CN109344679A - Building site monitoring method, device and readable storage medium storing program for executing based on image analysis - Google Patents
Building site monitoring method, device and readable storage medium storing program for executing based on image analysis Download PDFInfo
- Publication number
- CN109344679A CN109344679A CN201810830408.XA CN201810830408A CN109344679A CN 109344679 A CN109344679 A CN 109344679A CN 201810830408 A CN201810830408 A CN 201810830408A CN 109344679 A CN109344679 A CN 109344679A
- Authority
- CN
- China
- Prior art keywords
- collected object
- monitoring area
- face feature
- safety cap
- collected
- 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
- 238000012544 monitoring process Methods 0.000 title claims abstract description 148
- 238000000034 method Methods 0.000 title claims abstract description 64
- 238000010191 image analysis Methods 0.000 title claims abstract description 42
- 238000004590 computer program Methods 0.000 claims description 33
- 238000004422 calculation algorithm Methods 0.000 claims description 25
- 238000012806 monitoring device Methods 0.000 claims description 11
- 238000001514 detection method Methods 0.000 claims description 3
- 230000006870 function Effects 0.000 claims description 3
- 238000010276 construction Methods 0.000 description 24
- 238000010586 diagram Methods 0.000 description 10
- 238000005516 engineering process Methods 0.000 description 9
- 230000008569 process Effects 0.000 description 7
- 230000001960 triggered effect Effects 0.000 description 7
- 238000013475 authorization Methods 0.000 description 4
- 239000000284 extract Substances 0.000 description 4
- 210000003128 head Anatomy 0.000 description 4
- 230000009286 beneficial effect Effects 0.000 description 3
- 241000406668 Loxodonta cyclotis Species 0.000 description 2
- 238000004458 analytical method Methods 0.000 description 2
- 230000000694 effects Effects 0.000 description 2
- 230000009467 reduction Effects 0.000 description 2
- 238000012800 visualization Methods 0.000 description 2
- 206010019233 Headaches Diseases 0.000 description 1
- 238000013473 artificial intelligence Methods 0.000 description 1
- 230000005540 biological transmission Effects 0.000 description 1
- 230000000903 blocking effect Effects 0.000 description 1
- 210000004556 brain Anatomy 0.000 description 1
- 238000009435 building construction Methods 0.000 description 1
- 230000009172 bursting Effects 0.000 description 1
- 238000004364 calculation method Methods 0.000 description 1
- 230000008859 change Effects 0.000 description 1
- 239000000470 constituent Substances 0.000 description 1
- 238000013461 design Methods 0.000 description 1
- 238000011161 development Methods 0.000 description 1
- 230000002708 enhancing effect Effects 0.000 description 1
- 238000000605 extraction Methods 0.000 description 1
- 238000001914 filtration Methods 0.000 description 1
- 210000001061 forehead Anatomy 0.000 description 1
- 231100000869 headache Toxicity 0.000 description 1
- 230000006698 induction Effects 0.000 description 1
- 230000005764 inhibitory process Effects 0.000 description 1
- 238000012423 maintenance Methods 0.000 description 1
- 238000013507 mapping Methods 0.000 description 1
- 238000005065 mining Methods 0.000 description 1
- ZRHANBBTXQZFSP-UHFFFAOYSA-M potassium;4-amino-3,5,6-trichloropyridine-2-carboxylate Chemical compound [K+].NC1=C(Cl)C(Cl)=NC(C([O-])=O)=C1Cl ZRHANBBTXQZFSP-UHFFFAOYSA-M 0.000 description 1
- 238000012545 processing Methods 0.000 description 1
- 230000008439 repair process Effects 0.000 description 1
- 230000001360 synchronised effect Effects 0.000 description 1
- 238000012546 transfer Methods 0.000 description 1
- 238000003466 welding Methods 0.000 description 1
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V40/00—Recognition of biometric, human-related or animal-related patterns in image or video data
- G06V40/10—Human or animal bodies, e.g. vehicle occupants or pedestrians; Body parts, e.g. hands
- G06V40/16—Human faces, e.g. facial parts, sketches or expressions
- G06V40/172—Classification, e.g. identification
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q50/00—Information and communication technology [ICT] specially adapted for implementation of business processes of specific business sectors, e.g. utilities or tourism
- G06Q50/10—Services
- G06Q50/26—Government or public services
- G06Q50/265—Personal security, identity or safety
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V10/00—Arrangements for image or video recognition or understanding
- G06V10/70—Arrangements for image or video recognition or understanding using pattern recognition or machine learning
- G06V10/74—Image or video pattern matching; Proximity measures in feature spaces
- G06V10/75—Organisation of the matching processes, e.g. simultaneous or sequential comparisons of image or video features; Coarse-fine approaches, e.g. multi-scale approaches; using context analysis; Selection of dictionaries
- G06V10/751—Comparing pixel values or logical combinations thereof, or feature values having positional relevance, e.g. template matching
-
- 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
- G06V40/00—Recognition of biometric, human-related or animal-related patterns in image or video data
- G06V40/10—Human or animal bodies, e.g. vehicle occupants or pedestrians; Body parts, e.g. hands
- G06V40/16—Human faces, e.g. facial parts, sketches or expressions
- G06V40/168—Feature extraction; Face representation
Landscapes
- Engineering & Computer Science (AREA)
- Theoretical Computer Science (AREA)
- Physics & Mathematics (AREA)
- Health & Medical Sciences (AREA)
- General Physics & Mathematics (AREA)
- Multimedia (AREA)
- Business, Economics & Management (AREA)
- General Health & Medical Sciences (AREA)
- Oral & Maxillofacial Surgery (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Human Computer Interaction (AREA)
- Tourism & Hospitality (AREA)
- General Business, Economics & Management (AREA)
- Artificial Intelligence (AREA)
- Primary Health Care (AREA)
- Marketing (AREA)
- Human Resources & Organizations (AREA)
- Economics (AREA)
- Educational Administration (AREA)
- Development Economics (AREA)
- Computer Security & Cryptography (AREA)
- Strategic Management (AREA)
- Computing Systems (AREA)
- Databases & Information Systems (AREA)
- Evolutionary Computation (AREA)
- Medical Informatics (AREA)
- Software Systems (AREA)
- Image Analysis (AREA)
- Alarm Systems (AREA)
Abstract
The building site monitoring method based on image analysis that the present invention provides a kind of, device and readable storage medium storing program for executing, the described method includes: when thering is collected object to enter in the pre-set image acquisition range of monitoring area, acquire the image information of collected object, and the face feature information of object is collected according to image information acquisition, according to image information, detect whether collected object wears safety cap, when detecting that collected subject wears have safety cap, obtain the coding of safety cap, according to the coding of safety cap, obtain the face feature model for the monitoring area authorized user that there is one-to-one relationship with coding, the face feature information of collected object is matched with the face feature model of monitoring area authorized user, obtain matching result, when the matching result of the two is successful match, determining allows described in collected object entrance Monitoring area can be realized the one capped pipe control of a people of building site monitoring area, avoid that accident occurs.
Description
Technical field
The present invention relates to building site monitoring management field more particularly to a kind of building site monitoring methods based on image analysis, dress
It sets and readable storage medium storing program for executing.
Background technique
In recent years, with the development of economy and society, big and small construction site is seen everywhere in town and country, but due to building site
All kinds of accidents happen occasionally, the security management and control of construction site also become engineering quotient for it headache the problem of.
In order to improve the efficiency of management of construction site, prevents people without fixed duties etc. and swarm into building site, reinforce site safety control, engineering
Quotient is common to be selected to be to establish a set of safe and reliable video monitoring system for building site.And biological identification technology is extensive already
It is applied to mining, repairs subway, building construction etc. in the monitoring system of all kinds of construction sites, for example, by using face recognition technology or referring to
Line identification technology carries out site safety control, also has in the prior art using the figure identified to safety cap or work clothes certainly
It escorts safely as analytical technology for site construction, undeniably these all play certain effects.But want maximum journey
Degree ground meet requirement of the engineering quotient to one cap security management and control of a people, these be it is far from being enough, the prior art using biology know
Do not combined with image analysis with realize security management and control technically there are still some problems.
Summary of the invention
The main purpose of the present invention is to provide a kind of building site monitoring method, device and readable storage based on image analysis
Medium can not achieve one capped pipe control of a people, and multiple accident due to can not achieve one capped pipe control of a people to solve construction site
The problem of situation.
To achieve the above object, first aspect present invention provides a kind of building site monitoring method based on image analysis, packet
It includes:
When thering is collected object to enter in the pre-set image acquisition range of monitoring area, the collected object is acquired
Image information, and the face feature information of the collected object according to described image acquisition of information;
According to described image information, detect whether the collected object wears safety cap;
When detecting that the collected subject wears have safety cap, the coding of the safety cap is obtained;
According to the coding of the safety cap, the monitoring area authorization that there is one-to-one relationship with the coding is obtained
The face feature model of user;
By the face feature model of the face feature information of the collected object and the monitoring area authorized user into
Row matching, obtains matching result;
When the face feature model of the face feature information and monitoring area authorized user of the collected object
When matching result is successful match, determining allows the collected object to enter the monitoring area.
The second aspect of the present invention additionally provides a kind of building site monitoring device based on image analysis, including memory, place
The computer program managing device and storage in memory and can running on a processor, when which executes computer program
The step of realizing the above-mentioned building site monitoring method based on image analysis.
The third aspect of the present invention additionally provides a kind of computer readable storage medium, computer-readable recording medium storage
There is computer program, which realizes the above-mentioned building site monitoring method based on image analysis when being executed by processor
Step.
Above scheme of the invention is include at least the following beneficial effects:
By when thering is collected object to enter in the pre-set image acquisition range of monitoring area, acquiring collected object
Image information, and be collected according to image information acquisition the face feature information of object, then according to acquired image information,
It detects whether collected object wears safety cap, when detecting that collected subject wears have safety cap, obtains safety cap
Coding, according to the coding of the safety cap, obtaining with the coding there is the monitoring area authorization of one-to-one relationship to use
The face feature model at family, finally by the face feature mould of the face feature information of collected object and monitoring area authorized user
Type is matched, and matching result is obtained, when the face feature information of collected object and the face of monitoring area authorized user are special
When the matching result for levying model is successful match, determining allows collected object to enter the monitoring area, to realize building site
The one capped pipe control of a people of monitoring area, avoids that accident occurs.
Detailed description of the invention
In order to more clearly explain the embodiment of the invention or the technical proposal in the existing technology, to embodiment or will show below
There is attached drawing needed in technical description to be briefly described, it should be apparent that, the accompanying drawings in the following description is only this
Some embodiments of invention for those of ordinary skill in the art without creative efforts, can be with
It obtains other drawings based on these drawings.
Fig. 1 is a kind of network system architecture schematic diagram provided in an embodiment of the present invention;
Fig. 2 is a kind of flow diagram of the building site monitoring method based on image analysis provided in an embodiment of the present invention;
Fig. 3 is a kind of friendship of remote control center and infrared inductor and Image Acquisition terminal provided in an embodiment of the present invention
Mutual flow diagram;
Fig. 4 is the flow diagram of another building site monitoring method based on image analysis provided in an embodiment of the present invention;
Fig. 5 is a kind of process in application scenarios of the building site monitoring method based on image analysis provided in an embodiment of the present invention
Schematic diagram;
Fig. 6 is a kind of structural schematic diagram of the building site monitoring device based on image analysis provided in an embodiment of the present invention;
Specific embodiment
In order to enable those skilled in the art to better understand the solution of the present invention, below in conjunction in the embodiment of the present invention
Attached drawing, technical scheme in the embodiment of the invention is clearly and completely described, it is clear that described embodiment is only
The embodiment of a part of the invention, instead of all the embodiments.Based on the embodiments of the present invention, ordinary skill people
The model that the present invention protects all should belong in member's every other embodiment obtained without making creative work
It encloses.
The term " includes " and " having " and their any changes occurred in description of the invention, claims and attached drawing
Shape, it is intended that cover and non-exclusive include.Such as contain the process, method of a series of steps or units, system, product or
Equipment is not limited to listed step or unit, but optionally further comprising the step of not listing or unit or optional
Ground further includes the other step or units intrinsic for these process, methods, product or equipment.In addition, term " first ", " the
Two " and " third " etc. are and to be not intended to describe specific sequence for distinguishing different objects.
The embodiment of this programme is illustrated in conjunction with relevant drawings and citing first below, but is illustrated not to this hair
Bright embodiment causes to limit.
It illustrates first in conjunction with relevant drawings and introduces the network system frame that the scheme possible application of lower the embodiment of the present application is arrived
Structure.
Referring specifically to Fig. 1, network system architecture shown in FIG. 1 is related to Image Acquisition terminal, remote control center, display
Terminal.Wherein, remote control center is the brain of whole system, it can be understood as executes the server of row this programme method, control
Make the running of the other components of system;Image Acquisition terminal is specifically as follows and takes the photograph for acquiring image information in acquisition range
As head, capture machine, camera etc.;Display terminal is for showing Image Acquisition terminal acquired image information, naturally it is also possible to be
Some operations of remote control center provide Visualization Service, and each section carries out intercommunication by transmission assembly or network, make entire
The implementation of monitoring method based on image analysis is able to the support of system architecture.
Embodiment one
Referring to fig. 2, Fig. 2 is a kind of flow diagram of the building site monitoring method based on image analysis provided by the invention,
Method shown in Fig. 2 can be embodied based on network system architecture shown in Fig. 1 citing.
As shown in Fig. 2, one aspect of the present invention provides a kind of building site monitoring method based on image analysis, the method packet
It includes:
S11 acquires described collected pair when having collected object to enter in the pre-set image acquisition range of monitoring area
The image information of elephant, and the face feature information of the collected object according to described image acquisition of information.
Wherein, in the present embodiment, monitoring area can be entire building site, and pre-set image acquisition range can be image and adopt
In the range that can cover of collection terminal, such as several meters centered on passing in and out construction site passway, in more than ten meters, tens meters
It is interior, it might even be possible to be broader range.This sentences collected object by the gate of construction site or for passing through gate passage,
When detecting in pre-set image acquisition range has collected (can specifically detect in such a way that infrared inductor incudes), starting
Distributed image acquisition terminal (video camera, camera or capture machine etc.) at gate or gate passage, acquisition contain quilt
Acquisition target face or the image information, including image, video of face etc., and people is carried out to acquired image or video automatically
Face tracking, extracts the geometric constitution relationship between acquisition target face feature information point, among these just includes eyes, nose, mouth
Bar, the characteristic informations point such as forehead.The quilt entered in pre-set image acquisition range is determined according to the constituent relation between characteristic information point
The face feature information of acquisition target, it should be noted that after the face feature information for getting above-mentioned collected object,
And no hurry matches it with the pre-stored face feature model for being able to enter monitoring area authorized user.
S12 detects whether the collected object wears safety cap according to described image information.
Wherein, in the present embodiment, which is got using the face recognition technology in biological identification technology
Face feature information after, first determine whether the acquisition target wears safety cap, in an embodiment of the present invention, mainly
Acquired image information is detected using image matching algorithm.
It should be noted that image matching algorithm is divided into 3 classes, it is the matching algorithm based on gray scale respectively, based on feature
Matching algorithm and matching algorithm based on relationship, the matching algorithm based on gray scale mainly have the template matching algorithm based on gray scale,
Template matching (Blocking Matching) be found according to known template image into another piece image it is similar to template image
Subgraph, matched using space two-dimensional sleiding form, common are MAD (Mean Absolute Difference, put down
Equal absolute difference) algorithm, SAD (Sum of Absolute Difference, absolute error and) algorithm, NCC (Normalized
Cross correlation normalizes crosscorrelation) algorithm etc..Feature-based matching algorithm extracts the feature of image first,
Feature Descriptor is regenerated, is finally matched according to the similarity degree of description between the feature of two images, it is common
There is SIFT (Scale-Invariant Feature Transform, Scale invariant features transform) algorithm, SURF (Speeded-
Up Robust Features accelerates robust feature) algorithm, BRISK (Binary Robust Invariant Scalable
Keypoints, the constant scale feature of binary robust) algorithm etc..Matching algorithm based on relationship is that artificial intelligence field is being schemed
As the application in processing, breakthrough is relatively slow, and application is not extensive.Which specifically uses as the solution of the present invention
Class matching algorithm, is not limited by the embodiment of the present invention.
S13 obtains the coding of the safety cap when detecting that the collected subject wears have safety cap.
Wherein, on the basis of step S12, when the matched result of image matching algorithm reaches threshold requirement, institute is detected
Collected subject wears in acquired image or video have safety cap, and remote control center starts encoding identification device, obtains
Take the coding on the safety cap.
It should be noted that the safety cap coding in the embodiment of the present invention can be simple digital coding, one-dimensional barcode
Code is also possible to present widely used two dimensional code.Safety cap coding is the unique identities of all safety caps in the present embodiment
Mark.
S14 obtains the monitoring area for having one-to-one relationship with the coding according to the coding of the safety cap
The face feature model of authorized user.
Wherein, in an embodiment of the present invention, after having executed above-mentioned steps S13, remote control center can be with the coding
Local data base is read or called for major key, which refers specifically to safety cap coding and monitoring area authorized user's
Face feature relationship model mapping library is stored with the face feature model of safety cap Yu monitoring area authorized user in the database
Between one-to-one relationship, the face feature model of the fixed monitoring area authorized user of each safety cap coding binding.It is aobvious
And be clear to, the face feature mould of the monitoring area authorized user bound therewith can be got by getting a safety cap coding
Type, the face feature model for getting a monitoring area authorized user can equally get the safety cap coding bound therewith,
Based on this, step S14 is achieved.
S15, by the face feature mould of the face feature information of the collected object and the monitoring area authorized user
Type is matched, and matching result is obtained.
Wherein, in the present embodiment, above-mentioned matching result by the face feature information of collected object calculated with
The similarity degree value of the face feature Model Matching of the monitoring area authorized user determines that remote monitoring center is according to safety cap
After coding gets the face feature model of one-to-one monitoring area authorized user therewith, enabling image matching unit will be upper
It states the two be scanned, match, calculates the similarity degree of collected object and the face feature Model Matching of the authorized user
Value, obtains matching result.
S16, when the face feature information of the collected object and the face feature mould of the monitoring area authorized user
When the matching result of type is successful match, determining allows the collected object to enter the monitoring area.
Wherein, in the present embodiment, main according to the face feature information and the monitoring area authorization that are collected object
The relationship of the similarity degree value of the face feature Model Matching of user and threshold value come judge matching result whether successful match, when
When with success, indicate above-mentioned collected object reached one cap of a people by condition, remote control center is to access control master
Machine or gate send instruction, and the collected object is allowed to enter monitoring area.
The utility model has the advantages that compared with prior art, combination of embodiment of the present invention biological identification technology and image analysis technology,
By the image letter for when thering is collected object to enter in the pre-set image acquisition range of monitoring area, acquiring collected object
It ceases, and is collected the face feature information of object according to image information acquisition, then according to acquired image information, detect quilt
Whether acquisition target wears safety cap, when detecting that collected subject wears have safety cap, obtains the coding of safety cap, root
According to the coding of the safety cap, the face for the monitoring area authorized user that there is one-to-one relationship with the coding is obtained
Characteristic model, finally by the progress of the face feature model of the face feature information of collected object and monitoring area authorized user
Match, obtain matching result, when matching result is successful match, determining allows collected object to enter monitoring area, to solve
Certainly there is unauthorized people to occur on construction site often, realizes the one capped pipe control of a people of building site monitoring area, avoid that accident occurs.
Further, preferred embodiment, as shown in figure 3, in a specific embodiment of the present invention, remote control center can pass through
With infrared inductor and the step of interacting the face feature information for obtaining collected object of Image Acquisition terminal, specifically include:
S21, infrared inductor send the prompt that is triggered.
Wherein, the prompt that is triggered includes the letter that collected object enters in the pre-set image acquisition range of monitoring area
Breath.
S22, remote control center receives the prompt that is triggered, and sends image information collecting to Image Acquisition terminal and refer to
It enables.
Wherein, the Image Acquisition terminal in the embodiment of the present invention includes video camera, camera, capture machine, camera and sweeps
The terminal of image information can be acquired by retouching instrument etc..
S23, Image Acquisition terminal receive image information collecting instruction, start the image letter for acquiring the collected object
Breath.
Wherein, the image information of above-mentioned collected object includes image or video, and must be showed in the image or video
The face of collected object.
Acquired image synchronizing information is sent to remote control center by S24, Image Acquisition terminal.
S25, remote control center tracking, the face feature information for extracting the collected object.
Specifically, the embodiment of the present invention is to the collected object for wanting gate and gate passage by construction site
Before carrying out face feature information acquisition, collected object is judged whether there is by infrared inductor and enters pre-set image information
Acquisition range, remote control center just carry out control image acquisition terminal after receiving the prompt that infrared induction is triggered and carry out
The operation of image information collecting, moreover, Image Acquisition terminal is when acquiring image information, synchronized upload acquired image information
To remote control center, remote control center automatically tracks, extracts the face feature information of each collected object, can make whole
The running efficiency of a system is higher, and image information collecting is just carried out in the case where infrared inductor is triggered, is conducive to system
The reduction of maintenance cost.
Embodiment two
Shown in Figure 4, an aspect of of the present present invention additionally provides another building site monitoring method based on image analysis, tool
Body the following steps are included:
S11 acquires described collected pair when having collected object to enter in the pre-set image acquisition range of monitoring area
The image information of elephant, and the face feature information of the collected object according to described image acquisition of information.
The specific embodiment of step S11 has related description in the above-described embodiments, can equally be well applied to the present embodiment,
Excessive description is not just remake herein.
By taking construction group is changed at B from the A of construction site as an example, it is assumed that Li Si is just intending to enter together with group member now
It constructs at B, in the present embodiment, can be set up in image-capture field at A and between B, which can cover construction A
All vacant lot between place and B is also possible at construction B in a certain range of entrance, due to Image Acquisition terminal of the invention
Using Distributed Design, the coverage area that selection Image Acquisition terminal carries out image information collecting can according to need completely.When
When Li Si is entered in the pre-set image acquisition range of monitoring area, infrared inductor is triggered, and sends the prompt that is triggered, remotely
Control centre starts Image Acquisition terminal, acquires the image information of Li Si, and remote control center receives Image Acquisition terminal hair
After the image information sent, acquired image information is tracked, extracts the face feature information of Li Si, and voice can be carried out and mentioned
Show " subjects face feature information extraction success ".
S12 detects whether the collected object wears safety cap according to described image information.
The specific embodiment of step S12 has related description in the above-described embodiments, can equally be well applied to the present embodiment,
Excessive description is not just remake herein.
Wherein, step S12 can specifically include following implementations:
Acquired image information and the preset image that compares are carried out characteristic point using image matching algorithm by S31
Matching, obtains Feature Points Matching rate value;
S32 judges whether the collected object wears safety cap according to the Feature Points Matching rate value;
Further, preferred embodiment, it is above-mentioned that whether the collected object is judged according to the Feature Points Matching rate value
It the step of with safety cap, specifically includes:
The first step, when the Feature Points Matching rate value levels off to threshold value, it is determined that the acquisition target is with peace
Full cap;
Second step, when the Feature Points Matching rate value is discrete when threshold value, it is determined that the acquisition target is not worn
Safety cap.
On the basis of above-mentioned steps obtain the face feature information of Li Si, examined to whether Li Si wears safety cap
It surveys.When having monitored image capture instruction or operation, it is embedded in default comparison image in image display window, which can
It can also be only the schematic diagram for the safety cap that entire building site uniformly uses to be the schematic diagram of employee's standard safe wearing cap.
Can be excluded using SIFT algorithm because image is blocked with background clutter and the key point without matching relationship that generates, carry out first
SIFT feature detection, positions key point, and characteristic point filtering and accurate positioning are carried out in characteristic matching, ultimately produces SIFT feature
Vector.A SIFT key point in piece image is taken, and finds out its first two nearest with Euclidean distance in another piece image
Key point obtains a Feature Points Matching rate value divided by secondary close distance according to nearest distance in the two key points,
By judging whether this Feature Points Matching rate value is less than preset threshold T, to consider whether to receive this characteristic point, SIFT is calculated
Method founder recommend features described above point matching rate threshold be 0.8, certainly, preset threshold be according to matching result many times come
It chooses, is required according to the height to matching degree different and different.Meanwhile visualization display comparison process, favorably
In enhancing user experience.
Obviously, when the Feature Points Matching rate value is substantially equal to threshold value T, then receive characteristic point, determine that Li Si wears
With safety cap.When the Feature Points Matching rate value is discrete when threshold value T, that is to say, that Feature Points Matching rate value and threshold value
T gap is larger, does not receive characteristic point, it is determined that Li Si does not wear safety cap, at this point it is possible to generate the progress of respective broadcast information
Voice broadcast service " non-safe wearing cap must not enter " or " you do not wear safety cap ".
It should be noted that embodiment had had description in front, acquisition target is being judged, that is, Lee in this
Four, if on the step of wearing safety cap, do not limited by the embodiment of the present invention using which kind of image matching algorithm, herein
It is not the unique embodiment of the present embodiment that place, which carries out Feature Points Matching using SIFT algorithm,.
S13 obtains the coding of the safety cap when detecting that the collected subject wears have safety cap.
The specific embodiment of step S13 has related description in the above-described embodiments, can equally be well applied to the present embodiment,
Difference is, obtains the coding that object is the safety cap worn on Li Si's head in this example, does not just remake excessive description herein.
S14 obtains the monitoring area for having one-to-one relationship with the coding according to the coding of the safety cap
The face feature model of authorized user.
The specific embodiment of step S14 has related description in the above-described embodiments, can equally be well applied to the present embodiment,
Excessive description is not just remake herein.
Further, preferred embodiment, the above-mentioned coding according to the safety cap, obtaining has one-to-one correspondence with the coding
It the step of face feature model of the monitoring area authorized user of relationship, specifically includes:
It is encoded to major key with the safety cap, obtaining from preset face feature model table has with the coding
The face feature model of the monitoring area authorized user of one-to-one relationship;Wherein, remember in the face feature model table
Record has the corresponding all safety cap codings of the monitoring area and each safety cap to encode corresponding monitoring area authorized user
Face feature model.
Get on Li Si's head in front with safety cap and after recognizing safety cap coding, encoded with safety cap based on
Key traverses preset face feature model table or library, transfers the above-mentioned monitored space with the coding binding of the safety cap on Li Si's head
Domain authorized user face feature model (specifically can with remote control center to data call module send call instruction, by
Data call module is traversed and is called to complete).
S15, by the face feature mould of the face feature information of the collected object and the monitoring area authorized user
Type is matched, and matching result is obtained.
The specific embodiment of step S15 has related description in the above-described embodiments, can equally be well applied to the present embodiment,
Excessive description is not just remake herein.
Wherein, the specific implementation of step S15 includes:
S41 calculates the face feature information of the collected object and the face feature Model Matching of the authorized user
Similarity degree value;
S42 determines that the matching result is when the similarity degree value is greater than or equal to default similarity degree threshold value
With success;
S43 determines that the matching result loses for matching when the similarity degree value is less than default similarity degree threshold value
It loses.
Remote control center will be got in the face feature information of the Li Si got in step S11 and step S14
There is the face of the monitoring area authorized user of one-to-one relationship or binding relationship with the coding for the safety cap worn on Li Si's head
Portion's characteristic model is matched, similarity degree value between the two is calculated, face feature information and authorized user as Li Si
When matching similarity degree value between face feature model is greater than or equal to default similarity degree threshold value, determine matching result for matching
Success similarly when the similarity degree value is less than default similarity degree threshold value, determines that matching result is that it fails to match.
S16, when the face feature information of the collected object and the face feature mould of the monitoring area authorized user
When the matching result of type is successful match, determining allows the collected object to enter the monitoring area.
The specific embodiment of step S16 has related description in the above-described embodiments, can equally be well applied to the present embodiment,
Excessive description is not just remake herein.
The utility model has the advantages that the embodiment of the present invention by when monitoring area pre-set image acquisition range in have collected object into
It is fashionable, the image information of collected object is acquired, and the face feature information of object is collected according to image information acquisition, then
According to acquired image information, detect whether collected object wears safety cap using image matching algorithm, when detecting
When collected subject wears have safety cap, the coding of safety cap is obtained, according to the coding of the safety cap, is obtained and the coding
The face feature model of the monitoring area authorized user with one-to-one relationship, it is finally that the face of collected object is special
Reference breath is matched with the face feature model of monitoring area authorized user, obtains matching result, when the face of collected object
When the matching result of portion's characteristic information and the face feature model of monitoring area authorized user is successful match, determining allows to be adopted
Collect object and enter the monitoring area, can be realized the security management and control of one people of construction site, one cap, moreover it is possible to monitoring system be effectively reduced
The loss of system hardware device.
Further, preferred embodiment, the above method further include:
When detecting that the collected object do not wear the face feature information of safety cap or the collected object
When matching result with the face feature model of the monitoring area authorized user is that it fails to match, according to the collected object
Face feature information, judge the collected object whether be the monitoring area authorized user;
When the collected object is the authorized user of the monitoring area, the basic letter of the collected object is obtained
The essential information of the collected object is added to default blacklist library by breath, and determine do not allow the collected object into
Enter the monitoring area;Wherein, the essential information of the collected object includes the name of collected object, position, affiliated portion
Door, work number and contact method;
When the collected object is not the authorized user of the monitoring area, warning message is sent to administrator.
When determining Li Si is that this project under construction or this construction group enter the unauthorized user of monitoring area, directly to management
Member sends warning message, which can be sent to the mobile terminal of administrator in a manner of voice, such as mobile phone, right
It says machine etc., is also possible to SMS prompt, can also directly be broadcasted in a broadcast manner in building site, such as: " vigilant!There is stranger
It swarms into." when Li Si is the authorized user of monitoring area, determine that the non-safe wearing cap of Li Si or safety cap wear irregularity, from
The essential information of Li Si is transferred in authorized user's essential information library of pre-set monitoring area, and is shown in display window,
Such as " name: Li Si;Position: welder;The department: one group of welding;Work number: xxyyzz ... " adds above-mentioned essential information
To blacklist library, does not allow Li Si to enter at construction B and construct.
The utility model has the advantages that when detecting that collected object does not wear the face feature information of safety cap or collected object
It is special according to the face of collected object when matching result with the face feature model of monitoring area authorized user is that it fails to match
Reference breath, judge collected object whether be monitoring area authorized user, be not to alarm, be the authorized user of monitoring area
Then determine that non-safe wearing cap or safety cap wear irregularity, which is added to blacklist library, is further improved
The tightness of one people of building site, one capped pipe control.
Further, preferred embodiment is added to default blacklist library in the essential information by the collected object
The step of before, the method also includes:
Default blacklist library is traversed according to the work number of the collected object, counts the work number of the collected object in institute
State the frequency occurred in default blacklist library;
When the frequency that the work number of the collected object occurs in the default blacklist library is equal to or more than on default
When limit value, the step of essential information by the collected object is added to default blacklist library is executed.
Further, preferred embodiment, the above method further include: when the work number of the collected object presets black name described
When the frequency occurred in single library is less than preset upper limit value, determining allows the collected object to enter the monitoring area.
The essential information for the monitoring area authorized user that non-safe wearing cap and safety cap wear irregularity is added to pre-
If blacklist library, determine whether that this kind of people enters construction site according to the frequency that this kind of user occurs in blacklist
Monitoring area is conducive to the consciousness for improving monitoring area authorized user safe wearing cap.
Here, the implementation procedure of the building site monitoring method in this programme based on image analysis for ease of understanding, in this implementation
In example, wanted with a certain collected object through the gate inhibition of construction site or gate passage, or unidentified is adopted to a certain
Collection object activity in construction site is monitored for analysis, illustrates the stream of the above-mentioned building site monitoring method based on image analysis
Journey.Specifically, shown in Figure 5, process is as follows in this example:
S501, distributed image acquisition terminal acquire image and obtain the face feature information of collected object;
S502 judges whether safe wearing cap, if so, S503 is thened follow the steps, if it is not, thening follow the steps S504;
S503 obtains safety cap coding;
S504 judges whether it is authorized user, if so, S510 is thened follow the steps, if it is not, thening follow the steps S509;
S505 obtains the face feature model that one-to-one authorized user is encoded with safety cap;
Face feature information is matched with the face feature model of authorized user, obtains matching result by S506;
S507, judge matching result whether successful match, if so, S508 is thened follow the steps, if it is not, thening follow the steps
S504;
S508 allows collected object to enter;
S509 sends warning message to administrator;
S510 obtains essential information, traverses blacklist library;
S511 judges whether blacklist library frequency is more than the upper limit, if so, S512 is thened follow the steps, if it is not, thening follow the steps
S513;
S512 does not allow collected object to enter;
S513 is added to blacklist library;
S514 terminates process.
It will be apparent that the work based on image analysis by the process demonstration in above-mentioned example, in the embodiment of the present invention
Ground monitoring method is compared with the prior art, more effective to the monitoring in building site, tighter, the manpower of relative reduction engineering quotient at
This, being able to solve on construction site often has the problem of unauthorized people enters monitoring area, realizes the bursting tube of one cap of a people
Control.
Embodiment three
Shown in Figure 6, the specific embodiment of one aspect of the present invention provides a kind of building site monitoring based on image analysis
Device should include memory 61, processor 62 based on the building site monitoring device 6 of image analysis and be stored in memory 61 simultaneously
The computer program 63 that can be run on the processor 62, the processor 62 are realized above-mentioned based on figure when executing computer program 63
The step of building site monitoring method of picture analysis.
Specifically, processor 62 realizes following steps when executing computer program 63: when the pre-set image of monitoring area is adopted
When thering is collected object to enter in collection range, the image letter for the collected object that described image acquisition terminal is sent is received
Breath, and the face feature information of the collected object according to described image acquisition of information;According to described image information, institute is detected
State whether collected object wears safety cap;When detecting that the collected subject wears have safety cap, the peace is obtained
The coding of full cap;According to the coding of the safety cap, the monitoring area that there is one-to-one relationship with the coding is obtained
The face feature model of authorized user;By the face feature information of the collected object with the monitoring area authorized user's
Face feature model is matched, and matching result is obtained;Face feature information and the monitored space when the collected object
When the matching result of the face feature model of domain authorized user is successful match, determining allows described in the collected object entrance
Monitoring area.
Preferably, following steps are also realized when processor 62 executes computer program 63: when detecting described collected pair
As not wearing the face feature information of safety cap or the collected object and the face of the monitoring area authorized user
When the matching result of characteristic model is that it fails to match, according to the face feature information of the collected object, described adopted is judged
Collection object whether be the monitoring area authorized user;When the collected object is the authorized user of the monitoring area
When, the essential information of the collected object is obtained, the essential information of the collected object is added to default blacklist library,
And determining does not allow the collected object to enter the monitoring area;Wherein, the essential information of the collected object includes
Name, position, affiliated function, work number and the contact method of collected object;
Preferably, following steps are also realized when processor 62 executes computer program 63: will be adopted using image matching algorithm
The image information and the preset image that compares collected carries out Feature Points Matching, obtains Feature Points Matching rate value;Wherein, institute
State the standard wearing schematic for comparing that image is the safety cap;Judged according to the Feature Points Matching rate value described collected
Whether object wears safety cap.
Preferably, following steps are also realized when processor 62 executes computer program 63: when the Feature Points Matching ratio
Value level off to threshold value when, it is determined that the acquisition target wear safety cap;When the Feature Points Matching rate value is discrete in threshold
When value, it is determined that the acquisition target does not wear safety cap.
Preferably, following steps are also realized when processor 62 executes computer program 63: based on safety cap coding
Key, obtaining from preset face feature model table with the coding there is the monitoring area of one-to-one relationship to award
Weigh the face feature model of user;Wherein, record has the corresponding all peaces of the monitoring area in the face feature model table
Full cap coding and each safety cap encode the face feature model of corresponding monitoring area authorized user.
Preferably, following steps are also realized when processor 62 executes computer program 63: calculating the collected object
The similarity degree value of face feature information and the face feature Model Matching of the authorized user;When the similarity degree value is greater than
Or when being equal to default similarity degree threshold value, determine the matching result for successful match;It is preset when the similarity degree value is less than
When similarity degree threshold value, determine that the matching result is that it fails to match.
Preferably, following steps are also realized when processor 62 executes computer program 63: according to the collected object
Work number traverses default blacklist library, counts the frequency that the work number of the collected object occurs in the default blacklist library;
When the frequency that the work number of the collected object occurs in the default blacklist library is equal to or more than preset upper limit value, hold
The step of row essential information by the collected object is added to default blacklist library.
Preferably, following steps are also realized when processor 62 executes computer program 63: when the work of the collected object
When number frequency occurred in the default blacklist library is less than preset upper limit value, determining allows the collected object to enter institute
State monitoring area.
That is, in a specific embodiment of the present invention, based on the execution of the processor 62 of the building site monitoring device 6 of image analysis
The step of above-mentioned building site monitoring method based on image analysis is realized when calculation machine program 63, is able to solve on construction site often
There is unauthorized people to occur, realizes the one capped pipe control of a people of building site monitoring area, avoid that accident occurs.
Illustratively, the above-mentioned building site monitoring device 6 based on image analysis can be computer, notebook, remote service
The service equipments such as device, cloud server and remote control center.Building site monitoring device 6 based on image analysis may include, but not
It is only limitted to processor 62, memory 61.It will be understood by those skilled in the art that the schematic diagram is only based on image analysis
The example of building site monitoring device 6 does not constitute the restriction to the building site monitoring device 6 based on image analysis, may include than figure
Show more or fewer components, perhaps combines certain components or different components.
It should be noted that the processor 62 due to the building site monitoring device 6 based on image analysis executes computer program
The step of above-mentioned building site monitoring method based on image analysis is realized when 63, therefore the above-mentioned building site monitoring based on image analysis
All embodiments of method are suitable for the building site monitoring device 6 based on image analysis, and can reach the same or similar
Beneficial effect.
Example IV
The one side of the embodiment of the present invention additionally provides a kind of computer readable storage medium, computer readable storage medium
It is stored with computer program, which realizes the above-mentioned building site monitoring side based on image analysis when being executed by processor
The step of method.
Specifically, realizing following steps when computer program is executed by processor: when the pre-set image of monitoring area acquires
When having collected object to enter in range, the image information for the collected object that described image acquisition terminal is sent is received,
And the face feature information of object is collected according to described image acquisition of information;According to described image information, described in detection
Whether collected object wears safety cap;When detecting that the collected subject wears have safety cap, the safety is obtained
The coding of cap;According to the coding of the safety cap, obtaining with the coding there is the monitoring area of one-to-one relationship to award
Weigh the face feature model of user;By the face of the face feature information of the collected object and the monitoring area authorized user
Portion's characteristic model is matched, and matching result is obtained;When the face feature information and the monitoring area of the collected object
When the matching result of the face feature model of authorized user is successful match, determining allows the collected object to enter the prison
Control region.
Preferably, following steps are also realized when computer program is executed by processor: when detecting the collected object
The face of face feature information and the monitoring area authorized user not with safety cap or the collected object is special
When the matching result for levying model is that it fails to match, according to the face feature information of the collected object, judge described collected
Object whether be the monitoring area authorized user;When the collected object is the authorized user of the monitoring area,
The essential information of the collected object is added to default blacklist library by the essential information for obtaining the collected object, and
Determining does not allow the collected object to enter the monitoring area;Wherein, the essential information of the collected object includes quilt
Name, position, affiliated function, work number and the contact method of acquisition target;When the collected object is not the monitoring area
Authorized user when, to administrator send warning message.
Preferably, following steps are also realized when computer program is executed by processor: will be acquired using image matching algorithm
To image information and it is preset compare image carry out Feature Points Matching, obtain Feature Points Matching rate value;Wherein, described
Compare the standard wearing schematic that image is the safety cap;Described collected pair is judged according to the Feature Points Matching rate value
As if it is no with safety cap.
Preferably, following steps are also realized when computer program is executed by processor: when the Feature Points Matching rate value
Level off to threshold value when, it is determined that the acquisition target wear safety cap;When the Feature Points Matching rate value is discrete in threshold value
When, it is determined that the acquisition target does not wear safety cap.
Preferably, following steps are also realized when computer program is executed by processor: major key is encoded to the safety cap,
The monitoring area authorization that there is one-to-one relationship with the coding is obtained from preset face feature model table
The face feature model of user;Wherein, record has the corresponding all safety of the monitoring area in the face feature model table
Cap coding and each safety cap encode the face feature model of corresponding monitoring area authorized user.
Preferably, following steps are also realized when computer program is executed by processor: calculating the face of the collected object
The similarity degree value of the face feature Model Matching of portion's characteristic information and the authorized user;Be greater than when the similarity degree value or
When equal to default similarity degree threshold value, the matching result is determined for successful match, when the similarity degree value is less than default phase
When like degree threshold value, determine that the matching result is that it fails to match.
Preferably, following steps are also realized when computer program is executed by processor: according to the work of the collected object
Number default blacklist library is traversed, counts the frequency that the work number of the collected object occurs in the default blacklist library;When
When the frequency that the work number of the collected object occurs in the default blacklist library is equal to or more than preset upper limit value, execute
The step of essential information by the collected object is added to default blacklist library.
Preferably, following steps are also realized when computer program is executed by processor: when the work number of the collected object
When the frequency occurred in the default blacklist library is less than preset upper limit value, determining allows described in the collected object entrance
Monitoring area.
That is, being realized when the computer program of computer readable storage medium is executed by processor above-mentioned based on image analysis
Building site monitoring method the step of, being able to solve on construction site often has unauthorized people to occur, and realizes building site monitoring area
One people, one capped pipe control, avoids that accident occurs.
Illustratively, the computer program of computer readable storage medium includes computer program code, the computer
Program code can be source code form, object identification code form, executable file or certain intermediate forms etc..The computer can
Reading medium may include: any entity or device, recording medium, USB flash disk, mobile hard that can carry the computer program code
Disk, magnetic disk, CD, computer storage, read-only memory (ROM, Read-Only Memory), random access memory
(RAM, Random Access Memory), electric carrier signal, telecommunication signal and software distribution medium etc..
It should be noted that the computer program due to computer readable storage medium realized when being executed by processor it is above-mentioned
The building site monitoring method based on image analysis the step of, therefore all realities of the above-mentioned building site monitoring method based on image analysis
It applies example and is suitable for the computer readable storage medium, and can reach the same or similar beneficial effect.
The embodiment of the present invention has been described in detail above, specific case used herein to the principle of the present invention and
Embodiment is expounded, and the above description of the embodiment is only used to help understand the method for the present invention and its core ideas;
At the same time, for those skilled in the art can in specific embodiments and applications according to the thought of the present invention
There is change place, in conclusion the contents of this specification are not to be construed as limiting the invention.
Claims (10)
1. a kind of building site monitoring method based on image analysis, which is characterized in that the described method includes:
When thering is collected object to enter in the pre-set image acquisition range of monitoring area, the image of the collected object is acquired
Information, and the face feature information of the collected object according to described image acquisition of information;
According to described image information, detect whether the collected object wears safety cap;
When detecting that the collected subject wears have safety cap, the coding of the safety cap is obtained;
According to the coding of the safety cap, the monitoring area authorized user that there is one-to-one relationship with the coding is obtained
Face feature model;
By the progress of the face feature model of the face feature information of the collected object and the monitoring area authorized user
Match, obtains matching result;
When the matching of the face feature model of the face feature information and monitoring area authorized user of the collected object
When being as a result successful match, determining allows the collected object to enter the monitoring area.
2. the method according to claim 1, wherein the method also includes:
When detecting that the collected object do not wear face feature information and the institute of safety cap or the collected object
When the matching result for stating the face feature model of monitoring area authorized user is that it fails to match, according to the face of the collected object
Portion's characteristic information, judge the collected object whether be the monitoring area authorized user;
When the collected object is the authorized user of the monitoring area, the essential information of the collected object is obtained,
The essential information of the collected object is added to default blacklist library, and determination does not allow the collected object to enter institute
State monitoring area;Wherein, the essential information of the collected object includes the name of collected object, position, affiliated function, work
Number and contact method;
When the collected object is not the authorized user of the monitoring area, warning message is sent to administrator.
3. detection is described collected the method according to claim 1, wherein described according to described image information
The step of whether object wears safety cap, specifically includes:
Acquired image information and the preset image that compares are carried out by Feature Points Matching using image matching algorithm, obtained
Feature Points Matching rate value;Wherein, described to compare the standard wearing schematic that image is the safety cap;
Judge whether the collected object wears safety cap according to the Feature Points Matching rate value.
4. according to the method described in claim 3, it is characterized in that, described according to Feature Points Matching rate value judgement
The step of whether collected object wears safety cap, specifically includes:
When the Feature Points Matching rate value levels off to threshold value, it is determined that the acquisition target wears safety cap;
When the Feature Points Matching rate value is discrete when threshold value, it is determined that the acquisition target does not wear safety cap.
5. the method according to claim 1, wherein the coding according to the safety cap, obtain with it is described
Coding has the step of face feature model of the monitoring area authorized user of one-to-one relationship, specifically includes:
It is encoded to major key with the safety cap, obtaining from preset face feature model table has one by one with the coding
The face feature model of the monitoring area authorized user of corresponding relationship;Wherein, recording in the face feature model table has
The corresponding all safety cap codings of monitoring area and each safety cap encode the face of corresponding monitoring area authorized user
Portion's characteristic model.
6. the method according to claim 1, wherein the face feature information by the collected object with
The step of face feature model of the monitoring area authorized user matches, obtains matching result, specifically includes:
Calculate the similar journey of the face feature information of the collected object and the face feature Model Matching of the authorized user
Angle value;
When the similarity degree value is greater than or equal to default similarity degree threshold value, determine the matching result for successful match;
When the similarity degree value is less than default similarity degree threshold value, determine that the matching result is that it fails to match.
7. according to the method described in claim 2, it is characterized in that, being added in the essential information by the collected object
Before the step of to default blacklist library, the method also includes:
Default blacklist library is traversed according to the work number of the collected object, counts the work number of the collected object described pre-
If the frequency occurred in blacklist library;
When the frequency that the work number of the collected object occurs in the default blacklist library is equal to or more than preset upper limit value
When, execute the step of essential information by the collected object is added to default blacklist library.
8. the method according to the description of claim 7 is characterized in that the method also includes:
When the frequency that the work number of the collected object occurs in the default blacklist library is less than preset upper limit value, determine
The collected object is allowed to enter the monitoring area.
9. a kind of building site monitoring device based on image analysis, including memory, processor and storage are in the memory
And the computer program that can be run on the processor, which is characterized in that when the processor executes the computer program
The step of realizing the building site monitoring method as claimed in any one of claims 1 to 8 based on image analysis.
10. a kind of computer readable storage medium, the computer-readable recording medium storage has computer program, and feature exists
In the computer program realizes the work as claimed in any one of claims 1 to 8 based on image analysis when being executed by processor
The step of ground monitoring method.
Priority Applications (2)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201810830408.XA CN109344679A (en) | 2018-07-25 | 2018-07-25 | Building site monitoring method, device and readable storage medium storing program for executing based on image analysis |
PCT/CN2018/124839 WO2020019673A1 (en) | 2018-07-25 | 2018-12-28 | Construction site monitoring method and device based on image analysis, and readable storage medium |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201810830408.XA CN109344679A (en) | 2018-07-25 | 2018-07-25 | Building site monitoring method, device and readable storage medium storing program for executing based on image analysis |
Publications (1)
Publication Number | Publication Date |
---|---|
CN109344679A true CN109344679A (en) | 2019-02-15 |
Family
ID=65291684
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN201810830408.XA Pending CN109344679A (en) | 2018-07-25 | 2018-07-25 | Building site monitoring method, device and readable storage medium storing program for executing based on image analysis |
Country Status (2)
Country | Link |
---|---|
CN (1) | CN109344679A (en) |
WO (1) | WO2020019673A1 (en) |
Cited By (7)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN110533811A (en) * | 2019-08-28 | 2019-12-03 | 深圳市万睿智能科技有限公司 | The method and device and system and storage medium of safety cap inspection are realized based on SSD |
CN111178246A (en) * | 2019-12-27 | 2020-05-19 | 深圳供电局有限公司 | Remote monitoring method and device based on electric power construction operation and computer equipment |
CN111443633A (en) * | 2020-04-13 | 2020-07-24 | 深圳市水务技术服务有限公司 | Remote monitoring management method, device and equipment for integrated pump station and storage medium |
CN112016777A (en) * | 2019-05-30 | 2020-12-01 | 上海若泰工程建设管理技术有限公司 | Railway construction engineering quality safety management system and method |
CN113469043A (en) * | 2021-06-30 | 2021-10-01 | 南方科技大学 | Method and device for detecting wearing state of safety helmet, computer equipment and storage medium |
CN113570756A (en) * | 2021-06-18 | 2021-10-29 | 广联达科技股份有限公司 | Personnel counting method and device and electronic equipment |
CN113741317A (en) * | 2021-09-16 | 2021-12-03 | 镇江绿建工程咨询有限公司 | Solar-powered intelligent dangerous area person approaching detection system for construction site |
Families Citing this family (10)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN111753705B (en) * | 2020-06-19 | 2023-11-03 | 神思电子技术股份有限公司 | Intelligent construction site safety operation detection method based on video analysis |
CN111860256A (en) * | 2020-07-10 | 2020-10-30 | 云镝智慧科技有限公司 | Security detection method and device, computer equipment and storage medium |
CN112232239A (en) * | 2020-10-20 | 2021-01-15 | 华雁智能科技(集团)股份有限公司 | Substation construction safety signboard monitoring method and device and electronic equipment |
CN113408365B (en) * | 2021-05-26 | 2023-09-08 | 广东能源集团科学技术研究院有限公司 | Safety helmet identification method and device under complex scene |
CN113343846B (en) * | 2021-06-04 | 2024-03-15 | 温州大学 | Reflective clothing detecting system based on depth layer feature fusion |
CN113837030B (en) * | 2021-09-06 | 2024-03-22 | 中国福利会国际和平妇幼保健院 | Personnel intelligent management and control method and system for epidemic situation prevention and control and computer equipment |
CN114063489A (en) * | 2021-09-26 | 2022-02-18 | 中通服和信科技有限公司 | Wisdom gating system based on 3D is visual and internet of things |
CN114155669A (en) * | 2021-11-30 | 2022-03-08 | 安徽富煌钢构股份有限公司 | Building construction safety early warning protection system based on BIM |
CN115588167A (en) * | 2022-12-08 | 2023-01-10 | 山东法尔智能科技有限公司 | Safety monitoring method and system for engineering construction |
CN116758269B (en) * | 2023-08-22 | 2023-11-14 | 雄安雄创数字技术有限公司 | Position verification method |
Citations (7)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN102829788A (en) * | 2012-08-27 | 2012-12-19 | 北京百度网讯科技有限公司 | Live action navigation method and live action navigation device |
KR20130115749A (en) * | 2012-04-13 | 2013-10-22 | 경기대학교 산학협력단 | Intrusion detection system using mining based pattern analysis in smart home |
CN104517206A (en) * | 2013-09-27 | 2015-04-15 | 中国移动通信集团黑龙江有限公司 | Business processing method and device |
CN106778609A (en) * | 2016-12-15 | 2017-05-31 | 国网浙江省电力公司杭州供电公司 | A kind of electric power construction field personnel uniform wears recognition methods |
CN106993168A (en) * | 2017-04-28 | 2017-07-28 | 珠海格力电器股份有限公司 | A kind of monitoring method, device, electronic equipment and system |
CN108198318A (en) * | 2018-02-09 | 2018-06-22 | 厦门路桥信息股份有限公司 | A kind of system of real name channel guard method and system |
CN108287833A (en) * | 2017-01-09 | 2018-07-17 | 北京艺鉴通科技有限公司 | It is a kind of for the art work identification to scheme to search drawing method |
Family Cites Families (3)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN104506562A (en) * | 2015-01-13 | 2015-04-08 | 东北大学 | Two-dimension code and face recognition fused conference identity authentication device and method |
CN108198281A (en) * | 2017-12-15 | 2018-06-22 | 四川省大益科技有限公司 | Intelligent barrier gate Field Monitoring System and its control method |
CN107944838A (en) * | 2017-12-18 | 2018-04-20 | 四川省大益科技有限公司 | A kind of intelligent barrier gate Field Monitoring System and method |
-
2018
- 2018-07-25 CN CN201810830408.XA patent/CN109344679A/en active Pending
- 2018-12-28 WO PCT/CN2018/124839 patent/WO2020019673A1/en active Application Filing
Patent Citations (7)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
KR20130115749A (en) * | 2012-04-13 | 2013-10-22 | 경기대학교 산학협력단 | Intrusion detection system using mining based pattern analysis in smart home |
CN102829788A (en) * | 2012-08-27 | 2012-12-19 | 北京百度网讯科技有限公司 | Live action navigation method and live action navigation device |
CN104517206A (en) * | 2013-09-27 | 2015-04-15 | 中国移动通信集团黑龙江有限公司 | Business processing method and device |
CN106778609A (en) * | 2016-12-15 | 2017-05-31 | 国网浙江省电力公司杭州供电公司 | A kind of electric power construction field personnel uniform wears recognition methods |
CN108287833A (en) * | 2017-01-09 | 2018-07-17 | 北京艺鉴通科技有限公司 | It is a kind of for the art work identification to scheme to search drawing method |
CN106993168A (en) * | 2017-04-28 | 2017-07-28 | 珠海格力电器股份有限公司 | A kind of monitoring method, device, electronic equipment and system |
CN108198318A (en) * | 2018-02-09 | 2018-06-22 | 厦门路桥信息股份有限公司 | A kind of system of real name channel guard method and system |
Cited By (9)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN112016777A (en) * | 2019-05-30 | 2020-12-01 | 上海若泰工程建设管理技术有限公司 | Railway construction engineering quality safety management system and method |
CN110533811A (en) * | 2019-08-28 | 2019-12-03 | 深圳市万睿智能科技有限公司 | The method and device and system and storage medium of safety cap inspection are realized based on SSD |
CN111178246A (en) * | 2019-12-27 | 2020-05-19 | 深圳供电局有限公司 | Remote monitoring method and device based on electric power construction operation and computer equipment |
CN111178246B (en) * | 2019-12-27 | 2024-02-09 | 深圳供电局有限公司 | Remote monitoring method and device based on electric power construction operation and computer equipment |
CN111443633A (en) * | 2020-04-13 | 2020-07-24 | 深圳市水务技术服务有限公司 | Remote monitoring management method, device and equipment for integrated pump station and storage medium |
CN113570756A (en) * | 2021-06-18 | 2021-10-29 | 广联达科技股份有限公司 | Personnel counting method and device and electronic equipment |
CN113570756B (en) * | 2021-06-18 | 2023-02-10 | 广联达科技股份有限公司 | Personnel counting method and device and electronic equipment |
CN113469043A (en) * | 2021-06-30 | 2021-10-01 | 南方科技大学 | Method and device for detecting wearing state of safety helmet, computer equipment and storage medium |
CN113741317A (en) * | 2021-09-16 | 2021-12-03 | 镇江绿建工程咨询有限公司 | Solar-powered intelligent dangerous area person approaching detection system for construction site |
Also Published As
Publication number | Publication date |
---|---|
WO2020019673A1 (en) | 2020-01-30 |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
CN109344679A (en) | Building site monitoring method, device and readable storage medium storing program for executing based on image analysis | |
CN107590439B (en) | Target person identification and tracking method and device based on monitoring video | |
CN102663444B (en) | Method for preventing account number from being stolen and system thereof | |
CN110650316A (en) | Intelligent patrol and early warning processing method and device, electronic equipment and storage medium | |
CN206557873U (en) | A kind of anti-entrance system of intelligent security based on recognition of face | |
CN107578519A (en) | A kind of intelligent access control system and intelligent entrance guard method for unlocking | |
CN201845368U (en) | Human face and fingerprint access control with living body detection function | |
CN101496074A (en) | Device and method for detecting suspicious activity, program, and recording medium | |
CN109886697A (en) | Method, apparatus and electronic equipment are determined based on the other operation of expression group | |
EP3514760B1 (en) | Method and system for privacy compliant data recording | |
CN107577930B (en) | Unlocking detection method of touch screen terminal and touch screen terminal | |
KR100824757B1 (en) | Gait recognition method | |
CN111931567B (en) | Human body identification method and device, electronic equipment and storage medium | |
CN105574477A (en) | Secure anti-theft method, apparatus and system | |
CN112861826B (en) | Coal mine supervision method, system, equipment and storage medium based on video image | |
CN109448194A (en) | Intrusion detecting tracking system and method | |
CN109145556A (en) | A kind of Computer Intelligent Control System | |
CN111613253A (en) | Data acquisition method, data acquisition equipment and data acquisition system | |
CN105872466A (en) | Alarm method and alarm device based on smart TV | |
CN105184236A (en) | Robot-based face identification system | |
CN114898443A (en) | Face data acquisition method and device | |
CN109446774B (en) | Identity recognition application method and system | |
CN110895602B (en) | Identity authentication method and device, electronic equipment and storage medium | |
CN110633623A (en) | Management and control method for operation process of transformer substation worker | |
CN111507294B (en) | Classroom security early warning system and method based on three-dimensional face reconstruction and intelligent recognition |
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 | ||
RJ01 | Rejection of invention patent application after publication | ||
RJ01 | Rejection of invention patent application after publication |
Application publication date: 20190215 |