Enhancing Performance of Face Detection in Visual Sensor Networks with a Dynamic-based Approach

Enhancing Performance of Face Detection in Visual Sensor Networks with a Dynamic-based Approach A visual sensor network, as a special kind of wireless sensor network, is comprised of self-organizing sensor nodes, where some or all of them are equipped with a low-power camera. In most of the visual sensor network’s applications, human detection and recognition are one of the first challenges. Many different approaches that have been proposed to solve the object detection problem in visual sensor networks cause high transition cost in the network, and they are suitable for single object detection. Therefore, in this paper, we propose a new dynamic light-weight method to detect the faces of the objects in visual sensor networks. The proposed method employs a background subtraction technique, image reduction method, new low-complexity algorithm for extracting the bounding boxes of multiple objects and an innovative dynamic function that obtained from a probabilistic model for cutting each human face’s pixels. The proposed method is called Dynamic Light-weight Human Faces Detection (DLHFD). Our proposed method removes non-face pixels in camera nodes with a new energy-aware face detection method and sends only the faces’ information to the base station. The results from the implementation show that DLHFD method reduces the complexity of the image processing tasks on each camera node. Accordingly, the visual sensor network will last longer. Furthermore, the results prove that DLHFD method has very low processing and transition delay in comparison with other face detection methods. Hence, it is suitable for different monitoring and surveillance applications in visual sensor networks. http://www.deepdyve.com/assets/images/DeepDyve-Logo-lg.png Wireless Personal Communications Springer Journals

Enhancing Performance of Face Detection in Visual Sensor Networks with a Dynamic-based Approach

Loading next page...
 
/lp/springer_journal/enhancing-performance-of-face-detection-in-visual-sensor-networks-with-MujO8kek6I
Publisher
Springer US
Copyright
Copyright © 2017 by Springer Science+Business Media, LLC
Subject
Engineering; Communications Engineering, Networks; Signal,Image and Speech Processing; Computer Communication Networks
ISSN
0929-6212
eISSN
1572-834X
D.O.I.
10.1007/s11277-017-4832-9
Publisher site
See Article on Publisher Site

Abstract

A visual sensor network, as a special kind of wireless sensor network, is comprised of self-organizing sensor nodes, where some or all of them are equipped with a low-power camera. In most of the visual sensor network’s applications, human detection and recognition are one of the first challenges. Many different approaches that have been proposed to solve the object detection problem in visual sensor networks cause high transition cost in the network, and they are suitable for single object detection. Therefore, in this paper, we propose a new dynamic light-weight method to detect the faces of the objects in visual sensor networks. The proposed method employs a background subtraction technique, image reduction method, new low-complexity algorithm for extracting the bounding boxes of multiple objects and an innovative dynamic function that obtained from a probabilistic model for cutting each human face’s pixels. The proposed method is called Dynamic Light-weight Human Faces Detection (DLHFD). Our proposed method removes non-face pixels in camera nodes with a new energy-aware face detection method and sends only the faces’ information to the base station. The results from the implementation show that DLHFD method reduces the complexity of the image processing tasks on each camera node. Accordingly, the visual sensor network will last longer. Furthermore, the results prove that DLHFD method has very low processing and transition delay in comparison with other face detection methods. Hence, it is suitable for different monitoring and surveillance applications in visual sensor networks.

Journal

Wireless Personal CommunicationsSpringer Journals

Published: Aug 12, 2017

References

You’re reading a free preview. Subscribe to read the entire article.


DeepDyve is your
personal research library

It’s your single place to instantly
discover and read the research
that matters to you.

Enjoy affordable access to
over 18 million articles from more than
15,000 peer-reviewed journals.

All for just $49/month

Explore the DeepDyve Library

Search

Query the DeepDyve database, plus search all of PubMed and Google Scholar seamlessly

Organize

Save any article or search result from DeepDyve, PubMed, and Google Scholar... all in one place.

Access

Get unlimited, online access to over 18 million full-text articles from more than 15,000 scientific journals.

Your journals are on DeepDyve

Read from thousands of the leading scholarly journals from SpringerNature, Elsevier, Wiley-Blackwell, Oxford University Press and more.

All the latest content is available, no embargo periods.

See the journals in your area

DeepDyve

Freelancer

DeepDyve

Pro

Price

FREE

$49/month
$360/year

Save searches from
Google Scholar,
PubMed

Create lists to
organize your research

Export lists, citations

Read DeepDyve articles

Abstract access only

Unlimited access to over
18 million full-text articles

Print

20 pages / month

PDF Discount

20% off