CN109951637A - Safety monitoring probe analysis and processing method based on big data - Google Patents
Safety monitoring probe analysis and processing method based on big data Download PDFInfo
- Publication number
- CN109951637A CN109951637A CN201910209796.4A CN201910209796A CN109951637A CN 109951637 A CN109951637 A CN 109951637A CN 201910209796 A CN201910209796 A CN 201910209796A CN 109951637 A CN109951637 A CN 109951637A
- Authority
- CN
- China
- Prior art keywords
- head
- image
- probe
- face
- local computer
- 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
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04N—PICTORIAL COMMUNICATION, e.g. TELEVISION
- H04N7/00—Television systems
- H04N7/18—Closed-circuit television [CCTV] systems, i.e. systems in which the video signal is not broadcast
- H04N7/181—Closed-circuit television [CCTV] systems, i.e. systems in which the video signal is not broadcast for receiving images from a plurality of remote sources
-
- G—PHYSICS
- G08—SIGNALLING
- G08B—SIGNALLING OR CALLING SYSTEMS; ORDER TELEGRAPHS; ALARM SYSTEMS
- G08B13/00—Burglar, theft or intruder alarms
- G08B13/18—Actuation by interference with heat, light, or radiation of shorter wavelength; Actuation by intruding sources of heat, light, or radiation of shorter wavelength
- G08B13/189—Actuation by interference with heat, light, or radiation of shorter wavelength; Actuation by intruding sources of heat, light, or radiation of shorter wavelength using passive radiation detection systems
- G08B13/194—Actuation by interference with heat, light, or radiation of shorter wavelength; Actuation by intruding sources of heat, light, or radiation of shorter wavelength using passive radiation detection systems using image scanning and comparing systems
- G08B13/196—Actuation by interference with heat, light, or radiation of shorter wavelength; Actuation by intruding sources of heat, light, or radiation of shorter wavelength using passive radiation detection systems using image scanning and comparing systems using television cameras
- G08B13/19602—Image analysis to detect motion of the intruder, e.g. by frame subtraction
-
- G—PHYSICS
- G08—SIGNALLING
- G08B—SIGNALLING OR CALLING SYSTEMS; ORDER TELEGRAPHS; ALARM SYSTEMS
- G08B13/00—Burglar, theft or intruder alarms
- G08B13/18—Actuation by interference with heat, light, or radiation of shorter wavelength; Actuation by intruding sources of heat, light, or radiation of shorter wavelength
- G08B13/189—Actuation by interference with heat, light, or radiation of shorter wavelength; Actuation by intruding sources of heat, light, or radiation of shorter wavelength using passive radiation detection systems
- G08B13/194—Actuation by interference with heat, light, or radiation of shorter wavelength; Actuation by intruding sources of heat, light, or radiation of shorter wavelength using passive radiation detection systems using image scanning and comparing systems
- G08B13/196—Actuation by interference with heat, light, or radiation of shorter wavelength; Actuation by intruding sources of heat, light, or radiation of shorter wavelength using passive radiation detection systems using image scanning and comparing systems using television cameras
- G08B13/19639—Details of the system layout
- G08B13/19645—Multiple cameras, each having view on one of a plurality of scenes, e.g. multiple cameras for multi-room surveillance or for tracking an object by view hand-over
-
- G—PHYSICS
- G08—SIGNALLING
- G08B—SIGNALLING OR CALLING SYSTEMS; ORDER TELEGRAPHS; ALARM SYSTEMS
- G08B13/00—Burglar, theft or intruder alarms
- G08B13/18—Actuation by interference with heat, light, or radiation of shorter wavelength; Actuation by intruding sources of heat, light, or radiation of shorter wavelength
- G08B13/189—Actuation by interference with heat, light, or radiation of shorter wavelength; Actuation by intruding sources of heat, light, or radiation of shorter wavelength using passive radiation detection systems
- G08B13/194—Actuation by interference with heat, light, or radiation of shorter wavelength; Actuation by intruding sources of heat, light, or radiation of shorter wavelength using passive radiation detection systems using image scanning and comparing systems
- G08B13/196—Actuation by interference with heat, light, or radiation of shorter wavelength; Actuation by intruding sources of heat, light, or radiation of shorter wavelength using passive radiation detection systems using image scanning and comparing systems using television cameras
- G08B13/19654—Details concerning communication with a camera
-
- G—PHYSICS
- G08—SIGNALLING
- G08B—SIGNALLING OR CALLING SYSTEMS; ORDER TELEGRAPHS; ALARM SYSTEMS
- G08B13/00—Burglar, theft or intruder alarms
- G08B13/18—Actuation by interference with heat, light, or radiation of shorter wavelength; Actuation by intruding sources of heat, light, or radiation of shorter wavelength
- G08B13/189—Actuation by interference with heat, light, or radiation of shorter wavelength; Actuation by intruding sources of heat, light, or radiation of shorter wavelength using passive radiation detection systems
- G08B13/194—Actuation by interference with heat, light, or radiation of shorter wavelength; Actuation by intruding sources of heat, light, or radiation of shorter wavelength using passive radiation detection systems using image scanning and comparing systems
- G08B13/196—Actuation by interference with heat, light, or radiation of shorter wavelength; Actuation by intruding sources of heat, light, or radiation of shorter wavelength using passive radiation detection systems using image scanning and comparing systems using television cameras
- G08B13/19665—Details related to the storage of video surveillance data
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04N—PICTORIAL COMMUNICATION, e.g. TELEVISION
- H04N23/00—Cameras or camera modules comprising electronic image sensors; Control thereof
- H04N23/60—Control of cameras or camera modules
- H04N23/61—Control of cameras or camera modules based on recognised objects
- H04N23/611—Control of cameras or camera modules based on recognised objects where the recognised objects include parts of the human body
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04N—PICTORIAL COMMUNICATION, e.g. TELEVISION
- H04N23/00—Cameras or camera modules comprising electronic image sensors; Control thereof
- H04N23/70—Circuitry for compensating brightness variation in the scene
- H04N23/741—Circuitry for compensating brightness variation in the scene by increasing the dynamic range of the image compared to the dynamic range of the electronic image sensors
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04N—PICTORIAL COMMUNICATION, e.g. TELEVISION
- H04N23/00—Cameras or camera modules comprising electronic image sensors; Control thereof
- H04N23/80—Camera processing pipelines; Components thereof
Landscapes
- Engineering & Computer Science (AREA)
- Multimedia (AREA)
- Signal Processing (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Image Processing (AREA)
- Studio Devices (AREA)
- Image Analysis (AREA)
Abstract
The invention discloses the safety monitoring probe analysis and processing methods based on big data, and specific step is as follows for this method: acquiring image data by main monitoring probe, and image data is transferred on tangible display and is shown.Image data is acquired by main monitoring probe, and the extraction of head image is carried out by local computer, it is uploaded to Cloud Server again and the big data of citizen's information compares, the personnel in image data are identified and marked, staff can be facilitated to supervise the personnel in image data.It opens and is popped one's head in by three enhancings of setting and shoot the picture of different light exposures and resolution ratio, and the picture of shooting is cut and screened, make unidentified group high Qinghua of face and promote picture detail, and then promote the probability of matching citizen's information.It is provided with the function of output monitoring screenshot, the picture of probe H shooting is extracted and synthesized, forms the monitoring screenshot that all faces all clearly synthesize.
Description
Technical field
The present invention relates to protection and monitor fields, and in particular to the safety monitoring probe analysis and processing method based on big data.
Background technique
Recognition of face is a kind of biological identification technology for carrying out identification based on facial feature information of people.With camera shooting
Machine or camera acquire image or video flowing containing face, and automatic detection and tracking face in the picture, and then to detection
The face that arrives carries out a series of the relevant technologies of face, usually also referred to as Identification of Images, face recognition.Face identification system is main
Including four component parts, be respectively as follows: man face image acquiring and detection, facial image pretreatment, facial image feature extraction with
And it matches and identifies.
Monitor camera is used in the quasi- video camera in terms of security protection, its pixel and the video heads of resolution ratio computer are wanted
Height is lower than the digital camera or dv of profession.Monitor camera is mostly single video capturing device, seldom has data guarantor
Deposit function.Video data of the existing monitor camera due to wanting output quantity, it is contemplated that transimission and storage, local computer are also wanted
Calculating needed for processing identification, operating pressure is larger, the output resolution ratio and dynamic range of usual video data, in shooting one
When scene, face identification rate only nearby is higher, and the facial image of distant place can cause recognition success rate to drop because of lack of resolution
It is low, simultaneously because the light in actual scene is complicated, can there are dark portion and highlights in the picture of shooting, in this two parts
Face also can cause recognition success rate to reduce because picture detail is lost, and then influence the performance of identifying system.
Summary of the invention
In order to solve the above technical problems, the purpose of the present invention is to provide the safety monitoring probes point based on big data
Analyse processing method.
The technical problems to be solved by the invention are as follows:
(1) unrecognized caused by how solving the problems, such as because of lack of resolution;
(2) accuracy rate of dark portion or the recognition of face of highlights position how is improved;
(3) how to mitigate the operating pressure of local computer.
The purpose of the present invention can be achieved through the following technical solutions:
Safety monitoring probe analysis and processing method based on big data, specific step is as follows for this method:
S1, image data is acquired by main monitoring probe, and image data is transferred on tangible display and is shown, together
Three enhancings probe that Shi Qidong is mounted on main monitoring probe outer surface is taken pictures, and the picture range tune of three enhancing probes
Section is extremely identical as main monitoring probe, and the photo storage of three enhancing probe acquisitions is in a local computer;
S2, local computer identify the face in monitored picture by face recognition technology, when to obtain the time be T
Head image, and head image is transmitted in Cloud Server, Cloud Server passes through the criminal of including that is stored in Cloud Server
Citizen's information of guilty data, personal appearance data and personal identification data is compared with head image, by all head images
It is divided into crime group, normal group and unidentified group, while sends back local computer as preliminary recognition result;
S3, local computer according to preliminary recognition result by the corresponding face of crime group in image data with red collimation mark
Note, normally organizes corresponding face in image data with green collimation mark note, unidentified group of corresponding face in image data with
Grey box label, after clicking red block, the corresponding crime data of display face and personal identification data when clicking green frame, are shown
The corresponding personal identification data of face of leting others have a look at;When clicking grey box, display enhancing function button;
S4, after clicking enhancing function button, local computer obtains three enhancing probe differences for shooting when the time is T
The photo of light exposure cuts photo according to different enhancing probes, and the photo of probe L shooting is made only to retain close shot area
Image, the photo of probe M shooting only retains in scenic spot image, the photo that probe H is shot only retains the image of prospective area, finally
By local computer from head image of the unidentified group of corresponding face under different light exposures is extracted in the image after cutting, make
Cloud Server is uploaded to for enhancing head image;
S5, Cloud Server are compared with citizen's information again by head image is enhanced, by unidentified group of corresponding face
It is converted into crime group and normal group and invalid image group, while sending back to local computer as final recognition result;
S6, local computer will be converted into the corresponding face of crime group in shadow according to final recognition result from unidentified group
As being marked again with red block in data, will be converted into from unidentified group normally organize corresponding face in image data again with
Green collimation mark note will be converted into the corresponding face of invalid image group from unidentified group and cancel grey box label, and click red block
Afterwards, the corresponding personal appearance data of display face, crime data and personal identification data, when clicking green frame, show face pair
The personal identification data and personal appearance data answered;
The image pickup method of three enhancing probes is as follows:
Shooting picture is successively divided into three close shot area, middle scenic spot and prospective area focusing areas by local computer from bottom to up
Domain, and obtain the face location in each focusing area in unidentified group, as focus point, by the focus for the L that pops one's head in order according to
It is secondary to focus point each in close shot area at, by the focus for the M that pops one's head in order successively to focus point each in middle scenic spot at, will
Pop one's head in H focus in order successively to each focus point in prospective area at, three enhancings are popped one's head in every time to defocused, continuously
Shoot the photo of five different light exposures.
Further, the ratio of the occupied area of the close shot area, middle scenic spot and prospective area is 5:3:1.
Further, three it is described enhancing probe include a pixel be 300-500 ten thousand probe L, a pixel be 800
The probe H that ten thousand -1,200 ten thousand M and pixel of probe is 24,000,000, and three enhancing probes have the function of exposure compensating.
Further, it after the local computer obtains the face location in each focusing area in unidentified group, calculates
Face location to four sides of focusing area minimum range, and according to minimum range from being as low as ranked up greatly, according to sequence
The sequence of sequence setting focusing.
Further, the exposure compensating range of the enhancing probe is from -2EV to+2EV, with -2.0, -1.0,0 ,+1.0 ,+
2.0 offset as five ranks, as normal exposure amount photo when selecting 0EV.
Further, the local computer also has the function of the step of output monitoring screenshot, output monitoring screenshot such as
Under:
Step 1: the local computer is by face recognition technology to the photograph of five different light exposures of probe H shooting
Piece carries out the extraction of head image respectively, is uploaded to Cloud Server as synthetic material;
Step 2: synthetic material and citizen's information are compared, filtering out all can recognize that and expose closest to normal
The head image of light quantity photo sends back to local computer as synthesis head portrait;
Step 3: local computer uses synthesis head portrait and corresponding face on the normal exposure amount photo for H shooting of popping one's head in
It is covered, synthesizes a monitoring screenshot high-definition, and save in a local computer.
Beneficial effects of the present invention:
(1) image data is acquired by main monitoring probe, and carries out the extraction of head image by local computer, then on
It reaches Cloud Server and the big data of citizen's information compares, mitigate the calculation amount of local computer, in image data
Personnel identify and mark, and staff can be facilitated to supervise the personnel in image data.
(2) enhancing function can be voluntarily opened as needed, opened and popped one's head in by three enhancings of setting and shoot different exposures
The picture of amount and resolution ratio, and the picture of shooting is cut and screened, make unidentified group of the high Qinghua of face and promotion figure
Piece details, and then promote the probability of matching citizen's information.It can guarantee the balance of operating pressure and recognition performance.
(3) it is provided with the function of output monitoring screenshot, the picture of probe H shooting is extracted and synthesized, forms one
The monitoring screenshot that all faces all clearly synthesize.
Specific embodiment
The technical scheme in the embodiments of the invention will be clearly and completely described below, it is clear that described implementation
Example is only a part of the embodiment of the present invention, instead of all the embodiments.Based on the embodiments of the present invention, this field is common
Technical staff's all other embodiment obtained without creative efforts belongs to the model that the present invention protects
It encloses.
The safety monitoring probe analysis and processing method based on big data is present embodiments provided, the specific steps of this method are such as
Under:
S1, image data is acquired by main monitoring probe, it is contemplated that processing and storage pressure, the resolution ratio of image data is not
More than 1080p, pixel 2,000,000 hereinafter, and image data be transferred on tangible display show, while starting is mounted on
Three enhancings probe of main monitoring probe outer surface is taken pictures, and the picture range of three enhancing probes is adjusted to and main monitoring
It pops one's head in identical, the picture for making main monitoring probe enhance probe shooting with three is consistent, and facilitates post-processing, and three enhancings are visited
Head include a pixel be 300-500 ten thousand probe L, a pixel be 8,000,000-1,200 ten thousand probe M and a pixel be
24000000 probe H, and three enhancing probes have the function of exposure compensating.The resolution ratio of three enhancing probes successively improves, point
Different distances is not corresponded to, and high pixel photo can guarantee clarity amplification, then promote the efficiency and public affairs of face recognition
The corresponding accuracy of people's information, the photo storage of three enhancing probe acquisitions are in a local computer, convenient to call at any time;
S2, local computer identify the face in monitored picture by face recognition technology, face recognition technology
For the prior art, head image of time when being T is obtained, and head image is transmitted in Cloud Server, Cloud Server passes through
The citizen's information and head image comprising crime data, personal appearance data and personal identification data being stored in Cloud Server
It is compared, wherein citizen's information is provided by public security department, and all head images are divided into crime group, normal group and unidentified
Group, while local computer is sent back as preliminary recognition result;If personal appearance data and head image similarity are more than pre-
If threshold value, then be determined as the corresponding citizen's information of the head image, be not above preset threshold value, be then classified as unidentified
Head image is classified as crime group, if head image pair if there are crime datas in the corresponding citizen's information of head image by group
There is no crime data in the citizen's information answered, then head image is classified as normal group.
S3, local computer according to preliminary recognition result by the corresponding face of crime group in image data with red collimation mark
Note, normally organizes corresponding face in image data with green collimation mark note, unidentified group of corresponding face in image data with
Grey box label, after clicking red block, the corresponding crime data of display face and personal identification data when clicking green frame, are shown
The corresponding personal identification data of face of leting others have a look at;When clicking grey box, display enhancing function button;
S4, starting enhancing function can be chosen whether according to actual needs, after clicking enhancing function button, local computer is obtained
The photos of different light exposures for taking three enhancing probes to shoot when the time is T enhance the exposure compensating range of probe from -2EV
To+2EV, using -2.0, -1.0,0 ,+1.0 ,+2.0 as five ranks offset, select to shine when 0EV as normal exposure amount
Piece, and the overexposure of two ranks and the deficient exposure of two ranks are set, photo is cut according to different enhancing probes, makes to visit
The photo of head L shooting only retains the image in close shot area, the photo of probe M shooting only retains in scenic spot image, probe H shoots
Photo only retains the image of prospective area, and the facial image of distant place is smaller, needs to be identified and matched after amplifying, it is therefore desirable to compared with
High resolution ratio, and facial image nearby is larger, is not necessarily to high-resolution, helps to mitigate operation pressure, finally by locally counting
Calculation machine is only chosen and is not known from head image of the unidentified group of corresponding face under different light exposures is extracted in the image after cutting
Other group of face has been matched with the face of citizen's information without secondary comparison, has further mitigated operation pressure, as enhancing
Head image is uploaded to Cloud Server;High-resolution photo is shot by enhancing probe, unidentified group is recognized,
The matching rate that recognition success rate and citizen's information can be increased, shooting different light exposure pictures can increase positioned at highlights or dark portion
The details of face increases the probability of this part recognition of face and the probability of citizen's information matches.
S5, Cloud Server are compared with citizen's information again by head image is enhanced, will using identical control methods
Unidentified group of corresponding face is converted into crime group and normal group and invalid image group, while sending back to this as final recognition result
Ground computer;
S6, local computer will be converted into the corresponding face of crime group in shadow according to final recognition result from unidentified group
As being marked again with red block in data, will be converted into from unidentified group normally organize corresponding face in image data again with
Green collimation mark note will be converted into the corresponding face of invalid image group from unidentified group and cancel grey box label, and click red block
Afterwards, the corresponding personal appearance data of display face, crime data and personal identification data, when clicking green frame, show face pair
The personal identification data and personal appearance data answered;Citizen's information and collected face are corresponded, the head of people is located at
In frame, second-level menu will pop up when clicking frame, the corresponding citizen's information of display face is conveniently checked.And invalid image group is then not
It can show any frame.
The image pickup method of three enhancing probes is as follows:
Shooting picture is successively divided into three close shot area, middle scenic spot and prospective area focusing areas by local computer from bottom to up
Domain, the ratio of the occupied area in close shot area, middle scenic spot and prospective area are 5:3:1.And unidentified group is obtained in each focusing area
In face location, as focus point, after local computer obtains the face location in each focusing area in unidentified group, meter
The minimum range of face location to four sides of focusing area is calculated, and according to minimum range from being as low as ranked up greatly, according to sequence
Sequence setting focusing sequence, first shoot the face at edge, then shoot intermediate face, prevent from moving out outside field range,
By the focus for the L that pops one's head in order successively to focus point each in close shot area at, by the focus for the M that pops one's head in order successively in
In scenic spot at each focus point, by the focus for the H that pops one's head in order successively to each focus point in prospective area at, three enhancing
Probe to defocused, is being continuously shot the photo of five different light exposures every time.Three probes can be simultaneously in each focusing area
Unidentified group in face focused and shot, guarantee the effect of slice, be conducive to improve picture clarity.
Local computer also has the function of that the step of output monitoring screenshot, output monitoring screenshot is as follows:
Step 1: local computer is by face recognition technology to the photo point of five different light exposures of probe H shooting
Not carry out head image extraction, be uploaded to Cloud Server as synthetic material;The photo of the highest probe shooting of pixel is selected,
Clarity is secure, and selects multiple and different light exposures to extract head image and can guarantee that the face positioned at dark portion and highlights can also be clapped
That takes the photograph is clear.
Step 2: synthetic material and citizen's information are compared, filtering out all can recognize that and expose closest to normal
The head image of light quantity photo sends back to local computer as synthesis head portrait;The effect of normal exposure amount photo entirety is best, choosing
Select the quality that this monitoring screenshot can be promoted close to the head image of normal exposure amount photo.
Step 3: local computer uses synthesis head portrait and corresponding face on the normal exposure amount photo for H shooting of popping one's head in
It is covered, synthesizes a monitoring screenshot high-definition, and save in a local computer.It is original with normal exposure amount photo
This, replaces face too dark or too bright with the synthesis head portrait with optimal light exposure, and then entirely monitor face in screenshot
Clarity facilitates staff to print and check.
The specific work process of the present embodiment is as follows:
1) main monitoring probe acquires image data, and local computer filters out the facial image in image data, and transmits
The matching that citizen's information is carried out to Cloud Server, is classified as unidentified group for not successful match, will identify the successfully criminal of being divided into
Crime group and normal group, and the face progress distinctiveness mark in corresponding image data by crime group and is normally organized, unidentified group
Corresponding face is marked in image data with grey box, and enhancing function button is arranged, and will pop up second-level menu when clicking frame,
Show the corresponding citizen's information of face or enhancing function button.
If 2) preliminary recognition result meet demand, without clicking enhancing function button, degradation operation pressure, if needing
Unidentified group further identified, press enhancing function button, transfer three enhancing probes when the time is T to unidentified group
Corresponding face, which is focused and shoots the photo of five kinds of light exposures, obtains the enhancing of different light exposures by cutting and screening
Head image, and be transmitted in Cloud Server.
3) Cloud Server analyzes enhancing head image, and in actual photographed, real light condition is very complicated, and one
Secondary picture usually will appear dark portion and highlights, and the image for such as shooting prospective area includes tetra- head images of A, B, C, D, wherein A, B
It has been matched with citizen's information, C is located at dark portion, and under normal exposure amount, the state in deficient exposure, brightness is lower, though it is identified as
Head, but preliminary recognition result is classified as unidentified group, D is located at highlights, under normal exposure amount, the state in overexposure, and brightness
Higher, picture detail is lost, and preliminary recognition result is classified as unidentified group, and passes through the photo of five kinds of light exposures, can be from overexposure
The enhancing head image for the C that photo extracts is compared with citizen's information, and picture detail is promoted, and matched probability also accordingly mentions
It rises, similarly, originally because that highlights can not can be made to become according to light exposure is reduced with the face of citizen's information matches caused by overexposure
Secretly, it promotes picture detail to be promoted, and then promotes matched probability.
4) when if desired staff carries out scene confirmation, the function of output monitoring screenshot can be enabled, is shot from probe H
Overexposure is cut in picture and owes to expose clearly head image in photo, and replaces corresponding part on the photo of normal exposure,
Form the monitoring screenshot that all faces all clearly synthesize.
Above content is only to structure of the invention example and explanation, affiliated those skilled in the art couple
Described specific embodiment does various modifications or additions or is substituted in a similar manner, without departing from invention
Structure or beyond the scope defined by this claim, is within the scope of protection of the invention.
Claims (6)
- The analysis and processing method 1. safety monitoring based on big data is popped one's head in, which is characterized in that specific step is as follows for this method:S1, image data is acquired by main monitoring probe, and image data is transferred on tangible display and is shown, opened simultaneously The dynamic three enhancings probe for being mounted on main monitoring probe outer surface is taken pictures, and the picture range of three enhancing probes is adjusted to Identical as main monitoring probe, the photo storage of three enhancing probe acquisitions is in a local computer;S2, local computer identify the face in monitored picture by face recognition technology, obtains head of time when being T Portion's image, and head image is transmitted in Cloud Server, Cloud Server includes crime number by being stored in Cloud Server It is compared according to citizen's information of, personal appearance data and personal identification data with head image, all head images is divided into Crime group, normal group and unidentified group, while local computer is sent back as preliminary recognition result;S3, local computer are marked the corresponding face of crime group according to preliminary recognition result in image data with red block, Corresponding face is normally organized with green collimation mark note in image data, unidentified group of corresponding face is in image data with grey Collimation mark note, after clicking red block, the corresponding crime data of display face and personal identification data when clicking green frame, show people The corresponding personal identification data of face;When clicking grey box, display enhancing function button;S4, after clicking enhancing function button, local computer obtains the different exposures that three enhancing probes are shot when the time is T The photo of amount cuts photo according to different enhancing probes, and the photo of probe L shooting is made only to retain the figure in close shot area Picture, the photo of probe M shooting only retains in scenic spot image, the photo that probe H is shot only retains the image of prospective area, finally by Local computer from extracting head image of the unidentified group of corresponding face under different light exposures in the image after cutting, as Enhancing head image is uploaded to Cloud Server;S5, Cloud Server are compared with citizen's information again by head image is enhanced, and unidentified group of corresponding face is converted For crime group and normal group and invalid image group, while local computer is sent back to as final recognition result;S6, local computer will be converted into the corresponding face of crime group in image number according to final recognition result from unidentified group It is marked again with red block in, will be converted into from unidentified group and normally organize corresponding face in image data again with green Collimation mark note will be converted into the corresponding face of invalid image group from unidentified group and cancel grey box label, after clicking red block, show The corresponding personal appearance data of face of leting others have a look at, crime data and personal identification data, when clicking green frame, corresponding of display face People's identity data and personal appearance data;The image pickup method of three enhancing probes is as follows:Shooting picture is successively divided into three close shot area, middle scenic spot and prospective area focusing areas by local computer from bottom to up, and Obtain the face location in each focusing area in unidentified group, as focus point, by the focus for the L that pops one's head in order successively to In close shot area at each focus point, by the focus for the M that pops one's head in order successively to focus point each in middle scenic spot at, by the H that pops one's head in Focus in order successively to each focus point in prospective area at, three enhancings probe to defocused, is being continuously shot every time The photo of five different light exposures.
- The analysis and processing method 2. safety monitoring according to claim 1 based on big data is popped one's head in, which is characterized in that described The ratio of the occupied area in close shot area, middle scenic spot and prospective area is 5:3:1.
- The analysis and processing method 3. safety monitoring according to claim 1 based on big data is popped one's head in, which is characterized in that three It is described enhancing probe include a pixel be 300-500 ten thousand probe L, a pixel be 8,000,000-1,200 ten thousand probe M and one The probe H that a pixel is 24,000,000, and three enhancing probes have the function of exposure compensating.
- The analysis and processing method 4. safety monitoring according to claim 1 based on big data is popped one's head in, which is characterized in that described After local computer obtains the face location in each focusing area in unidentified group, face location is calculated to focusing area four The minimum range on side, and according to minimum range from being as low as ranked up greatly, according to the sequence of the sequence setting focusing of sequence.
- The analysis and processing method 5. safety monitoring according to claim 3 based on big data is popped one's head in, which is characterized in that described Enhance probe exposure compensating range from -2EV to+2EV, using -2.0, -1.0,0 ,+1.0 ,+2.0 as five ranks compensation Value, as normal exposure amount photo when selecting 0EV.
- The analysis and processing method 6. safety monitoring according to claim 1 based on big data is popped one's head in, which is characterized in that described Local computer also has the function of that the step of output monitoring screenshot, output monitoring screenshot is as follows:Step 1: the local computer is by face recognition technology to the photo point of five different light exposures of probe H shooting Not carry out head image extraction, be uploaded to Cloud Server as synthetic material;Step 2: synthetic material and citizen's information are compared, all can recognize that and closest to normal exposure amount is filtered out The head image of photo sends back to local computer as synthesis head portrait;Step 3: local computer is carried out using synthesis head portrait with corresponding face on the normal exposure amount photo for H shooting of popping one's head in Covering synthesizes a monitoring screenshot high-definition, and saves in a local computer.
Priority Applications (2)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN202010716654.XA CN111818308B (en) | 2019-03-19 | 2019-03-19 | Security monitoring probe analysis processing method based on big data |
CN201910209796.4A CN109951637B (en) | 2019-03-19 | 2019-03-19 | Security monitoring probe analysis processing method based on big data |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201910209796.4A CN109951637B (en) | 2019-03-19 | 2019-03-19 | Security monitoring probe analysis processing method based on big data |
Related Child Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN202010716654.XA Division CN111818308B (en) | 2019-03-19 | 2019-03-19 | Security monitoring probe analysis processing method based on big data |
Publications (2)
Publication Number | Publication Date |
---|---|
CN109951637A true CN109951637A (en) | 2019-06-28 |
CN109951637B CN109951637B (en) | 2020-09-11 |
Family
ID=67010245
Family Applications (2)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN202010716654.XA Active CN111818308B (en) | 2019-03-19 | 2019-03-19 | Security monitoring probe analysis processing method based on big data |
CN201910209796.4A Active CN109951637B (en) | 2019-03-19 | 2019-03-19 | Security monitoring probe analysis processing method based on big data |
Family Applications Before (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN202010716654.XA Active CN111818308B (en) | 2019-03-19 | 2019-03-19 | Security monitoring probe analysis processing method based on big data |
Country Status (1)
Country | Link |
---|---|
CN (2) | CN111818308B (en) |
Cited By (2)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN112036242A (en) * | 2020-07-28 | 2020-12-04 | 重庆锐云科技有限公司 | Face picture acquisition method and device, computer equipment and storage medium |
CN113313899A (en) * | 2021-02-24 | 2021-08-27 | 温州洪启信息科技有限公司 | Security monitoring analysis processing method based on big data |
Families Citing this family (1)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN114666555B (en) * | 2022-05-23 | 2023-03-24 | 创意信息技术股份有限公司 | Edge gateway front-end system |
Citations (10)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN103824064A (en) * | 2014-03-11 | 2014-05-28 | 深圳市中安视科技有限公司 | Huge-amount human face discovering and recognizing method |
CN104346602A (en) * | 2013-08-07 | 2015-02-11 | 上海贯城信息科技有限公司 | Face recognition method and device based on feature vectors |
CN105245836A (en) * | 2015-09-28 | 2016-01-13 | 深圳市澳亚迪电子设备有限公司 | Monitoring system for security door |
CN105574506A (en) * | 2015-12-16 | 2016-05-11 | 深圳市商汤科技有限公司 | Intelligent face tracking system and method based on depth learning and large-scale clustering |
CN205563604U (en) * | 2015-12-16 | 2016-09-07 | 深圳市尊豪网络科技有限公司 | A intelligent image recognition device for selling among management system |
CN107169906A (en) * | 2017-04-16 | 2017-09-15 | 悠泊物联网科技(上海)有限公司 | A kind of smart security guard and alarm control system |
US9832192B2 (en) * | 2013-06-24 | 2017-11-28 | Telefonica Digital Espana, S.L.U. | Computer implemented method to prevent attacks against authorization systems and computer programs products thereof |
US20180285651A1 (en) * | 2017-03-31 | 2018-10-04 | International Business Machines Corporation | Image processing to identify selected individuals in a field of view |
CN208433010U (en) * | 2018-01-29 | 2019-01-25 | 东莞市芯萌慧显电子科技有限公司 | Police AR display system based on recognition of face |
CN109299949A (en) * | 2018-09-29 | 2019-02-01 | 深圳先牛信息技术有限公司 | A kind of payment mechanism and method of payment based on iris recognition |
Family Cites Families (13)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN103093177A (en) * | 2011-10-28 | 2013-05-08 | 台湾色彩与影像科技股份有限公司 | Face identification, detection and monitoring method |
CN102542299B (en) * | 2011-12-07 | 2015-03-25 | 惠州Tcl移动通信有限公司 | Face recognition method, device and mobile terminal capable of recognizing face |
KR101365557B1 (en) * | 2012-04-25 | 2014-02-27 | (주)아이머큐리 | Apparatus and method for detecting traffic lane |
US20170113611A1 (en) * | 2015-10-27 | 2017-04-27 | Dura Operating, Llc | Method for stereo map generation with novel optical resolutions |
WO2017118982A1 (en) * | 2016-01-10 | 2017-07-13 | Project Ray Ltd. | Remotely controlled communicated image resolution |
CN105931407A (en) * | 2016-06-27 | 2016-09-07 | 合肥指南针电子科技有限责任公司 | Smart household antitheft system and method |
CN106331510B (en) * | 2016-10-31 | 2019-10-15 | 维沃移动通信有限公司 | A kind of backlight photographic method and mobile terminal |
CN107424208B (en) * | 2017-08-11 | 2018-07-20 | 江苏柚尊家居制造有限公司 | A kind of baby bed and monitoring method of smart home |
CN107862265B (en) * | 2017-10-30 | 2022-02-18 | Oppo广东移动通信有限公司 | Image processing method and related product |
CN108363956A (en) * | 2018-01-19 | 2018-08-03 | 深圳市中科智诚科技有限公司 | A kind of face recognition device with compensation shooting function of wide application of the crowd |
CN108776780A (en) * | 2018-05-31 | 2018-11-09 | 上海与德科技有限公司 | A kind of face identification method, device, storage medium and intelligent terminal |
CN109326073A (en) * | 2018-09-04 | 2019-02-12 | 重庆工业职业技术学院 | A kind of wireless sensor network safety defense monitoring system based on multipoint positioning |
CN109167924B (en) * | 2018-10-24 | 2021-05-11 | 清华-伯克利深圳学院筹备办公室 | Video imaging method, system, device and storage medium based on hybrid camera |
-
2019
- 2019-03-19 CN CN202010716654.XA patent/CN111818308B/en active Active
- 2019-03-19 CN CN201910209796.4A patent/CN109951637B/en active Active
Patent Citations (10)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
US9832192B2 (en) * | 2013-06-24 | 2017-11-28 | Telefonica Digital Espana, S.L.U. | Computer implemented method to prevent attacks against authorization systems and computer programs products thereof |
CN104346602A (en) * | 2013-08-07 | 2015-02-11 | 上海贯城信息科技有限公司 | Face recognition method and device based on feature vectors |
CN103824064A (en) * | 2014-03-11 | 2014-05-28 | 深圳市中安视科技有限公司 | Huge-amount human face discovering and recognizing method |
CN105245836A (en) * | 2015-09-28 | 2016-01-13 | 深圳市澳亚迪电子设备有限公司 | Monitoring system for security door |
CN105574506A (en) * | 2015-12-16 | 2016-05-11 | 深圳市商汤科技有限公司 | Intelligent face tracking system and method based on depth learning and large-scale clustering |
CN205563604U (en) * | 2015-12-16 | 2016-09-07 | 深圳市尊豪网络科技有限公司 | A intelligent image recognition device for selling among management system |
US20180285651A1 (en) * | 2017-03-31 | 2018-10-04 | International Business Machines Corporation | Image processing to identify selected individuals in a field of view |
CN107169906A (en) * | 2017-04-16 | 2017-09-15 | 悠泊物联网科技(上海)有限公司 | A kind of smart security guard and alarm control system |
CN208433010U (en) * | 2018-01-29 | 2019-01-25 | 东莞市芯萌慧显电子科技有限公司 | Police AR display system based on recognition of face |
CN109299949A (en) * | 2018-09-29 | 2019-02-01 | 深圳先牛信息技术有限公司 | A kind of payment mechanism and method of payment based on iris recognition |
Cited By (3)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN112036242A (en) * | 2020-07-28 | 2020-12-04 | 重庆锐云科技有限公司 | Face picture acquisition method and device, computer equipment and storage medium |
CN112036242B (en) * | 2020-07-28 | 2023-07-21 | 重庆锐云科技有限公司 | Face picture acquisition method and device, computer equipment and storage medium |
CN113313899A (en) * | 2021-02-24 | 2021-08-27 | 温州洪启信息科技有限公司 | Security monitoring analysis processing method based on big data |
Also Published As
Publication number | Publication date |
---|---|
CN111818308A (en) | 2020-10-23 |
CN109951637B (en) | 2020-09-11 |
CN111818308B (en) | 2022-02-08 |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
US7327890B2 (en) | Imaging method and system for determining an area of importance in an archival image | |
CN110428366A (en) | Image processing method and device, electronic equipment, computer readable storage medium | |
EP3007104B1 (en) | Object detection and recognition under out of focus conditions | |
US8861806B2 (en) | Real-time face tracking with reference images | |
DE60116949T2 (en) | FACE DETECTION METHOD | |
DE69934068T2 (en) | DETERMINATION OF THE POSITION OF EYES BY LIGHT REFLEX DETECTION AND CORRECTION OF DEFECTS IN A RECORDED IMAGE | |
CN109951637A (en) | Safety monitoring probe analysis and processing method based on big data | |
CN109089047A (en) | Control method and apparatus, the storage medium, electronic equipment of focusing | |
CN107945135A (en) | Image processing method, device, storage medium and electronic equipment | |
JP6376474B2 (en) | Multi-view imaging system, acquired image composition processing method, and program | |
CN109255282B (en) | Biological identification method, device and system | |
CN108322651A (en) | Image pickup method and device, electronic equipment, computer readable storage medium | |
CN110210292A (en) | A kind of target identification method based on deep learning | |
CN107920205B (en) | Image processing method, device, storage medium and electronic equipment | |
TWI255429B (en) | Method for adjusting image acquisition parameters to optimize objection extraction | |
JP5862071B2 (en) | Image processing apparatus, imaging apparatus, and program | |
JP2009123081A (en) | Face detection method and photographing apparatus | |
CN110392211A (en) | Image processing method and device, electronic equipment, computer readable storage medium | |
CN110365897A (en) | Image correcting method and device, electronic equipment, computer readable storage medium | |
CN111126378B (en) | Method for extracting video OSD and reconstructing coverage area | |
WO2021166289A1 (en) | Data registration device, biometric authentication device, and recording medium | |
CN110460783B (en) | Array camera module, image processing system, image processing method and electronic equipment | |
CN109345541A (en) | A kind of working method of intelligent monitor system | |
CN109064501A (en) | A kind of working method of sewage treatment monitoring system | |
CN108234868A (en) | The intelligent camera system and method for a kind of case-based reasioning |
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 | ||
TA01 | Transfer of patent application right | ||
TA01 | Transfer of patent application right |
Effective date of registration: 20200810 Address after: 050000 Hebei city in Shijiazhuang Province, Xinhua District No. 91 Xinhua Road Jinyi city building A-1602 Applicant after: HEBEI CHUANGU INFORMATION TECHNOLOGY Co.,Ltd. Address before: 325011 First Floor, No. 38 Longteng Road, Zhuangyuan New Street, Longwan District, Wenzhou City, Zhejiang Province Applicant before: WENZHOU HONGQI INFORMATION TECHNOLOGY Co.,Ltd. |
|
GR01 | Patent grant | ||
GR01 | Patent grant |