CN105513173B - Passenger flow direction recognizing method and system based on bidifly ligh-ranging - Google Patents
Passenger flow direction recognizing method and system based on bidifly ligh-ranging Download PDFInfo
- Publication number
- CN105513173B CN105513173B CN201510813086.4A CN201510813086A CN105513173B CN 105513173 B CN105513173 B CN 105513173B CN 201510813086 A CN201510813086 A CN 201510813086A CN 105513173 B CN105513173 B CN 105513173B
- Authority
- CN
- China
- Prior art keywords
- pedestrian
- feature
- time
- difference
- departure
- 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.)
- Active
Links
- 238000000034 method Methods 0.000 title claims abstract description 21
- 238000001514 detection method Methods 0.000 claims abstract description 118
- 238000010586 diagram Methods 0.000 description 3
- 230000006378 damage Effects 0.000 description 2
- 230000000694 effects Effects 0.000 description 2
- 238000007689 inspection Methods 0.000 description 2
- 238000012986 modification Methods 0.000 description 2
- 230000004048 modification Effects 0.000 description 2
- 238000012544 monitoring process Methods 0.000 description 2
- 208000027418 Wounds and injury Diseases 0.000 description 1
- 238000005516 engineering process Methods 0.000 description 1
- 230000005021 gait Effects 0.000 description 1
- 208000014674 injury Diseases 0.000 description 1
- 238000009434 installation Methods 0.000 description 1
- 230000003287 optical effect Effects 0.000 description 1
- 238000004445 quantitative analysis Methods 0.000 description 1
- 230000007704 transition Effects 0.000 description 1
- 230000000007 visual effect Effects 0.000 description 1
Classifications
-
- G—PHYSICS
- G07—CHECKING-DEVICES
- G07C—TIME OR ATTENDANCE REGISTERS; REGISTERING OR INDICATING THE WORKING OF MACHINES; GENERATING RANDOM NUMBERS; VOTING OR LOTTERY APPARATUS; ARRANGEMENTS, SYSTEMS OR APPARATUS FOR CHECKING NOT PROVIDED FOR ELSEWHERE
- G07C9/00—Individual registration on entry or exit
- G07C9/30—Individual registration on entry or exit not involving the use of a pass
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V40/00—Recognition of biometric, human-related or animal-related patterns in image or video data
- G06V40/10—Human or animal bodies, e.g. vehicle occupants or pedestrians; Body parts, e.g. hands
- G06V40/103—Static body considered as a whole, e.g. static pedestrian or occupant recognition
Landscapes
- Engineering & Computer Science (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Human Computer Interaction (AREA)
- Multimedia (AREA)
- Theoretical Computer Science (AREA)
- Traffic Control Systems (AREA)
Abstract
The present invention relates to a kind of passenger flow direction recognizing method and system based on bidifly ligh-ranging.This method includes：Obtain first pedestrian's feature of the detection faces by the laser detector；Obtain second pedestrian's feature by the laser detector detection faces；First pedestrian's feature and the entry time in second pedestrian's feature and/or time departure, height, width and position are matched successively, if all fitting through, first pedestrian's feature is characterized as same pedestrian with the second pedestrian；First pedestrian's feature is contrasted with entry time, time departure and peak in second pedestrian's feature by one or more time parameters in the detection faces time, direct of travel of the pedestrian in sense channel is identified according to comparing result；According to the direct of travel of each pedestrian, the passenger flow direction in sense channel is obtained.The present invention uses two laser scanning device rangings, it is not necessary to follows the trail of pedestrian, improves Statistical Speed, the detection place applied to large passenger flow.
Description
Technical field
The present invention relates to passenger flow statisticses technical field, more particularly to a kind of passenger flow direction discernment side based on bidifly ligh-ranging
Method and system.
Background technology
With expanding economy, flow of personnel aggravation, transport hub, museum, exhibition center and large-scale activity is caused to show
Etc. public place occur passenger flow jam situation in rush hour often, caused by emergency case and passenger flow condition monitoring are unfavorable
Harm is also increasingly severe.Therefore need to analyze passenger flow, effectively control intensity of passenger flow, prevent that stream of people's transition is crowded even
Trample the generation of the occurred events of public safety such as injury.For public transportation systems such as railway, subway and buses, full and accurate grasp is each
When bar circuit, the flow direction of website passenger flow, stream, the information such as flow and its distribution, public transport company's line adjustment will be facilitated and to car
Resource carries out reasonable disposition.
It was to utilize manual type in the past to obtain accurate volume of the flow of passengers data, and arranged special messenger to carry out mesh to key area
Depending on counting and measuring.But as intensity of passenger flow is increasing and the energy of monitoring personnel is limited so that manual method can only be made
Qualitatively to understand, it is difficult to make quantitative analysis, it is also difficult to a wide range of popularization and application.Have been carried out in the prior art
The automation of passenger flow statisticses, such as：(1) porch sets the contact method of mechanical lifeline：In porch, machinery is set
Lifeline, gateway order is strictly controlled, it is accurate to count.But for installed in can simultaneously as entrance with outlet
For the mechanical railing of passage, then there is difficulty in the direction for counting pedestrian.(2) non-contact method based on machine vision：Machine
The method of device vision can improve the speed of statistics for mechanical railing, but for the machine for two-way sense channel
Device, machine need to carry out detecting and tracking to pedestrian, so as to judge the direction of pedestrian, cause Statistical Rate to be affected, and
Also easily influenceed by environment, light, be not suitable for the detection place of large passenger flow.
The content of the invention
One of purpose of the present invention is to provide a kind of passenger flow direction recognizing method based on bidifly ligh-ranging and is
System, to solve the technical problem that mechanical railing and visual machine in the prior art are not suitable for large passenger flow detection place.
For achieving the above object, in a first aspect, the embodiments of the invention provide a kind of visitor based on bidifly ligh-ranging
Direction recognizing method is flowed, including：
First pedestrian's feature of the detection faces by first laser detection means is obtained, wherein the first row people feature bag
Include height, width, position, entry time, time departure and peak and pass through the detection faces time；
Second pedestrian's feature by second laser detection means detection faces is obtained, wherein the second pedestrian feature includes
Highly, width, position, entry time, time departure and peak pass through the detection faces time；
Match successively entry time in the first pedestrian feature and the second pedestrian feature and/or time departure,
Highly, width and position, if all fitting through, the first pedestrian feature is characterized as same row with second pedestrian
People；
The first pedestrian feature is contrasted with entry time, time departure and peak in the second pedestrian feature to pass through
One or more time parameters in the detection faces time, direct of travel of the pedestrian in sense channel is identified according to comparing result；
According to the direct of travel of each pedestrian, the passenger flow direction in the sense channel is obtained.
Alternatively, the entry time matched successively in the first pedestrian feature and the second pedestrian feature, from
ETAD expected time of arrival and departure, height, width and position, if all fitting through, the first pedestrian feature is characterized as with second pedestrian
In the step of same pedestrian, including：
The first pedestrian feature and the entry time and/or time departure in the second pedestrian feature are contrasted respectively,
To obtain the difference of the difference of entry time and/or time departure；If the difference of entry time and/or the difference of time departure exist
In preset time range, into continuing to match in next step；
The first pedestrian feature and the height and/or width in the second pedestrian feature are contrasted respectively, to obtain height
Spend difference and/or width differential；If height difference is in preset height difference range and/or width differential in predetermined width difference model
In enclosing, into continuing to match in next step；
The first pedestrian feature and the position in the second pedestrian feature are contrasted, to obtain position difference；If position
For difference in predeterminated position difference range, the first pedestrian feature represents same pedestrian with the second pedestrian feature.
Alternatively, contrast the first pedestrian feature and entry time, time departure in the second pedestrian feature
With peak by one or more time parameters in the detection faces time, identify the pedestrian in sense channel according to comparing result
Direct of travel the step of in, direct of travel of the pedestrian in sense channel is obtained using below equation：
In formula, orient is represented into outgoing direction, when orient be 1 interval scale pedestrian enter sense channel, when orient be 0
Interval scale pedestrian leaves sense channel；ITA, ITB are fashionable to enter in entry time, second pedestrian's feature in first pedestrian's feature
Between；OTA, OTB are time departure in entry time, second pedestrian's feature in first pedestrian's feature；HTA, HTB are that the first pedestrian is special
Peak passes through the detection faces time in entry time, second pedestrian's feature in sign.
Second aspect, the embodiment of the present invention additionally provide a kind of passenger flow direction discernment system based on bidifly ligh-ranging, bag
Include：First laser detection means, second laser detection means and processing unit, wherein：
The first laser detection means is arranged on the tip position of sense channel and its angle can cover the inspection
Passage is surveyed, for obtaining first pedestrian's feature of the detection faces by the laser detector, wherein the first row people feature
Pass through the detection faces time including height, width, position, entry time, time departure and peak；
The second laser detection means is arranged on the direction of sense channel pedestrian disengaging and examined with the first laser
Surveying device keeps pre-determined distance to be used to obtain second pedestrian's feature by the laser detector detection faces, wherein described second
Pedestrian's feature passes through the detection faces time including height, width, position, entry time, time departure and peak；
The processing unit is connected with the first laser detection means and the second laser detection means, is used for
Obtain the passenger flow direction in sense channel.
Alternatively, the processing unit includes：
Matching unit, for matching the first pedestrian feature and the entry time in the second pedestrian feature successively
And/or time departure, height, width and position, if all fitting through, the first pedestrian feature and second pedestrian
It is characterized as same pedestrian；
Direct of travel recognition unit, it is fashionable with entering in the second pedestrian feature for contrasting the first pedestrian feature
Between, time departure and peak by one or more time parameters in the detection faces time, the pedestrian is identified according to comparing result
Direct of travel in sense channel；
Passenger flow direction acquiring unit, for the direct of travel according to each pedestrian, obtain the passenger flow in the sense channel
Direction.
Alternatively, the matching unit includes：
First comparison unit is fashionable with entering in the second pedestrian feature for contrasting the first pedestrian feature respectively
Between and/or time departure, to obtain the difference of the difference of entry time and/or time departure；If the difference of entry time and/or
The difference of time departure is in preset time range, into continuing to match in next step；
Second comparison unit, for contrasting the first pedestrian feature and the height in the second pedestrian feature respectively
And/or width, to obtain height difference and/or width differential；If height difference is in preset height difference range and/or stand out
Value is in predetermined width difference range, into continuing to match in next step；
3rd comparison unit, for contrasting the first pedestrian feature and the position in the second pedestrian feature, to obtain
Difference is put in fetch bit；If position difference is in predeterminated position difference range, the first pedestrian feature and the second pedestrian feature
Represent same pedestrian.
Alternatively, in the direct of travel recognition unit, row of the pedestrian in sense channel is obtained using below equation
Enter direction：
In formula, orient is represented into outgoing direction, when orient be 1 interval scale pedestrian enter sense channel, when orient be 0
Interval scale pedestrian leaves sense channel；ITA, ITB are fashionable to enter in entry time, second pedestrian's feature in first pedestrian's feature
Between；OTA, OTB are time departure in entry time, second pedestrian's feature in first pedestrian's feature；HTA, HTB are that the first pedestrian is special
Peak passes through the detection faces time in entry time, second pedestrian's feature in sign.
The present invention uses two laser scanning device rangings, avoids the influence of environment and light；Also, by two laser
Scanning means detects pedestrian image respectively, it is not necessary to pedestrian is tracked, improves the Statistical Speed of system；In addition, laser
Scanning means sweep length can apply to the detection place of large passenger flow up to 20 meters.
Brief description of the drawings
The features and advantages of the present invention can be more clearly understood by reference to accompanying drawing, accompanying drawing is schematically without that should manage
Solve to carry out any restrictions to the present invention, in the accompanying drawings：
Fig. 1 is a kind of passenger flow direction recognizing method flow signal based on bidifly ligh-ranging provided in an embodiment of the present invention
Figure；
Fig. 2 is a kind of passenger flow direction discernment system block diagram based on bidifly ligh-ranging provided in an embodiment of the present invention；
Fig. 3 is the method flow schematic diagram of acquisition pedestrian's direct of travel provided in an embodiment of the present invention；
Fig. 4 is two laser detectors detection principle diagram provided in an embodiment of the present invention；
Fig. 5 is processing unit structured flowchart provided in an embodiment of the present invention.
Embodiment
With reference to the accompanying drawings and examples, the embodiment of the present invention is described in further detail.Implement below
Example is used to illustrate the present invention, but is not limited to the scope of the present invention.
In a first aspect, the embodiments of the invention provide a kind of passenger flow direction recognizing method based on bidifly ligh-ranging, such as Fig. 1
It is shown, including：
First pedestrian's feature of the detection faces by first laser detection means is obtained, wherein first pedestrian's feature includes height
Degree, width, position, entry time, time departure and peak pass through the detection faces time；
Second pedestrian's feature by second laser detection means detection faces is obtained, wherein second pedestrian's feature includes height
Degree, width, position, entry time, time departure and peak pass through the detection faces time；
First pedestrian's feature and the entry time and/or time departure, height, width in second pedestrian's feature are matched successively
And position, if all fitting through, first pedestrian's feature is characterized as same pedestrian with the second pedestrian；
When contrasting that entry time, time departure and peak pass through detection faces in first pedestrian's feature and second pedestrian's feature
Between middle one or more time parameters, direct of travel of the pedestrian in sense channel is identified according to comparing result；
According to the direct of travel of each pedestrian, the passenger flow direction in sense channel is obtained.
Passenger flow direction recognizing method provided by the invention is described in detail below.
As shown in Fig. 2 passenger flow direction recognizing method provided by the invention, for being provided with the visitor of two laser detectors
Flow direction discernment system.First laser detection means 200 is arranged on the tip position of sense channel 100 and its angle can be covered
Cover the sense channel 100.It is also equipped with keeping pre- with first laser detection means 200 on the direction of sense channel pedestrian disengaging
If the second laser detection means 300 of distance.Wherein, the detection range of first laser detection means 200 is detection faces 201, the
The detection range of dual-laser detection means 300 is detection faces 301.
It will be appreciated that above the installation site of first laser detection means 200 and second laser detection means 300 is protected
Hold pre-determined distance to refer to, the pre-determined distance can make two laser detector normal works, and both will not form interference.
The projected distance is not fixed value, and those skilled in the art can carry out reasonable set according to specifically used scene, and the present invention does not limit
It is fixed.
When pedestrian passes through detection faces 201, first laser detection means 200 obtains the first pedestrian by detection faces 201
Feature.The first pedestrian feature includes：Highly, width, position, entry time, time departure and peak pass through detection faces
Time.It will be appreciated that at the time of entry time refers to when pedestrian has just enter into detection faces；Time departure refers to that pedestrian has just left inspection
At the time of during survey face；Peak is referred to by the detection faces time, at the time of the head of people is located at detection faces.
Due to the spacing of the detection faces 201 and the detection faces 301 of second laser detection means of first laser detection means 200
From not too large, after pedestrian leaves detection faces 201, detection faces 301 can be entered, now second laser detection means 300 can obtain
Pass through second pedestrian's feature of detection faces 301.Identical with first pedestrian's feature, the second pedestrian feature includes height, width, position
Put, entry time, time departure and peak pass through the detection faces time.
First pedestrian's feature and second laser detection means 300, which are got, in first laser detection means 200 gets the
After two pedestrian's features, it is necessary to according to the direct of travel of above-mentioned first pedestrian feature and the second each pedestrian of pedestrian's feature recognition, such as
Shown in Fig. 3, identification step is as follows：
S1, when contrasting the entry time in the first pedestrian feature and the second pedestrian feature respectively and/or leaving
Between, to obtain the difference of the difference of entry time and/or time departure；If the difference of entry time and/or the difference of time departure
Value is in preset time range, into continuing to match in next step.
It will be appreciated that because two detection faces maintain a certain distance, therefore entrance of the pedestrian by two detection faces
Time can have certain difference with time departure.The difference of entry time and the difference of time departure are, it is necessary to according to two
The distance between detection faces and the gait of march of pedestrian are configured, and for different sense channels, above-mentioned difference can be entered
Row is rationally set.
S2, the first pedestrian feature and the height and/or width in the second pedestrian feature are contrasted respectively, to obtain
Height difference and/or width differential；If height difference is in preset height difference range and/or width differential in predetermined width difference
In the range of, into continuing to match in next step.
S3, contrast the first pedestrian feature and the position in the second pedestrian feature, to obtain position difference；If position
Difference is put in predeterminated position difference range, the first pedestrian feature represents same pedestrian with the second pedestrian feature.
It will be appreciated that the difference of position refers to, the transverse shifting of the position of pedestrian in two detection faces.Normal conditions
Under, if when same person is advanced, in the case that the distance between two detection faces is not too big, the transverse shifting of pedestrian
Be it is very small, can according to the distance between two detection faces rationally set location difference.
S4, first pedestrian's feature of contrast and entry time, time departure and peak in second pedestrian's feature pass through detection
One or more time parameters in the time of face, direct of travel of the pedestrian in sense channel is identified according to comparing result；
It will be appreciated that during identification direct of travel, due to different at the time of pedestrian passes through two detection faces, then can enter
The angle of incidence, time departure peak are identified by one or more time parameter in the detection faces time.Alternatively, this hair
In the step of direct of travel of the pedestrian in sense channel is identified in bright embodiment, the pedestrian is obtained using below equation and examined
The direct of travel surveyed in passage：
In formula, orient is represented into outgoing direction, when orient be 1 interval scale pedestrian enter sense channel, when orient be 0
Interval scale pedestrian leaves sense channel；ITA, ITB are fashionable to enter in entry time, second pedestrian's feature in first pedestrian's feature
Between；OTA, OTB are time departure in entry time, second pedestrian's feature in first pedestrian's feature；HTA, HTB are that the first pedestrian is special
Peak passes through the detection faces time in entry time, second pedestrian's feature in sign.
Such as the entry time by detection faces 200 is：5 points 30 seconds, and the entry time Jing Guo detection faces 300 is：5 points
31 seconds, and also specify, it is that then the direct of travel of pedestrian is entrance into sense channel from detection faces 200 to detection faces 300
Sense channel.Other situations can be configured according to the above description.
Second aspect, the embodiment of the present invention additionally provide a kind of passenger flow direction discernment system based on bidifly ligh-ranging, such as
Shown in Fig. 4, including：First laser detection means, second laser detection means and processing unit, wherein：
First laser detection means 200 is arranged on the tip position of sense channel 100 and its angle can cover detection
Passage, it is also equipped with keeping the second of pre-determined distance to swash with first laser detection means on the direction of sense channel pedestrian disengaging
Optical detection device 300；First laser detection means 200 is used for the first pedestrian for obtaining the detection faces by the laser detector
Feature, wherein first pedestrian's feature passes through detection faces including height, width, position, entry time, time departure and peak
Time；Second laser detection means 300 is used to obtain second pedestrian's feature by the laser detector detection faces, wherein the
Two pedestrian's features pass through the detection faces time including height, width, position, entry time, time departure and peak；
Processing unit 400 is connected with first laser detection means 200 and second laser detection means 300, for obtaining
Take the passenger flow direction in sense channel 100.
Alternatively, as shown in figure 5, above-mentioned processing unit 400 includes：
Matching unit, for matching first pedestrian's feature and the entry time in second pedestrian's feature successively and/or leaving
Time, height, width and position, if all fitting through, first pedestrian's feature is characterized as same pedestrian with the second pedestrian；
If matching is by the way that first pedestrian's feature is characterized as two pedestrians with the second pedestrian
Direct of travel recognition unit, during for contrasting entry time in first pedestrian's feature and second pedestrian's feature, leaving
Between and peak by one or more time parameters in the detection faces time, identify the pedestrian in sense channel according to comparing result
Interior direct of travel；
Passenger flow direction acquiring unit, for the direct of travel according to each pedestrian, obtain the passenger flow direction in sense channel.
Alternatively, matching unit includes：
First comparison unit, for contrast respectively entry time in first pedestrian's feature and second pedestrian's feature and/or
Time departure, to obtain the difference of the difference of entry time and/or time departure；If the difference of entry time and/or when leaving
Between difference in preset time range, into continuing to match in next step；
Second comparison unit, for contrasting first pedestrian's feature and the height and/or width in second pedestrian's feature respectively,
To obtain height difference and/or width differential；If height difference is in preset height difference range and/or width differential in default width
Spend in difference range, into continuing to match in next step；
3rd comparison unit, for contrasting first pedestrian's feature and the position in second pedestrian's feature, to obtain alternate position spike
Value；If position difference, in predeterminated position difference range, first pedestrian's feature represents same row with the second pedestrian feature
People.
Alternatively, in direct of travel recognition unit, the traveling side of the pedestrian in sense channel is obtained using below equation
To：
In formula, orient is represented into outgoing direction, when orient be 1 interval scale pedestrian enter sense channel, when orient be 0
Interval scale pedestrian leaves sense channel；ITA, ITB are fashionable to enter in entry time, second pedestrian's feature in first pedestrian's feature
Between；OTA, OTB are time departure in entry time, second pedestrian's feature in first pedestrian's feature；HTA, HTB are that the first pedestrian is special
Peak passes through the detection faces time in entry time, second pedestrian's feature in sign.
Passenger flow direction discernment system provided by the invention realized based on passenger flow direction recognizing method described above, thus can
To solve same technical problem, and identical technique effect is obtained, this is no longer going to repeat them.
Passenger flow direction recognizing method and system provided in an embodiment of the present invention based on bidifly ligh-ranging, using two laser
Scanning means ranging, avoid the influence of environment and light；Also, pedestrian image is detected respectively by two laser scanning devices,
Pedestrian need not be tracked, improve the Statistical Speed of system；In addition, laser scanning device sweep length is up to 20 meters,
It can apply to the detection place of large passenger flow.
In the present invention, term " first ", " second ", " the 3rd " are only used for describing purpose, and it is not intended that instruction or
Imply relative importance.Term " multiple " refers to two or more, is limited unless otherwise clear and definite.
Although being described in conjunction with the accompanying embodiments of the present invention, those skilled in the art can not depart from this hair
Various modifications and variations are made in the case of bright spirit and scope, such modifications and variations are each fallen within by appended claims
Within limited range.
Claims (4)
- A kind of 1. passenger flow direction recognizing method based on bidifly ligh-ranging, it is characterised in that including：First pedestrian's feature of the detection faces by first laser detection means is obtained, wherein the first row people feature includes height Degree, width, position, entry time, time departure and peak pass through the detection faces time；Second pedestrian's feature by second laser detection means detection faces is obtained, wherein the second pedestrian feature includes height Degree, width, position, entry time, time departure and peak pass through the detection faces time；Match successively entry time in the first pedestrian feature and the second pedestrian feature and/or time departure, height, Width and position, if all fitting through, the first pedestrian feature is characterized as same pedestrian with second pedestrian；Contrast the first pedestrian feature and pass through detection with entry time, time departure and peak in the second pedestrian feature One or more time parameters in the time of face, direct of travel of the pedestrian in sense channel is identified according to comparing result；According to the direct of travel of each pedestrian, the passenger flow direction in the sense channel is obtained；The first pedestrian feature and the entry time and/or time departure in the second pedestrian feature are contrasted respectively, to obtain Take the difference of entry time and/or the difference of time departure；If the difference of entry time and/or the difference of time departure are default In time range, into continuing to match in next step；The first pedestrian feature and the height and/or width in the second pedestrian feature are contrasted respectively, to obtain difference in height Value and/or width differential；If height difference is in preset height difference range and/or width differential in predetermined width difference range It is interior, into continuing to match in next step；The first pedestrian feature and the position in the second pedestrian feature are contrasted, to obtain position difference；If position difference In predeterminated position difference range, the first pedestrian feature represents same pedestrian with the second pedestrian feature.
- 2. passenger flow direction recognizing method according to claim 1, it is characterised in that contrast the first pedestrian feature Joined with entry time, time departure and peak in the second pedestrian feature by one or more times in the detection faces time Number, in the step of identifying direct of travel of the pedestrian in sense channel according to comparing result, the row is obtained using below equation Direct of travel of the people in sense channel：In formula, orient is represented into outgoing direction, when orient be 1 interval scale pedestrian enter sense channel, when orient was 0 epoch Table row people leaves sense channel；ITA, ITB are entry time in entry time, second pedestrian's feature in first pedestrian's feature； OTA, OTB are time departure in entry time, second pedestrian's feature in first pedestrian's feature；HTA, HTB are first pedestrian's feature Peak passes through the detection faces time in middle entry time, second pedestrian's feature.
- A kind of 3. passenger flow direction discernment system based on bidifly ligh-ranging, it is characterised in that including：First laser detection means, Second laser detection means and processing unit, wherein：The first laser detection means is arranged on the tip position of sense channel and its angle can cover the detection and lead to Road, for obtaining first pedestrian's feature of the detection faces by the laser detector, wherein the first row people feature includes Highly, width, position, entry time, time departure and peak pass through the detection faces time；The second laser detection means is arranged on the direction of sense channel pedestrian disengaging and detected with the first laser and filled Put and keep pre-determined distance to be used to obtain second pedestrian's feature by the laser detector detection faces, wherein second pedestrian Feature passes through the detection faces time including height, width, position, entry time, time departure and peak；The processing unit is connected with the first laser detection means and the second laser detection means, for obtaining Passenger flow direction in sense channel；The processing unit includes：Matching unit, for match successively entry time in the first pedestrian feature and the second pedestrian feature and/or Time departure, height, width and position, if all fitting through, the first pedestrian feature and the second pedestrian feature For same pedestrian；Direct of travel recognition unit, for contrast entry time in the first pedestrian feature and the second pedestrian feature, from ETAD expected time of arrival and departure and peak identify that the pedestrian is detecting by one or more time parameters in the detection faces time according to comparing result Direct of travel in passage；Passenger flow direction acquiring unit, for the direct of travel according to each pedestrian, obtain the passenger flow direction in the sense channel；The matching unit includes：First comparison unit, for contrasting the first pedestrian feature and the entry time in the second pedestrian feature respectively And/or time departure, to obtain the difference of the difference of entry time and/or time departure；If the difference of entry time and/or from The difference of ETAD expected time of arrival and departure is in preset time range, into continuing to match in next step；Second comparison unit, for contrast respectively height in the first pedestrian feature and the second pedestrian feature and/or Width, to obtain height difference and/or width differential；If height difference exists in preset height difference range and/or width differential In predetermined width difference range, into continuing to match in next step；3rd comparison unit, for contrasting the first pedestrian feature and the position in the second pedestrian feature, to obtain position Put difference；If position difference, in predeterminated position difference range, the first pedestrian feature represents with the second pedestrian feature Same pedestrian.
- 4. passenger flow direction discernment system according to claim 3, it is characterised in that in the direct of travel recognition unit, Direct of travel of the pedestrian in sense channel is obtained using below equation：In formula, orient is represented into outgoing direction, when orient be 1 interval scale pedestrian enter sense channel, when orient was 0 epoch Table row people leaves sense channel；ITA, ITB are entry time in entry time, second pedestrian's feature in first pedestrian's feature； OTA, OTB are time departure in entry time, second pedestrian's feature in first pedestrian's feature；HTA, HTB are first pedestrian's feature Peak passes through the detection faces time in middle entry time, second pedestrian's feature.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201510813086.4A CN105513173B (en) | 2015-11-20 | 2015-11-20 | Passenger flow direction recognizing method and system based on bidifly ligh-ranging |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201510813086.4A CN105513173B (en) | 2015-11-20 | 2015-11-20 | Passenger flow direction recognizing method and system based on bidifly ligh-ranging |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN105513173A CN105513173A (en) | 2016-04-20 |
| CN105513173B true CN105513173B (en) | 2018-03-16 |
Family
ID=55721124
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201510813086.4A Active CN105513173B (en) | 2015-11-20 | 2015-11-20 | Passenger flow direction recognizing method and system based on bidifly ligh-ranging |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN105513173B (en) |
Families Citing this family (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN110806588A (en) * | 2019-10-17 | 2020-02-18 | 北醒（北京）光子科技有限公司 | Pedestrian flow detection system based on laser radar |
| CN110929636A (en) * | 2019-11-20 | 2020-03-27 | 上海融军实业有限公司 | Passenger flow size and direction detection method and system |
Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN101644717A (en) * | 2009-08-31 | 2010-02-10 | 北京大学 | Pedestrian advancing direction judging method adopting laser scanning |
| CN102521906A (en) * | 2011-12-22 | 2012-06-27 | 北京竞业达数码科技有限公司 | Passenger flow direction identification method based on double laser ranging and device thereof |
| CN104112305A (en) * | 2013-10-17 | 2014-10-22 | 北京竞业达数码科技有限公司 | Passenger flow monitoring method and apparatus based on dual laser ranging |
| CN204463274U (en) * | 2015-03-19 | 2015-07-08 | 武汉万集信息技术有限公司 | The single laser pedestrian detection device of a kind of inclination |
Family Cites Families (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| JP2007018118A (en) * | 2005-07-06 | 2007-01-25 | Systec:Kk | Passing direction discrimination device by means of measuring distance |
-
2015
- 2015-11-20 CN CN201510813086.4A patent/CN105513173B/en active Active
Patent Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN101644717A (en) * | 2009-08-31 | 2010-02-10 | 北京大学 | Pedestrian advancing direction judging method adopting laser scanning |
| CN102521906A (en) * | 2011-12-22 | 2012-06-27 | 北京竞业达数码科技有限公司 | Passenger flow direction identification method based on double laser ranging and device thereof |
| CN104112305A (en) * | 2013-10-17 | 2014-10-22 | 北京竞业达数码科技有限公司 | Passenger flow monitoring method and apparatus based on dual laser ranging |
| CN204463274U (en) * | 2015-03-19 | 2015-07-08 | 武汉万集信息技术有限公司 | The single laser pedestrian detection device of a kind of inclination |
Also Published As
| Publication number | Publication date |
|---|---|
| CN105513173A (en) | 2016-04-20 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN109191911A (en) | A kind of tunnel road conditions early warning system, method and computer readable storage medium | |
| CN110515073A (en) | The trans-regional networking multiple target tracking recognition methods of more radars and device | |
| KR101689567B1 (en) | System for calculating vehicle speed in section of a road and method thereof | |
| KR101446546B1 (en) | Display system of vehicle information based on the position | |
| CN103091724B (en) | Foreign matter automatic testing method and device thereof between straight line metro platform shield door and train | |
| CN106448180A (en) | Long-and-large-tunnel traffic-event real-time detection system and method thereof | |
| CN102005069A (en) | Anti-tailing system using multi-person detection algorithm based on gait pattern tracking | |
| JP7230173B2 (en) | Abandoned object detection device and abandoned object detection method | |
| CN109801421A (en) | A kind of subway intelligent and safe detection system and method | |
| CN106864481B (en) | A kind of train automatic safeguarding method | |
| JP2011257400A (en) | Radiation portal comprising occupancy sensor system | |
| JP4286074B2 (en) | Spatial information distribution device | |
| KR102228403B1 (en) | Vehicles information collecting system and method | |
| CN106296951A (en) | A kind of system for subway station people's flow monitoring | |
| CN105513173B (en) | Passenger flow direction recognizing method and system based on bidifly ligh-ranging | |
| CN109305168A (en) | A kind of deviation alarm assessment system and appraisal procedure | |
| EP0928465A1 (en) | Detection system | |
| CN113574574A (en) | Moving object monitoring system, control server for moving object monitoring system, and moving object monitoring method | |
| CN116299751A (en) | Method and device for rapidly extracting passive terahertz human body security inspection information | |
| CN108639108A (en) | A kind of locomotive shunting security protection system | |
| KR101475062B1 (en) | Vehicle traffic information management system | |
| US10699572B2 (en) | Passenger counting for a transportation system | |
| KR20120110462A (en) | Regulation system of u-turn violation vehicle | |
| CN106251651A (en) | A kind of crossing traffic signal control method utilizing plane cognition technology and system | |
| CN108961524B (en) | Civilized queuing device and method thereof |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| C06 | Publication | ||
| PB01 | Publication | ||
| C10 | Entry into substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant | ||
| CP03 | Change of name, title or address | ||
| CP03 | Change of name, title or address |
Address after: 100073 Guanganmen street, Xicheng District, Xicheng District, Beijing Co-patentee after: Beijing jingyeda digital Polytron Technologies Inc Patentee after: Beijing Traffic Information Center Address before: 100073 Beijing Fengtai District six mile bridge, Nan Li Jia nine, the first building. Co-patentee before: Beijing Jingyeda Digital Technology Co., Ltd. Patentee before: Beijing Traffic Information Center |