National Research Nuclear University {"}MEPhI{"}",

number = "5",

}

TY - JOUR

T1 - Разработка алгоритма отслеживания лица человека на основе применения оптического потока

AU - Druki, A. A.

AU - Spitsyn, V. G.

AU - Bolotova, Y. A.

AU - Oliva, D.

AU - Gelginberg, A. V.

PY - 2018

Y1 - 2018

N2 - The article is devoted to the development of algorithms and software to increase the efficiency of detection and tracking of human faces on video sequences. The review of existing methods of objects detection and tracking on video sequences indicates their advantages and disadvantages. A human face tracking algorithm based on the application of an optical flow is developed, which uses the Viola-Jones detector to objects localization. The preprocessing of the frame is carried out using the Gaussian filter, flow calculation by the pyramidal Lucas-Kanade method. The article presents the results of the algorithm software implementation with description of the main functions and classes. The developed algorithm was tested and comparison of work results with analogues was carried out.

AB - The article is devoted to the development of algorithms and software to increase the efficiency of detection and tracking of human faces on video sequences. The review of existing methods of objects detection and tracking on video sequences indicates their advantages and disadvantages. A human face tracking algorithm based on the application of an optical flow is developed, which uses the Viola-Jones detector to objects localization. The preprocessing of the frame is carried out using the Gaussian filter, flow calculation by the pyramidal Lucas-Kanade method. The article presents the results of the algorithm software implementation with description of the main functions and classes. The developed algorithm was tested and comparison of work results with analogues was carried out.

KW - Computer vision

KW - Face detection

KW - Image classification

KW - Object tracking

KW - Optical flow

UR - http://www.scopus.com/inward/record.url?scp=85062649231&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=85062649231&partnerID=8YFLogxK

U2 - 10.26583/sv.10.5.06

DO - 10.26583/sv.10.5.06

M3 - Статья

AN - SCOPUS:85062649231

VL - 10

SP - 86

EP - 101

JO - Scientific Visualization

JF - Scientific Visualization

SN - 2079-3537

IS - 5

ER -

Разработка алгоритма отслеживания лица человека на основе применения оптического потока

Abstract

ASJC Scopus subject areas

Access to Document

Other files and links

Cite this