CN108985267A - Auditorium identity scene identification system - Google Patents
Auditorium identity scene identification system Download PDFInfo
- Publication number
- CN108985267A CN108985267A CN201810920632.8A CN201810920632A CN108985267A CN 108985267 A CN108985267 A CN 108985267A CN 201810920632 A CN201810920632 A CN 201810920632A CN 108985267 A CN108985267 A CN 108985267A
- Authority
- CN
- China
- Prior art keywords
- image
- equipment
- spectators
- processing
- segmentation threshold
- 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
- 238000012545 processing Methods 0.000 claims abstract description 65
- 238000005259 measurement Methods 0.000 claims abstract description 6
- 230000011218 segmentation Effects 0.000 claims description 69
- 238000001914 filtration Methods 0.000 claims description 30
- 238000004458 analytical method Methods 0.000 claims description 22
- 230000010354 integration Effects 0.000 claims description 18
- 230000001815 facial effect Effects 0.000 claims description 15
- 238000009826 distribution Methods 0.000 claims description 13
- 238000007781 pre-processing Methods 0.000 claims description 12
- 238000000034 method Methods 0.000 claims description 11
- 238000004891 communication Methods 0.000 claims description 4
- 230000008901 benefit Effects 0.000 claims description 3
- 239000003086 colorant Substances 0.000 claims description 3
- 238000004540 process dynamic Methods 0.000 claims description 3
- 230000000717 retained effect Effects 0.000 claims description 3
- 238000005516 engineering process Methods 0.000 description 6
- 230000005540 biological transmission Effects 0.000 description 5
- 230000003044 adaptive effect Effects 0.000 description 4
- 238000001228 spectrum Methods 0.000 description 4
- 230000001413 cellular effect Effects 0.000 description 3
- 238000012986 modification Methods 0.000 description 3
- 230000004048 modification Effects 0.000 description 3
- 238000001514 detection method Methods 0.000 description 2
- 239000004744 fabric Substances 0.000 description 2
- 241000208340 Araliaceae Species 0.000 description 1
- 235000005035 Panax pseudoginseng ssp. pseudoginseng Nutrition 0.000 description 1
- 235000003140 Panax quinquefolius Nutrition 0.000 description 1
- 238000004378 air conditioning Methods 0.000 description 1
- 238000013459 approach Methods 0.000 description 1
- 230000001174 ascending effect Effects 0.000 description 1
- 230000007812 deficiency Effects 0.000 description 1
- 238000013461 design Methods 0.000 description 1
- 238000011161 development Methods 0.000 description 1
- 230000018109 developmental process Effects 0.000 description 1
- 235000008434 ginseng Nutrition 0.000 description 1
- 238000004519 manufacturing process Methods 0.000 description 1
- 238000000926 separation method Methods 0.000 description 1
- XLYOFNOQVPJJNP-UHFFFAOYSA-N water Substances O XLYOFNOQVPJJNP-UHFFFAOYSA-N 0.000 description 1
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V20/00—Scenes; Scene-specific elements
- G06V20/50—Context or environment of the image
- G06V20/52—Surveillance or monitoring of activities, e.g. for recognising suspicious objects
- G06V20/53—Recognition of crowd images, e.g. recognition of crowd congestion
-
- 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
- G06V10/20—Image preprocessing
- G06V10/26—Segmentation of patterns in the image field; Cutting or merging of image elements to establish the pattern region, e.g. clustering-based techniques; Detection of occlusion
- G06V10/267—Segmentation of patterns in the image field; Cutting or merging of image elements to establish the pattern region, e.g. clustering-based techniques; Detection of occlusion by performing operations on regions, e.g. growing, shrinking or watersheds
Landscapes
- Engineering & Computer Science (AREA)
- Business, Economics & Management (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Theoretical Computer Science (AREA)
- Multimedia (AREA)
- Tourism & Hospitality (AREA)
- Educational Administration (AREA)
- Development Economics (AREA)
- Computer Security & Cryptography (AREA)
- Health & Medical Sciences (AREA)
- Economics (AREA)
- General Health & Medical Sciences (AREA)
- Human Resources & Organizations (AREA)
- Marketing (AREA)
- Primary Health Care (AREA)
- Strategic Management (AREA)
- General Business, Economics & Management (AREA)
- Image Analysis (AREA)
Abstract
The present invention relates to a kind of auditorium identity scene identification systems, comprising: the right opposite in stage performance place is arranged in spectators' seating arrangements, for providing viewing location for each spectators of viewing stage performance;Field camera structure, spectators' seating arrangements for the right opposite to stage performance place carry out live camera shooting, to obtain corresponding spectators seat image;First analytical equipment is connect with the field camera structure, is measured for the contrast to spectators seat image, and is exported measurement result as real time contrast;Second analytical equipment, it is connect respectively with the field camera structure and first analytical equipment, uniform piecemeal processing is carried out to spectators seat image for receiving the real time contrast and spectators seat image, and based on the real time contrast, to obtain corresponding multiple subgraphs.By means of the invention it is possible to improve the security dynamics at stage scene.
Description
Technical field
The present invention relates to stage security field more particularly to a kind of auditorium identity scene identification systems.
Background technique
Auditorium can be divided into short row's method: hard chair is no less than 0.80m, and soft chair is no less than 0.90m, step ground array pitch
Should suitably it increase, the horizontal distance of the chair back to a row behind most protrusion is no less than 0.30m;Long row's method: hard chair is not answered small
In 1.00m;Soft chair is no less than 1.10m.Step ground array pitch should suitably increase, the chair back to a row behind most protrusion water
Flat distance is no less than 0.50m;Rearward when wall setting seat, last row's seat array pitch of balcony and stall should at least increase
0.12m.Latter row seat should at least improve 0.12 meter than previous row seat.Away from cannot be less than for hard chair in the handrail of seat
0.5 meter;It cannot be less than 0.55 meter for soft chair.
Summary of the invention
In order to solve the technical issues of stage lacks the security system except entrance, the present invention provides a kind of auditorium bodies
The live identification system of part, is customized each spectators in spectators' seating arrangements of the right opposite in stage performance place high-precision
Image authentication is spent, and when identifying successfully, the wanted circular number of corresponding suspect is issued, effectively to safeguard stage site safety;It builds
The adaptive adjustment modes based on global threshold adjustment piecemeal threshold value are found, so that target detection takes into account whole feature and has spy
Point guarantees the validity of the target image to be processed for subsequent image processing;By being realized to based on image real time contrast
To the dividing processing of field camera structure output image, and based on the signature analysis to the subgraph after segmentation, the scene of determination is taken the photograph
Whether the image of camera structure output reaches focusing standard, to facilitate field camera structure to focus in time;Assembled according to image energy
Situation determines adaptive orientation band gain Promotion Strategy, ensure that the directionality and validity of image procossing.
According to an aspect of the present invention, a kind of auditorium identity scene identification system is provided, the system comprises:
The right opposite in stage performance place is arranged in spectators' seating arrangements, for each spectators to watch stage performance
Viewing location is provided;
Field camera structure, spectators' seating arrangements for the right opposite to stage performance place carry out live camera shooting, with
Obtain corresponding spectators seat image;
First analytical equipment is connect with the field camera structure, for the contrast to spectators seat image into
Row measurement, and exported measurement result as real time contrast;
Second analytical equipment is connect, for receiving respectively with the field camera structure and first analytical equipment
Real time contrast and spectators seat image are stated, and spectators seat image is carried out uniformly based on the real time contrast
Piecemeal processing, to obtain corresponding multiple subgraphs;
First processing equipment is connect with second analytical equipment, for receiving the multiple subgraph, and for each
A subgraph executes following processing: the R channel value of each pixel of the subgraph is obtained, by each picture of the subgraph
The R channel value of vegetarian refreshments is added, and the result after will add up is exported as the color parameter of the subgraph;
Second processing equipment is connect with first processing equipment, for receiving each color parameter of each subgraph,
And when all colours parameter is fallen in parameter preset threshold range, first control signal is issued, and there are color parameters
When falling in outside parameter preset threshold range, second control signal is issued;
Data output apparatus is connect, for receiving respectively with the second processing equipment and the field camera structure
When to the first control signal, focusing prompt information is sent to the field camera structure, be also used to receive it is described
When second control signal, any information is not sent to the field camera structure;
Global analysis equipment is connect with the field camera structure, for receiving spectators seat image, based on described
The distribution situation of the pixel value of each pixel determines the corresponding entirety point of spectators seat image inside spectators seat image
Cut threshold value;
Analysis of Contrast equipment, for receiving spectators seat image, to the spectators seat image degree of comparing
Analysis, to obtain and export corresponding contrast;
Self-adaptive processing equipment is connect with the Analysis of Contrast equipment, for receiving the contrast, and based on described
Contrast carries out image dividing processing to spectators seat image, to obtain multiple subgraphs, wherein the contrast is got over
The quantity of height, the subgraph of acquisition is more;
Regional analysis equipment is connect with the self-adaptive processing equipment, for receiving the multiple subgraph, based on each
The distribution situation of the pixel value of each pixel determines the corresponding region segmentation threshold value of the subgraph inside a subgraph, exports
The corresponding each region segmentation threshold of each subgraph;
Region corrective is connect, for receiving respectively with the regional analysis equipment and the global analysis equipment
State whole segmentation threshold and each region segmentation threshold, and based on the whole segmentation threshold to each region segmentation threshold value into
The adjustment of line number value obtains region segmentation threshold value adjusted to export as region adjustment threshold value;
Piecemeal splitting equipment is connect with the region corrective, for taking corresponding region to each subgraph
Adjustment threshold value is split processing, to obtain corresponding target subgraph, and all target subgraphs is combined to obtain
And export target image to be processed;
Pre-processing device is connect with the piecemeal splitting equipment, for receiving the target image to be processed, to it is described to
Each target shape in processing target image is detected, and intensification processing is carried out to each target shape detected, to obtain
It obtains corresponding intensification and handles image, and export the intensification processing image;
Energy measuring device is connect with the pre-processing device, for receiving the intensification processing image, and described in determination
Deepen to be distributed in the energy size of different frequency range in processing image, using energy be less than or equal to multiple frequency ranges of limitation as it is multiple to
Handle frequency range output;
Bandpass filtering equipment is connected with the energy measuring device and pre-processing device distribution, described for receiving
Multiple frequency ranges to be processed and the intensification handle image, are held based on the multiple frequency range to be processed to intensification processing image
Row bandpass filtering treatment, to obtain, from the intensification processing image, there are the bandpass filterings of the multiple frequency range to be processed
Image is also used to obtain from the band logical reservation image for deepening to remove the bandpass filtering image in processing image;
Automatic gain equipment is connect with the bandpass filtering equipment, for the dynamic based on the bandpass filtering image point
Cloth range executes gain process to the bandpass filtering image, handles image to obtain simultaneously output gain;
Image integration equipment is connect, for receiving respectively with the bandpass filtering equipment and the automatic gain equipment
It states gain process image and the band logical retains image, the gain process image and the band logical are retained into image integration to obtain
It obtains and exports image after integration;
Suspect's authentication equipment is connect with described image integration equipment, for receiving image after the integration, for being based on
Human facial profile is preset from each spectators' facial area is identified after the integration in image, each spectators' facial area is held
The following operation of row: the facial characteristics for being based respectively on each suspect carries out suspect's identification to spectators' facial area, and
When identifying successfully, the wanted circular number of corresponding suspect is issued.
More specifically, in the identification system of auditorium identity scene: in the automatic gain equipment, the band logical
The DYNAMIC DISTRIBUTION range of filtering image is wider, and the gain process dynamics executed to the bandpass filtering image is smaller.
More specifically, in the identification system of auditorium identity scene: frequency duplex communications interface, with the suspect
Authentication equipment connection, the wanted circular for that will correspond to suspect, which is numbered, to be wirelessly sent at nearest police service control centre server.
More specifically, in the identification system of auditorium identity scene: in the pre-processing device, to what is detected
Each target shape carries out intensification processing, includes: to obtain the target image to be processed to obtain corresponding intensification processing image
Each pixel of the middle each target shape of composition, the pixel value for each pixel that will acquire are reduced to the percentage of itself numerical value
60.
More specifically, in the identification system of auditorium identity scene: in the region corrective, based on described
Whole segmentation threshold to each region segmentation threshold value carry out numerical value adjustment include: based on the whole segmentation threshold to each
The size of the difference of region segmentation threshold value carries out numerical value adjustment to the region segmentation threshold value.
More specifically, in the identification system of auditorium identity scene: the parameter preset threshold range is by default ginseng
Number upper limit threshold and parameter preset lower threshold composition;
Wherein, the parameter preset upper limit threshold is less than the parameter preset lower threshold.
More specifically, in the identification system of auditorium identity scene: in the region corrective, based on described
The size of the difference of whole segmentation threshold to each region segmentation threshold value carries out numerical value adjustment to the region segmentation threshold value and includes:
Region segmentation threshold value adjusted be the region segmentation threshold value and the difference a quarter and.
More specifically, in the identification system of auditorium identity scene: in the region corrective, based on described
The size of the difference of whole segmentation threshold to each region segmentation threshold value carries out numerical value adjustment to the region segmentation threshold value and includes:
Region segmentation threshold value adjusted be the region segmentation threshold value and the difference half and.
Detailed description of the invention
Embodiment of the present invention is described below with reference to attached drawing, in which:
Fig. 1 is the bird according to the targeted auditorium of the auditorium identity scene identification system shown in embodiment of the present invention
It looks down from a height figure.
Specific embodiment
The embodiment of auditorium identity scene identification system of the invention is described in detail below with reference to accompanying drawings.
Auditorium is one of essential and basic facility of stage, is usually made of seat array.Auditorium uses sofa-type
Cushion form, for convenience of let out when personnel evacuation mostly use cushion that structure may be reversed.Seat be considered as seat number and
Seat is recognized convenient for user and found to adusk local lighting facility.
According to the design needs used with scene, the seat of hall needs to place file and supplies recording clipboard, special
Different hall also requires to consider to combine with simultaneous interpretation equipment and voting, speech equipment;Part theater or hall also require seat
Chair and air-conditioning system match.
In order to overcome above-mentioned deficiency, the present invention has built a kind of auditorium identity scene identification system, has efficiently solved phase
The technical issues of pass.
Fig. 1 is the bird according to the targeted auditorium of the auditorium identity scene identification system shown in embodiment of the present invention
It looks down from a height figure.Wherein, 1 and 2 be performer's approach corridor, and 3 be performance place outer, and 4 is perform edge in place, and 5 be seat array.
The auditorium identity scene identification system shown according to an embodiment of the present invention includes:
The right opposite in stage performance place is arranged in spectators' seating arrangements, for each spectators to watch stage performance
Viewing location is provided;
Field camera structure, spectators' seating arrangements for the right opposite to stage performance place carry out live camera shooting, with
Obtain corresponding spectators seat image;
First analytical equipment is connect with the field camera structure, for the contrast to spectators seat image into
Row measurement, and exported measurement result as real time contrast;
Second analytical equipment is connect, for receiving respectively with the field camera structure and first analytical equipment
Real time contrast and spectators seat image are stated, and spectators seat image is carried out uniformly based on the real time contrast
Piecemeal processing, to obtain corresponding multiple subgraphs;
First processing equipment is connect with second analytical equipment, for receiving the multiple subgraph, and for each
A subgraph executes following processing: the R channel value of each pixel of the subgraph is obtained, by each picture of the subgraph
The R channel value of vegetarian refreshments is added, and the result after will add up is exported as the color parameter of the subgraph;
Second processing equipment is connect with first processing equipment, for receiving each color parameter of each subgraph,
And when all colours parameter is fallen in parameter preset threshold range, first control signal is issued, and there are color parameters
When falling in outside parameter preset threshold range, second control signal is issued;
Data output apparatus is connect, for receiving respectively with the second processing equipment and the field camera structure
When to the first control signal, focusing prompt information is sent to the field camera structure, be also used to receive it is described
When second control signal, any information is not sent to the field camera structure;
Global analysis equipment is connect with the field camera structure, for receiving spectators seat image, based on described
The distribution situation of the pixel value of each pixel determines the corresponding entirety point of spectators seat image inside spectators seat image
Cut threshold value;
Analysis of Contrast equipment, for receiving spectators seat image, to the spectators seat image degree of comparing
Analysis, to obtain and export corresponding contrast;
Self-adaptive processing equipment is connect with the Analysis of Contrast equipment, for receiving the contrast, and based on described
Contrast carries out image dividing processing to spectators seat image, to obtain multiple subgraphs, wherein the contrast is got over
The quantity of height, the subgraph of acquisition is more;
Regional analysis equipment is connect with the self-adaptive processing equipment, for receiving the multiple subgraph, based on each
The distribution situation of the pixel value of each pixel determines the corresponding region segmentation threshold value of the subgraph inside a subgraph, exports
The corresponding each region segmentation threshold of each subgraph;
Region corrective is connect, for receiving respectively with the regional analysis equipment and the global analysis equipment
State whole segmentation threshold and each region segmentation threshold, and based on the whole segmentation threshold to each region segmentation threshold value into
The adjustment of line number value obtains region segmentation threshold value adjusted to export as region adjustment threshold value;
Piecemeal splitting equipment is connect with the region corrective, for taking corresponding region to each subgraph
Adjustment threshold value is split processing, to obtain corresponding target subgraph, and all target subgraphs is combined to obtain
And export target image to be processed;
Pre-processing device is connect with the piecemeal splitting equipment, for receiving the target image to be processed, to it is described to
Each target shape in processing target image is detected, and intensification processing is carried out to each target shape detected, to obtain
It obtains corresponding intensification and handles image, and export the intensification processing image;
Energy measuring device is connect with the pre-processing device, for receiving the intensification processing image, and described in determination
Deepen to be distributed in the energy size of different frequency range in processing image, using energy be less than or equal to multiple frequency ranges of limitation as it is multiple to
Handle frequency range output;
Bandpass filtering equipment is connected with the energy measuring device and pre-processing device distribution, described for receiving
Multiple frequency ranges to be processed and the intensification handle image, are held based on the multiple frequency range to be processed to intensification processing image
Row bandpass filtering treatment, to obtain, from the intensification processing image, there are the bandpass filterings of the multiple frequency range to be processed
Image is also used to obtain from the band logical reservation image for deepening to remove the bandpass filtering image in processing image;
Automatic gain equipment is connect with the bandpass filtering equipment, for the dynamic based on the bandpass filtering image point
Cloth range executes gain process to the bandpass filtering image, handles image to obtain simultaneously output gain;
Image integration equipment is connect, for receiving respectively with the bandpass filtering equipment and the automatic gain equipment
It states gain process image and the band logical retains image, the gain process image and the band logical are retained into image integration to obtain
It obtains and exports image after integration;
Suspect's authentication equipment is connect with described image integration equipment, for receiving image after the integration, for being based on
Human facial profile is preset from each spectators' facial area is identified after the integration in image, each spectators' facial area is held
The following operation of row: the facial characteristics for being based respectively on each suspect carries out suspect's identification to spectators' facial area, and
When identifying successfully, the wanted circular number of corresponding suspect is issued.
Then, continue that the specific structure of auditorium identity scene identification system of the invention is further detailed.
In the identification system of auditorium identity scene: in the automatic gain equipment, the bandpass filtering image
DYNAMIC DISTRIBUTION range it is wider, to the bandpass filtering image execute gain process dynamics it is smaller.
In the identification system of auditorium identity scene: frequency duplex communications interface, with suspect's authentication equipment
Connection, the wanted circular for that will correspond to suspect, which is numbered, to be wirelessly sent at nearest police service control centre server.
In the identification system of auditorium identity scene: in the pre-processing device, to each target detected
Shape carries out intensification processing, includes: to obtain in the target image to be processed to form respectively to obtain corresponding intensification processing image
Each pixel of a target shape, the pixel value for each pixel that will acquire are reduced to 60 the percent of itself numerical value.
In the identification system of auditorium identity scene: in the region corrective, based on the whole segmentation
It includes: based on the whole segmentation threshold to each region segmentation that threshold value, which carries out numerical value adjustment to each region segmentation threshold value,
The size of the difference of threshold value carries out numerical value adjustment to the region segmentation threshold value.
In the identification system of auditorium identity scene: the parameter preset threshold range is by parameter preset upper limit threshold
It is formed with parameter preset lower threshold;
Wherein, the parameter preset upper limit threshold is less than the parameter preset lower threshold.
In the identification system of auditorium identity scene: in the region corrective, based on the whole segmentation
It includes: adjusted that the size of the difference of threshold value to each region segmentation threshold value, which carries out numerical value adjustment to the region segmentation threshold value,
Region segmentation threshold value be the region segmentation threshold value and the difference a quarter and.
And in the identification system of auditorium identity scene: in the region corrective, being based on the entirety
It includes: adjustment that the size of the difference of segmentation threshold to each region segmentation threshold value, which carries out numerical value adjustment to the region segmentation threshold value,
Region segmentation threshold value afterwards be the region segmentation threshold value and the difference half and.
In addition, frequency division duplex refers in mode of frequency division duplexing, that is, fdd mode used by the frequency duplex communications interface
The transmission of uplink and downlink carries out over different frequencies respectively.
In the first and second generation cellular system, it is substantially using FDD technology and realizes duplex transmission.Especially
In generation cellular system, what it is due to transmission is continuous baseband signal, it is necessary to the uplink and downlink of duplex is provided with different frequencies
Link channel.When transmitting continuous information using FDD technology in first generation cellular system, transmitting-receiving both ends must all have generation different
The frequency synthesizer of carrier frequency must also have one to prevent transmitting signals leakiness to the duplex filtering of receiver in receiving end
Device.In addition, certain frequency interval will be had by receiving and dispatching between carrier frequency for the ease of the production of duplexer.In the second generation
In the systems such as GSM, IS-136 and IS-95, FDD technology is also used.In such systems, due to information be with slotted mode into
Row transmission, transmitting-receiving can carry out in different time slots, and the transmitting signal of mobile station or base station will not generate this receiver
Interference.So although with FDD technology, do not need expensive duplexer filter yet.
The characteristics of fdd mode is the system on two symmetrical frequency channels of separation (uplink and downlink frequency interval 190MHz)
It is received and is transmitted, reception and transmission channel are separated with protection frequency range.
Using technologies such as packet switch, the bottleneck of two generations development can be broken through, realizes high-speed data service, and frequency spectrum benefit can be improved
With rate, increase power system capacity.But FDD must use pairs of frequency, i.e., third generation business is provided in the bandwidth of every 2x5MHz.
Which can make full use of the frequency spectrum of uplink and downlink when supporting symmetrical service, but in asymmetrical packet switch (internet) work
When making, the availability of frequency spectrum then substantially reduce (due to low ascending load, the availability of frequency spectrum is caused to reduce about 40%), in this regard,
The advantage that tdd mode has FDD incomparable.
Using auditorium identity scene identification system of the invention, for the insufficient skill of stage security intensity in the prior art
Art problem, the high-precision figure being customized by each spectators in spectators' seating arrangements of the right opposite to stage performance place
As identifying, and when identifying successfully, the wanted circular number of corresponding suspect is issued, effectively to safeguard stage site safety;It establishes
Based on the adaptive adjustment modes of global threshold adjustment piecemeal threshold value, so that target detection takes into account whole feature and has feature,
Guarantee the validity of the target image to be processed for subsequent image processing;By realizing to based on image real time contrast to existing
Field shooting mechanism exports the dividing processing of image, and based on the signature analysis to the subgraph after segmentation, determines field camera
Whether the image of structure output reaches focusing standard, to facilitate field camera structure to focus in time;Assemble situation according to image energy
It determines adaptive orientation band gain Promotion Strategy, ensure that the directionality and validity of image procossing, to solve
State technical problem.
It is understood that although the present invention has been disclosed in the preferred embodiments as above, above-described embodiment not to
Limit the present invention.For any person skilled in the art, without departing from the scope of the technical proposal of the invention,
Many possible changes and modifications all are made to technical solution of the present invention using the technology contents of the disclosure above, or are revised as
With the equivalent embodiment of variation.Therefore, anything that does not depart from the technical scheme of the invention are right according to the technical essence of the invention
Any simple modifications, equivalents, and modifications made for any of the above embodiments still fall within the range of technical solution of the present invention protection
It is interior.
Claims (8)
1. a kind of auditorium identity scene identification system, the system comprises:
The right opposite in stage performance place is arranged in spectators' seating arrangements, for providing for each spectators of viewing stage performance
Viewing location;
Field camera structure, spectators' seating arrangements for the right opposite to stage performance place carry out live camera shooting, to obtain
Corresponding spectators seat image;
First analytical equipment is connect with the field camera structure, is surveyed for the contrast to spectators seat image
Amount, and exported measurement result as real time contrast;
Second analytical equipment is connect, for receiving the reality respectively with the field camera structure and first analytical equipment
When contrast and spectators seat image, and uniform piecemeal is carried out to spectators seat image based on the real time contrast
Processing, to obtain corresponding multiple subgraphs;
First processing equipment is connect with second analytical equipment, for receiving the multiple subgraph, and is directed to each height
Image executes following processing: the R channel value of each pixel of the subgraph is obtained, by each pixel of the subgraph
R channel value be added, result after will add up is exported as the color parameter of the subgraph;
Second processing equipment is connect with first processing equipment, for receiving each color parameter of each subgraph, and
When all colours parameter is fallen in parameter preset threshold range, first control signal is issued, and there are color parameters to fall in
When outside parameter preset threshold range, second control signal is issued;
Data output apparatus is connect, for receiving respectively with the second processing equipment and the field camera structure
When stating first control signal, focusing prompt information is sent to the field camera structure, is also used to receiving described second
When controlling signal, any information is not sent to the field camera structure;
Global analysis equipment is connect with the field camera structure, for receiving spectators seat image, is based on the spectators
The distribution situation of the pixel value of each pixel determines the corresponding whole segmentation threshold of spectators seat image inside seat image
Value;
Analysis of Contrast equipment analyzes spectators seat image degree of comparing for receiving spectators seat image,
To obtain and export corresponding contrast;
Self-adaptive processing equipment is connect with the Analysis of Contrast equipment, for receiving the contrast, and is based on the comparison
Degree carries out image dividing processing to spectators seat image, to obtain multiple subgraphs, wherein the contrast is higher, obtains
The quantity of the subgraph obtained is more;
Regional analysis equipment is connect with the self-adaptive processing equipment, for receiving the multiple subgraph, is based on each height
The distribution situation of the pixel value of each pixel determines the corresponding region segmentation threshold value of the subgraph inside image, exports each
The corresponding each region segmentation threshold of subgraph;
Region corrective is connect with the regional analysis equipment and the global analysis equipment respectively, described whole for receiving
Body segmentation threshold and each region segmentation threshold, and each region segmentation threshold value is counted based on the whole segmentation threshold
Value adjustment obtains region segmentation threshold value adjusted to export as region adjustment threshold value;
Piecemeal splitting equipment is connect with the region corrective, for taking corresponding region to adjust each subgraph
Threshold value is split processing, to obtain corresponding target subgraph, and all target subgraphs is combined to obtain and defeated
Target image to be processed out;
Pre-processing device is connect with the piecemeal splitting equipment, for receiving the target image to be processed, to described to be processed
Each target shape in target image is detected, and carries out intensification processing to each target shape detected, with acquisition pair
The intensification processing image answered, and export the intensification processing image;
Energy measuring device is connect with the pre-processing device, for receiving the intensification processing image, and determines the intensification
It is distributed in the energy size of different frequency range in processing image, energy is less than or equal to multiple frequency ranges of limitation as multiple to be processed
Frequency range output;
Bandpass filtering equipment is connected with the energy measuring device and pre-processing device distribution, the multiple for receiving
Frequency range to be processed and the intensification handle image, execute band to intensification processing image based on the multiple frequency range to be processed
Pass filter processing, with obtain from it is described deepen processing image, there are the bandpass filtering image of the multiple frequency range to be processed,
It is also used to obtain from the band logical for deepening to remove the bandpass filtering image in processing image and retains image;
Automatic gain equipment is connect with the bandpass filtering equipment, for the DYNAMIC DISTRIBUTION model based on the bandpass filtering image
It encloses and gain process is executed to the bandpass filtering image, handle image to obtain simultaneously output gain;
Image integration equipment is connect, for receiving the increasing respectively with the bandpass filtering equipment and the automatic gain equipment
Benefit manages image and the band logical retains image, and the gain process image and the band logical are retained image integration to obtain simultaneously
Image after output integration;
Suspect's authentication equipment is connect with described image integration equipment, for receiving image after the integration, for based on default
Human facial profile from each spectators' facial area is identified after the integration in image, to each spectators' facial area execute with
Lower operation: the facial characteristics for being based respectively on each suspect carries out suspect's identification to spectators' facial area, and is reflecting
Not Cheng Gong when, issue the wanted circular number of corresponding suspect.
2. auditorium identity as described in claim 1 scene identification system, it is characterised in that:
In the automatic gain equipment, the DYNAMIC DISTRIBUTION range of the bandpass filtering image is wider, to the bandpass filtering figure
As the gain process dynamics executed is smaller.
3. auditorium identity as claimed in claim 2 scene identification system, which is characterized in that the system also includes:
Frequency duplex communications interface is connect with suspect's authentication equipment, and the wanted circular for that will correspond to suspect is numbered wireless
It is sent at nearest police service control centre server.
4. auditorium identity as claimed in claim 3 scene identification system, it is characterised in that:
In the pre-processing device, intensification processing is carried out to each target shape detected, to obtain at corresponding intensification
Reason image includes: to obtain each pixel that each target shape is formed in the target image to be processed, and what be will acquire is each
The pixel value of pixel is reduced to 60 the percent of itself numerical value.
5. auditorium identity as claimed in claim 4 scene identification system, it is characterised in that:
In the region corrective, numerical value adjustment is carried out to each region segmentation threshold value based on the whole segmentation threshold
It include: that the size of the difference based on whole segmentation threshold to each region segmentation threshold value carries out the region segmentation threshold value
Numerical value adjustment.
6. auditorium identity as claimed in claim 5 scene identification system, it is characterised in that:
The parameter preset threshold range is made of parameter preset upper limit threshold and parameter preset lower threshold;
Wherein, the parameter preset upper limit threshold is less than the parameter preset lower threshold.
7. auditorium identity as claimed in claim 6 scene identification system, it is characterised in that:
In the region corrective, the size of the difference pair based on the whole segmentation threshold to each region segmentation threshold value
The region segmentation threshold value carry out numerical value adjustment include: region segmentation threshold value adjusted be the region segmentation threshold value with it is described
The sum of difference a quarter.
8. auditorium identity as claimed in claim 6 scene identification system, it is characterised in that:
In the region corrective, the size of the difference pair based on the whole segmentation threshold to each region segmentation threshold value
The region segmentation threshold value carry out numerical value adjustment include: region segmentation threshold value adjusted be the region segmentation threshold value with it is described
The sum of difference half.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201810920632.8A CN108985267B (en) | 2018-08-14 | 2018-08-14 | Audience seat identity on-site identification system |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201810920632.8A CN108985267B (en) | 2018-08-14 | 2018-08-14 | Audience seat identity on-site identification system |
Publications (2)
Publication Number | Publication Date |
---|---|
CN108985267A true CN108985267A (en) | 2018-12-11 |
CN108985267B CN108985267B (en) | 2022-04-29 |
Family
ID=64552986
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN201810920632.8A Active CN108985267B (en) | 2018-08-14 | 2018-08-14 | Audience seat identity on-site identification system |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN108985267B (en) |
Cited By (4)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN110728852A (en) * | 2019-11-07 | 2020-01-24 | 陈定良 | Solar traffic light |
CN111002890A (en) * | 2019-11-07 | 2020-04-14 | 陈嘉琴 | Large truck |
CN111086604A (en) * | 2019-11-07 | 2020-05-01 | 陈嘉琴 | Coal carrying ship |
CN111797661A (en) * | 2019-05-07 | 2020-10-20 | 王青雷 | Wireless notification method based on big data analysis |
Citations (5)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
US20130259323A1 (en) * | 2012-03-27 | 2013-10-03 | Kevin Keqiang Deng | Scene-based people metering for audience measurement |
WO2015025249A2 (en) * | 2013-08-23 | 2015-02-26 | Dor Givon | Methods, systems, apparatuses, circuits and associated computer executable code for video based subject characterization, categorization, identification, tracking, monitoring and/or presence response |
CN106060472A (en) * | 2016-06-27 | 2016-10-26 | 张兰 | Intelligent device cloud platform management system |
CN107248213A (en) * | 2017-06-13 | 2017-10-13 | 安徽禹缤体育科技有限公司 | A kind of user identity secure identification system applied to stadiums |
CN107967458A (en) * | 2017-12-06 | 2018-04-27 | 宁波亿拍客网络科技有限公司 | A kind of face identification method |
-
2018
- 2018-08-14 CN CN201810920632.8A patent/CN108985267B/en active Active
Patent Citations (5)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
US20130259323A1 (en) * | 2012-03-27 | 2013-10-03 | Kevin Keqiang Deng | Scene-based people metering for audience measurement |
WO2015025249A2 (en) * | 2013-08-23 | 2015-02-26 | Dor Givon | Methods, systems, apparatuses, circuits and associated computer executable code for video based subject characterization, categorization, identification, tracking, monitoring and/or presence response |
CN106060472A (en) * | 2016-06-27 | 2016-10-26 | 张兰 | Intelligent device cloud platform management system |
CN107248213A (en) * | 2017-06-13 | 2017-10-13 | 安徽禹缤体育科技有限公司 | A kind of user identity secure identification system applied to stadiums |
CN107967458A (en) * | 2017-12-06 | 2018-04-27 | 宁波亿拍客网络科技有限公司 | A kind of face identification method |
Non-Patent Citations (3)
Title |
---|
HAKAN CEVIKALP等: "Face recognition based on image sets", 《2010 IEEE COMPUTER SOCIETY CONFERENCE ON COMPUTER VISION AND PATTERN RECOGNITION》 * |
K. R. SREELAKSHMI等: "Multiple media based face recognition in unconstrained environments using eigenfaces", 《2016 INTERNATIONAL CONFERENCE ON NEXT GENERATION INTELLIGENT SYSTEMS (ICNGIS)》 * |
王盾等: "复杂环境下的人脸识别研究", 《自动化应用》 * |
Cited By (5)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN111797661A (en) * | 2019-05-07 | 2020-10-20 | 王青雷 | Wireless notification method based on big data analysis |
CN111797661B (en) * | 2019-05-07 | 2021-03-30 | 湖南琴海数码股份有限公司 | Wireless notification method based on big data analysis |
CN110728852A (en) * | 2019-11-07 | 2020-01-24 | 陈定良 | Solar traffic light |
CN111002890A (en) * | 2019-11-07 | 2020-04-14 | 陈嘉琴 | Large truck |
CN111086604A (en) * | 2019-11-07 | 2020-05-01 | 陈嘉琴 | Coal carrying ship |
Also Published As
Publication number | Publication date |
---|---|
CN108985267B (en) | 2022-04-29 |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
CN108985267A (en) | Auditorium identity scene identification system | |
US7155035B2 (en) | Personal authentication method, personal authentication apparatus and image capturing device | |
WO2018082711A1 (en) | Base station deployment method, network server, and unmanned aerial vehicle | |
EP3202160B1 (en) | Method of providing hearing assistance between users in an ad hoc network and corresponding system | |
CN101505447B (en) | Method of estimating weighting function of audio signals in a hearing aid | |
CN106470370A (en) | Automatic control directive horn and LED lighting lamp comprising same | |
CN208156681U (en) | A kind of video monitoring image identifying system | |
CN105282774B (en) | A kind of wireless signal transmission method and wireless access point | |
CN112351364B (en) | Voice playing method, earphone and storage medium | |
CN104581830B (en) | A kind of cut-in method and equipment of terminal device | |
Takano et al. | Visible light communication on LED-equipped drone and object-detecting camera for post-disaster monitoring | |
US11450333B2 (en) | Sound insulation method and device and system thereof based on LiFi optical communication | |
CN109712097A (en) | Image processing method, device, storage medium and electronic equipment | |
CN106682662A (en) | Multimodal biometric feature recognition module and method for mobile terminal | |
CN104852758A (en) | Vertical beamforming method in three-dimensional large-scale antenna network and device | |
CN107564043B (en) | A kind of residence area motion target tracking method | |
CN107589688A (en) | The method and device of MIC array received phonetic orders, speech control system | |
KR102365749B1 (en) | Jamming methods and apparatus for lte and wi-fi communication-based drones | |
CN113556189A (en) | Antenna adjusting method and device for unmanned aerial vehicle | |
EP3509389B1 (en) | Wireless communication device | |
CN109819500A (en) | Cell selecting method, terminal, base station and communication apparatus | |
CN107770488B (en) | A kind of real time monitoring type ground locking device based on high precision image acquisition | |
CN108039012A (en) | A kind of fire emergency lamp | |
CN107392186A (en) | Residence area Motion Object Tracking System | |
CN109861786B (en) | Method and device for shielding data interaction, storage medium and processor |
Legal Events
Date | Code | Title | Description |
---|---|---|---|
PB01 | Publication | ||
PB01 | Publication | ||
SE01 | Entry into force of request for substantive examination | ||
SE01 | Entry into force of request for substantive examination | ||
GR01 | Patent grant | ||
GR01 | Patent grant |