International Archives of the Photogrammetry, Remote Sensing and Spatial Information Sciences, Volume XXXIX-B3, 2012 
XXII ISPRS Congress, 25 August — 01 September 2012, Melbourne, Australia 
SPECTRUM-BASED OBJECT DETECTION AND TRACKING TECHNIQUE FOR 
DIGITAL VIDEO SURVEILLANCE 
Boris Vishnyakov, Yury Vizilter and Vladimir Knyaz 
The Federal State Unitary Enterprise "State Research Institute of Aviation Systems" 
Moscow, Viktorenko 7, Russia 
vishnyakov C gosniias.ru, viz ? gosniias.ru, knyaz 9 gosniias.ru 
http://gosniias.ru 
Commission III/4: Complex Scene Analysis and 3D Reconstruction; III/5: Image Sequence Analysis 
KEY WORDS: object, detection, tracking, monitoring, video, image 
ABSTRACT: 
This paper presents a motion detection and object tracking technique for digital video surveillance applications. Motion analysis algo- 
rithms are based on processing of multiple-regression pseudospectrums. Complete object detection and tracking scheme is described. 
Results of testing on public PETS and ETISEO test beds are outlined. 
1 INTRODUCTION 
The video surveillance is one of the key technologies of modern 
security systems. Digital video surveillance presumes the visual 
control of some territory with one or more video cameras, that 
allows storing and viewing digital video data, continuously eval- 
uating the state of controlled region and detecting some changes 
in observed scene as "security events". 
The main drawback of traditional video surveillance systems pro- 
viding raw video to a human operator is a serious decreasing 
of operator's response capability, while the system is growing 
in size. This problem is especially urgent in case of city-level 
surveillance systems. Well-known business case is an implemen- 
tation of video surveillance system in London, Great Britain in- 
cluding tens of thousands of cameras in a single network and 
more than half a million cameras in the whole city. Unfortu- 
nately, it did not provide a serious reduction of crime incidents 
or increasing of crime detection rate. Now we know that it is not 
enough just to broadcast cameras' video to the surveillance cen- 
ter. Video should be processed and alarms should be generated in 
real-time to attract the attention of operator in critical situations. 
So, the design of high-performance intellectual video analytic 
systems is a very actual practical task. Moreover, such intelli- 
gent systems can address both security and counterterrorism ob- 
jectives, and can be of use in some business applications. For 
example, they can collect statistical information about the atten- 
dance of observed object, distribution of visitors over time, main 
routes of movement, etc. Other possible application is a traffic 
monitoring and so on. 
The Motion analysis is a basis of all intelligent video surveillance 
technologies. In particular, it provides the fundamentals for au- 
tomatic detection and tracking of moving objects and automatic 
detection of new or disappeared objects of observed scene. It is 
the well-studied area of computer vision including many differ- 
ent techniques. The brief overview of these techniques is given 
in next section. 
This paper contains a description of proposed technique accom- 
panied with testing results on PETS (PETS video database, n.d.) 
and ETISEO (ETISEO video database, n.d.) public video test 
beds. 
559 
2 RELATED WORKS 
The motion detection and tracking problem is widely studied all 
around the world. There are lots of methods and algorithms, that 
detect motion and trace moving objects. Let us dwell on main 
approaches in video analysis task. First one is the optical flow 
approach (Horn and Schunck, 1981, Nagel, 1983, Barron et al., 
1994). It was the first mentioned in (Horn and Schunck, 1981). 
This approach is based on finding the pixel speed from previous 
to current frames. Let I(k) be an input image pixel matrix with 
width w and height on frame number k. It is assumed that the 
brightness of a point remains constant during a short period of 
time, which is expressed by the equation 
Uo © 
dius 
Hence we get an equation 
VI()s Kat o, 
where (u, v)7 — vector of pixel movement. 
Hence optical flow speed (u, v) can be found via iteration method 
from (Horn and Schunck, 1981, Barron et al., 1994). In different 
books and papers the number of required iterations varies, but to 
achieve a good result you have to make over 100 iterations over 
full image, what is very time consuming. 
The optical flow approach is useless if image sequence contains 
large amount of pixel noise. The next correlation approach (Anan- 
dan, 1989, Singh, 1992) is based on computing correlation func- 
tion of some area and minimizing it in surrounding region to find 
the best match for it and speed vector (u, v)”. Most of correla- 
tion algorithms are based on minimization of SSD-function (Sum 
of Squares Difference): 
SSD; (x, y, u, v) 
sn jm 
= N° N° Wisllotutertenilt T1) - Ich). 
i=—nj=—n 
where W; ; is weight function for the area.