CN108846389A - A kind of passenger flow analysis system and its method - Google Patents
A kind of passenger flow analysis system and its method Download PDFInfo
- Publication number
- CN108846389A CN108846389A CN201810916826.0A CN201810916826A CN108846389A CN 108846389 A CN108846389 A CN 108846389A CN 201810916826 A CN201810916826 A CN 201810916826A CN 108846389 A CN108846389 A CN 108846389A
- Authority
- CN
- China
- Prior art keywords
- monocular
- passenger flow
- visible light
- thermal imaging
- decision making
- 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
- 238000005206 flow analysis Methods 0.000 title claims abstract description 17
- 238000000034 method Methods 0.000 title claims abstract description 13
- 238000001514 detection method Methods 0.000 claims abstract description 94
- 238000004891 communication Methods 0.000 claims abstract description 74
- 238000004458 analytical method Methods 0.000 claims abstract description 68
- 238000001931 thermography Methods 0.000 claims abstract description 62
- 238000012544 monitoring process Methods 0.000 claims abstract description 34
- 238000012795 verification Methods 0.000 claims description 13
- 238000012545 processing Methods 0.000 claims description 9
- 230000005855 radiation Effects 0.000 claims description 8
- 238000010191 image analysis Methods 0.000 claims description 6
- 238000003709 image segmentation Methods 0.000 claims description 6
- 230000000737 periodic effect Effects 0.000 claims description 6
- 230000000007 visual effect Effects 0.000 claims description 5
- 238000007405 data analysis Methods 0.000 claims description 4
- 235000013399 edible fruits Nutrition 0.000 claims description 3
- 229910052732 germanium Inorganic materials 0.000 claims description 3
- GNPVGFCGXDBREM-UHFFFAOYSA-N germanium atom Chemical compound [Ge] GNPVGFCGXDBREM-UHFFFAOYSA-N 0.000 claims description 3
- 238000012360 testing method Methods 0.000 claims description 3
- 238000007689 inspection Methods 0.000 claims description 2
- 238000009434 installation Methods 0.000 claims description 2
- 239000002184 metal Substances 0.000 claims 1
- 238000005516 engineering process Methods 0.000 abstract description 2
- 230000007613 environmental effect Effects 0.000 description 6
- 230000005540 biological transmission Effects 0.000 description 3
- 230000000149 penetrating effect Effects 0.000 description 3
- 238000010276 construction Methods 0.000 description 2
- 238000013461 design Methods 0.000 description 2
- 238000011161 development Methods 0.000 description 2
- 230000018109 developmental process Effects 0.000 description 2
- 238000010079 rubber tapping Methods 0.000 description 2
- 238000013459 approach Methods 0.000 description 1
- 238000012937 correction Methods 0.000 description 1
- 238000010586 diagram Methods 0.000 description 1
- 238000000605 extraction Methods 0.000 description 1
- 238000003780 insertion Methods 0.000 description 1
- 230000037431 insertion Effects 0.000 description 1
- 230000013011 mating Effects 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
-
- G06T5/70—
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T7/00—Image analysis
- G06T7/10—Segmentation; Edge detection
- G06T7/11—Region-based segmentation
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V10/00—Arrangements for image or video recognition or understanding
- G06V10/40—Extraction of image or video features
- G06V10/44—Local feature extraction by analysis of parts of the pattern, e.g. by detecting edges, contours, loops, corners, strokes or intersections; Connectivity analysis, e.g. of connected components
Landscapes
- Engineering & Computer Science (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Theoretical Computer Science (AREA)
- Multimedia (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Traffic Control Systems (AREA)
- Closed-Circuit Television Systems (AREA)
- Image Processing (AREA)
Abstract
The invention discloses a kind of passenger flow analysis system and its methods, belong to monitoring technology field, including monocular or more mesh visible light video collecting and detecting devices, monocular passive type thermal imaging detection device, front end intellectual analysis decision making device, the pluggable multi-interface communication equipment in front end, remote monitoring and administration device and front end warning device, it solves to market, rail traffic, the volume of the flow of passengers of the occasions such as entrance and exit of the park and passageway carries out the technical issues of accurate passenger flow analysing, it is improved for the accuracy rate of volume of the flow of passengers identification, image is not only acquired by visible light video, for human body head and body contour, the feature of height is identified, analysis identification is also carried out to passenger flow number by human body thermography, improve recognition accuracy.
Description
Technical field
The invention belongs to monitoring technology field, in particular to a kind of passenger flow analysis system and its method.
Background technique
With business, the fast development of field of traffic, tourism industry, promptly and accurately grasp to volume of the flow of passengers situation, not only
Guarantee the needs of safety, while being also the necessary data support of these industry own operations management and business development.
Existing passenger flow statistics mode is more, wherein being most importantly based on video acquisition identification method, passes through in passenger flow
Entrance top at the top of, installation monocular, binocular or more mesh cameras shooting, collecting vertically downward are flutterred and catch the passing passenger flow crown
Portion and body contour image or height.Most of system is to be shot in the case of visible light using common pick-up lens multiframe
Acquisition visual picture is analyzed;Small part system is then directed in the invisible situation such as night, common infrared is taken the photograph using active
As head, the visual picture under multiframe shooting, collecting infrared light is analyzed, and principle is analyzed former with the Image Acquisition under visible light
It manages similar.
Existing video passenger flow analysing product generally passes through two dimension or multidimensional image technical approach is identified, main or base
In the extraction and study of the image key feature of human body, the removal of noise, to the more demanding of algorithm, algorithm becomes increasingly complex.
Existing video passenger flow analysing product is limited in that its data precision is limited, is difficult to accomplish high accuracy rate.
It is based primarily upon the features such as passing passenger flow head and body contour, height to identify and position, appearance is worked as in the reconstruction including multidimensional image
When passenger flow is crowded, height blocks, head wears special top cap, raising is too short, erroneous judgement inevitably will cause.
Existing video passenger flow analysing product is regarded for the characteristic images such as passenger flow head part and body contour, body height
Frequency identifies, the influence being easy by such environmental effects, especially environmental background is very big, including light, ground form and color, anti-
Penetrating etc. influences, and needs to avoid the direct irradiation of strong light and the strong reflection light on ground etc. as far as possible.
Existing video passenger flow analysing product is transmitted frequently with Ethernet wire communication, partially uses wireless mode, for choosing
The communication mode selected is more single, to field erected mating more demanding.
Summary of the invention
The object of the present invention is to provide a kind of passenger flow analysis system and its method, solve to market, rail traffic, park
The volume of the flow of passengers of the occasions such as entrance and passageway carries out the technical issues of accurate passenger flow analysing.
To achieve the above object, the present invention uses following technical scheme:
A kind of passenger flow analysis system, including monocular or more mesh visible light video collecting and detecting devices, monocular passive type heat at
As detection device, front end intellectual analysis decision making device, the pluggable multi-interface communication equipment in front end, remote monitoring and administration device and preceding
Hold warning device;
Monocular or more mesh visible light video collecting and detecting devices and monocular passive type thermal imaging detection device are mounted on out
Entrance is crossed right above road junction;
Monocular or more mesh visible light video collecting and detecting devices and monocular passive type thermal imaging detection device pass through data
Line connects front end intellectual analysis decision making device;
Front end intellectual analysis decision making device connects the pluggable multi-interface communication equipment in front end by data line;
The pluggable multi-interface communication equipment in front end is communicated by cable or wireless network with remote monitoring and administration device;
Remote monitoring and administration device is communicated by data line with front end warning device.
Preferential, the monocular or more mesh visible light video collecting and detecting devices include visible image capturing unit, at image
Reason and recognition unit, storage unit and communication unit, the model of the monocular or more mesh visible light video collecting and detecting devices
NJ-SWKJ-3D201D。
Preferential, the monocular passive type thermal imaging detection device includes passive type infrared thermal imaging camera unit, thermal map
As processing and recognition unit, storage unit and communication unit, the passive type infrared thermal imaging camera unit include germanium speculum
Head, uncooled fpa detector and encoder, the model NJ-SWKJ- of the monocular passive type thermal imaging detection device
IR101G。
Preferential, the front end intellectual analysis decision making device includes microprocessor algorithm processing unit, storage unit and leads to
Believe interface unit, the communication unit and the monocular passive type heat of the monocular or more mesh visible light video collecting and detecting devices at
The communications interface unit, the front end intellectual analysis decision making device are connected as the communication unit of detection device passes through data line
Model NJ-SWKJ-AI201D.
Preferential, the model NJ-SWKJ-CM201W of the pluggable multi-interface communication equipment in front end;The long-range prison
Control management device includes router, server and personal computer;The model NJ-SWKJ- of the front end warning device
AL001C。
A kind of passenger flow analysing method, includes the following steps:
Step 1:Establish a kind of passenger flow analysis system;
Step 2:Monocular or binocular visible light video collecting and detecting device are installed on entrance or crossed right above road junction, peace
It fills angle and uses 90 degree of right angle settings, mounting height is preferably suggested between 2.5 meters to 5 meters;Monocular or binocular visible light are regarded
Best acquisition parameters, IP address and related communication configuration, network time synchronization and periodic detection knot is arranged in frequency collecting and detecting device
Fruit is reported and submitted the period, and entrance Pedestrian flow detection regional scope is set, and monocular or binocular visible light video collecting and detecting device are used
In the flow of the people progress image analysis for entering and leaving the regional scope;
Monocular passive type thermal imaging detection device is installed on entrance or is crossed right above road junction, setting angle uses 90 degree
Right angle setting, mounting height are higher than visible light video collecting and detecting device, most to the setting of monocular passive type thermal imaging detection device
Good acquisition parameters, IP address and related communication configuration, network time synchronization and periodic detection result are reported and submitted the period, and setting enters and leaves
Mouth Pedestrian flow detection regional scope is consistent with the setting range of monocular or binocular visible light video collecting and detecting device, monocular quilt
Dynamic formula thermal imaging detection device is used to carry out thermal image analysis for the flow of the people for entering and leaving the region;
Step 3:IP address and related communication configuration are arranged to front end intellectual analysis decision making device, and selection setting is only
Visible light video collecting and detecting device communication data is received, or only receives passive type thermal imaging detection device and reports and submits data, or is complete
Reception mode;
Step 4:According to system application environment field network situation, the pluggable multi-interface communication equipment in front end is carried out practical
Physical configuration and network parameter setting;
Step 5:Monocular or binocular visible light video collecting and detecting device identify passenger flow moving direction, are examined according to passenger flow pedestrian
Model and the matching of various dimensions passenger flow characteristic are surveyed, with image segmentation algorithm and dynamic programming algorithm, monitoring section is left in calculating
The different directions passenger flow number in domain, using self-defined message, periodically will recognition result data and this during be used for verify key frame
Image is packaged into visible detection results messages body, and report and submit front end intellectual analysis decision making device global alignment analyze, it is described can
With detection time stamp and time range in light-exposed testing result message body;
Step 6:Monocular passive type thermal imaging detection device is for acquiring and identifying the infrared hot spoke issued in tested scene
The image for penetrating generation is matched according to passenger flow pedestrian's heat radiation detection model and thermal radiation of body characteristic, with image segmentation
Algorithm and dynamic programming algorithm, are analyzed for two dimensional image, are demarcated human body by infrared emanation thermography, are identified passenger flow
Moving direction calculates the different directions passenger flow number for leaving monitoring region, using self-defined message, periodically by recognition result data and
Key frame images during this for verification are packaged into infrared light detection results messages body, and front end intellectual analysis decision is reported and submitted to fill
Global alignment analysis is set, detection time stamp and time range are had in infrared light detection results messages body;
Step 7:Front end intellectual analysis decision making device carries out global alignment analysis according to itself initial setting up, selection:Front end
Intellectual analysis decision making device is used for the visitor reported and submitted in infrared light detection results messages body and visible detection results messages body
Person who lives in exile's number carries out analysis comparison;Directly pass through the pluggable multi-interface communication equipment in front end if the two data are consistent for passenger flow people
Number data are sent to remote monitoring and administration device;If inconsistent, just start verification scheme again, according to timestamp to temporary verification
Key frame images reanalyse verification in time range, and integrated use motion detection algorithm and sorting algorithm, which obtain, new to be sentenced
Disconnected result;
Step 8:Front end intellectual analysis decision making device is analyzed according to itself initial setting up, selection without global alignment:Directly
It connects using directly by the output of monocular passive type thermal imaging detection device as a result, directlying adopt monocular or binocular visible light and regarding
The result of frequency collecting and detecting device output is as final detection result;
Step 9:Front end intellectual analysis decision making device will be walked according to the actual disposition of the pluggable multi-interface communication equipment in front end
Rapid 7 or step 8 final result, remote monitoring and administration device is sent to by the pluggable multi-interface communication equipment in front end;
Under the data that front end intellectual analysis decision making device will be unable to be successfully transferred to remote monitoring and administration device temporarily save
Come, with it is to be communicated normal when resume;
Step 10:Remote monitoring and administration device for the data received are put in storage in real time, big data analysis, system
Meter, report and early warning;
Step 11:Warning device be used for when passenger flow is continued above preset threshold starting alarm or early warning, so as to
Manager, which takes action, accelerates passenger flow evacuation;Warning device includes computer application software figure or text importing alarm, mobile phone
Short message alarm, cell phone application application alarm or audible and visual alarm.
Preferably, the important component microprocessor algorithm processing unit of the front end intellectual analysis decision making device is optional
Select ARM9 series processors.
A kind of passenger flow analysis system of the present invention and its method, solve to market, rail traffic, entrance and exit of the park
The technical issues of carrying out accurate passenger flow analysing with the volume of the flow of passengers of the occasions such as passageway proposes the accuracy rate of volume of the flow of passengers identification
It rises, image is not only acquired by visible light video, is identified for the feature of human body head and body contour, height, it is also logical
It crosses Studies of Human Body Heat picture figure and analysis identification is carried out to passenger flow number, improve recognition accuracy;Present invention employs the progress of human body thermography
Volume of the flow of passengers identification, it is easy to use, do not need the calibration that fiducial temperature is carried out to passive type thermal imaging detection device.As long as human body with
There are the temperature difference for other objects or environment at one's side, and profile will be shown in thermography, is not related to the calibration of fiducial temperature, relatively hold
Easily carry out image recognition;Present invention employs human body thermographies to carry out volume of the flow of passengers identification, easy to implement, and human body is sent out under normal circumstances
The far infrared wavelength penetrated is near 9.6 microns, wavelength that the far infrared of wavelength (5.6-15 microns) and human body are launched
It overlaps, such thermal imaging apparatus industry is more general;The present invention carries out volume of the flow of passengers identification using Studies of Human Body Heat picture figure, can carry out two dimension
Image recognition, algorithm is relatively easy, not by such environmental effects, for whether there is or not luminous ray, ground form whether complicated, ground
Design and color whether especially, whether strong etc. the environmental factor of reflected light seemed inessential, these factors to heat radiation at
Picture and thermography identification do not cause at all to influence;The present invention uses front end intellectual analysis decision making device, can be conveniently special based on image
Seek peace neuroid algorithm load and improve extension, it is good right convenient for being provided for subsequent promotion accuracy rate more new algorithm
External tapping and running space;The present invention uses the pluggable multi-interface communication equipment in front end, can facilitate the building of communication network, not only
It can be communicated based on cable network, for the region of no construction wireline communication network, the WIFI using ad hoc network can be facilitated
Network, or the wireless network based on common carrier is used, NB-IoT network also can be used under extreme conditions, because NB-IoT covers
Lid gain has a distinct increment with respect to conventional wireless.
Detailed description of the invention
Fig. 1 is system structure diagram of the invention;
Fig. 2 is flow chart of the invention.
Specific embodiment
Embodiment 1:
A kind of passenger flow analysis system as shown in Figure 1, including monocular or more mesh visible light video collecting and detecting devices, monocular
Passive type thermal imaging detection device, front end intellectual analysis decision making device, the pluggable multi-interface communication equipment in front end, long-range monitoring pipe
Manage device and front end warning device;
Monocular or more mesh visible light video collecting and detecting devices and monocular passive type thermal imaging detection device are mounted on out
Entrance is crossed right above road junction, and passing passenger flow video image information under visible light is acquired, and identifies passenger flow stream of people number;
Monocular or more mesh visible light video collecting and detecting devices and monocular passive type thermal imaging detection device pass through data
Line connects front end intellectual analysis decision making device, acquires the thermography information of passing passenger flow, identifies passenger flow stream of people number;
Front end intellectual analysis decision making device connects the pluggable multi-interface communication equipment in front end by data line;
The pluggable multi-interface communication equipment in front end is communicated by cable or wireless network with remote monitoring and administration device;
Remote monitoring and administration device is communicated by data line with front end warning device.
Remote monitoring and administration device connects warning device, when passenger flow is continued above threshold values starting alarm prompt.
Preferential, the monocular or more mesh visible light video collecting and detecting devices include visible image capturing unit, at image
Reason and recognition unit, storage unit and communication unit, the model of the monocular or more mesh visible light video collecting and detecting devices
NJ-SWKJ-3D201D。
Monocular or binocular visible light video collecting and detecting device are wired to passing through after video image progress passenger flow number identification
Front end intellectual analysis decision making device is connected, periodically reports and submits front end intelligent recognition result data and the key frame images for being used to verify
The analysis of analysis decision device global alignment.
Preferential, the monocular passive type thermal imaging detection device includes passive type infrared thermal imaging camera unit, thermal map
As processing and recognition unit, storage unit and communication unit, the passive type infrared thermal imaging camera unit include germanium speculum
Head, uncooled fpa detector and encoder, the model NJ-SWKJ- of the monocular passive type thermal imaging detection device
IR101G。
After monocular passive type thermal imaging detection device carries out number identification to passenger flow thermal image, pass through wired connection front end intelligence
Recognition result data and the key frame images for being used to verify periodically are reported and submitted front end intellectual analysis decision to fill by energy analysis decision device
Set global alignment analysis.
Preferential, the front end intellectual analysis decision making device includes microprocessor algorithm processing unit, storage unit and leads to
Believe interface unit, the communication unit and the monocular passive type heat of the monocular or more mesh visible light video collecting and detecting devices at
The communications interface unit, the front end intellectual analysis decision making device are connected as the communication unit of detection device passes through data line
Model NJ-SWKJ-AI201D.
Front end intellectual analysis decision making device from visible light video collecting and detecting device and passive type thermal imaging detection for filling
The passenger flow number reported and submitted and is set, is directly sent to remotely by the pluggable multi-interface communication equipment in front end if the two unanimously matches
Passenger flow analysing operation management device;If inconsistent, just start verification scheme again, according to algorithm to the key frame figure for verification
After integrating recognition detection again, new judging result is obtained.
Preferential, the model NJ-SWKJ-CM201W of the pluggable multi-interface communication equipment in front end;
The pluggable multi-interface communication equipment in front end includes a variety of pluggable communications interface units, mainly Ethernet cable modem
Believe interface unit, RS485 wired communication interface unit, RS232 wired communication interface unit, WIFI radio interface unit, 2G/
3G/LTE wireless communication unit supports NB-IoT wireless communication interface unit, realizes that communication mode is optional.
The remote monitoring and administration device includes router, server and personal computer;Remote monitoring and administration device its
The data that real-time transmission is come are put in storage, big data analysis, statistics, report, early warning etc..
The model NJ-SWKJ-AL001C of the front end warning device.
Start a variety of announcements such as text or graphical display, acousto-optic, short message or APP application when passenger flow is continued above preset threshold
Police's formula accelerates passenger flow evacuation so that manager takes action.
Monocular passive type thermal imaging detection device is known mainly for human body with the temperature difference of other objects of periphery or environment
Not, temperature correction is not needed, it is different by the thermography temperature difference, with features such as ordinary two dimensional algorithm identification human body contour outline ranges.
The front end intellectual analysis decision making device can need to select setting reception monocular or more mesh visible according to scene
The data of light video acquisition detection device or only receive monocular passive type thermal imaging detection device report and submit data or receive mode entirely.
The front end intellectual analysis decision making device, it is possible to provide convenient and fast external network interface facilitates Remote Management of Network, real
The importing of existing new algorithm updates, and provides convenient and fast physical platform interface for the improvement of subsequent alignment algorithm.
Embodiment 2:
As shown in Fig. 2, a kind of passenger flow analysing method as described in example 2 is in a kind of passenger flow analysing described in embodiment 1
It realizes, includes the following steps on the basis of system:
Step 1:Establish a kind of passenger flow analysis system;
Step 2:Monocular or binocular visible light video collecting and detecting device are installed on entrance or crossed right above road junction, peace
It fills angle and uses 90 degree of right angle settings, mounting height is preferably suggested between 2.5 meters to 5 meters;Monocular or binocular visible light are regarded
Best acquisition parameters, IP address and related communication configuration, network time synchronization and periodic detection knot is arranged in frequency collecting and detecting device
Fruit is reported and submitted the period, and entrance Pedestrian flow detection regional scope is set, and monocular or binocular visible light video collecting and detecting device are used
In the flow of the people progress image analysis for entering and leaving the regional scope;
Monocular passive type thermal imaging detection device is installed on entrance or is crossed right above road junction, setting angle uses 90 degree
Right angle setting, mounting height are higher than visible light video collecting and detecting device, most to the setting of monocular passive type thermal imaging detection device
Good acquisition parameters, IP address and related communication configuration, network time synchronization and periodic detection result are reported and submitted the period, such as are arranged
The device communicate the address IPv4 192.168.1.61 (default) or other, setting IPv4 subnet mask 255.255.255.0 and silent
Recognize gateway, when setting network time synchronization is ntp server school, thermometric region is set depending on the site environment, and adjusts aperture, right
Reach best match than parameters such as degree and brightness, setting entrance Pedestrian flow detection regional scope is regarded with monocular or binocular visible light
The setting range of frequency collecting and detecting device is consistent, and monocular passive type thermal imaging detection device is used for the people for entering and leaving the region
Flow carries out thermal image analysis;
Step 3:IP address and related communication configuration are arranged to front end intellectual analysis decision making device, such as the device is set and is led to
Believe the address IPv4 192.168.1.62 (default) or other, IPv4 subnet mask 255.255.255.0 and default gateway are set, with
And selection setting is only to receive visible light video collecting and detecting device communication data, or only receive passive type thermal imaging detection device
Data are reported and submitted, or receive mode entirely;
Step 4:According to system application environment field network situation, the pluggable multi-interface communication equipment in front end is carried out practical
Physical configuration and network parameter setting;
Step 5:Monocular or binocular visible light video collecting and detecting device identify passenger flow moving direction, are examined according to passenger flow pedestrian
Model and the matching of various dimensions passenger flow characteristic are surveyed, with image segmentation algorithm and dynamic programming algorithm, monitoring section is left in calculating
The different directions passenger flow number in domain, using self-defined message, self-defined message uses Transmission Control Protocol, includes in testing result message body
Instant timestamp, detection time section (starting and end time) when collecting and detecting device number, the message are sent, inspection
The correspondence number measured, this message body whether incidentally transmission key frame images packet mark, periodically by recognition result data and this phase
Between for the key frame images of verification be packaged into visible detection results messages body, and report and submit front end intellectual analysis decision making device comprehensive
Composition and division in a proportion is to analysis, with detection time stamp and time range in the visible detection results messages body;
Step 6:Monocular passive type thermal imaging detection device is for acquiring and identifying the infrared hot spoke issued in tested scene
The image for penetrating generation is matched according to passenger flow pedestrian's heat radiation detection model and thermal radiation of body characteristic, with image segmentation
Algorithm and dynamic programming algorithm, are analyzed for two dimensional image, are demarcated human body by infrared emanation thermography, are identified passenger flow
Moving direction calculates the different directions passenger flow number for leaving monitoring region, using self-defined message, periodically by recognition result data and
Key frame images during this for verification are packaged into infrared light detection results messages body, and front end intellectual analysis decision is reported and submitted to fill
Global alignment analysis is set, detection time stamp and time range are had in infrared light detection results messages body;
Step 7:Front end intellectual analysis decision making device can choose according to itself initial setting up and carry out global alignment analysis:
Front end intellectual analysis decision making device is used for next to reporting and submitting in infrared light detection results messages body and visible detection results messages body
Passenger flow number carry out analysis comparison.It directly will be objective by the pluggable multi-interface communication equipment in front end if the two data are consistent
Person who lives in exile's number data are sent to remote monitoring and administration device;If inconsistent, just start verification scheme again, according to timestamp to temporary
Key frame images carry out reanalysing verification within the scope of checking time, and integrated use motion detection algorithm and sorting algorithm obtain newly
Judging result;
Step 8:Front end intellectual analysis decision making device can choose according to itself initial setting up without global alignment point
Analysis:It directlys adopt directly by the output of monocular passive type thermal imaging detection device as a result, directlying adopt monocular or binocular can
The result of light-exposed video acquisition detection device output is as final detection result;
Step 9:Front end intellectual analysis decision making device according to the actual disposition of the pluggable multi-interface communication equipment in front end, such as
Site of deployment only has Ethernet wiring, then just only needing configuration ethernet wired communication interface unit, other communication units can
It does not configure, only need to will be at the physical interface of the RJ45 head of the ethernet line insertion device Ethernet wired communication interface unit
It can.If site of deployment only has mobile operator 2G/3G/LTE wireless communication coverage, there is no wired ethernet environment, so that it may only match
2G/3G/LTE wireless communication unit is set, the parameters such as setting wireless aps N access point, dialed number, username and password will
The final result of step 7 or step 8 is sent to remote monitoring and administration device by the pluggable multi-interface communication equipment in front end;
Under the data that front end intellectual analysis decision making device will be unable to be successfully transferred to remote monitoring and administration device temporarily save
Come, with it is to be communicated normal when resume;
Step 10:Remote monitoring and administration device for the data received are put in storage in real time, big data analysis, system
Meter, report and early warning;
Step 11:Warning device be used for when passenger flow is continued above preset threshold starting alarm or early warning, so as to
Manager, which takes action, accelerates passenger flow evacuation;Warning device includes computer application software figure or text importing alarm, mobile phone
Short message alarm, cell phone application application alarm or audible and visual alarm.
Preferably, the important component microprocessor algorithm processing unit of the front end intellectual analysis decision making device is optional
Select ARM9 series processors.
A kind of passenger flow analysis system of the present invention and its method, solve to market, rail traffic, entrance and exit of the park
The technical issues of carrying out accurate passenger flow analysing with the volume of the flow of passengers of the occasions such as passageway proposes the accuracy rate of volume of the flow of passengers identification
It rises, image is not only acquired by visible light video, is identified for the feature of human body head and body contour, height, it is also logical
It crosses Studies of Human Body Heat picture figure and analysis identification is carried out to passenger flow number, improve recognition accuracy;Present invention employs the progress of human body thermography
Volume of the flow of passengers identification, it is easy to use, do not need the calibration that fiducial temperature is carried out to passive type thermal imaging detection device.As long as human body with
There are the temperature difference for other objects or environment at one's side, and profile will be shown in thermography, is not related to the calibration of fiducial temperature, relatively hold
Easily carry out image recognition;Present invention employs human body thermographies to carry out volume of the flow of passengers identification, easy to implement, and human body is sent out under normal circumstances
The far infrared wavelength penetrated is near 9.6 microns, wavelength that the far infrared of wavelength (5.6-15 microns) and human body are launched
It overlaps, such thermal imaging apparatus industry is more general;The present invention carries out volume of the flow of passengers identification using Studies of Human Body Heat picture figure, can carry out two dimension
Image recognition, algorithm is relatively easy, not by such environmental effects, for whether there is or not luminous ray, ground form whether complicated, ground
Design and color whether especially, whether strong etc. the environmental factor of reflected light seemed inessential, these factors to heat radiation at
Picture and thermography identification do not cause at all to influence;The present invention uses front end intellectual analysis decision making device, can be conveniently special based on image
Seek peace neuroid algorithm load and improve extension, it is good right convenient for being provided for subsequent promotion accuracy rate more new algorithm
External tapping and running space;The present invention uses the pluggable multi-interface communication equipment in front end, can facilitate the building of communication network, not only
It can be communicated based on cable network, for the region of no construction wireline communication network, the WIFI using ad hoc network can be facilitated
Network, or the wireless network based on common carrier is used, NB-IoT network also can be used under extreme conditions, because NB-IoT covers
Lid gain has a distinct increment with respect to conventional wireless.
Claims (7)
1. a kind of passenger flow analysis system, it is characterised in that:Including monocular or more mesh visible light video collecting and detecting devices, monocular quilt
Dynamic formula thermal imaging detection device, front end intellectual analysis decision making device, the pluggable multi-interface communication equipment in front end, remote monitoring and administration
Device and front end warning device;
Monocular or more mesh visible light video collecting and detecting devices and monocular passive type thermal imaging detection device are mounted on entrance
Or it crosses right above road junction;
Monocular or more mesh visible light video collecting and detecting devices and monocular passive type thermal imaging detection device are connected by data line
Connect front end intellectual analysis decision making device;
Front end intellectual analysis decision making device connects the pluggable multi-interface communication equipment in front end by data line;
The pluggable multi-interface communication equipment in front end is communicated by cable or wireless network with remote monitoring and administration device;
Remote monitoring and administration device is communicated by data line with front end warning device.
2. a kind of passenger flow analysis system as described in claim 1, it is characterised in that:The monocular or more mesh visible light videos are adopted
Collect detection device include visible image capturing unit, video procession unit, storage unit and communication unit, the monocular or
The model NJ-SWKJ-3D201D of more mesh visible light video collecting and detecting devices.
3. a kind of passenger flow analysis system as claimed in claim 2, it is characterised in that:The monocular passive type thermal imaging detection dress
It sets comprising passive type infrared thermal imaging camera unit, thermal image processing and recognition unit, storage unit and communication unit, the quilt
Dynamic formula infrared thermal imaging camera unit includes germanium metal shot, uncooled fpa detector and encoder, and the monocular is passive
The model NJ-SWKJ-IR101G of formula thermal imaging detection device.
4. a kind of passenger flow analysis system as claimed in claim 3, it is characterised in that:The front end intellectual analysis decision making device packet
Processing unit containing microprocessor algorithm, storage unit and communications interface unit, the monocular or the acquisition inspection of more mesh visible light videos
The communication unit and the communication unit of the monocular passive type thermal imaging detection device for surveying device pass through described in data line connects
Communications interface unit, the model NJ-SWKJ-AI201D of the front end intellectual analysis decision making device.
5. a kind of passenger flow analysis system as claimed in claim 3, it is characterised in that:The pluggable multi-interface communication dress in front end
The model NJ-SWKJ-CM201W set;The remote monitoring and administration device includes router, server and personal computer;Institute
State the model NJ-SWKJ-AL001C of front end warning device.
6. a kind of passenger flow analysing method, it is characterised in that:Include the following steps:
Step 1:Establish a kind of passenger flow analysis system;
Step 2:Monocular or binocular visible light video collecting and detecting device are installed on entrance or crossed right above road junction, established angle
Degree uses 90 degree of right angle settings, and mounting height is preferably suggested between 2.5 meters to 5 meters;Monocular or binocular visible light video are adopted
Best acquisition parameters, IP address and related communication configuration, network time synchronization and periodic detection result is arranged in collection detection device
Report and submit the period, set entrance Pedestrian flow detection regional scope, monocular or binocular visible light video collecting and detecting device for pair
Image analysis is carried out in the flow of the people for entering and leaving the regional scope;
Monocular passive type thermal imaging detection device is installed on entrance or is crossed right above road junction, setting angle is vertical using 90 degree
Installation, mounting height are higher than visible light video collecting and detecting device, and best clap is arranged to monocular passive type thermal imaging detection device
Reporting and submitting the period for parameter, IP address and related communication configuration, network time synchronization and periodic detection result is taken the photograph, entrance people is set
Flow detection regional scope is consistent with the setting range of monocular or binocular visible light video collecting and detecting device, monocular passive type
Thermal imaging detection device is used to carry out thermal image analysis for the flow of the people for entering and leaving the region;
Step 3:IP address and related communication configuration are arranged to front end intellectual analysis decision making device, and selection setting is only to receive
Visible light video collecting and detecting device communication data, or only receive passive type thermal imaging detection device and report and submit data, or full reception
Mode;
Step 4:According to system application environment field network situation, actual physics are carried out to the pluggable multi-interface communication equipment in front end
Configuration and network parameter setting;
Step 5:Monocular or binocular visible light video collecting and detecting device identify passenger flow moving direction, according to passenger flow pedestrian detection mould
Type and the matching of various dimensions passenger flow characteristic calculate with image segmentation algorithm and dynamic programming algorithm and leave monitoring region
Different directions passenger flow number, using self-defined message, periodically will recognition result data and this during be used for verify key frame images
It is packaged into visible detection results messages body, and front end intellectual analysis decision making device global alignment is reported and submitted to analyze, the visible light
With detection time stamp and time range in testing result message body;
Step 6:Monocular passive type thermal imaging detection device is used to acquire and identify that the infrared emanation issued in tested scene to be raw
At image, matched according to passenger flow pedestrian's heat radiation detection model and thermal radiation of body characteristic, with image segmentation algorithm
And dynamic programming algorithm, it is analyzed for two dimensional image, human body is demarcated by infrared emanation thermography, identification passenger flow is mobile
Direction calculates the different directions passenger flow number for leaving monitoring region, using self-defined message, periodically by recognition result data and this phase
Between for the key frame images of verification be packaged into infrared light detection results messages body, and report and submit front end intellectual analysis decision making device comprehensive
Composition and division in a proportion is to analysis, with detection time stamp and time range in infrared light detection results messages body;
Step 7:Front end intellectual analysis decision making device carries out global alignment analysis according to itself initial setting up, selection:Front end intelligence
Analysis decision device is used for the passenger flow people reported and submitted in infrared light detection results messages body and visible detection results messages body
Number carries out analysis comparison;Directly pass through the pluggable multi-interface communication equipment in front end if the two data are consistent for passenger flow number number
According to being sent to remote monitoring and administration device;If inconsistent, just start verification scheme again, according to timestamp to temporary checking time
Key frame images carry out reanalysing verification in range, and integrated use motion detection algorithm and sorting algorithm obtain new judgement knot
Fruit;
Step 8:Front end intellectual analysis decision making device is analyzed according to itself initial setting up, selection without global alignment:Directly adopt
With directly by the output of monocular passive type thermal imaging detection device as a result, directlying adopt monocular or binocular visible light video is adopted
Collect the result of detection device output as final detection result;
Step 9:Front end intellectual analysis decision making device is according to the actual disposition of the pluggable multi-interface communication equipment in front end, by step 7
Or the final result of step 8, remote monitoring and administration device is sent to by the pluggable multi-interface communication equipment in front end;
The data that front end intellectual analysis decision making device will be unable to be successfully transferred to remote monitoring and administration device temporarily preserve, with
It is resumed when to be communicated normal;
Step 10:Remote monitoring and administration device for the data received are put in storage in real time, big data analysis, statistics, report
Table and early warning;
Step 11:Warning device is used for starting alarm or early warning when passenger flow is continued above preset threshold, to manage
Person, which takes action, accelerates passenger flow evacuation;Warning device includes computer application software figure or text importing alarm, SMS
Alarm, cell phone application application alarm or audible and visual alarm.
7. a kind of passenger flow analysing method as described in claim 1, it is characterised in that:The front end intellectual analysis decision making device
ARM9 series processors may be selected in important component microprocessor algorithm processing unit.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201810916826.0A CN108846389A (en) | 2018-08-13 | 2018-08-13 | A kind of passenger flow analysis system and its method |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201810916826.0A CN108846389A (en) | 2018-08-13 | 2018-08-13 | A kind of passenger flow analysis system and its method |
Publications (1)
Publication Number | Publication Date |
---|---|
CN108846389A true CN108846389A (en) | 2018-11-20 |
Family
ID=64193031
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN201810916826.0A Pending CN108846389A (en) | 2018-08-13 | 2018-08-13 | A kind of passenger flow analysis system and its method |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN108846389A (en) |
Cited By (4)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN109803230A (en) * | 2019-01-24 | 2019-05-24 | 北京万相融通科技股份有限公司 | A method of draw station ride area people distribution thermodynamic chart |
CN110321982A (en) * | 2019-07-03 | 2019-10-11 | 南京睿铁信息科技有限公司 | A kind of rail traffic section volume of the flow of passengers real-time computing technique |
CN110532931A (en) * | 2019-08-23 | 2019-12-03 | 深圳市驱动新媒体有限公司 | A kind of passenger flow analysing method and apparatus and equipment |
CN111862521A (en) * | 2019-04-28 | 2020-10-30 | 杭州海康威视数字技术股份有限公司 | Behavior thermodynamic diagram generation and alarm method and device, electronic equipment and storage medium |
Citations (2)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN102622798A (en) * | 2012-03-28 | 2012-08-01 | 东南大学 | Passenger flow statistical analysis system |
CN108206935A (en) * | 2016-12-16 | 2018-06-26 | 北京迪科达科技有限公司 | A kind of personnel amount statistical monitoring analysis system |
-
2018
- 2018-08-13 CN CN201810916826.0A patent/CN108846389A/en active Pending
Patent Citations (2)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN102622798A (en) * | 2012-03-28 | 2012-08-01 | 东南大学 | Passenger flow statistical analysis system |
CN108206935A (en) * | 2016-12-16 | 2018-06-26 | 北京迪科达科技有限公司 | A kind of personnel amount statistical monitoring analysis system |
Cited By (6)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN109803230A (en) * | 2019-01-24 | 2019-05-24 | 北京万相融通科技股份有限公司 | A method of draw station ride area people distribution thermodynamic chart |
CN109803230B (en) * | 2019-01-24 | 2021-03-12 | 北京万相融通科技股份有限公司 | Method for drawing personnel distribution thermodynamic diagram of bus taking area of station |
CN111862521A (en) * | 2019-04-28 | 2020-10-30 | 杭州海康威视数字技术股份有限公司 | Behavior thermodynamic diagram generation and alarm method and device, electronic equipment and storage medium |
WO2020221031A1 (en) * | 2019-04-28 | 2020-11-05 | 杭州海康威视数字技术股份有限公司 | Behavior thermodynamic diagram generation and alarm method and apparatus, electronic device and storage medium |
CN110321982A (en) * | 2019-07-03 | 2019-10-11 | 南京睿铁信息科技有限公司 | A kind of rail traffic section volume of the flow of passengers real-time computing technique |
CN110532931A (en) * | 2019-08-23 | 2019-12-03 | 深圳市驱动新媒体有限公司 | A kind of passenger flow analysing method and apparatus and equipment |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
CN108846389A (en) | A kind of passenger flow analysis system and its method | |
CN109886096B (en) | Wisdom tourism supervision and safe emergency management linkage command system | |
CN109644320B (en) | Method for detecting pedestrian flow in public place by using WI-FI probe | |
CN104459183B (en) | A kind of one camera vehicle speed measuring system and method based on Internet of Things | |
CN104613892B (en) | Merge the compound snow depth monitoring system of video detection technology and laser ranging technique | |
CN103745484B (en) | Worker target safety early-warning method for hot-line work on electric power facility | |
CN109362038A (en) | The method and system of guest flow statistics analysis and service based on WiFi probe | |
CN202676156U (en) | Electric transmission line condition monitoring system based on target image identification and benchmark measurement | |
CN105516584B (en) | Full-view image acquisition system, the device and method for measuring skyline based on it | |
CN205263990U (en) | Infrared thermal imaging forest fires on -line monitoring system | |
CN108205862A (en) | Transmission line forest fire guard system | |
KR101461184B1 (en) | Wether condition data extraction system using cctv image | |
CN110345878A (en) | A kind of tunnel deformation automatic monitoring system and method based on infrared target technology | |
CN111060073A (en) | Building outer wall detection system and application method thereof | |
CN106355895A (en) | Traffic flow and vehicle speed collecting device and method based on infrared matrixes | |
CN109714710A (en) | A kind of a wide range of track acquisition method of non-active cooperation personnel | |
CN106652291A (en) | Indoor simple monitoring and alarming system and method based on Kinect | |
CN107316460A (en) | A kind of monitoring car system and method with exceeded candid photograph function | |
CN116545122B (en) | Power transmission line external damage prevention monitoring device and external damage prevention monitoring method | |
CN110322703A (en) | One kind tests the speed bayonet type intersection safety warning system | |
CN105070065A (en) | Mobile intelligent traffic gate system and method adopting same to monitor vehicles | |
CN114630202A (en) | Drilling real-time monitoring system and monitoring method based on 5G communication technology | |
CN103728503B (en) | A kind of three-dimensional discharge path automatic production record of thunderbolt and recording method thereof being applied to ancient buildings | |
CN208924280U (en) | A kind of Community Watch management system | |
CN110164071A (en) | A kind of security system |
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 |
Application publication date: 20181120 |
|
RJ01 | Rejection of invention patent application after publication |