Foreground Object Detection From Videos Containing Complex Background
Video Foreground Detection Based on Adaptive Mixture Gaussian Model for Video ... · 2015. 6....
Transcript of Video Foreground Detection Based on Adaptive Mixture Gaussian Model for Video ... · 2015. 6....
![Page 1: Video Foreground Detection Based on Adaptive Mixture Gaussian Model for Video ... · 2015. 6. 11. · detection algorithm that is robust against illumination changes and noise based](https://reader034.fdocuments.in/reader034/viewer/2022052009/601eb0ab67706642314884cb/html5/thumbnails/1.jpg)
Video Foreground Detection Based on Adaptive
Mixture Gaussian Model for Video Surveillance
Systems
Mohammad Ali Alavianmehr Deputy of Transportation and Traffic Shiraz Municipality, Shiraz Traffic Control Center, Iran
E-mail: [email protected]
Ashkan Tashk and Amir Sodagaran Dept. of Electronics and Electrical Engineering, Shiraz University of Technology, Iran
Deputy of Transportation and Traffic Shiraz Municipality, Shiraz Traffic Control Center, Iran
E-mail: [email protected]; [email protected]
Abstract—Modeling background and moving objects are
significant techniques for video surveillance and other video
processing applications. This paper presents a foreground
detection algorithm that is robust against illumination
changes and noise based on adaptive Gaussian mixture
model (GMM), and provides a novel and practical choice for
intelligent video surveillance systems using static cameras. In
the previous methods, the image of still objects (background
image) is not significant. On the contrary, this method is
based on forming a meticulous background image and
exploiting it for separating moving objects from their
background. The background image is specified either
manually, by taking an image without vehicles, or is detected
in real-time by forming a mathematical or exponential
average of successive images. In comparison to other mixture
models that are complex and computationally expensive, the
proposed method is fast and easy to implement. The
proposed scheme can offer low image degradation. The
simulation results demonstrate high degree of performance
for the proposed method. Index Terms—image processing, Background models, video
surveillance, foreground detection, Gaussian mixture model.
I. INTRODUCTION
The application of image processing and computer
vision techniques to the analysis of video sequences of
traffic flow suggests noticeable improvements over the
present methods of traffic data collection and road traffic
monitoring. Other methods such as the inductive loop, the
sonar and microwave detectors suffer from important
drawbacks in that they cost a lot to install and maintain and
they are not able to identify slow or stationary vehicles.
Video sensors offer a relatively low installation cost with
little traffic disruption during maintenance. Moreover,
they offer wide area monitoring allowing analysis of
traffic flows and turning movements (important to
junction design), speed measurement, multiple point
Manuscript received October 15, 2014; revised March 29, 2015.
vehicle counts, vehicle classification and highway state
assessment (e.g. congestion or incident detection) [1].
Image processing also provides extensive applications
in the related field of autonomous vehicle guidance,
mainly for recognizing the vehicle’s relative location in
the lane and for obstacle detection. The problem of
autonomous vehicle guidance solves several problems at
different abstraction levels. The vision system can assist in
the meticulous localization of the vehicle with regard to its
environment, which is made up of the appropriate lane and
obstacles or other moving vehicles. Both lane and obstacle
detection are based on estimation procedures for detecting
the borders of the lane and determining the path of the
vehicle. The estimation is often done by matching the
observations (images) to a presumed road and/or vehicle
model. Video systems for either traffic monitoring or
autonomous vehicle guidance normally involve two
important tasks of perception: (a) estimation of road
geometry and (b) vehicle and obstacle detection. Road
traffic monitoring is to recognize and analyze traffic
figures, including presence and numbers of vehicles, speed
distribution data, turning traffic flows at intersections,
queue-lengths, space and time occupancy rates, etc.
Therefore, for traffic monitoring it is vital to identify the
lane of the road and then sense and determine presence
and/or motion parameters of a vehicle. Also, in
autonomous vehicle guidance, the knowledge about road
geometry allows a vehicle to follow its route and the
detection of road obstacles becomes an essential and
serious task for avoiding other vehicles present on the
road.
In road traffic monitoring, the video acquisition
cameras are stationary. They are located on posts above
the ground to get optimal view of the road and the passing
vehicles. In automatic vehicle guidance, the cameras are
moving with the vehicle. In these applications it is
necessary to analyze the dynamic change of the
environment and its contents, as well as the dynamic
change of the camera itself. Accordingly, object detection
Journal of Traffic and Logistics Engineering Vol. 3, No. 1, June 2015
45©2015 Journal of Traffic and Logistics Engineeringdoi: 10.12720/jtle.3.1.45-51
![Page 2: Video Foreground Detection Based on Adaptive Mixture Gaussian Model for Video ... · 2015. 6. 11. · detection algorithm that is robust against illumination changes and noise based](https://reader034.fdocuments.in/reader034/viewer/2022052009/601eb0ab67706642314884cb/html5/thumbnails/2.jpg)
from a stationary camera is easier because it involves
fewer estimation procedures.
Initial approaches in this field include spatial, temporal
and spatio-temporal analysis of video sequences. More
advanced and effective approaches consider object
modeling and tracking using state-space estimation
procedures for matching the model to the observations and
for estimating the next state of the object. The most
common techniques, i.e. analysis of the optical flow field
and processing of stereo images, involve processing two or
more images. With optical-flow-field analysis, multiple
images are recognized at different times [2];
Optical-flow-based techniques detect obstacles indirectly
by analyzing the velocity field. Stereo image techniques
determine the correspondences between pixels in the
different images.
Object detection approaches have been classified
according to the method used to isolate the object from the
background on a single frame or a sequence of frames.
Approaches in this class are based on the edge-features
of objects. They can be applied to single images to detect
the edge structure of even still vehicles. Morphological
edge-detection schemes have been extensively applied,
since they exhibit superior performance. In traffic scenes,
the results of an edge detector generally highlight vehicles
as complex groups of edges, while road areas yield
relatively low edge content. Hence the existence of
vehicles may be detected by the edge complexity within
the road area, which can be quantified through analysis of
the histogram. Alternatively, the edges can be grouped
together to form the vehicle’s boundary. Towards this
direction, the algorithm must determine relevant features
(often line segments) and define a grouping strategy that
allows the identification of feature sets, each of which may
correspond to an object of interest (e.g. potential vehicle or
road obstacle). Vertical edges are more probable to form
dominant line segments corresponding to the vertical
boundaries of the profile of a road obstacle. Moreover, a
dominant line segment of a vehicle must have other line
segments in its neighborhood that are detected in nearly
perpendicular directions. Consequently, the detection of
vehicles and/or obstacles can be simply comprised of
finding the rectangles that enclose the dominant line
segments and their neighbors in the image plane. To
improve the shape of object regions Ref. [3], [4] uses the
Hought transform to extract consistent contour lines and
morphological operations to restore small breaks on the
detected contours. Symmetry offers an additional useful
feature for relating these line segments, since vehicle rears
are generally contour and region-symmetric about a
vertical central line.
The detection is then achieved by means of subtracting
the reference image from the current image. Thresholding
is done in order to obtain presence/absence information of
an object in motion. The shadows cast by buildings and
clouds or changes in lighting conditions can affect the
background significantly. With these changing
environmental conditions, it is essential to update the
background frame regularly. There is numerous
background updating techniques. The most common ones
are averaging and selective updating. In averaging, the
background is formed gradually by taking the average of
the previous background with the current frame.
While in exponential updating the background is built
by forming a weighted average between the previous
background and the current frame. In selective updating,
the background is replaced by the current frame only at
motionless regions; where the difference between the
current and the preceding frames is smaller than a
threshold. Selective updating can be done in a more robust
averaging form; that is the still regions of the background
are replaced by the average of the current frame and the
previous background.
This is the most direct method for making motionless
objects vanish and preserving only the traces of moving
objects between two successive frames. The immediate
consequence is that still or slow-moving objects are not
detected. The inter-frame difference succeeds in detecting
motion when temporal changes are obvious. Nevertheless,
it fails when the objects in motion are not sufficiently
textured and preserve uniform regions with the
background. To cope with this problem, the inter-frame
difference is described using a statistical framework often
utilizing spatial Markov random fields [5]. The
inter-frame difference is modeled trough a two-component
mixture density. These components are zero mean
corresponding to the static (background) and changing
(moving object) parts of the image.
Inter-frame differencing provides a crude but simple
tool for estimating moving regions. This process can be
complemented with background frame differencing in
order to improve the estimation accuracy [6]. With color
segmentation or accurate motion estimation we can further
refine the resulting mask of moving regions by means of
optical flow estimation and optimization of the displaced
frame difference to refine the segmentation of moving
objects.
In [7], a new mixture model for image segmentation is
presented. They propose a new way to incorporate spatial
information between neighboring pixels into the Gaussian
mixture model based on Markov random field (MRF). In
mixture models based on MRF, the M-step of the
expectation-maximization (EM) algorithm cannot be
directly applied to the prior distribution for maximization
of the log likelihood with respect to the corresponding
parameters.
Adaptive Gaussian mixture background model is
excellent background model cause of its good analytic
form and high operation efficiency. It is more appropriate
than single Gaussian models for high speed moving
objects detection under outdoor environment where image
background and illumination intensity changes slowly.
However, low convergence speed is its main
disadvantages especially as the illumination intensity
suddenly changes. It cannot adapt to these kinds of rapid
changes and often take changing background pixels as
moving objects, which makes the image foreground
information confused and moving objects lost. Recently,
although many modified Gaussian models (Chen, &He,
Journal of Traffic and Logistics Engineering Vol. 3, No. 1, June 2015
46©2015 Journal of Traffic and Logistics Engineering
![Page 3: Video Foreground Detection Based on Adaptive Mixture Gaussian Model for Video ... · 2015. 6. 11. · detection algorithm that is robust against illumination changes and noise based](https://reader034.fdocuments.in/reader034/viewer/2022052009/601eb0ab67706642314884cb/html5/thumbnails/3.jpg)
2007; Ma&Zhu, 2007; Chen& Zhou, 2007) [8]-[10] have
been developed this problem has not been solved
effectively. In their models, the moving objects shadows
are occasionally detected in HIS (Hue), saturation
intensity space or HSV (hue, saturation, value) space,
which cause the objects detection and shadow removal
need to be processed in different spaces and joined
together by complicated space transform. Yinghong Li in
[11] proposed a new method of detecting moving vehicles
based on edged Gaussian mixture model. Firstly, mixture
Gaussian model is founded for image edge processing
according to the features of image edge information which
is not sensitive to sudden change of illumination intensity.
And some parameters such as the mean vectors and
variance vectors of the pixels are obtained from the model
for moving vehicle shadows detection. Moreover, through
statistical approach moving vehicle shadows are
eliminated based on the differences of brightness
distortion between vehicle shadows and moving vehicles
relative to background.
In [12], presented an enhanced GMM method for the
task of background subtraction. To that purpose, they use
an adaptive variance estimator for the initialization of new
modes. The value computed by the variance estimator is
further employed to trigger a splitting rule, which is
applied to over dominating nodes in order to avoid
under-fitting the underlying background distribution.
Dibyendu [13] proposed a Gaussian mixture model with
advanced distance measure based on support weights and
histogram of gradients for background suppression. The
method also employs variable number of clusters for
generalization. The main advantages of the method are
implicit use of pixel relationships through distance
measure with least modification to the conventional GMM
and effective background noise removal through the use of
background layer concept with no post processing
involved.
Tom S.F. Haines [14] proposed a new method based on
Dirichlet process GMM, which are used to compute
per-pixel background distributions. Using a
non-parametric Bayesian method allows per-pixel mode
counts to be automatically inferred, avoiding over-/under-
fitting.
The main contributions of this paper are (i) to couple
real time systems in order to achieve good detection results
while being able to correctly classify pixels from
foreground images and new static objects, therefore,
notably improving the results presented, (ii) to further
enhance the system proposed in [12] by means of a more
robust estimator versus noise for the variance initialization
value, (iii) learning detected background according to 3
previous frames for more accuracy which means in this
paper as adaptively. The remainder of this paper is
ordered as follows. In section II, the proposed method is
described completely and background images detection
from foreground images described. Section III assigns to
the experimental results and simulations. Eventually, in
section IV, this paper is concluded.
II. PROPOSED METHOD
In this section, we explain the proposed method in detail.
Four phases exist in our algorithm in order to estimate the
traffic status and to compute the velocity. (Fig. 1).
Receiving the images through video surveillance camera
in first phase, we get use of GMM for each frame to
achieve a precise background image. This process will be
repeated as long as we seize an accurate background
images. This phase is called training phase. In the second
phase, the received images will be analyzed a long with
the trained images to extract the vehicles (moving objects)
based on this analysis. As the mention above, we may
extract vehicles more accurately as long as, we have a
more precise trained background images. In third phase, a
green block will surround each vehicles to enable the
researches count them. Either inaccurate training of the
background images or the shadow of moving vehicles
might cause problems in detecting vehicles in motion in
the second phase. To solve these problems besides
merging the blocks which overlap the other ones, the
researchers also make use of shadow removing algorithm
to compute the volume and density of traffic in final phase.
Figure. 1. Algorithm of proposed method
The background learning module is our
multi-dimensional Gaussian kernel density transform
employed for spatio-temporal smoothing. Other stages in
this flow chart are either explained later in this paper or are
self-evident. Note that ‘dilation’ and 'erosion’ are standard
morphological operations applied to a binary image,
where contiguous areas of either ones or zeros are grown
(dilation) or shrunk (erosion) by the radius of some
so-called structuring element. Morphological opening is
Journal of Traffic and Logistics Engineering Vol. 3, No. 1, June 2015
47©2015 Journal of Traffic and Logistics Engineering
![Page 4: Video Foreground Detection Based on Adaptive Mixture Gaussian Model for Video ... · 2015. 6. 11. · detection algorithm that is robust against illumination changes and noise based](https://reader034.fdocuments.in/reader034/viewer/2022052009/601eb0ab67706642314884cb/html5/thumbnails/4.jpg)
Journal of Traffic and Logistics Engineering Vol. 3, No. 1, June 2015
48©2015 Journal of Traffic and Logistics Engineering
an often-used methodology in image processing. Opening
of a binary image is erosion followed by a dilation using
the same structuring element for both operations.
Basic background subtraction (BS) techniques detect
foreground objects as the difference between two
consecutive video frames, operate at pixel level, and are
applicable to still backgrounds. Although the generic BS
method is easy to understand and implement, the
drawbacks of the frame difference BS are that it does not
provide a mechanism for selecting the parameters, such as
the detection threshold, and it is unable to deal with
multimodal distributions. One of the significant
techniques able to cope with multimodal background
distributions and to update the detection threshold
employs Gaussian mixture models (GMMs).
A Gaussian Mixture Model (GMM) is a parametric
probability density function represented as a weighted sum
of Gaussian component densities. GMMs are commonly
used as a parametric model of the probability distribution
of continuous measurements or as features in a biometric
system, such as color based tracking of an object in video.
In many computer related vision technology, it is vital to
determine moving objects from a sequence of videos
frames. In order to obtain this, background subtraction is
applied which mainly recognizes moving objects from
each portion of video frames. In video surveillance, target
recognitions and banks background subtraction or
segmentation technique is widely used. By using the
Gaussian Mixture Model background model, frame pixels
are removed from the required video to obtain the desired
results. The application of background subtraction
involves different factors which contain developing an
algorithm which is able to detect the required object
robustly, it should also be able to react to various changes
like illumination, starting and stopping of moving objects.
A. Background Subtraction
Background Subtraction is based on four important
steps which are stated below.
1) Preprocessing
Temporal or spatial smoothing is employed in the early
preprocessing stage to remove device noise which can be a
factor under different light intensity. Smoothing technique
also includes omitting various elements like environment
such as rain and snow (Fig. 2). In real-time systems, frame
size and frame rate are commonly adopted to decrease the
data processing rate. Another important factor in
preprocessing technique is the data format used by the
background subtraction model. Most algorithms can
handle luminance intensity which is one scalar value per
each pixel.
2) Background modeling
This step makes use of the new video frame in order to
compute and update the background model. The main
purpose of developing a background model is that it should
be robust against environmental changes in the background,
but sensitive enough to determine all moving objects of
interest. (Fig. 2).
3) Foreground detection
In this step, it recognizes the pixels in the frame.
Foreground detection compares the video frame with the
background model, and identify candidate foreground
pixels from the frame. To check whether the pixel is
significantly different from the corresponding background
estimate is a widely-used approach for foreground
detection.
4) Data validation
Finally, this step removed any pixels which are not
relevant to the image. It involves the process of improving
the foreground mask based on the information obtained
from the outside background model.
B. Algorithm of Gaussian Mixture Model
To give a better understanding of the algorithm used for
background subtraction the following steps were adopted
to achieve the desired results: 1. Firstly, we compare each
input pixels to the mean 'μ' of the associated components.
If the value of a pixel is close enough to a chosen
component's mean, then that component is counted as the
matched component. To be a matched component, the
difference between the pixels and mean must be less than
compared to the component's standard deviation. 2.
Secondly, update the Gaussian weight, mean and standard
deviation (variance) to reflect the new obtained pixel value.
Most background models lack three main points: 1.
ignoring any correlation between neighboring pixels 2. The
rate of adaption may not match the moving speed of the
foreground object. 3. Non-stationary pixels, from moving
leavers or shadow cast by objects in motion are at times
mistaken for true foreground objects.
In relation to non-matched components the weights 'w'
reduces whereas the mean and standard deviation stay the
same. It is dependent upon the learning component 'p' in
relation to how fast they are change. 3. Thirdly, here we
identify which components are parts of the background
model. To do this a threshold value applied to the
component weights 'w'. 4. Fourthly, in the final step we
determine the foreground pixels. Here the pixels that are
determined as foreground do not correspond with any
components identified to be the background.
(a)
(b)
Video Frame
![Page 5: Video Foreground Detection Based on Adaptive Mixture Gaussian Model for Video ... · 2015. 6. 11. · detection algorithm that is robust against illumination changes and noise based](https://reader034.fdocuments.in/reader034/viewer/2022052009/601eb0ab67706642314884cb/html5/thumbnails/5.jpg)
Journal of Traffic and Logistics Engineering Vol. 3, No. 1, June 2015
49©2015 Journal of Traffic and Logistics Engineering
(c)
Figure. 2. a, Original frame b, Background frame, c. Detected edge of
Background frame.
C. Formula of Gaussian Mixture Model
A Gaussian mixture model can be formulated in general
as follows:
𝑃(𝑋𝑡) = ∑ 𝑤𝑖,𝑡𝜂(𝑋𝑡; 𝜇𝑖,𝑡 , ∑ 𝑞𝑖,𝑡 )𝐾𝑖=1 (1)
where, obviously,
∑ 𝑤𝑖,𝑡 = 1𝐾𝑖=1 (2)
The mean of such a mixture equals
𝜇𝑡 = ∑ 𝑤𝑖,𝑡𝜇𝑖,𝑡𝐾𝑖=1 (3)
That is, the weighted sum of the means of the component densities.
where be the variable which represents the current pixel in frame, K is the number of distributions, and t represents time (i.e., the frame index), w is an estimate of the weight
of the ith Gaussian in the mixture at time t, is the mean value of the ith Gaussian in the mixture at time t, is the
covariance matrix of the ith Gaussian in the mixture at time
t.
III. EXPERIMENTAL RESULT
In this section, we present a quantitive evaluation of our
system. First, we evaluate the segmentation system, which includes background subtraction and shadow removal.
We present experiments that demonstrate how our
system detects the objects. Fig. 3 shows the results of Gaussian mixture model (GMM) in our method. The classical GMM relies on the statistical information of each
pixel, it fails to correctly detect moving objects in these
two datasets, however, and moving objects are correctly
detected by our method.
In order to quantitatively compare the proposed algorithms with their counterparts in the spatial domain,
we selected four typical frames and manually label all the
pixels of moving objects as the ground truth.
The sequential numbers of these frames are 505, 841,
1357, and 2269, respectively. Two metrics, false negative rate (FNR) and false positive rate (FPR), were used to
quantify the performance of each algorithm. They are
defined as
𝐹𝑁𝑅
=𝑡ℎ𝑒 𝑛𝑢𝑚𝑏𝑒𝑟 𝑜𝑓 𝑓𝑜𝑟𝑒𝑔𝑟𝑜𝑢𝑛𝑑 𝑝𝑖𝑥𝑒𝑙𝑠 𝑤𝑟𝑜𝑛𝑔𝑙𝑦 𝑐𝑙𝑎𝑠𝑠𝑖𝑓𝑖𝑒𝑑
𝑡ℎ𝑒 𝑛𝑢𝑚𝑏𝑒𝑟 𝑜𝑓 𝑓𝑜𝑟𝑒𝑔𝑟𝑜𝑢𝑛𝑑 𝑝𝑖𝑥𝑒𝑙𝑠 𝑖𝑛 𝑡ℎ𝑒 𝑔𝑟𝑜𝑢𝑛𝑑 𝑡𝑟𝑢𝑡ℎ
(4)
𝐹𝑃𝑅
=the number of background pixels wrongly classified
𝑡ℎ𝑒 𝑛𝑢𝑚𝑏𝑒𝑟 𝑜𝑓 𝑏𝑎𝑐𝑘𝑔𝑟𝑜𝑢𝑛𝑑 𝑝𝑖𝑥𝑒𝑙𝑠 𝑖𝑛 𝑡ℎ𝑒 𝑔𝑟𝑜𝑢𝑛𝑑 𝑡𝑟𝑢𝑡ℎ
(5)
In Table I, the experimental results show our algorithms
commonly have a lower FPR than their counterparts in
[12]. The background subtraction technique assumes each
pixel is independent of each other, so it classifies each
pixel independently. That makes the segmentation
procedure is very sensitive to illumination changes and
noises. From Fig. 4, the related FNR and FPR are very
different from that for the Dibyendu's algorithms. The
maximum FNR (about 10%) in our method occurs near the
15th frame. Because of the learning of background image
is not accomplished accuracy.
TABLE I: COMPARISON OF PERFORMANCES OF THE PROPOSED
ALGORITHM WITH THEIR COUTERPARTS IN THE SPATIAL DOMAIN
Proposed Method RUBÉN 's
Method [12]
FNR% FPR% FNR% FPR%
Chamran video 3.86 2.52 4.98 4.69
Zand Video 2.64 1.35 3.89 3.85
Namazi Video 1.25 1.85 2.35 5.86
Neyaesh Video 2.63 1.15 3.26 3.93
Pole Bagh Safa video
1.56 0.95 2.66 2.65
Gomrok Video 0.91 0.63 2.36 1.98
Figure. 3. Original and foreground images in our method based on GMM.
![Page 6: Video Foreground Detection Based on Adaptive Mixture Gaussian Model for Video ... · 2015. 6. 11. · detection algorithm that is robust against illumination changes and noise based](https://reader034.fdocuments.in/reader034/viewer/2022052009/601eb0ab67706642314884cb/html5/thumbnails/6.jpg)
Figure 4. Comparison between FPR and FNR (%) versus frame number
for test videos with [13].
Since the method is based on pixels, it results in a higher
probability to introduce foreground pixels than its
counterpart in the spatial domain. For instance, for a block
containing only one foreground pixel, the pixel will not
generally give rise to large change for the average of the
block compared with the case of no foreground pixel in it,
so the block is likely to be selected to represent the
background. Thus, the pixel-based median performs better
in the case. But the values of FNR for most frames are
below 5%.
IV. CONCLUSION
In this paper propose an approach to solve the crucial
problems related to Intelligent Transportation System (ITS)
for estimating important traffic parameters from video
sequences, that is detection algorithm as long with step
merging and estimate the moment velocity of vehicles, for
highway traffic surveillance. Our approach is low cost and
high accuracy, so the integration of this algorithm in vision
systems can enhance the performance of traffic parameters
estimation and vehicle detection. The proposed approach
succeeds to harness the advantages of both cues by
improving the detection rate without deteriorating the
precision. The results demonstrate its ability to improve
significantly the accuracy of the foreground segmentation
compared to other existing approaches in the literature.
The obtained superior results are significant since many
applications can be carried out after performing reliable
foreground segmentation.
ACKNOWLEDGMENTS
The authors would like to thank the anonymous
reviewers for their insightful comments that significantly
improved the quality of this paper. The authors would also
like to thank Mr. A. Zahmatkesh and Mrs. Sanaz
Akbarzadeh, Vice Chancellor for Transportation of Shiraz
Municipality, for their help on data collection and
experimental evaluations.
REFERENCES
[1] B. D. Stewart, I. Reading, M. S. Thomson, T. D. Binnie, K. W.
Dickinson, and C. L. Wan, “Adaptive lane finding in road traffic
image analysis,” in Proc. Seventh International Conference on Road Traffic Monitoring and Control, London, 1994.
[2] W. Enkelmann, “Obstacle detection by evaluation of optical flow
field from image sequences,” in Proc. European Conference on Computer Vision, Antibes, France, 1990, pp. 134–138.
[3] X. Li, Z. Q. Liu, and K. M. Leung, “Detection of vehicles from
traffic scenes using fuzzy integrals,” Pattern Recognition, vol. 35, pp. 967–980, 2002.
[4] H. Moon, R. Chellapa, and A. Rosenfeld, “Performance analysis of
a simple vehicle detection algorithm,” Image and Vision Computing, vol. 20, pp. 1–13, 2003.
[5] T. Aach and A. Kaup, “Bayesian algorithms for adaptive change
detection in image sequences using Markov random fields,” Signal
Processing: Image Communication, vol. 7, pp. 147–160, 1995. [6] J. B. Kim, H. S. Park, M. H. Park, and H. J. Kim, “A real-time
region-based motion segmentation using adaptive thresholding and
K-means clustering,” in, AI 2001, M. Brooks, D. Corbett, and M. Stumptner, Eds., Springer, Berlin, 2001, pp. 213–224.
[7] T. M. Nguyen and Q. M. J. Wu, “Fast and robust spatially
constrained gaussian mixture model for image segmentation,” IEEE Transactions on Circuits and Systems for Video Technology,
vol. 23, no. 4, 2013.
[8] Y. Ma, W. Zhu et al. “Improved moving objects detection method based on Gaussian mixture mode,” Computer Applications, vol. 27,
no. 10, pp. 2544-2548, 2007.
[9] Z. Chen, X. Chen, and H. He, “Moving object detection based on improved mixture Gaussian models,” Journal of Image and
Graphics, vol. 12, no. 9, pp. 1586-1589, 2007. [10] Z. Chen, R. Zhou, et al. “Simulation of an improved Gaussian
mixture model for background subtraction,” Computer Simulation,
vol. 24, no. 11, pp. 190-192, 2007. [11] Y. H. Li, Z. X. Li, H. F. Tian, and Y. Q. Wang, “Vehicle detecting
and shadow removing based on edged mixture Gaussian model,” in
Proc. Preprints of the 18th IFAC World Congress, Milano, Italy, 2011.
[12] R. H. Evangelio, M. Pätzold, I. Keller, and T. Sikora, “Adaptively
splitted GMM with feedback improvement for the taskof background subtraction,” IEEE Transactions on Information
Forensics and Security, vol. 9, no. 5, 2014.
[13] D. Mukherjee, Q. M. J. Wu, and T. M. Nguyen, “Gaussian mixture model with advanced distance measure based on support weights
and histogram of gradients for background suppression,” IEEE
Transactions on Industrial Information, vol. 10, no. 2, 2014. [14] T. S. F. Haines and T. Xiang, “Background subtraction with
dirichlet process mixture models,” IEEE Transactions on Pattern
Analysis and Machine Intelligence, vol. 36, no. 4, 2014.
M. A. Alavianmehr was born in Shiraz, Iran,
1985. He received the B.S. Degree in Electronics Engineering from the Bushehr
University in 2010 and the M.Sc. Degree from
the Sistan and Bluchestan (Zahedan) university in 2012. His areas of interests are
Image, Speech and video processing. He has
14 publications in both International Journals and International conference papers at various
International and National Conferences.
Recently, he is PhD candidate in Bushehr University and investigating Image and Video Processing for Traffic Application. He is now with
Vice Chancellor for Transportation of Shiraz Municipality, Shiraz
Traffic Control Center.
0 50 100 1500
1
2
3
4
5
6
7
8
9
10
Frame Number(%)
FN
R(%
)
[13]
Proposed Method
0 50 100 1500
1
2
3
4
5
6
7
8
9
Frame Number
FP
R(%
)
[13]
Proposed Method
Journal of Traffic and Logistics Engineering Vol. 3, No. 1, June 2015
50©2015 Journal of Traffic and Logistics Engineering
![Page 7: Video Foreground Detection Based on Adaptive Mixture Gaussian Model for Video ... · 2015. 6. 11. · detection algorithm that is robust against illumination changes and noise based](https://reader034.fdocuments.in/reader034/viewer/2022052009/601eb0ab67706642314884cb/html5/thumbnails/7.jpg)
A. Tashk received the B.Sc. Degree in Communication Engineering from the Shiraz
University of Technology, and M.Sc. Degree
in Communication Engineering from Shiraz University of Technology in 2009 and 2014
respectively. He is PhD student in Shiraz
University of Technology now. His current research interests include image and video
processing. He has published more than 20
papers in international journals and conferences.
A. Sodagaran received the M.S. degree in IT engineering from the Shiraz University, and
the M.Sc. degree in Information Technology
from university of British, Nottingham University. He then joined the Vice Chancellor
for Transportation of Shiraz Municipality,
Shiraz Traffic Control Center, Iran. His current research interests include visual surveillance,
image and video analysis, intelligent
transportation systems. He has published more than 5 papers in international journals and conferences.
Journal of Traffic and Logistics Engineering Vol. 3, No. 1, June 2015
51©2015 Journal of Traffic and Logistics Engineering