CN113739814B - Passenger getting-off point extraction optimization method based on taxi track sequence - Google Patents
Passenger getting-off point extraction optimization method based on taxi track sequence Download PDFInfo
- Publication number
- CN113739814B CN113739814B CN202110992319.7A CN202110992319A CN113739814B CN 113739814 B CN113739814 B CN 113739814B CN 202110992319 A CN202110992319 A CN 202110992319A CN 113739814 B CN113739814 B CN 113739814B
- Authority
- CN
- China
- Prior art keywords
- point
- sequence
- track
- points
- passenger
- 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
Classifications
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01C—MEASURING DISTANCES, LEVELS OR BEARINGS; SURVEYING; NAVIGATION; GYROSCOPIC INSTRUMENTS; PHOTOGRAMMETRY OR VIDEOGRAMMETRY
- G01C21/00—Navigation; Navigational instruments not provided for in groups G01C1/00 - G01C19/00
- G01C21/26—Navigation; Navigational instruments not provided for in groups G01C1/00 - G01C19/00 specially adapted for navigation in a road network
- G01C21/34—Route searching; Route guidance
- G01C21/3407—Route searching; Route guidance specially adapted for specific applications
- G01C21/343—Calculating itineraries, i.e. routes leading from a starting point to a series of categorical destinations using a global route restraint, round trips, touristic trips
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01C—MEASURING DISTANCES, LEVELS OR BEARINGS; SURVEYING; NAVIGATION; GYROSCOPIC INSTRUMENTS; PHOTOGRAMMETRY OR VIDEOGRAMMETRY
- G01C21/00—Navigation; Navigational instruments not provided for in groups G01C1/00 - G01C19/00
- G01C21/26—Navigation; Navigational instruments not provided for in groups G01C1/00 - G01C19/00 specially adapted for navigation in a road network
- G01C21/34—Route searching; Route guidance
- G01C21/3453—Special cost functions, i.e. other than distance or default speed limit of road segments
Landscapes
- Engineering & Computer Science (AREA)
- Radar, Positioning & Navigation (AREA)
- Remote Sensing (AREA)
- Automation & Control Theory (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Management, Administration, Business Operations System, And Electronic Commerce (AREA)
- Traffic Control Systems (AREA)
Abstract
The invention discloses a passenger getting-off point extraction optimization method based on a taxi track sequence, which specifically comprises the following steps of; s1, acquiring taxi track data and extracting a passenger point; s2, selecting a relatively determined entrance and exit of a destination point in the city, and setting buffer areas in front of the entrance and on adjacent roads leading to the entrance as a deviation area between a destination point accurate area and the destination point; s3, screening out a passenger point sitting in the buffer area; s4, extracting track points of the guest points reserved in the S3 respectively, and generating a non-partial sequence TST and a partial sequence TSW respectively after standardized processing; s5, respectively calculating the similarity of the track sequence in the TST and the track sequence in the TSW by using a DTW sequence similarity measurement method; s6, taking the point in the TSW, where the running speed is closest to the running speed of the 5 th track point in the TSM, as the corrected get-off point. The method provides an extraction optimization measure for the taxi boarding points, so that the extraction precision of the taxi boarding points is improved.
Description
Technical Field
The invention relates to a passenger getting-off point extraction optimization method based on a taxi track sequence, and belongs to the technical field of position deviation correction methods.
Background
With the continuous development of economy and society and the continuous improvement of living standard of people, people start to choose taxi travel services so as to meet the requirements of convenience and comfort. The taxi is one of the main components of urban traffic in China at present, and the taxi track data can well reflect the traveling behaviors of residents and the operation conditions of the urban traffic, so that many students can conduct research by utilizing the taxi track data, such as research on road congestion conditions based on the taxi track data, urban functional area identification research, population flow pattern research and urban entrance discovery research. Most of the above researches need the pick-up results of the taxi's boarding points, but in real life, the taxi driver usually finishes the order in advance habitually when arriving at the passenger destination, on one hand, the taxi driver gives the customer a sense of well, and on the other hand, the taxi driver is helpful for improving his own good score, and on the other hand, the taxi driver is also helpful for the system to arrange new orders for the taxi driver as soon as possible, so that the number of orders is increased. The behavior is multi-purpose for drivers, but causes a plurality of inconveniences for scientific researchers, so that the passenger getting-off points extracted by the taxi track information and the real passenger getting-off points have larger position deviation, thereby greatly influencing the experimental result. Therefore, it is necessary to design an optimization method for extracting the taxi get-off points, so that the extraction accuracy of the taxi get-off points is improved.
Disclosure of Invention
Aiming at the problems in the prior art, the invention provides a passenger getting-off point extraction optimization method based on a taxi track sequence, so that the extraction precision of the passenger getting-off point of a taxi is improved.
In order to achieve the above purpose, the technical scheme adopted by the invention is as follows: the passenger getting-off point extraction and optimization method based on the taxi track sequence specifically comprises the following steps of;
s1, acquiring taxi track data and extracting a passenger drop point according to the change condition of a passenger carrying state field and a time field;
s2, selecting a relatively determined entrance and exit of a destination point in the city, and setting buffer areas in front of the entrance and on adjacent roads leading to the entrance as a deviation area between a destination point accurate area and the destination point;
s3, screening out the passenger points sitting in the buffer area, and cleaning the passenger points according to the running direction and the running speed of the vehicle;
s4, extracting 4 track points from the lower guest points reserved in the S3, generating a track sequence with the length of 9, and respectively generating an unbiased sequence TST with accurate lower guest points and an ordered sequence TSW with deviation of the lower guest points after standardized processing;
s5, respectively calculating the similarity of the track sequence in the TST and the track sequence in the TSW by using a DTW sequence similarity measurement method;
s6, selecting a track sequence TSM with highest similarity with the TSW sequence in the TST as a matching sequence, and taking a point with the closest running speed to the 5 th track point in the TSW as a corrected passenger point.
Preferably, the step S1 specifically includes:
s11, pre-extracting a boarding point and a alighting point according to the change condition of a boarding state field of taxi track information, wherein the moment when the taxi is changed into an empty taxi is the alighting point, and the moment when the empty taxi is changed into the taxi is the boarding point;
s12, cleaning the extraction result of the customer points according to the time field in the track data, and removing the customer points on and off with the order execution time less than 5 minutes.
Preferably, the step S3 specifically includes:
s31, judging the spatial position relation between the lower guest point and the buffer area established in the S2 according to a ray-guiding method, namely, emitting a ray from the lower guest point, judging according to the number of intersection points of all sides of the ray and the polygon, if an odd number of intersection points exist, the lower guest point is inside the buffer area, and if an even number of intersection points exist, the lower guest point is outside the buffer area; screening out the visitor points with the number of the intersection points being odd, namely falling into the buffer zone;
s32: and cleaning the passenger points according to the running direction of the vehicle and the running speed of the vehicle in the buffer zone, namely removing the passenger points with the included angle between the running direction D1 in the adjacent road buffer zone and the direction D2 of the entrance and the vehicle being more than 45 degrees and the passenger points with the running speed being 0, so as to ensure that the destination of the passenger points extracted in the step S32 is the selected entrance.
Preferably, the step S4 specifically includes:
s41, taking the passenger point extracted in the S3 as a track center, extracting the running speeds of 4 track points before and after the point respectively, and generating a taxi track sequence { dp ] with the length of 9 1 ，dp 2 ，dp 3 ，dp 4 ，dp 5 ，dp 6 ，dp 7 ，dp 8 ，dp 9 (dp), where 5 Pre-extracting a foreign point for the sequence;
s42, processing the data by using a 0-1 standardization method to eliminate the influence of the data variation size factor, so as to generate an unbiased sequence TST with accurate position of the lower guest point and an ordered sequence TSW with deviation of the position of the lower guest point. The normalization formula is as follows:
wherein x is * For normalized sequence values, x is the current sequence value being processed, x min Is the minimum value of the current sequence, x max Is the maximum value of the current sequence.
Preferably, the step S5 specifically includes:
s51, using a matrix M of 9*9 to represent the distance between each point of two track sequences A and B, wherein the distance between the two points is as follows:
M(i，j)＝|A(i)-B(j)|，1≤i，j≤9
wherein M (i, j) is the distance between the ith point of the sequence A and the jth point of the sequence B, A (i) is the running speed of the ith track point of the track sequence A, and B (j) is the running speed of the jth track point of the track sequence B;
s52, initializing the shortest distance between the track sequences A and B, namely:
L min (1，1)＝M(1，1)
wherein L is min (1, 1) is the shortest distance from the 1 st point in the sequence A to the 1 st point in the sequence B, and M (1, 1) is the distance from the 1 st point in the sequence A to the 1 st point in the sequence B;
s53, solving the shortest distance between the track sequence A and the track sequence B according to the following recursion rule:
L min (i，j)＝min{L min (i，j-1)，L min (i-1，j)，L min (i-1，j-1)}+M(i，j)
wherein L is min (i, j) is the ith in sequence AThe shortest distance from the point to the jth point in the sequence B, M (i, j) is the distance from the ith point in the sequence A to the jth point in the sequence B;
the distance obtained according to the recursive algorithm is the shortest distance between the track sequences A and B, and the distance is used for representing the similarity degree of the two track sequences.
The beneficial effects of the invention are as follows: according to the method, the taxi track data are cleaned, so that the influence of systematic errors and accidental errors on the pick-up result of the passenger drop is eliminated; the taxi driving track sequence taking the passenger point as the center is constructed, the unbiased track sequence with the highest similarity with the biased track sequence is extracted by a DTW sequence similarity measurement method, the corrected passenger point is extracted by a vehicle speed matching method, and the extraction precision of the passenger point of the taxi is effectively improved.
Drawings
FIG. 1 is a flow chart of an embodiment of a method for optimizing the extraction of a passenger point based on a taxi track sequence;
FIG. 2 is a diagram of a buffer-based point of entry extraction of the present invention;
FIG. 3 is a schematic diagram of the highest similarity sequence based next-point optimization of the present invention;
fig. 4 is a graph of the extraction optimization result of the next point according to the present invention.
Detailed Description
The present invention will be further described in detail with reference to the drawings and examples, in order to make the objects, technical solutions and advantages of the present invention more apparent. It should be understood that the detailed description and specific examples, while indicating the invention, are intended for purposes of illustration only and are not intended to limit the scope of the invention.
Unless defined otherwise, all technical and scientific terms used herein have the same meaning as commonly understood by one of ordinary skill in the art to which this invention belongs, and the terms used herein in this description of the invention are for the purpose of describing particular embodiments only and are not intended to be limiting of the invention.
Referring to fig. 1 to 4, the passenger getting-off point extraction and optimization method based on a taxi track sequence of the invention comprises the following steps:
s1, acquiring taxi track data and extracting a passenger drop point according to the change condition of a passenger carrying state field and a time field;
s11, pre-extracting a boarding point and a alighting point according to the change condition of a boarding state field of taxi track information, wherein the moment when the taxi is changed into the empty taxi is the alighting point, and the moment when the taxi is changed into the taxi is the boarding point.
S12, taking account of noise points in the extraction result caused by systematic errors and accidental errors in the track data, cleaning the extraction result of the next guest point according to the time field in the track data, and removing the next guest point with the order execution time less than 5 minutes.
S2, selecting a relatively determined entrance and exit of the position of the destination in the city, and setting buffer areas in front of the entrance and on adjacent roads leading to the entrance as accurate areas of the position of the destination and areas of deviation of the position of the destination.
S3, screening out the passenger points sitting in the buffer area, and cleaning the passenger points according to the running direction and the running speed of the vehicle;
s31, judging the spatial position relation between the next point and the buffer area established in the S2 according to a ray-guiding method, namely, emitting a ray from the next point, judging according to the number of intersection points of all sides of the ray and the polygon, if an odd number of intersection points exist, the next point is inside the buffer area, and if an even number of intersection points exist, the next point is outside the buffer area. And screening out the points of intersection with odd number, namely the points of the offal falling in the buffer area.
S32: and cleaning the passenger points according to the running direction of the vehicle and the running speed of the vehicle in the buffer zone, namely removing the passenger points with the included angle between the running direction D1 in the adjacent road buffer zone and the direction D2 of the entrance and the vehicle being more than 45 degrees and the passenger points with the running speed being 0, so as to ensure that the destination of the passenger points extracted in the step S32 is the selected entrance.
S4, extracting 4 track points from the lower guest points reserved in the S3, generating a track sequence with the length of 9, and respectively generating an unbiased sequence TST with accurate lower guest points and an ordered sequence TSW with deviation of the lower guest points after standardized processing;
s41, taking the passenger point extracted in the S3 as a track center, extracting the running speeds of 4 track points before and after the point respectively, and generating a taxi track sequence { dp ] with the length of 9 1 ，dp 2 ，dp 3 ，dp 4 ，dp 5 ，dp 6 ，dp 7 ，dp 8 ，dp 9 (dp), where 5 Is the point of the sequence that is to be checked off.
S42, processing the data by using a 0-1 standardization method to eliminate the influence of the data variation size factor, so as to generate a track sequence TST with accurate position of the lower guest point and a track sequence TSW with deviation of the position of the lower guest point. The normalization formula is as follows:
wherein x is * For normalized sequence values, x is the current sequence value being processed, x min Is the minimum value of the current sequence, x max Is the maximum value of the current sequence.
S5, respectively calculating the similarity of the track sequence in the TST and the track sequence in the TSW by using a DTW sequence similarity measurement method.
S51, using a matrix M of 9*9 to represent the distance between each point of two track sequences A and B, wherein the distance between the two points is as follows:
M(i，j)＝|A(i)-B(j)|，1≤i，j≤9
where M (i, j) is the distance between the ith point of the sequence a and the jth point of the sequence B, a (i) is the travel speed of the ith track point of the track sequence a, and B (j) is the travel speed of the jth track point of the track sequence B.
S52, initializing the shortest distance between the track sequences A and B, namely:
L min (1，1)＝M(1，1)
wherein L is min (1, 1) is the first in the sequence AThe shortest distance from 1 point to the 1 st point in the sequence B, M (1, 1) is the distance from the 1 st point in the sequence a to the 1 st point in the sequence B.
S53, solving the shortest distance between the track sequence A and the track sequence B according to the following recursion rule:
L min (i，j)＝min{L min (i，j-1)，L min (i-1，j)，L min (i-1，j-1)}+M(i，j)
wherein L is min (i, j) is the shortest distance from the ith point in the sequence A to the jth point in the sequence B, and M (i, j) is the distance from the ith point in the sequence A to the jth point in the sequence B.
The distance obtained according to the recursive algorithm is the shortest distance between the track sequences A and B, and the distance is used for representing the similarity degree of the two track sequences.
S6, selecting a track sequence TSM with highest similarity with the TSW sequence in the TST as a matching sequence, and taking a point with the closest running speed to the 5 th track point in the TSW as a corrected passenger point.
Firstly, cleaning taxi track data, so that the influence of systematic errors and accidental errors on the pick-up result of a passenger drop is eliminated; the taxi driving track sequence taking the passenger point as the center is constructed, the unbiased track sequence with the highest similarity with the biased track sequence is extracted by a DTW sequence similarity measurement method, the corrected passenger point is extracted by a vehicle speed matching method, and the extraction precision of the passenger point of the taxi is effectively improved.
The foregoing description of the preferred embodiments of the invention is not intended to be limiting, but rather is intended to cover all modifications, equivalents, or alternatives falling within the spirit and principles of the invention.
Claims (5)
1. The passenger getting-off point extraction and optimization method based on the taxi track sequence is characterized by comprising the following steps of;
s1, acquiring taxi track data and extracting a passenger drop point according to the change condition of a passenger carrying state field and a time field;
s2, selecting a relatively determined entrance and exit of a destination point in the city, and setting buffer areas in front of the entrance and on adjacent roads leading to the entrance as a deviation area between a destination point accurate area and the destination point;
s3, screening out the passenger points sitting in the buffer area, and cleaning the passenger points according to the running direction and the running speed of the vehicle;
s4, extracting 4 track points from the lower guest points reserved in the S3, generating a track sequence with the length of 9, and respectively generating an unbiased sequence TST with accurate lower guest points and an ordered sequence TSW with deviation of the lower guest points after standardized processing;
s5, respectively calculating the similarity of the track sequence in the TST and the track sequence in the TSW by using a DTW sequence similarity measurement method;
s6, selecting a track sequence TSM with highest similarity with the TSW sequence in the TST as a matching sequence, and taking a point with the closest running speed to the 5 th track point in the TSW as a corrected passenger point.
2. The passenger getting-off point extraction and optimization method based on the taxi track sequence according to claim 1, wherein the step S1 is specifically:
s11, pre-extracting a boarding point and a alighting point according to the change condition of a boarding state field of taxi track information, wherein the moment when the taxi is changed into an empty taxi is the alighting point, and the moment when the empty taxi is changed into the taxi is the boarding point;
s12, cleaning the extraction result of the customer points according to the time field in the track data, and removing the customer points on and off with the order execution time less than 5 minutes.
3. The passenger getting-off point extraction and optimization method based on the taxi track sequence according to claim 1, wherein the step S3 is specifically:
s31, judging the spatial position relation between the lower guest point and the buffer area established in the S2 according to a ray-guiding method, namely, emitting a ray from the lower guest point, judging according to the number of intersection points of all sides of the ray and the polygon, if an odd number of intersection points exist, the lower guest point is inside the buffer area, and if an even number of intersection points exist, the lower guest point is outside the buffer area; screening out the visitor points with the number of the intersection points being odd, namely falling into the buffer zone;
s32: and cleaning the passenger points according to the running direction of the vehicle and the running speed of the vehicle in the buffer zone, namely removing the passenger points with the included angle between the running direction D1 in the adjacent road buffer zone and the direction D2 of the entrance and the vehicle being more than 45 degrees and the passenger points with the running speed being 0, so as to ensure that the destination of the passenger points extracted in the step S32 is the selected entrance.
4. The passenger getting-off point extraction and optimization method based on the taxi track sequence according to claim 1, wherein the step S4 is specifically:
s41, taking the passenger point extracted in the S3 as a track center, extracting the running speeds of 4 track points before and after the point respectively, and generating a taxi track sequence { dp ] with the length of 9 1 ，dp 2 ，dp 3 ，dp 4 ，dp 5 ，dp 6 ，dp 7 ，dp 8 ，dp 9 (dp), where 5 Pre-extracting a foreign point for the sequence;
s42, in order to eliminate the influence of the data variation size factor, a 0-1 standardization method is used for processing the data, so that an unbiased sequence TST with accurate position of a lower guest point and an ordered sequence TSW with deviation of the position of the lower guest point are generated, and the standardization formula is as follows:
wherein x is * For normalized sequence values, x is the current sequence value being processed, x min Is the minimum value of the current sequence, x max Is the maximum value of the current sequence.
5. The passenger getting-off point extraction and optimization method based on the taxi track sequence according to claim 1, wherein the step S5 is specifically:
s51, using a matrix M of 9*9 to represent the distance between each point of two track sequences A and B, wherein the distance between the two points is as follows:
M(i，j)＝|A(i)-B(j)|，1≤i，j≤9
wherein M (i, j) is the distance between the ith point of the sequence A and the jth point of the sequence B, A (i) is the running speed of the ith track point of the track sequence A, and B (j) is the running speed of the jth track point of the track sequence B;
s52, initializing the shortest distance between the track sequences A and B, namely:
L min (1，1)＝M(1，1)
wherein L is min (1, 1) is the shortest distance from the 1 st point in the sequence A to the 1 st point in the sequence B, and M (1, 1) is the distance from the 1 st point in the sequence A to the 1 st point in the sequence B;
s53, solving the shortest distance between the track sequence A and the track sequence B according to the following recursion rule:
L min (i，j)＝min{L min (i，j-1)，L min (i-1，j)，L min (i-1，j-1)}+M(i，j)
wherein L is min (i, j) is the shortest distance from the ith point in the sequence A to the jth point in the sequence B, and M (i, j) is the distance from the ith point in the sequence A to the jth point in the sequence B;
the distance obtained according to the recursive algorithm is the shortest distance between the track sequences A and B, and the distance is used for representing the similarity degree of the two track sequences.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202110992319.7A CN113739814B (en) | 2021-08-27 | 2021-08-27 | Passenger getting-off point extraction optimization method based on taxi track sequence |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202110992319.7A CN113739814B (en) | 2021-08-27 | 2021-08-27 | Passenger getting-off point extraction optimization method based on taxi track sequence |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN113739814A CN113739814A (en) | 2021-12-03 |
| CN113739814B true CN113739814B (en) | 2023-09-26 |
Family
ID=78733212
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202110992319.7A Active CN113739814B (en) | 2021-08-27 | 2021-08-27 | Passenger getting-off point extraction optimization method based on taxi track sequence |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN113739814B (en) |
Families Citing this family (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN114329247A (en) * | 2021-12-30 | 2022-04-12 | 联合汽车电子有限公司 | Method, device and equipment for acquiring travel route and storage medium |
Citations (9)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN108537391A (en) * | 2018-04-25 | 2018-09-14 | 哈尔滨工业大学 | A kind of taxi bus stop setting optimization method based on taxi track data |
| CN108959466A (en) * | 2018-06-20 | 2018-12-07 | 淮阴工学院 | Taxi hot spot method for visualizing and system based on BCS-DBSCAN |
| CN109254861A (en) * | 2018-09-17 | 2019-01-22 | 江苏智通交通科技有限公司 | OD requirement extract and its analysis method for reliability based on track data |
| CN110413855A (en) * | 2019-07-11 | 2019-11-05 | 南通大学 | A kind of region entrance Dynamic Extraction method based on taxi drop-off point |
| CN110458589A (en) * | 2019-02-01 | 2019-11-15 | 吉林大学 | Trackside formula taxi bus stop addressing preferred method based on track big data |
| CN110555992A (en) * | 2019-09-11 | 2019-12-10 | 中国矿业大学(北京) | taxi driving path information extraction method based on GPS track data |
| CN110990661A (en) * | 2019-10-23 | 2020-04-10 | 南通大学 | Interest area entrance and exit extraction method based on road network constraint and density clustering |
| CN111814596A (en) * | 2020-06-20 | 2020-10-23 | 南通大学 | Automatic city function partitioning method for fusing remote sensing image and taxi track |
| CN113163330A (en) * | 2021-03-24 | 2021-07-23 | 广州宸祺出行科技有限公司 | Method and device for correcting boarding and alighting recommended points based on door closing sound |
-
2021
- 2021-08-27 CN CN202110992319.7A patent/CN113739814B/en active Active
Patent Citations (9)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN108537391A (en) * | 2018-04-25 | 2018-09-14 | 哈尔滨工业大学 | A kind of taxi bus stop setting optimization method based on taxi track data |
| CN108959466A (en) * | 2018-06-20 | 2018-12-07 | 淮阴工学院 | Taxi hot spot method for visualizing and system based on BCS-DBSCAN |
| CN109254861A (en) * | 2018-09-17 | 2019-01-22 | 江苏智通交通科技有限公司 | OD requirement extract and its analysis method for reliability based on track data |
| CN110458589A (en) * | 2019-02-01 | 2019-11-15 | 吉林大学 | Trackside formula taxi bus stop addressing preferred method based on track big data |
| CN110413855A (en) * | 2019-07-11 | 2019-11-05 | 南通大学 | A kind of region entrance Dynamic Extraction method based on taxi drop-off point |
| CN110555992A (en) * | 2019-09-11 | 2019-12-10 | 中国矿业大学(北京) | taxi driving path information extraction method based on GPS track data |
| CN110990661A (en) * | 2019-10-23 | 2020-04-10 | 南通大学 | Interest area entrance and exit extraction method based on road network constraint and density clustering |
| CN111814596A (en) * | 2020-06-20 | 2020-10-23 | 南通大学 | Automatic city function partitioning method for fusing remote sensing image and taxi track |
| CN113163330A (en) * | 2021-03-24 | 2021-07-23 | 广州宸祺出行科技有限公司 | Method and device for correcting boarding and alighting recommended points based on door closing sound |
Non-Patent Citations (1)
| Title |
|---|
| Applicability Evaluation of Several Spatial Clustering Methods in Spatiotemporal Data Mining of Floating Car Trajectory;Hao-xuan Chen;《International Journal of Geo-Information》;第1-15页 * |
Also Published As
| Publication number | Publication date |
|---|---|
| CN113739814A (en) | 2021-12-03 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN110634299B (en) | Urban traffic state fine division and identification method based on multi-source track data | |
| CN112116100B (en) | Game theory decision method considering driver type | |
| CN111710170B (en) | Method and device for assisting in temperature detection at high-speed intersection | |
| CN111523932A (en) | Scoring method, device and system for network car booking service and storage medium | |
| CN112833903B (en) | Track prediction method, device, equipment and computer readable storage medium | |
| CN109767298B (en) | Method and system for passenger driver safety matching | |
| CN113739814B (en) | Passenger getting-off point extraction optimization method based on taxi track sequence | |
| CN115035491A (en) | Driving behavior road condition early warning method based on federal learning | |
| CN106227859A (en) | The method identifying the vehicles from gps data | |
| CN111340355A (en) | Matching method, device, server and medium of travel order | |
| CN110379443A (en) | Voice recognition device and sound identification method | |
| CN112507624A (en) | Intercity highway trip mode identification model construction and identification method and device | |
| CN114299742A (en) | Dynamic recognition and updating recommendation method for speed limit information of expressway | |
| CN112614375B (en) | Parking guidance method and system based on vehicle driving state | |
| CN117935388A (en) | Expressway charging monitoring system and method based on networking | |
| CN112927547A (en) | Method and device for supplementing getting-off time | |
| Van Hinsbergh et al. | Vehicle point of interest detection using in-car data | |
| CN115762140B (en) | Expressway traffic accident risk prediction method considering variable heterogeneity | |
| CN115080550B (en) | Road network traffic distribution method and device | |
| CN116050963A (en) | Distribution path selection method, system, device and medium based on traffic road conditions | |
| Song et al. | Impact of event encoding and dissimilarity measures on traffic crash characterization based on sequence of events | |
| CN111582563A (en) | Individual journey time short-term prediction method, system, device and storage medium | |
| CN111968365B (en) | Non-signalized intersection vehicle behavior analysis method and system and storage medium | |
| CN118280119B (en) | Expressway vehicle flow prediction method based on big data analysis | |
| CN117576926B (en) | Method, device and storage medium for detecting vehicle violations |
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 |