Professional Documents
Culture Documents
Abstract— Object tracking is an important task in the field task [2]. Also, to enable the system track an object’s
of computer vision. In which the camera tracking have become movement using simultaneous video data in real time, it is
a common requirement in today’s society. The inexpensive essential to minimize the processing time of the data. To
video camera and the high quality lens generate a great solve the target tracking problem, this paper proposes an
interest in the object tracking field. Generally, it is not easy to alternative method, in combination of bacteria colony
track human behavior in an environment with a large view. So optimization with a particle filter, to predict the trajectory of
the project aims to solve the big problems which are associated a moving human being.
with the large view camera system to track the people in the
large area which is single targets in nonlinear motion, handle The swarm intelligence is the emergent technology which
occlusion & to reduce the processing time. In this paper a new is used to solve the complex real world problems using the
algorithm is used to solve the problems which are by using a large no. of autonomous individuals. It inspired from the
GbLN-BCO & model based particle filter. The proposed behaviour of the animals the PSO & BCO was gleaned from
algorithm is tested on the several set of video data. The the flocking of the fish.
accuracy of the tracking perform is greater than the previous
techniques i.e. unscented Kalman filter & Parzen Particle In the rest, our research makes the following
Filter. contributions:
Keywords— GbLN-BCO, Model Based, Particle Filter, 1. The proposal and generalization of a new variant of
Multiple Targets, Occlusion BCO algorithm, called Global-best Local Neighborhood
oriented Bacteria Colony Optimization (GbLN-BCO)
algorithm to speed up the template matching process,
I. INTRODUCTION and consequently reduces the processing time in order to
Image processing and analyzing is vast area of search the object location.
application, one of which is in the field of computer vision .
2. The combination of GbLN-BCO and model-based
Human motion analysis is receiving increasing attention
particle filter is able to handle the problems in nonlinear
from researchers of different fields of study. The interest is
motion.
motivated by a wide spectrum of applications, such as
athletic performance analysis, surveillance, man-machine
interface, video-conferencing, human-computer interaction, II. OBJECTIVES
motion capture (games and animation). A complete model of The objectives of the project are listed below:
human consists of both the movements and the shape of the To study the Bacteria colony Optimization &
body. Many of the available systems consider the two particle filter.
modeling processes as separate even if they are very close.
Depending on the applications (animation, visualization, To implement GbLN BCO Model for object
medical imaging) different methods can be used for the Detection.
measurement of the body shape: laser scanner, infra-red light To track target in nonlinear motion.
scanner, photo grammetry, structured light. The modeling of Differentiate occlusion of images in large view.
the movement is often obtained capturing the motion with To reduce processing time.
tracking processes: this can be achieved with
photogrammetric methods, electromagnetic or mechanical III. LITERATURE SURVEY
sensors systems and image-based methods[2][3]. Various authors have researched on the object detection
In general the tracking process can be described as the and the tracking some of the literature are listed below.
establishment of correspondences of the image structure Muhammad Imran Shehzad et.al [1]the paper proposes
between consecutive frames, based on features related to the A novel methodology using the K-means and the
position, velocity, shape, color and texture [3]. The main occlusion is handled.. The proposed strategy is tried on a few
problem is to establish automatically the corresponding standard datasets including complex circumstances both in
features in different images. The tracking is required for 2D indoor and open air situations. The trial comes about
and 3D object localization and it is also used for object demonstrate that the proposed demonstrate effectively tracks
detection, classification and identification. different questions within the sight of impediment with high
A multi-camera tracking system has to record a large precision. Moreover, the proposed strategy has the ability to
volume of video data using a number of cameras, in which bargain long haul and finish impediment without any earlier
the cameras are located at different points of view in space. preparing of the shape and movement model of the items.
Hence, real-time processing is a critical issue in a multi- The exactness of the proposed strategy is practically identical
camera tracking system. This makes tracking an object’s with that of the GMM and histogram based techniques as it
movement over multiple video streams a very challenging effectively bargains with every one of object tracking cases
2018 Fourth International Conference on Computing Communication Control and Automation (ICCUBEA)
Migration, Communication. The Chemotaxis&
Communication is used to update the positions of the
bacteria. Bacteria swim by rotating whip-like
flagella.The bacteria is used to track the object.
Particle Filter:-In a particle filtering a set of particles
are used to track the object. The particle filter
methodology is used to solve Hidden Markov
Chain (HMM) and nonlinear filtering problems arising
in signal processing and Bayesian statistical inference.
Tracked Output:- The BCO is used for the detection of
the target and the particles filter is used for the tracking
purpose.
B. Flowchart
The whole design & development carried out in three
stages:
1) Video to image conversion and pre processing of
image.
2) Detection of target using BCO
3) Tracking of the detected part.
2018 Fourth International Conference on Computing Communication Control and Automation (ICCUBEA)
We calculate the local best and the global best when the
value of local best is equal to global best the bacteria is
updated and the target is detected. The output of the
bacteria are shown in figure 3(C)& 3(D).
2018 Fourth International Conference on Computing Communication Control and Automation (ICCUBEA)
Stage 4:- confusion matrix True positive rate = TP/ (TP+FN) = 823/ (823+177) =
Now, we computed the final result in the form of 82.3%
confusion matrix. The confusion matrix gives the output True negative rate = TN/ (TN+FP) = 109/ (109+891) =
accuracy of the proposed system. The below figure shows 19.1%
the confusion matrix.
Stage 4:-Graphical User Interface (GUI).
Comparision with the existing method The last stage of the proposed system is the formation of
Here, in this section the results of the proposed system os the GUI. The above results describes the system works very
efficiently and it detects and track the object very accurately
compared to the previous techniques for the comparision of
the processing time is very small than the other methods.
the result and for the result analysis.
Method Parameters
The numbers in the bottom side of the matrix give the REFERENCES
overall accuracy. We achieved the final accuracy of 96.48%
as shown in fig. 3(F) above. [1] Muhammad Imran Shehzad, Yasir A. Shah , ZahidMehmood , Abdul
The manual calculations are given below:- Waheed Malik , ShoaibAzmat” K-means based multiple objects
No of Data set Frames :- 1000 tracking with long-term occlusion handling ” ISSN 1751-9632
Received on 17th May 2016Revised 17th August 2016 IET Comput.
Positive (P):-843 Vis., © The Institution of Engineering and Technology 2016, Vol. 11
Negative (N):- 123 Iss. 1, pp. 68-77
2018 Fourth International Conference on Computing Communication Control and Automation (ICCUBEA)
[2] Huiling Wu, WeihaiLi “ROBUST ONLINE MULTI-OBJECT [7] Suraj K Mankani, Naman S Kumar, Prasad R Dongrekar,
TRACKING BASED ON KCF TRACKERS AND ShreekantSajjanar, Mohana, H V Ravish Aradhya “Real-Time
REASSIGNMENT “ 978-1-5090-4545-7\16\2016 IEEE PP 124-128 Implementation of Object Detection and Tracking on DSP for Video
[3] Koichi Ichige, Osamu Shibata “Accurate Radio-Based Moving Object Surveillance Applications ” IEEE International Conference On Recent
Tracking And Its Application to Sports Analysis” 2016 International Trends In Electronics Information Communication Technology, May
Conference on Advances in Electrical, Electronic and System 20-21, 2016, India, 978-1-5090-0774-5/16/$31.00 © 2016 IEEE PP
Engineering, 14-16 Nov 2016, Putrajaya, Malaysia 978-1-5090-2889- 1965-1969
4/16/$31.00 ©2016 IEEE PP 328-332 [8] Swati Naresh Sharma, AjitkumarKhachane, DilipMotwani “Multi-
[4] Nicolas PapadakisAurélieBugeau “Tracking with Occlusions via Object Tracking Using TLD Framework ” 978-1-5090-0774-5/16/
Graph Cuts” IEEE Transaction on Pattern Analysis and Machine 2016 IEEE International Conference On Recent Trends In Electronics
Intelligence ( Volume: 33,Issue :1 , Jan. 2011 ) 144 - 157. Jan 2011 Information Communication Technology, May 20-21, 2016, India PP
1766 -1769
[5] Yunji ZHAO, Hailong PEI “Object tracking based on particle filter
with discriminative features ” J Control Theory Application 2013 11 [9] Kai Xiang Yang, Ming HwaSheu “Edge-based Moving Object
(1) 42–53 DOI 10.1007/s11768-013-1088-0 PP 42-53 Tracking Algorithm for an Embedded System ”978-1-5090-1570-
2/16/$31.00 ©2016 IEEE PP 153-155 APCCAS 2016
[6] Koichi Ichige, Nobuya Arakawa, Yokohama “Accurate Radio-Based
Moving Object Tracking And Its Application to Sports Analysis” [10] G.G.h. JI Eryou, QIAN Wei-xian, BAI Lian-fa, SUI Xiu-bao,
978-1-5090-2889-4/16/$31.00 ©2016 IEEE 328 2016 International "Improved Particle Filtering Algorithm Based on the Multi-feature
Conference on Advances in Electrical, Electronic and System Fusion for Small IR Target Tracking," Proc. of SPIE, vol. Vol. 8193,
Engineering, PP 328-332 14-16 Nov 2016. 2011.
2018 Fourth International Conference on Computing Communication Control and Automation (ICCUBEA)