CN104978782B - Passenger flow analysing method based on touch screen technology - Google Patents
Passenger flow analysing method based on touch screen technology Download PDFInfo
- Publication number
- CN104978782B CN104978782B CN201410143258.7A CN201410143258A CN104978782B CN 104978782 B CN104978782 B CN 104978782B CN 201410143258 A CN201410143258 A CN 201410143258A CN 104978782 B CN104978782 B CN 104978782B
- Authority
- CN
- China
- Prior art keywords
- footprint
- passenger flow
- pedestrian
- marking
- module
- 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
Landscapes
- Image Analysis (AREA)
Abstract
The invention discloses a kind of passenger flow analysing method based on touch screen technology, it is a kind of brand-new passenger flow statisticses means, a series of footprints that this method is passed by touch panel by analyzing pedestrian and left, so as to obtain more accurately volume of the flow of passengers data and volume of the flow of passengers sex composition.Compared with existing passenger flow statistical method, this method can provide more abundant passenger flow information, and strong interference immunity, and deployment is simple, require relatively low to installation environment.
Description
Technical field
The present invention relates to passenger flow statisticses field, more particularly to a kind of passenger flow analysing method based on touch screen technology.
Background technology
Passenger flow analysing is all an important market survey means in public transport or Retail chain industry, immediately
Passenger flow data or the passenger flow data storehouse detected and set up for a long time can effectively instruct government decision and enterprise operation, Some Enterprises
Think that the sex composition analysis of the volume of the flow of passengers is also most important.
Existing guest flow statistics technology mainly has artificial statistics, infrared statistics, the passenger flow statisticses based on video.
It is personal that the accuracy rate manually counted directly depends on statistician, although can carry out volume of the flow of passengers gender analysis, but
It is that cost of labor is big, is only applicable to the sampling statistics of short period, is not easy to use with other intelligence systems synthesis.
Infrared statistics for entire group accuracy rate is relatively low, it is impossible to which congested conditions are carried out with effective detection, and application scenarios are limited, it is impossible to property
Do not analyze.
Passenger flow statisticses deployment based on video is more complicated, and environment is more sensitive to external world.
In summary, the installation and deployment that passenger flow analysing method of the prior art has are complicated, and some accuracys rate are too low, and
Passenger flow sex can not be all counted, however as the development of science and technology, touch screen technology application is more and more wider, and is widely used in figure
Development as analysis with the mode identification technology of process field in recent years is particularly rapid, pattern-recognition (Pattern
Recognition) refer to the various forms of information for characterizing things or phenomenon are handled and analyzed, with to things or phenomenon
The process for being described, recognize, classifying and explaining.When the surface of the touch Panel based on touch screen technology can be produced by ambient pressure
The marking of raw definite shape, such as when pedestrian is stepped down on panel, toy is stepped down on panel, object is pulled and can all produced on panel
The raw different markings, the characteristics of these are imprinted with respective, Land use models identification technology can classify these markings, obtain the marking
Species, the marking feature that masculinity and femininity is stepped down on panel is also different, and male's footprint marking and the female track marking are gathered around
The masculinity and femininity footprint marking can be made classification by the characteristics of having respective, Land use models identification technology, then by touch screen technology
It is combined with mode identification technology, a kind of brand-new passenger flow statistical method can be obtained.
The content of the invention
The purpose of the present invention is to propose to a kind of passenger flow analysing method based on touch screen technology.
The technical problem to be solved in the present invention is to provide a kind of passenger flow analysing method, and this method needs to dispose simply, to peace
Fill environmental requirement low, and more accurately volume of the flow of passengers data are provided, the sex composition of the volume of the flow of passengers can be analyzed simultaneously.
In order to solve the above technical problems, the present invention takes following technical scheme：A kind of passenger flow based on touch screen technology is provided
Statistical method, this method includes marking acquisition module, footprint recognition module, analysis counting module, and the marking acquisition module is used
Walked in gather pedestrian on touch panel, due to the marking that panel pressure changes and produces；The footprint recognition mould
Block is used for carrying out pattern-recognition to the marking, so as to judge which is pedestrian's footprint, the footprint recognition module can use foot
Mark grader judges whether the marking belongs to pedestrian, and footprint grader is training gained, training step is as follows, and all kinds of pedestrians are sufficient
Positive negative sample, using other markings as negative sample, is finally delivered to pattern recognition classifier device and learn by mark as positive sample
To footprint grader；The analysis counting module is used for analyzing footprint direction, the timeliness of footprint and spatiality flow of guests system
Meter, the module can also judge that footprint belongs to sex to obtain volume of the flow of passengers sex composition by pattern-recognition.
Brief description of the drawings
Fig. 1 --- the passenger flow analysing work structuring figure based on touch screen technology
Embodiment
The passenger flow analysing of the present invention based on touch screen technology is further elucidated below.
Passenger flow analysing method of the present invention is noteworthy characterized by based on touch screen technology, and touch screen is applied to when there is pressure
When on panel, panel can provide the coordinate of pressure exactly, and when there is the animals such as pedestrian, luggage or cat and dog by panel,
The marking of given shape can be obtained on panel.
Passenger flow analysing method of the present invention, mainly includes marking acquisition module, footprint recognition module, analysis count module
Block.
Wherein：
The marking acquisition module is used for the print that collection touch panel is produced due to the change of subregion pressure
Note, such as when pedestrian walking on touch panel, cat and dog step on panel, luggage it is dragged the various markings；
The footprint recognition module is used for judging which marking belongs to pedestrian's footprint, and which is not belonging to.Whether judge the marking
Belong to footprint, footprint grader can be used.Further, the footprint grader is obtained by training, is concretely comprised the following steps：
(1) footprint that all kinds of pedestrians leave is collected, is used as positive sample；
(2) other markings are collected, negative sample is used as；
(3) pattern recognition classifier device is given by positive negative sample, is learnt.
The analysis counting module is used for analyzing footprint information, so as to provide pedestrian's number and sex.Due to single people's
Footprint is in space or certain condition is met on the time, then can analyze that how many pedestrian passes through, the time formed by footprint
Or the direction of footprint may determine that the direction that pedestrian passes through, because the shoes of masculinity and femininity have larger in general
Difference, the footprint left on panel is also different, then may determine that pedestrian's sex by men and women's footprint grader.Enter
One step, men and women's footprint grader is obtained by training, is concretely comprised the following steps：
(1) male's footprint is collected, positive sample is used as；
(2) female track is collected, negative sample is used as
(3) pattern recognition classifier device is given by positive negative sample, is learnt.
The present invention has advantages below compared with prior art：
1. carrying out passenger flow statisticses by the footprint on touch-screen, accuracy rate is high.As long as pedestrian passes through on touch panel,
Necessarily leave certain marking, such marking strong interference immunity；
2. directly carrying out Sexual discriminating by footprint, method is simple, and accuracy rate is high；
3. deployment is simple, relatively low to outside environmental requirement, video passenger flow counts the position set up to camera and angle all
There is strict demand, dim environment also can decline statistics accuracy rate, and the present invention only needs to coming in and going out touch screen material-paving
Passway；
4. not being related to privacy concern, and it may be mounted at the place for focusing on privacy.
Claims (3)
1. the passenger flow analysing method based on touch screen technology, including marking acquisition module, footprint recognition module, analysis counting module,
Characterized in that, the marking acquisition module is used for what collection touch panel was produced due to the change of subregion pressure
The marking；The footprint recognition module is used for judging which marking belongs to pedestrian's footprint, and the footprint recognition module can use foot
Mark grader judges whether the marking belongs to pedestrian, and footprint grader is training gained, training step is as follows, and all kinds of pedestrians are sufficient
Positive negative sample, using other markings as negative sample, is finally delivered to pattern recognition classifier device and learnt by mark as positive sample；Institute
State analysis counting module to be used for analyzing footprint information, so as to provide pedestrian's number, by direction and sex.
2. passenger flow analysing method as claimed in claim 1, it is characterised in that the analysis count module block analysis footprint packet
Include following methods：Due to single people footprint is in space or certain condition is met on the time, then how many pedestrian can be analyzed
Pass through；The time formed by footprint or the direction of footprint may determine that the direction that pedestrian passes through；Due to masculinity and femininity
Shoes have larger difference in general, and the footprint left on panel is also different, so as to judge pedestrian
Sex.
3. method as claimed in claim 2, it is characterised in that the analysis counting module can be used when judging men and women's footprint
Men and women's footprint grader, men and women's footprint grader is training gained, using men and women's footprint as positive negative sample, by positive negative sample
Pattern recognition classifier device is delivered to be learnt.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201410143258.7A CN104978782B (en) | 2014-04-11 | 2014-04-11 | Passenger flow analysing method based on touch screen technology |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201410143258.7A CN104978782B (en) | 2014-04-11 | 2014-04-11 | Passenger flow analysing method based on touch screen technology |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN104978782A CN104978782A (en) | 2015-10-14 |
| CN104978782B true CN104978782B (en) | 2017-09-19 |
Family
ID=54275255
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201410143258.7A Active CN104978782B (en) | 2014-04-11 | 2014-04-11 | Passenger flow analysing method based on touch screen technology |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN104978782B (en) |
Families Citing this family (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN106295597A (en) * | 2016-08-17 | 2017-01-04 | 浪潮电子信息产业股份有限公司 | A kind of method and device obtaining passenger flow information |
| CN110837794B (en) * | 2019-11-04 | 2022-05-03 | 北京数衍科技有限公司 | Pedestrian number statistical method and device |
Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| GB1008251A (en) * | 1960-12-12 | 1965-10-27 | Emi Ltd | A device for learning and recognising patterns |
| CN1156791C (en) * | 1996-01-09 | 2004-07-07 | 富士通株式会社 | Pattern recognizing apparatus and method |
| CN2726028Y (en) * | 2004-08-18 | 2005-09-14 | 曹野源 | Public transit passenger flow statistical apparatus |
| CN103198548A (en) * | 2013-04-03 | 2013-07-10 | 深圳职业技术学院 | Regional bus on-off passenger number distinguishing algorithm based on switch sensors |
Family Cites Families (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN1744070A (en) * | 2004-09-03 | 2006-03-08 | 上海浩孚通信科技有限公司 | Public traffic vehicle passenger-flow counting method and system |
| CN101716078B (en) * | 2009-12-17 | 2011-12-14 | 北京航空航天大学 | Gait analysis system aiming at small animals |
| CN101874738B (en) * | 2009-12-23 | 2011-11-09 | 中国科学院自动化研究所 | Method for biophysical analysis and identification of human body based on pressure accumulated footprint image |
| CN102819764B (en) * | 2012-07-18 | 2015-07-08 | 郑州金惠计算机系统工程有限公司 | Method for counting pedestrian flow from multiple views under complex scene of traffic junction |
| CN103235932B (en) * | 2013-04-09 | 2016-06-08 | 重庆理工大学 | Gateway demographic method and device |
-
2014
- 2014-04-11 CN CN201410143258.7A patent/CN104978782B/en active Active
Patent Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| GB1008251A (en) * | 1960-12-12 | 1965-10-27 | Emi Ltd | A device for learning and recognising patterns |
| CN1156791C (en) * | 1996-01-09 | 2004-07-07 | 富士通株式会社 | Pattern recognizing apparatus and method |
| CN2726028Y (en) * | 2004-08-18 | 2005-09-14 | 曹野源 | Public transit passenger flow statistical apparatus |
| CN103198548A (en) * | 2013-04-03 | 2013-07-10 | 深圳职业技术学院 | Regional bus on-off passenger number distinguishing algorithm based on switch sensors |
Also Published As
| Publication number | Publication date |
|---|---|
| CN104978782A (en) | 2015-10-14 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN108765404B (en) | A kind of road damage testing method and device based on deep learning image classification | |
| US9418546B1 (en) | Traffic detection with multiple outputs depending on type of object detected | |
| CN106935035B (en) | Parking offense vehicle real-time detection method based on SSD neural network | |
| CN104751634B (en) | The integrated application method of freeway tunnel driving image acquisition information | |
| CN105184271A (en) | Automatic vehicle detection method based on deep learning | |
| CN105512640A (en) | Method for acquiring people flow on the basis of video sequence | |
| CN105760847B (en) | A kind of visible detection method of pair of helmet of motorcycle driver wear condition | |
| CN108229407A (en) | A kind of behavioral value method and system in video analysis | |
| CN104298969A (en) | Crowd scale statistical method based on color and HAAR feature fusion | |
| CN103324955A (en) | Pedestrian detection method based on video processing | |
| CN104021375A (en) | Model identification method based on machine learning | |
| CN104809470B (en) | A kind of vehicle based on SVM drives in the wrong direction detection device and detection method | |
| US11893727B2 (en) | Rail feature identification system | |
| CN102360434B (en) | Target classification method of vehicle and pedestrian in intelligent traffic monitoring | |
| CN103679214B (en) | Vehicle checking method based on online Class area estimation and multiple features Decision fusion | |
| CN103345842A (en) | Road vehicle classification system and method | |
| CN103020577B (en) | Moving target identification method based on hog characteristic and system | |
| CN108804987A (en) | Door open and-shut mode detection method and device and stream of people's detecting system | |
| CN104239908A (en) | Intelligent ridership automatic statistical method based on self-adaptive threshold value | |
| CN104268548A (en) | Accumulated snow detection method based on road images | |
| CN104978782B (en) | Passenger flow analysing method based on touch screen technology | |
| Ambata et al. | Public and private vehicle quantification and classification using vehicle detection and recognition | |
| Jensen et al. | A framework for automated traffic safety analysis from video using modern computer vision | |
| Khan et al. | Multiple moving vehicle speed estimation using Blob analysis | |
| Li et al. | A video-based algorithm for moving objects detection at signalized intersection |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| C06 | Publication | ||
| PB01 | Publication | ||
| C10 | Entry into substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| DD01 | Delivery of document by public notice |
Addressee: NANJING SHICHAZHE INFORMATION TECHNOLOGY CO., LTD. Document name: Notification of Publication and of Entering the Substantive Examination Stage of the Application for Invention |
|
| CB02 | Change of applicant information | ||
| CB02 | Change of applicant information |
Address after: Everwise road in Qinhuai District of Nanjing City, Jiangsu province 210014 No. 6 Baixia high-tech park, building 4, building 209 B Applicant after: Nanjing inspectors Image Recognition Technology Co., Ltd. Address before: North building, Guanghua Road, Baixia District Nanjing city Jiangsu province 210014 network No. 1 Baixia high-tech park Stenden Building 5 layer Applicant before: NANJING SHICHAZHE INFORMATION TECHNOLOGY CO., LTD. |
|
| GR01 | Patent grant | ||
| GR01 | Patent grant | ||
| TR01 | Transfer of patent right | ||
| TR01 | Transfer of patent right |
Effective date of registration: 20180525 Address after: 210014 F23, room B, four building, Nanjing Bai Xia hi tech Industrial Park, 6 Qinhuai District, Nanjing, Jiangsu. Patentee after: Nanjing Walker Intelligent Traffic Technology Co., Ltd. Address before: 210014 B 209, 4 building, Bai Xia hi tech park, No. 6, Yong Zhi Road, Qinhuai District, Nanjing, Jiangsu. Patentee before: Nanjing inspectors Image Recognition Technology Co., Ltd. |