CN117392855B - Vehicle overrun overload probability identification method and system based on satellite positioning data - Google Patents

Vehicle overrun overload probability identification method and system based on satellite positioning data Download PDF

Info

Publication number
CN117392855B
CN117392855B CN202311706339.9A CN202311706339A CN117392855B CN 117392855 B CN117392855 B CN 117392855B CN 202311706339 A CN202311706339 A CN 202311706339A CN 117392855 B CN117392855 B CN 117392855B
Authority
CN
China
Prior art keywords
track
data
historical
vehicle
track 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
Application number
CN202311706339.9A
Other languages
Chinese (zh)
Other versions
CN117392855A (en
Inventor
黄小杰
Current Assignee (The listed assignees may be inaccurate. Google has not performed a legal analysis and makes no representation or warranty as to the accuracy of the list.)
Nanchang Institute of Technology
Original Assignee
Nanchang Institute of Technology
Priority date (The priority date 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 date listed.)
Filing date
Publication date
Application filed by Nanchang Institute of Technology filed Critical Nanchang Institute of Technology
Priority to CN202311706339.9A priority Critical patent/CN117392855B/en
Publication of CN117392855A publication Critical patent/CN117392855A/en
Application granted granted Critical
Publication of CN117392855B publication Critical patent/CN117392855B/en
Active legal-status Critical Current
Anticipated expiration legal-status Critical

Links

Classifications

    • G—PHYSICS
    • G08—SIGNALLING
    • G08G—TRAFFIC CONTROL SYSTEMS
    • G08G1/00—Traffic control systems for road vehicles
    • G08G1/01—Detecting movement of traffic to be counted or controlled
    • G08G1/0104—Measuring and analyzing of parameters relative to traffic conditions
    • G08G1/0125—Traffic data processing
    • G08G1/0129—Traffic data processing for creating historical data or processing based on historical data
    • G—PHYSICS
    • G08—SIGNALLING
    • G08G—TRAFFIC CONTROL SYSTEMS
    • G08G1/00—Traffic control systems for road vehicles
    • G08G1/01—Detecting movement of traffic to be counted or controlled
    • G08G1/052—Detecting movement of traffic to be counted or controlled with provision for determining speed or overspeed
    • H—ELECTRICITY
    • H04—ELECTRIC COMMUNICATION TECHNIQUE
    • H04W—WIRELESS COMMUNICATION NETWORKS
    • H04W4/00—Services specially adapted for wireless communication networks; Facilities therefor
    • H04W4/02—Services making use of location information
    • H04W4/025—Services making use of location information using location based information parameters
    • H—ELECTRICITY
    • H04—ELECTRIC COMMUNICATION TECHNIQUE
    • H04W—WIRELESS COMMUNICATION NETWORKS
    • H04W4/00—Services specially adapted for wireless communication networks; Facilities therefor
    • H04W4/02—Services making use of location information
    • H04W4/029—Location-based management or tracking services
    • H—ELECTRICITY
    • H04—ELECTRIC COMMUNICATION TECHNIQUE
    • H04W—WIRELESS COMMUNICATION NETWORKS
    • H04W4/00—Services specially adapted for wireless communication networks; Facilities therefor
    • H04W4/30—Services specially adapted for particular environments, situations or purposes
    • H04W4/40—Services specially adapted for particular environments, situations or purposes for vehicles, e.g. vehicle-to-pedestrians [V2P]
    • H—ELECTRICITY
    • H04—ELECTRIC COMMUNICATION TECHNIQUE
    • H04W—WIRELESS COMMUNICATION NETWORKS
    • H04W84/00—Network topologies
    • H04W84/02—Hierarchically pre-organised networks, e.g. paging networks, cellular networks, WLAN [Wireless Local Area Network] or WLL [Wireless Local Loop]
    • H04W84/04—Large scale networks; Deep hierarchical networks
    • H04W84/06—Airborne or Satellite Networks

Landscapes

  • Engineering & Computer Science (AREA)
  • Computer Networks & Wireless Communication (AREA)
  • Signal Processing (AREA)
  • Physics & Mathematics (AREA)
  • General Physics & Mathematics (AREA)
  • Chemical & Material Sciences (AREA)
  • Analytical Chemistry (AREA)
  • Astronomy & Astrophysics (AREA)
  • Navigation (AREA)

Abstract

The invention discloses a vehicle overrun overload probability identification method and system based on satellite positioning data, wherein the method comprises the following steps: calculating local average speed, overall average speed and local average acceleration of each track data in the track set, and recording the running time of each track data; calculating target distances between each historical track data and the current track data in the track set according to the overall average speed and the running time of the track data, and judging whether each target distance is smaller than a preset distance threshold value or not; if the distance is smaller than the preset distance threshold value, defining at least one historical track data corresponding to at least one target distance as balanced historical track data, and forming a balanced historical track set; a directed distance between the first empirical distribution and the second empirical distribution is calculated, and an overrun overload probability of the vehicle corresponding to the current trajectory data is calculated from the directed distance.

Description

Vehicle overrun overload probability identification method and system based on satellite positioning data
Technical Field
The invention belongs to the technical field of vehicle overrun overload probability identification, and particularly relates to a satellite positioning data-based vehicle overrun overload probability identification method and system.
Background
The prior art of the excessive overload research and judgment of the vehicle is mainly a hardware technology, and can accurately research and judge whether the vehicle is excessive or not according to a physical principle and sensing equipment, but the defect is that the research and judgment place of the excessive overload vehicle is basically fixed (the inspection equipment rarely moves for a long distance or is a vehicle-mounted detection equipment only arranged on a single fixed vehicle), the cost is higher, the coverage is smaller, the tracking and the research and judgment of the excessive overload of the vehicle are more difficult, and a vehicle driver can unload goods or bypass an inspection site to avoid inspection before the inspection site.
Therefore, in combination with the existing hardware technology, a freight vehicle information management platform is also commonly used for checking and managing the overrun overload of the vehicle. Some data mining and AI technologies are adopted by some management platforms, and the excessive overload of the vehicle is pre-researched, judged and tracked by the data collected by the platforms, for example, the video data of the vehicle is collected, whether the excessive overload of the vehicle is caused is pre-judged by the image processing technology (equivalent to the observation of human eyes), or the bus data of the vehicle is collected, and the fuel consumption, the acceleration and the like during the running of the vehicle are analyzed so as to pre-research whether the excessive overload of the vehicle is caused. Through the data and the corresponding data technology, the overrun overload condition of the vehicle can be pre-researched and judged, although the pre-judging accuracy is not very high, whether the vehicle is overrun overload is still required to be further confirmed through the hardware technology, tracking management and guiding inspection are realized, inspection personnel can have better pertinence to the overrun overload inspection of the vehicle, good warning performance is achieved, a large amount of manpower and material resources can be reduced, and the inspection efficiency of the overrun overload is improved. The disadvantage of pre-judging overrun overload by the data technology is that: the accuracy of the pre-judgment is not high, and the information management platform of the freight vehicle cannot conveniently obtain the image data, bus data and the like of the related vehicle, so that the application range of the information management platform is also limited more because the data is difficult to obtain, and the information management platform is difficult to generate wide benefits; moreover, the data has complex structure, the bus standards of different automobile manufacturers are not completely the same, the technical complexity of pre-judging the overrun overload through the data and the data technology is higher, and the cost of data management and utilization is increased.
Disclosure of Invention
The invention provides a vehicle overrun overload probability identification method and system based on satellite positioning data, which are used for reducing a threshold for data acquisition, reducing the cost of data management and utilization, and expanding the range of tracking inspection overrun overload, so that the inspection efficiency and the assisted traffic safety are improved.
In a first aspect, the present invention provides a method for identifying an overrun overload probability of a vehicle based on satellite positioning data, including:
acquiring current track data of a vehicle in a current period and historical track data of the vehicle in different historical periods, and forming a track setWherein->For the current trajectory data of the current period, +.>Is->History trace data for each history period, +.>；
Calculating local average speed, global average speed and local average acceleration of each track data in the track set, and recording running time of each track data, wherein the track data comprises a vehicle identification codeDriver identification codeVehicle travel time->Longitudes where the vehicle is located->Latitude of vehicle>And the altitude of the vehicle->；
Calculating target distances between each historical track data and the current track data in the track set according to the overall average speed and the running time of the track data, and judging whether each target distance is smaller than a preset distance threshold value or not;
If the at least one target distance is smaller than the preset distance threshold value, defining at least one historical track data corresponding to the at least one target distance as balanced historical track data, andforming a balanced historical track setWherein->Is->Equalizing history trace data for each history period, +.>Is->Equalizing history trace data for each history period, +.>Is->Equalizing historical track data for each historical period;
computing a first empirical distribution of local average acceleration of the current trajectory data and the set of equalized historical trajectoriesAnd calculating the overrun overload probability of the vehicle corresponding to the current track data according to the directed distance.
In a second aspect, the present invention provides a satellite positioning data-based vehicle overrun overload probability recognition system, comprising:
an acquisition module configured to acquire current track data of the vehicle in a current period and historical track data of the vehicle in different historical periods, and form a track setWherein->For the current trajectory data of the current period, +.>Is the firstHistory trace data for each history period, +. >；
A first calculation module configured to calculate a local average speed, a global average speed, and a local average acceleration of each track data in the track set, and record a running duration of each track data, where the track data includes a vehicle identification codeDriver identification code->Vehicle travel time->Longitudes where the vehicle is located->Latitude of vehicle>And the altitude of the vehicle->；
The judging module is configured to calculate target distances between each historical track data and the current track data in the track set according to the overall average speed and the running time of the track data, and judge whether each target distance is smaller than a preset distance threshold value or not;
a definition module configured to define at least one historical track data corresponding to at least one target distance as an equalized historical track if the at least one target distance is less than a preset distance thresholdData and form a balanced historical track setWherein->Is->Equalizing history trace data for each history period, +.>Is->Equalizing history trace data for each history period, +.>Is->Equalizing historical track data for each historical period;
a second calculation module configured to calculate a first experience distribution of the current trajectory data and the equalized historical trajectory set And calculating the overrun overload probability of the vehicle corresponding to the current track data according to the directed distance.
In a third aspect, there is provided an electronic device, comprising: the system comprises at least one processor and a memory communicatively connected with the at least one processor, wherein the memory stores instructions executable by the at least one processor to enable the at least one processor to perform the steps of the satellite positioning data based vehicle overrun overload probability identification method of any one of the embodiments of the present invention.
In a fourth aspect, the present invention also provides a computer readable storage medium having stored thereon a computer program, which when executed by a processor, causes the processor to perform the steps of the satellite positioning data based vehicle overrun overload probability identification method according to any of the embodiments of the present invention.
The vehicle overrun overload probability identification method and system based on satellite positioning data have the following beneficial effects:
the method comprises the steps of obtaining current track data of a vehicle in a current period and historical track data in different historical periods, forming a track set, calculating local average speed, global average speed and local average acceleration of each track data in the track set, recording running time of each track data, calculating target distances between each historical track data and the current track data in the track set according to the global average speed and the running time of the track data, judging whether each target distance is smaller than a preset distance threshold, defining at least one historical track data corresponding to at least one target distance as balanced historical track data if at least one target distance is smaller than the preset distance threshold, forming a balanced historical track set, calculating a directed distance between a first experience distribution of the local average acceleration of the current track data and a second experience distribution of the local average acceleration of each balanced historical track data in the balanced historical track set, calculating an overrun overload probability of the vehicle corresponding to the current track data according to the directed distance, reducing data management and utilization costs, expanding a tracking power assisting overload range, and accordingly improving traffic safety.
Drawings
In order to more clearly illustrate the technical solutions of the embodiments of the present invention, the drawings required for the description of the embodiments will be briefly described below, and it is obvious that the drawings in the following description are 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 method for identifying a vehicle overrun overload probability based on satellite positioning data according to an embodiment of the present invention;
FIG. 2 is a diagram of a second empirical distribution of local average acceleration of equalized historical trajectory data for one embodiment of the invention;
FIG. 3 is a graph showing the directed distance between a first empirical distribution of local average acceleration of current trajectory data and a second empirical distribution of local average acceleration of equalized historical trajectory data for one embodiment of the invention;
FIG. 4 is a graph showing a variation of the overrun overload probability of a vehicle according to an embodiment of the present invention;
FIG. 5 is a block diagram of a vehicle overrun overload probability recognition system based on satellite positioning data according to an embodiment of the present invention;
Fig. 6 is a schematic structural diagram of an electronic device according to an embodiment of the present 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. 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.
Referring to fig. 1, a flowchart of a vehicle overrun overload probability identification method based on satellite positioning data is shown.
As shown in fig. 1, the method for identifying the overrun overload probability of the vehicle based on satellite positioning data specifically comprises the following steps:
step S101, acquiring current track data of the vehicle at the current moment and historical track data at different historical moments, and forming a track setWherein->For the current track data at the current moment, +.>Is->History trace data for each history instant +.>。
Satellite positioning data of a plurality of different historical periods of the vehicle and satellite positioning data of a period just elapsed in the current running process of the vehicle are acquired and stored, wherein one period corresponds to one track, and the satellite positioning data can be respectively called a historical track (data) and a current track (data). The history track refers to the original running track of the vehicle, and the current track is the track which the vehicle just passes by when running. We intend to estimate the probability of overrun overload of the vehicle by comparing the current trajectory of the vehicle with the historical trajectory.
The positioning data of the traveling vehicle at a certain fixed time is data in the following format, and includes 6 fields, and the meaning is as shown in table 1 below.
The symbols are as follows:representing the vehicle identification code, the vehicle driver identification code, the vehicle travel time, the vehicle longitude, the vehicle latitude and the vehicle altitude, respectively.
Each track stores recording data in chronological order.Indicating the vehicle and driver identification code as +.>Is>First>Positioning data of individual moments, wherein->，/>. Adjacent->Time and->The time interval of each moment is generally 5 to 20 seconds, and sparse satellite positioning data on the running track of the vehicle is obtained.
For example, two of the trajectories, i.eTheir satellite positioning data patterns are as follows in table 2.
，
The data can be the positioning data of different vehicles and different drivers when the data are collected, and the positioning data of the same vehicle and the same driver are classified into one type only by classifying and sorting the data according to the type of the vehicle and the driver respectively, namely the track data.
The track data is cleaned and tidied, and data with small or large distance between adjacent time points is removed, namely, points with small or large position variation of the vehicle are changed, and the time points are near stationary time points or abnormal positioning time points of the vehicle.
Step S102, calculating local average speed, global average speed and local average acceleration of each track data in the track set, and recording each track dataWherein the track data includes a vehicle identification codeDriver identification code->Vehicle travel time->Longitudes where the vehicle is located->Latitude of vehicle>And the altitude of the vehicle->。
In this step, the expression for calculating the local average speed of each track data in the track set is:
，
in the method, in the process of the invention,for the speed of the kth track at the ith moment, etc.>Longitude at time i+1 of kth track, +.>Longitude at the ith moment of the kth track, < >>For the latitude at the (i+1) th moment of the kth track,/->For the latitude at the ith moment of the kth track,/-, etc.>For the elevation of the kth track at time i+1,>for the elevation of the kth track at the ith moment, < >>For the travel time value at the (i+1) th track, the number ± is +>The travel time value at the i-th moment of the kth track.
The expression for calculating the overall average speed of each track data in the track set is as follows:
，
in the method, in the process of the invention,is the overall average speed of the kth trace;
，
in the method, in the process of the invention,for the travel time value of the kth track at the nth time,/->The running time value of the kth track at the 1 st moment;
，
In the method, in the process of the invention,for the speed of the kth track at the ith moment, etc.>Longitude at time i+1 of kth track, +.>Longitude at the ith moment of the kth track, < >>For the latitude at the (i+1) th moment of the kth track,/->For the latitude at the ith moment of the kth track,/-, etc.>For the elevation of the kth track at time i+1,>for the elevation of the kth track at the ith moment, < >>For the travel time value at the (i+1) th track, the number ± is +>The travel time value at the i-th moment of the kth track.
The expression for calculating the local average acceleration of each track data in the track set is as follows:
，
in the method, in the process of the invention,acceleration at the ith moment of the kth track, < >>For the speed of the kth track at the ith moment, etc.>The (i+1) th moment of the kth trackLongitude of->Longitude at the ith moment of the kth track, < >>For the latitude at the (i+1) th moment of the kth track,/->For the latitude at the ith moment of the kth track,/-, etc.>For the elevation of the kth track at time i+1,>for the elevation of the kth track at the ith moment, < >>For the travel time value at the (i+1) th track, the number ± is +>For the travel time value at the ith moment of the kth track,/for the kth track>For the travel time value at the kth track, i-1 th moment, < >>Longitude at i-1 time for kth track,/, for>For the latitude at the i-1 th moment of the kth track,/- >The altitude at the i-1 th moment of the kth trace.
Step S103, calculating target distances between each historical track data and the current track data in the track set according to the overall average speed and the running time of the track data, and judging whether each target distance is smaller than a preset distance threshold value.
In this step, it is assumed that the overall average speed and the running time length of each history trace data are respectivelyAnd->，And the overall average speed and the running time length of the current trajectory data are +.>And->；
Calculating target distances between each historical track data and current track data in the track set, wherein the expression for calculating the target distances is as follows:
，
in the method, in the process of the invention,for the current track data, +.>Is->Historical track data.
Specifically, the preset distance threshold is 0.1, i.eMay also use +.>Instead, wherein->Is a small positive number whose value can be adjusted according to the specific data, and is a pending parameter.
Step S104, if at least one target distance is smaller than a preset distance threshold, defining at least one history track data corresponding to the at least one target distance as balanced history track data, and forming a balanced history track set Wherein->Is->Equalizing historical track data of individual historical moments, +.>Is->Equalizing historical track data of individual historical moments, +.>Is->And equalizing the historical track data at each historical moment.
The speed of the same driver driving the same vehicle implies various information such as the environment, road condition, vehicle condition and the like of the vehicle, for example, the high running speed of the vehicle may mean that the road is smooth, the speed limit of the road is high, the driver is more urgent and the like, and the low running speed of the vehicle may mean that the speed limit of the road is low, overcast and rainy weather and the like. Therefore, the running speed of the vehicle can be used as a comprehensive characterization index of various information such as the running environment of the vehicle, road conditions, vehicle conditions and the like. The fact that the overall average speeds of the vehicles are similar means that the comprehensive influences of various factors such as the running environment, road conditions and vehicle conditions of the vehicles on the running states and positioning data of the vehicles are similar, and therefore the smaller the distance between tracks is.
The distance between tracks takes the running time of the tracks into consideration, because when the overall average speeds of the two tracks are the same, if the two tracks are more similar in the length, the comprehensive influence of various factors such as the running environment of the vehicle, road conditions, vehicle conditions and the like on the running state of the vehicle is more similar in the influence on the vehicle positioning data. For example, the overall average speeds of the three tracks are the same, and the time periods for them are 1 minute, 100 minutes, and 100 minutes, respectively, then it is apparent that the closer the overall influencing factors experienced by the two 100 minute vehicle tracks are, the more similar the overall average speed is and the longer the time period that is examined.
The fact that the distances between the historical balanced track and the current track are approximately zero means that various influence factors have similar effects on speed, so that the comprehensive influence on positioning data is similar, the influence of the factors is balanced to a certain extent, the influence is identical, namely the influence of the factors does not have influence on track data, and the influence is the reason that the historical balanced track data is called as balanced historical track data in the application. And reconstructing proper characteristics related to overrun overload to analyze the track data, and if the track data are different, highlighting the overrun overload condition of the vehicle.
Step S105, calculating the first experience distribution of the local average acceleration of the current track data and the balanced historical track setAnd calculating the overrun overload probability of the vehicle corresponding to the current track data according to the directed distance.
The local average acceleration may reflect an overrun overload situation of the driving vehicle, for example, small acceleration means large vehicle load, but single or several local accelerations are insufficient to characterize the overrun overload situation of the vehicle, so that the overrun overload of the vehicle is characterized by an empirical distribution of all local average accelerations on the track.
Let the local average acceleration of the current trajectory data be sharedIndividual, i.e.)>Count setFall into the interval->The number of elements of (2) divided by +.>Obtaining a first experience distribution of local average acceleration of the current track data;
then the track is balanced by historyThe empirical distribution of local average accelerations of (a) is calculated as follows:
local average acceleration sharing with balanced historical track dataIndividual, i.e.)>Count setFall into the interval->The number of elements of (2) divided by +.>Obtaining a second empirical distribution of local average acceleration of the equalized historical trajectory data; the first empirical distribution and the second empirical distribution are shown in figure 2, are stepwise, monotonically non-decreasing and right continuous.
The directed distance between the first empirical distribution and each of the second empirical distributions, i.e., the directed maximum spacing of points on the two empirical distribution function images, is calculated as shown in fig. 3.
Wherein the expression for calculating the directed distance is:
，
in the method, in the process of the invention,for the first trial distribution ++>For the second empirical distribution, +.>Is an empirically distributed argument, ++>Is a real set, i.e.)>Is described.
To calculateFor example, ask->At maximum, the sum of forward distances, which does not need to be distributed over the local average acceleration experience +. >All->This is not possible. It is noted that the empirical distribution function is a step function, which is in fact just +.>Walk->And (3) obtaining the product.
Wherein,track +.>And track->Local average acceleration of (c) may be:
，
the empirical distribution of the local average acceleration can reflect the overall situation of the vehicle acceleration contained in the vehicle track, and the directional distance between the empirical distribution can reflect the difference between the acceleration of the current track and the acceleration of the historical equilibrium track:
if positive, the current track distribution function value (cumulative probability) is large, i.e. +.>Is more concentrated at small values, meaning that the current trajectory +.>The acceleration condition of the vehicle is smaller than the acceleration of the historical equilibrium track, and the possibility of overrun and overload of the vehicle is larger;
negative, the current trajectory distribution function value (cumulative probability) is small, i.e. +.>Is more concentrated at large values, meaning that the current trajectory +.>Acceleration of acceleration condition versus history equalization trajectoryThe greater the overall degree, the less likely the vehicle will be overloaded.
Is provided withIs the current track +.>Track equalization with histories->The directional distances of the local average acceleration empirical distribution of (2) are divided into two groups according to positive directional distances and negative directional distances, and the sum of all the positive directional distances is recorded as +. >The absolute value of all negative directed distances sum is recorded as +.>The overrun overload probability of the vehicle is marked as +.>The expression of the overrun overload probability of the vehicle is:
，
in the method, in the process of the invention,is a standard normal distribution function, +.>The sum of the positive distances of the empirical distribution of local average accelerations,absolute value of the sum of negative directional distances of the empirical distribution of local average accelerations +.>For undetermined parameters, e.g. based on vehicle model, historical dataAnd the like.
The functional image of (2) is shown in figure 4.
Equal to 1 means that the local average acceleration in the history-equalized track data is greater than the current track +.>Is less than the current trace +.>The situation of (2) is basically the same, the local average acceleration of the current track is at the history equal level, and it is difficult to judge whether it is overloaded or not, so the probability is +.>；
Far greater than 1 means that the local average acceleration of the current track is far less than the historical overall level, the acceleration is small, the possibility of overrun overload is high, +.>；
Much smaller than 1 (near zero), meaning that the local average acceleration of the current trajectory is much greater than the overall level of the history, the acceleration is large, the possibility of overrun overload is small, +.>。
The value of (2) is dependent on a number of factors>Determining, and the positioning data of the history equalizing trajectory data are substantially similar, so that the respective factors +. >For->Is approximately equal in influence, so->Should approximately follow a normal distribution, but +.>The value of (2) is->Rather thanTherefore, the standard normal distribution function +.>The transformation is performed to obtain->Is a function of the distribution of (a).
To->The transformation has various modes and can be adjusted according to the specific vehicle type and service condition.
In a specific embodiment, two tracks obtained by driving a muck truck by a driver on a road similar to plain and straight line are selected as historical tracks, and the other track is selected as the current track (the overload probability of the muck truck is calculated, whether overload exists or not is predicted, and the muck truck does not have the overload condition such as ultra-high load condition, ultra-wide condition and the like). In order to check the calculation result, whether the muck truck is overloaded in three running tracks is known in advance so as to observe whether the calculation result coincides with the actual situation.
The positioning data are acquired at intervals of about 10 seconds, the common numbers of drivers and the muck trucks are omitted, the time is renumbered sequentially, the plain straight road on which the muck trucks run is taken as one coordinate axis, and the other two coordinates are approximately 0.
Two historical traces are shown in tables a, b, and c:
step 1, calculating local average speed, global average speed, local average acceleration and local average acceleration distribution law of historical tracks and current tracks of the truck, and recording the running time of each track.
By historical trackFor example, the local average speed between the first two positioning data is:
，
similarly, the local average velocity between other two adjacent anchor points is calculated, for example,the calculation results are shown in the second column of table 3 below.
By historical trackFor example, the local average acceleration (here not absolute value, so the calculation is signed) between its first three positioning data is:
，
similarly, the local average acceleration between the other three adjacent anchor points is calculated, for example,the calculation results are shown in the third column of Table 3. />
Calculating historical trajectoriesIs +.>；
Calculating historical trajectoriesThe local average acceleration distribution of (2) is shown in table 4.
，
Recording historical track of truckIs>。
Similar to historical trajectoriesThe method can obtain: historical track of truck->Local average speed, global average speed, local average acceleration distribution law, and operation time period. Such as table 5.
/>
Historical track of truckIs>；
Calculating historical trajectories for trucksThe local average acceleration distribution of (2) is shown in table 6.
Historical track of truckIs>。
Current track of truckLocal average speed, global average speed, local average acceleration distribution law, and operation time period. Such as table 7.
Current track of truckIs>；
Calculating the current track of the truckThe local average acceleration distribution of (2) is shown in table 8.
Current track of truckIs>。
And step 2, calculating the distance between the historical track and the current track of the truck, and selecting all the historical tracks with the distance from the current track smaller than a specified value, namely selecting an equilibrium historical track.
To calculate historical trajectoriesIs +.>The distance between them is exemplified by:
，
similarly, historical trajectoriesIs +.>The distance between the two is as follows:
，/>
here, the convention is that whenever the inter-track distance is less than 0.1, it is selected as the equalization track, so the equalization history track set is。
Step 3, calculating the balanced historical trackEmpirical distribution of local average acceleration and current trajectory +.>Directional distances of the local average acceleration empirical distribution. As shown in table 9:
thus, the current trackAbsolute value of the sum of positive directional distances from the empirical distribution of local average acceleration of the equilibrium history trajectory, +.>The method comprises the steps of carrying out a first treatment on the surface of the Current track->Absolute value of the negative directional distance sum from the equilibrium history trace local average acceleration experience distribution: />。
Step 4. Estimating the current trackAnd (5) overload probability of the truck.
，
The probability of overload of the muck truck is 80.23%, and the muck truck is prone to be judged to be overloaded and is matched with the actual record.
The above examples show that the overall average speed is fast and does not represent that no overrun overload exists, various interference factors for judging the overrun overload should be "equalized" as much as possible by utilizing the overall average speed, and then information of the overrun overload of the truck should be mined by utilizing the distribution characteristic of local average acceleration (only a certain local average acceleration cannot be seen, but the distribution of the whole local average acceleration should be seen).
Referring to fig. 5, a block diagram of a vehicle overrun overload probability recognition system based on satellite positioning data is shown.
As shown in fig. 5, the vehicle overrun overload probability recognition system 200 includes an acquisition module 210, a first calculation module 220, a judgment module 230, a definition module 240, and a second calculation module 250.
Wherein the acquisition module 210 is configured to acquire current track data of the vehicle at the current time and historical track data at different historical times, and form a track set，/>For the current track data at the current moment, +.>Is->History trace data for each history instant +.>The method comprises the steps of carrying out a first treatment on the surface of the A first calculation module 220 configured to calculate a local average speed, a global average speed and a local average acceleration of each track data in the track set, and record a running time of each track data, wherein the track data comprises a vehicle identification code- >Driver identification code->Vehicle travel time->Longitudes where the vehicle is located->Latitude of vehicle>And the altitude of the vehicle->The method comprises the steps of carrying out a first treatment on the surface of the The judging module 230 is configured to calculate a target distance between each historical track data and the current track data in the track set according to the overall average speed and the running time of the track data, and judge whether each target distance is smaller than a preset distance threshold; a definition module 240 configured to define at least one history track data corresponding to at least one target distance as balanced history track data and form a balanced history track set ∈if the at least one target distance is less than a preset distance threshold>Wherein->Is->Equalizing historical track data of individual historical moments, +.>Is->Equalizing historical track data of individual historical moments, +.>Is->Equalizing historical track data at each historical moment; a second calculation module 250 configured to calculate a first experience distribution of the current trajectory data and the balanced historical trajectory set +.>And calculating the overrun overload probability of the vehicle corresponding to the current track data according to the directed distance.
It should be understood that the modules depicted in fig. 5 correspond to the various steps in the method described with reference to fig. 1. Thus, the operations and features described above for the method and the corresponding technical effects are equally applicable to the modules in fig. 5, and are not described here again.
In other embodiments, the present invention further provides a computer readable storage medium, on which a computer program is stored, where the program instructions, when executed by a processor, cause the processor to perform the method for identifying a vehicle overrun overload probability based on satellite positioning data in any of the above method embodiments;
as one embodiment, the computer-readable storage medium of the present invention stores computer-executable instructions configured to:
acquiring current track data of a vehicle at a current moment and historical track data at different historical moments, and forming a track setWherein->For the current track data at the current moment, +.>Is->History trace data for each history instant +.>；
Calculating local average speed, global average speed and local average acceleration of each track data in the track set, and recording running time of each track data, wherein the track data comprises a vehicle identification code Driver identification codeVehicle travel time->Longitudes where the vehicle is located->Latitude of vehicle>And the altitude of the vehicle->；
Calculating target distances between each historical track data and the current track data in the track set according to the overall average speed and the running time of the track data, and judging whether each target distance is smaller than a preset distance threshold value or not;
if the at least one target distance is smaller than the preset distance threshold value, defining at least one historical track data corresponding to the at least one target distance as balanced historical track data, and forming a balanced historical track setWherein->Is->Equalizing historical track data of individual historical moments, +.>Is->Equalizing historical track data of individual historical moments, +.>Is->Equalizing historical track data at each historical moment;
computing a first empirical distribution of local average acceleration of the current trajectory data and the set of equalized historical trajectoriesAnd calculating the overrun overload probability of the vehicle corresponding to the current track data according to the directed distance.
The computer readable storage medium may include a storage program area and a storage data area, wherein the storage program area may store an operating system, at least one application program required for a function; the stored data area may store data created from the use of a satellite positioning data based vehicle overrun overload probability identification system, and the like. In addition, the computer-readable storage medium may include high-speed random access memory, and may also include memory, such as at least one magnetic disk storage device, flash memory device, or other non-volatile solid-state storage device. In some embodiments, the computer readable storage medium optionally includes memory remotely located relative to the processor, the remote memory being connectable to the satellite positioning data based vehicle overrun overload probability identification system via a network. Examples of such networks include, but are not limited to, the internet, intranets, local area networks, mobile communication networks, and combinations thereof.
Fig. 6 is a schematic structural diagram of an electronic device according to an embodiment of the present invention, as shown in fig. 6, where the device includes: a processor 310 and a memory 320. The electronic device may further include: an input device 330 and an output device 340. The processor 310, memory 320, input device 330, and output device 340 may be connected by a bus or other means, for example in fig. 6. Memory 320 is the computer-readable storage medium described above. The processor 310 executes various functional applications of the server and data processing by running non-volatile software programs, instructions and modules stored in the memory 320, i.e. implements the above-described method embodiment of identifying the overrun overload probability of a vehicle based on satellite positioning data. The input device 330 may receive input numeric or character information and generate key signal inputs related to user settings and function control of the satellite positioning data based vehicle overrun overload probability identification system. The output device 340 may include a display device such as a display screen.
The electronic equipment can execute the method provided by the embodiment of the invention, and has the corresponding functional modules and beneficial effects of the execution method. Technical details not described in detail in this embodiment may be found in the methods provided in the embodiments of the present invention.
As an implementation manner, the electronic device is applied to a vehicle overrun overload probability identification system based on satellite positioning data, and is used for a client, and the electronic device comprises: at least one processor; and a memory communicatively coupled to the at least one processor; wherein the memory stores instructions executable by the at least one processor, the instructions being executable by the at least one processor to enable the at least one processor to:
acquiring current track data of a vehicle at a current moment and historical track data at different historical moments, and forming a track setWherein->For the current track data at the current moment, +.>Is->History trace data for each history instant +.>；
Calculating local average speed, global average speed and local average acceleration of each track data in the track set, and recording running time of each track data, wherein the track data comprises a vehicle identification codeDriver identification codeVehicle travel time->Longitudes where the vehicle is located->Latitude of vehicle>And the altitude of the vehicle->The method comprises the steps of carrying out a first treatment on the surface of the Calculating target distances between each historical track data and the current track data in the track set according to the overall average speed and the running time of the track data, and judging whether each target distance is smaller than a preset distance threshold value or not;
If the at least one target distance is smaller than the preset distance threshold value, defining at least one historical track data corresponding to the at least one target distance as balanced historical track data, and forming a balanced historical track setWherein->Is->Equalizing historical track data of individual historical moments, +.>Is->Equalizing historical track data of individual historical moments, +.>Is->Equalizing historical track data at each historical moment;
computing a first empirical distribution of local average acceleration of the current trajectory data and the set of equalized historical trajectoriesAnd calculating the overrun overload probability of the vehicle corresponding to the current track data according to the directed distance.
From the above description of the embodiments, it will be apparent to those skilled in the art that the embodiments may be implemented by means of software plus necessary general hardware platforms, or of course may be implemented by means of hardware. Based on such understanding, the foregoing technical solutions may be embodied essentially or in part in the form of a software product, which may be stored in a computer-readable storage medium, such as a ROM/RAM, a magnetic disk, an optical disk, etc., including several instructions to cause a computer device (which may be a personal computer, a server, or a network device, etc.) to perform the various embodiments or methods of some parts of the embodiments.
Finally, it should be noted that: the above embodiments are only for illustrating the technical solution of the present invention, and are not limiting; although the invention has been described in detail with reference to the foregoing embodiments, it will be understood by those of ordinary skill in the art that: the technical scheme described in the foregoing embodiments can be modified or some technical features thereof can be replaced by equivalents; such modifications and substitutions do not depart from the spirit and scope of the technical solutions of the embodiments of the present invention.

Claims (7)

1. The method for identifying the overrun overload probability of the vehicle based on the satellite positioning data is characterized by comprising the following steps of:
acquiring current track data of a vehicle in a current period and historical track data of the vehicle in different historical periods, and forming a track setWherein->For the current trajectory data of the current period, +.>Is->History trace data for each history period, +.>；
Calculating local average speed, global average speed and local average acceleration of each track data in the track set, and recording running time of each track data, wherein the track data comprises a vehicle identification codeDriver identification code->Vehicle travel time- >Longitudes where the vehicle is located->Latitude of vehicle>And the altitude of the vehicle->；
Calculating target distances between each historical track data and the current track data in the track set according to the overall average speed and the running time length of the track data, and judging whether each target distance is smaller than a preset distance threshold value, wherein the calculating the target distances between each historical track data and the current track data in the track set according to the overall average speed and the running time length of the track data comprises the following steps:
setting the overall average speed and the running time of each historical track data asAnd->，/>And the overall average speed and the running time length of the current trajectory data are +.>And->；
Calculating target distances between each historical track data and current track data in the track set, wherein the expression for calculating the target distances is as follows:
，
in the method, in the process of the invention,for the current track data, +.>Is->Historical track data;
if the at least one target distance is smaller than the preset distance threshold value, defining at least one historical track data corresponding to the at least one target distance as balanced historical track data, and forming a balanced historical track set Wherein->Is->Equalizing history trace data for each history period, +.>Is->The equalized historical track data for each historical period,is->Equalizing historical track data for each historical period;
computing a first empirical distribution of local average acceleration of the current trajectory data and the set of equalized historical trajectoriesDirected distances between second empirical distributions of local average accelerations of respective equilibrium historical track data, and calculating an overrun overload probability of a vehicle corresponding to the current track data according to the directed distances, wherein the calculation of the first empirical distribution of the current track data and the equilibrium historical track set->The directed distance between the second empirical distributions of the respective equalization history trajectory data comprises:
let the local average acceleration of the current trajectory data be sharedIndividual, i.e.)>Count set->Fall into the interval->The number of elements of (2) divided by +.>Obtaining a first experience distribution of local average acceleration of the current track data;
local average acceleration sharing with balanced historical track dataIndividual, i.e.)>Count setFall into the interval->The number of elements of (2) divided by +.>Obtaining a second empirical distribution of local average acceleration of the equalized historical trajectory data;
Calculating a directed distance between the first empirical distribution and each second empirical distribution, wherein calculating the directed distance is expressed as:
，
in the method, in the process of the invention,for the first trial distribution ++>For the second empirical distribution, +.>Is an empirically distributed argument, ++>Is a real set, i.e.)>Is a range of variation of (2);
the expression of the overrun overload probability of the vehicle corresponding to the current track data is calculated as follows:
，
in the method, in the process of the invention,is a standard normal distribution function, +.>Sum of forward distances, which is an empirical distribution of local average accelerations, +.>Absolute value of the sum of negative directional distances of the empirical distribution of local average accelerations +.>Is a pending parameter.
2. The method for identifying the overrun overload probability of a vehicle based on satellite positioning data according to claim 1, wherein the expression for calculating the local average speed of each track data in the track set is:
，
in the method, in the process of the invention,for the speed of the kth track at the ith moment, etc.>Longitude at time i+1 of kth track, +.>Longitude at the ith moment of the kth track, < >>Weft yarn at (i+1) th moment of kth trackDegree (f)>For the latitude at the i-th moment of the kth track,for the elevation of the kth track at time i+1, >For the elevation of the kth track at the ith moment, < >>For the travel time value at the (i+1) th track, the number ± is +>The travel time value at the i-th moment of the kth track.
3. The method for identifying the overrun overload probability of a vehicle based on satellite positioning data according to claim 1, wherein the expression for calculating the overall average speed of each track data in the track set is:
，
in the method, in the process of the invention,is the overall average speed of the kth trace;
，
in the method, in the process of the invention,for the travel time value of the kth track at the nth time,/->The running time value of the kth track at the 1 st moment;
，
in the method, in the process of the invention,for the speed of the kth track at the ith moment, etc.>Longitude at time i+1 of kth track, +.>Longitude at the ith moment of the kth track, < >>For the latitude at the (i+1) th moment of the kth track,/->For the latitude at the i-th moment of the kth track,for the elevation of the kth track at time i+1,>for the elevation of the kth track at the ith moment, < >>For the travel time value at the (i+1) th track, the number ± is +>The travel time value at the i-th moment of the kth track.
4. The method for identifying the overrun overload probability of a vehicle based on satellite positioning data according to claim 1, wherein the expression for calculating the local average acceleration of each track data in the track set is:
，
In the method, in the process of the invention,acceleration at the ith moment of the kth track, < >>For the speed of the kth track at the ith moment, etc.>Longitude at time i+1 of kth track, +.>Longitude at the ith moment of the kth track, < >>For the latitude at the i+1 time of the kth track,for the latitude at the ith moment of the kth track,/-, etc.>For the elevation of the kth track at time i+1,>for the elevation of the kth track at the ith moment, < >>For the travel time value at the (i+1) th track, the number ± is +>The travel time value at the i-th moment of the kth track,for the travel time value at the kth track, i-1 th moment, < >>Longitude at i-1 time for kth track,/, for>For the latitude at the i-1 th moment of the kth track,/->The altitude at the i-1 th moment of the kth trace.
5. A satellite positioning data based vehicle overrun overload probability identification system, comprising:
an acquisition module configured to acquire current track data of the vehicle in a current period and historical track data of the vehicle in different historical periods, and form a track setWherein->For the current trajectory data of the current period, +.>Is->History trace data for each history period, +.>；
A first calculation module configured to calculate a local average of the respective trajectory data in the trajectory set Speed, overall average speed and local average acceleration, and recording the running time of each track data, wherein the track data comprises a vehicle identification codeDriver identification code->Vehicle travel time->Longitudes where the vehicle is located->Latitude of vehicle>And the altitude at which the vehicle is located；
The judging module is configured to calculate a target distance between each historical track data and the current track data in the track set according to the overall average speed and the running time length of the track data, and judge whether each target distance is smaller than a preset distance threshold value, wherein the calculating the target distance between each historical track data and the current track data in the track set according to the overall average speed and the running time length of the track data comprises the following steps:
setting the overall average speed and the running time of each historical track data asAnd->，/>And current track data +.>Is +.about.the overall average speed and the run length, respectively>And->；
Calculating target distances between each historical track data and current track data in the track set, wherein the expression for calculating the target distances is as follows:
，
in the method, in the process of the invention,for the current track data, +.>Is->Historical track data;
A definition module configured to define at least one historical track data corresponding to at least one target distance as balanced historical track data and form a balanced historical track set if the at least one target distance is smaller than a preset distance thresholdWherein->Is->Equalizing history trace data for each history period, +.>Is->Equalizing history trace data for each history period, +.>Is->Equalizing historical track data for each historical period;
a second calculation module configured to calculate a first experience distribution of the current trajectory data and the equalized historical trajectory setThe second experience distribution of the equalization history track data, and calculating the overrun overload probability of the vehicle corresponding to the current track data according to the directed distance, wherein the calculation of the first experience distribution of the current track data and the equalization history track set>The directed distance between the second empirical distributions of the respective equalization history trajectory data comprises:
let the local average acceleration of the current trajectory data be sharedIndividual, i.e.)>Count set->Fall into the interval->The number of elements of (2) divided by +.>Obtaining a first experience distribution of local average acceleration of the current track data;
Local average acceleration sharing with balanced historical track dataIndividual, i.e.)>Count setFall into the interval->The number of elements of (2) divided by +.>Obtaining a second empirical distribution of local average acceleration of the equalized historical trajectory data;
calculating a directed distance between the first empirical distribution and each second empirical distribution, wherein calculating the directed distance is expressed as:
，
in the method, in the process of the invention,for the first trial distribution ++>For the second empirical distribution, +.>Is an empirically distributed argument, ++>Is a real set, i.e.)>Is a range of variation of (2);
the expression of the overrun overload probability of the vehicle corresponding to the current track data is calculated as follows:
，
in the method, in the process of the invention,is a standard normal distribution function, +.>Sum of forward distances, which is an empirical distribution of local average accelerations, +.>Absolute value of the sum of negative directional distances of the empirical distribution of local average accelerations +.>Is a pending parameter.
6. An electronic device, comprising: at least one processor, and a memory communicatively coupled to the at least one processor, wherein the memory stores instructions executable by the at least one processor to enable the at least one processor to perform the method of any one of claims 1 to 4.
7. A computer readable storage medium, on which a computer program is stored, characterized in that the program, when being executed by a processor, implements the method of any of claims 1 to 4.
CN202311706339.9A 2023-12-13 2023-12-13 Vehicle overrun overload probability identification method and system based on satellite positioning data Active CN117392855B (en)

Priority Applications (1)

Application Number Priority Date Filing Date Title
CN202311706339.9A CN117392855B (en) 2023-12-13 2023-12-13 Vehicle overrun overload probability identification method and system based on satellite positioning data

Applications Claiming Priority (1)

Application Number Priority Date Filing Date Title
CN202311706339.9A CN117392855B (en) 2023-12-13 2023-12-13 Vehicle overrun overload probability identification method and system based on satellite positioning data

Publications (2)

Publication Number Publication Date
CN117392855A CN117392855A (en) 2024-01-12
CN117392855B true CN117392855B (en) 2024-02-20

Family

ID=89439605

Family Applications (1)

Application Number Title Priority Date Filing Date
CN202311706339.9A Active CN117392855B (en) 2023-12-13 2023-12-13 Vehicle overrun overload probability identification method and system based on satellite positioning data

Country Status (1)

Country Link
CN (1) CN117392855B (en)

Citations (6)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
JP2005049355A (en) * 2004-09-13 2005-02-24 Pioneer Electronic Corp Navigation device and velocity calculation method
CN107507420A (en) * 2017-08-15 2017-12-22 深圳智慧车联科技有限公司 Overload of vehicle monitoring method, system and vehicle
CN112147658A (en) * 2019-06-27 2020-12-29 财付通支付科技有限公司 Method, device and equipment for judging moving direction of vehicle and storage medium
CN112270460A (en) * 2020-09-30 2021-01-26 交通运输部规划研究院 Goods source station identification method for overweight truck based on multi-source data
CN113561996A (en) * 2021-09-23 2021-10-29 国汽智控(北京)科技有限公司 Trajectory planning method and device
CN115077675A (en) * 2022-07-21 2022-09-20 鹰驾科技（深圳）有限公司 Truck overload monitoring system and method based on Beidou navigation

Patent Citations (6)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
JP2005049355A (en) * 2004-09-13 2005-02-24 Pioneer Electronic Corp Navigation device and velocity calculation method
CN107507420A (en) * 2017-08-15 2017-12-22 深圳智慧车联科技有限公司 Overload of vehicle monitoring method, system and vehicle
CN112147658A (en) * 2019-06-27 2020-12-29 财付通支付科技有限公司 Method, device and equipment for judging moving direction of vehicle and storage medium
CN112270460A (en) * 2020-09-30 2021-01-26 交通运输部规划研究院 Goods source station identification method for overweight truck based on multi-source data
CN113561996A (en) * 2021-09-23 2021-10-29 国汽智控(北京)科技有限公司 Trajectory planning method and device
CN115077675A (en) * 2022-07-21 2022-09-20 鹰驾科技（深圳）有限公司 Truck overload monitoring system and method based on Beidou navigation

Non-Patent Citations (1)

* Cited by examiner, † Cited by third party
Title
基于大货车GPS数据的轨迹相似性度量有效性研究;李颖;赵莉;赵祥模;陈珂;;中国公路学报;20200215(02);150-161 *

Also Published As

Publication number Publication date
CN117392855A (en) 2024-01-12

Similar Documents

Publication Publication Date Title
WO2020042984A1 (en) Vehicle behavior detection method and apparatus
CN110371112A (en) A kind of intelligent barrier avoiding system and method for automatic driving vehicle
CN105744232A (en) Method for preventing power transmission line from being externally broken through video based on behaviour analysis technology
CN105513349A (en) Double-perspective learning-based mountainous area highway vehicle event detection method
CN108877213A (en) The recognition methods and system of traffic accident
CN112749210B (en) Vehicle collision recognition method and system based on deep learning
CN115861973A (en) Road abnormal state detection method, system, electronic equipment and storage medium
CN105574502A (en) Automatic detection method for violation behaviors of self-service card sender
US11836994B2 (en) Methods and apparatus for automatic collection of under-represented data for improving a training of a machine learning model
CN105957352B (en) Parking offense detection method and device
CN102622883B (en) Method and device for judging release of traffic incident
CN103714695A (en) Method for analyzing vehicle operation state based on vehicle running data
CN111967451B (en) Road congestion detection method and device
CN117392855B (en) Vehicle overrun overload probability identification method and system based on satellite positioning data
CN105719359B (en) The acquisition methods and device of information of vehicles
CN106585634B (en) Method and device for analyzing driving behaviors
CN114446042B (en) Method, device, equipment and storage medium for early warning traffic accidents
CN113393011B (en) Method, device, computer equipment and medium for predicting speed limit information
CN112766746A (en) Traffic accident recognition method and device, electronic equipment and storage medium
CN109034116A (en) Density of stream of people detection method and system
CN117576926B (en) Method, device and storage medium for detecting vehicle violations
Gao et al. An In-Car Objects Detection Algorithm Based on Improved Spatial-Temporal Entropy Image
US11989949B1 (en) Systems for detecting vehicle following distance
CN114387695B (en) Parking charging timing method and related device
CN112557057B (en) Method and device for supervising test operation of automatic driving automobile road and vehicle-mounted terminal

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