Human detection framework for automated surveillance systems

Redwan A K Noaman, Mohd Alauddin Mohd Ali, Nasharuddin Zainal, Faisal Saeed

Research output: Contribution to journalArticle

4 Citations (Scopus)

Abstract

Vision-based systems for surveillance applications have been used widely and gained more research attention. Detecting people in an image stream is challenging because of their intra-class variability, the diversity of the backgrounds, and the conditions under which the images were acquired. Existing human detection solutions suffer in their effectiveness and efficiency. In particular, the accuracy of the existing detectors is characterized by their high false positive and negative. In addition, existing detectors are slow for online surveillance systems which lead to large delay that is not suitable for surveillance systems for real-time monitoring. In this paper, a holistic framework is proposed for enhancing the performance of human detection in surveillance system. In general, the framework includes the following stages: environment modeling, motion object detection, and human object recognition. In environment modeling, modal algorithm has been suggested for background initialization and extraction. Then for effectively classifying the motion object, edge detecting and B-spline algorithm have been used for shadow detection and removal. Then, enhanced Lucas-Kanade optical flow has been used to get the area of interest for object segmentation. Finally, to enhance the segmentation, some morphological processes were performed. In the motion object recognition stage, segmentation for each blob is performed and processed to the human detector which is a complete learning-based system for detecting and localizing objects/humans in images using mixtures of deformable part models (PFF detector). Results show enhancement in each phase of the proposed framework. These enhancements are shown in the overall performance of human detection in surveillance system.

Original languageEnglish
Pages (from-to)877-886
Number of pages10
JournalInternational Journal of Electrical and Computer Engineering
Volume6
Issue number2
DOIs
Publication statusPublished - 1 Apr 2016

Fingerprint

Detectors
Object recognition
Optical flows
Splines
Monitoring
Object detection

Keywords

  • Automatic Surveillance System
  • Background Subtraction
  • Human Detection
  • Luckas-Kanade
  • Optical Flow
  • PFF detector
  • Shadow Removal

ASJC Scopus subject areas

  • Electrical and Electronic Engineering
  • Computer Science(all)

Cite this

Human detection framework for automated surveillance systems. / Noaman, Redwan A K; Mohd Ali, Mohd Alauddin; Zainal, Nasharuddin; Saeed, Faisal.

In: International Journal of Electrical and Computer Engineering, Vol. 6, No. 2, 01.04.2016, p. 877-886.

Research output: Contribution to journalArticle

Noaman, Redwan A K ; Mohd Ali, Mohd Alauddin ; Zainal, Nasharuddin ; Saeed, Faisal. / Human detection framework for automated surveillance systems. In: International Journal of Electrical and Computer Engineering. 2016 ; Vol. 6, No. 2. pp. 877-886.
@article{095201d0de4142398e530e79e95d9963,
title = "Human detection framework for automated surveillance systems",
abstract = "Vision-based systems for surveillance applications have been used widely and gained more research attention. Detecting people in an image stream is challenging because of their intra-class variability, the diversity of the backgrounds, and the conditions under which the images were acquired. Existing human detection solutions suffer in their effectiveness and efficiency. In particular, the accuracy of the existing detectors is characterized by their high false positive and negative. In addition, existing detectors are slow for online surveillance systems which lead to large delay that is not suitable for surveillance systems for real-time monitoring. In this paper, a holistic framework is proposed for enhancing the performance of human detection in surveillance system. In general, the framework includes the following stages: environment modeling, motion object detection, and human object recognition. In environment modeling, modal algorithm has been suggested for background initialization and extraction. Then for effectively classifying the motion object, edge detecting and B-spline algorithm have been used for shadow detection and removal. Then, enhanced Lucas-Kanade optical flow has been used to get the area of interest for object segmentation. Finally, to enhance the segmentation, some morphological processes were performed. In the motion object recognition stage, segmentation for each blob is performed and processed to the human detector which is a complete learning-based system for detecting and localizing objects/humans in images using mixtures of deformable part models (PFF detector). Results show enhancement in each phase of the proposed framework. These enhancements are shown in the overall performance of human detection in surveillance system.",
keywords = "Automatic Surveillance System, Background Subtraction, Human Detection, Luckas-Kanade, Optical Flow, PFF detector, Shadow Removal",
author = "Noaman, {Redwan A K} and {Mohd Ali}, {Mohd Alauddin} and Nasharuddin Zainal and Faisal Saeed",
year = "2016",
month = "4",
day = "1",
doi = "10.11591/ijece.v6i1.9578",
language = "English",
volume = "6",
pages = "877--886",
journal = "International Journal of Electrical and Computer Engineering",
issn = "2088-8708",
publisher = "Institute of Advanced Engineering and Science (IAES)",
number = "2",

}

TY - JOUR

T1 - Human detection framework for automated surveillance systems

AU - Noaman, Redwan A K

AU - Mohd Ali, Mohd Alauddin

AU - Zainal, Nasharuddin

AU - Saeed, Faisal

PY - 2016/4/1

Y1 - 2016/4/1

N2 - Vision-based systems for surveillance applications have been used widely and gained more research attention. Detecting people in an image stream is challenging because of their intra-class variability, the diversity of the backgrounds, and the conditions under which the images were acquired. Existing human detection solutions suffer in their effectiveness and efficiency. In particular, the accuracy of the existing detectors is characterized by their high false positive and negative. In addition, existing detectors are slow for online surveillance systems which lead to large delay that is not suitable for surveillance systems for real-time monitoring. In this paper, a holistic framework is proposed for enhancing the performance of human detection in surveillance system. In general, the framework includes the following stages: environment modeling, motion object detection, and human object recognition. In environment modeling, modal algorithm has been suggested for background initialization and extraction. Then for effectively classifying the motion object, edge detecting and B-spline algorithm have been used for shadow detection and removal. Then, enhanced Lucas-Kanade optical flow has been used to get the area of interest for object segmentation. Finally, to enhance the segmentation, some morphological processes were performed. In the motion object recognition stage, segmentation for each blob is performed and processed to the human detector which is a complete learning-based system for detecting and localizing objects/humans in images using mixtures of deformable part models (PFF detector). Results show enhancement in each phase of the proposed framework. These enhancements are shown in the overall performance of human detection in surveillance system.

AB - Vision-based systems for surveillance applications have been used widely and gained more research attention. Detecting people in an image stream is challenging because of their intra-class variability, the diversity of the backgrounds, and the conditions under which the images were acquired. Existing human detection solutions suffer in their effectiveness and efficiency. In particular, the accuracy of the existing detectors is characterized by their high false positive and negative. In addition, existing detectors are slow for online surveillance systems which lead to large delay that is not suitable for surveillance systems for real-time monitoring. In this paper, a holistic framework is proposed for enhancing the performance of human detection in surveillance system. In general, the framework includes the following stages: environment modeling, motion object detection, and human object recognition. In environment modeling, modal algorithm has been suggested for background initialization and extraction. Then for effectively classifying the motion object, edge detecting and B-spline algorithm have been used for shadow detection and removal. Then, enhanced Lucas-Kanade optical flow has been used to get the area of interest for object segmentation. Finally, to enhance the segmentation, some morphological processes were performed. In the motion object recognition stage, segmentation for each blob is performed and processed to the human detector which is a complete learning-based system for detecting and localizing objects/humans in images using mixtures of deformable part models (PFF detector). Results show enhancement in each phase of the proposed framework. These enhancements are shown in the overall performance of human detection in surveillance system.

KW - Automatic Surveillance System

KW - Background Subtraction

KW - Human Detection

KW - Luckas-Kanade

KW - Optical Flow

KW - PFF detector

KW - Shadow Removal

UR - http://www.scopus.com/inward/record.url?scp=84960157534&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=84960157534&partnerID=8YFLogxK

U2 - 10.11591/ijece.v6i1.9578

DO - 10.11591/ijece.v6i1.9578

M3 - Article

AN - SCOPUS:84960157534

VL - 6

SP - 877

EP - 886

JO - International Journal of Electrical and Computer Engineering

JF - International Journal of Electrical and Computer Engineering

SN - 2088-8708

IS - 2

ER -