CN103605967A - Subway fare evasion prevention system and working method thereof based on image recognition - Google Patents
Subway fare evasion prevention system and working method thereof based on image recognition Download PDFInfo
- Publication number
- CN103605967A CN103605967A CN201310611194.4A CN201310611194A CN103605967A CN 103605967 A CN103605967 A CN 103605967A CN 201310611194 A CN201310611194 A CN 201310611194A CN 103605967 A CN103605967 A CN 103605967A
- Authority
- CN
- China
- Prior art keywords
- people
- card
- image
- counter
- detection zone
- 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
Images
Landscapes
- Image Processing (AREA)
Abstract
The invention discloses a subway fare evasion prevention system and a working method thereof based on image recognition. The subway fare evasion prevention system is characterized by comprising a card swiping information adapter and an imaging device; the card swiping information adapter and the imaging device are both connected with an embedded central processing module, and the embedded central processing module is further connected with an alarm device and a door opening and closing control device; the card swiping information adapter is connected with a signal port of a pull-in card swiping system. On the basis of an existing gateway automatic fare collection system, a machine visual system and the card swiping information adapter are additionally arranged, and an embedded signal processing system is used for obtaining the information of the number of people in a current detection area and replacement information of the number of people in real time, so whether the fare evasion happens can be judged by comparing a count value of a counter for the number of people swiping cards and a count value of a counter for the number of people in the detection area to control opening of a gateway and give out an alarm.
Description
Technical field
The present invention relates to a kind of subway based on image recognition anti-steal a ride system and method for work thereof, belong to subway intelligence ticket-checking system technical field.
Background technology
Along with the develop rapidly of Chinese national economy and improving constantly of living standards of the people, people's trip is also more frequent, and urban track traffic, as a kind of important and trip mode easily, is accepted and selects by increasing people.The active demand that urban track traffic is equally also faced with to be increased capacity, improve service quality, improve the competitiveness.In order to adapt to its demand for development, how to utilize advanced intellectualized technology create a safety, easily and efficiently docking system become current in the urgent need to.AFC system, as the important tool constantly exchanging with trip crowd in Rail Transit System, is also faced with huge challenge, and AFC system is in terminal device, associated the most complicated equipment between internal part.The use of automatic ticket checker, has realized passenger's brush ticket that enters the station self-oriented and intelligent, greatly reduces the manpower consumption who is brought by artificial ticket checking, has improved the efficiency that enters the station, the unnecessary mistake that simultaneously also can avoid manual operation to cause.But meanwhile,, owing to adopting full automatic unattended self-service ticket-checking system, also easily there is the steal a ride generation of phenomenon and various leaks and the drawback in ticket checking process.
Summary of the invention
The technical problem to be solved in the present invention is: a kind of Vision Builder for Automated Inspection and image processing techniques utilized is provided, realize subway anti-system and the method for work thereof of stealing a ride of the subway based on image recognition of automatic alarm of stealing a ride that enter the station, solved generation and the various leaks in ticket checking process and the problem of drawback of the phenomenon of stealing a ride.
In order to solve the problems of the technologies described above, technical scheme of the present invention has been to provide the anti-system of stealing a ride of a kind of subway based on image recognition, it is characterized in that, comprise card using information adapter, imaging device, card using information adapter, imaging device are connected with embedded central processing module respectively, embedded central processing module is also connected with warning device, switch gate control device, card using information adapter taps into the signal port of station card-punching system, and in embedded central processing module, is provided with respectively swipe the card counter for number of people and detection zone counter for number of people.
A method of work for the anti-system of stealing a ride of subway based on image recognition, is characterized in that, comprises following job step:
Step 1: gather the trigger pip of card using information adapter, if enter the station the signal of swiping the card, the counter for number of people of swiping the card adds 1, otherwise the count value of the counter for number of people of swiping the card is constant;
Step 2: by camera collection detection zone present image, and itself and background template image are differed from after shadow computing, the poor image of gained is carried out to row projection, according to the feature of drop shadow curve, realize target is cut apart, and extracts the current number in detection zone, charges to detection zone counter for number of people;
Step 3: by the human body target tracking to directly front frame and current frame image, obtain the replacement information of detection zone number, and revise the count value of the counter for number of people of swiping the card;
Step 4: the value of relatively swipe the card counter for number of people and detection zone counter for number of people, if the former equals the latter, open sluice gate, proceeds to step 1; Otherwise, close sluice gate, and send alerting signal, wait pending.
Preferably, the replacement information of described step 3 detection zone number, be by present image and its directly before the human body target region barycenter of frame do relevant matches, by following the tracks of the human body target of adjacent image frame, realize newly entering human body number and exiting the statistics of human body number present image detection zone.
In order to realize better robotization and the intellectuality of ticket checking process, the generation of phenomenon prevents from stealing a ride, the present invention is on automatic ticket checking system basis, existing lock road, install Vision Builder for Automated Inspection and card using information adapter additional, number replacement information by embedded signal processing system Real-time Obtaining current detection district's number and detection zone, and by the count value of relatively swipe the card counter for number of people and detection zone counter for number of people, enter the station on the basis of speed and existing operator management mode not affecting passenger, judge the phenomenon of stealing a ride, and control unlatching and the warning of sluice gate, the realization automatic alarm of stealing a ride.Compared with prior art, the present invention has advantages of following: the present invention can not change on the basis of existing equipment, makes up the deficiency of existing equipment.Utilize machine vision and image processing techniques to carry out the intelligent identification phenomenon of stealing a ride, and provide alerting signal, improve accuracy and the intelligent degree of the automatic fare collection that enters the station.
Accompanying drawing explanation
Fig. 1 is the systematic functional structrue schematic diagram that the present invention adopts;
Fig. 2 is camera scheme of installation of the present invention;
Fig. 3 is the detection zone schematic diagram of image of the present invention.
Wherein: 1 is camera, 2 positions, Wei Zha road, 3 is the passage that enters the station, and 4 is detection zone, and 5 is toll zone, and 6 is free district, and 7 is the position of swiping the card, and 8 is ENTRANCE, and 9 is ticket checking entrance.
Embodiment
For the present invention is become apparent, hereby with preferred embodiment, and coordinate accompanying drawing to be described in detail below.
Below in conjunction with specific embodiment, further set forth the present invention.Should be understood that these embodiment are only not used in and limit the scope of the invention for the present invention is described.In addition should be understood that, after having read content of the present invention, those skilled in the art can make various changes or modifications the present invention, these equivalent form of values fall within the application's appended claims limited range equally.
The present invention relates to a kind of subway based on image recognition anti-steal a ride system and method for work thereof, image acquisition, processing, demonstration and control function are integrated in one, by machine vision, detection zone is monitored, realize the anti-function of stealing a ride of subway.Embedded central processing module be take Cortex-A8 as central processing unit part, design of graphics picture is processed and is detected control platform, comprise signal adapter, liquid crystal display etc., meanwhile, construction device also comprises that LED white light source, digital CMOS imageing sensor, alarm and system detect software etc.Its systematic functional structrue as shown in Figure 1.
The anti-system of stealing a ride of a kind of subway based on image recognition, it comprises card using information adapter, imaging device, card using information adapter, imaging device are connected with embedded central processing module respectively, and embedded central processing module is also connected with warning device, switch gate control device.Card using information adapter taps into the signal port of station card-punching system, and in embedded central processing module, is provided with respectively swipe the card counter for number of people and detection zone counter for number of people.
The present invention, on automatic ticket checking system basis, existing lock road, is installed Vision Builder for Automated Inspection and card using information adapter additional, and its camera scheme of installation as shown in Figure 2.Intelligent processing method by embedded central processing module to detection zone video image, the number replacement information of automatic acquisition present image detection zone number and detection zone, by the count value of relatively swipe the card counter for number of people and detection zone counter for number of people, judge the phenomenon of stealing a ride, and control unlatching and the warning of sluice gate.
A method of work for the anti-system of stealing a ride of subway based on image recognition, comprises following job step:
Step 1: gather the trigger pip of signal adapter of swiping the card, if enter the station the signal of swiping the card, the counter for number of people of swiping the card adds 1, otherwise the counter for number of people count value of swiping the card is constant.
Step 2: by camera 1 acquisition testing district 4 present images, and itself and background template image are differed from after shadow computing, the poor image of gained is carried out to row projection, according to the feature of drop shadow curve, realize target is cut apart, and extracts the number in detection zone 4, charges to detection zone counter for number of people.
Step 3: by directly front frame and current frame image human body target tracking, obtain the replacement information of detection zone 4 numbers, and revise the counter for number of people of swiping the card.The replacement information of detection zone 4 numbers, by the human body target region barycenter of present image and its directly front frame is done to relevant matches, follow the tracks of the human body target of adjacent image frame, realize newly entering human body number and exiting the statistics of human body number present image detection zone 4.
Step 4: the value of relatively swipe the card counter for number of people and detection zone counter for number of people, if the former equals the latter, open sluice gate, proceeds to step 1; Otherwise, close sluice gate, and send alerting signal, wait pending.
In testing process, the number in the detection zone 4 obtaining is exactly key point of the present invention.The present invention adopts image projection Region Segmentation Algorithm and image sequence human body target tracking method is obtained to the current number in detection zone 4 and human body target information converting.Human body target recognition and tracking, is for the accurate recognition detection district 4 current numbers that exit, thereby upgrades the human body number in ticket checking counter.To being the prerequisite that human body classification, tracking and behavior are understood effectively cutting apart of the district of the detection zone human body target of image.Consider the unchangeability of requirement of real-time of the present invention and image background, in image processing process, first need the present image obtaining and background image to subtract each other, remove background interference, highlight characteristics of human body's information of surveyed area image, particularly suppress dynamic environment noise etc. and have a significant effect.By present image and background image are differed to shadow, then column direction projection is carried out in detection zone 4, can effectively realize human region and cut apart.
If current, obtaining image subtracts after shadow computing, the image obtaining is F (x, y), the image of its effective detection zone 4 is g (i, j), region, walkway after its in fact corresponding ticket checking is swiped the card, if its size is W * N, as shown in Figure 3, its correspondence position 7 of swiping the card, the right, the position of entering the station, corresponding lock road, the left side, border, corresponding walkway, upper and lower limit.Clearly, by removing after background, this region unmanned by time, institute's respective pixel value is 0, when having people to pass through, will cause that corresponding area grayscale value changes.If g (i, j) image is carried out, after the computing of vertical direction Gray Projection, just can realizing detection zone human body target vertical direction being cut apart.With V (i), represent the vertical direction projection (i.e. row projection) of g (i, j) gray-scale map, that is:
Wherein, g (i, j) represents that difference result image is at the pixel value of (i, j) position, and W is the height of detection zone image, and N is detection zone picture traverse.For the error that reduces to produce because of noise, first V (i) array is carried out to medium filtering, remove impulsive noise and salt-pepper noise.Near can obviously finding out each peak value from V (i), it is the potential region of movement human.In order realizing, potential human body region to be cut apart, can be found adaptively a rational threshold value according to the distribution situation of drop shadow curve, be partitioned into individual regions.In the present invention, by following method, human body target is cut apart.First calculate V (i) maximal value V
max, wherein i ∈ [1, N], meets V (i)>=α V at a certain continuum
max, (0≤α≤1), and this continuum width is while meeting certain condition, can think that this interval has potential human body and exists.If use i=a
kthe starting position that represents k potential human body domain of the existence; I=b
kthe end position that represents k region, at interval [a
k, b
k] all there is V (i)>=α V
max.Suppose that the minimum widith that single human body occupies in image is pW (can measure by experiment), due to when 2 people or more people enter detection zone 4 simultaneously, if they are close to, for monocular cam, be to be difficult to distinguish enter this interval and have on earth how many individuals.But from experience, 2 people's the shared interval certainly interval more shared than 1 people is large, even an interval that people is shared, due to the relation of the bodily form, clothes, also may have the poor of size.In order to process this situation, the present invention has adopted following experimental formula to judge:
If meet: pW≤(b
k-a
k) <1.4pW can think single interval.
If meet: 1.4pW≤(b
k-a
k) <2.6pW can think double continuum.
If meet: 2.6pW≤(b
k-a
k) <3.6pW can think three people's continuums.
If meet: 3.6pW≤(b
k-a
k) <4.8pW can think four people's continuums.
If meet: 4.8pW≤(b
k-a
k) <5.8pW can think five people's continuums.
To from above-mentioned many people Region Segmentation, go out single shared region exactly, can divide by further improving the threshold value of V (i), until by the interval number of dividing, meet the requirement of human body number.
The process entering the station due to people is a dynamic continuous process, and on any frame of sequence of video images, all likely the disappear situation of (enter the station and walk out detection zone) of (ticket checking enters detection zone) or old target appears in fresh target.In order to judge exactly the phenomenon of stealing a ride, need to compare current image frame and direct detected personal feature and the number of prior image frame frame thereof, before identifying directly, frame does not exist, but current frame image exists newly enter individuality, directly before frame exist, but current frame image is non-existent exit individuality and directly before the reservation that all exists of frame and current frame image individual, thereby correctly revise the numerical value of the current counter for number of people of swiping the card, for the correct decision phenomenon of stealing a ride is given security.In order to reach this object, the individuality that need to enter detection zone to ticket checking is followed the tracks of.The present invention adopts correlation matching algorithm, by human body target region barycenter is mated, realizes individual goal is accurately followed the tracks of.
In the present invention, the trace point using the barycenter of the single rectangular area being partitioned into as movement human.Because the time interval between video image consecutive frame is shorter, clarification of objective parameter can not be undergone mutation, the frame of same human body target gained at the target centroid position of adjacent two two field pictures with in detecting changes little, target have velocity tapering process and approximate at the uniform velocity, i.e. motion has continuity.In detection zone, because passage is narrower, and shorter, human body target is form motion and the dynamic change with queue, without jumping the queue phenomenon.The present invention adopts relevant matches tracking as follows: establish sometime in interval, the image sequence of the detection zone that obtains is G=(G
1, G
2..., G
n..), and n two field picture G
nm individual goal detected and be respectively s
1, n, s
2, n..., s
m, n, target s
i, nthe coordinate of the barycenter of (1≤i≤m) is ((pos_x
i, pos_y
i).If k target detected at n-1 frame, be designated as s
1, n-1, s
2, n-2..., s
k, n-1, adopt correlation matching algorithm, be to mate and set with each individual target area barycenter.
First by G
n-1target s
1, n-1with G
nframe detects target s
1, n, s
2, n..., s
m, ndo in order matching operation, once can with certain target s wherein
i, ncan match, according to the character of queue, can judge the target item s before it
1, n, s
2, n..., s
i-1, n, be the target of the human body that newly enters surveyed area.
Then same method, by G
ntarget s
m, nwith G
n-1frame detects target s
k, n-1, s
k-1, n-1..., s
1, n-1do in order matching operation, once can with certain target s wherein
j, n-1can match, by according to the character of queue, target item s above
k, n-1, s
k-1, n-1..., s
j-1, n-1, be and leave the human body target that detection zone enters lock road.
By said method, not only can determine the number in current detection district 4, and can determine, prior image frame comparison direct with it, in present image, how much have is the number that ticket checking newly enters detection zone 4 of swiping the card, how much have is just to have left detection zone 4 and the number that enters the station.
In implementation process of the present invention, tracking and matching algorithm has Pixel-level precision, meets individual tracking accuracy requirement completely.Its implementation is that the two continuous two field pictures of hypothesis image sequence are respectively f
t-1and f
t.Wherein, we are by f
tregard as present image, and f
t-1it is the directly front frame of present image.The task of following the tracks of is exactly according to f
t-1certain characteristic area subimage d at known person body region center of mass point p (x, the y) place on image, adopts the method for relevant matches at f
tthe enterprising line search of image, finds the region subimage d ' mating most with it.After searching for successfully, by region corresponding some p ' of subimage d ' (x, y) point, be exactly the position of the corresponding center of mass point p of d subregion (x, y).Wherein, by a p (x, y), to the respective distance between p ' (x, y) point, represented that this human body target is at image f
t-1and f
tthe moving displacement of compartment.In order to realize a coupling, can define a related function, represent the matching degree of 2 region subimage d of p (x, y) and p ' (x, y) and d '.If two width mate the image f calculating
t-1and f
t, at f
t-1the area image at the subregion image d place of middle selection is g, and its size is m * n, and at image f
tselected coupling subregion figure is S, and its size is M * N, uses S
x, yrepresent to take (x, y) as the upper left angle point sub-block identical with g size in S.With formula (2), represent correlation computations expression formula, when the value of γ reaches maximum, its extreme point (maximal value) corresponding coordinate (x, y) represents optimum matching.In formula
with
the gray average that represents respectively its image-region.
The present invention, in implementation process, can adopt following equipment:
(1) embedded central processing module: the development board that adopts Rrea1210 model, its major parameter is: kernel is the Samsung hummingbird processor S5PV210 of processor Cortex-A8, dominant frequency is 1GHz, support NEON instruction, support 3D figure to accelerate (Power VR SGX540) and OpenGL-1.1 & 2.0, OpenVG1.0, support JPEG hardware compression, maximum 8192 * 8192 resolution of supporting, inside save as 4G bits DDR2.Support RGB24Bit interface and the output of TVOUT video.
(2) imageing sensor: the CMOS model of employing is OV3460,2048*1536 pixel, imaging region size is 3626 μ m x2709 μ m, and pixel size is 1.75 μ m x1.75 μ m, and it is per second that top speed can reach 30 frames.
(3) white light source YBL-86-29, electric parameter 24v/8.6w, physical dimension (mm) 86 * 29 * 18, LED row is 5, band diffusion disk.When environment temperature is 25 ℃, with the continuous reliably working of 50% white light source brightness, surpass 30,000 hours (when damping capacity is 50%), and can extend the serviceable life of light source while using frequent flashing control.
(4) optical lens: M3Z1228C-MP FA industry 300 everything element camera lenses, specification Format:2/3 "; Interface mode: C; Focal length (mm): 12-36 (variable); Aperture (F): 2.8-16C; Field angle (horizontal HOR) °: 41.0-13.6; Recently object image distance is from (M): 0.2; Effective aperture: front Front
27.2; Rear Rear
12.1; Pre-filter screw thread
35.5 * 0.5; Physical dimension
41.6 * 53.
Claims (3)
1. the subway based on image recognition is prevented the system of stealing a ride, it is characterized in that, comprise card using information adapter, imaging device, card using information adapter, imaging device are connected with embedded central processing module respectively, embedded central processing module is also connected with warning device, switch gate control device, card using information adapter taps into the signal port of station card-punching system, and in embedded central processing module, is provided with respectively swipe the card counter for number of people and detection zone counter for number of people.
2. a method of work for the anti-system of stealing a ride of the subway based on image recognition as claimed in claim 1, is characterized in that, comprises following job step:
Step 1: gather the trigger pip of card using information adapter, if enter the station the signal of swiping the card, the counter for number of people of swiping the card adds 1, otherwise the count value of the counter for number of people of swiping the card is constant;
Step 2: by camera (1) acquisition testing district (4) present image, and itself and background template image are differed from after shadow computing, poor image to gained carries out row projection, according to the feature of drop shadow curve, realize target is cut apart, and extract the current number in detection zone (4), charge to detection zone counter for number of people;
Step 3: by the human body target tracking to directly front frame and current frame image, obtain the replacement information of detection zone (4) number, and revise the count value of the counter for number of people of swiping the card;
Step 4: the value of relatively swipe the card counter for number of people and detection zone counter for number of people, if the former equals the latter, open sluice gate, proceeds to step 1; Otherwise, close sluice gate, and send alerting signal, wait pending.
3. a kind of subway based on image recognition as claimed in claim 2 is prevented the method for work of the system of stealing a ride, it is characterized in that, the replacement information of described step 3 detection zone (4) number, that the human body target region barycenter of present image and its directly front frame is done to relevant matches, by following the tracks of the human body target of adjacent image frame, realize newly entering human body number and exiting the statistics of human body number present image detection zone (4).
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201310611194.4A CN103605967A (en) | 2013-11-26 | 2013-11-26 | Subway fare evasion prevention system and working method thereof based on image recognition |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201310611194.4A CN103605967A (en) | 2013-11-26 | 2013-11-26 | Subway fare evasion prevention system and working method thereof based on image recognition |
Publications (1)
Publication Number | Publication Date |
---|---|
CN103605967A true CN103605967A (en) | 2014-02-26 |
Family
ID=50124187
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN201310611194.4A Pending CN103605967A (en) | 2013-11-26 | 2013-11-26 | Subway fare evasion prevention system and working method thereof based on image recognition |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN103605967A (en) |
Cited By (19)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN103942865A (en) * | 2014-04-18 | 2014-07-23 | 上海交通大学 | Subway ticket evasion preventing system based on ultrasonic sensor and design method thereof |
CN104200545A (en) * | 2014-07-11 | 2014-12-10 | 中交一公局第二工程有限公司 | Real-time dynamic management system of building engineering construction, and work method thereof |
CN104766372A (en) * | 2015-04-29 | 2015-07-08 | 深圳市保千里电子有限公司 | Fare evasion judging system using face recognition and using method thereof |
CN104805784A (en) * | 2015-03-30 | 2015-07-29 | 苏州华兴致远电子科技有限公司 | Gate fare evasion detection system and gate fare evasion detection method |
CN105321230A (en) * | 2014-06-28 | 2016-02-10 | 陈娇 | Bus fare evasion warning system |
CN106447879A (en) * | 2016-12-01 | 2017-02-22 | 深圳翎云思创网络科技有限公司 | Monitoring system, monitoring method and door control system |
CN106612415A (en) * | 2015-10-27 | 2017-05-03 | 北京航天长峰科技工业集团有限公司 | Production workshop personnel exiting and entering supervision method |
CN107025418A (en) * | 2016-01-29 | 2017-08-08 | 广州地铁集团有限公司 | Anti- detection method of stealing a ride, detecting system and its system based on image procossing |
CN107220970A (en) * | 2017-05-25 | 2017-09-29 | 宋妍 | A kind of method of collision free |
CN107784289A (en) * | 2017-11-02 | 2018-03-09 | 深圳市共进电子股份有限公司 | A kind of security-protecting and monitoring method, apparatus and system |
CN108629334A (en) * | 2018-06-01 | 2018-10-09 | 西京学院 | A kind of bus based on Face datection is stolen a ride verifying attachment and the method for inspection |
CN108960150A (en) * | 2018-07-05 | 2018-12-07 | 东华大学 | A kind of unmanned transit riding payment monitor system |
CN109118623A (en) * | 2015-12-28 | 2019-01-01 | 王成财 | A kind of ticket checking monitoring method |
CN110099253A (en) * | 2019-05-20 | 2019-08-06 | 浙江大华技术股份有限公司 | Execution method, the display equipment of alarm operation |
CN110415418A (en) * | 2019-08-09 | 2019-11-05 | 苏州富欣智能交通控制有限公司 | A kind of rail electricity passenger flow volume statistical method |
CN110443901A (en) * | 2019-06-26 | 2019-11-12 | 成都信息工程大学 | In conjunction with the ticket checking method, device and storage medium of multiple view |
CN110766809A (en) * | 2018-07-25 | 2020-02-07 | 比亚迪股份有限公司 | Vehicle, vehicle-mounted ticket checking system and ticket checking method of vehicle-mounted ticket checking system |
CN111064925A (en) * | 2019-12-04 | 2020-04-24 | 常州工业职业技术学院 | Subway passenger ticket evasion behavior detection method and system |
CN112200828A (en) * | 2020-09-03 | 2021-01-08 | 浙江大华技术股份有限公司 | Detection method and device for ticket evasion behavior and readable storage medium |
Citations (5)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN101763504A (en) * | 2009-12-30 | 2010-06-30 | 邱怀骏 | Human head identification method under complex scene |
CN202351685U (en) * | 2011-12-06 | 2012-07-25 | 四川久远新方向智能科技有限公司 | Subway automatic frequency control (AFC) passenger traffic control system |
JP2012194719A (en) * | 2011-03-16 | 2012-10-11 | Omron Corp | Gate system |
CN102930334A (en) * | 2012-10-10 | 2013-02-13 | 北京凯森世纪科技发展有限公司 | Video recognition counter for body silhouette |
CN103218866A (en) * | 2013-04-24 | 2013-07-24 | 太原科技大学 | Method for controlling single person entering in closed space by computer |
-
2013
- 2013-11-26 CN CN201310611194.4A patent/CN103605967A/en active Pending
Patent Citations (5)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN101763504A (en) * | 2009-12-30 | 2010-06-30 | 邱怀骏 | Human head identification method under complex scene |
JP2012194719A (en) * | 2011-03-16 | 2012-10-11 | Omron Corp | Gate system |
CN202351685U (en) * | 2011-12-06 | 2012-07-25 | 四川久远新方向智能科技有限公司 | Subway automatic frequency control (AFC) passenger traffic control system |
CN102930334A (en) * | 2012-10-10 | 2013-02-13 | 北京凯森世纪科技发展有限公司 | Video recognition counter for body silhouette |
CN103218866A (en) * | 2013-04-24 | 2013-07-24 | 太原科技大学 | Method for controlling single person entering in closed space by computer |
Non-Patent Citations (1)
Title |
---|
张嫄: "城市轨道交通系统的闸机中图像处理与识别技术", 《中国优秀硕士学位论文全文数据库 信息科技辑》, 31 January 2007 (2007-01-31), pages 138 - 419 * |
Cited By (21)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN103942865A (en) * | 2014-04-18 | 2014-07-23 | 上海交通大学 | Subway ticket evasion preventing system based on ultrasonic sensor and design method thereof |
CN105321230A (en) * | 2014-06-28 | 2016-02-10 | 陈娇 | Bus fare evasion warning system |
CN104200545A (en) * | 2014-07-11 | 2014-12-10 | 中交一公局第二工程有限公司 | Real-time dynamic management system of building engineering construction, and work method thereof |
CN104805784A (en) * | 2015-03-30 | 2015-07-29 | 苏州华兴致远电子科技有限公司 | Gate fare evasion detection system and gate fare evasion detection method |
CN104766372A (en) * | 2015-04-29 | 2015-07-08 | 深圳市保千里电子有限公司 | Fare evasion judging system using face recognition and using method thereof |
CN106612415A (en) * | 2015-10-27 | 2017-05-03 | 北京航天长峰科技工业集团有限公司 | Production workshop personnel exiting and entering supervision method |
CN109118623A (en) * | 2015-12-28 | 2019-01-01 | 王成财 | A kind of ticket checking monitoring method |
CN109118623B (en) * | 2015-12-28 | 2021-01-12 | 王成财 | Ticket checking monitoring method |
CN107025418A (en) * | 2016-01-29 | 2017-08-08 | 广州地铁集团有限公司 | Anti- detection method of stealing a ride, detecting system and its system based on image procossing |
CN106447879A (en) * | 2016-12-01 | 2017-02-22 | 深圳翎云思创网络科技有限公司 | Monitoring system, monitoring method and door control system |
CN107220970A (en) * | 2017-05-25 | 2017-09-29 | 宋妍 | A kind of method of collision free |
CN107784289A (en) * | 2017-11-02 | 2018-03-09 | 深圳市共进电子股份有限公司 | A kind of security-protecting and monitoring method, apparatus and system |
CN108629334A (en) * | 2018-06-01 | 2018-10-09 | 西京学院 | A kind of bus based on Face datection is stolen a ride verifying attachment and the method for inspection |
CN108960150A (en) * | 2018-07-05 | 2018-12-07 | 东华大学 | A kind of unmanned transit riding payment monitor system |
CN110766809A (en) * | 2018-07-25 | 2020-02-07 | 比亚迪股份有限公司 | Vehicle, vehicle-mounted ticket checking system and ticket checking method of vehicle-mounted ticket checking system |
CN110099253A (en) * | 2019-05-20 | 2019-08-06 | 浙江大华技术股份有限公司 | Execution method, the display equipment of alarm operation |
CN110443901A (en) * | 2019-06-26 | 2019-11-12 | 成都信息工程大学 | In conjunction with the ticket checking method, device and storage medium of multiple view |
CN110415418A (en) * | 2019-08-09 | 2019-11-05 | 苏州富欣智能交通控制有限公司 | A kind of rail electricity passenger flow volume statistical method |
CN111064925A (en) * | 2019-12-04 | 2020-04-24 | 常州工业职业技术学院 | Subway passenger ticket evasion behavior detection method and system |
CN111064925B (en) * | 2019-12-04 | 2021-05-04 | 常州工业职业技术学院 | Subway passenger ticket evasion behavior detection method and system |
CN112200828A (en) * | 2020-09-03 | 2021-01-08 | 浙江大华技术股份有限公司 | Detection method and device for ticket evasion behavior and readable storage medium |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
CN103605967A (en) | Subway fare evasion prevention system and working method thereof based on image recognition | |
CN102542289B (en) | Pedestrian volume statistical method based on plurality of Gaussian counting models | |
CN102110376B (en) | Roadside parking space detection device based on computer vision | |
CN105260749B (en) | Real-time target detection method based on direction gradient binary pattern and soft cascade SVM | |
CN101727748B (en) | Method, system and equipment for monitoring vehicles based on vehicle taillight detection | |
CN108596129A (en) | A kind of vehicle based on intelligent video analysis technology gets over line detecting method | |
CN102426785B (en) | Traffic flow information perception method based on contour and local characteristic point and system thereof | |
EP0567059A1 (en) | Object recognition system and abnormality detection system using image processing | |
CN105744232A (en) | Method for preventing power transmission line from being externally broken through video based on behaviour analysis technology | |
CN104408932A (en) | Drunk driving vehicle detection system based on video monitoring | |
CN103824070A (en) | Rapid pedestrian detection method based on computer vision | |
Pan et al. | Traffic surveillance system for vehicle flow detection | |
CN107909012B (en) | Real-time vehicle tracking detection method and device based on disparity map | |
CN103077423A (en) | Crowd quantity estimating, local crowd clustering state and crowd running state detection method based on video stream | |
CN105574502A (en) | Automatic detection method for violation behaviors of self-service card sender | |
CN111507237A (en) | Video-based abnormal event detection method and device applied to expressway | |
CN104616006A (en) | Surveillance video oriented bearded face detection method | |
CN102610104B (en) | Onboard front vehicle detection method | |
CN105046948A (en) | System and method of monitoring illegal traffic parking in yellow grid line area | |
CN106156695A (en) | Outlet and/or entrance area recognition methods and device | |
CN109791607A (en) | It is detected from a series of images of video camera by homography matrix and identifying object | |
CN103164958A (en) | Method and system for vehicle monitoring | |
Chen et al. | Traffic congestion classification for nighttime surveillance videos | |
CN104463104A (en) | Fast detecting method and device for static vehicle target | |
CN107452212B (en) | Crossing signal lamp control method and system |
Legal Events
Date | Code | Title | Description |
---|---|---|---|
C06 | 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 | ||
RJ01 | Rejection of invention patent application after publication |
Application publication date: 20140226 |