CN108460357A - A kind of windowing alarm detection system and method based on image recognition - Google Patents
A kind of windowing alarm detection system and method based on image recognition Download PDFInfo
- Publication number
- CN108460357A CN108460357A CN201810209075.9A CN201810209075A CN108460357A CN 108460357 A CN108460357 A CN 108460357A CN 201810209075 A CN201810209075 A CN 201810209075A CN 108460357 A CN108460357 A CN 108460357A
- Authority
- CN
- China
- Prior art keywords
- windowing
- image
- alarm detection
- image recognition
- pixel
- 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.)
- Granted
Links
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V20/00—Scenes; Scene-specific elements
- G06V20/50—Context or environment of the image
- G06V20/52—Surveillance or monitoring of activities, e.g. for recognising suspicious objects
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V10/00—Arrangements for image or video recognition or understanding
- G06V10/20—Image preprocessing
- G06V10/255—Detecting or recognising potential candidate objects based on visual cues, e.g. shapes
-
- G—PHYSICS
- G08—SIGNALLING
- G08B—SIGNALLING OR CALLING SYSTEMS; ORDER TELEGRAPHS; ALARM SYSTEMS
- G08B5/00—Visible signalling systems, e.g. personal calling systems, remote indication of seats occupied
- G08B5/22—Visible signalling systems, e.g. personal calling systems, remote indication of seats occupied using electric transmission; using electromagnetic transmission
Landscapes
- Physics & Mathematics (AREA)
- Engineering & Computer Science (AREA)
- General Physics & Mathematics (AREA)
- Multimedia (AREA)
- Theoretical Computer Science (AREA)
- Electromagnetism (AREA)
- Alarm Systems (AREA)
- Image Analysis (AREA)
- Closed-Circuit Television Systems (AREA)
Abstract
The present invention relates to a kind of windowing alarm detection system and method based on image recognition, wherein system include:Image capture module, for acquiring the video image for including window;Image pre-processing module switchs to HSI images for carrying out color space conversion to the video image by RGB;Open a window detection module, for determining windowing alert locations according to the luminance component image data in HSI images;Display control module, for showing windowing alert locations.The present invention by the video image of acquisition by being first converted to HSI images, and the luminance component image data in HSI images is identified, it can realize that the detection to building windowing behavior is positioned with alarm, realizes the effective monitoring to key area Adjacent Buildings and danger early warning.
Description
Technical field
The present invention relates to computer picture detection field more particularly to a kind of windowing alarm detection systems based on image recognition
System and method.
Background technology
Increasingly mature with Video Supervision Technique, occasion security on-site supervision is presented that monitoring point is more, distribution is wide, shows
The feature of the multiple security units in field and mobile personnel's contact complexity.Wherein, site of activity is to its ambient outdoor outside vertical surface of building
Monitoring it is particularly important, monitoring and the timely processing of the hazardous acts such as object especially are thrown to windowing, have become security work urgency
It need to solve the problems, such as.
It would therefore be highly desirable to develop a kind of system and method that can be quickly detected to windowing behavior and position.
Invention content
The technical problem to be solved in the present invention is, for the defect above in the prior art, provides a kind of based on image
The windowing alarm detection system and method for identification.
In order to solve the above technical problem, the present invention provides a kind of windowing alarm detection system based on image recognition,
Including:
Image capture module, for acquiring the video image for including window;
Image pre-processing module switchs to HSI images for carrying out color space conversion to the video image by RGB;
Open a window detection module, for determining windowing alert locations according to the luminance component image data in HSI images;
Display control module, for showing windowing alert locations.
In the windowing alarm detection system according to the present invention based on image recognition, the windowing detection module packet
It includes:
Foreground extraction unit for judging that pixel belongs to background or foreground, and extracts the length and width of foreground area;
Size judging unit is to be judged as windowing row for judging whether the size of foreground area meets preset range
For.
In the windowing alarm detection system according to the present invention based on image recognition, it is preferable that the display control mould
Block is additionally operable to the long L of pixel of input image to be detected0With wide W0To the size judging unit.
In the windowing alarm detection system according to the present invention based on image recognition, it is preferable that the display control mould
Block is additionally operable to receive the floor information of the video image of user annotation, and generates the parameter coordinate information of floor;The windowing inspection
It further includes floor determination unit to survey module, for determining windowing floor according to the parameter coordinate information of windowing alert locations and floor
Information;The display control module is additionally operable to show the windowing floor information.
In the windowing alarm detection system according to the present invention based on image recognition, it is preferable that the windowing alarm inspection
Examining system further includes alarm module, for being alarmed according to the windowing behavioral value result of windowing detection module.
The present invention also provides a kind of windowing alarm detection system based on image recognition, including:
Camera, for acquiring the video image for including window;
Comprehensive display control device switchs to HSI images, then root for carrying out color space conversion to the video image by RGB
Windowing alert locations are determined according to the luminance component image data in HSI images, and windowing alert locations are shown to user.
The present invention also provides a kind of windowing alarm detection procedure based on image recognition, includes the following steps:
Acquisition includes the video image of window;
Color space conversion is carried out to the video image, HSI images are switched to by RGB;
Windowing alert locations are determined according to the luminance component image data in HSI images;
Display windowing alert locations.
In the windowing alarm detection procedure according to the present invention based on image recognition, in the image according to HSI
Luminance component image data determine windowing alert locations include:
Foreground extraction sub-step judges that pixel belongs to background or foreground, and extracts the length and width of foreground area;
Size judges sub-step, judges whether the size of foreground area meets preset range, is to be judged as windowing behavior.
In the windowing alarm detection procedure according to the present invention based on image recognition, it is preferable that the method further includes:
Input the long L of pixel of image to be detected0With wide W0Supply size judges sub-step.
In the windowing alarm detection procedure according to the present invention based on image recognition, it is preferable that the method further includes:
The floor information of the video image of user annotation is received, and generates the parameter coordinate information of floor;According to windowing alert locations and
The parameter coordinate information of floor determines windowing floor information;Show the windowing floor information.
The windowing alarm detection system and method based on image recognition for implementing the present invention, have the advantages that:This
Invention knows the luminance component image data in HSI images by the way that the video image of acquisition is first converted to HSI images
Not, to determine the alert locations that open a window, it can realize that the detection to building windowing behavior is positioned with alarm, is realized to key area
The effective monitoring of Adjacent Buildings and danger early warning.
Description of the drawings
Fig. 1 is the module frame chart according to the windowing alarm detection system based on image recognition of the preferred embodiment of the present invention;
Fig. 2 is according to windowing detection mould in the windowing alarm detection system based on image recognition of the preferred embodiment of the present invention
The block diagram of block;
Fig. 3 is the windowing alarm detection surface chart based on image recognition according to the preferred embodiment of the present invention;
Fig. 4 is the windowing alarming result display interface figure based on image recognition according to the preferred embodiment of the present invention;
Fig. 5 is the hardware structure diagram according to the windowing alarm detection system based on image recognition of the present invention;
Fig. 6 is the flow chart according to the windowing alarm detection procedure based on image recognition of the preferred embodiment of the present invention.
Specific implementation mode
In order to make the object, technical scheme and advantages of the embodiment of the invention clearer, below in conjunction with the embodiment of the present invention
In attached drawing, technical scheme in the embodiment of the invention is clearly and completely described, it is clear that described embodiment is
A part of the embodiment of the present invention, instead of all the embodiments.Based on the embodiments of the present invention, ordinary skill people
The every other embodiment that member is obtained without making creative work, shall fall within the protection scope of the present invention.
Referring to Fig. 1, for according to the mould of the windowing alarm detection system based on image recognition of the preferred embodiment of the present invention
Block block diagram.As shown in Figure 1, the system that the embodiment provides includes:Image capture module 101, is opened image pre-processing module 102
Window detection module 103 and display control module 104.
Image capture module 101 is for acquiring the video image for including window.
Image pre-processing module 102 is used to carry out color space conversion to the video image, switchs to H (tone) S by RGB
(saturation degree) I (brightness) image.And I channel image components are passed into windowing detection module 103.
The detection module 103 that opens a window is used to determine windowing alert locations according to the luminance component image data in HSI images.
Display control module 104 is for showing windowing alert locations.
Referring to Fig. 2, to be opened according in the windowing alarm detection system based on image recognition of the preferred embodiment of the present invention
The block diagram of window detection module.As shown in Figure 2, it is preferable that windowing detection module 103 include:Foreground extraction unit 201 and size are sentenced
Disconnected unit 202.
The detection of windowing alarm is completed by windowing detection module 103, is as follows:Foreground extraction unit
201 are modeled each pixel of image by the superposition of multiple Gaussian Profiles of different weights, each Gaussian Profile corresponds to
One there may be the state of the presented brightness of pixel, the weights and distributed constant of each Gaussian Profile to update at any time.
For the observation data set { x of stochastic variable X1,x2,…,xN, xtFor the luma samples of t moment pixel, 1≤t≤
N, wherein N are the total sample number of the pixel of acquisition;Then single sampled point xtIts Gaussian mixtures probability density letter obeyed
Number:
Wherein k is Gaussian Profile pattern sum, η (xt,μi,t,τi,t) it is i-th of Gaussian Profile of t moment, μi,tFor it
Value, τi,tFor its covariance matrix, δi,tFor variance, I is unit matrix, ωi,tFor the weight of i-th of Gaussian Profile of t moment.
Foreground extraction unit 201 is used to pass through following formula (4) by each new pixel value xtAs the following formula with current k model
It is compared, to judge that pixel belongs to background or foreground:
|xt-μi,t-1|≤2.5δi,t-1 (4)
Wherein xtFor the luma samples of t moment pixel, { x1,x2,…,xN, μi,t-1For i-th of Gaussian Profile of t-1 moment
Mean value, δi,t-1For the variance of i-th of Gaussian Profile of t-1 moment.
When meeting above-mentioned formula (4), which belongs to foreground, and otherwise the pixel belongs to background.Foreground is passed through swollen
The Morphological scale-spaces such as swollen corrosion, extract the length L and width W of foreground area.
Size judging unit 202 is used to by following formula (5) judge whether the size of foreground area meets preset range,
It is to be judged as windowing behavior:
Wherein, L and W is respectively the length and width of extracted foreground area, LcAnd WcRespectively preset length lower limit
Value and width lower limiting value;L0And W0The long L of pixel of respectively preset window image to be detected0With wide W0.Wherein, L can be usedc=
10 and Wc=10, that is, it is noise jamming rather than windowing behavior, length lower limiting value and width lower limiting value to give tacit consent to 10*10 foregrounds below
It can be modified according to detection case.When windowing foreground meets above-mentioned condition, windowing behavior is as detected.
Preferably, display control module 104 is used for the display and control of video image, including cradle head control that may be present
Deng video camera is directed at outside vertical surface of building to be observed by automatic or manual, selects and confirm actual observation range, operates mouse
Actual observation region is drawn, floor information, and the long L of pixel of input window image to be detected are marked in image corresponding position0
With wide W0Deng.The windowing alarm detection interface based on image recognition of the present invention is as shown in Figure 3.Preferably, display control module
104 by the long L of the pixel of image to be detected input by user0With wide W0It is sent to size judging unit 202.
In the preferred embodiment of the present invention, display control module 104 is additionally operable to receive the video figure of user annotation
The floor information of picture, and generate the parameter coordinate information of floor.The detection module 103 that opens a window further includes floor determination unit, is used for
Windowing floor information is determined according to the parameter coordinate information of windowing alert locations and floor.Display control module 104 is additionally operable to show
Show windowing floor information.That is windowing detection module 103 further matches just according to the image coordinate of windowing alert locations
The parameter coordinate information for the floor that beginning is generated by display control module 104 realizes the positioning to floor of alarming.Finally windowing is reported
The image coordinate of alert position passes to display control module 104 with windowing floor information and is shown.As shown in figure 4, by prominent
Go out the wire frame of the color position that will open a window to show in the video image of acquisition, at the same can also by the floor information of windowing with
The forms such as number are shown.
Preferably, windowing alarm detection system of the invention further includes alarm module, for according to windowing detection module
Windowing behavioral value result is alarmed.
Fig. 5 is please referred to, for according to the hardware configuration of the windowing alarm detection system based on image recognition of the present invention
Figure.As shown in figure 5, the windowing alarm detection system based on image recognition of the present invention includes mainly camera 501 and therewith
The synthesis display control device 503 of communication.Preferably, which further includes the network switch 502.
Camera 501 is realized for acquiring the video image for including window for example, by using high-definition camera.The network switch
502 by 501 the image collected of camera by transmission of network summarize to the network switch 502 finally with comprehensive display control device
503 are connected.Image capture module 101 can acquire the video image for including window by the camera 501.
Comprehensive display control device 503 is used to carry out color space conversion to the video image that camera 501 acquires, and is turned by RGB
For HSI images, determines windowing alert locations further according to the luminance component image data in HSI images, windowing alert locations are shown
Show to user.Preferably, the host computer display and control software disposed in comprehensive display control device 3 completes the display and control of video image,
Including cradle head control that may be present etc., video camera is directed at outside vertical surface of building to be observed by automatic or manual, is selected and true
Recognize actual observation range, operation mouse draws actual observation region, and marks floor information, and input in image corresponding position
The long L of pixel of window image to be detected0With wide W0.Aforementioned image pre-processing module 102, windowing detection module 103 and display control
Module 104 can be realized by the synthesis display control device 503.
Referring to Fig. 6, for according to the stream of the windowing alarm detection procedure based on image recognition of the preferred embodiment of the present invention
Cheng Tu.As shown in fig. 6, the method that the embodiment provides includes the following steps:
First, in step sl, acquisition includes the video image of window;
Then, in step s 2, color space conversion is carried out to the video image, HSI images is switched to by RGB;
Then, in step s3, windowing alert locations are determined according to the luminance component image data in HSI images;
Finally, in step s 4, display windowing alert locations.Preferably, with protrusion in the video image of acquired original
The wire frame of color indicates windowing alert locations.
Preferably, determine that windowing alert locations include according to the luminance component image data in HSI images in step S3:
1) foreground extraction sub-step judges that pixel belongs to background or foreground by following formula, and extracts foreground area
Length and width;
|xt-μi,t-1|≤2.5i,t-1
Wherein xtFor the luma samples of t moment pixel, { x1,x2,…,xN, xtFor the luma samples of t moment pixel, 1≤t
≤ N, wherein N are the total sample number of the pixel of acquisition;μi,t-1For the mean value of i-th of Gaussian Profile of t-1 moment, δi,t-1For t-1
The variance of i-th of Gaussian Profile of moment;Wherein, for the observation data set { x of stochastic variable X1,x2,…,xN, xtFor t moment
The luma samples of pixel, then single sampled point xtThe Gaussian mixtures probability density function of obedience is:
Wherein k is Gaussian Profile pattern sum, η (xt,μi,t,τi,t) it is i-th of Gaussian Profile of t moment, μi,tFor it
Value, τi,tFor its covariance matrix, δi,tFor variance, I is unit matrix, ωi,tFor the weight of i-th of Gaussian Profile of t moment;
When meeting above-mentioned formula, which belongs to foreground, and otherwise the pixel belongs to background;
2) size judges sub-step, judges whether the size of foreground area meets preset range by following formula, is then
It is judged as windowing behavior:
Wherein, L and W is respectively the length and width of extracted foreground area, LcAnd WcRespectively preset length lower limit
Value and width lower limiting value;L0And W0The long L of pixel of respectively preset window image to be detected0With wide W0。
Preferably, above-mentioned in the windowing alarm detection procedure based on image recognition, this method further includes:It inputs to be detected
The long L of pixel of image0With wide W0Supply size judges sub-step.
It is highly preferred that this method further includes:It receives the floor information of the video image of user annotation and generates the ginseng of floor
Number coordinate information;Then, windowing floor information is determined according to the parameter coordinate information of windowing alert locations and floor;Show this again
Open a window floor information.
Preferably, the method further includes:It is alarmed according to the windowing behavioral value result of windowing detection module.
In conclusion the present invention is based on high definition video image capture and computer image recognition technology, opened a window by building
Alarm detection system can effectively and accurately detect outside vertical surface of building windowing unusual fluctuation behavior, and this is positioned and is alarmed,
It realizes the effective monitoring to key area Adjacent Buildings and danger early warning, has greatly ensured the security guard work of key activities
Make, saving, police strength etc. contribution is especially prominent.Finally it should be noted that:Above example is only to illustrate the skill of the present invention
Art scheme, rather than its limitations;Although the present invention is described in detail referring to the foregoing embodiments, the common skill of this field
Art personnel should understand that:Its still can with technical scheme described in the above embodiments is modified, or to its middle part
Technical characteristic is divided to carry out equivalent replacement;And these modifications or replacements, the present invention that it does not separate the essence of the corresponding technical solution
The spirit and scope of each embodiment technical solution.
Claims (10)
1. a kind of windowing alarm detection system based on image recognition, which is characterized in that including:
Image capture module, for acquiring the video image for including window;
Image pre-processing module switchs to HSI images for carrying out color space conversion to the video image by RGB;
Open a window detection module, for determining windowing alert locations according to the luminance component image data in HSI images;
Display control module, for showing windowing alert locations.
2. the windowing alarm detection system according to claim 1 based on image recognition, which is characterized in that the windowing inspection
Surveying module includes:
Foreground extraction unit for judging that pixel belongs to background or foreground by following formula, and extracts the length of foreground area
Degree and width;
|xt-μi,t-1|≤2.5δi,t-1
Wherein xtFor the luma samples of t moment pixel, μi,t-1For the mean value of i-th of Gaussian Profile of t-1 moment, δi,t-1For t-1 when
Carve the variance of i-th of Gaussian Profile;Wherein, for the observation data set { x of stochastic variable X1,x2,…,xN, xtFor t moment picture
The luma samples of element, then single sampled point xtThe Gaussian mixtures probability density function of obedience is:
Wherein k is Gaussian Profile pattern sum, η (xt,μi,t,τi,t) it is i-th of Gaussian Profile of t moment, μi,tFor its mean value, τi,t
For its covariance matrix, δi,tFor variance, I is unit matrix, ωi,tFor the weight of i-th of Gaussian Profile of t moment;
When meeting above-mentioned formula, which belongs to foreground, and otherwise the pixel belongs to background;
Size judging unit is to judge for judging whether the size of foreground area meets preset range by following formula
For the behavior that opens a window:
Wherein, L and W is respectively the length and width of extracted foreground area, LcAnd WcRespectively preset length lower limiting value and
Width lower limiting value;L0And W0The long L of pixel of respectively preset window image to be detected0With wide W0。
3. the windowing alarm detection system according to claim 2 based on image recognition, which is characterized in that the display control
Molding block is additionally operable to the long L of pixel of input image to be detected0With wide W0To the size judging unit.
4. the windowing alarm detection system described in any one of claim 1 to 3 based on image recognition, feature exist
In:
The display control module is additionally operable to receive the floor information of the video image of user annotation, and the parameter for generating floor is sat
Mark information;
The windowing detection module further includes floor determination unit, for being believed according to the parameter coordinate of windowing alert locations and floor
Breath determines windowing floor information;
The display control module is additionally operable to show the windowing floor information.
5. the windowing alarm detection system described in any one of claim 1 to 3 based on image recognition, feature exist
In:The windowing alarm detection system further includes alarm module, for the windowing behavioral value result according to windowing detection module
It alarms.
6. a kind of windowing alarm detection system based on image recognition, which is characterized in that including:
Camera, for acquiring the video image for including window;
Comprehensive display control device, for video image progress color space conversion, switching to HSI images by RGB, further according to
Luminance component image data in HSI images determines windowing alert locations, and windowing alert locations are shown to user.
7. a kind of windowing alarm detection procedure based on image recognition, which is characterized in that include the following steps:
Acquisition includes the video image of window;
Color space conversion is carried out to the video image, HSI images are switched to by RGB;
Windowing alert locations are determined according to the luminance component image data in HSI images;
Display windowing alert locations.
8. the windowing alarm detection procedure according to claim 7 based on image recognition, which is characterized in that the basis
Luminance component image data in HSI images determines that windowing alert locations include:
Foreground extraction sub-step judges that pixel belongs to background or foreground by following formula, and extracts the length of foreground area
And width;
|xt-μi,t-1|≤2.5δi,t-1
Wherein xtFor the luma samples of t moment pixel, μi,t-1For the mean value of i-th of Gaussian Profile of t-1 moment, δi,t-1For t-1 when
Carve the variance of i-th of Gaussian Profile;Wherein, for the observation data set { x of stochastic variable X1,x2,…,xN, xtFor t moment picture
The luma samples of element, then single sampled point xtThe Gaussian mixtures probability density function of obedience is:
Wherein k is Gaussian Profile pattern sum, η (xt,μi,t,τi,t) it is i-th of Gaussian Profile of t moment, μi,tFor its mean value, τi,t
For its covariance matrix, δi,tFor variance, I is unit matrix, ωi,tFor the weight of i-th of Gaussian Profile of t moment;
When meeting above-mentioned formula, which belongs to foreground, and otherwise the pixel belongs to background;
Size judges sub-step, judges whether the size of foreground area meets preset range by following formula, is to be judged as
Windowing behavior:
Wherein, L and W is respectively the length and width of extracted foreground area, LcAnd WcRespectively preset length lower limiting value and
Width lower limiting value;L0And W0The long L of pixel of respectively preset window image to be detected0With wide W0。
9. the windowing alarm detection procedure according to claim 8 based on image recognition, which is characterized in that the method is also
Including:Input the long L of pixel of image to be detected0With wide W0Supply size judges sub-step.
10. the windowing alarm detection procedure based on image recognition according to any one of claim 7~9, feature exist
In the method further includes:
The floor information of the video image of user annotation is received, and generates the parameter coordinate information of floor;
Windowing floor information is determined according to the parameter coordinate information of windowing alert locations and floor;
Show the windowing floor information.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201810209075.9A CN108460357B (en) | 2018-03-14 | 2018-03-14 | Windowing alarm detection system and method based on image recognition |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201810209075.9A CN108460357B (en) | 2018-03-14 | 2018-03-14 | Windowing alarm detection system and method based on image recognition |
Publications (2)
Publication Number | Publication Date |
---|---|
CN108460357A true CN108460357A (en) | 2018-08-28 |
CN108460357B CN108460357B (en) | 2020-05-05 |
Family
ID=63219967
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN201810209075.9A Active CN108460357B (en) | 2018-03-14 | 2018-03-14 | Windowing alarm detection system and method based on image recognition |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN108460357B (en) |
Cited By (3)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN110969604A (en) * | 2019-11-26 | 2020-04-07 | 北京工业大学 | Intelligent security real-time windowing detection alarm system and method based on deep learning |
CN111369761A (en) * | 2019-03-05 | 2020-07-03 | 杭州海康威视系统技术有限公司 | Early warning range determining method, device, equipment and system |
CN111726532A (en) * | 2020-06-30 | 2020-09-29 | 北京环境特性研究所 | Windowing alarm detection system and method |
Citations (2)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN102073854A (en) * | 2011-01-14 | 2011-05-25 | 天津大学 | Color license plate positioning method |
CN105163067A (en) * | 2015-08-12 | 2015-12-16 | 武汉大学 | High toss act evidence obtaining system based on digital image processing technology |
-
2018
- 2018-03-14 CN CN201810209075.9A patent/CN108460357B/en active Active
Patent Citations (2)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN102073854A (en) * | 2011-01-14 | 2011-05-25 | 天津大学 | Color license plate positioning method |
CN105163067A (en) * | 2015-08-12 | 2015-12-16 | 武汉大学 | High toss act evidence obtaining system based on digital image processing technology |
Cited By (5)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN111369761A (en) * | 2019-03-05 | 2020-07-03 | 杭州海康威视系统技术有限公司 | Early warning range determining method, device, equipment and system |
CN110969604A (en) * | 2019-11-26 | 2020-04-07 | 北京工业大学 | Intelligent security real-time windowing detection alarm system and method based on deep learning |
CN110969604B (en) * | 2019-11-26 | 2024-02-27 | 北京工业大学 | Intelligent security real-time windowing detection alarm system and method based on deep learning |
CN111726532A (en) * | 2020-06-30 | 2020-09-29 | 北京环境特性研究所 | Windowing alarm detection system and method |
CN111726532B (en) * | 2020-06-30 | 2021-08-27 | 北京环境特性研究所 | Windowing alarm detection system and method |
Also Published As
Publication number | Publication date |
---|---|
CN108460357B (en) | 2020-05-05 |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
CN108446630B (en) | Intelligent monitoring method for airport runway, application server and computer storage medium | |
CN106412501B (en) | A kind of the construction safety behavior intelligent monitor system and its monitoring method of video | |
CN110428522A (en) | A kind of intelligent safety and defence system of wisdom new city | |
CN105160297B (en) | Masked man's event automatic detection method based on features of skin colors | |
CN108062349A (en) | Video frequency monitoring method and system based on video structural data and deep learning | |
KR102122859B1 (en) | Method for tracking multi target in traffic image-monitoring-system | |
CN108053427A (en) | A kind of modified multi-object tracking method, system and device based on KCF and Kalman | |
KR102195706B1 (en) | Method and Apparatus for Detecting Intruder | |
CN105184258A (en) | Target tracking method and system and staff behavior analyzing method and system | |
CN102348128A (en) | Surveillance camera system having camera malfunction detection function | |
CN109309808A (en) | A kind of monitoring system and method based on recognition of face | |
CN108460357A (en) | A kind of windowing alarm detection system and method based on image recognition | |
CN105208325B (en) | The land resources monitoring and early warning method captured and compare analysis is pinpointed based on image | |
CN108376246A (en) | A kind of identification of plurality of human faces and tracking system and method | |
Alshammari et al. | Intelligent multi-camera video surveillance system for smart city applications | |
CN105844245A (en) | Fake face detecting method and system for realizing same | |
CN110189355A (en) | Safe escape channel occupies detection method, device, electronic equipment and storage medium | |
CN110096945B (en) | Indoor monitoring video key frame real-time extraction method based on machine learning | |
CN112287823A (en) | Facial mask identification method based on video monitoring | |
CN112184773A (en) | Helmet wearing detection method and system based on deep learning | |
CN110781735A (en) | Alarm method and system for identifying on-duty state of personnel | |
CN113955594B (en) | Elevator control method and device, computer equipment and storage medium | |
CN114067396A (en) | Vision learning-based digital management system and method for live-in project field test | |
JP4607394B2 (en) | Person detection system and person detection program | |
CN113095160A (en) | Power system personnel safety behavior identification method and system based on artificial intelligence and 5G |
Legal Events
Date | Code | Title | Description |
---|---|---|---|
PB01 | Publication | ||
PB01 | Publication | ||
SE01 | Entry into force of request for substantive examination | ||
SE01 | Entry into force of request for substantive examination | ||
GR01 | Patent grant | ||
GR01 | Patent grant |