CN116541727B - Track similarity calculation method and system - Google Patents

Track similarity calculation method and system Download PDF

Info

Publication number
CN116541727B
CN116541727B CN202310825917.4A CN202310825917A CN116541727B CN 116541727 B CN116541727 B CN 116541727B CN 202310825917 A CN202310825917 A CN 202310825917A CN 116541727 B CN116541727 B CN 116541727B
Authority
CN
China
Prior art keywords
track
dynamic
segment
static
similarity
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
CN202310825917.4A
Other languages
Chinese (zh)
Other versions
CN116541727A (en
Inventor
白长治
王伟
窦明哲
周剑桥
李家峰
吴波
李兆靖
赵可昕
辛腾龙
王皓宇
张烜通
李伯垚
叶胜峰
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.)
China Ordins Group Co ltd
Original Assignee
China Ordins Group Co ltd
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 China Ordins Group Co ltd filed Critical China Ordins Group Co ltd
Priority to CN202310825917.4A priority Critical patent/CN116541727B/en
Publication of CN116541727A publication Critical patent/CN116541727A/en
Application granted granted Critical
Publication of CN116541727B publication Critical patent/CN116541727B/en
Active legal-status Critical Current
Anticipated expiration legal-status Critical

Links

Classifications

    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06F—ELECTRIC DIGITAL DATA PROCESSING
    • G06F18/00—Pattern recognition
    • G06F18/20—Analysing
    • G06F18/22—Matching criteria, e.g. proximity measures
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06F—ELECTRIC DIGITAL DATA PROCESSING
    • G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
    • G06F16/20—Information retrieval; Database structures therefor; File system structures therefor of structured data, e.g. relational data
    • G06F16/29—Geographical information databases
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06F—ELECTRIC DIGITAL DATA PROCESSING
    • G06F2123/00—Data types
    • G06F2123/02—Data types in the time domain, e.g. time-series data
    • Y—GENERAL TAGGING OF NEW TECHNOLOGICAL DEVELOPMENTS; GENERAL TAGGING OF CROSS-SECTIONAL TECHNOLOGIES SPANNING OVER SEVERAL SECTIONS OF THE IPC; TECHNICAL SUBJECTS COVERED BY FORMER USPC CROSS-REFERENCE ART COLLECTIONS [XRACs] AND DIGESTS
    • Y02—TECHNOLOGIES OR APPLICATIONS FOR MITIGATION OR ADAPTATION AGAINST CLIMATE CHANGE
    • Y02D—CLIMATE CHANGE MITIGATION TECHNOLOGIES IN INFORMATION AND COMMUNICATION TECHNOLOGIES [ICT], I.E. INFORMATION AND COMMUNICATION TECHNOLOGIES AIMING AT THE REDUCTION OF THEIR OWN ENERGY USE
    • Y02D30/00—Reducing energy consumption in communication networks
    • Y02D30/70—Reducing energy consumption in communication networks in wireless communication networks

Landscapes

  • Engineering & Computer Science (AREA)
  • Theoretical Computer Science (AREA)
  • Data Mining & Analysis (AREA)
  • Physics & Mathematics (AREA)
  • Databases & Information Systems (AREA)
  • General Physics & Mathematics (AREA)
  • General Engineering & Computer Science (AREA)
  • Bioinformatics & Cheminformatics (AREA)
  • Evolutionary Computation (AREA)
  • Evolutionary Biology (AREA)
  • Computer Vision & Pattern Recognition (AREA)
  • Bioinformatics & Computational Biology (AREA)
  • Artificial Intelligence (AREA)
  • Life Sciences & Earth Sciences (AREA)
  • Remote Sensing (AREA)
  • Radar Systems Or Details Thereof (AREA)

Abstract

The application relates to a track similarity calculation method and a track similarity calculation system, belongs to the technical field of track tracking, and solves the problems of overlarge track length difference and low overall calculation efficiency in the process of comparing a dynamic track with a static track in the prior art. The method comprises the following steps: acquiring a dynamic track, segmenting the dynamic track according to time parameters, and determining a dynamic track segment; acquiring a static track, segmenting the static track according to the dynamic track segments, and determining static track segments corresponding to the dynamic track segments one by one; calculating the segment similarity of each dynamic track segment and the corresponding static track segment; and carrying out weighted calculation on the segment similarity to obtain the similarity of the dynamic track and the static track. The calculation efficiency and the calculation precision of the track similarity are effectively improved.

Description

Track similarity calculation method and system
Technical Field
The present application relates to the field of track tracking technologies, and in particular, to a track similarity calculation method and system.
Background
In the comparative trajectory similarity calculation model, the temporal dimension and the spatial dimension are the main study extension directions. In the calculation model of the similarity of the two tracks, the judgment of the relative distance between the two tracks is the core of the calculation model of the similarity of the whole track. In the traditional track similarity calculation model, the comparison is often carried out on double static or double dynamic tracks through time or space dimensions.
In living scenes, more scenes such as automobile navigation, track tracking and the like are dynamic tracks and static tracks, and whether the current dynamic track is on the current static track is judged, so that the functions of route navigation, fence early warning and the like are performed.
The existing track similarity comparison calculation model can calculate the similarity of track data with similar track length and time dimension, but has two problems:
1) The track length difference is large, and the calculation result is interfered: in the track matching process, the lengths of two tracks which are mostly compared are greatly different, such as vehicle map navigation, at the moment, the length of a road track is far greater than the length of a vehicle running track, all track points can participate in calculation in the calculation process, at the moment, abnormal track points participate in track similarity calculation, and calculation results are interfered.
2) The time attribute is missing, and the total calculation efficiency is low: in the vehicle navigation situation, when the tracks are compared, one track is a static track and the other track is a dynamic track, the dynamic track has time attribute and can be segmented in time, but the static track cannot be segmented in time due to the fact that the time attribute does not exist, so that the total calculation of track data is caused, the calculation amount is large, the calculation efficiency is influenced, and the efficiency is low.
Disclosure of Invention
In view of the above analysis, the present embodiment of the present application aims to provide a track similarity calculation method, which is used to solve the problems of excessive track length difference and low overall calculation efficiency in the existing dynamic track and static track comparison process.
In one aspect, an embodiment of the present application provides a method for calculating a track similarity, including the following steps: acquiring a dynamic track, segmenting the dynamic track according to time parameters, and determining a dynamic track segment;
acquiring a static track, segmenting the static track according to the dynamic track segments, and determining static track segments corresponding to the dynamic track segments one by one;
calculating the segment similarity of each dynamic track segment and the corresponding static track segment;
and carrying out weighted calculation on the segment similarity to obtain the similarity of the dynamic track and the static track.
Based on the further improvement of the above technical solution, the segmenting the dynamic track according to the time parameter, determining a dynamic track segment includes:
performing de-duplication treatment on the dynamic track;
segmenting the dynamic track according to preset time, so that the time length of the dynamic track segment is the preset time, or segmenting according to the interval time of track points in the dynamic track.
Based on the further improvement of the technical scheme, the method segments according to the interval time of the track points in the dynamic track, and comprises the following steps:
calculating the actual interval time between every two adjacent track points in the dynamic track;
judging whether all the actual interval time meets a preset condition or not; the preset conditions are used for representing the change frequency of the track points;
when all the actual interval time meets the preset conditions, segmenting the dynamic track according to the preset time;
and when the actual interval time does not meet the preset condition, segmenting the dynamic track according to the actual interval time.
Based on further improvement of the above technical solution, the preset conditions include: the difference value between the actual interval time and the average interval time between two points in the dynamic track is smaller than a preset difference value; segmenting the dynamic track according to the actual interval time, including:
taking the first track point of two track points with the difference value of the actual interval time and the average interval time being more than or equal to the preset difference value as a demarcation point, and segmenting the dynamic track;
and for the segments with the segment time length longer than the preset time, carrying out segment segmentation on the segments according to the preset time.
Based on the further improvement of the above technical solution, the segmenting the static track according to the dynamic track segment, determining a static track segment corresponding to the dynamic track segment one-to-one, includes:
acquiring a position error threshold; wherein the position error threshold is determined by an error of satellite positioning;
and searching track points with the distance smaller than or equal to the position error threshold value from the static track to form the static track section corresponding to the dynamic track section.
Based on the further improvement of the above technical solution, the calculating the segment similarity between each dynamic track segment and the corresponding static track segment includes:
calculating the dynamic track segmentTo the static track segment->Is +.>Said static track segment->To the dynamic track segment->Is +.>；
Calculation ofAnd->As the average value of the segment similarity +.>。
Based on the further improvement of the technical scheme, the dynamic track segment is calculatedTo the static track segment->Is +.>Comprising:
calculating the dynamic track segmentEach trace point of->To the static track segment->Distance of (2)：/> ；
According toCalculating the dynamic track segment->To the static track segment->Is a relative area of (2)：/>；
Wherein the dynamic track segmentTo static track segment->Correspondingly (I)>For static track segments->Track points in>For the dynamic track segment->Is a trace point total number.
Based on the further improvement of the technical scheme, the step of carrying out weighted calculation on the segmentation similarity to obtain the similarity of the dynamic track and the static track comprises the following steps:
calculating the ratio of the number of track points of each dynamic track segment to the number of track points of the dynamic track as a segmentation weight;
multiplying each segment weight and the corresponding segment similarity, and then adding to obtain the similarity of the dynamic track and the static track.
In another aspect, an embodiment of the present application provides a track similarity calculation system, including the following modules:
the dynamic track segmentation module is used for acquiring a dynamic track, segmenting the dynamic track according to time parameters and determining a dynamic track segment;
the static track segmentation module is used for acquiring a static track, segmenting the static track according to the dynamic track segments and determining static track segments corresponding to the dynamic track segments one by one;
the segmentation similarity calculation module is used for calculating the segmentation similarity of each dynamic track segment and the corresponding static track segment;
and the similarity calculation module is used for carrying out weighted calculation on the segment similarity to obtain the similarity of the dynamic track and the static track.
Based on the further improvement of the above technical solution, the dynamic track segmentation module segments the dynamic track according to a time parameter, and determines a dynamic track segment, including:
performing de-duplication treatment on the dynamic track;
segmenting the dynamic track according to preset time, so that the time length of the dynamic track segment is the preset time, or segmenting according to the interval time of track points in the dynamic track.
According to the scheme, in order to solve the problems that the track length difference is too large and the overall calculation efficiency is low in the process of comparing the dynamic track and the static track, the application provides a dynamic track similarity calculation model.
Compared with the prior art, the application has at least one of the following beneficial effects:
1. the time segmentation is carried out based on the dynamic track, the static track is intercepted based on the threshold value through the segmentation result, whether the lengths of the two tracks are similar or not does not need to be considered, and meanwhile, the time attribute is weakened and the two tracks must be acted.
2. The similarity is calculated in a segmented mode, the calculated data size is reduced, and the calculation speed can be improved. And meanwhile, the similarity results of the segments are aggregated according to the proportion of the segments to the original track as weights, so that the final similarity is obtained, and the accuracy of the similarity results is improved.
In the application, the technical schemes can be mutually combined to realize more preferable combination schemes. Additional features and advantages of the application will be set forth in the description which follows, and in part will be obvious from the description, or may be learned by practice of the application. The objectives and other advantages of the application may be realized and attained by the structure particularly pointed out in the written description and drawings.
Drawings
The drawings are only for purposes of illustrating particular embodiments and are not to be construed as limiting the application, like reference numerals being used to designate like parts throughout the drawings;
FIG. 1 is a flowchart of a track similarity calculation method according to an embodiment of the present application;
fig. 2 is a block diagram of a track similarity calculation system according to an embodiment of the present application.
Detailed Description
The following detailed description of preferred embodiments of the application is made in connection with the accompanying drawings, which form a part hereof, and together with the description of the embodiments of the application, are used to explain the principles of the application and are not intended to limit the scope of the application.
In one embodiment of the present application, a track similarity calculation method is disclosed, as shown in fig. 1, and the method includes the following steps:
s1: acquiring a dynamic track, segmenting the dynamic track according to time parameters, and determining a dynamic track segment;
s2: acquiring a static track, segmenting the static track according to the dynamic track segments, and determining static track segments corresponding to the dynamic track segments one by one;
s3: calculating the segment similarity of each dynamic track segment and the corresponding static track segment;
s4: and carrying out weighted calculation on the segment similarity to obtain the similarity of the dynamic track and the static track.
In practice, a dynamic track, such as a driving track of a vehicle, has a time attribute, and a static track, such as a road track, has no time attribute.
In the above embodiment, the time segmentation is performed based on the dynamic track, and the static track is intercepted based on the threshold value by the segmentation result, so that it is not necessary to consider whether the lengths of the two tracks are similar, and the time attribute is weakened and the two tracks must be acted on. And the similarity of the sectional moving and static tracks is calculated after the sectional operation, so that the calculated data volume is reduced, and the calculation speed is improved. Meanwhile, the similarity results of the segments are aggregated according to the proportion of the segments to the original track as weights, so that the final similarity is obtained, and the accuracy of the similarity results is improved. The method effectively solves the problems of overlarge track length difference and low overall calculation efficiency in the existing dynamic track and static track comparison process, effectively improves the calculation efficiency, and improves the calculation accuracy of the similarity.
In a preferred embodiment of the present application, the step of segmenting according to the interval time of the track points in the dynamic track to determine the dynamic track segment includes: firstly, carrying out de-duplication treatment on a dynamic track; when the dynamic track D is a continuous coordinate point with time attribute, judging whether the continuous same track point exists in the current dynamic track or not, namely, two points with completely consistent longitude and latitude coordinates exist in the dynamic track, and when the two points with completely consistent longitude and latitude coordinates exist, indicating that the dynamic track is unchanged, and performing de-weighting on the points with consistent longitude and latitude, so that the subsequent calculated amount can be reduced. The scheme is that the dynamic track is de-duplicated, and before calculation, the static track can be de-duplicated. If the points with consistent longitude and latitude exist in the static track, the points belong to abnormal track points, the points should not participate in the calculation of the similarity of the current track, the accuracy of the calculation of the similarity of the track is affected, and the points need to be removed.
After the deduplication process, segmentation can be performed in two ways: the dynamic track is segmented according to the preset time, so that the time length of the dynamic track segment is the preset time, or the dynamic track is segmented according to the interval time of track points in the dynamic track.
For the first segmentation method, the time length of each dynamic track segment is consistent, and the time length is preset, for example, one hour.
For the second segmentation mode, segmentation is performed according to the interval time of track points in the dynamic track, and specifically comprises the following steps: calculating the actual interval time between every two adjacent track points in the dynamic track; judging whether all actual interval time meets preset conditions or not; the preset conditions are used for representing the change frequency of the track points; segmenting the dynamic track according to the preset time when all the actual interval time meets the preset condition; and when the actual interval time does not meet the preset condition, segmenting the dynamic track according to the actual interval time. The second segmentation method considers whether the dynamic track changes or not, if the dynamic track changes continuously, the dynamic track can be segmented directly according to time, if the dynamic track does not change for a period of time, the situation that track points in the dynamic track segment are very few after the dynamic track segment is segmented according to the time length is avoided, and the segmentation is performed in a mode of actual interval time. In specific implementation, the preset conditions include: the difference between the actual interval time and the average interval time between two points in the dynamic trajectory is smaller than a preset difference, for example 2 minutes.
Segmenting the dynamic track according to the actual interval time, including: taking the first track point of two track points with the difference value of the actual interval time and the average interval time being greater than or equal to the preset difference value as a demarcation point, and segmenting the dynamic track; and segmenting each section of dynamic track according to the interval time of track points. And for the segments with the segment time length longer than the preset time, carrying out segment segmentation on the segments according to the preset time.
And after the point with the completely consistent longitude and latitude is de-duplicated, acquiring the time length of the whole dynamic track, then acquiring the interval time between the average two coordinate points of the current dynamic track through the time length and the point number of the dynamic track, and segmenting once per hour when the difference between the current interval time and the average interval time of all the points is less than 2 minutes. If the current interval time of the existing point and the average interval time are directly different by more than 2 minutes, the dynamic track is segmented according to the current point. For example, two adjacent dynamic trace pointsAnd->The difference between the actual interval time and the average interval time is greater than 2 minutes. In->As a demarcation point, the dynamic track is segmented.
After the segmentation, if the segmentation time length is longer than the preset time, the segmentation is carried out on the segmentation with the segmentation time length longer than the preset time according to the preset time, namely, the segmentation is carried out on the segmentation with the segmentation time length longer than 1 hour again according to each 1 hour.
After segmentation is performed according to the rule, the position is transmitted once according to the GPS every 5s according to the satellite, 1200 times of transmission are taken as a reference, the track of more than 300 and less than 600 coordinate points is divided into two sections according to the number of coordinate points contained in the segmentation, and the coordinate point of more than 600 is divided into 3 sections.
After segmenting the dynamic track, segmenting the static track according to the dynamic track segments, and determining the static track segments corresponding to the dynamic track segments one by one, wherein the method comprises the following steps:
s21, acquiring a position error threshold; wherein the position error threshold is determined by an error of satellite positioning;
s22, searching track points with the distance smaller than or equal to the position error threshold value from the static track to form the static track segment corresponding to the dynamic track segment.
Firstly, determining a position error threshold epsilon according to satellite positioning errors, wherein the threshold epsilon is a difference range between longitude and latitude, the difference threshold between longitude and latitude is about 0.001, the difference between longitude and latitude is 80-90 meters on a map, and the threshold epsilon is selected according to the currently selected satellite positioning errors and is generally set to be 0.002-0.003.
The obtained static track points are expressed asM total number of static track points. Post-segmentation->The dynamic track segment of an individual is denoted +.>N represents the number of segments of the dynamic track, +.>Indicate->Track segment point number of segment dynamic track segments.
For each track point in each dynamic track segmentAnd searching track points with the distance smaller than or equal to the position error threshold value in the static track segment to form a static track segment corresponding to the dynamic track segment.
Wherein the distance is calculated by the formulaCalculated, ifThen (I)>Belonging to->Static track section corresponding to the dynamic track section +.>。
For dynamic track pointsIf there is no static track point with a distance less than ε, the dynamic track point is an outlier, at ε>And deleting the point in the dynamic track segment, so that the influence of an abnormal coordinate point generated during satellite positioning on calculation is reduced. If the proportion of the abnormal points to the total dynamic track points exceeds a threshold value, for example, 5%, the dynamic track is considered to be abnormal, and whether the dynamic track is similar to the static track or not cannot be calculated effectively.
For the firstSegment static track segment->In order to prevent the repeated track points from participating in the subsequent track similarity calculation, the points with the same longitude and latitude are de-duplicated and the points with the same latitude and longitude are added with->Indicate->Track segment point number of segment static track segments.
After the dynamic track and the static track are segmented, calculating the segmentation similarity of each dynamic track segment and the corresponding static track segment comprises the following steps:
s31, calculating the dynamic track segmentTo the static track segment->Is +.>Static track segment->To dynamic track segment->Is +.>；
For the firstSegment dynamic track segment->Track points +.>Calculate it to and +.>Static track section corresponding to the dynamic track section +.>Distance of->：
；
Wherein, the liquid crystal display device comprises a liquid crystal display device,is->Segment static track segment->Is included in the static track points. />Representation->Point-to-static track segment->Is the closest euclidean distance of (c).
According toCalculating dynamic track segment->To static track segment->Is +.>：。
Dynamic track segmentTo static track segment->Is the relative area of (i.e. dynamic track segment>To static track segment->Is one-way distance of->For dynamic track segments->Is a trace point total number.
The static track section can be calculated by the same methodTo dynamic track segment->Is a relative area of (2)。
S32, calculatingAnd->As the average value of the segment similarity +.>。
Calculating dynamic trajectoriesAnd static track segment->The relative area between them, i.e.)>And->Mean value of>As a dynamic track +.>And static track segment->Segment similarity between:
wherein, the liquid crystal display device comprises a liquid crystal display device,for track segment->And track segment->Relative area values between.
In implementation, the relative area of the corresponding dynamic track segment and the static track segment can be calculated in a multithreading concurrency mode.
And after calculating the segment similarity between the corresponding track sections, carrying out weighted calculation on the segment similarity to obtain the similarity of the dynamic track and the static track. The method specifically comprises the following steps:
s41, calculating the ratio of the number of track points of each dynamic track segment to the number of track points of the dynamic track as a segmentation weight;
for each dynamic track segmentDynamic track segment->The ratio of the total number of track points to the total number of track points of the dynamic track D +.>As its weight.
S42, multiplying each segment weight by the corresponding segment similarity and then adding the multiplied segment weights to obtain the similarity of the dynamic track and the static track.
Multiplying each segment weight and the corresponding segment similarity, adding, and finally summarizing all weighted results to obtain a similarity result of the final dynamic track and the static track。
；
Wherein, the liquid crystal display device comprises a liquid crystal display device,for dynamic track segments->The ratio of the total number of track points to the total number of track points of the dynamic track D is the weight.
The closer the final track similarity result is to 0, the more similar the two tracks are.
When the route navigation is carried out, whether the current dynamic track is on the current static track or not is judged by judging whether the dynamic track of the vehicle is similar to the static track of the road or not, namely, whether the vehicle runs on the road or not is judged, and then the route navigation is carried out.
In one embodiment of the present application, a track similarity calculation system is disclosed, as shown in fig. 2, comprising the following modules:
the dynamic track segmentation module is used for acquiring a dynamic track, segmenting according to the interval time of track points in the dynamic track and determining a dynamic track segment;
the static track segmentation module is used for acquiring a static track, segmenting the static track according to the dynamic track segments and determining static track segments corresponding to the dynamic track segments one by one;
the segmentation similarity calculation module is used for calculating the segmentation similarity of each dynamic track segment and the corresponding static track segment;
and the similarity calculation module is used for carrying out weighted calculation on the segment similarity to obtain the similarity of the dynamic track and the static track.
Preferably, the dynamic track segmentation module segments the dynamic track according to a time parameter, and determines a dynamic track segment, including:
performing de-duplication treatment on the dynamic track;
segmenting the dynamic track according to preset time, so that the time length of the dynamic track segment is the preset time, or segmenting according to the interval time of track points in the dynamic track.
The method embodiment and the system embodiment are based on the same principle, and the related parts can be mutually referred to and can achieve the same technical effect. The specific implementation process refers to the foregoing embodiment, and will not be described herein.
Those skilled in the art will appreciate that all or part of the flow of the methods of the embodiments described above may be accomplished by way of a computer program to instruct associated hardware, where the program may be stored on a computer readable storage medium. Wherein the computer readable storage medium is a magnetic disk, an optical disk, a read-only memory or a random access memory, etc.
The present application is not limited to the above-mentioned embodiments, and any changes or substitutions that can be easily understood by those skilled in the art within the technical scope of the present application are intended to be included in the scope of the present application.

Claims (9)

1. The track similarity calculation method is characterized by comprising the following steps of:
acquiring a dynamic track, segmenting the dynamic track according to time parameters, and determining a dynamic track segment;
acquiring a static track, segmenting the static track according to the dynamic track segments, and determining static track segments corresponding to the dynamic track segments one by one; the static track has no time attribute;
calculating the segment similarity of each dynamic track segment and the corresponding static track segment;
weighting calculation is carried out on the segmentation similarity to obtain the similarity of the dynamic track and the static track;
the step of segmenting the static track according to the dynamic track segments to determine static track segments corresponding to the dynamic track segments one by one comprises the following steps:
acquiring a position error threshold; wherein the position error threshold is determined by an error of satellite positioning;
and searching track points with the distance smaller than or equal to the position error threshold value from the static track to form the static track section corresponding to the dynamic track section.
2. The track similarity calculation method according to claim 1, wherein the segmenting the dynamic track according to the time parameter, determining a dynamic track segment, includes:
performing de-duplication treatment on the dynamic track;
segmenting the dynamic track according to preset time, so that the time length of the dynamic track segment is the preset time, or segmenting according to the interval time of track points in the dynamic track.
3. The track similarity calculation method according to claim 2, wherein the segmenting according to the interval time of the track points in the dynamic track comprises:
calculating the actual interval time between every two adjacent track points in the dynamic track;
judging whether all the actual interval time meets a preset condition or not; the preset conditions are used for representing the change frequency of the track points;
when all the actual interval time meets the preset conditions, segmenting the dynamic track according to the preset time;
and when the actual interval time does not meet the preset condition, segmenting the dynamic track according to the actual interval time.
4. The trajectory similarity calculation method according to claim 3, wherein the preset conditions include: the difference value between the actual interval time and the average interval time between two points in the dynamic track is smaller than a preset difference value; segmenting the dynamic track according to the actual interval time, including:
taking the first track point of two track points with the difference value of the actual interval time and the average interval time being more than or equal to the preset difference value as a demarcation point, and segmenting the dynamic track;
and for the segments with the segment time length longer than the preset time, carrying out segment segmentation on the segments according to the preset time.
5. The track similarity calculation method according to claim 1, wherein the calculating the segment similarity of each of the dynamic track segments and the static track segment corresponding thereto includes:
calculating the dynamic track segmentTo the static track segment->Is +.>Said static track segment->To the dynamic track segment->Is +.>；
Calculation ofAnd->As the average value of the segment similarity +.>。
6. The trajectory similarity calculation method according to claim 5, wherein the dynamic trajectory segment is calculatedTo the static track segment->Is +.>Comprising:
calculating the dynamic track segmentEach trace point of->To the static track segment->Distance of->：；
According toCalculating the dynamic track segment->To the static track segment->Is +.>：
；
Wherein the dynamic track segmentTo static track segment->Correspondingly (I)>For static track segments->Track points in>For the dynamic track segment->Is a trace point total number.
7. The track similarity calculation method according to claim 5, wherein weighting the segment similarity to obtain the similarity between the dynamic track and the static track includes:
calculating the ratio of the number of track points of each dynamic track segment to the number of track points of the dynamic track as a segmentation weight;
multiplying each segment weight and the corresponding segment similarity, and then adding to obtain the similarity of the dynamic track and the static track.
8. A track similarity computing system, comprising the following modules:
the dynamic track segmentation module is used for acquiring a dynamic track, segmenting the dynamic track according to time parameters and determining a dynamic track segment;
the static track segmentation module is used for acquiring a static track, segmenting the static track according to the dynamic track segments and determining static track segments corresponding to the dynamic track segments one by one; the static track has no time attribute;
the segmentation similarity calculation module is used for calculating the segmentation similarity of each dynamic track segment and the corresponding static track segment;
the similarity calculation module is used for carrying out weighted calculation on the segmentation similarity to obtain the similarity of the dynamic track and the static track;
the step of segmenting the static track according to the dynamic track segments to determine static track segments corresponding to the dynamic track segments one by one comprises the following steps:
acquiring a position error threshold; wherein the position error threshold is determined by an error of satellite positioning;
and searching track points with the distance smaller than or equal to the position error threshold value from the static track to form the static track section corresponding to the dynamic track section.
9. The track similarity calculation system of claim 8, wherein the dynamic track segmentation module segments the dynamic track according to a time parameter to determine a dynamic track segment, comprising:
performing de-duplication treatment on the dynamic track;
segmenting the dynamic track according to preset time, so that the time length of the dynamic track segment is the preset time, or segmenting according to the interval time of track points in the dynamic track.
CN202310825917.4A 2023-07-07 2023-07-07 Track similarity calculation method and system Active CN116541727B (en)

Priority Applications (1)

Application Number Priority Date Filing Date Title
CN202310825917.4A CN116541727B (en) 2023-07-07 2023-07-07 Track similarity calculation method and system

Applications Claiming Priority (1)

Application Number Priority Date Filing Date Title
CN202310825917.4A CN116541727B (en) 2023-07-07 2023-07-07 Track similarity calculation method and system

Publications (2)

Publication Number Publication Date
CN116541727A CN116541727A (en) 2023-08-04
CN116541727B true CN116541727B (en) 2023-09-12

Family

ID=87456432

Family Applications (1)

Application Number Title Priority Date Filing Date
CN202310825917.4A Active CN116541727B (en) 2023-07-07 2023-07-07 Track similarity calculation method and system

Country Status (1)

Country Link
CN (1) CN116541727B (en)

Citations (5)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN103593430A (en) * 2013-11-11 2014-02-19 胡宝清 Clustering method based on mobile object spatiotemporal information trajectory subsections
CN106960006A (en) * 2017-02-24 2017-07-18 河海大学 Measuring similarity system and its measure between a kind of different tracks
CN110909106A (en) * 2019-11-26 2020-03-24 杭州三汇数字信息技术有限公司 Trajectory prediction method and system
CN112037245A (en) * 2020-07-22 2020-12-04 杭州海康威视数字技术股份有限公司 Method and system for determining similarity of tracked target
CN113032502A (en) * 2021-02-09 2021-06-25 北京工业大学 Ship anomaly detection method based on improved track segment DBSCAN clustering

Family Cites Families (1)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
DE102020200183A1 (en) * 2020-01-09 2021-07-15 Continental Automotive Gmbh Method for creating a probabilistic free space map with static and dynamic objects

Patent Citations (5)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN103593430A (en) * 2013-11-11 2014-02-19 胡宝清 Clustering method based on mobile object spatiotemporal information trajectory subsections
CN106960006A (en) * 2017-02-24 2017-07-18 河海大学 Measuring similarity system and its measure between a kind of different tracks
CN110909106A (en) * 2019-11-26 2020-03-24 杭州三汇数字信息技术有限公司 Trajectory prediction method and system
CN112037245A (en) * 2020-07-22 2020-12-04 杭州海康威视数字技术股份有限公司 Method and system for determining similarity of tracked target
CN113032502A (en) * 2021-02-09 2021-06-25 北京工业大学 Ship anomaly detection method based on improved track segment DBSCAN clustering

Non-Patent Citations (1)

* Cited by examiner, † Cited by third party
Title
SDFA: A Vessel Trajectory Clustering Technology and Application Oriented to Multi-feature Fusion Model;Shuhao Yu et al.;《 IEEE Xplore》;全文 *

Also Published As

Publication number Publication date
CN116541727A (en) 2023-08-04

Similar Documents

Publication Publication Date Title
US10074270B2 (en) Clustering observations of objects along roads for navigation-related operations
CN109444932B (en) Vehicle positioning method and device, electronic equipment and storage medium
WO2020206861A1 (en) Yolo v3-based detection method for key object at transportation junction
CN106871924B (en) A kind of VMT Vehicle-Miles of Travel calculation method based on satellite positioning signal
CN109344899B (en) Multi-target detection method and device and electronic equipment
CN110426050B (en) Map matching correction method, device, equipment and storage medium
CN113191550B (en) Map matching method and device
SE1251163A1 (en) System and method in connection with the occurrence of vehicle trains
CN102722706A (en) Particle filter-based infrared small dim target detecting and tracking method and device
CN105374049B (en) Multi-corner point tracking method and device based on sparse optical flow method
CN113593218A (en) Method and device for detecting traffic abnormal event, electronic equipment and storage medium
CN116541727B (en) Track similarity calculation method and system
CN114625744A (en) Updating method and device of electronic map
CN112100565B (en) Road curvature determination method, device, equipment and storage medium
WO2022099620A1 (en) Three-dimensional point cloud segmentation method and apparatus, and mobile platform
CN113465616B (en) Track abnormal point detection method and device, electronic equipment and storage medium
CN115272899A (en) Risk early warning method and device, aircraft and storage medium
CN109612467B (en) Track simplifying method and system and track visualization system
CN104931068A (en) Distance measurement method and device
CN105675007A (en) Method for reporting GPS data during vehicle curve running and vehicle-mounted GPS
US20190197038A1 (en) Feature data storage apparatus
CN117689907B (en) Vehicle tracking method, device, computer equipment and storage medium
WO2023097873A1 (en) Method and apparatus for checking vehicle positioning, and storage medium and device
US20230118134A1 (en) Methods and systems for estimating lanes for a vehicle
CN116403415A (en) Lane-level road condition acquisition method and device, electronic equipment and storage medium

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