CN100358299C - Home intelligent image monitor method and system basedon realtime network - Google Patents
Home intelligent image monitor method and system basedon realtime network Download PDFInfo
- Publication number
- CN100358299C CN100358299C CNB2004100533093A CN200410053309A CN100358299C CN 100358299 C CN100358299 C CN 100358299C CN B2004100533093 A CNB2004100533093 A CN B2004100533093A CN 200410053309 A CN200410053309 A CN 200410053309A CN 100358299 C CN100358299 C CN 100358299C
- Authority
- CN
- China
- Prior art keywords
- image
- real
- light
- family
- threshold value
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Expired - Fee Related
Links
- 238000000034 method Methods 0.000 title claims abstract description 23
- 238000012544 monitoring process Methods 0.000 claims abstract description 18
- 238000001914 filtration Methods 0.000 claims description 16
- 230000005540 biological transmission Effects 0.000 claims description 13
- 230000006835 compression Effects 0.000 claims description 13
- 238000007906 compression Methods 0.000 claims description 13
- 230000008859 change Effects 0.000 claims description 10
- 239000004744 fabric Substances 0.000 claims description 6
- 239000012141 concentrate Substances 0.000 claims description 3
- 230000002159 abnormal effect Effects 0.000 abstract description 4
- 101150012579 ADSL gene Proteins 0.000 abstract description 3
- 102100020775 Adenylosuccinate lyase Human genes 0.000 abstract description 3
- 108700040193 Adenylosuccinate lyases Proteins 0.000 abstract description 3
- 230000002265 prevention Effects 0.000 abstract description 2
- 230000000694 effects Effects 0.000 description 5
- 238000010586 diagram Methods 0.000 description 4
- 238000012545 processing Methods 0.000 description 3
- 238000012546 transfer Methods 0.000 description 3
- 238000001514 detection method Methods 0.000 description 2
- 238000012986 modification Methods 0.000 description 2
- 230000004048 modification Effects 0.000 description 2
- 230000009471 action Effects 0.000 description 1
- 230000000996 additive effect Effects 0.000 description 1
- 230000000386 athletic effect Effects 0.000 description 1
- 230000007812 deficiency Effects 0.000 description 1
- 238000011161 development Methods 0.000 description 1
- 230000008030 elimination Effects 0.000 description 1
- 238000003379 elimination reaction Methods 0.000 description 1
- 230000006870 function Effects 0.000 description 1
- 230000007774 longterm Effects 0.000 description 1
- 238000005259 measurement Methods 0.000 description 1
- 230000036651 mood Effects 0.000 description 1
- 230000007935 neutral effect Effects 0.000 description 1
- 230000024159 perception of rate of movement Effects 0.000 description 1
- 238000011002 quantification Methods 0.000 description 1
- 230000009467 reduction Effects 0.000 description 1
- 230000000630 rising effect Effects 0.000 description 1
- 238000004088 simulation Methods 0.000 description 1
- 238000006467 substitution reaction Methods 0.000 description 1
- 230000000007 visual effect Effects 0.000 description 1
- 239000002699 waste material Substances 0.000 description 1
Images
Landscapes
- Image Analysis (AREA)
- Alarm Systems (AREA)
Abstract
The present invention discloses a method and a system for family intelligent image monitoring on the basis of real-time network, which is mainly composed of a USB camera, a personal computer (PC), a network card and an ADSL modem. Compared with the previous monitor systems, the method uses any USB camera as an image collecting device, modeling is carried out toward light interference in the PC, and interference caused by light variation is firstly filtered before motion images are detected, so that both the compatibility and the intelligence of the system are enhanced. When abnormal conditions happen, abnormal images are compressed and stored by the system in the format of JPEG (Joint Photographic Experts Group), and users are informed by the network card or the ADSL modem by way of E-mail to handle the abnormal conditions. In addition, egressive users can sent commands to the system through a client end to actively check the current family conditions. The present invention has the advantages of cheap price, intelligence and good real-time performance, and is mainly applied to occasions, such as family theft protection, fire prevention, etc., so that egressive family householders can be concentrated on work, recreation and life enjoyment.
Description
Technical field
The present invention relates to image processing and picture control field, more precisely, relate to a kind of method for supervising, relate to a kind of home intelligent frequency image monitoring system based on real-time network with Intelligent Recognition moving image and real-time Transmission image.
Background technology
Image capture device is frequency image monitoring system " eyes ", is one of important component part of native system.At present, most of image capture device uses image pick-up card or simulation camera, transmits by coaxial cable, uses bnc interface as the data relay interface, general collection of this equipment and transmission speed are all lower, are the bottlenecks of frequency image monitoring system real-time.
The image monitoring method aspect, general employing is following three kinds of methods at present:
1. directly analog image is sent to Control Room, carries out closed monitoring by the full-time staff, this has not only invaded the private right of privacy, and monitoring effect is influenced by full-time staff's mood, degree of fatigue also.
2. digital video all is transferred to the user by network mode, the video data volume is very huge, for common CIF transmission, press the rgb image transmission of per second 24 frames, compression ratio 16: 1, then requiring transmission bandwidth is that (wherein 352 * 288 are CIF transmission resolution to 352 * 288 * 24 * 8 * 3/16=3.48Mbps, 24 is the per second transfer rate, 8 transfer the position for unit of transfer to by byte, and 3 is shared byte number of pixel of true coloured picture), this quite takies Internet resources.
3. carry out simple image processing, because this class frequency image monitoring system lacks the consideration aspect the light filtering algorithm, moving image detects effect and is subjected to the weather conditions interference easily, catches neutral gear to the lawless person easily.And whether this class frequency image monitoring system only changes to image aspect image detection is judged, and do not take in for the situation that object moves in image, this causes easily when the motion object occurs, constantly send the flood peak phenomenon of picture to the user, this causes the congested of network easily, causes certain waste.
In addition, for carrying out the supervisory control system that simple image is handled, the compression algorithm compression efficiency that adopts is low at present, and not only compression back data volume is huge, and compression speed is slow, the image detail partial loss, can not reach the purpose of passing on precise information to the user in real time.
Aspect Network Transmission, current system tends to use wireless transmission, but wireless transmission speed is slow, and wireless signal is easily affected by environment, even loss signal sometimes, and it is unreliable to transmit.
Summary of the invention
At the deficiencies in the prior art, the object of the present invention is to provide a kind of home intelligent frequency image monitoring system based on real-time network, propose to solve the method for practical problem, specific as follows:
1. the exploitation physical layer interface makes native system can use USB device as image capture device;
2. filtering light interference method is proposed;
3. the motion image detecting method based on Fourier transform time shift characteristic is proposed;
4. the higher compression algorithm of development efficiency;
5. utilize the current Internet network eaily characteristics carry out Realtime Alerts;
6. allow the user to obtain the image of family's present case by the Internet network.
In order to reach above purpose, the present invention adopts following technical scheme: a kind of home intelligent image monitoring method based on real-time network, it is characterized in that, and may further comprise the steps:
(1) acquisition of image data is with USB camera collection view data;
(2) filtering light disturbs, and light is disturbed carry out modeling, the light in the view data of gathering is changed the interference filtering that brings;
(3) detect moving image, detect moving image: the image that removes after filtration after light disturbs is carried out Fourier transform, and get its amplitude-frequency, amplitude-frequency to front and back two width of cloth figure pursues pixel relatively then, because the amplitude-frequency information spinner behind the Fourier transform will concentrate on the center of image, so when comparing, each pixel is got different threshold values, less threshold value is got at the center that information is relatively concentrated, and big threshold value is got in other places, deep pixel is got maximum threshold value, compared result is weighted then, compares with total threshold value, with the situation of change of two width of cloth figure before and after distinguishing again, thereby whether occur new object in the analysis image, and the motion of original object in the image is not handled;
(4) compression and transmission image compress detecting the image that new object occurs, and the image file of compression are sent to the user.
The present invention has following technique effect: cheap, intelligent, monitoring in real time, be mainly used in occasions such as home security, fire prevention, and abdicate on outer domestic household more is absorbed in work, amusement and enjoys life.
Description of drawings
Fig. 1 is the home intelligent image monitoring method block diagram based on real-time network of the present invention;
Fig. 2 is a light interference filtering method flow chart of the present invention;
Fig. 3 is the Fourier transform TIME SHIFT INVARIANCE schematic diagram of same object;
Fig. 4 is the Fourier transform time shift characteristic schematic diagram of different objects.
Embodiment
Describe the present invention below with reference to the accompanying drawings in detail.
The invention provides a kind of home intelligent image monitoring method based on real-time network, its principle as shown in Figure 1.The present invention includes following steps:
One. acquisition of image data
The USB transmission rate is fast, the error rate is low, from charged, the present invention utilizes it as the intermediate conveyor medium, has not only improved IMAQ speed, and image capture device can be used the electric energy of PC, be convenient to supervisory control system and be hidden in the shelter, throughout the year need not the dismounting and change battery.
Characteristics of the present invention also are to adopt arbitrary USB camera as IMAQ instrument acquisition of image data, because the Windows stream picture device driver of USB camera producer exploitation all has standard as a reference, be respectively based on the flow transmission driver standard of WDM with based on Windows video (Video forWindows, VFW) capture card standard, based on above standard, the DirectShow kit of native system use Microsoft encapsulates the driver of different manufacturers, reserve an interface unique at last to upper level applications, thus can compatible all USB cameras.
Two, filtering light disturbs
Light, Changes in weather can exert an influence to entire image, change and be distributed in the entire image zone equably, show the rising or the reduction that the gray scale of each pixel of image are produced certain value in the influence of images acquired then being, when this value arrives certain degree greatly, make system produce the wrong report phenomenon easily, influence the detection algorithm accuracy of image.The present invention carries out dynamic modeling with regard to these characteristics that light disturbs to interference source, and from the image that collects this model of filtering to reach the removal effects of jamming.
, after view data, at first carry out filtering light and disturb by the USB camera collection, utilize Fourier to change the characteristics that satisfy proportionality and additive property, to obtain the automatic compensation effect of light.Set forth the method that filtering light disturbs below.
Can think that it all is the whole zone of stepless action in images acquired that light disturbs the most of the time.Suppose that (m n) for the spatial domain expression formula of light (wherein m is the row of image, and n is the row of image), then has l
L (m, n)=N (m, n=arbitrary value) (1)
Wherein N gets different values according to the power of light, will obtain this value by deriving below, thus its interference of elimination.(m, Fourier transform n) is l
M=320 * 240 * N (320 * 240 is image resolution ratio) wherein.
During the native system running software, at first can determine Background, light interference filtering algorithm disturbs zero point with this Background as light, and promptly system thinks that this point is not disturbed by light, and system will be that datum mark carries out the operation of image light interference filtering to realtime graphic with this image.Suppose that background image m is capable, the pixel value of n row is B (m, n), currently obtain that image m is capable, the pixel value of n row is C (m, n), above-mentioned again hypothesis light interference model be l (m, n), if C (m, n) for the image of great change does not take place, ignore the minor variations that causes because of reasons such as gentle breezes, then have
C(m，n)＝B(m，n)+l(m，n) (3)
This formula is carried out Fourier transform, have
DFS[C(m，n)]＝DFS[B(m，n)+l(m，n)]
＝DFS[B(m，n)]+DFS[l(m，n)] (4)
＝DFS[B(m，n)]+L(j，k)
With 2 formula substitutions, 4 formulas, have
Then can obtain
M＝DFS[C(0，0)]-DFS[B(0，0)] (6)
Thereby can obtain
It is as follows to obtain the light interference model at last:
According to long-term practical experience, light disturbs the variation of image grayscale changing value in 15 minutes that causes
＜1%, promptly the light model can not change in 15 minutes, and specific implementation such as program circuit Fig. 2 institute are not.
As shown in Figure 2, the light interference model is initialized as 0, be l (m, n)=0, then carried out one time model modification every 15 minutes, image is a moving image when upgrading if run into, and then program is carried out an IMAQ again and whether detected moving image, up to the image of gathering is not moving image, carries out the light interference model again and upgrades operation.
Three, detect moving image
Generally speaking, it is interested whether the user new object occurs to image, such as thief's appearance.After new object occurs, the user can take measures areput, at this moment, the motion of object in the visual field, then there is no need to transmit, the user has taked treatment measures first, how object is moved lose interest in, second the frequent athletic meeting of object forms huge data volume, causes the congested of network easily.The user can send the situation that family is checked in order by Internet to the kinesthesia interest of object in image if go out.
The present invention utilizes the time shift characteristic of Fourier transform, proposes the method for Intelligent Measurement moving image, whether occurs new object in the analysis image, and the motion of object in the image is not handled, and intelligently is better than any in the past system.
The present image processing field of time shift property list of Fourier transform is supposed the image that Fig. 3 (a) collects for collecting device as shown in Figure 3 and Figure 4, and wherein square is represented object A, and then the amplitude-frequency of its Fourier transform is shown in Fig. 3 (b); If the object A among Fig. 3 (a) is moved to shown in Fig. 3 (c), the amplitude-frequency of its Fourier transform is not difficult to find that Fig. 3 (b) and Fig. 3 (d) are in full accord shown in Fig. 3 (d).And for shown in Figure 4, Fig. 4 (a), Fig. 4 (b) are identical with Fig. 3 (a), Fig. 3 (b), Fig. 4 (c) then is a new object B, then its Fourier transform is shown in Fig. 4 (d), comparison diagram 4 (b) and Fig. 4 (d), can find that when object changes the amplitude-frequency of Fourier transform will take place to change greatly.
According to These characteristics, this method is at first carried out Fourier transform to the image that removes after filtration after light disturbs, and get its amplitude-frequency, amplitude-frequency to front and back two width of cloth figure pursues pixel relatively then, because the amplitude-frequency information spinner behind the Fourier transform will concentrate on the center of image, so when comparing, each pixel is got different threshold values, get less threshold value as the center that information is relatively concentrated, and big threshold value is got in other places, and deep pixel is got maximum threshold value, and compared result is weighted then, compare with total threshold value again, with the situation of change of two width of cloth figure before and after distinguishing.
Four, compressed image
The present invention adopts the JPEG method based on discrete cosine transform, for the requirement of native system to real-time and compression factor, the unicity of background when adding family's supervision, native system is innovated on the quantification link of JPEG method, uses special quantized value combination that image is compressed.
Five, images
Through moving image detect and compression after image, will be by the mode of EMAIL, with network interface card in local area network (LAN), perhaps with ADSL MODEM by the PSTN network, the abnormal image file that family is occurred adopts the ESMTP agreement to encode, and sends to the user.The form that the user also can take the initiative of going out is checked the family situation, send message to family's main frame by Internet, after main frame is received information, earlier graphic file is stored in this locality, the back sends the mode of image by file to distant place user by udp protocol, realizes real-time query function; And EMAIL can user's close region is wired receive after, the mode by near radio local area network (LAN)s such as WIFI is transferred to user's hand-held convenient tool such as PDA on one's body, the situation of real-time informing user family changes.
The foregoing description is used for the present invention that explains, rather than limits the invention, and in the protection range of spirit of the present invention and claim, any modification and change to the present invention makes all fall into protection scope of the present invention.
Claims (3)
1. the home intelligent image monitoring method based on real-time network is characterized in that, may further comprise the steps:
(1) acquisition of image data: with USB camera collection view data;
(2) filtering light disturbs: light is disturbed carry out modeling, the light in the view data of gathering is changed the interference filtering that brings;
(3) detect moving image: the image that removes after filtration after light disturbs is carried out Fourier transform, and get its amplitude-frequency, amplitude-frequency to front and back two width of cloth figure pursues pixel relatively then, because the amplitude-frequency information spinner behind the Fourier transform will concentrate on the center of image, so when comparing, each pixel is got different threshold values, less threshold value is got at the center that information is relatively concentrated, and big threshold value is got in other places, and deep pixel is got maximum threshold value, and compared result is weighted then, compare with total threshold value again, with the situation of change of two width of cloth figure before and after distinguishing, thereby whether occur new object in the analysis image, and the motion of original object in the image is not handled;
(4) compression and transmission image: compress detecting the image that new object occurs, and the image file of compression is sent to the user.
2. the home intelligent image monitoring method based on real-time network according to claim 1 is characterized in that, in the described step (4), with the image of JPEG mode compressed detected to the new object of appearance.
3. the home intelligent image monitoring method based on real-time network according to claim 1 is characterized in that, in the described step (4), in the mode of EMAIL the image file of compression is sent to the user.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CNB2004100533093A CN100358299C (en) | 2004-07-30 | 2004-07-30 | Home intelligent image monitor method and system basedon realtime network |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CNB2004100533093A CN100358299C (en) | 2004-07-30 | 2004-07-30 | Home intelligent image monitor method and system basedon realtime network |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN1588891A CN1588891A (en) | 2005-03-02 |
| CN100358299C true CN100358299C (en) | 2007-12-26 |
Family
ID=34602816
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CNB2004100533093A Expired - Fee Related CN100358299C (en) | 2004-07-30 | 2004-07-30 | Home intelligent image monitor method and system basedon realtime network |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN100358299C (en) |
Families Citing this family (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN101571982B (en) * | 2009-05-11 | 2011-04-13 | 宁波海视智能系统有限公司 | Method for judging stolen articles in video monitoring range |
| CN102305664A (en) * | 2011-05-19 | 2012-01-04 | 中国农业大学 | Thermal imaging temperature measurement and fault location inspection system |
| CN106886217B (en) * | 2017-02-24 | 2020-09-08 | 深圳中智卫安机器人技术有限公司 | Autonomous navigation control method and device |
| CN110764450B (en) * | 2019-11-01 | 2020-07-24 | 威海市豪顿风机股份有限公司 | Linkage control system based on field environment data monitoring |
Citations (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| KR20010001274A (en) * | 1999-06-03 | 2001-01-05 | 박현규 | Internet Image Observation System |
| CN1309482A (en) * | 2000-02-12 | 2001-08-22 | 韩国电气通信公社 | Real time remote-end monitoring system and method using inverse ADSL modem |
| US20040083256A1 (en) * | 2002-10-24 | 2004-04-29 | Icp Electronics Inc. | System and method for real time image transmission monitoring |
-
2004
- 2004-07-30 CN CNB2004100533093A patent/CN100358299C/en not_active Expired - Fee Related
Patent Citations (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| KR20010001274A (en) * | 1999-06-03 | 2001-01-05 | 박현규 | Internet Image Observation System |
| CN1309482A (en) * | 2000-02-12 | 2001-08-22 | 韩国电气通信公社 | Real time remote-end monitoring system and method using inverse ADSL modem |
| US20040083256A1 (en) * | 2002-10-24 | 2004-04-29 | Icp Electronics Inc. | System and method for real time image transmission monitoring |
Also Published As
| Publication number | Publication date |
|---|---|
| CN1588891A (en) | 2005-03-02 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN106600888B (en) | Automatic forest fire detection method and system | |
| CN111928888A (en) | Intelligent monitoring and analyzing method and system for water pollution | |
| CN109951363B (en) | Data processing method, device and system | |
| CN105516652B (en) | A kind of intelligent campus street lamp illumination system | |
| CN108537157A (en) | A kind of video scene judgment method and device based on artificial intelligence classification realization | |
| CN114038012A (en) | Fall detection method and system based on millimeter wave radar and machine learning | |
| CN111476964A (en) | Remote forest fire prevention monitoring system and method | |
| CN116761049B (en) | Household intelligent security monitoring method and system | |
| CN100358299C (en) | Home intelligent image monitor method and system basedon realtime network | |
| CN101764922A (en) | Method and device for adaptive generation of luminance threshold | |
| CN209247120U (en) | Based on balance bell-type pressure sensor water level measurement system | |
| CN112883755A (en) | Smoking and calling detection method based on deep learning and behavior prior | |
| CN116843514B (en) | Property comprehensive management system and method based on data identification | |
| CN103513624A (en) | Intelligent monitoring method and system based on remote controller | |
| CN105450992A (en) | Smart home monitoring method and system based on motion detection | |
| CN102801964A (en) | Intelligent home monitoring method based on motion detection and system thereof | |
| CN111024215A (en) | Noise monitoring method and device, electronic equipment and computer readable storage medium | |
| CN104463114A (en) | Method for catching images and quickly recognizing targets and embedded device | |
| CN115083132B (en) | Research and judgment method for reducing false alarm rate of fire alarm | |
| CN105959184A (en) | Smart indoor air purification system | |
| CN109283907A (en) | Video signal integral electrical production water drainage automatic checkout system and its method | |
| CN115880633A (en) | Sea wave video monitoring system based on AI artificial intelligence | |
| CN202374374U (en) | Shopping mall crowd flow dynamic management system based on remote images | |
| CN202773005U (en) | Intelligent home monitoring system | |
| CN110234088A (en) | A kind of curtain wall monitoring transmission method |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| C06 | Publication | ||
| PB01 | Publication | ||
| C10 | Entry into substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| C14 | Grant of patent or utility model | ||
| GR01 | Patent grant | ||
| C17 | Cessation of patent right | ||
| CF01 | Termination of patent right due to non-payment of annual fee |
Granted publication date: 20071226 Termination date: 20100730 |