CN110968616A - Side turning point identification system based on DBSCAN and working method thereof - Google Patents
Side turning point identification system based on DBSCAN and working method thereof Download PDFInfo
- Publication number
- CN110968616A CN110968616A CN201910708929.2A CN201910708929A CN110968616A CN 110968616 A CN110968616 A CN 110968616A CN 201910708929 A CN201910708929 A CN 201910708929A CN 110968616 A CN110968616 A CN 110968616A
- Authority
- CN
- China
- Prior art keywords
- connection port
- processor
- dbscan
- early warning
- objects
- 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.)
- Pending
Links
- 238000000034 method Methods 0.000 title claims abstract description 27
- 238000004458 analytical method Methods 0.000 claims abstract description 10
- 238000007781 pre-processing Methods 0.000 claims description 3
- 230000005611 electricity Effects 0.000 description 4
- 230000008569 process Effects 0.000 description 4
- 230000009471 action Effects 0.000 description 3
- 238000010586 diagram Methods 0.000 description 3
- 238000005516 engineering process Methods 0.000 description 3
- 230000009286 beneficial effect Effects 0.000 description 2
- 238000001514 detection method Methods 0.000 description 2
- 238000010801 machine learning Methods 0.000 description 2
- 206010039203 Road traffic accident Diseases 0.000 description 1
- 230000002776 aggregation Effects 0.000 description 1
- 238000004220 aggregation Methods 0.000 description 1
- 230000004075 alteration Effects 0.000 description 1
- 230000002457 bidirectional effect Effects 0.000 description 1
- 238000004364 calculation method Methods 0.000 description 1
- 230000007547 defect Effects 0.000 description 1
- 230000000694 effects Effects 0.000 description 1
- 230000007246 mechanism Effects 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 238000005192 partition Methods 0.000 description 1
- 238000000638 solvent extraction Methods 0.000 description 1
- 238000006467 substitution reaction Methods 0.000 description 1
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
- G06F16/20—Information retrieval; Database structures therefor; File system structures therefor of structured data, e.g. relational data
- G06F16/24—Querying
- G06F16/245—Query processing
- G06F16/2458—Special types of queries, e.g. statistical queries, fuzzy queries or distributed queries
- G06F16/2465—Query processing support for facilitating data mining operations in structured databases
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
- G06F16/20—Information retrieval; Database structures therefor; File system structures therefor of structured data, e.g. relational data
- G06F16/29—Geographical information databases
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/21—Design or setup of recognition systems or techniques; Extraction of features in feature space; Blind source separation
- G06F18/214—Generating training patterns; Bootstrap methods, e.g. bagging or boosting
-
- 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
-
- 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
-
- 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
- G08G1/0137—Measuring and analyzing of parameters relative to traffic conditions for specific applications
Landscapes
- Engineering & Computer Science (AREA)
- Theoretical Computer Science (AREA)
- Physics & Mathematics (AREA)
- Data Mining & Analysis (AREA)
- General Physics & Mathematics (AREA)
- Databases & Information Systems (AREA)
- General Engineering & Computer Science (AREA)
- Analytical Chemistry (AREA)
- Chemical & Material Sciences (AREA)
- Bioinformatics & Computational Biology (AREA)
- Evolutionary Biology (AREA)
- Life Sciences & Earth Sciences (AREA)
- Artificial Intelligence (AREA)
- Evolutionary Computation (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Bioinformatics & Cheminformatics (AREA)
- Remote Sensing (AREA)
- Fuzzy Systems (AREA)
- Mathematical Physics (AREA)
- Probability & Statistics with Applications (AREA)
- Software Systems (AREA)
- Computational Linguistics (AREA)
- Navigation (AREA)
Abstract
The invention discloses a DBSCAN-based rollover point identification system which comprises a processor, an input device, an early warning module, a memory, an output device and a power module, wherein an electric connection port of the processor is electrically connected with an electric connection port of the input device, the electric connection port of the processor is electrically connected with an electric connection port of the early warning module, the electric connection port of the processor is electrically connected with an electric connection port of the memory, the electric connection port of the processor is electrically connected with an electric connection port of the output device, and the processor, the input device, the early warning module, the memory and the output device are all electrically connected with the power module. The side turning point identification system based on the DBSCAN and the working method thereof based on the DBSCAN analysis algorithm of the vehicle side turning points can rapidly and effectively cluster the side turning points, find out side turning multi-issue point segments and more comprehensively analyze the spatial distribution rule of the side turning event.
Description
Technical Field
The invention relates to the technical field of computers, in particular to a side turning point identification system based on DBSCAN and a working method thereof.
Background
At present, traffic safety is more and more emphasized, and needs to be continuously improved, for example, in some road sections, rollover accidents of running vehicles are easy to happen, and traffic accidents are caused.
DBSCAN (sensitivity-Based Spatial Clustering of Applications with Noise) is a relatively representative Density-Based Clustering algorithm. Unlike the partitioning and hierarchical clustering method, which defines clusters as the largest set of density-connected points, it is possible to partition areas with sufficiently high density into clusters and find clusters of arbitrary shape in a spatial database of noise.
With the continuous progress of science and technology, prediction can be provided through a rollover point identification mode at present. Most of the existing rollover point identification algorithms adopt rules of a specific scene for judgment, rollover risk road section information is formed according to historical rollover time, afterwards assessment is carried out, potential risks are prevented in advance, a management target value is set according to experience of management departments and reference to past statistical data or standards set by other mechanisms, however, how to serve transportation safety early warning is still only stopped on the surface, actual guidance is lacked, rollover factors are various due to different rollover accidents, the prior art does not have generalization, corresponding technologies are difficult to apply to actual scenes, and related intelligent identification technologies lack stretching-in research.
Disclosure of Invention
Aiming at the defects of the prior art, the invention provides a rollover point identification system based on DBSCAN and a working method thereof, which can learn the data characteristics of rollover section information, adopt the duration, the duration distance, the rollover longitude and the rollover latitude of a rollover event, and utilize the data space distribution characteristics and a DBSCAN algorithm to learn the spatial data characteristics, thereby realizing the approximate calculation of a vehicle rollover section and giving early warning.
In order to achieve the purpose, the invention is realized by the following technical scheme: the utility model provides a rollover point identification system based on DBSCAN, includes treater, input device, early warning module, memory, output device and power module, the electricity port that connects of treater and input device connects electric port electric connection, the electricity port that connects of treater and early warning module connects electric port electric connection, the electricity port that connects of treater and memory connects electric port electric connection, the electricity port that connects of treater and output device connect electric port electric connection, treater, input device, early warning module, memory and output device all with power module electric connection.
Preferably, the early warning module execution component mainly displays early warning and voice prompt on a screen.
Preferably, the input device mainly inputs position information through a touch screen, and the output device displays analysis information through the touch screen.
Preferably, the processor, the input device, the early warning module, the memory, the output device and the power module are all in one-way connection, and the memory is in two-way connection.
A working method of a side turning point identification system based on DBSCAN comprises the following specific steps:
the method comprises the following steps: preparing data: in the data preprocessing stage, a rollover data set is collected, data are labeled, data are filtered, compensated and transformed, and the data quantity and the robustness of model training are enhanced. E: radius of linear neighborhood, MinTime: the shortest time;
step two: reading any unclassified object p in the rollover data T;
step three: retrieving all objects Lneeps (p) with the path of the roll-over data to p not larger than E, and calculating the maximum time interval maxTime (p) between adjacent objects;
step four: if the | maxtime (p) | < MinTime, marking p as noise (i.e. p is a non-core object), and executing the step one;
step five: otherwise (i.e. p is the core object), all the objects in the lneps (p) are marked as new, and the objects are put into the set Seeds;
step six: let current object be seeds.top; then retrieving all objects belonging to Lneeps (currentObject), if | maxTime (currentObject) | > MinTime, rejecting the objects marked, marking the rest unclassified objects with class labels, and then putting the objects into a set;
step seven: pop, judging whether the feeds are empty, if so, executing the step one, otherwise, executing the step six.
Advantageous effects
The invention provides a side turning point identification system based on DBSCAN and a working method thereof. The method has the following beneficial effects:
(1) the side turning point identification system based on the DBSCAN and the working method thereof based on the DBSCAN analysis algorithm of the vehicle side turning points can rapidly and effectively cluster the side turning points, find out side turning multi-issue point segments and more comprehensively analyze the spatial distribution rule of the side turning event.
(2) The side turning point identification system based on the DBSCAN and the working method thereof provide the side turning road section identification model on the basis of knowing the side turning of the vehicle through actual research on the trailer driving road section and vehicle data on the side turning road section on-site analysis, so that the model is more suitable for the actual situation, and the accuracy is higher.
(3) The side turning point identification system based on the DBSCAN and the working method thereof remember the use scene of the learning algorithm, correct the data characteristics in the side turning process and improve the detection accuracy of the side turning road section by adopting the machine learning algorithm.
Drawings
FIG. 1 is a schematic diagram of the system of the present invention;
FIG. 2 is a diagram of the working steps of the present invention;
FIG. 3 is a schematic diagram of a trajectory clustering rollover point according to the present invention.
In the figure: the system comprises a processor 1, an input device 2, an early warning module 3, a memory 4, an output device 5 and a power supply module 6.
Detailed Description
The technical solutions in the embodiments of the present invention will be clearly and completely described below with reference to the drawings in the embodiments of the present invention, and it is obvious that the described embodiments are only a part of the embodiments of the present invention, and not all of the embodiments. All other embodiments, which can be derived by a person skilled in the art from the embodiments given herein without making any creative effort, shall fall within the protection scope of the present invention.
Referring to fig. 1-3, the present invention provides a technical solution: a rollover point identification system based on DBSCAN comprises a processor 1, an input device 2, an early warning module 3, a memory 4, an output device 5 and a power module 6, wherein a power connection port of the processor 1 is electrically connected with a power connection port of the input device 2, the input device 2 inputs rollover cluster aggregation (G), a candidate rollover set (R) and a minimum time threshold (minimum), the power connection port of the processor 1 is electrically connected with the power connection port of the early warning module 3, the power connection port of the processor 1 is electrically connected with the power connection port of the memory 4, the power connection port of the processor 1 is electrically connected with the power connection port of the output device 5, the output device 5 outputs a rollover point (S) and a moving point (M), the processor 1, the input device 2, the early warning module 3, the memory 4 and the output device 5 are electrically connected with the power module 6, for each cluster Gi in rollover, searching whether each candidate rollover Ri in the R has an intersection with Gi, and if the intersection exists and the intersection time t is more than the minimum, marking the candidate rollover Ri as rollover S; otherwise (Gi is not intersected with all Ris), marking Gi as unknown rollover unknowS; sub-tracks (noise points in a cluster of tracks) that are neither a rollover nor an unknown rollover are identified as moves (M), such as shown in fig. 3: the track T has four potential side turning points which are track point clusters G1, G2, G3 and G4. At the same time, the four candidate rollover positions are also marked along the traces in the figure, which are R1, R2, R3 and R4. The intersection time of the cluster G1 and the candidate rollover R1 is longer than the minimum time, the first rollover of the track is R1, the same situation corresponds to the cluster G3, and R3 is called the second rollover of the track. And G2, G4 mark them as candidate rollover without any rain candidate rollover coincidence.
Early warning module 3 executive component is mainly screen display early warning and voice prompt, through screen display early warning information, warn people, there is voice prompt simultaneously, early warning risk highway section, input device 2 is mainly touch-sensitive screen input positional information, output device 5 is touch-sensitive screen display analysis information, after the information is handled by processor 1, can show the analysis result, processor 1 and input device 2, early warning module 3, memory 4, output device 5 and power module 6 are the unidirectional connection, and memory 4 is the bidirectional connection, processor 1 can call the storage information of memory 4, the accident of turning on one's side that takes place before is analyzed and classified, be convenient for carry out the analysis to the instant scene, reach more accurate result.
A working method of a side turning point identification system based on DBSCAN comprises the following specific steps:
the method comprises the following steps: preparing data: in the data preprocessing stage, a rollover data set is collected, data are labeled, data are filtered, compensated and transformed, and the data quantity and the robustness of model training are enhanced. E: radius of linear neighborhood, MinTime: the shortest time;
step two: reading any unclassified object p in the rollover data T;
step three: retrieving all objects Lneeps (p) with the path of the roll-over data to p not larger than E, and calculating the maximum time interval maxTime (p) between adjacent objects;
step four: if the | maxtime (p) | < MinTime, marking p as noise (i.e. p is a non-core object), and executing the step one;
step five: otherwise (i.e. p is the core object), all the objects in the lneps (p) are marked as new, and the objects are put into the set Seeds;
step six: let current object be seeds.top; then retrieving all objects belonging to Lneeps (currentObject), if | maxTime (currentObject) | > MinTime, rejecting the objects marked, marking the rest unclassified objects with class labels, and then putting the objects into a set;
step seven: pop, judging whether the feeds are empty, if so, executing the step one, otherwise, executing the step six.
The invention has the beneficial effects that: (1) the side turning point identification system based on the DBSCAN and the working method thereof based on the DBSCAN analysis algorithm of the vehicle side turning points can rapidly and effectively cluster the side turning points, find out side turning multi-issue point segments and more comprehensively analyze the spatial distribution rule of the side turning event.
(2) The side turning point identification system based on the DBSCAN and the working method thereof provide the side turning road section identification model on the basis of knowing the side turning of the vehicle through actual research on the trailer driving road section and vehicle data on the side turning road section on-site analysis, so that the model is more suitable for the actual situation, and the accuracy is higher.
(3) The side turning point identification system based on the DBSCAN and the working method thereof remember the use scene of the learning algorithm, correct the data characteristics in the side turning process and improve the detection accuracy of the side turning road section by adopting the machine learning algorithm.
It is noted that, herein, relational terms such as first and second, and the like may be used solely to distinguish one entity or action from another entity or action without necessarily requiring or implying any actual such relationship or order between such entities or actions. Also, the terms "comprises," "comprising," or any other variation thereof, are intended to cover a non-exclusive inclusion, such that a process, method, article, or apparatus that comprises a list of elements does not include only those elements but may include other elements not expressly listed or inherent to such process, method, article, or apparatus. Without further limitation.
Although embodiments of the present invention have been shown and described, it will be appreciated by those skilled in the art that changes, modifications, substitutions and alterations can be made in these embodiments without departing from the principles and spirit of the invention, the scope of which is defined in the appended claims and their equivalents.
Claims (5)
1. The utility model provides a rollover point identification system based on DBSCAN, includes treater (1), input device (2), early warning module (3), memory (4), output device (5) and power module (6), its characterized in that: the power connection port of the processor (1) is electrically connected with the power connection port of the input device (2), the power connection port of the processor (1) is electrically connected with the power connection port of the early warning module (3), the power connection port of the processor (1) is electrically connected with the power connection port of the memory (4), the power connection port of the processor (1) is electrically connected with the power connection port of the output device (5), and the processor (1), the input device (2), the early warning module (3), the memory (4) and the output device (5) are all electrically connected with the power supply module (6).
2. The DBSCAN-based rollover point identification system according to claim 1, wherein: and the execution part of the early warning module (3) mainly displays early warning and voice prompt for a screen.
3. The DBSCAN-based rollover point identification system according to claim 1, wherein: the input device (2) mainly inputs position information for a touch screen, and the output device (5) displays analysis information for the touch screen.
4. The DBSCAN-based rollover point identification system according to claim 1, wherein: the processor (1) is in one-way connection with the input device (2), the early warning module (3), the memory (4), the output device (5) and the power module (6), and the memory (4) is in two-way connection.
5. A working method of a side turning point identification system based on DBSCAN is characterized in that: the method comprises the following specific steps:
the method comprises the following steps: preparing data: in the data preprocessing stage, a rollover data set is collected, data are labeled, data are filtered, compensated and transformed, and the data quantity and the robustness of model training are enhanced. E: radius of linear neighborhood, MinTime: the shortest time;
step two: reading any unclassified object p in the rollover data T;
step three: retrieving all objects Lneeps (p) with the path of the roll-over data to p not larger than E, and calculating the maximum time interval maxTime (p) between adjacent objects;
step four: if the | maxtime (p) | < MinTime, marking p as noise (i.e. p is a non-core object), and executing the step one;
step five: otherwise (i.e. p is the core object), all the objects in the lneps (p) are marked as new, and the objects are put into the set Seeds;
step six: let current object be seeds.top; then retrieving all objects belonging to Lneeps (currentObject), if | maxTime (currentObject) | > MinTime, rejecting the objects marked, marking the rest unclassified objects with class labels, and then putting the objects into a set;
step seven: pop, judging whether the feeds are empty, if so, executing the step one, otherwise, executing the step six.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201910708929.2A CN110968616A (en) | 2019-08-01 | 2019-08-01 | Side turning point identification system based on DBSCAN and working method thereof |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201910708929.2A CN110968616A (en) | 2019-08-01 | 2019-08-01 | Side turning point identification system based on DBSCAN and working method thereof |
Publications (1)
Publication Number | Publication Date |
---|---|
CN110968616A true CN110968616A (en) | 2020-04-07 |
Family
ID=70029537
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN201910708929.2A Pending CN110968616A (en) | 2019-08-01 | 2019-08-01 | Side turning point identification system based on DBSCAN and working method thereof |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN110968616A (en) |
Citations (4)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
US20160061625A1 (en) * | 2014-12-02 | 2016-03-03 | Kevin Sunlin Wang | Method and system for avoidance of accidents |
CN106740829A (en) * | 2017-03-23 | 2017-05-31 | 吉林大学 | Based on the double semi-dragging truck riding stability automatic identifications of cluster analysis and early warning system |
CN106960571A (en) * | 2017-03-30 | 2017-07-18 | 百度在线网络技术(北京)有限公司 | Congestion in road bottleneck point determines method, device, server and storage medium |
CN108986453A (en) * | 2018-06-15 | 2018-12-11 | 华南师范大学 | A kind of traffic movement prediction method based on contextual information, system and device |
-
2019
- 2019-08-01 CN CN201910708929.2A patent/CN110968616A/en active Pending
Patent Citations (4)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
US20160061625A1 (en) * | 2014-12-02 | 2016-03-03 | Kevin Sunlin Wang | Method and system for avoidance of accidents |
CN106740829A (en) * | 2017-03-23 | 2017-05-31 | 吉林大学 | Based on the double semi-dragging truck riding stability automatic identifications of cluster analysis and early warning system |
CN106960571A (en) * | 2017-03-30 | 2017-07-18 | 百度在线网络技术(北京)有限公司 | Congestion in road bottleneck point determines method, device, server and storage medium |
CN108986453A (en) * | 2018-06-15 | 2018-12-11 | 华南师范大学 | A kind of traffic movement prediction method based on contextual information, system and device |
Non-Patent Citations (2)
Title |
---|
邱莉榕: "《算法设计与优化》", 28 February 2017, 中央民族大学出版社 * |
鲍海涛: "聚类分析在交通事故黑点智能排查中的应用", 《中国优秀硕士学位论文全文数据库信息科技辑》 * |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
CN107680401B (en) | Parking space satisfaction evaluation method based on interval two-type fuzzy set | |
Morris et al. | Real-time video-based traffic measurement and visualization system for energy/emissions | |
CN107195180B (en) | Traffic travel track extraction method and device based on electric police data | |
Chen et al. | Analysis of factors affecting the severity of automated vehicle crashes using XGBoost model combining POI data | |
Xu et al. | Taxi-RS: Taxi-hunting recommendation system based on taxi GPS data | |
Jiang et al. | Analysis of motorcycle accidents using association rule mining-based framework with parameter optimization and GIS technology | |
CN105225515A (en) | A kind of method for supervising based on fence and system | |
CN103971523A (en) | Mountainous road traffic safety dynamic early-warning system | |
CN107705551A (en) | The appraisal procedure and device of traffic | |
CN113159403A (en) | Method and device for predicting pedestrian track at intersection | |
Li et al. | Research on lane change prediction model based on GBDT | |
CN104598548A (en) | Method and device for analyzing spatial correlation of agricultural product price | |
CN105404858A (en) | Vehicle type recognition method based on deep Fisher network | |
Zhang et al. | How road network transformation may be associated with reduced carbon emissions: An exploratory analysis of 19 major Chinese cities | |
He et al. | Visualization and analysis of mapping knowledge domain of heterogeneous traffic flow | |
Vlachogiannis et al. | Intersense: An XGBoost model for traffic regulator identification at intersections through crowdsourced GPS data | |
Hezaveh et al. | Pedestrian crashes in Tennessee: A data mining approach | |
CN110968616A (en) | Side turning point identification system based on DBSCAN and working method thereof | |
CN102880881A (en) | Method for identifying car type on basis of binary support vector machines and genetic algorithm | |
Ranacher et al. | A model to estimate and interpret the energy-efficiency of movement patterns in urban road traffic | |
CN114495421B (en) | Intelligent open type road construction operation monitoring and early warning method and system | |
Prezioso et al. | Machine Learning Insights for Behavioral Data Analysis Supporting the Autonomous Vehicles Scenario | |
Jain et al. | Analysis of road accidents in India and prediction of accident severity | |
Grigoropoulos et al. | Detection and Classification of Bicyclist Group Behavior for Automated Vehicle Applications | |
Yang et al. | Rapid analysis and detection algorithm and prevention countermeasures of urban traffic accidents under artificial intelligence |
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 | ||
RJ01 | Rejection of invention patent application after publication |
Application publication date: 20200407 |
|
RJ01 | Rejection of invention patent application after publication |