CN115688682B - Vehicle track data compression method and device based on fuzzy prediction - Google Patents
Vehicle track data compression method and device based on fuzzy prediction Download PDFInfo
- Publication number
- CN115688682B CN115688682B CN202211706702.2A CN202211706702A CN115688682B CN 115688682 B CN115688682 B CN 115688682B CN 202211706702 A CN202211706702 A CN 202211706702A CN 115688682 B CN115688682 B CN 115688682B
- Authority
- CN
- China
- Prior art keywords
- fuzzy
- vehicle
- track
- prediction
- data
- 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 36
- 238000013144 data compression Methods 0.000 title claims abstract description 28
- 238000004364 calculation method Methods 0.000 claims abstract description 15
- 238000007906 compression Methods 0.000 claims abstract description 8
- 230000006835 compression Effects 0.000 claims abstract description 8
- 238000006073 displacement reaction Methods 0.000 claims description 42
- 230000006870 function Effects 0.000 claims description 15
- 230000008859 change Effects 0.000 claims description 9
- 238000012217 deletion Methods 0.000 claims description 6
- 230000037430 deletion Effects 0.000 claims description 6
- 230000004927 fusion Effects 0.000 claims description 6
- 238000013528 artificial neural network Methods 0.000 claims description 3
- 238000006243 chemical reaction Methods 0.000 claims description 3
- 238000005070 sampling Methods 0.000 claims description 2
- 230000001133 acceleration Effects 0.000 claims 1
- 238000004891 communication Methods 0.000 abstract description 4
- 230000000694 effects Effects 0.000 abstract description 3
- 230000006855 networking Effects 0.000 abstract 1
- 238000004321 preservation Methods 0.000 abstract 1
- 238000012545 processing Methods 0.000 description 9
- 238000004590 computer program Methods 0.000 description 2
- 238000013461 design Methods 0.000 description 2
- 238000010586 diagram Methods 0.000 description 2
- 238000005516 engineering process Methods 0.000 description 2
- 230000008569 process Effects 0.000 description 2
- 238000012549 training Methods 0.000 description 2
- 238000009825 accumulation Methods 0.000 description 1
- 230000004913 activation Effects 0.000 description 1
- 238000013459 approach Methods 0.000 description 1
- 230000006399 behavior Effects 0.000 description 1
- 230000009286 beneficial effect Effects 0.000 description 1
- 230000005540 biological transmission Effects 0.000 description 1
- 238000013135 deep learning Methods 0.000 description 1
- 230000007547 defect Effects 0.000 description 1
- 238000013507 mapping Methods 0.000 description 1
- 239000011159 matrix material Substances 0.000 description 1
- 238000005065 mining Methods 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 238000010606 normalization Methods 0.000 description 1
- 238000005457 optimization Methods 0.000 description 1
- 239000002245 particle Substances 0.000 description 1
- 230000000306 recurrent effect Effects 0.000 description 1
Abstract
The invention discloses a vehicle track data compression method and device based on fuzzy prediction, comprising the following steps: (1) Track data are collected in the edge car networking environment, a membership function is determined, and the track data are blurred. (2) Track fuzzy prediction, which predicts the driving intention through the original track data and then carries out fuzzy prediction according to the fuzzy data to obtain the fuzzy track data. (3) Error calculation and track point preservation, comparing the original fuzzy data with the predicted fuzzy data, and if the error is larger than a set threshold value, preserving the fuzzy track point. The method is based on the fuzzy representation of the track data, and has a lightweight privacy protection function. And the track data expression based on the fuzzy characters is adopted, so that the communication quantity of the data of the edge internet of vehicles is obviously reduced, and the bandwidth consumption is reduced. The track data is further compressed based on fuzzy prediction of the track, and the compression effect is greatly improved.
Description
Technical Field
The invention relates to the technical fields of track compression, fuzzy theory and track prediction, in particular to a vehicle track data compression method and device based on fuzzy prediction.
Background
The mining and analyzing of the track data of the vehicles is helpful for users or city planners to make better decisions, and has wide application scenes. Such as optimization and design of traffic routes, identification of dangerous driving behavior, traffic prediction for cities, etc. The vehicle-mounted GPS equipment can collect track data of the vehicle in real time, transmit the track data to the cloud data center and store the track data. However, the accumulation of time and space generates massive data, severely consuming bandwidth resources and space storage resources. Therefore, the track data needs to be compressed and then transmitted to the cloud. In the environment of the Internet of vehicles, the computing capability of widely distributed edge equipment can be fully utilized to rapidly compress the track data, so that the communication bandwidth consumption in track data transmission is reduced.
On the other hand, with the wide application of the internet of vehicles, the problem of safety and privacy of vehicle information is increasingly receiving attention of people. The track data of the vehicle contains personal information of a plurality of users, such as the current position, identification and state of the users, if the data are directly transmitted in the internet of vehicles, an attacker can easily acquire the information of the users through the attack means such as fake base stations, fake legal terminals and the like, thereby revealing the privacy of the users of the vehicle and even threatening the personal safety of the users of the vehicle. One technology adopted at present for protecting the safety privacy of users is a safety authentication technology, and identity authentication is realized through digital signature and encryption. However, this approach not only increases the communication burden of the internet of vehicles environment where resources are limited, but also leaks the privacy of the vehicle user when decrypted by an attacker.
In addition, in most of the existing prediction-based trajectory data compression methods, some of the prediction models are simple to calculate, but the prediction errors are large, for example, the linear-based trajectory prediction models. Some predictive models predict more accurately, but require more computational power and more computation time, such as a deep learning based trajectory prediction model. Therefore, it is difficult for the above models to achieve a balance between the accuracy of prediction and the predictive computation force.
In order to solve the above problems, how to design a reasonable track data structure to represent the track data of the vehicle in the environment of the edge internet of vehicles and create a track prediction model on the basis of the reasonable track data structure to realize the balance between the prediction precision and the prediction calculation force is a problem to be solved.
Disclosure of Invention
The invention aims to overcome the defects of the prior art, and provides a vehicle track data compression method and device based on fuzzy prediction.
The aim of the invention is realized by the following technical scheme: in a first aspect, the present invention provides a vehicle track data compression method based on fuzzy prediction, the method comprising the steps of:
(1) Blurring track data: collecting vehicle track data, and determining parameters of a membership function according to the statistical data of the vehicle displacement increment sequence so as to define the membership function; dividing a plurality of domains according to the membership function and representing the domains by fuzzy characters, and converting the track data into fuzzy characters;
(2) Fuzzy prediction of trajectories: predicting the driving intention of the target vehicle through a neural network, and selecting a corresponding multi-order fusion Markov model according to the driving intention to perform fuzzy prediction of a future fuzzy displacement increment sequence;
(3) Residual calculation and track point deletion: and according to the comparison of the fuzzy characters of the fuzzy prediction and the original fuzzy characters, deleting the track points with residual errors smaller than the set threshold value, and retaining the track points with residual errors larger than the set threshold value.
Further, in the step (1), the detailed steps of blurring the trajectory data are as follows:
(1-1) trajectory data coordinate conversion: the vehicle sends the original track data to a nearby edge gateway (RSU) through a vehicle network, and the longitude and latitude coordinate sequence of the vehicle is converted into a two-dimensional coordinate sequence taking the edge gateway as an origin by taking the position of the gateway as the origin;
(1-2) blurring of trajectory data based on the blurred character: respectively calculating displacement increment sequences in the longitude x and latitude y directions; the method comprises the following steps: calculating displacement sequences in the x and y directions, and extracting the symbols to obtain a displacement increment sequence and a displacement symbol sequence in the x direction, and a displacement increment sequence and a displacement symbol sequence in the y direction; and for the displacement increment sequence in the x direction, determining the fuzzy granularity according to the accuracy of the road type information or the track data, further creating r fuzzy sets, and converting the value of the displacement increment sequence into a corresponding fuzzy character representation, so that the displacement increment sequence is converted into a fuzzy character string.
Further, mapping the original track sequence to two-dimensional coordinates with the edge gateway as an origin; the vehicle acquires the position of the vehicle in real time through the vehicle-mounted GPS equipment, and obtains the original track data expressed by longitude and latitude at each moment.
Further, the blur granularity is determined according to the accuracy of the road type information or the track data, thereby creating r blur sets.
Further, in the step (2), the detailed steps of the track ambiguity prediction are as follows:
(2-1) prediction of driving intention: inputting information of the target vehicle and information of surrounding vehicles into a network overlapped by the GRU unit, and outputting driving intentions of three target vehicles, namely, left lane change, straight running and right lane change;
(2-2) track position prediction: and selecting a corresponding multi-order fusion Markov model according to the driving intention of the target vehicle, and predicting a future fuzzy displacement increment sequence by the historical fuzzy displacement increment sequence.
Further, the information of the target vehicle includes a historical track position, speed and lane number; the information of the surrounding vehicles includes the collision time of the target vehicle with the surrounding vehicles and the lane number in which the surrounding vehicles are located.
Further, in the step (3), the detailed steps of residual calculation and trace point deletion are as follows:
(3-1) residual calculation based on the blurred character: the model predicted fuzzy character needs to be compared with the real fuzzy character, and the residual error of the fuzzy character is calculated as shown in the following formula:
wherein i is the sequence number of the fuzzy character set to which the predicted fuzzy character belongs, j is the sequence number of the fuzzy character set to which the original fuzzy character belongs, and r is the number of the fuzzy characters;
(3-2) removing the trace point according to the set threshold value: setting a threshold value，If the predicted result has no deviation from the real track position, namely the residual error is smaller than the threshold value, the track position is removed, and if the predicted result has deviation, namely the residual error is larger than the threshold value, the track position is reserved, so that the purpose of compression is achieved.
Further, when the threshold is set to 0, it indicates that prediction is not allowed to have errors, and as long as the predicted value and the original value have errors, the original value is added to the compressed track; when the threshold is set to 1, it means that any prediction is within the error tolerance range, at which time no original value is added to the compressed track; thus, the threshold valueThe larger the prediction-allowed error range is, the larger the prediction-allowed error range is.
In a second aspect, the present invention provides a vehicle track data compression device based on fuzzy prediction, including a memory and one or more processors, where the memory stores executable codes, and the processors are configured to implement the steps of the vehicle track data compression method based on fuzzy prediction when executing the executable codes.
In a third aspect, the present invention provides a computer-readable storage medium having stored thereon a program which, when executed by a processor, implements the steps of the vehicle trajectory data compression method based on fuzzy prediction.
The beneficial effects of the invention are mainly shown in the following steps:
(1) The track data is subjected to fuzzy coding, and a lightweight privacy protection function is provided.
(2) The track data expression based on the fuzzy characters obviously reduces the communication quantity of the data of the edge internet of vehicles and reduces the bandwidth consumption.
(3) Track data is further compressed based on fuzzy prediction of tracks, and compression effect is greatly improved.
Drawings
In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the drawings that are required in the embodiments or the description of the prior art will be briefly described, and it is obvious that the drawings in the following description are only some embodiments of the present invention, and other drawings may be obtained according to these drawings without inventive effort for a person skilled in the art.
Fig. 1 is a flowchart of a track data compression method based on fuzzy prediction.
Fig. 2 is a flowchart of track blur prediction.
Fig. 3 is a block diagram of a track data compression device based on fuzzy prediction.
Detailed Description
The invention will be further described with reference to the accompanying drawings.
Referring to fig. 1, the present invention provides a track data compression method based on fuzzy prediction, comprising the steps of:
(1) Blurring track data: and acquiring original track data of the vehicle, and determining parameters of a membership function according to the statistical data of the track data of the vehicle, thereby defining the membership function. And dividing the domain according to the membership function and representing the domain by fuzzy characters, and converting the track data into fuzzy characters. The detailed steps of the track data blurring of the vehicle are as follows:
(1-1) trajectory data coordinate conversion: the original track sequence is mapped to two-dimensional coordinates with the edge gateway as the origin. The vehicle collects the position of the vehicle in real time through the vehicle-mounted GPS equipment, and sets the slaveFrom moment to momentTime of day, raw trajectory dataIndicating that the vehicle is inFrom moment to momentThe position of the moment in time,raw trace data of time of dayIndicating that the vehicle is inLongitude of time vehicle (Longitude) isLatitude (Latitude) is. Transmitting it to nearby edge gateway (RSU) through vehicle-to-vehicle network, and providing edge gatewaykThe position of (2) isThe position of the gateway is used as the origin of coordinates, and the longitude and latitude coordinate sequence of the vehicle is converted into a two-dimensional coordinate sequence with the edge gateway as the originWhereinRepresentation ofTwo-dimensional coordinates of the moment.
(1-2) blurring of trajectory data based on the blurred character: and respectively calculating the displacement increment sequences in the x and y directions. The method comprises the following steps: calculated atxAndyextracting the displacement symbol by the directional displacement sequence to obtainxSequence of directional displacement incrementsAnd a sequence of shift symbolsSequence of displacement increments in the y-directionAnd a sequence of shift symbols。Representation oft 1 Relative to time of dayt 0 At the moment ofxThe displacement in the direction is increased by an increment,representation oft n Time trace position relative tot n-1 At the moment ofxThe displacement in the direction is increased by an increment,representation ofIs a displacement sign of (2);representation oft 1 Relative to time of dayt 0 At the moment ofyThe displacement in the direction is increased by an increment,representation oft n Time trace position relative tot n-1 At the moment ofyThe displacement in the direction is increased by an increment,representation ofIs a shift sign of (c). For the followingxA sequence of directional displacement increments, r fuzzy sets are created by formulas (1) - (3)Wherein the parameters of all fuzzy sets are determined by equation (4). Fuzzy character set，Wherein the particle size of blurringThe greater the number of fuzzy sets and fuzzy characters, the finer the granularity of the fuzzification, determined according to the accuracy of the road type information or the trajectory data.yIncremental blurring of displacement of directionxDirection. Converting the value of the displacement increment sequence into a corresponding fuzzy character representation, and converting the displacement increment sequence into fuzzy charactersStrings.
Wherein,is the membership function of the 1 st to 5 th fuzzy sets,is a fuzzy set membership function parameter and is determined according to historical data distribution.，Andis divided intoxAndyminimum, maximum and average of displacement increment of two adjacent positions in the direction.
(2) Fuzzy prediction of trajectories: and predicting the driving intention of the target vehicle through the gating circulating unit GRU (Gate Recurrent Unit) network, and selecting a corresponding multi-order fusion Markov model according to the driving intention to perform fuzzy prediction. Referring to fig. 2, the detailed steps of the trajectory blur prediction are as follows:
(2-1) prediction of driving intention: the information of the target vehicle including the historical track position, speed and lane number is input into the network overlapped by the GRU unit, and three driving intentions, namely, left lane change, straight lane change and right lane change are output.
The input data is the position and speed of the target vehicleAcceleration ofLane markingThe method comprises the steps of carrying out a first treatment on the surface of the Time to collision TTC with surrounding vehicle, lane markingAnd the TTC and the lane number of the j vehicle and the target vehicle at the moment i are indicated. The total input data of the driving intention prediction module is，T is the total sampling time. The network structure adopts multi-layer GRU superposition, and adds a Droupout layer to prevent overfitting, and then connects with a softmax layer to output the probabilities of left lane change, straight running and right lane change of each driving intention. TTC (Time to Collision) is a safety index of the constant track, and the calculation formula of TTC of the target vehicle and surrounding vehicles is shown as formula (5).
Wherein the method comprises the steps ofRepresentation ofTime to collision TTC of the moment with the surrounding vehicle j,the lane number indicating the target vehicle is the same as the lane number of the vehicle j,for the relative distance of the target vehicle from the vehicle j in the x-direction,for the relative speed of the target vehicle and vehicle j in the x-direction,for the relative distance of the target vehicle from the vehicle j in the y-direction,for the relative speed of the target vehicle and vehicle j in the y direction,andthe angles between the traveling directions of the target vehicle and the vehicle j and the x direction are respectively. The TTC comprises the distance relation and the speed relation between the target vehicle and other surrounding vehicles, and the position and the speed of the surrounding vehicles are converted into the collision time TTC between the surrounding vehicles and the target vehicle, so that the input dimension is effectively reduced, the parameters of the network are reduced, and the calculated amount is reduced.
The GRU cell includes two gates, a reset gate and an update gate. Can be calculated by formulas (6) to (9).
Wherein,r t indicating the number of reset gate layers,representing the sigmoid activation function,h t-1 is the output at time t-1,the input at time t is indicated,representing a weight matrix that resets the gate layer. In the use of the reset gate, the new memory will store history-related information using the reset gate as shown in equations (7) and (8).
Wherein the method comprises the steps ofThe representation of the updated gate level is provided,is the new output at time t. Finally, the output of the GRU is updated as shown in equation (9).
Wherein,representing element-by-element multiplication (elementwise product).
(2-2) track position prediction: and selecting a corresponding multi-order fusion Markov Model (Adaboost-Markov Model) according to the driving intention of the target vehicle, and predicting a future fuzzy displacement increment sequence from the historical fuzzy displacement increment sequence, wherein the calculation formulas of the multi-order fusion Markov Model are shown as (10) - (13).
In the formulas (10) to (13),is thatmThe order Markov model corresponds to the weights of the training samples.Is thatmTraining sample corresponding to order Markov modeli Is provided.Is thatmThe weight coefficient of the order Markov model.Is thatmThe order normalization factor is used to determine,is thatm-Probability distribution of order 1 Markov model.For the normalized m-order Markov model weight coefficient, k represents the order,is an m-order Markov model.Is the final Markov model.
(3) Residual calculation and track point deletion: and according to the comparison of the fuzzy characters of the fuzzy prediction and the original fuzzy characters, deleting the track points with residual errors smaller than the set threshold value, and reserving the track points with residual errors larger than the set threshold value. Given a fuzzy character string to be predicted, the detailed steps of residual calculation and track point deletion are as follows:
(3-1) residual calculation based on the blurred character: the model predicted ambiguous character needs to be compared with the real ambiguous character and the residual calculation of the ambiguous character is shown in equation (14). Wherein i is the sequence number of the fuzzy character set to which the predicted fuzzy character Pred belongs, j is the sequence number of the fuzzy character set to which the original fuzzy character belongs, and r is the number of the fuzzy characters.
(3-2) removing the trace point according to the set threshold value: setting a threshold valueIf the predicted result has no deviation from the real track position, the track position is removed, and if the deviation is larger than the threshold, the track position is reserved, so that the aim of compression is fulfilled. When the threshold is set to 0, indicating that prediction is not allowed to be error, the original value is added to the compressed track as long as the predicted value and the original value are error. When the threshold is set to 1, it means that any prediction is within the error tolerance range, at which time no original value is added to the compressed track. Thus, the threshold valueThe larger the prediction-allowed error range is, the better the compression effect (compression ratio) is.
The present invention also provides an embodiment of a track data compression device based on fuzzy prediction, corresponding to the embodiment of the track data compression method based on fuzzy prediction.
Referring to fig. 3, the track data compression device based on fuzzy prediction provided by the embodiment of the invention includes a memory and one or more processors, wherein executable codes are stored in the memory, and the processors are used for implementing the track data compression method based on fuzzy prediction in the above embodiment when executing the executable codes.
The track data compression device based on fuzzy prediction can be applied to any device with data processing capability, such as a computer or the like. The apparatus embodiments may be implemented by software, or may be implemented by hardware or a combination of hardware and software. Taking software implementation as an example, the device in a logic sense is formed by reading corresponding computer program instructions in a nonvolatile memory into a memory by a processor of any device with data processing capability. In terms of hardware, as shown in fig. 3, a hardware structure diagram of an arbitrary device with data processing capability where the trace data compression device based on fuzzy prediction is located in the present invention is shown in fig. 3, and in addition to the processor, the memory, the network interface, and the nonvolatile memory shown in fig. 3, the arbitrary device with data processing capability where the device is located in the embodiment generally includes other hardware according to the actual function of the arbitrary device with data processing capability, which is not described herein again.
The implementation process of the functions and roles of each unit in the above device is specifically shown in the implementation process of the corresponding steps in the above method, and will not be described herein again.
For the device embodiments, reference is made to the description of the method embodiments for the relevant points, since they essentially correspond to the method embodiments. The apparatus embodiments described above are merely illustrative, wherein the elements illustrated as separate elements may or may not be physically separate, and the elements shown as elements may or may not be physical elements, may be located in one place, or may be distributed over a plurality of network elements. Some or all of the modules may be selected according to actual needs to achieve the purposes of the present invention. Those of ordinary skill in the art will understand and implement the present invention without undue burden.
The embodiment of the present invention also provides a computer-readable storage medium having a program stored thereon, which when executed by a processor, implements the track data compression method based on fuzzy prediction in the above embodiment.
The computer readable storage medium may be an internal storage unit, such as a hard disk or a memory, of any of the data processing enabled devices described in any of the previous embodiments. The computer readable storage medium may be any external storage device that has data processing capability, such as a plug-in hard disk, a Smart Media Card (SMC), an SD Card, a Flash memory Card (Flash Card), or the like, which are provided on the device. Further, the computer readable storage medium may include both internal storage units and external storage devices of any data processing device. The computer readable storage medium is used for storing the computer program and other programs and data required by the arbitrary data processing apparatus, and may also be used for temporarily storing data that has been output or is to be output.
The above-described embodiments are intended to illustrate the present invention, not to limit it, and any modifications and variations made thereto are within the spirit of the invention and the scope of the appended claims.
Claims (7)
1. A vehicle trajectory data compression method based on fuzzy prediction, characterized in that the method comprises the following steps:
(1) Blurring track data: collecting vehicle track data, and determining parameters of a membership function according to the statistical data of the vehicle displacement increment sequence so as to define the membership function; dividing a plurality of domains according to membership functions, creating fuzzy sets, converting values of displacement increment sequences of two adjacent moments of a vehicle into corresponding fuzzy character representations through the fuzzy sets and the fuzzy division, and converting the displacement increment sequences into fuzzy character strings;
(2) Fuzzy prediction of trajectories: predicting the driving intention of a target vehicle through a neural network to obtain three driving intentions of left lane changing, straight running and right lane changing, selecting a corresponding multi-order fusion Markov model according to the driving intentions, and predicting a future fuzzy displacement increment sequence through a historical fuzzy displacement increment sequence;
the data input by the neural network is a two-dimensional coordinate sequence of the position of the target vehicleVelocity v i Acceleration a i Lane mark Lane i ，x i ，y i Representing t i Two-dimensional coordinates of the moment; time to collision TTC with surrounding vehicle, lane markingThe TTC and the lane number of the j vehicle and the target vehicle at the moment i are represented; driving intention predicts total input data as +.>T is the total sampling time; the network structure adopts multi-layer GRU superposition, and outputs the probabilities of left lane change, straight running and right lane change of each driving intention; the TTC comprises a distance relation and a speed relation between the target vehicle and other surrounding vehicles, and the calculation formula of the TTC between the target vehicle and the surrounding vehicles is as follows:
wherein the method comprises the steps ofRepresenting t i Time to collision TTC, +.>The lane number indicating the target vehicle is the same as the lane number of vehicle j, |x-x j The I is the relative distance between the target vehicle and the vehicle j in the x direction, and the I vcos theta-v j cos β| is the relative speed of the target vehicle and vehicle j in the x direction, |y-y j The I is the relative distance between the target vehicle and the vehicle j in the y direction, and the I v sin theta-v j sin beta| is the relative speed of the target vehicle and the vehicle j in the y direction, and theta and beta are the included angles of the running direction of the target vehicle and the vehicle j and the x direction respectively;
(3) Residual calculation and track point deletion: according to the fuzzy character of fuzzy prediction and the original fuzzy character, deleting the track points with residual errors smaller than the set threshold value, and reserving the track points with residual errors larger than the set threshold value;
the residual calculation and track point deletion steps are as follows:
(3-1) residual calculation based on the blurred character: the model predicted fuzzy character needs to be compared with the real fuzzy character, and the residual error of the fuzzy character is calculated as shown in the following formula:
wherein m is the sequence number of the fuzzy character set to which the predicted fuzzy character belongs, n is the sequence number of the fuzzy character set to which the original fuzzy character belongs, and r' is the number of the fuzzy characters;
(3-2) removing the trace point according to the set threshold value: setting a threshold epsilon, wherein epsilon is more than or equal to 0 and less than or equal to 1, if the predicted result has no deviation from the actual track position, namely the residual error is less than the threshold, removing the track position, and if the predicted result has the deviation, namely the residual error is greater than the threshold, retaining the track position, thereby achieving the purpose of compression.
2. The vehicle track data compression method based on fuzzy prediction of claim 1, wherein in the step (1), the detailed steps of fuzzification of the track data are as follows:
(1-1) trajectory data coordinate conversion: the vehicle sends the track data to a nearby edge gateway RSU through a vehicle-to-vehicle network, and the longitude and latitude coordinate sequence of the vehicle is converted into a two-dimensional coordinate sequence with the edge gateway as an origin by taking the position of the gateway as the origin;
(1-2) blurring of trajectory data based on the blurred character: respectively calculating displacement increment sequences in the longitude x and latitude y directions; the method comprises the following steps: calculating displacement sequences in the x and y directions, and extracting the symbols to obtain a displacement increment sequence and a displacement symbol sequence in the x direction, and a displacement increment sequence and a displacement symbol sequence in the y direction; for a sequence of displacement increments in the x and y directions, r fuzzy sets are created.
3. The vehicle track data compression method based on fuzzy prediction according to claim 2, wherein the original track sequence is mapped to two-dimensional coordinates with an edge gateway as an origin; the vehicle acquires the position of the vehicle in real time through the vehicle-mounted GPS equipment, and obtains the original track data expressed by longitude and latitude at each moment.
4. The vehicle trajectory data compression method based on fuzzy prediction of claim 2, wherein the fuzzy granularity is determined according to the accuracy of the road type information or the trajectory data, thereby creating r fuzzy sets.
5. The vehicle track data compression method based on fuzzy prediction of claim 1, wherein when the threshold is set to 0, it indicates that prediction is not allowed to occur error, and the original value is added to the compressed track whenever there is an error between the predicted value and the original value; when the threshold is set to 1, it means that any prediction is within the error tolerance range, at which time no original value is added to the compressed track; thus, the larger the threshold ε, the larger the prediction-allowed error range.
6. A vehicle track data compression device based on fuzzy prediction comprising a memory and one or more processors, the memory having executable code stored therein, wherein the processor, when executing the executable code, is operative to implement the steps of a vehicle track data compression method based on fuzzy prediction as claimed in any one of claims 1 to 5.
7. A computer-readable storage medium, on which a program is stored, characterized in that the program, when being executed by a processor, implements the steps of a vehicle trajectory data compression method based on fuzzy prediction as claimed in any one of claims 1 to 5.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202211706702.2A CN115688682B (en) | 2022-12-29 | 2022-12-29 | Vehicle track data compression method and device based on fuzzy prediction |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202211706702.2A CN115688682B (en) | 2022-12-29 | 2022-12-29 | Vehicle track data compression method and device based on fuzzy prediction |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN115688682A CN115688682A (en) | 2023-02-03 |
| CN115688682B true CN115688682B (en) | 2023-11-14 |
Family
ID=85055170
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202211706702.2A Active CN115688682B (en) | 2022-12-29 | 2022-12-29 | Vehicle track data compression method and device based on fuzzy prediction |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN115688682B (en) |
Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN107247961A (en) * | 2017-05-10 | 2017-10-13 | 西安交通大学 | A kind of trajectory predictions method of application blurring trajectorie sequence |
| CN111654290A (en) * | 2020-04-24 | 2020-09-11 | 北京中交兴路车联网科技有限公司 | Method, device and equipment for compressing vehicle track data and storage medium |
| WO2021249020A1 (en) * | 2020-06-10 | 2021-12-16 | 华为技术有限公司 | Method and apparatus for predicting driving state, and terminal device |
| CN113911129A (en) * | 2021-11-23 | 2022-01-11 | 吉林大学 | Traffic vehicle intention identification method based on driving behavior generation mechanism |
| CN114368387A (en) * | 2021-12-21 | 2022-04-19 | 吉林大学 | Attention mechanism-based driver intention identification and vehicle track prediction method |
| CN115027484A (en) * | 2022-05-23 | 2022-09-09 | 吉林大学 | Human-computer fusion perception method for high-degree automatic driving |
Family Cites Families (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| DE112018002143T5 (en) * | 2017-04-24 | 2020-01-16 | Mobileye Vision Technologies Ltd. | SYSTEMS AND METHODS FOR COMPRESSING TRAFFIC DATA |
| EP3857531A1 (en) * | 2018-09-27 | 2021-08-04 | KPIT Technologies Limited | A system for grid-based merge cut-in prediction and method thereof |
-
2022
- 2022-12-29 CN CN202211706702.2A patent/CN115688682B/en active Active
Patent Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN107247961A (en) * | 2017-05-10 | 2017-10-13 | 西安交通大学 | A kind of trajectory predictions method of application blurring trajectorie sequence |
| CN111654290A (en) * | 2020-04-24 | 2020-09-11 | 北京中交兴路车联网科技有限公司 | Method, device and equipment for compressing vehicle track data and storage medium |
| WO2021249020A1 (en) * | 2020-06-10 | 2021-12-16 | 华为技术有限公司 | Method and apparatus for predicting driving state, and terminal device |
| CN113911129A (en) * | 2021-11-23 | 2022-01-11 | 吉林大学 | Traffic vehicle intention identification method based on driving behavior generation mechanism |
| CN114368387A (en) * | 2021-12-21 | 2022-04-19 | 吉林大学 | Attention mechanism-based driver intention identification and vehicle track prediction method |
| CN115027484A (en) * | 2022-05-23 | 2022-09-09 | 吉林大学 | Human-computer fusion perception method for high-degree automatic driving |
Non-Patent Citations (6)
| Title |
|---|
| Arlei Silva,et al. .Prediction-based Online Trajectory Compression.《arXiv》.2016,全文. * |
| Qi Deng,et al..Improved driving behaviors prediction based on Fuzzy Logic-Hidden Markov Model (FL-HMM).《IEEE》.2018,全文. * |
| Yinglong Li,et al..fuzzyCom: Privacy-Aware Trajectory Data Compression Using Fuzzy Sets in Edge Vehicular Networks.《IEEE Xplore》.2022,第613-619页. * |
| 王献伟.基于自然驾驶数据的驾驶行为辨识和建模方法研究.《中国优秀硕士学位论文全文数据库 工程科技II辑》.2021,(2),C035-454. * |
| 陈煜 等.基于预测模型的轨迹数据压缩方法.《计算机应用》.2018,38(1),第171-175页. * |
| 面向群体行驶场景的时空信息融合车辆轨迹预测;李立 等;《交通运输工程学报》;全文 * |
Also Published As
| Publication number | Publication date |
|---|---|
| CN115688682A (en) | 2023-02-03 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| Tian et al. | Spatial‐temporal attention wavenet: A deep learning framework for traffic prediction considering spatial‐temporal dependencies | |
| Lv et al. | Deep-learning-enabled security issues in the internet of things | |
| Qiu et al. | Topological graph convolutional network-based urban traffic flow and density prediction | |
| James | Travel mode identification with GPS trajectories using wavelet transform and deep learning | |
| Oliveira-Neto et al. | Online license plate matching procedures using license-plate recognition machines and new weighted edit distance | |
| KR20210043516A (en) | Method and apparatus for training trajectory planning model, electronic device, storage medium and program | |
| CN112163446B (en) | Obstacle detection method and device, electronic equipment and storage medium | |
| Varghese et al. | Deep learning in transport studies: A meta-analysis on the prediction accuracy | |
| Katariya et al. | Deeptrack: Lightweight deep learning for vehicle trajectory prediction in highways | |
| Gollapalli et al. | A Neuro-Fuzzy Approach to Road Traffic Congestion Prediction. | |
| Song et al. | Learn travel time distribution with graph deep learning and generative adversarial network | |
| Wang et al. | Vehicle trajectory prediction algorithm in vehicular network | |
| Xiao et al. | Vehicle trajectory interpolation based on ensemble transfer regression | |
| CN113159403A (en) | Method and device for predicting pedestrian track at intersection | |
| Chellapandi et al. | Federated learning for connected and automated vehicles: A survey of existing approaches and challenges | |
| Dai et al. | Attention based simplified deep residual network for citywide crowd flows prediction | |
| Zhang et al. | Riskcast: social sensing based traffic risk forecasting via inductive multi-view learning | |
| Zhang et al. | Vehicle trajectory data mining for artificial intelligence and real-time traffic information extraction | |
| Feng et al. | A hybrid model integrating local and global spatial correlation for traffic prediction | |
| Chen et al. | CAE‐GAN: A hybrid model for vehicle trajectory prediction | |
| Aghabayk et al. | Exploring a local linear model tree approach to car‐following | |
| Zhao et al. | Traffic inflow and outflow forecasting by modeling intra-and inter-relationship between flows | |
| Cheong et al. | Missing traffic data imputation for artificial intelligence in intelligent transportation systems: review of methods, limitations, and challenges | |
| Wang et al. | Trajectory forecasting with neural networks: An empirical evaluation and a new hybrid model | |
| Dai et al. | ST-InNet: Deep spatio-temporal inception networks for traffic flow prediction in smart cities |
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 |