CN108765954B - Road traffic safety condition monitoring method based on SNN density ST-OPTIC improved clustering algorithm - Google Patents
Road traffic safety condition monitoring method based on SNN density ST-OPTIC improved clustering algorithm Download PDFInfo
- Publication number
- CN108765954B CN108765954B CN201810605328.4A CN201810605328A CN108765954B CN 108765954 B CN108765954 B CN 108765954B CN 201810605328 A CN201810605328 A CN 201810605328A CN 108765954 B CN108765954 B CN 108765954B
- Authority
- CN
- China
- Prior art keywords
- data
- snn
- density
- clustering algorithm
- vehicle
- 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
Images
Classifications
-
- G—PHYSICS
- G08—SIGNALLING
- G08G—TRAFFIC CONTROL SYSTEMS
- G08G1/00—Traffic control systems for road vehicles
- G08G1/01—Detecting movement of traffic to be counted or controlled
- G08G1/0104—Measuring and analyzing of parameters relative to traffic conditions
- G08G1/0108—Measuring and analyzing of parameters relative to traffic conditions based on the source of data
- G08G1/0112—Measuring and analyzing of parameters relative to traffic conditions based on the source of data from the vehicle, e.g. floating car data [FCD]
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/23—Clustering techniques
- G06F18/232—Non-hierarchical techniques
- G06F18/2321—Non-hierarchical techniques using statistics or function optimisation, e.g. modelling of probability density functions
- G06F18/23213—Non-hierarchical techniques using statistics or function optimisation, e.g. modelling of probability density functions with fixed number of clusters, e.g. K-means clustering
-
- G—PHYSICS
- G08—SIGNALLING
- G08G—TRAFFIC CONTROL SYSTEMS
- G08G1/00—Traffic control systems for road vehicles
- G08G1/01—Detecting movement of traffic to be counted or controlled
- G08G1/0104—Measuring and analyzing of parameters relative to traffic conditions
- G08G1/0108—Measuring and analyzing of parameters relative to traffic conditions based on the source of data
- G08G1/012—Measuring and analyzing of parameters relative to traffic conditions based on the source of data from other sources than vehicle or roadside beacons, e.g. mobile networks
-
- G—PHYSICS
- G08—SIGNALLING
- G08G—TRAFFIC CONTROL SYSTEMS
- G08G1/00—Traffic control systems for road vehicles
- G08G1/01—Detecting movement of traffic to be counted or controlled
- G08G1/0104—Measuring and analyzing of parameters relative to traffic conditions
- G08G1/0125—Traffic data processing
-
- 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
- Y02T—CLIMATE CHANGE MITIGATION TECHNOLOGIES RELATED TO TRANSPORTATION
- Y02T10/00—Road transport of goods or passengers
- Y02T10/10—Internal combustion engine [ICE] based vehicles
- Y02T10/40—Engine management systems
Landscapes
- Engineering & Computer Science (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Analytical Chemistry (AREA)
- Data Mining & Analysis (AREA)
- Chemical & Material Sciences (AREA)
- Theoretical Computer Science (AREA)
- Life Sciences & Earth Sciences (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Evolutionary Biology (AREA)
- Evolutionary Computation (AREA)
- General Engineering & Computer Science (AREA)
- Bioinformatics & Computational Biology (AREA)
- Bioinformatics & Cheminformatics (AREA)
- Artificial Intelligence (AREA)
- Probability & Statistics with Applications (AREA)
- Traffic Control Systems (AREA)
Abstract
The invention discloses a road traffic safety condition monitoring method based on an SNN density ST-OPTICS improved clustering algorithm, which comprises the following steps: s1, collecting vehicle and mobile phone positioning data on the selected road; s2, preprocessing the data and warehousing; s3, map matching is carried out through the key positioning information; s4, calculating an SNN density similarity map, and estimating the number of vehicles running on the selected road according to the similarity map; s5, performing cluster analysis on the vehicle and mobile phone positioning data points through an ST-OPTIC clustering algorithm, and outputting cluster sequencing; s6, taking the passenger object metric as support degree, and storing the corresponding vehicle information into a database; and S7, acquiring the data set meeting the minimum support degree to perform positioning analysis. The invention uses the intelligent mobile phone positioning data, the base station positioning data and the vehicle-mounted GPS technology to establish a detection model to intelligently detect the traffic safety condition of the selected road.
Description
Technical Field
The invention relates to the fields of intelligent transportation, data mining and big data processing and analysis, in particular to a road traffic safety condition monitoring method based on an SNN density ST-optiCS improved clustering algorithm.
Background
SNN (Shared Nearest Neighbor) density measures how much a point is surrounded by similar points (with respect to the Nearest Neighbor), and clusters found based on SNN density clusters are all strongly correlated with each other. Initial parameter values epsilon neighborhood and Minpts in a Clustering algorithm Based on DBSCAN (Density-Based Spatial Clustering with Noise application) need to be manually set, and the Clustering result with large difference can be caused by slight difference of parameter values. To overcome the disadvantages of using a set of global parameters in cluster analysis, an OPTICS (Ordering of clusters to identify the clustering structure by point Ordering) cluster analysis method is proposed, which does not explicitly generate data set clustering, but generates an augmented cluster Ordering calculated from parameter ε neighborhood, Minpts, which is a linear table of all analysis objects and represents the density-based clustering structure of the data.
Disclosure of Invention
In order to overcome the defect that vehicles on a selected road need to be monitored and law-enforcement in a manual mode in the prior art, the invention provides a road traffic safety condition monitoring method based on an SNN density ST-optiCS improved clustering algorithm, which uses mobile phone positioning, base station positioning data and vehicle-mounted GPS technology to intelligently monitor the vehicle traffic safety condition of the selected road.
The technical scheme adopted by the invention is as follows:
a road traffic safety condition monitoring method based on an SNN density ST-optiCS improved clustering algorithm comprises the following steps:
s1: collecting GPS positioning data of vehicles running on a selected road and GPS positioning data and base station positioning data of mobile phones of vehicle-mounted passengers;
s2: preprocessing the data to generate an operability data set, and storing the operability data set in a database;
s3: performing map matching through key positioning information including longitude and latitude of the operable data set;
s4: calculating an SNN density similarity graph by adopting mobile phone positioning track data points in the operability data set, automatically determining the number of clusters in the operability data set, and estimating the number of vehicles running on the selected road;
s5: clustering analysis is carried out on the vehicle and mobile phone positioning data points through an ST-OPTICS clustering algorithm, and corresponding cluster sequencing is output, so that passenger object metric values corresponding to all clusters are obtained;
s6: taking the passenger object measurement value as the support degree of a positioning analysis model, taking the number N of the vehicle-mounted people conforming to the vehicle as the minimum support degree according to the actual regulation of the selected road, detecting the running vehicle, and storing the information of the conforming vehicle into a corresponding database;
s7: and taking the data set meeting the minimum support degree as a basis for selecting a road driving vehicle and a mobile phone positioning analysis model.
Preferably, the preprocessing of the data in S2 includes comparing data formats, removing logical error data, and completing default data.
Preferably, the eliminating logic error data comprises deleting the positioning data with the visible satellite number less than 4.
Preferably, the complementing default data includes calculating positions of trace points 30 seconds before and after the signal is lost, and uniformly complementing the trace points of corresponding number according to the distance by taking two central positions before and after the signal is lost as end points.
Preferably, the number N of persons in the conforming vehicle in S6 is 2.
Compared with the prior art, the invention has the beneficial effects that:
according to the invention, SNN density and ST-OPTIC clustering algorithm are creatively combined to create a new clustering algorithm, and the algorithm is used to establish a positioning analysis model in combination with smartphone positioning technology and vehicle-mounted GPS technology, so that intelligent monitoring can be carried out on the road needing to detect the number of vehicle-mounted personnel; the method can save infrastructure construction cost and provide a new monitoring means for law enforcement of roads in traffic parts.
Of course, it is not necessary for any product in which the invention is practiced to achieve all of the above-described advantages at the same time.
Drawings
Fig. 1 is a flowchart of a road traffic safety condition monitoring method based on an SNN density ST-OPTICS improved clustering algorithm according to an embodiment of the present invention.
Detailed Description
In order to make the objects, technical solutions and advantages of the present invention more apparent, embodiments of the present invention will be described in detail below with reference to the accompanying drawings.
The following is a detailed description of the vehicle traffic safety monitoring of the HOV lane as an example, but the scope of the invention is not limited thereto.
ST-OPTIC is based on the OPTIC analysis method and uses the time stamps of spatio-temporal objects to improve the cluster ordering of data objects. Combining the SNN density with the ST-OPTICS algorithm, creating a new clustering algorithm, starting clustering by using an SNN similarity graph, and establishing a vehicle and smart phone positioning analysis model based on the algorithm, wherein the method mainly comprises the following three steps: the first stage is to estimate the number of vehicles running on the HOV lane by calculating an SNN similarity graph of an operability data set, namely representing the number of cluster groups distributed by the operability data, and the second stage is to cluster the mobile smart phone positioning data and the base station positioning data by an ST-OPTICS clustering algorithm, and output an augmented cluster sequence representing a linear table of an analysis object. And the third stage is to calculate passenger object measurement values corresponding to all clusters according to an ST-OPTICS clustering algorithm based on SNN density. And taking the passenger object measurement as the support degree of the positioning analysis model, detecting the vehicles which accord with the driving in the HOV lane according to the minimum support degree of the passenger object measurement which accords with the vehicle-mounted number of people of the vehicles according to the actual specification of the HOV lane, and storing the information of the vehicles which accord with the detection into a corresponding database.
The idea of the ST-OPTICS clustering algorithm based on SNN density is specifically described as shown in Table 1:
TABLE 1 SNN Density-based ST-OPTIC clustering algorithm
Referring to fig. 1, a method for monitoring road traffic safety conditions based on an SNN density ST-OPTICS improved clustering algorithm includes the following 7 steps:
step 1: the GPS positioning data of the running vehicle on the HOV lane and the GPS positioning data and the base station positioning data of the vehicle-mounted passenger smart phone are collected, wherein the collected mobile phone base station data are used as auxiliary data of the mobile phone GPS positioning data, so that the mobile phone positioning is more accurate.
Step 2: and preprocessing the data to generate an operability data set, and storing the operability data set in a database. The preprocessing of the data comprises comparing data formats, eliminating logic error data, complementing default data and the like. Because the GPS positioning data of the mobile phone is large in quantity, the data can be uncontrollably changed in each stage of acquisition, uploading and downloading, and common data format error forms are messy code forms, data repetition and the like; these data with obvious problems were directly deleted by alignment analysis. In addition, the mobile phone has abnormal working states such as card machines and black screens in the data acquisition process, or the mobile phone is shielded by a high-rise building, so that the number of satellites capable of receiving GPS signals by the mobile phone is small, and the GPS positioning has large deviation. Therefore, when data preprocessing is carried out, the positioning data with the number of visible satellites less than 4 is deleted. And supplementing the missing data, namely calculating the positions of the trace points of 30 seconds before and after the signal is missing, and uniformly supplementing the trace points of corresponding number according to the distance by taking the two central positions before and after the signal is missing as end points.
Step 3: map matching is performed by key positioning information including latitude and longitude of the operational data set.
Step 4: and calculating an SNN density similarity graph by adopting mobile phone positioning track data points in the operability data set, and automatically determining the number of clusters in the operability data set so as to estimate the number of vehicles running on the HOV lane. Wherein, the SNN (shared neighbor) density similarity map reflects the degree of a point surrounded by similar points (related to Nearest neighbors), and the points in the clusters found by the SNN density-based clustering are all strongly related to each other. The dots in the high density, low density region generally have a relatively high SNN density. The similarity map is used for automatically determining the number of clusters in the operability data set from the map, namely predicting the number of vehicles running on the HOV lane.
Step 5: and performing cluster analysis on the vehicle and mobile phone positioning data points through an ST-OPTICS clustering algorithm, and outputting corresponding cluster sequencing to obtain a passenger object metric value corresponding to each cluster.
Step 6: taking the passenger object metric value as the support degree of a positioning analysis model, and according to the HOV lane actual regulation: and (3) detecting the running vehicle by taking the number of the vehicle-mounted people of the conforming vehicle as the minimum support degree of the conforming vehicle more than 2, and storing the conforming vehicle information into a corresponding database.
Step 7: and taking the data set meeting the minimum support degree as a basis of an HOV lane driving vehicle and mobile phone positioning analysis model.
Compared with the traditional method of taking pictures by matching an infrared thermal imaging technology with a video monitoring device, manually identifying the number of real-load passengers of vehicles on a road, and automatically capturing the vehicles illegally driving into an HOV lane by relying on the video monitoring device, the method creatively provides a new clustering algorithm by combining the SNN density and the ST-OPTIC clustering algorithm, and establishes a positioning analysis model by combining the algorithm with a smart phone positioning technology and a vehicle-mounted GPS technology, so that vehicle-mounted personnel detection can be carried out on the selected road, the selected road is not limited to the HOV lane, and the selected road is the road which is selected according to the detection requirement of the traffic safety condition. The monitoring method based on the positioning analysis model can save infrastructure construction cost and provide a new monitoring means for law enforcement of roads in traffic parts.
The above description is only for the preferred embodiment of the present invention, but the scope of the present invention is not limited thereto, and any changes or substitutions that can be easily conceived by those skilled in the art within the technical scope of the present invention are included in the scope of the present invention. Therefore, the protection scope of the present invention shall be subject to the protection scope of the claims.
Claims (5)
1. A road traffic safety condition monitoring method based on an SNN density ST-optiCS improved clustering algorithm is characterized by comprising the following steps:
s1: collecting GPS positioning data of vehicles running on a selected road and GPS positioning data and base station positioning data of mobile phones of vehicle-mounted passengers;
s2: preprocessing the data to generate an operability data set, and storing the operability data set in a database;
s3: performing map matching through key positioning information including longitude and latitude of the operable data set;
s4: calculating an SNN density similarity graph by adopting mobile phone positioning track data points in an operability data set, automatically determining the number of clusters in the operability data set, and estimating the number of vehicles running on a selected road;
s5: clustering analysis is carried out on the vehicle and mobile phone positioning data points through an ST-OPTICS clustering algorithm, and corresponding cluster sequencing is output, so that passenger object metric values corresponding to all clusters are obtained;
s6: taking the passenger object metric value as the support degree of a positioning analysis model, taking the number N of the passengers in the vehicle as the minimum support degree according to the actual specification of the selected road, detecting the running vehicle, and storing the information of the vehicles in accordance into a corresponding database;
s7: and taking the data set meeting the minimum support degree as a basis for selecting a road driving vehicle and a mobile phone positioning analysis model.
2. The SNN density ST-optiCS improved clustering algorithm-based road traffic safety condition monitoring method according to claim 1, wherein the preprocessing performed on the data in S2 comprises comparing data formats, removing logical error data and complementing default data.
3. The SNN density ST-optiCS improved clustering algorithm-based road traffic safety condition monitoring method according to claim 2, wherein the culling logic error data comprises deleting positioning data with a visible satellite number less than 4.
4. The SNN density ST-optiCS improved clustering algorithm-based road traffic safety condition monitoring method according to claim 2, wherein the complementing default data comprises calculating positions of track points 30 seconds before and after signal loss, and uniformly complementing the corresponding number of track points according to intervals by taking two central positions before and after the signal loss as end points.
5. The SNN density ST-optiCS improved clustering algorithm-based road traffic safety condition monitoring method according to claim 1, wherein the number N of the qualified vehicles in S6 is 2.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201810605328.4A CN108765954B (en) | 2018-06-13 | 2018-06-13 | Road traffic safety condition monitoring method based on SNN density ST-OPTIC improved clustering algorithm |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201810605328.4A CN108765954B (en) | 2018-06-13 | 2018-06-13 | Road traffic safety condition monitoring method based on SNN density ST-OPTIC improved clustering algorithm |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN108765954A CN108765954A (en) | 2018-11-06 |
| CN108765954B true CN108765954B (en) | 2022-05-24 |
Family
ID=64021103
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201810605328.4A Active CN108765954B (en) | 2018-06-13 | 2018-06-13 | Road traffic safety condition monitoring method based on SNN density ST-OPTIC improved clustering algorithm |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN108765954B (en) |
Families Citing this family (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US12112635B2 (en) * | 2020-02-19 | 2024-10-08 | GM Global Technology Operations LLC | Process and system for local traffic approximation through analysis of cloud data |
| CN114937359B (en) * | 2022-05-20 | 2023-04-07 | 四川大学 | Method, system, terminal and medium for positioning and analyzing cascade fault of traffic infrastructure |
Citations (9)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN102194129A (en) * | 2011-05-13 | 2011-09-21 | 南京大学 | Vehicle-type-clustering-based video detection method for traffic flow parameters |
| CN104217015A (en) * | 2014-09-22 | 2014-12-17 | 西安理工大学 | Hierarchical clustering method based on mutual shared nearest neighbors |
| CN104269057A (en) * | 2014-09-29 | 2015-01-07 | 银江股份有限公司 | Bayonet sensor layout method based on floating car OD data |
| CN105488509A (en) * | 2015-11-19 | 2016-04-13 | Tcl集团股份有限公司 | Image clustering method and system based on local chromatic features |
| CN105679031A (en) * | 2016-03-17 | 2016-06-15 | 福州大学 | Active forewarning method for express way maintenance construction area |
| CN105787520A (en) * | 2016-03-25 | 2016-07-20 | 中国农业大学 | Cluster and outlier discovery algorithm based on natural shared nearest neighbor search |
| CN105788273A (en) * | 2016-05-18 | 2016-07-20 | 武汉大学 | Urban intersection automatic identification method based on low precision space-time trajectory data |
| CN106600960A (en) * | 2016-12-22 | 2017-04-26 | 西南交通大学 | Traffic travel origin and destination identification method based on space-time clustering analysis algorithm |
| CN107958589A (en) * | 2017-11-22 | 2018-04-24 | 烟台大学 | A kind of device and system of smart city design |
Family Cites Families (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20100191731A1 (en) * | 2009-01-23 | 2010-07-29 | Vasile Rus | Methods and systems for automatic clustering of defect reports |
| EP2289754B1 (en) * | 2009-08-31 | 2015-04-29 | Toyota Motor Europe NV/SA | Vehicle or traffic control method and system |
| US9697730B2 (en) * | 2015-01-30 | 2017-07-04 | Nissan North America, Inc. | Spatial clustering of vehicle probe data |
-
2018
- 2018-06-13 CN CN201810605328.4A patent/CN108765954B/en active Active
Patent Citations (9)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN102194129A (en) * | 2011-05-13 | 2011-09-21 | 南京大学 | Vehicle-type-clustering-based video detection method for traffic flow parameters |
| CN104217015A (en) * | 2014-09-22 | 2014-12-17 | 西安理工大学 | Hierarchical clustering method based on mutual shared nearest neighbors |
| CN104269057A (en) * | 2014-09-29 | 2015-01-07 | 银江股份有限公司 | Bayonet sensor layout method based on floating car OD data |
| CN105488509A (en) * | 2015-11-19 | 2016-04-13 | Tcl集团股份有限公司 | Image clustering method and system based on local chromatic features |
| CN105679031A (en) * | 2016-03-17 | 2016-06-15 | 福州大学 | Active forewarning method for express way maintenance construction area |
| CN105787520A (en) * | 2016-03-25 | 2016-07-20 | 中国农业大学 | Cluster and outlier discovery algorithm based on natural shared nearest neighbor search |
| CN105788273A (en) * | 2016-05-18 | 2016-07-20 | 武汉大学 | Urban intersection automatic identification method based on low precision space-time trajectory data |
| CN106600960A (en) * | 2016-12-22 | 2017-04-26 | 西南交通大学 | Traffic travel origin and destination identification method based on space-time clustering analysis algorithm |
| CN107958589A (en) * | 2017-11-22 | 2018-04-24 | 烟台大学 | A kind of device and system of smart city design |
Non-Patent Citations (2)
| Title |
|---|
| 基于图的流行排序的显著目标检测改进算法;张晴等;《计算机工程与应用》;20161115(第22期);全文 * |
| 改进的共享最近邻聚类算法;李霞等;《计算机工程与应用》;20110311(第08期);全文 * |
Also Published As
| Publication number | Publication date |
|---|---|
| CN108765954A (en) | 2018-11-06 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN108318043B (en) | Method, apparatus, and computer-readable storage medium for updating electronic map | |
| US10854076B2 (en) | Method and system for computing parking occupancy | |
| CN110945320B (en) | Vehicle positioning method and system | |
| CN110208739B (en) | Method, device and equipment for assisting vehicle positioning by using V2X based on road side equipment | |
| US11538239B2 (en) | Joint modeling of object population estimation using sensor data and distributed device data | |
| US12055628B2 (en) | Position coordinates estimation device, position coordinates estimation method, and program | |
| JP2008267875A (en) | Generating method of digital road map and map generating system | |
| CN109507699B (en) | Satellite positioning correction method and device for vehicle | |
| US20200162724A1 (en) | System and method for camera commissioning beacons | |
| CN105096590B (en) | Traffic information creating method and traffic information generating device | |
| CN111319560B (en) | Information processing system, program, and information processing method | |
| Ndoye et al. | A recursive multiscale correlation-averaging algorithm for an automated distributed road-condition-monitoring system | |
| KR20190043396A (en) | Method and system for generating and providing road weather information by using image data of roads | |
| CN108765954B (en) | Road traffic safety condition monitoring method based on SNN density ST-OPTIC improved clustering algorithm | |
| CN105761538A (en) | Assistant station reporting method and system based on video recognition and vehicle-mounted terminal | |
| US11823368B1 (en) | Automated road surface condition quality assessment using smart (IoT) devices | |
| CN111651547B (en) | Method and device for acquiring high-precision map data and readable storage medium | |
| CN115129796A (en) | Positioning data analysis method, apparatus, device and medium | |
| CN111881233A (en) | Distributed point cloud map construction method and device, server and computer readable storage medium | |
| CN113689705A (en) | Method and device for detecting red light running of vehicle, computer equipment and storage medium | |
| Al-Suleiman et al. | Assessment of the effect of alligator cracking on pavement condition using WSN-image processing | |
| CN113850837B (en) | Video processing method and device, electronic equipment, storage medium and computer product | |
| US11488390B2 (en) | Map generation device, recording medium and map generation method | |
| US20230194650A1 (en) | Positioning using locally unique neighbor cell identifiers | |
| US20230177952A1 (en) | A system and method for generating utilization data of a vehicle |
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 |