CN117373262A - Intersection average driving speed analysis method, system and storage medium - Google Patents
Intersection average driving speed analysis method, system and storage medium Download PDFInfo
- Publication number
- CN117373262A CN117373262A CN202311347588.3A CN202311347588A CN117373262A CN 117373262 A CN117373262 A CN 117373262A CN 202311347588 A CN202311347588 A CN 202311347588A CN 117373262 A CN117373262 A CN 117373262A
- Authority
- CN
- China
- Prior art keywords
- intersection
- driving speed
- average driving
- average
- running speed
- 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
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
- G08G1/052—Detecting movement of traffic to be counted or controlled with provision for determining speed or overspeed
-
- 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
-
- 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
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Chemical & Material Sciences (AREA)
- Analytical Chemistry (AREA)
- Traffic Control Systems (AREA)
Abstract
The invention relates to the field of running speed analysis, and discloses a method, a system and a storage medium for analyzing average running speed of an intersection; the method for analyzing the average running speed of the intersection comprises the following steps: step 1, acquiring map data of an analysis area, and analyzing road information from the map data; step 2, identifying intersections in the road information, and acquiring driving speed information in a preset range of each intersection; step 3, learning the running speed information to obtain an intersection average running speed prediction model; and 4, predicting the average running speed of each intersection through the intersection average running speed prediction model, and recommending an optimal route according to the average running speed of each intersection. The method and the device can accurately predict the average running speed of the road junction so as to improve the accuracy of obtaining the optimal path.
Description
Technical Field
The invention relates to the field of travel speed analysis, in particular to an intersection average travel speed analysis method, an intersection average travel speed analysis system and a storage medium.
Background
In urban civilization construction, traffic is one of the symbols that best represents urban vitality. The traffic of one city is convenient, the traffic tool is advanced, and the vitality is high. Traffic serves as a large artery for urban operation, and plays a role in urban construction. The vehicle networking is an interactive wireless network constructed according to the information of the vehicle position, speed, route and the like, and the acquisition of the environment and state information of the vehicle is completed by means of the vehicle networking through devices such as GPS, RFID, sensors, camera image processing and the like. Through the internet and computer technology, the information is analyzed and processed, the optimal route of the vehicle is calculated, road conditions and weather are reported in time, the period of signal lamps is arranged, and the like, so that the organic interaction of the vehicle, the road and people is realized, and the intellectualization of the vehicle and traffic is realized.
However, the optimal route is only selected under the condition of grasping the current road condition, the optimization effect is not obvious in the traffic jam peak period, especially in the holiday or the rush hours, the road jam is serious, when the vehicle is in the jammed road section, the road around the vehicle body is blocked, the road replacement cannot be carried out, the road condition is not invariable, and the road condition of each road is changed in real time in the road planning and driving process, so that the time prediction accuracy of the prior art on the passing road is low, and the accuracy of the optimal route is further reduced. The crossing is used as a key point for changing a driving road, and the average driving speed at the crossing plays a decisive role in the whole-course driving speed of the vehicle.
Disclosure of Invention
The invention aims to provide a method, a system and a storage medium for analyzing average running speed of an intersection, so as to accurately predict the average running speed of the intersection and improve the accuracy of obtaining an optimal path.
In order to achieve the above purpose, the invention adopts the following technical scheme:
the method for analyzing the average running speed of the intersection comprises the following steps:
step 1, acquiring map data of an analysis area, and analyzing road information from the map data;
step 2, identifying intersections in the road information, and acquiring driving speed information in a preset range of each intersection;
step 3, learning the running speed information to obtain an intersection average running speed prediction model;
and 4, predicting the average running speed of each intersection through the intersection average running speed prediction model, and recommending an optimal route according to the average running speed of each intersection.
The principle and the advantages of the scheme are as follows: when the method is actually applied, map data of an analysis area are obtained, and road information is analyzed from the map data; identifying intersections in the road information, and acquiring running speed information within a preset range of each intersection; the intersection is a junction and a split position of vehicles and is a key position for selecting a replacement route, and the traffic flow conditions in all directions can be mastered through the running speed information, so that an optimal path can be timely and accurately acquired; learning the running speed information to obtain an intersection average running speed prediction model; and predicting the average running speed of each intersection by using the intersection average running speed prediction model, and recommending an optimal route according to the average running speed of each intersection.
Preferably, as an improvement, the map information also resolves building information, wherein the building information comprises building position, building name and building use; the road information comprises a road structure diagram, the number of lanes, the driving direction, red and green lamps, the type of lanes, the gradient of the lanes and the flatness of the road surface.
The technical effects are as follows: and the surrounding building information and the road information are beneficial to analyzing the influence factors of the average running speed of the crossing, so that maintenance and improvement are performed.
Preferably, as an improvement, the step 2 includes:
step 21, identifying an intersection in the road information;
step 22, determining the range of average running speed calculation at each intersection;
step 23, obtaining the average running speed of the vehicle within the preset time period in the range of the intersection, wherein the average running speed comprises the unidirectional average running speed and the comprehensive average running speed.
The technical effects are as follows: because the destinations are different, though the road junction is passed, the congestion conditions are different, the average running speeds are different, more accurate path navigation can be provided according to the destination by acquiring the unidirectional running average running speed and the comprehensive average running speed, and meanwhile, the comprehensive service level of the road junction can be mastered, so that the subsequent adjustment and maintenance are facilitated.
Preferably, as an improvement, the step 22 further includes:
step 221, scoring the complexity of the intersection according to the conflict points and the confluence points of the intersection, wherein the specific scoring is as follows:
wherein C is i For the number of the conflict points of the intersection i,the weight corresponding to the number x of the conflict points; h i For the number of the intersection i-junction points, delta y The weight corresponding to the number y of the current points is obtained; d (D) iz For the number of lanes at the z-th exit of intersection i, gamma j The weight value corresponding to the number j of the lanes; epsilon is a complexity correction constant;
step 222, dividing the road length between two intersections according to the complexity ratio, and calculating the average running speed in the area within the ratio range.
The technical effects are as follows: the more the conflict points and the flow combining points of the crossing are, the more the vehicles are interfered by other lanes in the running process of the vehicle, the more the lanes running in the same direction are, the more the risk of lane changing interference is, the greater the influence on the running speed of the crossing is, the calculation range of the average running speed is divided by the mode, and the crossing with high complexity is facilitated to acquire and analyze sufficient vehicle data, so that the prediction result is more accurate.
Preferably, as an improvement, the preset time period includes an early peak, a late peak, a daytime and a night off-peak, and the morning peak is 7:30-9:30, peak late at 17:00-19:00, daytime 8:00-20:00; the night time is 20: 00-the next day 8:00, specifically, acquiring the average running speed of the vehicle with any fixed duration in a preset time period.
The technical effects are as follows: the average running speed of the vehicle is acquired all the day, the workload is huge, and the acquisition of redundant data can be reduced by dividing time periods and selecting representative data.
Preferably, as a modification, in step 23, the method for obtaining the average running speed includes: stopwatch velocimetry, tachometer measurement, vehicle induction instrument velocimetry.
The technical effects are as follows: according to the actual situation, a measuring method is selected, so that the average running speed of the vehicle can be conveniently and rapidly obtained.
Preferably, as a modification, the step 3 includes:
step 31, cleaning the average running speed information to obtain uniform format data;
step 32, carrying out time and intersection labeling on the unified format data to obtain a data set, and dividing the data set into a training set and a testing set;
and 33, substituting the training set into the neural network model for training, and testing the neural network model by adopting the testing set to obtain the intersection driving speed prediction model.
The technical effects are as follows: the driving speed of the intersection is predicted by the intersection driving speed prediction model, so that an optimal route can be provided for vehicle driving more accurately.
Preferably, as an improvement, the method further comprises a step 5 of analyzing the relation between building information and the predicted average running speed of the intersection by adopting a cluster analysis method;
and 6, recommending an auxiliary road dredging scheme according to the relation between the building information and the predicted average running speed of the intersection.
The technical effects are as follows: by means of the scheme recommendation of assisting in dredging the road, the traffic smoothness is facilitated, and the crossing passing efficiency is improved.
The intersection average running speed analysis system uses the intersection average running speed analysis method.
A storage medium having stored thereon a computer program which, when run on a computer, causes the computer to perform the intersection average travel speed analysis method.
Drawings
Fig. 1 is a flow chart of an analysis method of average driving speed at an intersection.
Detailed Description
The following is a further detailed description of the embodiments:
an example is substantially as shown in figure 1:
the method for analyzing the average running speed of the intersection comprises the following steps:
step 1, acquiring map data of an analysis area, and analyzing road information from the map data; specifically, map data of an analysis area is obtained from multi-source map software, such as a Goldmap, a hundred-degree map, a Beidou satellite map and the like, and the map data obtained by the multi-source map software are subjected to coordinate system unified conversion and calibration, so that the same position in different map data is overlapped; and then analyzing road information from the multi-source map data, when different results are analyzed at the same position, taking the latest updated map data as the reference, and when the map updating time is the same, taking the maximum number of analyzed identical results as the reference.
The road information comprises a road structure diagram, the number of lanes, the driving direction, red and green lamps, the type of lanes, the gradient of the lanes, the flatness of the road surface and the like.
Step 2, identifying intersections in the road information, and acquiring driving speed information in a preset range of each intersection; the step 2 specifically includes:
step 21, identifying an intersection in the road information; the intersections comprise turning-around intersections, crossroads, X-shaped intersections, T-shaped intersections, Y-shaped intersections, annular intersections and the like.
Step 22, determining the range of average running speed calculation at each intersection; the step 22 further includes:
step 221, scoring the complexity of the intersection according to the conflict points and the confluence points of the intersection, wherein the specific scoring is as follows:
wherein C is i For the number of the conflict points of the intersection i,the weight corresponding to the number x of the conflict points; h i For the number of the intersection i-junction points, delta y The weight corresponding to the number y of the current points is obtained; d (D) iz For the number of lanes at the z-th exit of intersection i, gamma j The weight value corresponding to the number j of the lanes; epsilon is a complexity correction constant;
different preset time periods correspond to differentδ y 、γ j And epsilon value, so that the range of average running speed calculation at each intersection changes with time to better accord with actual conditions.δ y 、γ j The epsilon value is obtained by training historical data, specifically, the historical average speed of the crossing, the number of salient points, the number of current-collecting points and the number of lanes corresponding to the historical average speed are obtained, and learning and training are carried out on the historical average speed of different time periods, the number of salient points, the number of current-collecting points and the number of lanes corresponding to the historical average speed, so as to obtain &corresponding to different time periods>δ y 、γ j Epsilon value.
The conflict point refers to a point where vehicles from different directions cross each other at a larger angle; the junction point refers to a place where vehicles from different directions merge to travel in the same direction at a smaller angle; three paths of intersections, such as T-shaped intersections and Y-shaped intersections, comprise 3 conflict points and 3 confluence points; the intersections of the four-way intersection such as the cross intersection, the X-shaped intersection and the like comprise 16 conflict points and 8 confluence points; the five-way intersection comprises 50 conflict points and 8 confluence points. The more the conflict points and the current combining points are, the lower the driving safety is, the dangerous degree of the conflict points is greater than that of the current combining points, and the conflict points can be limited in a smaller range by adopting methods such as channelized traffic.
Step 222, dividing the road length between two intersections according to the complexity ratio, and calculating the average running speed in the area within the ratio range. The more complex the road is, the slower the vehicle passing speed is, the fewer vehicles pass through in the same time, and the road length between two intersections is divided according to the complexity ratio, so that the intersections with high complexity can acquire enough vehicle data for analysis, and the prediction result is more accurate.
Step 23, obtaining the average running speed of the vehicle within the preset time period in the range of the intersection, wherein the average running speed comprises the unidirectional average running speed and the comprehensive average running speed.
The unidirectional average running speed is the average running speed of vehicles in all running directions in the intersection; if the intersections are three-way intersections, each intersection is a bidirectional lane, and no special sign board exists, vehicles in 6 directions travel, namely 6 unidirectional average travel speeds; the comprehensive average running speed is the average value of 6 unidirectional average running speeds.
The preset time period comprises an early peak, a late peak, a daytime and a night off-peak, and the morning peak is 7:30-9:30, peak late at 17:00-19:00, daytime 8:00-20:00; the night time is 20: 00-the next day 8:00, specifically, acquiring the average running speed of the vehicle with any fixed duration in a preset time period. For example, the sampling time is 1 hour, and then average running speeds of 1 hour are obtained in the time periods of the early peak, the late peak, the daytime peak and the night off-peak respectively. The method for acquiring the average running speed comprises the following steps: stopwatch velocimetry, tachometer measurement, vehicle induction instrument velocimetry.
The stopwatch velocimetry is an artificial measuring method, a measuring distance L is firstly determined, the time of various vehicles passing through two ends of the distance L is measured by using a stopwatch, the distance L, the vehicle type and the passing time t are recorded, and the average running speed v=1/t×3.6; the measured distance L is related to the vehicle speed, and in order to facilitate the observation of the reading, the elapsed time t of the vehicle is not less than 1.5s, and in this embodiment, 2s is preferably taken. Acquiring an average running speed within 1 hour, wherein when the average running speed is less than 40km/h, the L minimum value is 25m; when the average vehicle speed is 40-60 km/h, lmin is 50m, and when the average vehicle speed is greater than 65km/h, lmin is 75m.
When the average running speed is measured by using a velocimeter method, the velocimeter is a radar velocimeter, the speed is different according to the different vibration frequencies of the electric waves reflected by the moving object along with the moving speed of the object, the instantaneous speed of the vehicle passing through a speed measuring place is directly measured, speed data are directly recorded and printed, and the velocimeter is an ideal tool for measuring the place speed, but the measurement is difficult when measuring the low-speed vehicle, and only the speed of the high-speed vehicle is displayed when two vehicles are perceived simultaneously.
When the average running speed is measured by using a vehicle sensing instrument speed measurement method, the vehicle sensing instrument speed measurement is measured by using a vehicle sensor, and the passing distance and time of the vehicle are sensed simultaneously through electromagnetic induction or ultrasonic reflection, so that the passing speed of the vehicle is calculated. But when a faulty vehicle or an accident vehicle stays on the sensor, the vehicle speed record is abnormal.
Step 3, learning the running speed information to obtain an intersection average running speed prediction model; the step 3 comprises the following steps:
step 31, cleaning the average running speed information to obtain uniform format data; the average running speed information of different intersections obtained by different methods has the differences of expression forms, storage formats and the like, and the average running speed information is beneficial to data unification by cleaning, so that the error occurrence condition in the subsequent calculation can be reduced.
Step 32, carrying out time and intersection labeling on the unified format data to obtain a data set, and dividing the data set into a training set and a testing set; in different time periods, the average running speeds of the intersections are different, for example, the vehicles are more in the early peak and the late peak, the congestion condition is more serious, and the average running speed of the same intersection is relatively slower; for different intersections, because the vehicles arrive at different destinations, the traffic jam conditions of the lanes in different directions at the same intersection are also different, for example, the lanes running in the direction concentrated in the industrial park are blocked in the early peak, the average running speed is low, the lanes running in the direction concentrated in the residential area are blocked in the late peak, and the average running speed is low.
And 33, substituting the training set into the neural network model for training, and testing the neural network model by adopting the testing set to obtain the intersection driving speed prediction model.
And 4, predicting the average running speed of each intersection through the intersection average running speed prediction model, and recommending an optimal route according to the average running speed of each intersection.
The map information also analyzes building information, wherein the building information comprises building positions, building names and building uses;
the method further comprises the step 5 of analyzing the relation between building information and the predicted average running speed of the intersection by adopting a cluster analysis method; the application of the building has direct or indirect influence on the average running speed of the road opening; such as weekends or holidays, more vehicles exist at intersections near markets, scenic spots and entertainment places, and the average running speed is low; on the workday, the vehicles around schools, office buildings and industrial parks are more, and the average running speed is low;
and 6, recommending an auxiliary road dredging scheme according to the relation between the building information and the predicted average running speed of the intersection. The proposal recommendation of the auxiliary dredging road is carried out by combining road information, namely a road structure diagram, the number of lanes, the driving direction, red and green lamps, the type of lanes, the gradient of the lanes, the evenness of the road surface and the like; if the average running speed is smaller than the threshold value, temporarily occupying the roads with more lanes and fewer vehicles; and temporarily shortening the red light time of the lane with slow speed in the driving direction.
The intersection average running speed analysis system uses the intersection average running speed analysis method.
A storage medium having stored thereon a computer program which, when run on a computer, causes the computer to perform the intersection average travel speed analysis method.
The foregoing is merely exemplary of the present invention, and specific technical solutions and/or features that are well known in the art have not been described in detail herein. It should be noted that, for those skilled in the art, several variations and modifications can be made without departing from the technical solution of the present invention, and these should also be regarded as the protection scope of the present invention, which does not affect the effect of the implementation of the present invention and the practical applicability of the patent. The protection scope of the present application shall be subject to the content of the claims, and the description of the specific embodiments and the like in the specification can be used for explaining the content of the claims.
Claims (10)
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202311347588.3A CN117373262A (en) | 2023-10-17 | 2023-10-17 | Intersection average driving speed analysis method, system and storage medium |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202311347588.3A CN117373262A (en) | 2023-10-17 | 2023-10-17 | Intersection average driving speed analysis method, system and storage medium |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN117373262A true CN117373262A (en) | 2024-01-09 |
Family
ID=89396033
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202311347588.3A Pending CN117373262A (en) | 2023-10-17 | 2023-10-17 | Intersection average driving speed analysis method, system and storage medium |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN117373262A (en) |
Citations (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| KR20060110085A (en) * | 2005-04-19 | 2006-10-24 | 엘지전자 주식회사 | How to search for driving route of moving object using traffic information |
| CN105046985A (en) * | 2015-06-12 | 2015-11-11 | 重庆电讯职业学院 | Traffic control system for whole segments of main street based on big data |
| CN106595684A (en) * | 2016-11-22 | 2017-04-26 | 上海斐讯数据通信技术有限公司 | Electronic map-based navigation method and device |
| CN110827546A (en) * | 2019-11-21 | 2020-02-21 | 银江股份有限公司 | Signalized intersection road section short-term speed prediction method |
| CN114996372A (en) * | 2022-03-24 | 2022-09-02 | 阿里巴巴（中国）有限公司 | Traffic feature prediction method, electronic device and storage medium |
| CN116386323A (en) * | 2023-02-10 | 2023-07-04 | 腾讯科技（深圳）有限公司 | Method, device and equipment for training duration prediction model and estimating vehicle flow speed |
| CN116608878A (en) * | 2023-06-14 | 2023-08-18 | 南京四维智联科技有限公司 | Navigation path planning method, device, computer equipment and storage medium |
-
2023
- 2023-10-17 CN CN202311347588.3A patent/CN117373262A/en active Pending
Patent Citations (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| KR20060110085A (en) * | 2005-04-19 | 2006-10-24 | 엘지전자 주식회사 | How to search for driving route of moving object using traffic information |
| CN105046985A (en) * | 2015-06-12 | 2015-11-11 | 重庆电讯职业学院 | Traffic control system for whole segments of main street based on big data |
| CN106595684A (en) * | 2016-11-22 | 2017-04-26 | 上海斐讯数据通信技术有限公司 | Electronic map-based navigation method and device |
| CN110827546A (en) * | 2019-11-21 | 2020-02-21 | 银江股份有限公司 | Signalized intersection road section short-term speed prediction method |
| CN114996372A (en) * | 2022-03-24 | 2022-09-02 | 阿里巴巴（中国）有限公司 | Traffic feature prediction method, electronic device and storage medium |
| CN116386323A (en) * | 2023-02-10 | 2023-07-04 | 腾讯科技（深圳）有限公司 | Method, device and equipment for training duration prediction model and estimating vehicle flow speed |
| CN116608878A (en) * | 2023-06-14 | 2023-08-18 | 南京四维智联科技有限公司 | Navigation path planning method, device, computer equipment and storage medium |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| US11521487B2 (en) | System and method to generate traffic congestion estimation data for calculation of traffic condition in a region | |
| CN107305131B (en) | Node-centric navigation optimization | |
| EP3016086B1 (en) | Negative image for sign placement detection | |
| EP2966590B1 (en) | Lane level traffic | |
| EP2681512B1 (en) | Vehicle route calculation | |
| US11460312B2 (en) | Method, apparatus, and computer program product for determining lane level traffic information | |
| CN100463009C (en) | A traffic information fusion processing method and system | |
| US11237007B2 (en) | Dangerous lane strands | |
| JP5649726B2 (en) | How to determine cross-failure information | |
| US11024166B2 (en) | Method, apparatus, and computer program product for estimating traffic speed through an intersection | |
| US20190145794A1 (en) | System and Method for Predicting Hyper-Local Conditions and Optimizing Navigation Performance | |
| US11915583B2 (en) | Traffic predictions at lane level | |
| CN107807542A (en) | Automatic Pilot analogue system | |
| WO2018171464A1 (en) | Method, apparatus and system for planning vehicle speed according to navigation path | |
| EP2743898A3 (en) | A method of and a navigation device for time-dependent route planning | |
| EP3821388A1 (en) | Method, apparatus, and computer program product for evaluating public transportation use | |
| US12174032B2 (en) | Real-time lane-level traffic processing system and method | |
| US9911332B1 (en) | Method, apparatus, and computer program product for parking likelihood estimation based on probe data collection | |
| US11341845B2 (en) | Methods and systems for roadwork zone identification | |
| US20220205799A1 (en) | Method, apparatus, and computer program product for determining benefit of restricted travel lane | |
| JP2007140745A (en) | Traffic jam prediction system, traffic jam factor estimation system, traffic jam prediction method, and traffic jam factor estimation method | |
| CN117373262A (en) | Intersection average driving speed analysis method, system and storage medium | |
| CN116343468B (en) | Devices and methods for predicting transit time and methods for predicting travel time | |
| Wang et al. | Traffic monitoring using floating car data in Hefei | |
| Guo et al. | Traffic flow estimation methods during highway reconstruction |
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 |