SlideShare a Scribd company logo
1 of 3
Download to read offline
2012 International Conference on Computer Science and Electronics Engineering




                  Image processing and detection based on
                          ARM+Linux platform
                                                                 Zhang Xiaozhi
                                                 Department of information Engineering
                                                       Zibo vocational institute
                                                     Zibo,shandong,china,255314
                                                     zhangxiaozhi1116@126.com


 Abstract—video monitoring system plays a vital role in
 maintaining social stability, it can capture device and monitor the
 scene by making use of camera and advanced image recognition                                                                         GPRS
 technology. When the abnormal situation is discovered, it can                                                FLASH
                                                                                             USB
 send out alarm sound and record the scene at the same time by
 using pictures or video, and at last use a variety of ways to notice           CAMERA
 the danger. The topic on video monitoring system is one of the                                               SDRAM
 key parts -- image acquisition processing and detection, using the                                                                   LCD
 platform of Beijing BoChuang UP-NETARM2410-S ,this paper
 introduce the image information processing as well as of the                                                   CPU
 movement object detection.

      Keywords- three frame difference algorithm; threshold; median
 filtering method
                                                                                                      Fig 1 Structure of the system
                        I.      INTRODUCTION
                                                                                  The camera is mainly responsible for the collection of
     As the video monitoring system developing more than 20                   image information, the camera has used the mesh 2000B, it has
 years, it experiences from analog to digital. The hardware and               the advantages of fast speed, low power consumption
 software are correspondingly improved in the functional and                  advantages. Its speed in the 352 * 288 resolution can be
 performance, but many deficiencies still exist. The original                 reached at least 25FPS, and support 24 bit color depth, its
 control is manual operation. Artificial monitoring system can                image quality is very good, many parameters with it can be
 consume quite a lot of manpower and material resources and                   adjusted by hand, brightness and exposure also can be adjusted
 not be remotely controlled, and the function is also single,                 automatically. Mesh 2000B can use USB interface, connection
 which will result to that the error report rate is high, it can only         and convenient to use, does not require an external power
 alarm on the spot and can not achieve real-time remote alarm to              source.
 reduce losses and the working situation of record. These
 drawbacks make alarm system will fail to alarm and alarm                         After system acquire image by use of camera continuously,
 error information, alarm system security and utility will                    it will process a series of image to get the final image, and
 seriously reduce.                                                            judge by the image to decide whether to use the GSM network
                                                                              alarm the user and display on the LCD [3].
     The video monitoring system needs to monitor and detect
 the work locations, according to the acquired image
 information, so it is very important to process the image. This                                   III.   IMAGE PROCESSING
 article will focus on the introduction of image acquisition and                 A large amount of noise maybe produced when receiving
 moving image detection according to the collected images [1].                video frame for the influence of equipment. So de-noise
                                                                              method of image median is needed first, and then the three
                      II.     SYSTEM PLATFORM                                 frames algorithm method, which are developed for board
                                                                              camera is used to analyze the image [4], after that if there is the
     This paper is based on the Beijing BoChuang S3C2410                      moving object is judged according to the image.
 embedded experiment platform. The experimental platform
 adopted S3C2410 processor, the internal integrated ARM920T                      Image preprocessing of the system is image denoising,
 processor for 32 bit MCU of the ARM Company, which has                       which is the first step after the original image extracted.
 the advantages of small volume, high performance, low cost                       Image is denoised by the way of 3 * 3 median filter, and
 and low power consumption, the frequency of it is up to                      system use rapid parallel median filter, which can avoid
 203MHz. In addition, the platform is also equipped with 64M                  amount of the repeated comparison operation. Each window of
 NAND FLASH and 64M SDRAM [2]. System structure                                                                 m ), the whole time of
 diagram is shown in Figure 1 system structure.                               the filter need time about O


978-0-7695-4647-6/12 $26.00 © 2012 IEEE                                 399
DOI 10.1109/ICCSEE.2012.245
2
                                                                         whether or not movement object by the difference of threshold
calculation is O ( N
                            *m
                            ) ,and it’s easy to realize parallel         of image.
processing on hardware processor. Its fast algorithm and
implementation is as follows:                                                According to the experimental observation, the system gets
                                                                         the way of judging movement objects by way of threshold: for
    1) For illustration, each of the 3 x 3 pixels within the
window is respectively defined as follows and the pixels are             three        successive           images
                                                                                                                        p     i −1
                                                                                                                                     (x, y)           p   i
                                                                                                                                                              (x, y)

arranged as shown in Table .                                              p   i +1
                                                                                     (x, y)
                                                                                              .

                                                                             1. That whether d i − 1 , i   or d i , i + 1
                   TABLE I.      PIXEL ROWS LIST
                                                                                                                   ( x, y)                    ( x, y)
                                                                                                                          is more than
                   zero column     first column    second column         or equal to 20 shows existence of movement objects.
                                                                                                            (x, y) −
                                                                            2. When d i − 1 , i          d i ,i + 1
    zeroth line         P00           P01              P02                                        |                                   (x, y) |
                                                                                                                      is more than or
    first line          P10           P11              P12               equal to 10, it shows existence of movement objects.
    second line         P20           P21              P22                   In the process of detecting of movement object, there may
    2) First of all, each column (or row) within the window will         be too fast or too slow movement objects which can’t be
be calculated to get the maximum value, median value and the             detected only by three continuous frames. So the system
minimum value. By this way there will be three set of data,              doesn’t just use three continuous image frames to carry out
which can be respectively marked for the maximum value                   operation but to detect movement objects by using “double
group, the median group and the minimum group. The                       frame three” method according to the characteristics of camera
calculation process is represented as follows:                           [7]. That is when the first" three frame" could not detect the
                                                                         movement information, then the second" frame three" can be
  MAX0=MAX(P00,P10,P20);MAX1=MAX(P01,P11,P21),                           used to detect it. If the second" frame three" can’t detect the
MAX2=MAX(P02,P12,P22)                                                    movement objects, we can use the value of the difference
  MED0=MED(P00,P10,P20);MED1=MED(P01,P11,P21),                           image which come from the subtraction of continuous " frame
MED2=MED(P02,P12,P22)                                                    three". Then we can judge there is a movement object whether
                                                                         or not and operate just like this again and again. Using this
  MIN0=MIN(P00,P10,P20);MIN1=MIN(P01,P11,P21),MI                         method we can not only detect movement objects too fast but
N2=MIN(P02,P12,P22)                                                      also movement objects too slow. And the detection effect is
    3) It can be seen that the maximum value of maximum                  very good. Movement object extraction processes such as
value group and the minimum value of minimum value group                 Figure 2 movement object extraction process chart.
must be the maximum and minimum value of the two columns                                Capture three frames of image(P1,P2,P3)
within the nine pixels. Minimum value of median group is less                          take the difference of image P2-P1 and
than five pixels at least. Similarly, the median value of                                      P3-P2 and threshold T1 T2
maximum group is more than five pixels and the median value
in the minimum group is less than 5 pixels at least. We can note
the minimum value in maximum group of MAX_MIN, the                                                    T1>=20 || T2>=20 ||
                                                                                                                                              Y
                                                                                                                                                      alarm
median value in median group of MED_MED and the                                                          T1-T2 >=10
maximum value in minimum group of MIN_MAX. then
WINMED which is output pixel value from filter results should                                                     N
be the median value of MAX_MIN, MED_MED and                                            Capture three frames of image(P1ƍ,P2ƍ,P3ƍ)
MIN_MAX. The computational process is represented as                                  take the difference of image P2ƍ-P1ƍ and
follows:                                                                                     P3ƍ-P2ƍ and threshold T1ƍ T2ƍ

   WINMED = MED(MAX_MIN MED_MED MIN_MAX).

    Using this method, the median is calculated for seventeen                                         T1ƍ>=20 || T2ƍ>=20 ||
                                                                                                                                                  Y
times. Compared with the traditional algorithm, it can reduce                                             T1ƍ-T2ƍ >=10
for in the number of nearly two times, and the algorithm is very
applicable to the real-time processor for parallel processing.                                                    N

                                                                                           T11ƍ=        P1-P1ƍ T22ƍ= P2-P2ƍ
           IV.    MOVEMENT INFORMATION DETECTION                                                         T33ƍ= P3-P3ƍ
    Movement information detection is mainly responsible for
difference value and threshold calculation coming from the
                                                                                                                                                  Y
acquired image frames. And then it can judge that there is                                            T11ƍ>=15||T22>=15 ||
                                                                                                           T33ƍ>=15
whether or not movement objects [5] [6]. The development of
three frames algorithm method is used for image processing.                                       N
This method can observe the threshold under the condition of
existing movement objects and static objects and then identify                                    Fig 2 flow chart of movement object extraction




                                                                   400
Movement target in the judgment process is divided into the              Table 2 and table 3 each represent a difference image, it can
following several steps:                                                 be seen in Table 2 that the pixel difference is not much, so it
                                                                         can be concluded that the two pictures did not change and
   (1) to take three successive frames of image difference               adaptive method to obtain the threshold is also small. The pixel
image and threshold;                                                     difference in Table 3 is large, it can be concluded that
    (2) to determine whether threshold is more than 20 or                movement object exits and adaptive method to obtain the
difference of threshold is more than 10, if a jump to (7 )or not         threshold is large too.
to jump to ( 3);
   (3) to capture image difference and threshold of three                                              V.     SUMMARY
consecutive image frames;                                                   This paper focused on the study of information processing
                                                                         and movement information detection based on the platform of
    (4) to determine whether threshold is more than 20 or
                                                                         ARM+Linux. The main results are as follows:
difference of threshold is more than 10, if a jump to (7 )or not
to jump to ( 5);                                                             (1) a video surveillance system is developed based on the
                                                                         embedded development platform of ARM+Linux, which could
    (5) to calculate respectively difference image and threshold
                                                                         be widely used for using USB camera. The results show that,
of two three frame image;
                                                                         the platform has stable performance, it is easy to use and
   (6) to determine whether threshold is more than 15, if a              expand, and the image information acquired by the picture is
jump to (7 )or not to jump to ( 5);                                      relatively clear. so it is accord with future development trend of
                                                                         video monitoring application.
   (7) to alarm to the user and jump to ( 1).
                                                                             (2) using median filter to process image and the de-noising
   3, to determine whether there is a movement object                    effect is much better.
according to threshold.
                                                                             (3) the modified three frame difference algorithm is used
    The threshold represents characteristics of a difference             for image processing. the method observe the threshold size of
image. That the threshold is more representative of the two              moving objects and moving objects under the condition and
images of the poor more, and it can determine whether a                  then judge the difference image threshold to identify whether
movement object exists. Table   and table     can shows it as            there is a moving object method. The experimental results
follows:                                                                 show that the extraction effect of moving target information is
                                                                         quite good.
                  TABLE II.         PIXEL ROWS LIST

            1         2            0           1      1
                                                                                                        REFERENCES
                                                                         [1]   Wen Jun. How to effectively realize the intelligent video surveillance [J
            0         0            1           0      2
                                                                               ]. China Security ( technology and application ), 2008, 11, 55-57.
            1         2            0           2      1                  [2]   BoChuang technology. UP-NETARM2410-S Linux embedded system
            3         4            0           5      2                        experiment instruction book [ M]. Beijing BoChuang science and
                                                                               technology 2004.
            2         1            0           3      2
                                                                         [3]   Yao Cong, Fang Yong, Wang Min. Based on the ARM embedded image
            1         0            3           2      1                        acquisition and processing system and its wireless transmission [J ].
                                                                               Electronic technology, 2003, ( 11).
                  TABLE III.        PIXEL ROWS LIST                      [4]   Zhou Xi-Han, Liu Bo,Zhou Heqin. Based on a symmetric difference and
                                                                               background subtraction method for motion detection [ J]. computer
       12        23            7               8      20                       simulation,2005 ( 4).
                                                                         [5]   Wang Yaming, Huang Wenqing, Zhou Hai-ying. Dynamic image
       34        21            10             21      15                       sequence of moving target detection [ J]. Computer Measurement and
                                                                               control, 2003, 11 ( 8).
       13        22            30             22      18
                                                                         [6]   Li Haifeng. Based on streaming video motion information analysis
       34        24            10             35      23                       system research and implementation [D ], Jilin University, 2009.
                                                                         [7]   Wen Hao,Chen Hongtao.Based on background subtraction and
       26        19            20             31      12
                                                                               symmetrical difference moving target detection [ J]. Micro computer
       12        30            34             21      17                       information,2007 ( 25) .




                                                                   401

More Related Content

What's hot

IJERD (www.ijerd.com) International Journal of Engineering Research and Devel...
IJERD (www.ijerd.com) International Journal of Engineering Research and Devel...IJERD (www.ijerd.com) International Journal of Engineering Research and Devel...
IJERD (www.ijerd.com) International Journal of Engineering Research and Devel...IJERD Editor
 
Conference research paper_target_tracking
Conference research paper_target_trackingConference research paper_target_tracking
Conference research paper_target_trackingpatrobadri
 
IRJET- A Non Uniformity Process using High Picture Range Quality
IRJET-  	  A Non Uniformity Process using High Picture Range QualityIRJET-  	  A Non Uniformity Process using High Picture Range Quality
IRJET- A Non Uniformity Process using High Picture Range QualityIRJET Journal
 
Automated traffic sign board
Automated traffic sign boardAutomated traffic sign board
Automated traffic sign boardijcsa
 
01 introduction image processing analysis
01 introduction image processing analysis01 introduction image processing analysis
01 introduction image processing analysisRumah Belajar
 
3.introduction onwards deepa
3.introduction onwards deepa3.introduction onwards deepa
3.introduction onwards deepaSafalsha Babu
 
Basic image processing
Basic image processingBasic image processing
Basic image processingJay Thakkar
 
Image Processing By SAIKIRAN PANJALA
 Image Processing By SAIKIRAN PANJALA Image Processing By SAIKIRAN PANJALA
Image Processing By SAIKIRAN PANJALASaikiran Panjala
 
A Novel Approach for Tracking with Implicit Video Shot Detection
A Novel Approach for Tracking with Implicit Video Shot DetectionA Novel Approach for Tracking with Implicit Video Shot Detection
A Novel Approach for Tracking with Implicit Video Shot DetectionIOSR Journals
 
Imageprocessing teaching schedule
Imageprocessing teaching scheduleImageprocessing teaching schedule
Imageprocessing teaching schedulesatyasaivani
 
Video indexing using shot boundary detection approach and search tracks
Video indexing using shot boundary detection approach and search tracksVideo indexing using shot boundary detection approach and search tracks
Video indexing using shot boundary detection approach and search tracksIAEME Publication
 
Background differencing algorithm for moving object detection using system ge...
Background differencing algorithm for moving object detection using system ge...Background differencing algorithm for moving object detection using system ge...
Background differencing algorithm for moving object detection using system ge...eSAT Publishing House
 
Digital image processing
Digital image processingDigital image processing
Digital image processingDeevena Dayaal
 
SECURE OMP BASED PATTERN RECOGNITION THAT SUPPORTS IMAGE COMPRESSION
SECURE OMP BASED PATTERN RECOGNITION THAT SUPPORTS IMAGE COMPRESSIONSECURE OMP BASED PATTERN RECOGNITION THAT SUPPORTS IMAGE COMPRESSION
SECURE OMP BASED PATTERN RECOGNITION THAT SUPPORTS IMAGE COMPRESSIONsipij
 

What's hot (19)

Gi3511181122
Gi3511181122Gi3511181122
Gi3511181122
 
IJERD (www.ijerd.com) International Journal of Engineering Research and Devel...
IJERD (www.ijerd.com) International Journal of Engineering Research and Devel...IJERD (www.ijerd.com) International Journal of Engineering Research and Devel...
IJERD (www.ijerd.com) International Journal of Engineering Research and Devel...
 
Conference research paper_target_tracking
Conference research paper_target_trackingConference research paper_target_tracking
Conference research paper_target_tracking
 
IRJET- A Non Uniformity Process using High Picture Range Quality
IRJET-  	  A Non Uniformity Process using High Picture Range QualityIRJET-  	  A Non Uniformity Process using High Picture Range Quality
IRJET- A Non Uniformity Process using High Picture Range Quality
 
Automated traffic sign board
Automated traffic sign boardAutomated traffic sign board
Automated traffic sign board
 
01 introduction image processing analysis
01 introduction image processing analysis01 introduction image processing analysis
01 introduction image processing analysis
 
3.introduction onwards deepa
3.introduction onwards deepa3.introduction onwards deepa
3.introduction onwards deepa
 
Background subtraction
Background subtractionBackground subtraction
Background subtraction
 
Gg3311121115
Gg3311121115Gg3311121115
Gg3311121115
 
Basic image processing
Basic image processingBasic image processing
Basic image processing
 
Image Processing By SAIKIRAN PANJALA
 Image Processing By SAIKIRAN PANJALA Image Processing By SAIKIRAN PANJALA
Image Processing By SAIKIRAN PANJALA
 
A Novel Approach for Tracking with Implicit Video Shot Detection
A Novel Approach for Tracking with Implicit Video Shot DetectionA Novel Approach for Tracking with Implicit Video Shot Detection
A Novel Approach for Tracking with Implicit Video Shot Detection
 
Imageprocessing teaching schedule
Imageprocessing teaching scheduleImageprocessing teaching schedule
Imageprocessing teaching schedule
 
Video indexing using shot boundary detection approach and search tracks
Video indexing using shot boundary detection approach and search tracksVideo indexing using shot boundary detection approach and search tracks
Video indexing using shot boundary detection approach and search tracks
 
Background differencing algorithm for moving object detection using system ge...
Background differencing algorithm for moving object detection using system ge...Background differencing algorithm for moving object detection using system ge...
Background differencing algorithm for moving object detection using system ge...
 
Digital image processing
Digital image processingDigital image processing
Digital image processing
 
Digital image processing
Digital image processingDigital image processing
Digital image processing
 
Cb35446450
Cb35446450Cb35446450
Cb35446450
 
SECURE OMP BASED PATTERN RECOGNITION THAT SUPPORTS IMAGE COMPRESSION
SECURE OMP BASED PATTERN RECOGNITION THAT SUPPORTS IMAGE COMPRESSIONSECURE OMP BASED PATTERN RECOGNITION THAT SUPPORTS IMAGE COMPRESSION
SECURE OMP BASED PATTERN RECOGNITION THAT SUPPORTS IMAGE COMPRESSION
 

Viewers also liked

De-Mystifying Twitter for Small Business: Tweeting Towards Sales
De-Mystifying Twitter for Small Business: Tweeting Towards SalesDe-Mystifying Twitter for Small Business: Tweeting Towards Sales
De-Mystifying Twitter for Small Business: Tweeting Towards SalesCharlie Conard
 
The Kiss!pure Innocent love my precious budgies
The Kiss!pure Innocent love my precious budgiesThe Kiss!pure Innocent love my precious budgies
The Kiss!pure Innocent love my precious budgiesMrs Rizwana A Mundewadi
 
Facebook for Business Seminar - 12 Secrets to Market Your Business Better
Facebook for Business Seminar - 12 Secrets to Market Your Business BetterFacebook for Business Seminar - 12 Secrets to Market Your Business Better
Facebook for Business Seminar - 12 Secrets to Market Your Business BetterCharlie Conard
 
Presentation for itethic
Presentation for itethicPresentation for itethic
Presentation for itethicsinisbad123
 
Real Estate - Open the Door to Your Next Sale Using an Effective Social Media...
Real Estate - Open the Door to Your Next Sale Using an Effective Social Media...Real Estate - Open the Door to Your Next Sale Using an Effective Social Media...
Real Estate - Open the Door to Your Next Sale Using an Effective Social Media...Charlie Conard
 
Social-Media-Analytics-How-Can-You-Measure-Social-Media?
Social-Media-Analytics-How-Can-You-Measure-Social-Media?Social-Media-Analytics-How-Can-You-Measure-Social-Media?
Social-Media-Analytics-How-Can-You-Measure-Social-Media?Charlie Conard
 
De-Mystifying Twitter for Small Business - 2016
De-Mystifying Twitter for Small Business - 2016De-Mystifying Twitter for Small Business - 2016
De-Mystifying Twitter for Small Business - 2016Charlie Conard
 
Social Isolation & Neurosis
Social Isolation & NeurosisSocial Isolation & Neurosis
Social Isolation & Neurosisamanda_cook
 
Pelayanan prima berdasarkan konsep tindakan
Pelayanan prima berdasarkan konsep tindakanPelayanan prima berdasarkan konsep tindakan
Pelayanan prima berdasarkan konsep tindakanSri Utami Widijowati
 

Viewers also liked (13)

Coca
CocaCoca
Coca
 
Smart x
Smart xSmart x
Smart x
 
De-Mystifying Twitter for Small Business: Tweeting Towards Sales
De-Mystifying Twitter for Small Business: Tweeting Towards SalesDe-Mystifying Twitter for Small Business: Tweeting Towards Sales
De-Mystifying Twitter for Small Business: Tweeting Towards Sales
 
The Kiss!pure Innocent love my precious budgies
The Kiss!pure Innocent love my precious budgiesThe Kiss!pure Innocent love my precious budgies
The Kiss!pure Innocent love my precious budgies
 
Vita derm saude
Vita derm   saudeVita derm   saude
Vita derm saude
 
Facebook for Business Seminar - 12 Secrets to Market Your Business Better
Facebook for Business Seminar - 12 Secrets to Market Your Business BetterFacebook for Business Seminar - 12 Secrets to Market Your Business Better
Facebook for Business Seminar - 12 Secrets to Market Your Business Better
 
Vita derm saude
Vita derm   saudeVita derm   saude
Vita derm saude
 
Presentation for itethic
Presentation for itethicPresentation for itethic
Presentation for itethic
 
Real Estate - Open the Door to Your Next Sale Using an Effective Social Media...
Real Estate - Open the Door to Your Next Sale Using an Effective Social Media...Real Estate - Open the Door to Your Next Sale Using an Effective Social Media...
Real Estate - Open the Door to Your Next Sale Using an Effective Social Media...
 
Social-Media-Analytics-How-Can-You-Measure-Social-Media?
Social-Media-Analytics-How-Can-You-Measure-Social-Media?Social-Media-Analytics-How-Can-You-Measure-Social-Media?
Social-Media-Analytics-How-Can-You-Measure-Social-Media?
 
De-Mystifying Twitter for Small Business - 2016
De-Mystifying Twitter for Small Business - 2016De-Mystifying Twitter for Small Business - 2016
De-Mystifying Twitter for Small Business - 2016
 
Social Isolation & Neurosis
Social Isolation & NeurosisSocial Isolation & Neurosis
Social Isolation & Neurosis
 
Pelayanan prima berdasarkan konsep tindakan
Pelayanan prima berdasarkan konsep tindakanPelayanan prima berdasarkan konsep tindakan
Pelayanan prima berdasarkan konsep tindakan
 

Similar to Image processing

Multimodel Operation for Visually1.docx
Multimodel Operation for Visually1.docxMultimodel Operation for Visually1.docx
Multimodel Operation for Visually1.docxAROCKIAJAYAIECW
 
Human Motion Detection in Video Surveillance using Computer Vision Technique
Human Motion Detection in Video Surveillance using Computer Vision TechniqueHuman Motion Detection in Video Surveillance using Computer Vision Technique
Human Motion Detection in Video Surveillance using Computer Vision TechniqueIRJET Journal
 
Digital image processing for camera application in mobile devices using artif...
Digital image processing for camera application in mobile devices using artif...Digital image processing for camera application in mobile devices using artif...
Digital image processing for camera application in mobile devices using artif...Alexander Decker
 
11.digital image processing for camera application in mobile devices using ar...
11.digital image processing for camera application in mobile devices using ar...11.digital image processing for camera application in mobile devices using ar...
11.digital image processing for camera application in mobile devices using ar...Alexander Decker
 
IEEE projects in IOT for B.E / B.Tech Students at SLN Technologies
IEEE projects in IOT for B.E / B.Tech Students at SLN Technologies IEEE projects in IOT for B.E / B.Tech Students at SLN Technologies
IEEE projects in IOT for B.E / B.Tech Students at SLN Technologies SLN Technologies - Chennai
 
Canny Edge Detection Algorithm on FPGA
Canny Edge Detection Algorithm on FPGA Canny Edge Detection Algorithm on FPGA
Canny Edge Detection Algorithm on FPGA IOSR Journals
 
IRJET- Intrusion Detection through Image Processing and Getting Notified ...
IRJET-  	  Intrusion Detection through Image Processing and Getting Notified ...IRJET-  	  Intrusion Detection through Image Processing and Getting Notified ...
IRJET- Intrusion Detection through Image Processing and Getting Notified ...IRJET Journal
 
IJCER (www.ijceronline.com) International Journal of computational Engineerin...
IJCER (www.ijceronline.com) International Journal of computational Engineerin...IJCER (www.ijceronline.com) International Journal of computational Engineerin...
IJCER (www.ijceronline.com) International Journal of computational Engineerin...ijceronline
 
Visual pattern recognition in robotics
Visual pattern recognition in roboticsVisual pattern recognition in robotics
Visual pattern recognition in roboticsIAEME Publication
 
A Smart Camera Processing Pipeline for Image Applications Utilizing Marching ...
A Smart Camera Processing Pipeline for Image Applications Utilizing Marching ...A Smart Camera Processing Pipeline for Image Applications Utilizing Marching ...
A Smart Camera Processing Pipeline for Image Applications Utilizing Marching ...sipij
 
IRJET- Image based Approach for Indian Fake Note Detection by Dark Channe...
IRJET-  	  Image based Approach for Indian Fake Note Detection by Dark Channe...IRJET-  	  Image based Approach for Indian Fake Note Detection by Dark Channe...
IRJET- Image based Approach for Indian Fake Note Detection by Dark Channe...IRJET Journal
 
An optimized discrete wavelet transform compression technique for image trans...
An optimized discrete wavelet transform compression technique for image trans...An optimized discrete wavelet transform compression technique for image trans...
An optimized discrete wavelet transform compression technique for image trans...IJECEIAES
 
Web-Based Online Embedded Security System And Alertness Via Social Media
Web-Based Online Embedded Security System And Alertness Via Social MediaWeb-Based Online Embedded Security System And Alertness Via Social Media
Web-Based Online Embedded Security System And Alertness Via Social MediaIRJET Journal
 
Development of Human Tracking in Video Surveillance System for Activity Anal...
Development of Human Tracking in Video Surveillance System  for Activity Anal...Development of Human Tracking in Video Surveillance System  for Activity Anal...
Development of Human Tracking in Video Surveillance System for Activity Anal...IOSR Journals
 
Detection of a user-defined object in an image using feature extraction- Trai...
Detection of a user-defined object in an image using feature extraction- Trai...Detection of a user-defined object in an image using feature extraction- Trai...
Detection of a user-defined object in an image using feature extraction- Trai...IRJET Journal
 
The International Journal of Engineering and Science (The IJES)
The International Journal of Engineering and Science (The IJES)The International Journal of Engineering and Science (The IJES)
The International Journal of Engineering and Science (The IJES)theijes
 
Visual pattern recognition in robotics
Visual pattern recognition in roboticsVisual pattern recognition in robotics
Visual pattern recognition in roboticsIAEME Publication
 

Similar to Image processing (20)

Multimodel Operation for Visually1.docx
Multimodel Operation for Visually1.docxMultimodel Operation for Visually1.docx
Multimodel Operation for Visually1.docx
 
Human Motion Detection in Video Surveillance using Computer Vision Technique
Human Motion Detection in Video Surveillance using Computer Vision TechniqueHuman Motion Detection in Video Surveillance using Computer Vision Technique
Human Motion Detection in Video Surveillance using Computer Vision Technique
 
Dip sdit 7
Dip sdit 7Dip sdit 7
Dip sdit 7
 
Digital image processing for camera application in mobile devices using artif...
Digital image processing for camera application in mobile devices using artif...Digital image processing for camera application in mobile devices using artif...
Digital image processing for camera application in mobile devices using artif...
 
11.digital image processing for camera application in mobile devices using ar...
11.digital image processing for camera application in mobile devices using ar...11.digital image processing for camera application in mobile devices using ar...
11.digital image processing for camera application in mobile devices using ar...
 
IEEE projects in IOT for B.E / B.Tech Students at SLN Technologies
IEEE projects in IOT for B.E / B.Tech Students at SLN Technologies IEEE projects in IOT for B.E / B.Tech Students at SLN Technologies
IEEE projects in IOT for B.E / B.Tech Students at SLN Technologies
 
Canny Edge Detection Algorithm on FPGA
Canny Edge Detection Algorithm on FPGA Canny Edge Detection Algorithm on FPGA
Canny Edge Detection Algorithm on FPGA
 
C010111519
C010111519C010111519
C010111519
 
IRJET- Intrusion Detection through Image Processing and Getting Notified ...
IRJET-  	  Intrusion Detection through Image Processing and Getting Notified ...IRJET-  	  Intrusion Detection through Image Processing and Getting Notified ...
IRJET- Intrusion Detection through Image Processing and Getting Notified ...
 
IJCER (www.ijceronline.com) International Journal of computational Engineerin...
IJCER (www.ijceronline.com) International Journal of computational Engineerin...IJCER (www.ijceronline.com) International Journal of computational Engineerin...
IJCER (www.ijceronline.com) International Journal of computational Engineerin...
 
H028038042
H028038042H028038042
H028038042
 
Visual pattern recognition in robotics
Visual pattern recognition in roboticsVisual pattern recognition in robotics
Visual pattern recognition in robotics
 
A Smart Camera Processing Pipeline for Image Applications Utilizing Marching ...
A Smart Camera Processing Pipeline for Image Applications Utilizing Marching ...A Smart Camera Processing Pipeline for Image Applications Utilizing Marching ...
A Smart Camera Processing Pipeline for Image Applications Utilizing Marching ...
 
IRJET- Image based Approach for Indian Fake Note Detection by Dark Channe...
IRJET-  	  Image based Approach for Indian Fake Note Detection by Dark Channe...IRJET-  	  Image based Approach for Indian Fake Note Detection by Dark Channe...
IRJET- Image based Approach for Indian Fake Note Detection by Dark Channe...
 
An optimized discrete wavelet transform compression technique for image trans...
An optimized discrete wavelet transform compression technique for image trans...An optimized discrete wavelet transform compression technique for image trans...
An optimized discrete wavelet transform compression technique for image trans...
 
Web-Based Online Embedded Security System And Alertness Via Social Media
Web-Based Online Embedded Security System And Alertness Via Social MediaWeb-Based Online Embedded Security System And Alertness Via Social Media
Web-Based Online Embedded Security System And Alertness Via Social Media
 
Development of Human Tracking in Video Surveillance System for Activity Anal...
Development of Human Tracking in Video Surveillance System  for Activity Anal...Development of Human Tracking in Video Surveillance System  for Activity Anal...
Development of Human Tracking in Video Surveillance System for Activity Anal...
 
Detection of a user-defined object in an image using feature extraction- Trai...
Detection of a user-defined object in an image using feature extraction- Trai...Detection of a user-defined object in an image using feature extraction- Trai...
Detection of a user-defined object in an image using feature extraction- Trai...
 
The International Journal of Engineering and Science (The IJES)
The International Journal of Engineering and Science (The IJES)The International Journal of Engineering and Science (The IJES)
The International Journal of Engineering and Science (The IJES)
 
Visual pattern recognition in robotics
Visual pattern recognition in roboticsVisual pattern recognition in robotics
Visual pattern recognition in robotics
 

Recently uploaded

Apidays Singapore 2024 - Building Digital Trust in a Digital Economy by Veron...
Apidays Singapore 2024 - Building Digital Trust in a Digital Economy by Veron...Apidays Singapore 2024 - Building Digital Trust in a Digital Economy by Veron...
Apidays Singapore 2024 - Building Digital Trust in a Digital Economy by Veron...apidays
 
Data Cloud, More than a CDP by Matt Robison
Data Cloud, More than a CDP by Matt RobisonData Cloud, More than a CDP by Matt Robison
Data Cloud, More than a CDP by Matt RobisonAnna Loughnan Colquhoun
 
Raspberry Pi 5: Challenges and Solutions in Bringing up an OpenGL/Vulkan Driv...
Raspberry Pi 5: Challenges and Solutions in Bringing up an OpenGL/Vulkan Driv...Raspberry Pi 5: Challenges and Solutions in Bringing up an OpenGL/Vulkan Driv...
Raspberry Pi 5: Challenges and Solutions in Bringing up an OpenGL/Vulkan Driv...Igalia
 
How to convert PDF to text with Nanonets
How to convert PDF to text with NanonetsHow to convert PDF to text with Nanonets
How to convert PDF to text with Nanonetsnaman860154
 
The Role of Taxonomy and Ontology in Semantic Layers - Heather Hedden.pdf
The Role of Taxonomy and Ontology in Semantic Layers - Heather Hedden.pdfThe Role of Taxonomy and Ontology in Semantic Layers - Heather Hedden.pdf
The Role of Taxonomy and Ontology in Semantic Layers - Heather Hedden.pdfEnterprise Knowledge
 
Slack Application Development 101 Slides
Slack Application Development 101 SlidesSlack Application Development 101 Slides
Slack Application Development 101 Slidespraypatel2
 
A Year of the Servo Reboot: Where Are We Now?
A Year of the Servo Reboot: Where Are We Now?A Year of the Servo Reboot: Where Are We Now?
A Year of the Servo Reboot: Where Are We Now?Igalia
 
GenCyber Cyber Security Day Presentation
GenCyber Cyber Security Day PresentationGenCyber Cyber Security Day Presentation
GenCyber Cyber Security Day PresentationMichael W. Hawkins
 
Real Time Object Detection Using Open CV
Real Time Object Detection Using Open CVReal Time Object Detection Using Open CV
Real Time Object Detection Using Open CVKhem
 
08448380779 Call Girls In Diplomatic Enclave Women Seeking Men
08448380779 Call Girls In Diplomatic Enclave Women Seeking Men08448380779 Call Girls In Diplomatic Enclave Women Seeking Men
08448380779 Call Girls In Diplomatic Enclave Women Seeking MenDelhi Call girls
 
Automating Google Workspace (GWS) & more with Apps Script
Automating Google Workspace (GWS) & more with Apps ScriptAutomating Google Workspace (GWS) & more with Apps Script
Automating Google Workspace (GWS) & more with Apps Scriptwesley chun
 
Bajaj Allianz Life Insurance Company - Insurer Innovation Award 2024
Bajaj Allianz Life Insurance Company - Insurer Innovation Award 2024Bajaj Allianz Life Insurance Company - Insurer Innovation Award 2024
Bajaj Allianz Life Insurance Company - Insurer Innovation Award 2024The Digital Insurer
 
How to Troubleshoot Apps for the Modern Connected Worker
How to Troubleshoot Apps for the Modern Connected WorkerHow to Troubleshoot Apps for the Modern Connected Worker
How to Troubleshoot Apps for the Modern Connected WorkerThousandEyes
 
The 7 Things I Know About Cyber Security After 25 Years | April 2024
The 7 Things I Know About Cyber Security After 25 Years | April 2024The 7 Things I Know About Cyber Security After 25 Years | April 2024
The 7 Things I Know About Cyber Security After 25 Years | April 2024Rafal Los
 
08448380779 Call Girls In Friends Colony Women Seeking Men
08448380779 Call Girls In Friends Colony Women Seeking Men08448380779 Call Girls In Friends Colony Women Seeking Men
08448380779 Call Girls In Friends Colony Women Seeking MenDelhi Call girls
 
Factors to Consider When Choosing Accounts Payable Services Providers.pptx
Factors to Consider When Choosing Accounts Payable Services Providers.pptxFactors to Consider When Choosing Accounts Payable Services Providers.pptx
Factors to Consider When Choosing Accounts Payable Services Providers.pptxKatpro Technologies
 
Workshop - Best of Both Worlds_ Combine KG and Vector search for enhanced R...
Workshop - Best of Both Worlds_ Combine  KG and Vector search for  enhanced R...Workshop - Best of Both Worlds_ Combine  KG and Vector search for  enhanced R...
Workshop - Best of Both Worlds_ Combine KG and Vector search for enhanced R...Neo4j
 
Finology Group – Insurtech Innovation Award 2024
Finology Group – Insurtech Innovation Award 2024Finology Group – Insurtech Innovation Award 2024
Finology Group – Insurtech Innovation Award 2024The Digital Insurer
 
From Event to Action: Accelerate Your Decision Making with Real-Time Automation
From Event to Action: Accelerate Your Decision Making with Real-Time AutomationFrom Event to Action: Accelerate Your Decision Making with Real-Time Automation
From Event to Action: Accelerate Your Decision Making with Real-Time AutomationSafe Software
 
Handwritten Text Recognition for manuscripts and early printed texts
Handwritten Text Recognition for manuscripts and early printed textsHandwritten Text Recognition for manuscripts and early printed texts
Handwritten Text Recognition for manuscripts and early printed textsMaria Levchenko
 

Recently uploaded (20)

Apidays Singapore 2024 - Building Digital Trust in a Digital Economy by Veron...
Apidays Singapore 2024 - Building Digital Trust in a Digital Economy by Veron...Apidays Singapore 2024 - Building Digital Trust in a Digital Economy by Veron...
Apidays Singapore 2024 - Building Digital Trust in a Digital Economy by Veron...
 
Data Cloud, More than a CDP by Matt Robison
Data Cloud, More than a CDP by Matt RobisonData Cloud, More than a CDP by Matt Robison
Data Cloud, More than a CDP by Matt Robison
 
Raspberry Pi 5: Challenges and Solutions in Bringing up an OpenGL/Vulkan Driv...
Raspberry Pi 5: Challenges and Solutions in Bringing up an OpenGL/Vulkan Driv...Raspberry Pi 5: Challenges and Solutions in Bringing up an OpenGL/Vulkan Driv...
Raspberry Pi 5: Challenges and Solutions in Bringing up an OpenGL/Vulkan Driv...
 
How to convert PDF to text with Nanonets
How to convert PDF to text with NanonetsHow to convert PDF to text with Nanonets
How to convert PDF to text with Nanonets
 
The Role of Taxonomy and Ontology in Semantic Layers - Heather Hedden.pdf
The Role of Taxonomy and Ontology in Semantic Layers - Heather Hedden.pdfThe Role of Taxonomy and Ontology in Semantic Layers - Heather Hedden.pdf
The Role of Taxonomy and Ontology in Semantic Layers - Heather Hedden.pdf
 
Slack Application Development 101 Slides
Slack Application Development 101 SlidesSlack Application Development 101 Slides
Slack Application Development 101 Slides
 
A Year of the Servo Reboot: Where Are We Now?
A Year of the Servo Reboot: Where Are We Now?A Year of the Servo Reboot: Where Are We Now?
A Year of the Servo Reboot: Where Are We Now?
 
GenCyber Cyber Security Day Presentation
GenCyber Cyber Security Day PresentationGenCyber Cyber Security Day Presentation
GenCyber Cyber Security Day Presentation
 
Real Time Object Detection Using Open CV
Real Time Object Detection Using Open CVReal Time Object Detection Using Open CV
Real Time Object Detection Using Open CV
 
08448380779 Call Girls In Diplomatic Enclave Women Seeking Men
08448380779 Call Girls In Diplomatic Enclave Women Seeking Men08448380779 Call Girls In Diplomatic Enclave Women Seeking Men
08448380779 Call Girls In Diplomatic Enclave Women Seeking Men
 
Automating Google Workspace (GWS) & more with Apps Script
Automating Google Workspace (GWS) & more with Apps ScriptAutomating Google Workspace (GWS) & more with Apps Script
Automating Google Workspace (GWS) & more with Apps Script
 
Bajaj Allianz Life Insurance Company - Insurer Innovation Award 2024
Bajaj Allianz Life Insurance Company - Insurer Innovation Award 2024Bajaj Allianz Life Insurance Company - Insurer Innovation Award 2024
Bajaj Allianz Life Insurance Company - Insurer Innovation Award 2024
 
How to Troubleshoot Apps for the Modern Connected Worker
How to Troubleshoot Apps for the Modern Connected WorkerHow to Troubleshoot Apps for the Modern Connected Worker
How to Troubleshoot Apps for the Modern Connected Worker
 
The 7 Things I Know About Cyber Security After 25 Years | April 2024
The 7 Things I Know About Cyber Security After 25 Years | April 2024The 7 Things I Know About Cyber Security After 25 Years | April 2024
The 7 Things I Know About Cyber Security After 25 Years | April 2024
 
08448380779 Call Girls In Friends Colony Women Seeking Men
08448380779 Call Girls In Friends Colony Women Seeking Men08448380779 Call Girls In Friends Colony Women Seeking Men
08448380779 Call Girls In Friends Colony Women Seeking Men
 
Factors to Consider When Choosing Accounts Payable Services Providers.pptx
Factors to Consider When Choosing Accounts Payable Services Providers.pptxFactors to Consider When Choosing Accounts Payable Services Providers.pptx
Factors to Consider When Choosing Accounts Payable Services Providers.pptx
 
Workshop - Best of Both Worlds_ Combine KG and Vector search for enhanced R...
Workshop - Best of Both Worlds_ Combine  KG and Vector search for  enhanced R...Workshop - Best of Both Worlds_ Combine  KG and Vector search for  enhanced R...
Workshop - Best of Both Worlds_ Combine KG and Vector search for enhanced R...
 
Finology Group – Insurtech Innovation Award 2024
Finology Group – Insurtech Innovation Award 2024Finology Group – Insurtech Innovation Award 2024
Finology Group – Insurtech Innovation Award 2024
 
From Event to Action: Accelerate Your Decision Making with Real-Time Automation
From Event to Action: Accelerate Your Decision Making with Real-Time AutomationFrom Event to Action: Accelerate Your Decision Making with Real-Time Automation
From Event to Action: Accelerate Your Decision Making with Real-Time Automation
 
Handwritten Text Recognition for manuscripts and early printed texts
Handwritten Text Recognition for manuscripts and early printed textsHandwritten Text Recognition for manuscripts and early printed texts
Handwritten Text Recognition for manuscripts and early printed texts
 

Image processing

  • 1. 2012 International Conference on Computer Science and Electronics Engineering Image processing and detection based on ARM+Linux platform Zhang Xiaozhi Department of information Engineering Zibo vocational institute Zibo,shandong,china,255314 zhangxiaozhi1116@126.com Abstract—video monitoring system plays a vital role in maintaining social stability, it can capture device and monitor the scene by making use of camera and advanced image recognition GPRS technology. When the abnormal situation is discovered, it can FLASH USB send out alarm sound and record the scene at the same time by using pictures or video, and at last use a variety of ways to notice CAMERA the danger. The topic on video monitoring system is one of the SDRAM key parts -- image acquisition processing and detection, using the LCD platform of Beijing BoChuang UP-NETARM2410-S ,this paper introduce the image information processing as well as of the CPU movement object detection. Keywords- three frame difference algorithm; threshold; median filtering method Fig 1 Structure of the system I. INTRODUCTION The camera is mainly responsible for the collection of As the video monitoring system developing more than 20 image information, the camera has used the mesh 2000B, it has years, it experiences from analog to digital. The hardware and the advantages of fast speed, low power consumption software are correspondingly improved in the functional and advantages. Its speed in the 352 * 288 resolution can be performance, but many deficiencies still exist. The original reached at least 25FPS, and support 24 bit color depth, its control is manual operation. Artificial monitoring system can image quality is very good, many parameters with it can be consume quite a lot of manpower and material resources and adjusted by hand, brightness and exposure also can be adjusted not be remotely controlled, and the function is also single, automatically. Mesh 2000B can use USB interface, connection which will result to that the error report rate is high, it can only and convenient to use, does not require an external power alarm on the spot and can not achieve real-time remote alarm to source. reduce losses and the working situation of record. These drawbacks make alarm system will fail to alarm and alarm After system acquire image by use of camera continuously, error information, alarm system security and utility will it will process a series of image to get the final image, and seriously reduce. judge by the image to decide whether to use the GSM network alarm the user and display on the LCD [3]. The video monitoring system needs to monitor and detect the work locations, according to the acquired image information, so it is very important to process the image. This III. IMAGE PROCESSING article will focus on the introduction of image acquisition and A large amount of noise maybe produced when receiving moving image detection according to the collected images [1]. video frame for the influence of equipment. So de-noise method of image median is needed first, and then the three II. SYSTEM PLATFORM frames algorithm method, which are developed for board camera is used to analyze the image [4], after that if there is the This paper is based on the Beijing BoChuang S3C2410 moving object is judged according to the image. embedded experiment platform. The experimental platform adopted S3C2410 processor, the internal integrated ARM920T Image preprocessing of the system is image denoising, processor for 32 bit MCU of the ARM Company, which has which is the first step after the original image extracted. the advantages of small volume, high performance, low cost Image is denoised by the way of 3 * 3 median filter, and and low power consumption, the frequency of it is up to system use rapid parallel median filter, which can avoid 203MHz. In addition, the platform is also equipped with 64M amount of the repeated comparison operation. Each window of NAND FLASH and 64M SDRAM [2]. System structure m ), the whole time of diagram is shown in Figure 1 system structure. the filter need time about O 978-0-7695-4647-6/12 $26.00 © 2012 IEEE 399 DOI 10.1109/ICCSEE.2012.245
  • 2. 2 whether or not movement object by the difference of threshold calculation is O ( N *m ) ,and it’s easy to realize parallel of image. processing on hardware processor. Its fast algorithm and implementation is as follows: According to the experimental observation, the system gets the way of judging movement objects by way of threshold: for 1) For illustration, each of the 3 x 3 pixels within the window is respectively defined as follows and the pixels are three successive images p i −1 (x, y) p i (x, y) arranged as shown in Table . p i +1 (x, y) . 1. That whether d i − 1 , i or d i , i + 1 TABLE I. PIXEL ROWS LIST ( x, y) ( x, y) is more than zero column first column second column or equal to 20 shows existence of movement objects. (x, y) − 2. When d i − 1 , i d i ,i + 1 zeroth line P00 P01 P02 | (x, y) | is more than or first line P10 P11 P12 equal to 10, it shows existence of movement objects. second line P20 P21 P22 In the process of detecting of movement object, there may 2) First of all, each column (or row) within the window will be too fast or too slow movement objects which can’t be be calculated to get the maximum value, median value and the detected only by three continuous frames. So the system minimum value. By this way there will be three set of data, doesn’t just use three continuous image frames to carry out which can be respectively marked for the maximum value operation but to detect movement objects by using “double group, the median group and the minimum group. The frame three” method according to the characteristics of camera calculation process is represented as follows: [7]. That is when the first" three frame" could not detect the movement information, then the second" frame three" can be MAX0=MAX(P00,P10,P20);MAX1=MAX(P01,P11,P21), used to detect it. If the second" frame three" can’t detect the MAX2=MAX(P02,P12,P22) movement objects, we can use the value of the difference MED0=MED(P00,P10,P20);MED1=MED(P01,P11,P21), image which come from the subtraction of continuous " frame MED2=MED(P02,P12,P22) three". Then we can judge there is a movement object whether or not and operate just like this again and again. Using this MIN0=MIN(P00,P10,P20);MIN1=MIN(P01,P11,P21),MI method we can not only detect movement objects too fast but N2=MIN(P02,P12,P22) also movement objects too slow. And the detection effect is 3) It can be seen that the maximum value of maximum very good. Movement object extraction processes such as value group and the minimum value of minimum value group Figure 2 movement object extraction process chart. must be the maximum and minimum value of the two columns Capture three frames of image(P1,P2,P3) within the nine pixels. Minimum value of median group is less take the difference of image P2-P1 and than five pixels at least. Similarly, the median value of P3-P2 and threshold T1 T2 maximum group is more than five pixels and the median value in the minimum group is less than 5 pixels at least. We can note the minimum value in maximum group of MAX_MIN, the T1>=20 || T2>=20 || Y alarm median value in median group of MED_MED and the T1-T2 >=10 maximum value in minimum group of MIN_MAX. then WINMED which is output pixel value from filter results should N be the median value of MAX_MIN, MED_MED and Capture three frames of image(P1ƍ,P2ƍ,P3ƍ) MIN_MAX. The computational process is represented as take the difference of image P2ƍ-P1ƍ and follows: P3ƍ-P2ƍ and threshold T1ƍ T2ƍ WINMED = MED(MAX_MIN MED_MED MIN_MAX). Using this method, the median is calculated for seventeen T1ƍ>=20 || T2ƍ>=20 || Y times. Compared with the traditional algorithm, it can reduce T1ƍ-T2ƍ >=10 for in the number of nearly two times, and the algorithm is very applicable to the real-time processor for parallel processing. N T11ƍ= P1-P1ƍ T22ƍ= P2-P2ƍ IV. MOVEMENT INFORMATION DETECTION T33ƍ= P3-P3ƍ Movement information detection is mainly responsible for difference value and threshold calculation coming from the Y acquired image frames. And then it can judge that there is T11ƍ>=15||T22>=15 || T33ƍ>=15 whether or not movement objects [5] [6]. The development of three frames algorithm method is used for image processing. N This method can observe the threshold under the condition of existing movement objects and static objects and then identify Fig 2 flow chart of movement object extraction 400
  • 3. Movement target in the judgment process is divided into the Table 2 and table 3 each represent a difference image, it can following several steps: be seen in Table 2 that the pixel difference is not much, so it can be concluded that the two pictures did not change and (1) to take three successive frames of image difference adaptive method to obtain the threshold is also small. The pixel image and threshold; difference in Table 3 is large, it can be concluded that (2) to determine whether threshold is more than 20 or movement object exits and adaptive method to obtain the difference of threshold is more than 10, if a jump to (7 )or not threshold is large too. to jump to ( 3); (3) to capture image difference and threshold of three V. SUMMARY consecutive image frames; This paper focused on the study of information processing and movement information detection based on the platform of (4) to determine whether threshold is more than 20 or ARM+Linux. The main results are as follows: difference of threshold is more than 10, if a jump to (7 )or not to jump to ( 5); (1) a video surveillance system is developed based on the embedded development platform of ARM+Linux, which could (5) to calculate respectively difference image and threshold be widely used for using USB camera. The results show that, of two three frame image; the platform has stable performance, it is easy to use and (6) to determine whether threshold is more than 15, if a expand, and the image information acquired by the picture is jump to (7 )or not to jump to ( 5); relatively clear. so it is accord with future development trend of video monitoring application. (7) to alarm to the user and jump to ( 1). (2) using median filter to process image and the de-noising 3, to determine whether there is a movement object effect is much better. according to threshold. (3) the modified three frame difference algorithm is used The threshold represents characteristics of a difference for image processing. the method observe the threshold size of image. That the threshold is more representative of the two moving objects and moving objects under the condition and images of the poor more, and it can determine whether a then judge the difference image threshold to identify whether movement object exists. Table and table can shows it as there is a moving object method. The experimental results follows: show that the extraction effect of moving target information is quite good. TABLE II. PIXEL ROWS LIST 1 2 0 1 1 REFERENCES [1] Wen Jun. How to effectively realize the intelligent video surveillance [J 0 0 1 0 2 ]. China Security ( technology and application ), 2008, 11, 55-57. 1 2 0 2 1 [2] BoChuang technology. UP-NETARM2410-S Linux embedded system 3 4 0 5 2 experiment instruction book [ M]. Beijing BoChuang science and technology 2004. 2 1 0 3 2 [3] Yao Cong, Fang Yong, Wang Min. Based on the ARM embedded image 1 0 3 2 1 acquisition and processing system and its wireless transmission [J ]. Electronic technology, 2003, ( 11). TABLE III. PIXEL ROWS LIST [4] Zhou Xi-Han, Liu Bo,Zhou Heqin. Based on a symmetric difference and background subtraction method for motion detection [ J]. computer 12 23 7 8 20 simulation,2005 ( 4). [5] Wang Yaming, Huang Wenqing, Zhou Hai-ying. Dynamic image 34 21 10 21 15 sequence of moving target detection [ J]. Computer Measurement and control, 2003, 11 ( 8). 13 22 30 22 18 [6] Li Haifeng. Based on streaming video motion information analysis 34 24 10 35 23 system research and implementation [D ], Jilin University, 2009. [7] Wen Hao,Chen Hongtao.Based on background subtraction and 26 19 20 31 12 symmetrical difference moving target detection [ J]. Micro computer 12 30 34 21 17 information,2007 ( 25) . 401