Pedestrian detection in surveillance videos based on CS-LBP feature

Domonkos Varga, László Havasi, T. Szirányi

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

8 Citations (Scopus)

Abstract

Detecting different categories of objects in an image and video content is one of the fundamental tasks in computer vision research. Pedestrian detection is a hot research topic, with several applications including robotics, surveillance and automotive safety. Pedestrians are key participants in transportation systems, so pedestrian detection in video surveillance systems is of great significance to the research and application of Intelligent Transportation Systems (ITS). Pedestrian detection is a challenging problem due to the variance of illumination, color, scale, pose, and so forth. Extraction of effictive features is a key to this task. In this work, we present the multi-scale Center-symmetric Local Binary Pattern feature for pedestrian detection. The proposed feature captures gradient information and some texture and scale information. We completed the detection task with a foreground segmentation method. Experiments on CAVIAR sequences show that the proposed feature with support vector machines can detect pedestrians in real-time effectively in surveillance videos.

Original languageEnglish
Title of host publication2015 International Conference on Models and Technologies for Intelligent Transportation Systems, MT-ITS 2015
PublisherInstitute of Electrical and Electronics Engineers Inc.
Pages413-417
Number of pages5
ISBN (Print)9789633131428
DOIs
Publication statusPublished - Aug 25 2015
EventInternational Conference on Models and Technologies for Intelligent Transportation Systems, MT-ITS 2015 - Budapest, Hungary
Duration: Jun 3 2015Jun 5 2015

Other

OtherInternational Conference on Models and Technologies for Intelligent Transportation Systems, MT-ITS 2015
CountryHungary
CityBudapest
Period6/3/156/5/15

Fingerprint

pedestrian
surveillance
video
transportation system
Computer vision
Support vector machines
Robotics
Textures
Lighting
information capture
Color
Experiments
experiment

Keywords

  • pedestrian detection
  • video surveillance

ASJC Scopus subject areas

  • Mechanical Engineering
  • Transportation
  • Computer Science Applications
  • Automotive Engineering

Cite this

Varga, D., Havasi, L., & Szirányi, T. (2015). Pedestrian detection in surveillance videos based on CS-LBP feature. In 2015 International Conference on Models and Technologies for Intelligent Transportation Systems, MT-ITS 2015 (pp. 413-417). [7223288] Institute of Electrical and Electronics Engineers Inc.. https://doi.org/10.1109/MTITS.2015.7223288

Pedestrian detection in surveillance videos based on CS-LBP feature. / Varga, Domonkos; Havasi, László; Szirányi, T.

2015 International Conference on Models and Technologies for Intelligent Transportation Systems, MT-ITS 2015. Institute of Electrical and Electronics Engineers Inc., 2015. p. 413-417 7223288.

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

Varga, D, Havasi, L & Szirányi, T 2015, Pedestrian detection in surveillance videos based on CS-LBP feature. in 2015 International Conference on Models and Technologies for Intelligent Transportation Systems, MT-ITS 2015., 7223288, Institute of Electrical and Electronics Engineers Inc., pp. 413-417, International Conference on Models and Technologies for Intelligent Transportation Systems, MT-ITS 2015, Budapest, Hungary, 6/3/15. https://doi.org/10.1109/MTITS.2015.7223288
Varga D, Havasi L, Szirányi T. Pedestrian detection in surveillance videos based on CS-LBP feature. In 2015 International Conference on Models and Technologies for Intelligent Transportation Systems, MT-ITS 2015. Institute of Electrical and Electronics Engineers Inc. 2015. p. 413-417. 7223288 https://doi.org/10.1109/MTITS.2015.7223288
Varga, Domonkos ; Havasi, László ; Szirányi, T. / Pedestrian detection in surveillance videos based on CS-LBP feature. 2015 International Conference on Models and Technologies for Intelligent Transportation Systems, MT-ITS 2015. Institute of Electrical and Electronics Engineers Inc., 2015. pp. 413-417
@inproceedings{e178f6e0d97c4f18bf5126889fcd552d,
title = "Pedestrian detection in surveillance videos based on CS-LBP feature",
abstract = "Detecting different categories of objects in an image and video content is one of the fundamental tasks in computer vision research. Pedestrian detection is a hot research topic, with several applications including robotics, surveillance and automotive safety. Pedestrians are key participants in transportation systems, so pedestrian detection in video surveillance systems is of great significance to the research and application of Intelligent Transportation Systems (ITS). Pedestrian detection is a challenging problem due to the variance of illumination, color, scale, pose, and so forth. Extraction of effictive features is a key to this task. In this work, we present the multi-scale Center-symmetric Local Binary Pattern feature for pedestrian detection. The proposed feature captures gradient information and some texture and scale information. We completed the detection task with a foreground segmentation method. Experiments on CAVIAR sequences show that the proposed feature with support vector machines can detect pedestrians in real-time effectively in surveillance videos.",
keywords = "pedestrian detection, video surveillance",
author = "Domonkos Varga and L{\'a}szl{\'o} Havasi and T. Szir{\'a}nyi",
year = "2015",
month = "8",
day = "25",
doi = "10.1109/MTITS.2015.7223288",
language = "English",
isbn = "9789633131428",
pages = "413--417",
booktitle = "2015 International Conference on Models and Technologies for Intelligent Transportation Systems, MT-ITS 2015",
publisher = "Institute of Electrical and Electronics Engineers Inc.",

}

TY - GEN

T1 - Pedestrian detection in surveillance videos based on CS-LBP feature

AU - Varga, Domonkos

AU - Havasi, László

AU - Szirányi, T.

PY - 2015/8/25

Y1 - 2015/8/25

N2 - Detecting different categories of objects in an image and video content is one of the fundamental tasks in computer vision research. Pedestrian detection is a hot research topic, with several applications including robotics, surveillance and automotive safety. Pedestrians are key participants in transportation systems, so pedestrian detection in video surveillance systems is of great significance to the research and application of Intelligent Transportation Systems (ITS). Pedestrian detection is a challenging problem due to the variance of illumination, color, scale, pose, and so forth. Extraction of effictive features is a key to this task. In this work, we present the multi-scale Center-symmetric Local Binary Pattern feature for pedestrian detection. The proposed feature captures gradient information and some texture and scale information. We completed the detection task with a foreground segmentation method. Experiments on CAVIAR sequences show that the proposed feature with support vector machines can detect pedestrians in real-time effectively in surveillance videos.

AB - Detecting different categories of objects in an image and video content is one of the fundamental tasks in computer vision research. Pedestrian detection is a hot research topic, with several applications including robotics, surveillance and automotive safety. Pedestrians are key participants in transportation systems, so pedestrian detection in video surveillance systems is of great significance to the research and application of Intelligent Transportation Systems (ITS). Pedestrian detection is a challenging problem due to the variance of illumination, color, scale, pose, and so forth. Extraction of effictive features is a key to this task. In this work, we present the multi-scale Center-symmetric Local Binary Pattern feature for pedestrian detection. The proposed feature captures gradient information and some texture and scale information. We completed the detection task with a foreground segmentation method. Experiments on CAVIAR sequences show that the proposed feature with support vector machines can detect pedestrians in real-time effectively in surveillance videos.

KW - pedestrian detection

KW - video surveillance

UR - http://www.scopus.com/inward/record.url?scp=84950987937&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=84950987937&partnerID=8YFLogxK

U2 - 10.1109/MTITS.2015.7223288

DO - 10.1109/MTITS.2015.7223288

M3 - Conference contribution

AN - SCOPUS:84950987937

SN - 9789633131428

SP - 413

EP - 417

BT - 2015 International Conference on Models and Technologies for Intelligent Transportation Systems, MT-ITS 2015

PB - Institute of Electrical and Electronics Engineers Inc.

ER -