CN101854517A - Intelligent monitoring system and method thereof - Google Patents
Intelligent monitoring system and method thereof Download PDFInfo
- Publication number
- CN101854517A CN101854517A CN200910129257A CN200910129257A CN101854517A CN 101854517 A CN101854517 A CN 101854517A CN 200910129257 A CN200910129257 A CN 200910129257A CN 200910129257 A CN200910129257 A CN 200910129257A CN 101854517 A CN101854517 A CN 101854517A
- Authority
- CN
- China
- Prior art keywords
- image
- intelligent method
- intelligent
- original
- supervising
- 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.)
- Pending
Links
Images
Landscapes
- Closed-Circuit Television Systems (AREA)
Abstract
The invention discloses an intelligent monitoring system and a method thereof. An image sensor is utilized to acquire an original image; the original image is adjusted to obtain an adjusted image; an adjusted movement image is detected from the adjusted image; an original movement image in the original image is captured according to positioning information of the adjusted movement image; and finally the original movement image is displayed or stored. In the intelligent monitoring system and the method thereof, the single image sensor is utilized to acquire and retain a high-resolution panoramic image and then additionally generate a low-resolution panoramic image so as to detect, track and position a mobile object. Then the image sensor newly positions at a region on the high-resolution panoramic image so as to obtain the high-resolution image of the mobile object without digital amplification.
Description
Technical field
The present invention relates to a kind of supervisory control system and method thereof, particularly a kind of intelligent monitoring system and method thereof.
Background technology
Recently crime rate constantly raises, and makes people begin to pay attention to saving from damage the importance of mechanism.And save a machine-processed most important part from damage is exactly supervisory control system (surveillance system), and its maximum function is to solve the undermanned problem of dimension peace, makes the user can find the variation of environment things rapidly.One supervisory control system that packages can reach guarantees purpose of safety, reduces the degree of injury and the waste that reduces manpower.
The image dynamic detection technology has the ability of being judged when image changed.If the image dynamic detection technology is applied in digital monitor system or traditional closed-circuit television (Closed Circuit Television, usually abbreviate CCTV as) words on the supervisory control system, can make supervisory control system judge that picture just starts recording function when changing, therefore can save the storage area of image.Also can produce simultaneously warning message and remind and save personnel from damage and note, in real time the generation incident be handled, reach the purpose of monitoring automation.
Resolution sizes be meant picture imaging pixel what.Please refer to Fig. 2 (a), it is depicted as an object.Please refer to Fig. 2 (b), after its this object that is depicted as this Fig. 2 (a) is taken through a low resolution video camera, the result after the amplification octuple.Please refer to Fig. 2 (c), the result after its this object that is depicted as this Fig. 2 (a) is taken through a high resolution camera.That can understand finds out, the imaging size will be different when taking same target with the different resolution video camera.If when going to change the imaging size of the captured image of low resolution in numeral amplification mode, have the problem of fuzzy distortion, therefore can't be applied in the security monitoring.
For addressing the above problem, the user can use two equal resolution video cameras traditionally.Wherein a video camera (panoramic camera, panorama camera) maintains static, and is responsible for supervising panorama, to set up the background of guarded region.Via obtaining mobile object's position behind present image and the background subtracting, panoramic camera reinforms another and has that broad visual angle is selected and PTZ (Pan-Tile-Zoom) video camera that can adjust zooming parameter carries out mobile object tracing, accurately locatees and carries out image and amplify.So just can obtain the high definition image of mobile object.
The video camera of may command camera lens is called the PTZ video camera, is called quick ball-type (Speed Dome) video camera again.The PTZ video camera is to use the motor driven board to rotate and camera lens stretches reaches required moving and amplification effect.Yet the process of capture often is activated and the restriction of mechanical structure, and its machinery itself also can be because of long-time monitoring loss easily.Moreover the autozoom function of PTZ video camera also can influence the video camera capture time, and enlargement ratio is followed the trail of mobile object when too high and exceeded the camera lens scope easily and cause problems such as erroneous judgement.
Summary of the invention
For improving the shortcoming of above-mentioned prior art, a purpose of the present invention is to provide a kind of intelligent monitoring system.
For improving the shortcoming of above-mentioned prior art, another purpose of the present invention is to provide a kind of intelligent method for supervising.
For reaching a purpose of the invention described above, intelligent monitoring system of the present invention comprises: an image sensor, a data scratch-pad memory, a digitized video processor and a program internal memory.This digitized video processor is electrically connected to this image sensor, this data scratch-pad memory and this program internal memory.Wherein this image sensor is sent to this digitized video processor after capturing a raw video.This digitized video processor is adjusted this raw video, adjusts image to obtain one.This digitized video processor detects one in this adjustment image and adjusts motion image.This digitized video processor is adjusted the locating information of motion image according to this, grasps the original movement image in this raw video.
For reaching the another purpose of the invention described above, intelligent method for supervising of the present invention is to utilize an image sensor to capture a raw video.This raw video is adjusted, adjusted image to obtain one.Detect one in this adjustment image and adjust motion image.Adjust the locating information of motion image according to this, grasp the original movement image in this raw video.Effect of the present invention is that intelligent monitoring system of the present invention and method thereof are in conjunction with the digitized video treatment technology, can replace the PTZ video camera, the technology that reaches identical benefit even surpass.Can carry out identification and tracking at the personnel of special scenes, send alert news in real time, so that the related personnel can be handled immediately.And with monitoring scene, personnel movement feature, with fixed area supervision etc. all the video recording build files be stored in database, use as the research of successor retrieval.
Describe the present invention below in conjunction with the drawings and specific embodiments, but not as a limitation of the invention.
Description of drawings
Fig. 1 is an intelligent monitoring system calcspar of the present invention;
Fig. 2 (a) is an object schematic diagram;
Fig. 2 (b) is that a low resolution video camera is taken back amplification octuple striograph;
Fig. 2 (c) is that a high resolution camera is taken the back striograph;
Fig. 3 detects the schematic diagram that one in this adjustment image adjusted the motion image method;
Fig. 4 should adjust the flow chart of motion image for repairing and labelization;
Fig. 5 is 3x3 shielding construction figure;
Fig. 6 is 3x1 shielding construction figure;
Fig. 7 (a) is for originally being full of the striograph of noise;
Fig. 7 (b) is for eliminating the striograph of noise through corroding the back;
Fig. 8 is through the image sequence chart after the triple-expansion;
Fig. 9 is eight connection schematic diagrames;
Figure 10 is a label object schematic diagram;
Figure 11 is image output example figure of the present invention;
Figure 12 is an intelligent method for supervising flow chart of the present invention;
Figure 13 is for expanding (Dilation) and corroding (Erosion) calculation example figure;
Figure 14 is for expanding (Dilation) and corroding (Erosion) scanning schematic diagram;
Figure 15 is a schematic diagram after (Dilation) calculation of expanding;
Figure 16 is a schematic diagram after corroding (Erosion) calculation.
Wherein, Reference numeral
Image A1
Shielding B1
Data scratch-pad memory 20
Digitized video processor 30
Program internal memory 40
The present frame grey-tone image is denoted as M2
The former frame grey-tone image is denoted as M1
The first two frame grey-tone image is denoted as M0
The fixed background imaging marker is M3
The first binaryzation image M5
The second binaryzation image M4
The 3rd binaryzation image M7
The 4th binaryzation image M6
The 5th binaryzation image M8
Step S10～S40
First moves object Ma
Second moves object Mb
The user sets guarded region A1
Step S100～S700
Embodiment
Below in conjunction with accompanying drawing structural principle of the present invention and operation principle are done concrete description:
Intelligent monitoring system of the present invention and method thereof are in conjunction with the digitized video treatment technology, can replace the PTZ video camera, the technology that reaches identical benefit even surpass.Can carry out identification and tracking at the personnel of special scenes, send alert news in real time, so that the related personnel can be handled immediately.And with monitoring scene, personnel movement feature, with fixed area supervision etc. all the video recording build files be stored in database, use as the research of successor retrieval.
Intelligent monitoring system of the present invention and method thereof are to utilize the low resolution panorama to carry out object tracing, obtain the tracked object image of high definition from high resolution pictures again, to replace conventional P TZ camera application in intelligent monitoring system.At first keep the high-resolution panorama and produce the low resolution panorama in addition, to carry out intelligent mobile object detection and tracing and positioning, re-position at the zone on the former high-resolution panorama again, and digital zooming moves the object picture automatically.Intelligent monitoring system of the present invention and method thereof can effectively solve the tracking dead angle and the delay issue of conventional P TZ video camera, also can follow the trail of many objects simultaneously, and exempt mechanical wear and the long influence that causes of reaction time that rotating mechanism caused, to build the intelligent real-time no worker monitor of the cover system of putting.
Please refer to Fig. 1, it is an intelligent monitoring system calcspar of the present invention.Intelligent monitoring system of the present invention comprises: an image sensor 10, a data scratch-pad memory 20, a digitized video processor 30, a program internal memory 40 and an image output device 50.This digitized video processor 30 is electrically connected to this image sensor 10, this data scratch-pad memory 20, this program internal memory 40 and this image output device 50.
Wherein be sent to this digitized video processor 30 behind these image sensor 10 acquisition one raw videos (not icon).30 pairs of these raw videos of this digitized video processor are adjusted, and adjust image (not icon) to obtain one.This digitized video processor 30 is looked demand and is rebuild background.This digitized video processor 30 detects one in this adjustment image and adjusts motion image (not icon).This digitized video processor 30 is looked demand and is repaired and this adjustment motion image of labelization, to obtain a label image (not icon).This digitized video processor 30 grasps the original movement image (not icon) in this raw video according to the locating information of this label image; If this adjustment motion image does not need to be repaired and labelization by this digitized video processor 30, then this digitized video processor 30 is the locating information according to this adjustment motion image, grasps the original movement image in this raw video.Utilize these image output device 50 demonstrations at last or store this original movement image.Wherein this image sensor 10 is to be the fixed video camera of a high-resolution; This image output device 50 is a display or a recording apparatus.The detailed operation of intelligent monitoring system of the present invention will cooperate flowchart text later.
30 pairs of these raw video adjustment of this digitized video processor are to comprise: adjust this raw video and be of a size of a preliminary dimension, this raw video is carried out color conversion and filtering point-like noise.At first keep panorama high resolution pictures (i.e. this raw video), dwindle resolution (for example to 320 * 240 pixels) more separately to reduce data operation quantity.The high resolution image data volume is huge, is example with 5,000,000 pixel video cameras, and the original resolution of each image is 2560 * 1920 pixels, and is full-color 24bit RGB image.Therefore data calculation amount is excessive in the image processing, is applied to can cause the reaction time long in the monitoring in real time.So according to an example of the present invention, the resolution that can reduce panorama high resolution pictures (i.e. this raw video) is 320 * 240 pixels.And full-color 24bit RGB picture reduced to GTG 8bit Gray Level picture, to reduce data operation quantity.Last filtering noise can be reached by image low pass filter (Image Low Pass Filter).
Wherein, so-called background is the minimum part of continuous image difference.Because software program might exist mobile object when starting, or influence such as shadow at sunshine is arranged in the environment, cause the background video obtained and imperfect, just must rebuild background this moment.After static a period of time of the imperfect part of background, background can be rebulid back.After finding that background and continuous image difference surpass to a certain degree, just must restart the background re-establishment mechanism, avoid influencing the subsequent movement object detection.
This digitized video processor 30 is to utilize a fixed background image and continuous three framing control images to detect the interior adjustment motion image of this adjustment image, and details are as follows now.It is to utilize continuous three images to cooperate the fixed background of previous foundation and calculate real mobile object.Please refer to Fig. 3, it is to adjust the schematic diagram of motion image method for detecting one in this adjustment image.Wherein, a present frame grey-tone image is denoted as M2; One former frame grey-tone image is denoted as M1; One the first two frame grey-tone image is denoted as M0; One fixed background imaging marker is M3.And set a binaryzation image threshold value, in order to become the foundation of binaryzation image (binary image) as those grey-tone images of conversion.At first, this present frame grey-tone image M2 and this former frame grey-tone image M1 are done mutual exclusion or (XOR) computing, obtain one first grey-tone image (not icon).Then, more relatively: if the pixel of this first grey-tone image then is made as bright spot more than or equal to this binaryzation image threshold value with the pixel of this first grey-tone image and this binaryzation image threshold value; If the pixel of this first grey-tone image then is made as dim spot less than this binaryzation image threshold value, can obtain one first binaryzation image M5 for this reason.
Similarly, this former frame grey-tone image M1 and this first two frame grey-tone image M0 are done mutual exclusion or (XOR) computing, and obtain one second grey-tone image (not icon), and compare with this binaryzation image threshold value again, and obtain one second binaryzation image M4.With this first binaryzation image M5 and this second binaryzation image M4 (AND) computing of occuring simultaneously, can obtain one the 3rd binaryzation image M7 of mobile target edgesization.Moreover, this former frame grey-tone image M1 and this fixed background image M3 do the image additive operation, and obtain one the 4th grey-tone image (not icon), and again with this binaryzation image threshold value relatively, can obtain one the 4th binaryzation image M6 with the prospect object of background separation.At last, the 3rd binaryzation image M7 and the 4th binaryzation image M6 are joined collection (OR) computing, can obtain one the 5th binaryzation image M8 (i.e. this adjustment motion image) of complete mobile object.
Above-mentioned this digitized video processor 30 hereinafter will be described in detail in detail repair and this adjustment motion image of labelization, to obtain a label image flow process.Please refer to Fig. 4, it is the flow chart for repairing and this adjustment motion image of labelization.At first step S10 and S20 because the 5th binaryzation image M8 still has a fragmentation, carry out the image repairing so must utilize the expansion (Dilation) of image processing kenel and corrode (Erosion).
Expansion (Dilation) is the most basic computing on the morphology.Suppose in the plane image A1 and shielding (Mask) B1 are arranged, as shown in figure 13.Then the expansion of this image A1 and this shielding B1 calculation is defined as: this shielding B1 along this image A1 from top to bottom, scanning (as shown in figure 14) from left to right, if the value of any its binaryzation of pixel is arranged in this shielding B1 scope (oblique line) is 1 o'clock (this image A1 internal oblique line part), then central point in the shielding of this image A1 is set at 1, otherwise is 0.This image A1 expands the back result as shown in figure 15 through this shielding B1.Zone after wherein expanding is the part that is denoted as X.
Corroding (Erosion) is morphologic another kind of computing.Suppose in the plane image A1 and shielding (Mask) B1 are arranged, as shown in figure 13.Then the erosion of this image A1 and this shielding B1 calculation is defined as: when this shielding B1 along this image A1 from top to bottom, when scanning from left to right (as shown in figure 14), if the value of any its binaryzation of pixel is arranged in this shielding B1 scope (oblique line) is 0 o'clock (non-oblique line part in this image A1), then central point in the shielding of this image A1 is set at 0, otherwise is 1.This image A1 corrodes the back result as shown in figure 16 through this shielding B1.Zone after wherein corroding is the part that is denoted as X.
Consider that supervisory control system is based on guarder's class behavior, be different from general kenel expansion (Dilation) and corrode (Erosion) with 3 * 3,5 * 5 shielding foundation structures that method of the present invention adopts Fig. 5,3x3 shielding construction (Mask) corrodes calculation; Adopt Fig. 6,3x1 shielding construction calculation of expanding.At first through the erosion (Erosion) of one time 3 * 3 formula, its purpose is for eliminating the noise that complex background left behind.For example Fig. 7 (a) is depicted as the image that is full of noise originally; Fig. 7 (b) is through the image behind erosion (Erosion) the back elimination noise of one time 3 * 3 formula.Then, do the expansion (Dilation) of three times 3 * 1 formulas for personnel's block combinations such as the head that may separate, trunk, pin, must mobile to the end object than complete image, as shown in Figure 8.
Follow step S30 and S40, because mobile object more than two might occur, so must calculate mobile object number in the label mode.Being communicated with mark (Connected Components Labeling) main purpose is that contiguous some clustering is become identical numbering, to calculate colony's number, is mobile object number in the present invention.Figure 9 shows that eight are communicated with (8-adjacent) schematic diagram.According to eight rules that are communicated with, right by a left side, from top to bottom scan the binaryzation image, be the value of all adjacent binaryzations that 1 pixel gives an identical and unique label symbol, reach the purpose of calculating mobile number of objects by the label symbol quantity.(wherein the right figure of Figure 10 more can know after line and sees and provide three mobile objects, that is be respectively to be given the label symbol be 1,2,3 mobile object) as shown in figure 10.Can obtain aforesaid those label images at this.
Then, this digitized video processor 30 is grabbed out a original movement image in this raw video according to the locating information of this label image.By above-mentioned label process, can learn start position and the most last some position of object, calculate object size and object in the picture relative position.The information that is located again reaches former high resolution pictures (i.e. this raw video), to present the former figure size of object (i.e. this original movement image) at this image output device 50, must not amplify the amplification effect that promptly reaches numeral.
Intelligent monitoring system of the present invention is demonstration at last or stores this original movement image.Please refer to Figure 11, it is to be image output example figure of the present invention.Figure 11 upper left corner is depicted as panorama 320 * 240 pixels (being this adjustment image that 2560 * 1920 pixels are reduced to 320 * 240 pixels from original resolution for example promptly), comprises one first and moves that object Ma, one second moves object Mb and a user sets guarded region A1 (detailed description that the user can order guarded region certainly is detailed later).With this that is captured under 320 * 240 pixels of panorama shown in Figure 11 upper left corner first move object Ma, this second moves object Mb and this user sets guarded region A1, corresponding to the former resolution picture of this image sensor 10 (i.e. this raw video, 2560 * 1920 pixels for example) position and size present with 320 * 240 pixel size scopes that on the former resolution picture this first moves object Ma, this second moves object Mb and this user sets guarded region A1.For example, second to move object Mb be 10 * 20 pixels in the size of Figure 11 upper left corner sprite for this, with 5,000,000 pixels (i.e. 2560 * 1920 pixels) fixedly video camera build and deposit, the meeting that is presented at lower left corner sprite is 80 * 160 pixels.Do not carrying out under the situation of convergent-divergent, promptly reaching the multiplication factor (shown in Figure 11 lower left corner) of wide, high each octuple.Equal to save from damage personnel and handle a PTZ video camera, move the effect of object with the real-time manual trace of wide, high each octuple enlargement ratio.In addition, if the mobile object of following the trail of surpasses 320 * 240 pixels with respect to the size of the former resolution picture of video camera or during less than 320 * 240 pixels, will do automatic digital zooming to suitable size with image processing.For example this first to move the size of object Ma in Figure 11 upper left corner be the circle of 50 * 50 pixels, be 400 * 400 pixels with respect to former resolution picture, presenting object with 320 * 240 pixel pictures can appearance, so automatic digital zooming is adjusted.At last, with the picture video recording deposit record of this 640 * 480 pixel, put to reach building of intelligent unmanned real-time monitoring system.
Intelligent monitoring system of the present invention is except that doing the intelligent tracing monitoring at mobile object, and the user is the scene of frame choosing (and can order scaling certainly) desire monitoring, for example gateway or non-smoking area or the like voluntarily also.At first the user adjusts the image setting guarded region at this.Then this digitized video processor 30 grasps the original guarded region image in this raw video according to the locating information of this guarded region.Utilize this image output device 50 to show or this original guarded region image of storage at last.
Please refer to Figure 12, it is to be intelligent method for supervising flow chart of the present invention.At first step S100 utilizes an image sensor to capture a raw video.Then step S200 adjusts this raw video, adjusts image to obtain one.The step S300 demand of looking is rebuild background then.The step S400 that continues detects one in this adjustment image and adjusts motion image.Then the step S500 demand of looking is repaired and this adjustment motion image of labelization, to obtain a label image.Step S600 is according to the locating information of this label image then, the original movement image of extracting in this raw video be not (if this adjustment motion image needs to be repaired and labelization, then this step S600 is the locating information according to this adjustment motion image, grasps the original movement image in this raw video).Final step S700 shows or stores this original movement image.Wherein this image sensor is to be the fixed video camera of a high-resolution; This image output device is a display or a recording apparatus.
Wherein step S200 (this raw video is adjusted) is to comprise: adjust this raw video and be of a size of a preliminary dimension, this raw video is carried out color conversion and filtering point-like noise.At first keep panorama high resolution pictures (i.e. this raw video), dwindle resolution (for example to 320 * 240 pixels) more separately to reduce data operation quantity.According to an example of the present invention, the resolution that can reduce panorama high resolution pictures (i.e. this raw video) is 320 * 240 pixels.And full-color 24bit RGB picture reduced to GTG 8bit Gray Level picture, to reduce data operation quantity.Last filtering noise can be reached by image low pass filter (Image Low Pass Filter).
Wherein step S400 (detect one in this adjustment image and adjust motion image) is to utilize a fixed background image and continuous three framing control images to detect the interior adjustment motion image of this adjustment image.Its flow process is identical with the content of aforementioned intelligent monitoring system of the present invention, so repeat no more in this.
Wherein step S500 (repairing and labelization should be adjusted motion image, to obtain a label image flow process) utilizes the calculation technology of the erosion (once corroding with the 3x3 shielding construction) of digitized video processing and expand (carrying out triple-expansion with the 3x1 shielding construction) to repair this adjustment motion image.And because mobile object more than two might occur, so must calculate mobile object number in the label mode.
Intelligent method for supervising of the present invention is except that doing the intelligent tracing monitoring at mobile object, and the user is the scene of frame choosing (and can order scaling certainly) desire monitoring, for example gateway or non-smoking area or the like voluntarily also.At first the user adjusts the image setting guarded region at this.Then, grasp the original guarded region image in this raw video according to the locating information of this guarded region.Show at last or this original guarded region image of storage.
Intelligent monitoring system of the present invention and method thereof have following characteristics:
1, be example with 5,000,000 pixel video cameras, full-color 2560 * 1920 pixels of videorama, consume system resources and to occupy storage capacity very huge, picture is 640 * 480 pixels and the present invention records a video, the storage capacity that only needs former resolution ten sixths, can do high definition and present from ordering the zone mobile object and user, reach the highest benefit.
2, can replace the PTZ video camera, release mechanism, nothing monitor that dead angle, nothing move delay and tool detects mobile object ability more than two simultaneously.
3, can replace a low resolution video camera with a fixed high resolution camera and add a low resolution PTZ video camera, reduce the manpower and materials cost, promote quality of life, home safety greatly, make the various environment that are applied in that supervisory control system can be more effective and general.
4, the present invention has easy extendibility, easy conformability, product generality, low-cost and high-quality, maneuverable advantage, and the layman all can operate.
Certainly; the present invention also can have other various embodiments; under the situation that does not deviate from spirit of the present invention and essence thereof; those of ordinary skill in the art work as can make various corresponding changes and distortion according to the present invention, but these corresponding changes and distortion all should belong to the protection range of the appended claim of the present invention.
Claims (18)
1. an intelligent monitoring system is characterized in that, comprises:
One image sensor;
One digitized video processor is electrically connected to this image sensor;
One data scratch-pad memory is electrically connected to this digitized video processor; And
One program internal memory is electrically connected to this digitized video processor,
Wherein this image sensor is sent to this digitized video processor after capturing a raw video;
This digitized video processor is adjusted this raw video, adjusts image to obtain one;
This digitized video processor detects one in this adjustment image and adjusts motion image; And
This digitized video processor is adjusted the locating information of motion image according to this, grasps the original movement image in this raw video.
2. intelligent monitoring system according to claim 1 is characterized in that, also comprises an image output device, is electrically connected to this digitized video processor, to show or to store this original movement image.
3. intelligent monitoring system according to claim 1 is characterized in that, this image sensor is the fixed video camera of a high-resolution.
4. intelligent monitoring system according to claim 2 is characterized in that, this image output device is a display or a recording apparatus.
5. an intelligent method for supervising is characterized in that, comprises step:
A. utilize an image sensor to capture a raw video;
B. this raw video is adjusted, adjusted image to obtain one;
C. detect one in this adjustment image and adjust motion image; And
D. adjust the locating information of motion image according to this, grasp the original movement image in this raw video.
6. intelligent method for supervising according to claim 5 is characterized in that, also comprises a step e 1 after this step D: show this original movement image.
7. intelligent method for supervising according to claim 5 is characterized in that, also comprises a step e 2 after this step D: store this original movement image.
8. intelligent method for supervising according to claim 5 is characterized in that, this step B comprises:
B1. adjust this raw video and be of a size of a preliminary dimension;
B2. this raw video is carried out color conversion; And
B3. filtering point-like noise.
9. intelligent method for supervising according to claim 8 is characterized in that, the described preliminary dimension of this step b1 is the 320x240 pixel.
10. intelligent method for supervising according to claim 8 is characterized in that, this step b2 reduces to GTG 8bit Gray Level by full-color 24bit RGB.
11. intelligent method for supervising according to claim 8 is characterized in that, this step b3 is for passing through image low pass filter filters out point-like noise.
12. intelligent method for supervising according to claim 5 is characterized in that, this step C utilizes a fixed background image and continuous three framing control images to detect the interior adjustment motion image of this adjustment image.
13. intelligent method for supervising according to claim 5 is characterized in that, also comprises after this step C:
C1. repairing and labelization should be adjusted motion image, to obtain a label image;
C2. according to the locating information of this label image, grasp the original movement image in this raw video; And
C3. show this original movement image.
14. intelligent method for supervising according to claim 13 is characterized in that, also comprises:
C4. store this original movement image.
15. intelligent method for supervising according to claim 13 is characterized in that, this step C1 utilizes the erosion of digitized video processing and the calculation technology of expansion to repair this adjustment motion image.
16. intelligent method for supervising according to claim 15 is characterized in that, is once to corrode calculation with the 3x3 shielding construction, and carries out the triple-expansion calculation with the 3x1 shielding construction.
17. intelligent method for supervising according to claim 5 is characterized in that, also comprises the following step after this step B:
B1. adjust the image setting guarded region at this;
B2. according to the locating information of this guarded region, grasp the original guarded region image in this raw video; And
B3. show this original guarded region image.
18. intelligent method for supervising according to claim 17 is characterized in that, also comprises:
B4. store this original guarded region image.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN200910129257A CN101854517A (en) | 2009-04-03 | 2009-04-03 | Intelligent monitoring system and method thereof |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN200910129257A CN101854517A (en) | 2009-04-03 | 2009-04-03 | Intelligent monitoring system and method thereof |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN101854517A true CN101854517A (en) | 2010-10-06 |
Family
ID=42805745
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN200910129257A Pending CN101854517A (en) | 2009-04-03 | 2009-04-03 | Intelligent monitoring system and method thereof |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN101854517A (en) |
Cited By (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN103454228A (en) * | 2013-09-16 | 2013-12-18 | 北京首钢自动化信息技术有限公司 | Smoke blackness monitoring system adopting motion monitoring technology |
| CN105491353A (en) * | 2016-01-15 | 2016-04-13 | 广东小天才科技有限公司 | Remote monitoring method and device |
-
2009
- 2009-04-03 CN CN200910129257A patent/CN101854517A/en active Pending
Cited By (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN103454228A (en) * | 2013-09-16 | 2013-12-18 | 北京首钢自动化信息技术有限公司 | Smoke blackness monitoring system adopting motion monitoring technology |
| CN103454228B (en) * | 2013-09-16 | 2015-07-29 | 北京首钢自动化信息技术有限公司 | Adopt the flue gas blackness supervisory system of motion detecting technology |
| CN105491353A (en) * | 2016-01-15 | 2016-04-13 | 广东小天才科技有限公司 | Remote monitoring method and device |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN111191576B (en) | Personnel behavior target detection model construction method, intelligent analysis method and system | |
| CN201248107Y (en) | Master-slave camera intelligent video monitoring system | |
| CN111242025B (en) | Real-time action monitoring method based on YOLO | |
| CN103929592A (en) | All-dimensional intelligent monitoring equipment and method | |
| CN104754302A (en) | Target detecting tracking method based on gun and bullet linkage system | |
| CN101123722A (en) | Panorama video intelligent monitoring method and system | |
| CN100551046C (en) | The method and apparatus of information processing | |
| CN101924923B (en) | Embedded intelligent automatic zooming snapping system and method thereof | |
| JP2010009134A (en) | Image processing system, image processing method, and program | |
| WO2020057353A1 (en) | Object tracking method based on high-speed ball, monitoring server, and video monitoring system | |
| CN107509055A (en) | A kind of rotary panorama focus identification optronic tracker and its implementation | |
| CN1980384A (en) | Space mobile-object locking aim-searching device and method | |
| US20100302367A1 (en) | Intelligent surveillance system and method for the same | |
| CN206389471U (en) | A kind of overall view monitoring early warning system | |
| JP3486229B2 (en) | Image change detection device | |
| CN115527158A (en) | Method and device for detecting abnormal behaviors of personnel based on video monitoring | |
| CN102291568A (en) | Accelerated processing method of large-view-field intelligent video monitoring system | |
| CN202231803U (en) | Intelligent monitoring system for multi-aspect video object tracking detection | |
| CN101854517A (en) | Intelligent monitoring system and method thereof | |
| TWI389060B (en) | Intelligent surveillance system and method for the same | |
| CN111669547B (en) | Panoramic video structuring method | |
| CN112633157A (en) | AGV working area safety real-time detection method and system | |
| US20120075467A1 (en) | Image capture device and method for tracking moving object using the same | |
| EP2254097A1 (en) | Intelligent surveillance system and method for the same | |
| CN115100245A (en) | High-altitude parabola-based tracing system and tracing method thereof |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| C06 | Publication | ||
| PB01 | Publication | ||
| C10 | Entry into substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| C02 | Deemed withdrawal of patent application after publication (patent law 2001) | ||
| WD01 | Invention patent application deemed withdrawn after publication |
Open date: 20101006 |