CN115273488A - Road vehicle parking judgment method based on travel time - Google Patents
Road vehicle parking judgment method based on travel time Download PDFInfo
- Publication number
- CN115273488A CN115273488A CN202210907646.2A CN202210907646A CN115273488A CN 115273488 A CN115273488 A CN 115273488A CN 202210907646 A CN202210907646 A CN 202210907646A CN 115273488 A CN115273488 A CN 115273488A
- Authority
- CN
- China
- Prior art keywords
- vehicle
- travel time
- road section
- cluster
- time data
- 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.)
- Granted
Links
Images
Classifications
-
- G—PHYSICS
- G08—SIGNALLING
- G08G—TRAFFIC CONTROL SYSTEMS
- G08G1/00—Traffic control systems for road vehicles
- G08G1/065—Traffic control systems for road vehicles by counting the vehicles in a section of the road or in a parking area, i.e. comparing incoming count with outgoing count
-
- 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
- G08G1/017—Detecting movement of traffic to be counted or controlled identifying vehicles
- G08G1/0175—Detecting movement of traffic to be counted or controlled identifying vehicles by photographing vehicles, e.g. when violating traffic rules
-
- 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
Landscapes
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Traffic Control Systems (AREA)
Abstract
The invention belongs to the technical field of vehicle monitoring, and relates to a road section vehicle parking judgment method based on travel time, which comprises the following steps: acquiring traffic flow of a road section, and dividing traffic flow time periods; setting a time window and acquiring vehicle travel time sample data; constructing a clustering model; classifying the vehicle travel time data in each time window to obtain a classification result; obtaining separated vehicle travel time data of normal running and delayed running; determining the overtaking state of a vehicle with delayed running at the end position of a road section; and judging whether the vehicle with delayed running has parking activity in the road section. According to the method, the time window is selected according to the traffic flow time period, whether the vehicle has parking activity or not is judged, and the speed characteristics of the vehicle in different time periods are better met; the vehicle travel time is classified through the clustering model, whether the vehicle has parking activity or not is judged according to the overtaking state and the vehicle travel time of the vehicle, and the accuracy of the judgment result is improved.
Description
Technical Field
The invention relates to the technical field of vehicle monitoring, in particular to a road section vehicle parking judgment method based on travel time.
Background
The existing road vehicle parking judging method mainly focuses on researching vehicle travel time classification, divides vehicle travel time into a plurality of types through a machine learning algorithm, and defines vehicle running states according to travel time characteristics so as to judge whether vehicles are parked or not. The existing method cannot distinguish the condition that the vehicle stops for the second time at the intersection due to the road congestion and the condition that the vehicle stops for a short time but the total travel time is short.
Disclosure of Invention
In order to solve the technical problem, the invention provides a road section vehicle parking judgment method based on travel time, which comprises the following steps of:
acquiring traffic flow of a road section, and dividing traffic flow time periods according to the traffic flow;
setting time windows according to the traffic flow time periods, and acquiring vehicle travel time sample data in each time window;
constructing a K-Means clustering model by using the vehicle travel time sample data in each time window;
classifying the vehicle travel time data in each time window by using the K-Means clustering model to obtain a classification result;
according to the classification result, obtaining separated vehicle travel time data of normal running and vehicle travel time data of delayed running;
acquiring the sequence of each vehicle at the initial position of a road section and the queue sequence of the tail position of the road section, determining the overtaking state of the vehicle with delayed running at the tail position of the road section, and acquiring the vehicle travel time data of the vehicle with delayed running at the road section;
judging whether the vehicle with delayed running has parking activity in the road section according to the overtaking state of the vehicle with delayed running at the tail end of the road section and the vehicle travel time data of the vehicle with delayed running in the road section; if the vehicle with delayed running has overtaking and the vehicle travel time data in the road section is larger than the set threshold value of the vehicle travel time data, the vehicle with delayed running has parking activity in the road section, otherwise the vehicle with delayed running has no parking activity in the road section.
The invention has the beneficial effects that: according to the method, the time window is selected according to the traffic flow time period, whether the vehicle has parking activity or not is judged, and the speed characteristics of the vehicle in different time periods are better met; the vehicle travel time is classified through the K-Means clustering model, whether the vehicle has parking activity or not is judged according to the overtaking state and the vehicle travel time of the vehicle under each classification condition, and the accuracy of the judgment result is improved.
On the basis of the technical scheme, the invention can be further improved as follows.
Further, the method also includes: and acquiring the time difference of the overtaking vehicle and the overtaken vehicle passing through a signal lamp at the tail position of the road section, and judging whether the time difference is larger than the set multiple of the signal lamp period, wherein if so, the overtaken vehicle has parking activity, otherwise, the overtaken vehicle does not have parking activity.
Further, constructing the K-Means clustering model comprises:
calculating the average value of the dispersion in the cluster;
the method comprises the steps of utilizing a trace of a cluster divergence matrix to represent the density degree of the same cluster, and utilizing a trace of an inter-cluster divergence matrix to represent the distance degree between different clusters;
calculating the ratio of the average value of the intra-cluster dispersion to the inter-cluster dispersion to obtain a variance ratio standard;
determining the value of the number of the classification clusters according to the standard size of the variance ratio;
and determining a time window according to the value of the classification cluster number.
Further, the classification result comprises first cluster vehicle travel time data and second cluster vehicle travel time data; the first cluster vehicle travel time data are smaller than a first set value, and the traffic flow data are larger than a second set value; the second cluster vehicle travel time data is larger than a third set value, and the traffic flow data is smaller than a second set value; the first set value is less than the third set value.
Further, still include: and judging whether the vehicle travel time data of the vehicles which are not overtaken are greater than the set time or not for the vehicles which are not overtaken, if so, parking activity exists in the vehicles which are not overtaken, and otherwise, no parking activity exists in the vehicles which are not overtaken.
Further, the set threshold value of the vehicle travel time data in the night time period is greater than or equal to the sum of the first cluster vehicle travel time data and the cycle time of the road section ending position signal.
Further, the same vehicle is determined at the initial position of the road section and the end position of the road section by means of image acquisition and license plate number identification, and the overtaking state of the vehicle is determined by combining the time when the vehicle reaches the initial position of the road section and the end position of the road section or the sequence of the vehicles in the queue.
Drawings
Fig. 1 is a flowchart of a method for determining vehicle parking on a road segment based on travel time according to embodiment 1 of the present invention;
FIG. 2 is a schematic diagram of overtaking of a vehicle for a road section parking activity in embodiment 1 of the present invention;
FIG. 3 is a schematic view of a vehicle arriving at an intersection;
FIG. 4 is a table of vehicle travel time data categories for peak time periods in the morning and evening of traffic flow;
FIG. 5 is a table of vehicle travel time data categories for peak time periods in the morning and evening of traffic flow;
FIG. 6 is a chart of vehicle travel time data categories for the early morning hours;
FIG. 7 is a table showing the number of overtaken vehicles for parking;
FIG. 8 is a simulation diagram of vehicle travel time classification results throughout the day;
fig. 9 is a schematic diagram showing a relationship between a time at which a vehicle passes through an intersection of a road section and a vehicle travel time.
Detailed Description
In order to make the objects, technical solutions and advantages of the embodiments of the present invention clearer, 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 some, but not all, embodiments of the present invention. The components of embodiments of the present invention generally described and illustrated in the figures herein may be arranged and designed in a wide variety of different configurations.
Example 1
As an embodiment, as shown in fig. 1, to solve the above technical problem, the embodiment provides a method for determining vehicle parking on a road segment based on travel time, including the steps of:
acquiring traffic flow of a road section, and dividing traffic flow time periods according to the traffic flow; optionally, dividing the vehicle flow time period into a first time period (00-06 00), a second time period (7;
setting time windows according to the traffic flow time period, and acquiring vehicle travel time sample data in each time window; optionally, for a second time period with a larger traffic flow, the time window is set to 15 minutes; setting a time window of 30 minutes for the first time period and the third time period;
constructing a K-Means clustering model by using the vehicle travel time sample data in each time window;
classifying the vehicle travel time data in each time window by using a K-Means clustering model to obtain a classification result;
according to the classification result, obtaining separated vehicle travel time data of normal running and vehicle travel time data of delayed running;
acquiring the sequence of each vehicle at the initial position of the road section and the queue sequence of the tail position of the road section, determining the overtaking state of the vehicle with delayed running at the tail position of the road section, and acquiring the vehicle travel time data of the vehicle with delayed running at the road section;
judging whether the vehicle with delayed running has parking activity in the road section according to the overtaking state of the vehicle with delayed running at the tail end of the road section and the vehicle travel time data of the vehicle with delayed running in the road section; if the vehicle with the delayed running has overtaking and the vehicle travel time data in the road section is larger than the set threshold value of the vehicle travel time data, the vehicle with the delayed running has parking activity in the road section, otherwise the vehicle with the delayed running does not have parking activity in the road section.
The invention has the beneficial effects that: according to the method, the time window is selected according to the traffic flow time period, whether the vehicle has parking activity or not is judged, and the speed characteristics of the vehicle in different time periods are better met; the vehicle travel time is classified through the K-Means clustering model, whether the vehicle has parking activity or not is judged according to the vehicle overtaking state and the vehicle travel time under each classification condition, and the accuracy of the judgment result is improved.
In practical applications, the vehicle parking activity is the vehicle parking at the roadside activity, such as: getting on and off a bus, ordering a taxi through a taxi network, and the like, and stopping a taxi by a driver.
As shown in the schematic diagram of fig. 2, the vehicle for parking activity is overtaken, the road is provided with four lanes L1, L2, L3 and L4, the vehicle M1 has parking activity on the road section, and finally leaves the road section through the lane L3 at the intersection, and the vehicle M2 passing through during parking overtakes, so that a parking delay is generated. The overtaking vehicle M1 is positioned at the intersection L3 lane queue and then leaves the road section, namely the overtaking vehicle M1 passes through the downstream intersection L3 lane later than the overtaking vehicle M2.
Optionally, the method further includes: and acquiring the travel time difference of the overtaking vehicle and the overtaken vehicle passing through the end position of the road section, judging whether the time difference is greater than the signal lamp period of a set multiple, if so, determining that the overtaken vehicle has parking activity, otherwise, determining that the overtaken vehicle does not have parking activity.
In the practical application process, the overtaking vehicle and the overtaken vehicle pass through the initial position of the road section, so that the time when the overtaking vehicle passes through the upstream intersection is 1 or more signal cycles later than the time when the overtaken vehicle passes through the initial position of the road section, and the time when the overtaken vehicle passes through the end position of the road section is earlier than the time when the overtaken vehicle passes through the initial position of the road section. Optionally, the time difference is a green time length, that is, the overtaking situation of the vehicle passing through the initial position of the road section in the same signal period is not considered, and the overtaking situation of the vehicle passing through the initial position of the road section in a non-same signal period is only considered.
Let t be the moment when the overtaking vehicle passes through the initial position of the road sectionstartThe time when the overtaking vehicle passes through the initial position of the road section is t'startThe moment when the overtaking vehicle passes through the end position of the road section is tendT 'is the time when the overtaking vehicle passes through the link end position'endThe green time at the end of the road section is tgThen: t is tstart-t'start>tgAnd t isend>t'end。
Because the vehicles at the intersection part do not pass through the intersection at the tail position of the road section within the time of one green light, the vehicles need to wait for the next green light, and the vehicles are influenced by the red light to cause delay. However, such vehicles are in the queue at the intersection, so that subsequent vehicles are queued behind them and are not normally overrun by the following vehicles. As shown in fig. 3, the vehicle M4 is located in the L3 and L4 lanes, and when the green light is turned on, these vehicles M4 start simultaneously with the vehicles M3 in the L1 and L2 lanes, but due to the driver skill and vehicle performance, some of the vehicles that do not reach the intersection may overtake the vehicles in the L1 and L2 lanes. When the vehicles in the L1 and L2 lanes arrive at the intersection under the condition of not changing lanes, the vehicles which arrive at the intersection in the last signal lamp period of the L1 and L2 lanes are not overtaken by the vehicles which do not arrive in the L1 and L2 lanes.
Optionally, constructing the K-Means clustering model includes:
calculating the average value of the dispersion in the cluster;
the method comprises the steps of utilizing a trace of a cluster divergence matrix to represent the density degree of the same cluster, and utilizing a trace of an inter-cluster divergence matrix to represent the distance degree between different clusters;
calculating the ratio of the average value of the intra-cluster dispersion to the inter-cluster dispersion to obtain a variance ratio standard;
determining the value of the number of the classification clusters according to the standard size of the variance ratio;
and determining a time window according to the value of the classification cluster number.
In the practical application process, the number of classified clusters of the clustered data is set as k, the number of data points is set as N, the trace of the cluster divergence matrix is Tr (Bk), and the trace of the inter-cluster divergence matrix is Tr (Wk), wherein:
in the formula: cqA set of points that is a cluster q; c. CqIs the center point of cluster q; n isqPoints that are clusters q; c is the center of all data sets;
the variance ratio standard:
the trace of the cluster divergence matrix represents the density of the same cluster, and the smaller the trace, the denser the data set of the same cluster (the smaller the variance ratio standard); the trace of the inter-cluster divergence matrix represents the degree of separation between different clusters, the larger the trace, the larger the degree of separation between different clusters (the larger the variance ratio criterion). And determining the number of the classified clusters by selecting a variance ratio standard, performing cluster evaluation on the clustering method by comparing the variance ratio standards under different classified clusters, and determining the optimal classified cluster.
The variance ratio standard can quantify the clustering quality and reflect the effect under different clustering clusters. By calculating the number of the optimal clusters in each classification cluster, dense clusters in the clusters are separated, and the clustering effect is optimal.
Optionally, the classification result includes travel time data of the first cluster type vehicle and travel time data of the second cluster type vehicle; the travel time data of the first cluster type vehicles are smaller than a first set value, and the traffic flow data are larger than a second set value; the travel time data of the second cluster type vehicles are larger than a third set value, and the traffic flow data are smaller than a second set value; the first set value is less than the third set value.
In practical use, the first time period (00-06.
The average speed of the vehicles corresponding to the first cluster vehicle travel time data is high, and the vehicles passing through the road section are not influenced by signal delay; the average speed of the vehicles corresponding to the travel time data of the second cluster type of vehicles is low, and the vehicles are influenced by parking activities such as signal delay or secondary queuing and the like when passing through the road section.
As shown in fig. 4, in the traffic flow early-late peak time period vehicle travel time data classification table, the ratio of the first cluster vehicle travel time data and the second cluster vehicle travel time data of the early-late peak is basically consistent, and the general trend of the vehicle travel time is that the early peak is larger than the late peak.
As shown in fig. 5, in the vehicle travel time data classification table in the peak-averaging time period of the traffic flow, the first cluster vehicle travel time data and the second cluster vehicle travel time data are obviously layered, but the aggregation degree of the first cluster vehicle travel time data is obviously higher than that of the second cluster vehicle travel time data, and the variance is also obviously smaller than that of the second cluster vehicle travel time data. The travel time data proportion of the first cluster type vehicles in the peak leveling period is 85.35% through statistics, and the travel time data proportion of the second cluster type vehicles is 14.65%.
As shown in fig. 6, in the classification table of the vehicle travel time data in the early morning time period, there are fewer vehicles in the early morning time period at night, and the signal period in the research area is shorter, and it can be known by clustering the vehicle travel time data at night that the travel time variance in the early morning at night is not large and the travel time mean value is small, but the proportion of the first cluster of vehicle travel time data is still large. The statistical data rate of the travel time data of the first cluster type vehicles is 78.90%, and the data rate of the travel time data of the second cluster type vehicles is 21.10%.
As shown in the simulation diagram of the classification result of the vehicle travel time in the whole day shown in fig. 7, the travel time data of the first cluster type vehicle is 83.79% and the travel time data of the second cluster type vehicle is 16.21%. Wherein, the number of vehicles is less at night, and the travel time is more stable; the early peak has large travel time due to the large flow and the influence of phase difference, and reaches the maximum value all day; the flow is small during the peak-off period, and the travel time of the vehicle is correspondingly reduced.
Figure 8 shows a number meter for overtaking due to parking activity of vehicle in one week
Optionally, the method further includes: and judging whether the travel time data of the vehicles which are not overtaken is greater than the set time or not for the vehicles which are not overtaken, if so, parking activity exists for the vehicles which are not overtaken, and otherwise, the vehicles which are not overtaken do not have parking activity.
In the practical application process, when the traffic flow of the road segment is small, the parked vehicle has a condition that the vehicle is not overtaken, that is, whether the vehicle is parked or not cannot be judged by using the overtaking characteristic, so that a time period (00-00 in the morning. And analyzing the travel time by combining intersection signal cycle data of the tail positions of the road sections on the basis of vehicle travel time data classification, thereby determining a vehicle travel time data set threshold under the condition of vehicle parking on the road sections, and judging whether vehicle parking activity exists in the time section with smaller traffic flow of the road sections by utilizing the vehicle travel time data set threshold.
Optionally, the set threshold of the vehicle travel time data in the night time period is greater than or equal to the sum of the first cluster vehicle travel time data and the cycle time of the road section ending position signal.
In the practical application process, the vehicle travel time is delayed due to the influence of signal lamps, and the phase of the signal lamp at the tail position of the road section can cause the arrival of the vehicle to present different phenomena.
Fig. 9 is a schematic diagram showing the relationship between the time when the vehicle passes through the intersection of the road segment and the travel time of the vehicle, wherein two ends of the line segment respectively represent the time when the vehicle passes through the intersection at the initial position of the road segment and the time when the vehicle passes through the intersection at the end position of the road segment.
(1) Scenario one: and when the vehicle passes through the intersection at the position of the tail end of the road section without signal delay, the travel time of the vehicle at the time is the travel time corresponding to the free-flow vehicle speed. The vehicle that has passed this time period has the shortest travel time, and therefore corresponds to the vehicle at the position of the point corresponding to the region Q1 in fig. 9. Let the vehicle travel time at this time be t0.
(2) Scenario two: the green light of the intersection at the initial position of the road section is released, the motorcade is started, the signal light is red when the vehicle arrives at the initial position of the road section, and the vehicle needs to wait for the time of the red light to pass, so the vehicle is delayed by the signal light. The vehicle travel time at this time period is: t is t1＝t+td1In the formula: t is t1As the vehicle travel time, t is the vehicle free stream travel time, td1Delay time for vehicles effected by signal lamps, where td1<c-g, wherein c is the intersection signal period of the end position of the road section, and g is the green time. The vehicle corresponding to this case is the midpoint of the region Q2 in FIG. 9The vehicle is affected by the signal delay, but the vehicle still passes the intersection within one green time of the intersection at the end of the road section, t1<t+c-g。
(3) Scenario three: the green light of the upstream intersection is released, the motorcade is started, the intersection signal light when the vehicle reaches the tail position of the road section is the red light, and the vehicle needs to wait for a complete red light time to pass, so the vehicle is delayed by the signal light. The vehicle travel time in this period is: t is t2＝t+td2In the formula: t is t2Is the vehicle travel time, t is the vehicle free stream travel time, t2Delay time for vehicles effected by signal lamps, c-g<＝td2<= c. The vehicle corresponding to this situation is the position of the midpoint of the area Q3 in fig. 9, the vehicle is affected by the signal delay, and the vehicle fails to pass through the intersection in this signal cycle, so the vehicle must wait for a red light time before passing through the intersection, and the total travel time of the vehicle is: t + c-g<＝t2<＝t+c。
The three scenarios described above correspond to several situations where the vehicle arrives at the intersection, and several situations where the vehicle is traveling for a certain time. Now, assume that the traffic state of scenario one is a, the traffic state of scenario two is B, and the traffic state of scenario three is C. The difference in travel time between the two states, scene one and scene two, is [0, c-g ]; the travel time difference between the scene one and the scene three is [ c-g, c ]; the travel time difference between the two states of scene two and scene three is [0, c ]. Therefore, the upper limit value of the travel time when the vehicle is not parked on the road is t + c.
Optionally, the vehicle is determined to be the same vehicle at the initial position of the road section and the end position of the road section in a mode of identifying the license plate number through image acquisition, and the overtaking state of the vehicle is determined by combining the time when the vehicle reaches the initial position of the road section and the end position of the road section or the sequence of the vehicles in the queue. The time that the vehicle reaches the initial position of the road section is compared with the time that the vehicle reaches the end position of the road section, if the vehicle reaching the initial position of the road section first reaches the end position of the road section later than the vehicle at the initial position of the road section, the vehicle is overtaken; or the sequence of the vehicle reaching the initial position of the road section and reaching the end position of the road section is changed, namely, one vehicle is positioned in front of the other vehicle when reaching the initial position of the road section, and the vehicle reaching the end position of the road section is positioned behind the other vehicle in the queue of the intersection, so that the vehicle is overtaken in the process of the road section.
The above is only a preferred embodiment of the present invention, and is not intended to limit the present invention, and various modifications and changes will occur to those skilled in the art. Any modification, equivalent replacement, or improvement made within the spirit and principle of the present invention should be included in the protection scope of the present invention.
Claims (7)
1. A road section vehicle parking judgment method based on travel time is characterized by comprising the following steps:
acquiring traffic flow of a road section, and dividing traffic flow time periods according to the traffic flow;
setting time windows according to the traffic flow time periods, and acquiring vehicle travel time sample data in each time window;
constructing a K-Means clustering model by using the vehicle travel time sample data in each time window;
classifying the vehicle travel time data in each time window by using the K-Means clustering model to obtain a classification result;
according to the classification result, obtaining separated vehicle travel time data of normal running and vehicle travel time data of delayed running;
acquiring the sequence of each vehicle at the initial position of a road section and the queue sequence of the tail position of the road section, determining the overtaking state of the vehicle with delayed running at the tail position of the road section, and acquiring the vehicle travel time data of the vehicle with delayed running at the road section;
judging whether the vehicle with delayed running has parking activity in the road section according to the overtaking state of the vehicle with delayed running at the tail end of the road section and the vehicle travel time data of the vehicle with delayed running in the road section; if the vehicle with the delayed running has overtaking and the vehicle travel time data in the road section is larger than the set threshold value of the vehicle travel time data, the vehicle with the delayed running has parking activity in the road section, otherwise the vehicle with the delayed running does not have parking activity in the road section.
2. The method for judging whether to park the vehicle on the road section based on the travel time according to claim 1, further comprising:
and acquiring a travel time difference value of the overtaking vehicle and the overtaken vehicle passing through the end position of the road section, and judging whether the time difference is greater than a set multiple of signal lamp period, wherein if so, the overtaken vehicle has parking activity, otherwise, the overtaken vehicle does not have parking activity.
3. The road segment vehicle parking judgment method based on the travel time as claimed in claim 1, wherein the constructing of the K-Means clustering model comprises:
calculating the average value of the dispersion in the cluster;
the method comprises the steps of utilizing a trace of a cluster divergence matrix to represent the density degree of the same cluster, and utilizing a trace of an inter-cluster divergence matrix to represent the distance degree between different clusters;
calculating the ratio of the average value of the intra-cluster dispersion to the inter-cluster dispersion to obtain a variance ratio standard;
determining the value of the number of the classification clusters according to the standard size of the variance ratio;
and determining a time window according to the value of the classification cluster number.
4. The method for judging road section vehicle parking based on travel time according to claim 1, wherein the classification result comprises first cluster type vehicle travel time data and second cluster type vehicle travel time data; the first cluster vehicle travel time data are smaller than a first set value, and the traffic flow data are larger than a second set value; the second cluster vehicle travel time data is larger than a third set value, and the traffic flow data is smaller than a second set value; the first set value is smaller than the third set value.
5. The method for judging whether to park the vehicle on the road section based on the travel time according to claim 1, further comprising: and judging whether the vehicle travel time data of the vehicles which are not overtaken are greater than the set time or not for the vehicles which are not overtaken, if so, parking activity exists in the vehicles which are not overtaken, and otherwise, no parking activity exists in the vehicles which are not overtaken.
6. The method as claimed in claim 1, wherein the vehicle travel time data set threshold value in the night time period is greater than or equal to the sum of the travel time data of the first cluster type vehicle and the cycle time of the end position signal of the road section.
7. The method as claimed in claim 1, wherein the vehicle is determined to be the same vehicle at the initial position of the road section and at the end position of the road section by recognizing the number plate through image acquisition, and the overtaking state of the vehicle is determined by combining the time when the vehicle reaches the initial position of the road section and the end position of the road section or the sequence of the vehicles in the queue.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202210907646.2A CN115273488B (en) | 2022-07-29 | 2022-07-29 | Road section vehicle parking judging method based on travel time |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202210907646.2A CN115273488B (en) | 2022-07-29 | 2022-07-29 | Road section vehicle parking judging method based on travel time |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN115273488A true CN115273488A (en) | 2022-11-01 |
| CN115273488B CN115273488B (en) | 2023-09-22 |
Family
ID=83772595
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202210907646.2A Active CN115273488B (en) | 2022-07-29 | 2022-07-29 | Road section vehicle parking judging method based on travel time |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN115273488B (en) |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN117133130A (en) * | 2023-10-26 | 2023-11-28 | 中国市政工程西南设计研究总院有限公司 | Airport road congestion prediction simulation method and system |
Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| JP2005234656A (en) * | 2004-02-17 | 2005-09-02 | Matsushita Electric Ind Co Ltd | Delay time estimating device, method, system and program |
| CN106571029A (en) * | 2016-10-18 | 2017-04-19 | 青岛海信网络科技股份有限公司 | Method and device for detecting vehicle queue length |
| CN106652458A (en) * | 2017-02-20 | 2017-05-10 | 东南大学 | Online urban road route travel time estimation method based on virtual vehicle locus reconstruction |
| CN113112816A (en) * | 2021-04-06 | 2021-07-13 | 安徽百诚慧通科技有限公司 | Method for extracting average running delay of vehicle on road section |
| CN113380036A (en) * | 2021-06-16 | 2021-09-10 | 上海应用技术大学 | Queuing length calculation method based on electronic police data |
| CN114241776A (en) * | 2021-12-31 | 2022-03-25 | 连云港杰瑞电子有限公司 | Road section parking number dynamic estimation method based on rolling time window |
-
2022
- 2022-07-29 CN CN202210907646.2A patent/CN115273488B/en active Active
Patent Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| JP2005234656A (en) * | 2004-02-17 | 2005-09-02 | Matsushita Electric Ind Co Ltd | Delay time estimating device, method, system and program |
| CN106571029A (en) * | 2016-10-18 | 2017-04-19 | 青岛海信网络科技股份有限公司 | Method and device for detecting vehicle queue length |
| CN106652458A (en) * | 2017-02-20 | 2017-05-10 | 东南大学 | Online urban road route travel time estimation method based on virtual vehicle locus reconstruction |
| CN113112816A (en) * | 2021-04-06 | 2021-07-13 | 安徽百诚慧通科技有限公司 | Method for extracting average running delay of vehicle on road section |
| CN113380036A (en) * | 2021-06-16 | 2021-09-10 | 上海应用技术大学 | Queuing length calculation method based on electronic police data |
| CN114241776A (en) * | 2021-12-31 | 2022-03-25 | 连云港杰瑞电子有限公司 | Road section parking number dynamic estimation method based on rolling time window |
Cited By (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN117133130A (en) * | 2023-10-26 | 2023-11-28 | 中国市政工程西南设计研究总院有限公司 | Airport road congestion prediction simulation method and system |
| CN117133130B (en) * | 2023-10-26 | 2024-03-01 | 中国市政工程西南设计研究总院有限公司 | Airport road congestion prediction simulation method and system |
Also Published As
| Publication number | Publication date |
|---|---|
| CN115273488B (en) | 2023-09-22 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN110111592B (en) | Method for dynamically matching optimal signal timing scheme based on traffic signal controller | |
| CN109191830B (en) | Road congestion detection method based on video image processing | |
| CN111341095B (en) | Traffic signal control system and method based on edge side online calculation | |
| CN112017437B (en) | Intersection traffic information perception control system and method | |
| CN103680163A (en) | Regional bus signal priority method based on bus demands | |
| CN106971546B (en) | Road section bus permeability estimation method based on bus GPS data | |
| CN108109403B (en) | Adaptive traffic light control system and method based on traffic flow | |
| CN113516854B (en) | Multi-interface coordination self-adaptive control method based on police card and video detector | |
| CN115273488B (en) | Road section vehicle parking judging method based on travel time | |
| CN113380027A (en) | Intersection traffic state parameter estimation method and system based on multi-source data | |
| CN114202916B (en) | Single-point intersection traffic signal control method | |
| CN106023610B (en) | A kind of bus and the green wave Synchronization of private car main line considering motorcade dispersion feature | |
| CN108615374B (en) | Intersection lamp group phase conflict configuration method based on traffic flow | |
| CN107705590B (en) | Intelligent phase control method and system for tramcar passing intersection | |
| CN109377771B (en) | Demand judgment method and device for arranging external left-turn lane at signalized intersection | |
| CN113506442B (en) | Urban road network traffic signal lamp control method based on expected income estimation | |
| CN111754771A (en) | Individual travel time prediction method based on traffic signals and density delay | |
| CN113823102A (en) | Self-adaptive signal timing system and method under software-defined vehicle-mounted network environment | |
| CN111882889B (en) | Intelligent traffic signal control system and method | |
| CN110046535B (en) | Intelligent travel time prediction system, method and storage medium based on machine learning | |
| CN113066286B (en) | Method and device for judging vehicle running risk road sections of vehicle-road cooperative road network | |
| CN110049467B (en) | Region clustering method based on different signal lamp states | |
| CN115019525A (en) | Travel time data screening method and traffic signal control method | |
| CN110853350B (en) | Arterial road phase difference optimization method based on floating car track data | |
| CN114299736A (en) | Multi-intersection traffic self-adaptive coordination control method |
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 |