CN111860976B - Gate traffic time prediction method and device - Google Patents
Gate traffic time prediction method and device Download PDFInfo
- Publication number
- CN111860976B CN111860976B CN202010614071.6A CN202010614071A CN111860976B CN 111860976 B CN111860976 B CN 111860976B CN 202010614071 A CN202010614071 A CN 202010614071A CN 111860976 B CN111860976 B CN 111860976B
- Authority
- CN
- China
- Prior art keywords
- infrared
- prediction
- time
- gate
- value
- 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 56
- 238000001914 filtration Methods 0.000 claims abstract description 4
- 230000006698 induction Effects 0.000 claims description 18
- 238000005070 sampling Methods 0.000 claims description 17
- 238000005562 fading Methods 0.000 claims description 14
- 239000011159 matrix material Substances 0.000 claims description 12
- 230000008569 process Effects 0.000 claims description 12
- 230000006870 function Effects 0.000 claims description 6
- 230000003044 adaptive effect Effects 0.000 claims description 4
- 125000003275 alpha amino acid group Chemical group 0.000 claims description 4
- 150000001875 compounds Chemical class 0.000 claims description 4
- 238000012360 testing method Methods 0.000 claims description 3
- 230000006978 adaptation Effects 0.000 claims description 2
- 230000017105 transposition Effects 0.000 claims description 2
- 239000013598 vector Substances 0.000 claims description 2
- 239000000654 additive Substances 0.000 claims 1
- 230000000996 additive effect Effects 0.000 claims 1
- 230000009471 action Effects 0.000 description 7
- 208000014674 injury Diseases 0.000 description 4
- 208000027418 Wounds and injury Diseases 0.000 description 3
- 238000004891 communication Methods 0.000 description 3
- 230000008878 coupling Effects 0.000 description 3
- 238000010168 coupling process Methods 0.000 description 3
- 238000005859 coupling reaction Methods 0.000 description 3
- 230000006378 damage Effects 0.000 description 3
- 238000001514 detection method Methods 0.000 description 2
- 238000010586 diagram Methods 0.000 description 2
- 238000002474 experimental method Methods 0.000 description 2
- 208000012260 Accidental injury Diseases 0.000 description 1
- 238000009825 accumulation Methods 0.000 description 1
- 230000006399 behavior Effects 0.000 description 1
- 230000009286 beneficial effect Effects 0.000 description 1
- 230000000903 blocking effect Effects 0.000 description 1
- 238000004364 calculation method Methods 0.000 description 1
- 230000008859 change Effects 0.000 description 1
- 230000007547 defect Effects 0.000 description 1
- 238000013461 design Methods 0.000 description 1
- 230000000694 effects Effects 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 230000003287 optical effect Effects 0.000 description 1
- 238000012545 processing Methods 0.000 description 1
- 238000012549 training Methods 0.000 description 1
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q10/00—Administration; Management
- G06Q10/04—Forecasting or optimisation specially adapted for administrative or management purposes, e.g. linear programming or "cutting stock problem"
-
- E—FIXED CONSTRUCTIONS
- E01—CONSTRUCTION OF ROADS, RAILWAYS, OR BRIDGES
- E01F—ADDITIONAL WORK, SUCH AS EQUIPPING ROADS OR THE CONSTRUCTION OF PLATFORMS, HELICOPTER LANDING STAGES, SIGNS, SNOW FENCES, OR THE LIKE
- E01F13/00—Arrangements for obstructing or restricting traffic, e.g. gates, barricades ; Preventing passage of vehicles of selected category or dimensions
- E01F13/04—Arrangements for obstructing or restricting traffic, e.g. gates, barricades ; Preventing passage of vehicles of selected category or dimensions movable to allow or prevent passage
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q50/00—Information and communication technology [ICT] specially adapted for implementation of business processes of specific business sectors, e.g. utilities or tourism
- G06Q50/40—Business processes related to the transportation industry
Landscapes
- Engineering & Computer Science (AREA)
- Business, Economics & Management (AREA)
- Human Resources & Organizations (AREA)
- Economics (AREA)
- Strategic Management (AREA)
- Physics & Mathematics (AREA)
- Tourism & Hospitality (AREA)
- Theoretical Computer Science (AREA)
- Marketing (AREA)
- General Physics & Mathematics (AREA)
- General Business, Economics & Management (AREA)
- Quality & Reliability (AREA)
- Development Economics (AREA)
- Game Theory and Decision Science (AREA)
- Operations Research (AREA)
- Entrepreneurship & Innovation (AREA)
- Architecture (AREA)
- Civil Engineering (AREA)
- Structural Engineering (AREA)
- Health & Medical Sciences (AREA)
- General Health & Medical Sciences (AREA)
- Primary Health Care (AREA)
- Traffic Control Systems (AREA)
- Management, Administration, Business Operations System, And Electronic Commerce (AREA)
Abstract
The invention discloses a gate passing time prediction method and a gate passing time prediction device, wherein the method comprises the following steps: acquiring an infrared information sequence of a pedestrian entering a gate at present; acquiring a preset pedestrian infrared sequence model; identifying residual errors between the infrared information sequences and infrared prediction sequences corresponding to different human types by using a residual error identification method, and judging whether the residual errors exceed a preset threshold value or not; if the residual error between the infrared information sequence and one of the infrared prediction sequences is lower than the preset threshold value, fusing the infrared information sequence and the infrared prediction sequences by improving a square root unscented Kalman filtering algorithm to complete the prediction of pedestrian passing time; and if the residual errors of the infrared information sequences and all the infrared prediction sequences are higher than the preset threshold value, finishing prediction of pedestrian passing time by adopting a fuzzy control algorithm. The invention can improve the passing efficiency of the gate.
Description
Technical Field
The invention belongs to the technical field of public transportation coordination, and particularly relates to a gate passing time prediction method and device.
Background
The working process of the ticket gate generally comprises the steps of card swiping and ticket checking, gate opening, pedestrian passing, gate closing and the like. Only one pedestrian should be allowed to pass through in the time interval from opening to closing of the gate each time; thus, the gate opening time interval needs to be maintained for a reasonable period of time. On one hand, the ticket inspector can pass through the ticket inspector in a safe and comfortable way, and on the other hand, the phenomenon that the ticket is followed by escaping due to overlong opening time of the gate is avoided. When the number of the passing gate exceeds the number of checked tickets, the buzzer is started to give an alarm, so that the ticket jumper can be prevented from running the gate in the time interval from opening to closing with a motion obviously faster than that of a normal person. The running of the gate not only causes the ticket evasion, but also brings higher accidental injury risk to the gate running person.
The existing ticket gate has the defects that firstly, a fixed time length is adopted in a time interval from opening to closing after ticket checking of the gate each time, and in order to ensure safety and smooth completion of traffic under most conditions, the fixed time length of the time interval can only be set to exceed the actual traffic time of normal pedestrians, and the time length exceeding each time is extremely short, but the accumulation still brings non-negligible influence on traffic efficiency, and the traffic efficiency is reduced in a peak time period or a dense passenger flow area. Secondly, for a few situations that the passing can not be completed in the time interval, such as slow action of the old, luggage carrying by the passenger, children traction by parents, etc., repeated opening and closing phenomena of the gate can be avoided in order to avoid accidental clamping, or the situation that the passersby is already closed without passing through the gate of the blocking device can reduce the passing efficiency, and even the situation needs to be manually solved, so that the effect that the gate can not effectively pass within a few minutes can be caused.
Disclosure of Invention
In order to overcome the above-mentioned drawbacks, the present invention provides a method and apparatus for predicting the passing time of a gate, which can improve the passing efficiency of the gate; when the passersby passes slowly, the passersby is carried or children are pulled, repeated ineffective closing and opening actions of the gate are avoided, the phenomena of passing obstruction and time delay caused by errors are prevented, and the personal injury risk is reduced.
In order to solve the problems, the invention is realized according to the following technical scheme:
a method for predicting gate transit time, the method comprising:
acquiring an infrared information sequence of a pedestrian entering a gate at present;
acquiring a preset pedestrian infrared sequence model; the pedestrian infrared sequence model comprises infrared prediction sequences corresponding to different human types;
Identifying residual errors between the infrared information sequences and infrared prediction sequences corresponding to different human types by using a residual error identification method, and judging whether the residual errors exceed a preset threshold value or not;
If the residual error between the infrared information sequence and one of the infrared prediction sequences is lower than the preset threshold value, fusing the infrared information sequence and the infrared prediction sequences by improving a square root unscented Kalman filtering algorithm to complete the prediction of pedestrian passing time;
And if the residual errors of the infrared information sequences and all the infrared prediction sequences are higher than the preset threshold value, finishing prediction of pedestrian passing time by adopting a fuzzy control algorithm.
The invention also discloses a gate passing time prediction device, which comprises a processor and a storage, wherein the storage stores program codes, and the processor executes the program codes to execute the gate passing time prediction method.
Compared with the prior art, the invention has the beneficial effects that:
The invention discloses a gate passing time prediction method and device, which can improve the passing efficiency of a gate; when the passersby passes slowly, the passersby is carried or children are pulled, repeated ineffective closing and opening actions of the gate are avoided, the phenomena of passing obstruction and time delay caused by errors are prevented, and the personal injury risk is reduced.
Drawings
FIG. 1 is a schematic diagram illustrating steps of a method for predicting gate transit time according to an embodiment of the present invention.
FIG. 2 is a schematic diagram of a gate transit time prediction device according to an embodiment of the invention.
Detailed Description
For the purpose of making the objects, technical solutions and advantages of the embodiments of the present invention more apparent, the technical solutions of the embodiments of the present invention will be clearly and completely described below with reference to the accompanying drawings in the embodiments of the present invention, and it is apparent that the described embodiments are some embodiments of the present invention, but not all embodiments of the present invention. The components of the embodiments of the present invention generally described and illustrated in the figures herein may be arranged and designed in a wide variety of different configurations.
Thus, the following detailed description of the embodiments of the invention, as presented in the figures, is not intended to limit the scope of the invention, as claimed, but is merely representative of selected embodiments of the invention. All other embodiments, which can be made by those skilled in the art based on the embodiments of the invention without making any inventive effort, are intended to be within the scope of the invention.
It is noted that relational terms such as first and second, and the like are used solely to distinguish one entity or action from another entity or action without necessarily requiring or implying any actual such relationship or order between such entities or actions. Moreover, the terms "comprises," "comprising," or any other variation thereof, are intended to cover a non-exclusive inclusion, such that a process, method, article, or apparatus that comprises a list of elements does not include only those elements but may include other elements not expressly listed or inherent to such process, method, article, or apparatus. Without further limitation, an element defined by the phrase "comprising one … …" does not exclude the presence of other like elements in a process, method, article, or apparatus that comprises the element.
In the description of the present invention, it should also be noted that, unless explicitly specified and limited otherwise, the terms "disposed", "connected" and "connected" are to be construed broadly, and may be, for example, fixedly connected, detachably connected or integrally connected; can be mechanically or electrically connected; can be directly connected or indirectly connected through an intermediate medium, and can be communication between two elements. The specific meaning of the above terms in the present invention will be understood in specific cases by those of ordinary skill in the art.
Example 1
As shown in fig. 1, the present embodiment discloses a gate traffic time prediction method, which includes the following steps:
s1, acquiring an infrared information sequence of a pedestrian currently entering a gate;
S2, acquiring a preset pedestrian infrared sequence model; the pedestrian infrared sequence model comprises infrared prediction sequences corresponding to different human types;
S3, identifying residual errors between the infrared information sequences and infrared prediction sequences corresponding to different human types by using a residual error identification method, and judging whether the residual errors exceed a preset threshold value or not;
if the residual of the infrared information sequence and one of the infrared prediction sequences is below the predetermined threshold, then:
S4, fusing the infrared information sequence and the infrared prediction sequence through an improved square root unscented Kalman filtering algorithm to complete the prediction of pedestrian traffic time;
If the residuals of the infrared information sequence and all the infrared prediction sequences are higher than the predetermined threshold value, then:
s5, predicting the pedestrian passing time by adopting a fuzzy control algorithm.
Specifically, in this embodiment, the pedestrian infrared sequence model is established by the following steps:
Dividing pedestrians passing through the gate into a single person type and a non-single person type;
respectively acquiring two groups of infrared information sequences of pedestrians belonging to the two categories when passing through the gate, and combining each group of infrared information sequences to obtain the infrared prediction sequence corresponding to each category;
And according to the time stamp of the infrared prediction sequence, the pedestrian speed is divided into fast, medium and slow speed, so that the final opening duration of the gate door is obtained.
Specifically, in this embodiment, the infrared information sequence is obtained through an infrared sensing light curtain disposed on the gate; the infrared induction light curtain comprises a plurality of infrared sensors, wherein the infrared sensors are used for acquiring the infrared information sequences and the corresponding time stamps which are obtained when the infrared sensors are shielded.
Specifically, in this embodiment, the residuals between the infrared information sequences and the infrared prediction sequences corresponding to the different human types are calculated by the following formula:
wherein D is a residual error, N is the number of the infrared sensors in the infrared sensing light curtain, x ij represents the state of the jth infrared sensor when the ith infrared sensor is blocked for the first time in the infrared information sequence, and y ij represents the state of the jth infrared sensor when the ith infrared sensor is blocked for the first time in the infrared prediction sequence.
Specifically, in this embodiment, the step S4 specifically includes the following steps:
The observed noise covariance R k at time S41, k is as follows:
r k-1 represents the observed noise covariance at time K-1, z k represents the observed quantity at time K, For the observation predicted value at the k moment after weighting, the self-adaptive factor d k＝(1-b)/(1-bk), b is a forgetting factor, the value range is (0, 1), and the superscript is T which represents the transposition of the matrix; adjusting the adaptation factor d k by adapting the parameter W k, thereby adapting the influence of different sensor noise characteristics on the system, converting equation (2) into:
In formula (3), I k is an n×n identity matrix, W k is an adaptive adjustment parameter, W k＝diag(m1,...,mn), where 0<m i <1, i=1, …, n, diag () is a diagonal matrix composed of vectors;
the adaptive factor d k is shown in formula (4):
dk＝(dupper-dlower)·bk+dlower (4)
Wherein d upper is the upper limit of the value of the self-adaptive factor, d lower is the lower limit of the value of the self-adaptive factor, the value ranges of d upper and d lower are (0, 1), and d upper>dlower, b is the forgetting factor, and the value range is (0.9,1);
updating the covariance of the observed noise by adjusting d lower;
The method for estimating the statistical characteristics of the observed noise comprises the following steps:
In the above-mentioned (5) (6), Is the Cholesky factor update value of the observed noise covariance at time k-1.
S42, setting initial conditions:
In the formula (7), the amino acid sequence of the compound, Representing an initial value of the state variable estimate, x 0 representing an initial value of the state variable, P x,0 representing an initial value of the error covariance of the state variable estimate, S x,0 representing a Cholesky factor;
S43, predicting state variables:
according to state variables And error covariance square root S x,k-1 using unscented transforms to obtain 2n+1 sigma points, as follows:
In the formula (8), the amino acid sequence of the compound, The i-th sampling point at the k-1 moment is represented, and i or i-n after brackets represents the i-th or i-n column of the covariance square root matrix of the state variable error; λ=a 2 × (n+k) -n, where a represents the spread factor, the range of values is [10 -6, 1], n represents the dimension of the state variable, k represents the auxiliary scale factor, satisfying k+n+.0.
Then, the state variables are updated in time according to equation (8), see equations (9) and (10).
In the method, in the process of the invention,State prediction value representing the i-th sampling point,/>State value representing the i-th sampling point,/>State variable predictive value representing time k/>The expected weight of the ith sampling point is shown in the specific formula (11).
Where the square root of error covariance S x,k-1 is replaced with *Sx,k-1.
S44, state variable error covariance square root prediction by introducing multiple fading factors:
Note that: pre-amble represents the values of each variable after the introduction of multiple fading factors.
Error covariance square root predictor without multiple fading factors introduced at time kAs shown in equation (24), P xz,k is an error covariance matrix of the state quantity and observed quantity, as shown in equation (13):
in the method, in the process of the invention, Error covariance square root predictor representing time k,/>Representing the i-th sample point error covariance weight, Q k is the variance of the system noise at time K, see in particular equation (15), sign () represents the sign bit.
Where b represents a pre-test distribution factor, typically taken as 2.
Can be obtained byAnd/>Structured sigma sampling points/>And/>The following are provided:
Representing the observed prediction value of the i-th sampling point after introducing strong tracking. Thereby obtaining an error covariance square root predicted value after introducing multiple fading factors at the k moment as shown in a formula (19):
Zeta k in formula (18) represents a multiple fading factor.
S45, updating an observation variable:
in the method, in the process of the invention, Representing an observation predicted value of an ith sampling point after introducing strong tracking; /(I)For/>And/>Constructing sigma sampling points; /(I)The observed predicted value at k time after the weighted introduction of multiple fading factors is shown.
S46, updating the covariance square root of the observed variable error:
wherein *Sz,k represents the observed variable error covariance square root update value after multiple fading factors are introduced, *Pxz,k is the error covariance matrix of the state quantity and observed quantity.
S47, kalman gain updating *Kk is as follows:
S48, state variable And state variable error covariance square root *Sx,k update:
s43, repeating the steps S43 to S48 to obtain the optimal passing time.
Specifically, in this embodiment, the step S5 specifically includes the following steps:
according to the value of the residual error D, a fuzzy control algorithm is selected, D is taken as input, the passing time T is taken as output, the fuzzy theory domains are [ -N, N ], the language variable value [ NL, NM, NS, ZO, PS, PM, PL ], and the membership function is a symmetrical triangle; the rule front part and implication adopt 'small-taking' operation, and a COG reverse gelatinization method is adopted; substituting D into the membership function to obtain corresponding weights, and multiplying the respective weights by the transit time under different modes to obtain the final predicted transit time.
Wherein, the fuzzy rule table is as follows:
Specifically, in this embodiment, an infrared light curtain is installed on the gate of the ticket gate, and includes several sets of infrared transmitters and infrared receivers that are in one-to-one correspondence, and the infrared light curtain generates an infrared passing detection signal according to the blocked condition of infrared rays, so as to be used for characterizing the position area of pedestrians in the passing space of the gate. According to the algorithm, the infrared passing detection signals generated when pedestrians pass through the gate are analyzed, the passing mode of the pedestrians (including single passing, dragging luggage passing and the like) is determined, the passing time of the pedestrians passing through the gate is predicted according to the residual quantity obtained by the algorithm based on different passing modes, so that the opening time interval from opening to closing of the gate is adaptively adjusted according to the passing time, the opening time interval matched with the predicted passing time is reached, and the passing efficiency of the gate is improved; when the passersby passes slowly, the passersby is carried or children are pulled, repeated ineffective closing and opening actions of the gate are avoided, the phenomena of passing obstruction and time delay caused by errors are prevented, and the personal injury risk is reduced.
An optional technical implementation idea of the method for implementing the traffic logic control is described below:
Firstly, establishing an infrared induction sequence model of different crowds passing through ticket gate in the traffic logic prediction method. The model divides different crowds into a single mode and a non-single mode according to behavior characteristics, records infrared induction sequences generated by normal pedestrians passing through a gate for many times by taking the single mode as an example, and each group of infrared induction sequence information comprises the following parts: the time stamp of the first change of the sensor signal, the status of all infrared receivers; assuming that the gate portion is equipped with N pairs of infrared transmitters and infrared receivers, one test can obtain N sets of data. After multiple experiments, according to the distribution frequency of the infrared induction sequences, we obtain a model of the infrared induction sequences in a single person mode, and according to the time stamp and the length of the gate, predicting the single person passing time. The training mode of the non-single person mode is identical to that of the single person mode.
On the basis of establishing an infrared induction sequence model, when a pedestrian swipes a card to prepare to pass through a gate, the infrared induction devices at two sides inside the gate start to induce, and a group of infrared induction sequence inputs are obtained when the pedestrian arrives at the gate; matching the infrared induction sequence with the model established in the step 1, and distinguishing the pedestrian into single person or non-single person (including baggage and baby carriage pedestrians) categories according to the matching result; after the pedestrian category is distinguished, the pedestrian speed is divided fast, medium and slow according to the time stamp of the infrared induction sequence, so that the final opening duration of the gate door is obtained.
In the process of pattern matching, the algorithm adopts a residual error identification method to identify whether the preset threshold value is exceeded. Firstly, carrying out residual calculation on the obtained infrared induction sequence and the infrared induction sequence of the single person mode, and if the obtained residual is lower than a preset threshold value, considering that the obtained residual is matched with the single person mode. Due to the difference of different individuals, the invention can distinguish the crowd at low speed, medium speed and fast speed according to the average speed calculated by the time stamp of the infrared induction sequence. And comparing the obtained average speed with the existing speed in the infrared induction sequence to obtain a proportionality coefficient, and multiplying the proportionality coefficient by the preset passing time to obtain the predicted passing time of the passing. And if the residual error exceeds a preset threshold value when the matching is performed with the single-person mode, the matching is performed with the non-single-person mode, and the matching process is the same as that of the single-person mode. If the secondary infrared induction sequence is not matched with the mode in the established infrared induction model, a fuzzy control method is adopted, residual errors are used as input, a set of weights in a single-person mode and a non-single-person mode are obtained through a fuzzy controller preset by a system, and the preset time in the corresponding mode is multiplied to obtain the final predicted pedestrian passing time.
Example 2
As shown in fig. 2, the present embodiment discloses a gate transit time prediction device, which includes a processor and a memory, wherein the memory stores program codes, and the processor executes the program codes to perform the gate transit time prediction method described in embodiment 1.
Those of ordinary skill in the art will appreciate that the various illustrative method steps described in connection with the embodiments disclosed herein can be implemented as electronic hardware, or as a combination of computer software and electronic hardware. Whether such functionality is implemented as hardware or software depends upon the particular application and design constraints imposed on the solution. Skilled artisans may implement the described functionality in varying ways for each particular application, but such implementation decisions should not be interpreted as causing a departure from the scope of the present invention.
In the embodiments provided in the present application, it should be understood that the disclosed apparatus and method may be implemented in other manners. For example, the apparatus embodiments described above are merely illustrative, e.g., the division of the units is merely a logical function division, and there may be additional divisions when actually implemented, e.g., multiple units or components may be combined or integrated into another system, or some features may be omitted or not performed. Alternatively, the coupling or direct coupling or communication connection shown or discussed with each other may be an indirect coupling or communication connection via some interfaces, devices or units, which may be in electrical, mechanical or other form.
The units described as separate units may or may not be physically separate, and units shown as units may or may not be physical units, may be located in one place, or may be distributed on a plurality of network units. Some or all of the units may be selected according to actual needs to achieve the purpose of the solution of this embodiment.
In addition, each functional unit in the embodiments of the present invention may be integrated in one processing unit, or each unit may exist alone physically, or two or more units may be integrated in one unit.
The functions, if implemented in the form of software functional units and sold or used as a stand-alone product, may be stored in a computer-viewable storage medium. Based on this understanding, the technical solution of the present invention may be embodied essentially or in a part contributing to the prior art or in a part of the technical solution, in the form of a software product stored in a storage medium, comprising several instructions for causing a computer device (which may be a personal computer, a server, a network device, etc.) to perform all or part of the steps of the method according to the embodiments of the present invention. And the aforementioned storage medium includes: a usb disk, a removable hard disk, a ROM, a RAM, a magnetic disk, or an optical disk, etc.
While the preferred embodiments of the present invention have been described in detail, it should be understood that numerous modifications and variations can be made in accordance with the concepts of the invention by those skilled in the art without undue burden. Therefore, all technical solutions which can be obtained by logic analysis, reasoning or according to limited experiments by a person skilled in the art based on the prior art according to the inventive concept shall be within the scope of protection defined by the claims.
Claims (6)
1. A method for predicting gate transit time, the method comprising:
acquiring an infrared information sequence of a pedestrian entering a gate at present;
acquiring a preset pedestrian infrared sequence model; the pedestrian infrared sequence model comprises infrared prediction sequences corresponding to different human types;
Identifying residual errors between the infrared information sequences and infrared prediction sequences corresponding to different human types by using a residual error identification method, and judging whether the residual errors exceed a preset threshold value or not;
If the residual error between the infrared information sequence and one of the infrared prediction sequences is lower than the preset threshold value, fusing the infrared information sequence and the infrared prediction sequences by improving a square root unscented Kalman filtering algorithm to complete the prediction of pedestrian passing time;
If the residual errors of the infrared information sequences and all the infrared prediction sequences are higher than the preset threshold value, a fuzzy control algorithm is adopted to complete the prediction of the pedestrian passing time;
the pedestrian infrared sequence model is established through the following steps:
Dividing pedestrians passing through the gate into a single person type and a non-single person type;
respectively acquiring two groups of infrared information sequences of pedestrians belonging to the two categories when passing through the gate, and combining each group of infrared information sequences to obtain the infrared prediction sequence corresponding to each category;
And according to the time stamp of the infrared prediction sequence, the pedestrian speed is divided into fast, medium and slow speed, so that the final opening duration of the gate door is obtained.
2. The gate travel time prediction method according to claim 1, wherein the infrared information sequence is acquired through an infrared sensing light curtain provided at the gate; the infrared induction light curtain comprises a plurality of infrared sensors, and the infrared sensors are used for acquiring the infrared information sequences and the corresponding time stamps which are obtained when the infrared sensors are shielded.
3. The gate transit time prediction method according to claim 2, wherein residuals between the infrared information sequences and the infrared prediction sequences corresponding to the different human types are calculated by the following formula:
wherein D is a residual error, N is the number of the infrared sensors in the infrared sensing light curtain, x ij represents the state of the jth infrared sensor when the ith infrared sensor is blocked for the first time in the infrared information sequence, and y ij represents the state of the jth infrared sensor when the ith infrared sensor is blocked for the first time in the infrared prediction sequence.
4. The method of claim 1, wherein the step of fusing the infrared information sequence with the infrared prediction sequence by a modified square root unscented kalman filter algorithm to complete the prediction of the pedestrian traffic time comprises the steps of:
The observed noise covariance R k at time S41, k is as follows:
r k-1 represents the observed noise covariance at time K-1, z k represents the observed quantity at time K, For the observation predicted value at the k moment after weighting, the self-adaptive factor d k＝(1-b)/(1-bk), b is a forgetting factor, the value range is (0, 1), and the upper mark is T which represents the transposition of the matrix; adjusting the adaptation factor d k by adapting the parameter W k, thereby adapting the influence of different sensor noise characteristics on the system, converting equation (2) into:
In formula (3), I k is an n×n identity matrix, W k is an adaptive adjustment parameter, W k＝diag(m1,...,mn), where 0<m i <1, i=1, …, n, diag () is a diagonal matrix composed of vectors;
the adaptive factor d k is shown in formula (4):
dk＝(dupper-dlower)·bk+dlower (4)
Wherein d upper is the upper limit of the value of the self-adaptive factor, d lower is the lower limit of the value of the self-adaptive factor, the value ranges of d upper and d lower are (0, 1), and d upper>dlower, b is the forgetting factor, and the value range is (0.9,1);
updating the covariance of the observed noise by adjusting d lower;
The method for estimating the statistical characteristics of the observed noise comprises the following steps:
In the above-mentioned (5) (6), Is the Cholesky factor update value of the observed noise covariance at time k-1;
S42, setting initial conditions:
In the formula (7), the amino acid sequence of the compound, Representing an initial value of the state variable estimate, x 0 representing an initial value of the state variable, P x,0 representing an initial value of the error covariance of the state variable estimate, S x,0 representing a Cholesky factor;
S43, predicting state variables:
according to state variables And error covariance square root S x,k-1 using unscented transforms to obtain 2n+1 sigma points, as follows:
In the formula (8), the amino acid sequence of the compound, The i-th sampling point at the k-1 moment is represented, and i or i-n after brackets represents the i-th or i-n column of the covariance square root matrix of the state variable error; λ=a 2 × (n+k) -n, where a represents the spread factor, the range of values is [10 -6, 1], n represents the dimension of the state variable, k represents the auxiliary scale factor, satisfying k+n+.0;
Then, the state variables are updated in time according to formula (8), see formulas (9) and (10);
in the method, in the process of the invention, State prediction value representing the i-th sampling point,/>State value representing the i-th sampling point,/>State variable predictive value representing time k/>The expected weight of the ith sampling point is shown in the specific formula (11);
Wherein the square root of error covariance S x,k-1 is replaced with *Sx,k-1;
s44, state variable error covariance square root prediction by introducing multiple fading factors:
Additive represents the values of each variable after introduction of multiple fading factors;
Error covariance square root predictor without multiple fading factors introduced at time k As shown in equation (24), P xz,k is an error covariance matrix of the state quantity and observed quantity, as shown in equation (13):
in the method, in the process of the invention, Error covariance square root predictor representing time k,/>Representing the error covariance weight of the ith sampling point, wherein Q k is the variance of the system noise at the K moment, and the sign () represents the sign bit;
Wherein b represents a pre-test distribution factor, and 2 is taken;
Can be obtained by And/>Structured sigma sampling points/>And/>The following are provided:
Representing an observation predicted value of an ith sampling point after introducing strong tracking; thereby obtaining an error covariance square root predicted value after introducing multiple fading factors at the k moment as shown in a formula (19):
Zeta k in formula (18) represents a multiple fading factor;
s45, updating an observation variable:
in the method, in the process of the invention, Representing an observation predicted value of an ith sampling point after introducing strong tracking; /(I)For/>And/>Constructing sigma sampling points; /(I)Representing the observed predicted value at k time after the weighted multiple fading factors are introduced;
s46, updating the covariance square root of the observed variable error:
Wherein *Sz,k represents the observed variable error covariance square root update value after multiple fading factors are introduced, *Pxz,k is the error covariance matrix of the state quantity and observed quantity;
S47, kalman gain updating *Kk is as follows:
S48, state variable And state variable error covariance square root *Sx,k update:
and S43, repeating the steps S43 to S48 to obtain the optimal passing time.
5. The method for predicting the traffic time of a gate as defined in claim 4, wherein the step of predicting the traffic time of a pedestrian by using a fuzzy control algorithm comprises the steps of:
According to the value of the residual error D, a fuzzy control algorithm is selected, D is taken as input, the passing time T is taken as output, the fuzzy theory domains are [ -N, N ], the language variable value [ NL, NM, NS, ZO, PS, PM, PL ], and the membership function is a symmetrical triangle; the rule front part and implication adopt 'small-taking' operation, and a COG reverse gelatinization method is adopted; substituting D into the membership function to obtain corresponding weights, and multiplying the respective weights by the transit time under different modes to obtain the final predicted transit time.
6. A gate transit time prediction device comprising a processor and a memory, wherein the memory has program code stored therein, and wherein the processor executes the program code to perform the gate transit time prediction method of any of claims 1-5.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202010614071.6A CN111860976B (en) | 2020-06-30 | 2020-06-30 | Gate traffic time prediction method and device |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202010614071.6A CN111860976B (en) | 2020-06-30 | 2020-06-30 | Gate traffic time prediction method and device |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN111860976A CN111860976A (en) | 2020-10-30 |
| CN111860976B true CN111860976B (en) | 2024-04-30 |
Family
ID=72988815
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202010614071.6A Active CN111860976B (en) | 2020-06-30 | 2020-06-30 | Gate traffic time prediction method and device |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN111860976B (en) |
Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN106651730A (en) * | 2016-12-22 | 2017-05-10 | 东南大学 | System and method for metro passenger flow early warning based on passenger flow density and gate pass time |
| CN109916410A (en) * | 2019-03-25 | 2019-06-21 | 南京理工大学 | A kind of indoor orientation method based on improvement square root Unscented kalman filtering |
| CN110110690A (en) * | 2019-05-16 | 2019-08-09 | 廊坊鑫良基科技有限公司 | A kind of target pedestrian method for tracing, device, equipment and storage medium |
| CN110782480A (en) * | 2019-10-15 | 2020-02-11 | 哈尔滨工程大学 | Infrared pedestrian tracking method based on online template prediction |
-
2020
- 2020-06-30 CN CN202010614071.6A patent/CN111860976B/en active Active
Patent Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN106651730A (en) * | 2016-12-22 | 2017-05-10 | 东南大学 | System and method for metro passenger flow early warning based on passenger flow density and gate pass time |
| CN109916410A (en) * | 2019-03-25 | 2019-06-21 | 南京理工大学 | A kind of indoor orientation method based on improvement square root Unscented kalman filtering |
| CN110110690A (en) * | 2019-05-16 | 2019-08-09 | 廊坊鑫良基科技有限公司 | A kind of target pedestrian method for tracing, device, equipment and storage medium |
| CN110782480A (en) * | 2019-10-15 | 2020-02-11 | 哈尔滨工程大学 | Infrared pedestrian tracking method based on online template prediction |
Also Published As
| Publication number | Publication date |
|---|---|
| CN111860976A (en) | 2020-10-30 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| Chen et al. | Traffic flow prediction by an ensemble framework with data denoising and deep learning model | |
| Coifman | Vehicle re-identification and travel time measurement in real-time on freeways using existing loop detector infrastructure | |
| Dong et al. | Flow rate and time mean speed predictions for the urban freeway network using state space models | |
| US6950813B2 (en) | Fuzzy inference network for classification of high-dimensional data | |
| Hope et al. | Heterogeneity in the frequency distribution of crime victimization | |
| CN113744526B (en) | Highway risk prediction method based on LSTM and BF | |
| CN104538041A (en) | Method and system for detecting abnormal sounds | |
| RU2705770C1 (en) | Method for operational and technical protection of boundaries of objects and boundaries | |
| CN103440493A (en) | Hyperspectral image blur classification method and device based on related vector machine | |
| CN112989361A (en) | Model security detection method based on generation countermeasure network | |
| Abdulhai et al. | Spatio-temporal inductance-pattern recognition for vehicle re-identification | |
| CN112765607A (en) | Neural network model backdoor attack detection method | |
| Sheu | A sequential detection approach to real-time freeway incident detection and characterization | |
| CN111967308A (en) | Online road surface unevenness identification method and system | |
| CN111860976B (en) | Gate traffic time prediction method and device | |
| CN116597642A (en) | Traffic jam condition prediction method and system | |
| Klevtsov | Identification of the state of technical objects based on analyzing a limited set of parameters | |
| Goncharov et al. | Mathematical modeling of the security management process of an information system in conditions of unauthorized external influences | |
| CN115964670A (en) | Frequency spectrum anomaly detection method | |
| CN109583741B (en) | Driving track risk assessment method and system | |
| Herbinger et al. | Decomposing global feature effects based on feature interactions | |
| CN116310542A (en) | Image classification method based on improved cross entropy loss function | |
| CN115909717A (en) | Expressway short-term traffic flow prediction method based on deep learning | |
| Poulos et al. | Automatic stationary detection of time series using auto-correlation coefficients and LVQ—Neural network | |
| Bruce et al. | Automated accident detection in intersections via digital audio signal processing |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |