CN110505583B - Trajectory matching method based on bayonet data and signaling data - Google Patents
Trajectory matching method based on bayonet data and signaling data Download PDFInfo
- Publication number
- CN110505583B CN110505583B CN201910666051.0A CN201910666051A CN110505583B CN 110505583 B CN110505583 B CN 110505583B CN 201910666051 A CN201910666051 A CN 201910666051A CN 110505583 B CN110505583 B CN 110505583B
- Authority
- CN
- China
- Prior art keywords
- track
- vehicle
- data
- mobile phone
- matching
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Active
Links
- 230000011664 signaling Effects 0.000 title claims abstract description 44
- 238000000034 method Methods 0.000 title claims abstract description 18
- 238000004422 calculation algorithm Methods 0.000 claims abstract description 32
- 238000004364 calculation method Methods 0.000 claims abstract description 20
- 238000012216 screening Methods 0.000 claims abstract description 8
- 238000007781 pre-processing Methods 0.000 claims abstract description 7
- 238000013145 classification model Methods 0.000 claims abstract description 6
- 238000011160 research Methods 0.000 claims description 13
- 238000012544 monitoring process Methods 0.000 claims description 12
- 238000007635 classification algorithm Methods 0.000 claims description 5
- 238000004140 cleaning Methods 0.000 claims description 3
- 238000005070 sampling Methods 0.000 claims description 3
- 238000003066 decision tree Methods 0.000 claims description 2
- 238000001914 filtration Methods 0.000 claims description 2
- 230000000694 effects Effects 0.000 abstract description 2
- 238000005259 measurement Methods 0.000 abstract 1
- 238000012549 training Methods 0.000 description 3
- 238000012986 modification Methods 0.000 description 2
- 230000004048 modification Effects 0.000 description 2
- 238000004458 analytical method Methods 0.000 description 1
- 230000009286 beneficial effect Effects 0.000 description 1
- 238000012937 correction Methods 0.000 description 1
- 230000002354 daily effect Effects 0.000 description 1
- 238000011161 development Methods 0.000 description 1
- 238000010586 diagram Methods 0.000 description 1
- 238000005516 engineering process Methods 0.000 description 1
- 238000011156 evaluation Methods 0.000 description 1
- 230000003203 everyday effect Effects 0.000 description 1
- 231100001263 laboratory chemical safety summary Toxicity 0.000 description 1
- 239000000523 sample Substances 0.000 description 1
Images
Classifications
-
- 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
-
- 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
- H04W4/20—Services signaling; Auxiliary data signalling, i.e. transmitting data via a non-traffic channel
-
- 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]
Landscapes
- Engineering & Computer Science (AREA)
- Computer Networks & Wireless Communication (AREA)
- Signal Processing (AREA)
- Mobile Radio Communication Systems (AREA)
- Traffic Control Systems (AREA)
Abstract
The invention provides a trajectory matching algorithm based on bayonet data and signaling data, which comprises data preprocessing, a space-time trajectory matching algorithm, a data enhancement algorithm and a classification model for judging whether a vehicle trajectory is matched with a mobile phone trajectory or not. Firstly, removing invalid data in different data sets, and screening out vehicles and mobile phone equipment with frequent activities by calculating information entropy; then, a potential matching data set of the vehicle and the mobile phone is obtained according to a space-time track matching algorithm, and the vehicle and the mobile phone are determined to be matched according to long-time tracking of the vehicle and the mobile phone track; then, performing sample expansion on the determined matching track by using a data enhancement algorithm; and finally, selecting reasonable model characteristics by using the track matching result, and establishing a track classification model. The method is applied to matching of mass vehicle tracks and mobile phone signaling tracks, and solves the problems of poor calculation efficiency, single measurement index and the like of the existing track matching.
Description
Technical Field
The invention relates to the field of track matching algorithms, in particular to a track matching method based on bayonet data and signaling data.
Background
In recent years, with the development of positioning technology, a large amount of individual trajectory data has appeared. The trajectory of the vehicle may be recorded by fixed position sensors, such as an automatic license plate recognition system at a road monitoring gate. It can identify the license plate number of the vehicle from the image taken by the color, black and white or infrared camera. The vehicle trajectory can be reconstructed from the data recorded by the gate. In addition to fixed position sensors, mobile traffic sensors can move with the vehicle, including probe cars, GPS devices, cell phones, and the like. When the mobile phone is used for making a call or surfing the internet, the mobile phone can be in contact with a nearby base station, the base station can record data such as current time, position and equipment number, and detailed movement tracks of mobile phone equipment or individuals can be restored through the data.
Based on millions of vehicles and mobile phone track data in a city, the most similar track pairs are found out from two heterogeneous data sets, namely a driver and a vehicle in the city are paired, so that the method has a great application value, and theoretical reference can be provided for research fields such as resident trip mode identification, urban internal vehicle restriction policy influence analysis and privacy data release.
At present, a plurality of trajectory similarity calculation methods are proposed at home and abroad, and the trajectory similarity calculation methods can be mainly divided into two categories of space similarity and space-time similarity. The spatial similarity mainly finds the tracks with similar geometric shapes, omits the time dimension, and considers the time and spatial characteristics of the tracks at the same time. However, these algorithms need to calculate the similarity every two tracks, which is too high for millions of tracks in a city, and often only one index is used to evaluate the similarity of the tracks, so that the similarity of the tracks cannot be completely described.
Disclosure of Invention
The invention provides a trajectory matching algorithm based on bayonet data and signaling data, and the algorithm provides a more reasonable calculation method with less calculation complexity and more evaluation indexes for matching of massive heterogeneous trajectories.
In order to achieve the technical effects, the technical scheme of the invention is as follows:
a trajectory matching algorithm based on bayonet data and signaling data comprises the following steps:
s1: acquiring a road gate monitoring data set and a mobile phone signaling data set in a research area and a research time period;
s2: preprocessing a bayonet data set and a signaling data set, wherein the preprocessing comprises invalid data cleaning, time span screening and frequent movement track screening;
s3: obtaining a potential matching data set of the vehicle and the mobile phone through a space-time trajectory matching algorithm;
s4: matching tracks of the vehicle and the mobile phone in the potential matching data set in different time periods, wherein if the tracks of the vehicle and the mobile phone keep the same matching relation in a time range, the vehicle and the mobile phone are determined to be matched;
s5: sampling the determined matching track by using a data enhancement algorithm to obtain more vehicle and mobile phone matching right cases; randomly selecting a vehicle and a mobile phone track from the bayonet and the signaling data set, and selecting the vehicle and mobile phone track which are in error matching as a counter example of matching between the vehicle and the mobile phone;
s6: and establishing a track classification model based on the positive example track data and the negative example track data obtained in the steps by adopting reasonable model characteristics and a classification algorithm with high accuracy.
Further, in step S1, the handset signaling data includes: (1) user number isdn: the unique identification of the mobile phone user; (2) longitude, ng: the longitude of the location of the user; (3) latitude lat: the latitude of the location of the user; (4) time: the signaling records the time of generation. The bayonet monitoring data comprises: (1) bayonet number kdbh: monitoring the unique identifier of the bayonet; (2) longitude kkjd: monitoring the longitude of the gate; (3) latitude kkwd: monitoring the latitude of the bayonet; (4) vehicle number plate hphm: passing through the license plate number of the vehicle at the bayonet; (5) passing time gcsj: the time the vehicle passes the gate.
Further, in step S2, the invalid data includes position anomaly data, that is, the longitude and latitude of the mount or the signaling data are not within the study range; field missing data, namely data with missing fields such as time, longitude and latitude, vehicle number plate and the like; and misidentification data, specifically data that the vehicle license plate identified by the gate is incorrect.
Further, in step S2, the time span filtering specifically includes selecting signaling and checkpoint data of 6:00 to 24:00 per day for calculation, and eliminating data outside the time period.
Further, in step S2, the movement frequency of the tracks is measured by calculating the information entropy of each track, and only tracks with information entropy greater than a threshold are selected for track matching calculation, where the information entropy threshold is 2. The specific calculation mode of the track information entropy value is as follows:
wherein D is a moving track of a vehicle or a mobile phone, Ent (D) is an information entropy value of the track, and pkM is the proportion of the k-th position point in the track, and m is the number of different position points in the track.
Further, in step S3, the specific process of the spatio-temporal trajectory matching algorithm is as follows:
a) extracting a moving track of a vehicle from the checkpoint data set according to the license plate number and the passing time, and arranging track points according to a time sequence;
b) sequentially taking a vehicle track point as a research object, and searching whether time-space constraint data which is centered on the vehicle track point and formed by a time threshold tau and a distance threshold epsilon exists in a signaling data set;
c) if yes, recording all mobile phone devices meeting the space-time constraint condition as a potential mobile phone matching data set of the vehicle;
d) then, taking the next vehicle track point, searching whether mobile phone equipment meeting the space-time constraint of the track point exists, if so, solving an intersection of the mobile phone equipment corresponding to the two track points, and if not, failing to match the vehicle;
e) and if the potential mobile phone matching data set is not empty at the last track point, the vehicle matching is successful.
The time threshold tau in the algorithm is 600 seconds and the distance threshold epsilon is 2000 meters.
Further, in step S4, the time range is one week or more, and the determination of the match indicates that the mobile phone is the mobile phone device carried by the corresponding vehicle driver.
Further, in step S5, the specific process of the data enhancement algorithm is as follows:
a) selecting a vehicle track and a mobile phone track which are determined to be matched, and randomly selecting a plurality of points from vehicle track points to form a new vehicle track;
b) for a new vehicle track, selecting a signaling data point meeting the space-time constraint of the new vehicle track from the corresponding mobile phone tracks to form a new mobile phone signaling track;
c) the sampled vehicle trajectory and signaling trajectory may be used as a new pair of deterministic matching trajectories.
Further, in step S6, the model is characterized by a shortest distance (CPD), a Hausdorff Distance (HD), a dynamic time warping Distance (DTW), a largest common substring (lcs), and an Edit Distance (EDR).
Further, in the step S6, the classification algorithm is a LightGBM algorithm, which is a fast, distributed, and high-performance gradient boosting algorithm based on a decision tree algorithm.
Compared with the prior art, the technical scheme of the invention has the beneficial effects that:
1. the traditional similarity calculation method is to enumerate any two tracks and calculate the similarity of the two tracks, and for millions of mobile phone users and vehicles in a city, a large amount of calculation resources are needed to finish the matching degree calculation. The method improves the matching calculation efficiency of massive heterogeneous tracks, firstly eliminates the tracks which are not frequently moved through the track information entropy, and secondly quickly eliminates a large number of dissimilar tracks by using the space-time constraint condition in the space-time track matching algorithm, thereby reducing a large amount of calculation overhead and reducing the calculation time.
2. The method combines a plurality of classical similarity indexes to construct a classification model based on the LightGBM algorithm, and the model can describe the space-time characteristics of the tracks more completely and effectively judge whether the two given heterogeneous tracks have a matching relation.
Drawings
FIG. 1 is a schematic flow diagram of the present invention.
Detailed Description
The drawings are for illustrative purposes only and are not to be construed as limiting the patent;
for the purpose of better illustrating the embodiments, certain features of the drawings may be omitted, enlarged or reduced, and do not represent the size of an actual product;
it will be understood by those skilled in the art that certain well-known structures in the drawings and descriptions thereof may be omitted.
The technical solution of the present invention is further described below with reference to the accompanying drawings and examples.
Example 1
As shown in fig. 1, a trajectory matching algorithm based on bayonet data and signaling data includes the following steps:
s1: acquiring a road gate monitoring data set and a mobile phone signaling data set in a research area and a research time period;
s2: preprocessing a bayonet data set and a signaling data set, wherein the preprocessing comprises invalid data cleaning, time span screening and frequent movement track screening;
s3: obtaining a potential matching data set of the vehicle and the mobile phone through a space-time trajectory matching algorithm;
s4: matching tracks of the vehicle and the mobile phone in the potential matching data set in different time periods, wherein if the tracks of the vehicle and the mobile phone keep the same matching relation in a time range, the vehicle and the mobile phone are determined to be matched;
s5: sampling the determined matching track by using a data enhancement algorithm to obtain more vehicle and mobile phone matching right cases; randomly selecting a vehicle and a mobile phone track from the bayonet and the signaling data set, and selecting the vehicle and mobile phone track which are in error matching as a counter example of matching between the vehicle and the mobile phone;
s6: and establishing a track classification model based on the positive example track data and the negative example track data obtained in the steps by adopting reasonable model characteristics and a classification algorithm with high accuracy.
The above steps will be described in detail below.
First, it is necessary to acquire recorded data of more than one week for all road checkpoints and cell phone base stations in a research area such as a prefecture-level administrative district or a county-level administrative district.
Secondly, vehicle access data and mobile phone signaling data are preprocessed:
a) deleting data of which the longitude and latitude coordinates are not in the research area; deleting data with field information being null value or invalid value; according to the motor vehicle number plate regulation of the people's republic of China (GA 36-2007), the data of wrong number plates in the card port data set is deleted.
b) And eliminating data of 0:00-6:00 in the vehicle access data set and the mobile phone signaling data set every day without participating in track matching calculation.
c) Screening out the daily tracks of each vehicle and each mobile phone through the license plate number, the mobile phone equipment number and the recording time, and calculating the information entropy value according to the geographical position of the track point in each track, wherein the calculation formula is as follows:
wherein D is a moving track of a vehicle or a mobile phone, Ent (D) is an information entropy value of the track, and pkM is the proportion of the k-th position point in the track, and m is the number of different position points in the track.
If the information entropy value of the track is less than 2, deleting the track from the corresponding data set without participating in track matching calculation.
And then, taking the bayonet data set and the signaling data set of a certain day in the research range to perform space-time trajectory matching algorithm operation.
a) Extracting a moving track c of a vehicle from the checkpoint data set according to the license plate number and the passing time, wherein track points are arranged according to a time sequence;
b) sequentially taking a vehicle track point lc1As a research object, whether data meeting space-time constraint formed by a time threshold τ and a distance threshold ε with the vehicle trajectory point as a center exists in a signaling data set is searched, and the space-time constraint is as follows:
(lc.x-ε,lc.y-ε,lc.t-τ)≤(ls.x,ls.y,ls.t)≤(lc.x+ε,lc.y+ε,lc.t+τ)
c) if the signaling data ls meeting the space-time constraint exists, the mobile phone devices corresponding to the tracks are recorded as a potential mobile phone matching data set cs of the vehicle1;
d) Then taking down a vehicle track point lc2Searching whether mobile phone cs meeting the space-time constraint of the track point exists or not2If the two track points exist, intersection of the mobile phone devices corresponding to the two track points is obtained, and if the two track points do not exist or the intersection is empty, the intersection is obtainedOrThe vehicle match fails;
e) and if the potential mobile phone matching data set is not empty at the last track point, the vehicle matching is successful.
Then, for a certain vehicle, if a certain mobile phone appears in its potential mobile phone matching data set within seven days of the week, the vehicle and the mobile phone are considered to be a definite match, i.e. the mobile phone is a mobile device carried by the driver of the vehicle.
Next, for a certain vehicle track c (lc) determined to match1,lc2,lc3,lc4,lc5,lc6) And a certain handset signaling trace s ═ (ls)1,ls2,ls3,ls4,ls5,ls6) Randomly selecting 3 points from the vehicle track to obtain a new vehicle trackThen according to the space-time constraint relation, a corresponding new mobile phone signaling track is obtainedThus, a new vehicle and mobile phone can be obtainedA correction example is carried out; and then randomly selecting the track of the vehicle and the mobile phone from the bayonet and the signaling data set, and selecting the track of the vehicle and the mobile phone which are in error matching as a counter example of matching of the vehicle and the mobile phone.
Finally, different eigenvalues of the matching positive examples and the matching negative examples, including the shortest distance (CPD), the Hausdorff Distance (HD), the dynamic time warping Distance (DTW), the largest common substring (lcs), and the Edit Distance (EDR), are calculated, respectively, to form a data set as shown in table 1.
Table 1 schematic representation of data sets
ID | hphm | isdn | CPD | SPD | DTW | LCSS | EDR | Label |
1 | @#$E8 | 5ea3bd | 38.80 | 2354 | 397.66 | 5 | 46 | 1 |
2 | $%#91 | 2fb9df | 42.48 | 3812 | 266.43 | 3 | 47 | 0 |
3 | !#$@19 | ed2e83. | 19.16 | 227 | 237.84 | 7 | 51 | 1 |
And randomly selecting 70% of data from the data set as a training set, inputting the training set into a LightGBM model for training, and predicting the rest 30% of data.
The same or similar reference numerals correspond to the same or similar parts;
the positional relationships depicted in the drawings are for illustrative purposes only and are not to be construed as limiting the present patent;
it should be understood that the above-described embodiments of the present invention are merely examples for clearly illustrating the present invention, and are not intended to limit the embodiments of the present invention. Other variations and modifications will be apparent to persons skilled in the art in light of the above description. And are neither required nor exhaustive of all embodiments. Any modification, equivalent replacement, and improvement made within the spirit and principle of the present invention should be included in the protection scope of the claims of the present invention.
Claims (7)
1. A track matching method based on bayonet data and signaling data is characterized by comprising the following steps:
s1: acquiring a road gate monitoring data set and a mobile phone signaling data set in a research area and a research time period;
s2: preprocessing a bayonet data set and a signaling data set, wherein the preprocessing comprises invalid data cleaning, time span screening and frequent movement track screening;
s3: obtaining a potential matching data set of the vehicle and the mobile phone through a space-time trajectory matching algorithm;
s4: matching tracks of the vehicle and the mobile phone in the potential matching data set in different time periods, wherein if the tracks of the vehicle and the mobile phone keep the same matching relation in a time range, the vehicle and the mobile phone are determined to be matched;
s5: sampling the determined matching track by using a data enhancement algorithm to obtain more vehicle and mobile phone matching right cases; randomly selecting a vehicle and a mobile phone track from the bayonet and the signaling data set, and selecting the vehicle and mobile phone track which are in error matching as a counter example of matching between the vehicle and the mobile phone;
s6: establishing a track classification model based on the positive example track data and the negative example track data obtained in the step by adopting model characteristics and a classification algorithm;
in step S2, the movement frequency of the tracks is measured by calculating the information entropy of each track, and only tracks with information entropy greater than a threshold are selected for track matching calculation, where the information entropy threshold is 2; the specific calculation mode of the track information entropy value is as follows:
wherein D is a moving track of a vehicle or a mobile phone, Ent (D) is an information entropy value of the track, and pkM is the proportion of the k-th position point in the track, and m is the number of different position points in the track;
in step S3, the specific process of the space-time trajectory matching algorithm is as follows:
a) extracting a moving track of a vehicle from the checkpoint data set according to the license plate number and the passing time, and arranging track points according to a time sequence;
b) sequentially taking a vehicle track point as a research object, and searching whether time-space constraint data which is centered on the vehicle track point and formed by a time threshold tau and a distance threshold epsilon exists in a signaling data set;
c) if yes, recording all mobile phone devices meeting the space-time constraint condition as a potential mobile phone matching data set of the vehicle;
d) then, taking the next vehicle track point, searching whether mobile phone equipment meeting the space-time constraint of the track point exists, if so, solving an intersection of the mobile phone equipment corresponding to the two track points, and if not, failing to match the vehicle;
e) if the potential mobile phone matching data set is not empty at the last track point, the vehicle matching is successful;
in the algorithm, the time threshold tau is 600 seconds, and the distance threshold epsilon is 2000 meters;
in step S5, the specific process of the data enhancement algorithm is as follows:
a) selecting a vehicle track and a mobile phone track which are determined to be matched, and randomly selecting a plurality of points from vehicle track points to form a new vehicle track;
b) for a new vehicle track, selecting a signaling data point meeting the space-time constraint of the new vehicle track from the corresponding mobile phone tracks to form a new mobile phone signaling track;
c) the sampled vehicle trajectory and signaling trajectory may be used as a new pair of deterministic matching trajectories.
2. The trajectory matching method based on bayonet data and signaling data according to claim 1, wherein the mobile phone signaling data in step S1 includes: (1) user number isdn: the unique identification of the mobile phone user; (2) longitude, ng: the longitude of the location of the user; (3) latitude lat: the latitude of the location of the user; (4) time: the time when the signaling record is generated; the bayonet monitoring data comprises: (1) bayonet number kdbh: monitoring the unique identifier of the bayonet; (2) longitude kkjd: monitoring the longitude of the gate; (3) latitude kkwd: monitoring the latitude of the bayonet; (4) vehicle number plate hphm: passing through the license plate number of the vehicle at the bayonet; (5) passing time gcsj: the time the vehicle passes the gate.
3. The trajectory matching method based on bayonet data and signaling data as claimed in claim 2, wherein in step S2, the invalid data includes position anomaly data, i.e. the longitude and latitude of the bayonet data or the signaling data are not in the study range; field missing data, namely data with missing fields such as time, longitude and latitude, vehicle number plate and the like; and misidentification data, specifically data that the vehicle license plate identified by the gate is incorrect.
4. The trajectory matching method according to claim 3, wherein in step S2, the time span filtering is to select signaling and checkpoint data from 6:00 to 24:00 per day for calculation, and to eliminate data outside the time period.
5. The trajectory matching method according to claim 4, wherein in step S4, the time range is one week or more, and the determination of the matching indicates that the mobile phone is a mobile phone device carried by the corresponding vehicle driver.
6. The trajectory matching method according to claim 5, wherein in step S6, the models are characterized by a shortest distance (CPD), a Hausdorff Distance (HD), a dynamic time warping Distance (DTW), a largest common substring (LCSS), and an Edit Distance (EDR).
7. The trajectory matching method according to claim 6, wherein in step S6, the classification algorithm is a LightGBM algorithm, which is a fast, distributed, and high-performance gradient boosting algorithm based on a decision tree algorithm.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201910666051.0A CN110505583B (en) | 2019-07-23 | 2019-07-23 | Trajectory matching method based on bayonet data and signaling data |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201910666051.0A CN110505583B (en) | 2019-07-23 | 2019-07-23 | Trajectory matching method based on bayonet data and signaling data |
Publications (2)
Publication Number | Publication Date |
---|---|
CN110505583A CN110505583A (en) | 2019-11-26 |
CN110505583B true CN110505583B (en) | 2021-01-22 |
Family
ID=68586670
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN201910666051.0A Active CN110505583B (en) | 2019-07-23 | 2019-07-23 | Trajectory matching method based on bayonet data and signaling data |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN110505583B (en) |
Families Citing this family (18)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN111417088B (en) * | 2020-03-25 | 2024-03-15 | 商车云(北京)科技有限公司 | Identity attribute authentication method for Internet of vehicles data |
CN111523577A (en) * | 2020-04-13 | 2020-08-11 | 南京烽火星空通信发展有限公司 | Mass trajectory similarity calculation method based on improved LCSS algorithm |
CN111521191A (en) * | 2020-04-20 | 2020-08-11 | 中国农业科学院农业信息研究所 | Mobile phone user moving path map matching method based on signaling data |
CN111950937B (en) * | 2020-09-01 | 2023-12-01 | 上海海事大学 | Important personnel risk assessment method based on fusion of space-time trajectories |
CN112511971B (en) * | 2020-11-26 | 2022-08-16 | 西安建筑科技大学 | Travel mode identification method based on mobile phone signaling data |
CN112672288B (en) * | 2020-12-15 | 2022-11-04 | 佳都科技集团股份有限公司 | Vehicle track prediction method and device based on checkpoint recording |
CN112785223B (en) * | 2021-01-05 | 2022-06-07 | 中交智运有限公司 | Space-time trajectory matching method and system based on Beidou positioning and mobile signaling |
CN112734219B (en) * | 2021-01-05 | 2023-07-21 | 中交智运有限公司 | Vehicle transportation running behavior analysis method and system |
CN112634457B (en) * | 2021-01-06 | 2022-07-05 | 广西科技大学 | Point cloud simplification method based on local entropy of Hausdorff distance and average projection distance |
CN113160551B (en) * | 2021-01-12 | 2022-08-19 | 北京品恩科技股份有限公司 | Traffic big data based accompanying model application method |
CN113487865B (en) * | 2021-07-02 | 2022-07-22 | 江西锦路科技开发有限公司 | System and method for acquiring information of vehicles running on highway |
CN113723316B (en) * | 2021-09-01 | 2024-04-16 | 杭州智诚惠通科技有限公司 | Vehicle identification method, device, equipment and storage medium |
CN113806465B (en) * | 2021-09-22 | 2022-05-03 | 公安部交通管理科学研究所 | Bayonet position longitude and latitude deviation correction method based on new energy automobile track data |
CN114390459A (en) * | 2021-12-27 | 2022-04-22 | 安徽百诚慧通科技有限公司 | Method for identifying illegal and excessive person carrying of agricultural vehicle and storage medium |
CN114416710B (en) * | 2021-12-29 | 2023-04-07 | 苏州大学 | Method and system for extracting OD position of express way vehicle |
CN114372382B (en) * | 2022-03-22 | 2022-06-10 | 交通运输部公路科学研究所 | Method, device and storage medium for evaluating reliability of vehicle track |
CN115877343B (en) * | 2023-02-02 | 2023-05-05 | 中电信数字城市科技有限公司 | Man-car matching method and device based on radar target tracking and electronic equipment |
CN116258488B (en) * | 2023-03-17 | 2024-01-26 | 中远海运科技股份有限公司 | Data preprocessing method and system for accurately restoring actual passing track of vehicle |
Citations (6)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN104462193A (en) * | 2014-10-28 | 2015-03-25 | 上海市政工程设计研究总院(集团)有限公司 | Vehicle movement trajectory searching system and method based on time-space matching |
CN106303962A (en) * | 2016-08-17 | 2017-01-04 | 公安部道路交通安全研究中心 | A kind of method and system realizing people's car information association |
EP3376390A1 (en) * | 2017-03-17 | 2018-09-19 | TTTech Computertechnik AG | Fault tolerant method for controlling an autonomous controlled object |
CN108629978A (en) * | 2018-06-07 | 2018-10-09 | 重庆邮电大学 | A kind of traffic trajectory predictions method based on higher-dimension road network and Recognition with Recurrent Neural Network |
CN109344725A (en) * | 2018-09-04 | 2019-02-15 | 上海交通大学 | A kind of online tracking of multirow people based on space-time attention rate mechanism |
CN109635059A (en) * | 2018-11-23 | 2019-04-16 | 武汉烽火众智数字技术有限责任公司 | People's vehicle association analysis method and system based on track similarity mode |
Family Cites Families (2)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
US10102247B2 (en) * | 2015-09-30 | 2018-10-16 | International Business Machines Corporation | Precision adaptive vehicle trajectory query plan optimization |
CN107463940B (en) * | 2017-06-29 | 2020-02-21 | 清华大学 | Vehicle type identification method and device based on mobile phone data |
-
2019
- 2019-07-23 CN CN201910666051.0A patent/CN110505583B/en active Active
Patent Citations (6)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN104462193A (en) * | 2014-10-28 | 2015-03-25 | 上海市政工程设计研究总院(集团)有限公司 | Vehicle movement trajectory searching system and method based on time-space matching |
CN106303962A (en) * | 2016-08-17 | 2017-01-04 | 公安部道路交通安全研究中心 | A kind of method and system realizing people's car information association |
EP3376390A1 (en) * | 2017-03-17 | 2018-09-19 | TTTech Computertechnik AG | Fault tolerant method for controlling an autonomous controlled object |
CN108629978A (en) * | 2018-06-07 | 2018-10-09 | 重庆邮电大学 | A kind of traffic trajectory predictions method based on higher-dimension road network and Recognition with Recurrent Neural Network |
CN109344725A (en) * | 2018-09-04 | 2019-02-15 | 上海交通大学 | A kind of online tracking of multirow people based on space-time attention rate mechanism |
CN109635059A (en) * | 2018-11-23 | 2019-04-16 | 武汉烽火众智数字技术有限责任公司 | People's vehicle association analysis method and system based on track similarity mode |
Non-Patent Citations (3)
Title |
---|
《UPS: Combatting Urban Vehicle Localization with Cellular-Aware Trajectories》;Hua Xue;《2016 IEEE Global Communications Conference (GLOBECOM)》;20170206;全文 * |
《基于大数据的城市居民出行分析建模》;蔡正义;《中国博士学位论文全文数据库》;20181231;全文 * |
《基于无线网络流量的用户移动性分析与应用》;吕遒健;《中国博士学位论文全文数据库》;20180228;全文 * |
Also Published As
Publication number | Publication date |
---|---|
CN110505583A (en) | 2019-11-26 |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
CN110505583B (en) | Trajectory matching method based on bayonet data and signaling data | |
CN107040894B (en) | A kind of resident trip OD acquisition methods based on mobile phone signaling data | |
CN105574506A (en) | Intelligent face tracking system and method based on depth learning and large-scale clustering | |
CN205451095U (en) | A face -identifying device | |
Zhou et al. | A data-driven method for trip ends identification using large-scale smartphone-based GPS tracking data | |
Huang et al. | Crowdsourcing-based urban anomaly prediction system for smart cities | |
Yue et al. | Detect: Deep trajectory clustering for mobility-behavior analysis | |
CN111666823B (en) | Pedestrian re-identification method based on individual walking motion space-time law collaborative identification | |
CN108363783B (en) | The binding method and device of MAC Address and identity information | |
CN112770265B (en) | Pedestrian identity information acquisition method, system, server and storage medium | |
CN103699677A (en) | Criminal track map drawing system and method based on face recognition | |
Huo et al. | Short-term estimation and prediction of pedestrian density in urban hot spots based on mobile phone data | |
CN104200206A (en) | Double-angle sequencing optimization based pedestrian re-identification method | |
CN105426862A (en) | Analysis method and system based on RFID (Radio Frequency Identification Devices), positioning technology and video technology | |
CN115841683A (en) | Light-weight pedestrian re-identification method combining multi-level features | |
Ghorpade et al. | An integrated stop-mode detection algorithm for real world smartphone-based travel survey | |
CN113962326A (en) | Clustering method, device, equipment and computer storage medium | |
Imai et al. | Origin-destination trips generated from operational data of a mobile network for urban transportation planning | |
CN115511210A (en) | Community life circle defining method and device based on multi-source big data | |
CN111078973A (en) | Fake-licensed vehicle identification method and equipment based on big data and storage medium | |
CN111651484B (en) | Method and device for analyzing accompanying relation of moving object based on semantic track similarity | |
CN115002697A (en) | Contact user identification method, device, equipment and storage medium for user to be checked | |
Ma et al. | Human trajectory completion with transformers | |
Zhang et al. | Prnet: Outdoor position recovery for heterogenous telco data by deep neural network | |
CN111970685B (en) | One-person multi-card identification method in big data environment |
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 | ||
OL01 | Intention to license declared |