CN102622487A - Sensor arrangement computer aided design and simulation system for automatic ticket checker (ticket gate) - Google Patents
Sensor arrangement computer aided design and simulation system for automatic ticket checker (ticket gate) Download PDFInfo
- Publication number
- CN102622487A CN102622487A CN2012100755958A CN201210075595A CN102622487A CN 102622487 A CN102622487 A CN 102622487A CN 2012100755958 A CN2012100755958 A CN 2012100755958A CN 201210075595 A CN201210075595 A CN 201210075595A CN 102622487 A CN102622487 A CN 102622487A
- Authority
- CN
- China
- Prior art keywords
- file
- video
- gate
- training
- automatic ticket
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Granted
Links
- 238000011960 computer-aided design Methods 0.000 title claims abstract description 10
- 238000005094 computer simulation Methods 0.000 title abstract description 4
- 238000012549 training Methods 0.000 claims abstract description 32
- 238000012360 testing method Methods 0.000 claims abstract description 25
- 238000013461 design Methods 0.000 claims abstract description 22
- 238000003062 neural network model Methods 0.000 claims abstract description 10
- 238000004088 simulation Methods 0.000 claims abstract description 7
- 238000013528 artificial neural network Methods 0.000 claims description 10
- 230000001537 neural effect Effects 0.000 claims description 4
- 238000000605 extraction Methods 0.000 claims description 3
- 230000008676 import Effects 0.000 claims description 3
- 238000005516 engineering process Methods 0.000 abstract description 3
- 239000000463 material Substances 0.000 abstract description 2
- 238000000034 method Methods 0.000 description 13
- 238000006243 chemical reaction Methods 0.000 description 3
- 238000010586 diagram Methods 0.000 description 3
- 230000008569 process Effects 0.000 description 3
- 238000009434 installation Methods 0.000 description 2
- 238000009825 accumulation Methods 0.000 description 1
- 230000009471 action Effects 0.000 description 1
- 230000008901 benefit Effects 0.000 description 1
- 238000011161 development Methods 0.000 description 1
- 239000012467 final product Substances 0.000 description 1
- 230000006872 improvement Effects 0.000 description 1
- 230000005764 inhibitory process Effects 0.000 description 1
- 239000000047 product Substances 0.000 description 1
Images
Landscapes
- Devices For Checking Fares Or Tickets At Control Points (AREA)
- Management, Administration, Business Operations System, And Electronic Commerce (AREA)
Abstract
The invention discloses a sensor arrangement computer aided design and simulation system for an automatic ticket checker (ticket gate). The system comprises the following steps of: shooting a great number of video files of a ticket holder during passing the automatic ticket checker (ticket gate) under different special conditions, and building an example library by using the video files; converting the original video example library by using video conversion software, making a sample set by combining a video file set with a specified sensor arrangement coordinate file through simulation software; simulating the sample set by utilizing the simulation function of the simulation software, and generating a training set; training the training set so as to establish a neural network model; establishing a test set; testing the test set by using the simulation software, and thus obtaining a passing rate result file of the sensor arrangement design. By the adoption of a computer simulation technology, labor cost, financial resources and material resources in the sensor arrangement design are effectively reduced.
Description
Technical field
The present invention relates to a kind of automatic ticket checker (gate) sensor placement Computer Aided Design & Imitation system, belong to automatic ticket checker and gate inhibition's design field.
Background technology
The behavior that (card) people that in the actual life, takes ticket produces during through automatic ticket checker (gate) is very complicated, runs into (card) people leap that takes ticket through regular meeting, behavior such as bores, trails down.In order effectively to screen whether legal the passing through of (card) people that take ticket, it is current perhaps whether to carry children, luggage, pet, the necessary sensor installation system of automatic ticket checker (gate), and adopt special sensor algorithm, the behavior that (card) people that takes ticket passes through is judged.Simultaneously, traditional automatic ticket checker (gate) sensor placement has very big limitation, relies on the designer fully through experience accumulation; Ad-hoc location sensor installation at automatic ticket checker (gate); This method wastes time and energy, in case accomplish the sensor placement design, just must recruit employ that a large amount of personnel do not stop pass through automatic ticket checker (gate) model machine with stream of people's environment that is virtually reality like reality; And final product is because of being detected by the real stream of people, and has unforeseen problem; And at present especially in field of track traffic; The mode that domestic and international market adopts is according to passenger flow and requirements of different users; Every newly-built rail line generally all adopts dissimilar automatic ticket checkers; This has just proposed challenge to the traditional design mode of automatic ticket checker sensor, and the conventional artificial mode can't satisfy the new product needs of dramatic growth again.
Summary of the invention
The objective of the invention is to; Provide a kind of employing Computer Simulation to produce 1,000,000 grades of stream of people's samples; And according to newly-designed sensor placement; Automatically generate (card) people behavior examination algorithm that takes ticket through the artificial neural network, make traditional handicraft need the model machine development cost of several months, hundreds of people, units up to a million, once shorten to several days, several expert engineer, several automatic ticket checker (gate) the sensor placement Computer Aided Design & Imitation systems that notebook computer can be finished the work.
For solving the problems of the technologies described above, the present invention adopts following technical scheme: a kind of automatic ticket checker (gate) sensor placement Computer Aided Design & Imitation system may further comprise the steps:
S1 takes (card) people that takes ticket under a large amount of different specified conditions and makes example storehouse L through the video file of automatic ticket checker (gate);
S2 is converted into video clip M through using video conversion software with original video example storehouse L;
S3 makes sample set N through using simulation software to combine a cover sensor placement coordinate file XY of appointment to add software inhouse in the lump to video clip M;
S4, the function of utilizing simulation software emulation generates the data streaming file training set P of special format to sample set N emulation;
S5, through the function of the neural metwork training in the use simulation software, thereby neural network model is set up in training to data stream file training set P.
S6 sets up data streaming file test set Q through the step of above S1～S4;
S7; Through using the function of the neural network test in the simulation software; In the neural network model of after step S5 accomplishes, setting up data stream file test set Q is tested, obtain (card) people percent of pass destination file F that takes ticket of each attribute of this cover sensor placement design.
The step of video conversion software is:
S21, original video example storehouse L sets through the setting and the file size of specific threshold, changes into black and white binaryzation video clip M from the color video file;
S22, the coordinate spanned file of automatic ticket checker (gate) among the extraction original video example storehouse L.
The step of simulation software is:
S31, input pickup layout coordinate file XY judges whether to edit the training set sample; Be, then get into step S32-S34, set up training set P; , then do not get into step S32-S34 and set up test set Q.
S32, training video file set storage directory after the selection binaryzation;
S33, the Parameter File T and the importing of editing this video clip;
S34 imports the gate coordinate in this video and forms sample set N; Get into step S41;
S41 is to training set P or test set Q emulation; Get into step S51;
S51, neural network is trained training set P simulation result;
S52 produces neural network model; Get into step S71;
S71, the neural network under this model is tested the test set simulation result;
S72 produces percent of pass destination file F.
The present invention with computing machine can be perfect gradually the example storehouse in sample emulation; The method of neural metwork training test; Can draw (card) people percent of pass form document that takes ticket under horizontal a few cover automatic ticket checkers (gate) sensor placement design proposal, then, these several forms of longitudinal comparison again; After taking all factors into consideration, can select a cover sensor placement scheme is the design proposal of new type auto ticket checking machine (gate).
Pass through foregoing description; It is thus clear that, use the method to design new type auto ticket checking machine (gate), not only do not employ manpower up to a hundred comes the testing sensor layout through gate rationality; Do not spend units up to a million yet and make model machine; Just in this cover Computer Aided Design & Imitation system, revise the sensor placement parameter, just can obtain corresponding (card) people percent of pass form document that takes ticket, thereby can determine whether can be used as the sensor placement design proposal of novel gate.
Than the traditional sensors layout design method; Advantage of the present invention is obvious; Improve work efficiency greatly, saved the input of manpower and materials significantly, the more important thing is the method and the foundation that automatic ticket checker (gate) sensor placement designed rationality have been proposed perspective study.
Description of drawings:
Fig. 1 is a system architecture diagram of the present invention;
Fig. 2 is system works flow process figure of the present invention;
Fig. 3 is video conversion software workflow figure of the present invention;
Fig. 4 is a simulation software of the present invention workflow diagram.
Below in conjunction with accompanying drawing and embodiment the present invention is further described.
Embodiment
Embodiments of the invention:
Shown in Fig. 1-4, instance is: for subway designs a new type auto ticket checking machine, one of requiring is to have anti-pinch passenger adjunct (such as draw-bar box etc.) function.This is used of the present invention to execute step following:
The first step: generate a passenger's percent of pass destination file F1 under the cover automatic ticket checker Sensor Design scheme of using.Be divided into following several little steps:
As shown in Figure 2:
S1, a large amount of passengers of shooting make original video example storehouse L through the video file of gate.
This step can be chosen in certain subway station and take, and also can be chosen in intra-company and build scene, utilizes own automatic ticket checker, asks the employee to work together and replaces the passenger to take through gate.These large quantities of video files will be made into library file as source document, can directly call afterwards, and need not to take again, but the file that can constantly add new element enrich the storehouse body.
S2, open video conversion software, original video example storehouse L is converted into the video clip M of special format.
Catalogue and some parameters that file after catalogue that the source document that this step only need set needs conversion is deposited and the conversion is preserved are clicked " conversion " key then, and software automatically performs task.
S3, open simulation software, combine a cover sensor placement coordinate file XY on the organic type to add software inhouse in the lump to video clip M and make sample set N.
This step method is similar to S2, selects on the software interface to configure parameter, clicks a key, and software automatically performs task.
S4, utilize simulation software emulation function to sample set N emulation, generate the data streaming file training collection P of special format.
This step method is similar to S2, S3, selects on the software interface to configure parameter, clicks a key, and software automatically performs task.
S5, through using the function of the neural metwork training in the simulation software, thereby neural network model is set up in training to data stream file training collection P.
This step method is similar to S2, S3, S4, selects on the software interface to configure parameter, clicks a key, and software automatically performs task.
S6, set up data streaming file test set Q with the method for above S1～S4.
S7, the function of passing through to use the neural network in the simulation software to test, thus Q test obtains passenger's percent of pass destination file F1 that this overlaps each attribute of sensor placement design to data stream file test set in the neural network model of after S5 does, setting up.
As shown in Figure 3:
The step of video conversion software is:
S21, original video example storehouse L sets through the setting and the file size of specific threshold, changes into black and white binaryzation video clip M from the color video file;
S22, the coordinate spanned file of automatic ticket checker (gate) among the extraction original video example storehouse L.
As shown in Figure 4:
The step of simulation software is:
S31, input pickup layout coordinate file XY judges whether to edit the training set sample; Be, then get into step S32-S34, set up training set P; , then do not get into step S32-S34 and set up test set Q.
S32, training video file set M storage directory after the selection binaryzation;
S33, the Parameter File T and the importing of editing this video clip;
S34 imports the gate coordinate in this video and forms sample set N; Get into step S41;
S41 is to training set P or test set Q emulation; Get into step S51;
S51, neural network is trained training set P simulation result;
S52 produces neural network model; Get into step S71;
S71, the neural network under this model is tested the test set simulation result;
S72 produces percent of pass destination file F1.
The second largest step: generate a passenger's percent of pass destination file F2 under the upon request newly-designed cover automatic ticket checker Sensor Design scheme.The several little step of carrying out is with S2～S7 in the first step, and S1 can not do, and repeats no more here.
The third-largest step: compare the index in F1 and the F2 destination file; " adjunct " one particularly, if the data among the F2 have descended than F1, that explanation new departure is not as existing program; Otherwise; Then explanation, new departure function in this respect has improvement, can consider the final plan of this scheme as the sensor placement design of new type auto ticket checking machine.
In a word, the present invention can be applied in the precision that the current result of passenger that various automatic ticket checkers (gate) produce depends on the sensor placement design fully.The present invention offers high effectively, high sensor placement method for designing of automatic ticket checker accurately of slip-stick artist.As shown in Figure 1, wherein submodule 1 is the original video files of taken of passengers through automatic ticket checker, is disposable action, does not need all to do this link at every turn, but can the not timing non-quantitative the video collection be done replenishes and perfect; Submodule 2 is a video conversion software of the present invention, and its internal work flow process figure sees Fig. 3.
The main source code of part is following:
Submodule 3 is a whole set of Sensor Design scheme; Submodule 4 is a simulation software of the present invention, and its internal work flow process figure sees Fig. 4.Wherein M1, M2 can be identical, certainly T1, T2 are also just identical, but test set should be the subclass of training set usually.The main source code of part is following:
Submodule 5 is final purpose property conclusion content of the present invention, through respectively overlapping different this document that the sensor placement design proposal obtains, and obtains the sensor placement design proposal of more excellent sensor placement design proposal as new type auto ticket checking machine.Whole workflow diagram of the present invention is seen Fig. 2.
Claims (3)
1. an automatic ticket checker (gate) sensor placement Computer Aided Design & Imitation system is characterized in that: may further comprise the steps:
S1 takes (card) people that takes ticket under a large amount of different specified conditions and makes example storehouse L through the video file of automatic ticket checker (gate);
S2 is converted into video clip M through using video conversion software with original video example storehouse L;
S3 makes sample set N through using simulation software to combine a cover sensor placement coordinate file XY of appointment to add software inhouse in the lump to video clip M;
S4, the function of utilizing simulation software emulation generates the data streaming file training set P of special format to sample set N emulation;
S5, through the function of the neural metwork training in the use simulation software, thereby neural network model is set up in training to data stream file training set P.
S6 sets up data streaming file test set Q through the step of above S1～S4;
S7; Through using the function of the neural network test in the simulation software; In the neural network model of after step S5 accomplishes, setting up data stream file test set Q is tested, obtain (card) people percent of pass destination file F that takes ticket of each attribute of this cover sensor placement design.
2. automatic ticket checker according to claim 1 (gate) sensor placement Computer Aided Design & Imitation system, it is characterized in that: the step of described video conversion software is:
S21, original video example storehouse L sets through the setting and the file size of specific threshold, changes into black and white binaryzation video clip M from the color video file;
S22, the coordinate spanned file of automatic ticket checker (gate) among the extraction original video example storehouse L.
3. automatic ticket checker according to claim 2 (gate) sensor placement Computer Aided Design & Imitation system, it is characterized in that: the step of described simulation software is:
S31, input pickup layout coordinate file XY judges whether to edit the training set sample; Be, then get into step S32-S34, set up training set P; , then do not get into step S32-S34 and set up test set Q.
S32, training video file set storage directory after the selection binaryzation;
S33, the Parameter File T and the importing of editing this video clip;
S34 imports the gate coordinate in this video and forms sample set N; Get into step S41;
S41 is to training set P or test set Q emulation; Get into step S51;
S51, neural network is trained training set P simulation result;
S52 produces neural network model; Get into step S71;
S71, the neural network under this model is tested the test set simulation result;
S72 produces percent of pass.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201210075595.8A CN102622487B (en) | 2012-03-21 | 2012-03-21 | A kind of automatic ticket checker (gate) sensor placement Computer Aided Design & Imitation system |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201210075595.8A CN102622487B (en) | 2012-03-21 | 2012-03-21 | A kind of automatic ticket checker (gate) sensor placement Computer Aided Design & Imitation system |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN102622487A true CN102622487A (en) | 2012-08-01 |
| CN102622487B CN102622487B (en) | 2016-04-06 |
Family
ID=46562403
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201210075595.8A Active CN102622487B (en) | 2012-03-21 | 2012-03-21 | A kind of automatic ticket checker (gate) sensor placement Computer Aided Design & Imitation system |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN102622487B (en) |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN103487694A (en) * | 2013-09-25 | 2014-01-01 | 无锡俊达测试技术服务有限公司 | Passing test device for automatic ticket checker |
Citations (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN101482981A (en) * | 2008-04-09 | 2009-07-15 | 天津市先志越洋科技有限公司 | License event recognition method for special shearing type door gate machine used in urban track traffic |
| CN101826200A (en) * | 2010-04-02 | 2010-09-08 | 北京交通大学 | Method for evaluating operating effect of urban track traffic hub |
-
2012
- 2012-03-21 CN CN201210075595.8A patent/CN102622487B/en active Active
Patent Citations (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN101482981A (en) * | 2008-04-09 | 2009-07-15 | 天津市先志越洋科技有限公司 | License event recognition method for special shearing type door gate machine used in urban track traffic |
| CN101826200A (en) * | 2010-04-02 | 2010-09-08 | 北京交通大学 | Method for evaluating operating effect of urban track traffic hub |
Non-Patent Citations (3)
| Title |
|---|
| 《中国优秀博硕士学位论文全文数据库(博士) 信息科技辑》 20060715 曲日 城市轨道交通中闸机智能识别系统及其识别技术的研究 1-3 , 第7期 * |
| 曲日: "城市轨道交通中闸机智能识别系统及其识别技术的研究", 《中国优秀博硕士学位论文全文数据库(博士) 信息科技辑》 * |
| 李胤: "门式检票机设计及通行法则研究", 《中国优秀硕士学位论文全文数据库 工程科技Ⅱ辑》 * |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN103487694A (en) * | 2013-09-25 | 2014-01-01 | 无锡俊达测试技术服务有限公司 | Passing test device for automatic ticket checker |
Also Published As
| Publication number | Publication date |
|---|---|
| CN102622487B (en) | 2016-04-06 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN105608254A (en) | Automated design method and platform oriented to intelligent hardware system development | |
| CN106599230A (en) | Method and system for evaluating distributed data mining model | |
| Lin et al. | Semantic classification and hash code accelerated detection of design changes in BIM models | |
| CN106778876A (en) | User classification method and system based on mobile subscriber track similitude | |
| CN101430714B (en) | Content structuring process method and system based on model | |
| CN104978411B (en) | A kind of automobile development method and apparatus of bullet train | |
| CN109858414A (en) | A kind of invoice piecemeal detection method | |
| CN111144281B (en) | Urban rail transit OD passenger flow estimation method based on machine learning | |
| CN105975466A (en) | Method and device for machine manuscript writing aiming at short newsflashes | |
| CN111368391B (en) | Model conversion method oriented to carrier rocket system simulation | |
| CN106155769A (en) | A kind of workflow processing method, device and workflow engine | |
| Al-Shalabi et al. | BrIM implementation for documentation of bridge condition for inspection | |
| CN103455896A (en) | Paperless assembling quality control method based on internet of things | |
| CN111353377A (en) | Elevator passenger number detection method based on deep learning | |
| Papadonikolaki et al. | How can Digital Twins support the Net Zero vision? | |
| CN104765763B (en) | A kind of semantic matching method of the Heterogeneous Spatial Information classification of service based on concept lattice | |
| Chen et al. | Research on the intelligent generation of the spatial form of the island city historic district Based on parameterization: Taking Macau Taipa Village as an example | |
| CN109801040A (en) | Multidimensional mould based on BIM examines design collaboration platform | |
| CN105912723A (en) | Storage method of custom field | |
| CN104361086A (en) | Data integration method for measurable asset entire life-cycle management system | |
| CN102622487B (en) | A kind of automatic ticket checker (gate) sensor placement Computer Aided Design & Imitation system | |
| CN105373473B (en) | CDR accuracys method of testing and test system based on original signaling decoding | |
| CN109767031A (en) | Model classifiers method for building up, device, computer equipment and storage medium | |
| CN113255499B (en) | Digital automatic modeling method for secondary loop of transformer substation cable | |
| CN101655850B (en) | Generating equipment for knowledge extraction process, regulating equipment for knowledge extraction process and methods 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 | ||
| C14 | Grant of patent or utility model | ||
| GR01 | Patent grant | ||
| DD01 | Delivery of document by public notice |
Addressee: BEIJING JIANYI CENTURY TECHNOLOGY Co.,Ltd. Person in charge of patents Document name: payment instructions |
|
| DD01 | Delivery of document by public notice |