Face detection on real low resolution surveillance videos

Rolando Jesus T. Cardenas; César A.Beltrán Castañón; Juan Carlos Gutierrez Caceres

doi:10.1145/3193077.3193084

Face detection on real low resolution surveillance videos

Rolando Jesus T. Cardenas, César A.Beltrán Castañón, Juan Carlos Gutierrez Caceres

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution › peer-review

2 Scopus citations

Abstract

The use of video cameras for security reasons has increased in recent times. Identify a person with automatic face detection systems have greater importance today; but the low-quality of the videos make it difficult and are still an open problem that many researchers are trying to solve. We propose a novel methodology for face detection on low-resolution videos based on parallel Gunnar Farnebäck optical flow algorithm, Haar Cascades and Local Binary Patterns. Our model does not use illumination normalization or super-resolution techniques, commonly used in literature. The results on the Caviar Database prove a better detection rate compared with OpenCv Library, Dlib C++ Library and Matlab function, which use the known Viola-Jones Haar cascade algorithm and HOGs. Even though these tools not have a number of detections up to 1%, our proposal can detect faces in a rate of 50%.

Original language	English
Title of host publication	ICCDA 2018 - Proceedings of 2018 the 2nd International Conference on Compute and Data Analysis
Publisher	Association for Computing Machinery
Pages	52-59
Number of pages	8
ISBN (Electronic)	9781450363594
DOIs	https://doi.org/10.1145/3193077.3193084
State	Published - 23 Mar 2018
Externally published	Yes
Event	2nd International Conference on Compute and Data Analysis, ICCDA 2018 - DeKalb, United States Duration: 23 Mar 2018 → 25 Mar 2018

Publication series

Name	ACM International Conference Proceeding Series

Conference

Conference	2nd International Conference on Compute and Data Analysis, ICCDA 2018
Country/Territory	United States
City	DeKalb
Period	23/03/18 → 25/03/18

Bibliographical note

Funding Information:
This research was supported by CIENCIACTIVA, CONCYTEC and the National University of San Agustin (UNSA). We thank all professors who collaborate in the research.

Publisher Copyright:
© 2018 Association for Computing Machinery.

Keywords

Face Detection
Haar cascade
LBP
Low-resolution
Optical Flow
Video

Access to Document

10.1145/3193077.3193084

Cite this

Cardenas, R. J. T., Castañón, C. A. B., & Gutierrez Caceres, J. C. (2018). Face detection on real low resolution surveillance videos. In ICCDA 2018 - Proceedings of 2018 the 2nd International Conference on Compute and Data Analysis (pp. 52-59). (ACM International Conference Proceeding Series). Association for Computing Machinery. https://doi.org/10.1145/3193077.3193084

@inproceedings{24133a7326214e02b621762093775aec,

title = "Face detection on real low resolution surveillance videos",

abstract = "The use of video cameras for security reasons has increased in recent times. Identify a person with automatic face detection systems have greater importance today; but the low-quality of the videos make it difficult and are still an open problem that many researchers are trying to solve. We propose a novel methodology for face detection on low-resolution videos based on parallel Gunnar Farneb{\"a}ck optical flow algorithm, Haar Cascades and Local Binary Patterns. Our model does not use illumination normalization or super-resolution techniques, commonly used in literature. The results on the Caviar Database prove a better detection rate compared with OpenCv Library, Dlib C++ Library and Matlab function, which use the known Viola-Jones Haar cascade algorithm and HOGs. Even though these tools not have a number of detections up to 1%, our proposal can detect faces in a rate of 50%.",

keywords = "Face Detection, Haar cascade, LBP, Low-resolution, Optical Flow, Video",

author = "Cardenas, {Rolando Jesus T.} and Casta{\~n}{\'o}n, {C{\'e}sar A.Beltr{\'a}n} and {Gutierrez Caceres}, {Juan Carlos}",

note = "Publisher Copyright: {\textcopyright} 2018 Association for Computing Machinery.; null ; Conference date: 23-03-2018 Through 25-03-2018",

year = "2018",

month = mar,

day = "23",

doi = "10.1145/3193077.3193084",

language = "Ingl{\'e}s",

series = "ACM International Conference Proceeding Series",

publisher = "Association for Computing Machinery",

pages = "52--59",

booktitle = "ICCDA 2018 - Proceedings of 2018 the 2nd International Conference on Compute and Data Analysis",

}

Cardenas, RJT, Castañón, CAB & Gutierrez Caceres, JC 2018, Face detection on real low resolution surveillance videos. in ICCDA 2018 - Proceedings of 2018 the 2nd International Conference on Compute and Data Analysis. ACM International Conference Proceeding Series, Association for Computing Machinery, pp. 52-59, 2nd International Conference on Compute and Data Analysis, ICCDA 2018, DeKalb, United States, 23/03/18. https://doi.org/10.1145/3193077.3193084

Face detection on real low resolution surveillance videos. / Cardenas, Rolando Jesus T.; Castañón, César A.Beltrán; Gutierrez Caceres, Juan Carlos.

ICCDA 2018 - Proceedings of 2018 the 2nd International Conference on Compute and Data Analysis. Association for Computing Machinery, 2018. p. 52-59 (ACM International Conference Proceeding Series).

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution › peer-review

TY - GEN

T1 - Face detection on real low resolution surveillance videos

AU - Cardenas, Rolando Jesus T.

AU - Castañón, César A.Beltrán

AU - Gutierrez Caceres, Juan Carlos

PY - 2018/3/23

Y1 - 2018/3/23

N2 - The use of video cameras for security reasons has increased in recent times. Identify a person with automatic face detection systems have greater importance today; but the low-quality of the videos make it difficult and are still an open problem that many researchers are trying to solve. We propose a novel methodology for face detection on low-resolution videos based on parallel Gunnar Farnebäck optical flow algorithm, Haar Cascades and Local Binary Patterns. Our model does not use illumination normalization or super-resolution techniques, commonly used in literature. The results on the Caviar Database prove a better detection rate compared with OpenCv Library, Dlib C++ Library and Matlab function, which use the known Viola-Jones Haar cascade algorithm and HOGs. Even though these tools not have a number of detections up to 1%, our proposal can detect faces in a rate of 50%.

AB - The use of video cameras for security reasons has increased in recent times. Identify a person with automatic face detection systems have greater importance today; but the low-quality of the videos make it difficult and are still an open problem that many researchers are trying to solve. We propose a novel methodology for face detection on low-resolution videos based on parallel Gunnar Farnebäck optical flow algorithm, Haar Cascades and Local Binary Patterns. Our model does not use illumination normalization or super-resolution techniques, commonly used in literature. The results on the Caviar Database prove a better detection rate compared with OpenCv Library, Dlib C++ Library and Matlab function, which use the known Viola-Jones Haar cascade algorithm and HOGs. Even though these tools not have a number of detections up to 1%, our proposal can detect faces in a rate of 50%.

KW - Face Detection

KW - Haar cascade

KW - LBP

KW - Low-resolution

KW - Optical Flow

KW - Video

UR - http://www.scopus.com/inward/record.url?scp=85048319786&partnerID=8YFLogxK

U2 - 10.1145/3193077.3193084

DO - 10.1145/3193077.3193084

M3 - Contribución a la conferencia

AN - SCOPUS:85048319786

T3 - ACM International Conference Proceeding Series

SP - 52

EP - 59

BT - ICCDA 2018 - Proceedings of 2018 the 2nd International Conference on Compute and Data Analysis

PB - Association for Computing Machinery

Y2 - 23 March 2018 through 25 March 2018

ER -

Face detection on real low resolution surveillance videos

Abstract

Publication series

Conference

Bibliographical note

Keywords

Access to Document

Other files and links

Fingerprint

Cite this