Received: 27 September 2019 Revised: 6 January 2020 Accepted: 17 January 2020
DOI: 10.1111/coin.12292
SPECIAL ISSUE ARTICLE
L
1
norm based pedestrian detection using video
analytics technique
Anandamurugan Selvaraj
1
Jeeva Selvaraj
1,2
Sivabalakrishnan Maruthaiappan
2
Gokulnath Chandra Babu
3
Priyan Malarvizhi Kumar
4
1
Department of Information Technology,
Kongu Engineering College, Erode, India
2
School of Computing Science and
Engineering, VIT, Chennai, India
3
School of Computing Science and
Engineering, VIT, Vellore, India
4
Department of CSE, Middlesex
University, London, UK
Correspondence
Jeeva Selvaraj, School of Computing
Science and Engineering, VIT, Chennai,
India
Email: sassyjeeva@gmail.com
Abstract
Pedestrian detection from images of the visible spectrum
is a high relevant area of research given its potential
impact in the design of pedestrian protection systems.
In general, detection is made with two different phases,
feature extraction and classification. Also, features for
detection of pedestrian are already are available such as
optimal feature model. But still required is an improve-
ment in detection by reducing the execution time and
false positive. The proposed model has three different
phases, that is, background subtraction, feature extrac-
tion, and classification. In spite of giving entire infor-
mation into feature extraction, the system gives only a
useful information (foreground image) by twin back-
ground model. Then the foreground image moves to the
feature extraction and classifies the pedestrian. For fea-
ture extraction, histogram of orientation gradient (HOG)
L
1
normalization has been used. This will increase the
detection accuracy and reduce the computation time
of a process. In addition, false positive rate has been
minimized.
KEYWORDS
HOG, human detection, pedestrian detection, SVM, twin background
model
Computational Intelligence. 2020;1–11. wileyonlinelibrary.com/journal/coin © 2020 Wiley Periodicals, Inc. 1