Abstract
This paper proposes a method of automatic people
counting used in air-conditioning energy-saving. The method
has counted the number of people in the indoor environments
through three modules: image pre-processing module, image
marking module and people counting module, in order to
control air-conditioning controller to achieve the purpose of
saving energy. Through experiment comparing, image preprocessing
module chooses image graying, Gaussian average
filter, binarization and opening operation to optimize images.
The following image marking module uses connected
component detection algorithm, removing false contouring
based on head shape properties and region marking. Finally,
people counting module is used to count the number of people.
The experimental results show that the method of automatic
people counting about a large number of indoor images is
effective and can maintain high statistics accuracy to those
images which have little background noise. The method is very
suitable for small cost of air-conditioning system to realize airconditioning
energy-saving and achieve the goal of energy
saving.
Keywords-person counting; air-conditioning energy-saving;
image pre-processing; image marking, remove false contouring;
region marking
I. INTRODUCTION
In building energy conservation, the "energy saving,
environmental protection and gaining healthy and
comfortable environment near natural conditions " is the
eternal theme. The statistics shows that China's current
building energy consumption is about 28.5 percent in the
proportion of total energy consumption. The Ministry of
Construction estimates that in China building energy
consumption will account for 30%-40% of total energy
consumption by the year 2020-2030 and air conditioning
energy consumption will account for 40%-60% of building
energy consumption. With the increasingly scarce of world
energy, how to achieve building energy-saving is an urgent
problem. Because air-conditioning energy consumption is
the major energy consumption in modern architecture, we
need to find a balance in the scarce of energy supply and the
indoor comfortable environment requirement for maximum
air-conditioning energy-saving. To realize air-conditioning
energy-saving, in this paper a new method of automatic
person counting using image recognition technology is
introduced to the air-conditioning system. The method not
only uses head shape to identify the number of people in the
indoor environments, but also combines with a lot of
judgmental methods and the head feature to improve
recognition accuracy, in order to control air-conditioning to
realize energy-saving purposes.
Traditional people counting methods are artificial
counting or trigger counting used manual electronic device
that are very intrusive and limit people’s freedom of
movement. With the fast development of information
technology, automatic people counting method using nonintrusive
and cheap solution is necessary.
A lot of literatures have addressed the related issues in
the field in the past decade. People counting methods have
achieved many successfully application in fields of video
surveillance [1,2,3]. These existing methods can be classified
into three categories, which include human body features,
mould matching and neural network. However, the above
methods require a bigger frequency or higher processing
speed, determine training and scores with a very complex
program and choose an appropriate threshold more
difficultly, simultaneously counting method used in aircondition
energy-saving is still an unsolved problem.
In this paper, we propose a method of automatic people
counting used in air-conditioning energy-saving which not
only can meet the requirements of high real-time, but also is
easily realized. This method based on video image
processing handles image data using commercial PC.

Download full report
http://googleurl?sa=t&source=web&cd=2&ve...485957.pdf%3Farnumber%3D5485957&ei=tTcxTojvDPHXiAKMv4SNBg&usg=AFQjCNHRdDxSHxP6xmSMG6jxiV7wCibiig&sig2=nGvPYdJEcMWtD3NX-9C6AQ