Sunteți pe pagina 1din 6

International Journal of Innovative Research in Information Security (IJIRIS)

Volume 1 Issue 2 (August 2014)

ISSN: 2349-7017(O)
ISSN: 2349-7009 (P)
http://ijiris.com

Object Tracking System Using Motion Detection and Sound


Detection
Prashansha Jain
Computer Science department
Medicaps Institute of Technology and Management,
Indore, MP, India

Dr. C.S. Satsangi


Head of Department, information technology
Medicaps Institute of Technology and Management
Indore, MP, India

Abstract-Visual monitoring activities using cameras automatically without human intervention is a big and challenging
problem so we need automatic object tracker system. This paper presents a new object tracking system in Real time that
systematically combines both motion detection and sound detection. In this system detect motion as well as sound in a real
time and if lack of security it is also give alert message through alarm. The proposed method is excellent in real-time
performance because it detect the moving objects efficiently and accurately form the video recorded by a shaking camera
with changing background and noises.
Keywords - Object detection, Motion detection, Object tracking, Background Subtraction and Sound detection
I.
INTRODUCTION
Intelligent vision analysis has been one of the most important technologies in intelligent environment, security monitoring and
human computer interaction. A real time visual surveillance system detecting and tracking multiple people and monitoring
their activities in an outdoor environment [1].
There are many Applications that could be realized with reliable motion detection and tracking:
1. Automated surveillance for security-many places such as airports, casinos, museums, and government installations:
Intelligent software is used to monitor security cameras and detect suspicious behaviour. So automated surveillance are
increases the productivity of the human operator and increases coverage of the surveillance.
2. Human interaction for mobile robotics: Autonomous mobile robots in the workplace or home could interact with the
humans and their environment, if they could reliably detect their Presence.
3. Safety devices for pedestrian detection on motor vehicles: There are many intelligent software on a Camera-equipped car
could detect pedestrians and warn the driver.
4. Automatic motion capture for film and television: Producing computer-generated imagery of accurate motion currently
requires the use of a motion-capture System that stores exact 2-D or 3- motion of a human body.
Difficulties in object tracking:
1. Abrupt object motion.
2. Changing appearance patterns of both the object and the scene.
3. Non rigid object structures.
4. Object-to-object and object-to-scene occlusions.
5. Camera motion Tracking.
A method for real-time segmentation of moving regions in image sequences involves background subtraction, or
thresholdingfind error between an estimate of the image without moving objects and the current image. Due to its complex
computation and the poor anti-noise performance, use the special hardware is needed in real time processing. The frame
difference, or time difference are use to extracts the motion regions by the threshold of time difference in adjacent frames
pixels. The advantages of this method are the insensitive to the change of light, fast background update and good adaptive
performance [1].
1.1 Motion DetectionMotion detection is the process use change in position of an object related to its surrounding or the change in the surrounding
relative to an object [2]
1.2 Background SubtractionBackground Subtraction is a process used for Object detection and it can be achieved by building a representation of the scene
called the background model and then it is finding deviations from the model for each incoming frame and change in an image
region from the background model signifies a moving object. The pixels for each frame in regions marked for further
processing. This process is called the background subtraction.
Another way of general background subtraction is to subtract the gray-level value of the present frame from correspondent
background. So the little change of background luminance, if the correspondent pixels gray-level value is lower than the
thresholding, the object is considered to be static. Otherwise, the region is considered to be dynamic and marked. The location
______________________________________________________________________________________________________
2014, IJIRIS- All Rights Reserved
Page - 53

International Journal of Innovative Research in Information Security (IJIRIS)


Volume 1 Issue 2 (August 2014)

ISSN: 2349-7017(O)
ISSN: 2349-7009 (P)
http://ijiris.com

of the moving object can be obtained based on the marked regions. The general background subtraction uses the pixel
dependent time difference and fixed threshold in present frame and background frame to extract the motion region.
II. PROPOSED MODEL FOR REAL TIME OBJECT TRACKING
In any Real Time Object Tracking system using motion detection, one of the most important problems is the video recorded by
a shaking camera with changing background and noises.The basic block Diagram for the proposed Model is shown below:
This is the model which is adapted in this research Work for the purpose of Object Tracking using Motion Detection and
Sound Detection in Real Time.

Object detection
tracker

Sound detection

Motion detection

Motion detection
Or
Sound detection

Alarm alert

Fig. 1 Proposed Model Diagram

Table 1. MATLAB specifications


Methodology Adopted: Tool/Software used
MATLAB

Version
MatlabR2010a

2.1 Problem StatementReal time object tracking in shaking camera with changing background and noises, its a big problem because many time
camera is not detect the object efficiently and accurately form the video recorded by a shaking camera with changing
background and noises. This system is detecting the real time object with motion as well as sound. As object is detected,
through motion and sound and lack of the security, start the alarm.
2.2 Steps of Implemented AlgorithmA) For motion detection1. Capture the live video frames through webcam.
2. Frames acquired are stored in the Matlab directory as matrix in which each element of the matrix contains information
about the pixel value of the image at a particular location.
3. Compare every single pixel of each frame being acquired by the device with the previously acquired Frame and checks for
the difference between the total values of each frame.
4. If difference is greater than the threshold value (T), start storing video until motion will be stopped otherwise delete the
previous frame.
5. As motion is detected, start the alarm.
6. The video and audio files which will be in media player format will be made and stored in the particular desired folder.

______________________________________________________________________________________________________
2014, IJIRIS- All Rights Reserved
Page - 54

International Journal of Innovative Research in Information Security (IJIRIS)


Volume 1 Issue 2 (August 2014)

ISSN: 2349-7017(O)
ISSN: 2349-7009 (P)
http://ijiris.com

B) For sound detection1. Create an analog input object for input sound.
2. Set the trigger type as manual.
3. Repeat the trigger configuration.
4. Set the sample to record i per sample.
5. Now set the analog output object for alarm.
6. Set fs=11025 HZ.
7. Start recording.
8. Play the recording voice.
9. Now write the wave file of hard disk.
10. Now read the wave file.
11. Set the sound thresholding 0.08.
12. Now compute the lowest sound by finding average value and its deviation for mean.
13. Now show the sound and maximum value graph.
14. Now check the value of sound max with these sounds.
15. If sound max > sound thresholding
Them set noise =true
Wave play for alarm data
Otherwise false
16. End.
2.3 Flow chart of proposed algorithmStart

Input the frame i

Calculate the pixel


variant for pair of
frame i
Threshold pair of
frame i

No
motion
detected

Is pixel
variant?
I>T

Stop

Track the
movement
in the
frame

Motion
detected

Fig. 2 Flow chart of proposed algorithm

______________________________________________________________________________________________________
2014, IJIRIS- All Rights Reserved
Page - 55

International Journal of Innovative Research in Information Security (IJIRIS)


Volume 1 Issue 2 (August 2014)

ISSN: 2349-7017(O)
ISSN: 2349-7009 (P)
http://ijiris.com

III. RESULTS
A) Difference between same imagesa.

Fig. 3 Take two same images.

b.

c.

Fig. 4 Histogram of same image


d.

Fig. 5 Detect motion of same images

e.

Fig. 6 Difference between same images

______________________________________________________________________________________________________
2014, IJIRIS- All Rights Reserved
Page - 56

International Journal of Innovative Research in Information Security (IJIRIS)


Volume 1 Issue 2 (August 2014)

ISSN: 2349-7017(O)
ISSN: 2349-7009 (P)
http://ijiris.com

The detected motion is shown by Fig. 5 and difference between same images as shown in Fig. 6 and the difference is zero,
there is no motion.
B) Difference between two different imagesf.

Fig. 7 Take two different images


g.
h.

Fig.8 Histogram of image

i.

Fig. 9 Detected motion between two images


j.

______________________________________________________________________________________________________
2014, IJIRIS- All Rights Reserved
Page - 57

International Journal of Innovative Research in Information Security (IJIRIS)


Volume 1 Issue 2 (August 2014)

ISSN: 2349-7017(O)
ISSN: 2349-7009 (P)
http://ijiris.com

Fig.10 Difference between two images

The detected motion is shown by Fig. 9 and difference between two images is shown in Fig.10. Difference between two
images is not zero so there is some motion.
IV. CONCLUSION
It is a real time object detection system, detect motion as well sound .it is a enhance system as CCTV.CCTV camera only
monitor and recorded the area. but this system monitor and recorded the area and also detect object in real time sound or
motion detection, if camera sometime not detect motion of a object in changing background, so through sound detection, it is
detect sound of a object in a real time and object is detected so it is also play the alarm for lack of security in real time sound or
motion detection.
ACKNOWLEDGEMENT
We would like to sincerely thankful to respected Dr. C.S.Satsangi, (Head of Department Information Technology) for his
contribution and help in writing this Paper. We would also thankful to our team-mates and all my friends who involved in the
discussions and Deliberations during the implementation and Development aspect.
REFERENCES
[1] Jin-Bin yang, Min shi, Qing-Ming yi A New Method for Motion Target Detection by Background Subtraction and
Update, International Conference on Medical Physics and Biomedical Engineering, 1875-3892 2012 Published by
Elsevier B.V. Selection.
[2] Harsha K. Ingle and Prof. Dr. D.S. Borma, Object Tracking System Using MotioDetection, International Journal
ScientificResearchEngineering &Technology (IJSRET) Volume 1, Issue2 pp, 021-026 May 2012.
[3] Alper Yilmaz and Mubarak Shah, Object Tracking: A Survey, ACM Computing Surveys, Vol. 38, No. 4, Article 13,
Publication date: December 2006.
[4] Zhen Yu, Yanping Chen, A real-time motion detection algorithm for traffic monitoring systems based on consecutive
temporal difference, Proceedings of the 7th Asian Control Conference, Hong Kong, China, August 27-29, 2009.
[5] Shui-gen Wei, Lei Yang, Zhen Chen, Zhen-feng Liu, Motion Detection Based on Optical Flow and Self-adaptive
Threshold Segmentation 2011 Published by Elsevier Ltd.
[6] Gonzalez, Rafael C. Digital Image Processing Includes bibliographical references ISBN 0-201-18075-8.
[7] RafaelC.Gonzalez, Richard E. Woods, Steven L. Eddins, Digital Image processing using matlab.
[8] Haritaoglu, Harwood, and Davis Real-time surveillance of people and their activitiesIEEE trans. patt. Analy. Mach.
intell. 22, 8, 809830, l 2000.
[9] Cai, and Aggarwal, J. 1999. Tracking human motion in structured environments using a distributed camera system, IEEE
Trans. Patt. Analy. Mach. Intell. 2, 11, 12411247.
[10] Kang, Cohen, Andmedioni, 2003. Continuous tracking within and across camera streams, In IEEE Conference on
Computer Vision and Pattern Recognition (CVPR). 267272.

______________________________________________________________________________________________________
2014, IJIRIS- All Rights Reserved
Page - 58

S-ar putea să vă placă și