CN113724499A - Three-dimensional visual analysis method and system for road traffic events - Google Patents
Three-dimensional visual analysis method and system for road traffic events Download PDFInfo
- Publication number
- CN113724499A CN113724499A CN202111296981.5A CN202111296981A CN113724499A CN 113724499 A CN113724499 A CN 113724499A CN 202111296981 A CN202111296981 A CN 202111296981A CN 113724499 A CN113724499 A CN 113724499A
- Authority
- CN
- China
- Prior art keywords
- data
- event
- traffic
- dimensional
- road
- 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
Images
Classifications
-
- G—PHYSICS
- G08—SIGNALLING
- G08G—TRAFFIC CONTROL SYSTEMS
- G08G1/00—Traffic control systems for road vehicles
- G08G1/01—Detecting movement of traffic to be counted or controlled
- G08G1/0104—Measuring and analyzing of parameters relative to traffic conditions
- G08G1/0125—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
- G08G1/0125—Traffic data processing
- G08G1/0129—Traffic data processing for creating historical data or processing based on historical 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
- G08G1/0137—Measuring and analyzing of parameters relative to traffic conditions for specific applications
-
- 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
- G08G1/07—Controlling traffic signals
- G08G1/08—Controlling traffic signals according to detected number or speed of vehicles
Abstract
The invention discloses a three-dimensional visual analysis method and a three-dimensional visual analysis system for road traffic events, wherein the method comprises the following steps: when a traffic event occurs, acquiring detection data of front-end road side equipment, internet traffic event data and three reported data for fusion; according to the result of data fusion, correlating traffic flow data and congestion conditions of upstream and downstream intersections, and constructing a three-dimensional event model based on a high-precision map; and predicting the subsequent influence of the congestion event according to the three-dimensional event model, and generating a new signal control scheme. The method restores the traffic condition of the congestion point through a three-dimensional visualization technology, associates the traffic flow and the congestion condition of the upstream and downstream intersections, and constructs a three-dimensional event model on a high-precision map. The traffic situation is predicted by using the model data, the collision of the intersection is monitored and early warned, lane-level flow indexes can be provided for a signal machine, the current intersection signal control scheme is adjusted, and the signal control optimization scheme is sent to a signal control platform, so that the signal control optimization effect of the intersection and a trunk line is realized.
Description
Technical Field
The invention relates to the technical field of intelligent traffic, in particular to a three-dimensional visual analysis method and a three-dimensional visual analysis system for road traffic events.
Background
At present, in the field of road traffic, the related high-precision map positioning technology and three-dimensional visual modeling technology are as follows:
(1) high-precision map positioning technology: the map is accurate to the centimeter level and the data dimension is embodied in that it includes surrounding static information related to traffic in addition to road information.
The high-precision map can provide high-precision static information such as road networks, road shapes, lanes, POIs, buildings, road signs and the like, and also contains dynamic real-time traffic information, and a virtual full-element space is formed by fusing the two types of information.
(2) Three-dimensional visual modeling technology: the full-element 3D technology is used for completely reproducing road information, traffic incident information, roadside traffic equipment information, obstacles and traffic participant information to a virtual three-dimensional space through a high-precision map. The information has relative coordinates and absolute coordinates, and can provide accurate positioning of the object. And modeling analysis is carried out according to historical data, and the traffic jam condition is predicted and simulated.
The existing method for analyzing the road event congestion mainly relies on video flow detector data and a bayonet camera video for verification or generates road condition information according to internet floating car data to judge the road congestion.
When traffic jam occurs at the intersection, the video flow detector analyzes the vehicles based on the video, and data collection of the vehicles which are stopped statically in one direction cannot be accurately counted; the checking and verification of the bayonet video is limited by the fixed installation position and angle of the equipment, the whole road cannot be fully covered, and only partial visual angles can be checked; the floating car data can only pass through the principle of mobile phone positioning, and the event information and the influence cannot be accurately described even if part of the data is repeated.
Therefore, how to accurately describe the traffic incident information, predict the traffic influence and further provide an optimized traffic signal control scheme becomes a problem to be solved urgently.
Disclosure of Invention
The invention aims to provide a three-dimensional visual analysis method and a three-dimensional visual analysis system for a road traffic incident, which can solve the problems that the traffic condition cannot be accurately described and a corresponding optimization scheme cannot be provided in the prior art.
In order to achieve the purpose, the invention adopts the technical scheme that:
in a first aspect, an embodiment of the present invention provides a three-dimensional visualization analysis method for a road traffic event, including:
s1, when a traffic event occurs, acquiring detection data of front-end road side equipment, internet traffic event data and three reported data for fusion;
s2, according to the result of data fusion, associating traffic flow data and congestion conditions of the upstream and downstream intersections, and constructing a three-dimensional event model based on a high-precision map;
and S3, predicting the subsequent influence of the congestion event according to the three-dimensional event model, and generating a new signal control scheme.
Further, the front-end roadside apparatus detection data in the step S1 is: a flow detector, radar traffic flow data, comprising: equipment number, intersection name, intersection position, lane number, lane flow direction, vehicle speed, flow, average time occupancy, average vehicle length, queuing length and event occurrence time;
the internet traffic event data includes: event type, road name, line coordinate, longitude and latitude, authority issue, time picture, event occurrence time, event description and data source;
the three reported data include: the method comprises the following steps of road/intersection, occurrence place, longitude and latitude, event occurrence time, event type, time picture, event detailed description, reporter and event type.
Further, the step of S1 includes:
s11, when a traffic event occurs, de-overlapping and processing the collected front-end roadside device detection data, the Internet traffic event data and the three reported data according to the event occurrence time, the occurrence place and the reporting frequency;
s12, filtering the data after de-coincidence and processing by adopting a limiting condition;
and S13, fusing the filtered data according to a preset rule to generate complete standard structured data.
Further, the limiting conditions in the step S12 include:
(1) selecting data within a preset kilometer range of the radius of the traffic incident occurrence point;
(2) when the event occurrence time detected by the front-end road side equipment exists, selecting data of each data source within x minutes before and after the reference time; when the event occurrence time detected by the front-end road side equipment does not exist, selecting data of each data source within x minutes before and after the event occurrence time in the three reported data is taken as reference time;
(3) and classifying according to the traffic accident, the traffic jam and the traffic violation to determine the event type.
Further, the step of S13 includes:
s131, describing front-end road side equipment detection data, internet traffic event data and three reported data which are included in the filtered data by adopting unified traffic event related parameters; the traffic event related parameters include: the method comprises the following steps of (1) information type, information source, event occurrence road, occurrence road section, occurrence time, specific position, longitude and latitude, detailed description, reporter and reporter telephone;
s132, if any two detection results exist simultaneously and are consistent in the front-end road side equipment detection data, the Internet traffic event data and the three reported data, the result is taken as the standard; the detection result is any field in the related parameters of the traffic incident;
s133, when only two detection results exist in the front-end road side equipment detection data, the internet traffic event data and the three reported data and are inconsistent, performing D-S fusion on the two detection results;
and S134, when the detection results of the front-end road side equipment detection data, the Internet traffic event data and the three reported data are inconsistent, performing D-S fusion.
Further, the step of S2 includes:
s21, establishing a three-dimensional model based on the acquisition and analysis of vector data and picture data according to the result of data fusion;
and S22, correlating traffic flow data and congestion conditions of upstream and downstream intersections, inquiring and counting traffic congestion conditions caused by the same type of traffic event data, analyzing intersection flow, saturation, parking times and queuing length, and constructing a three-dimensional event model based on a high-precision map.
Further, the step of S3 includes:
and generating an improved signal control scheme according to the three-dimensional event model by taking the current period phase difference and the signal period as optimization parameters and taking the average vehicle queuing, the lane length ratio and the system traffic capacity as optimization targets.
In a second aspect, an embodiment of the present invention further provides a three-dimensional visualization analysis system for a road traffic event, including:
the acquisition and fusion module is used for acquiring detection data of front-end road side equipment, Internet traffic event data and three reported data for fusion when a traffic event occurs;
the association building module is used for associating traffic flow data and congestion conditions of the upstream and downstream intersections according to the result of data fusion and building a three-dimensional event model based on a high-precision map;
and the prediction generation module is used for predicting the subsequent influence of the congestion event according to the three-dimensional event model and generating a new signal control scheme.
Compared with the prior art, the invention has the following beneficial effects:
the embodiment of the invention provides a three-dimensional visual analysis method for a road traffic event, which comprises the following steps: when a traffic event occurs, acquiring detection data of front-end road side equipment, internet traffic event data and three reported data for fusion; according to the result of data fusion, correlating traffic flow data and congestion conditions of upstream and downstream intersections, and constructing a three-dimensional event model based on a high-precision map; and predicting the subsequent influence of the congestion event according to the three-dimensional event model, and generating a new signal control scheme. The method restores the traffic condition of the congestion point through a three-dimensional visualization technology, associates the traffic flow and the congestion condition of the upstream and downstream intersections, and constructs a three-dimensional event model on a high-precision map. The traffic situation is predicted by using the model data, the collision of the intersection is monitored and early warned, lane-level flow indexes can be provided for a signal machine, the current intersection signal control scheme is adjusted, and the signal control optimization scheme is sent to a signal control platform, so that the signal control optimization effect of the intersection and a trunk line is realized.
Drawings
Fig. 1 is a flowchart of a three-dimensional visualization analysis method for a road traffic event according to an embodiment of the present invention.
Fig. 2 is a block diagram of a three-dimensional visualization analysis system for a road traffic event according to an embodiment of the present invention.
Detailed Description
In order to make the technical means, the creation characteristics, the achievement purposes and the effects of the invention easy to understand, the invention is further described with the specific embodiments.
In the description of the present invention, it should be noted that the terms "upper", "lower", "inner", "outer", "front", "rear", "both ends", "one end", "the other end", and the like indicate orientations or positional relationships based on those shown in the drawings, and are only for convenience of description and simplicity of description, but do not indicate or imply that the referred device or element must have a specific orientation, be constructed in a specific orientation, and be operated, and thus, should not be construed as limiting the present invention. Furthermore, the terms "first" and "second" are used for descriptive purposes only and are not to be construed as indicating or implying relative importance.
In the description of the present invention, it is to be noted that, unless otherwise explicitly specified or limited, the terms "mounted," "disposed," "connected," and the like are to be construed broadly, such as "connected," which may be fixedly connected, detachably connected, or integrally connected; can be mechanically or electrically connected; they may be connected directly or indirectly through intervening media, or they may be interconnected between two elements. The specific meanings of the above terms in the present invention can be understood in specific cases to those skilled in the art.
Referring to fig. 1, an embodiment of the present invention provides a three-dimensional visualization analysis method for a road traffic event, including:
s1, when a traffic event occurs, acquiring detection data of front-end road side equipment, internet traffic event data and three reported data for fusion;
s2, according to the result of data fusion, associating traffic flow data and congestion conditions of the upstream and downstream intersections, and constructing a three-dimensional event model based on a high-precision map;
and S3, predicting the subsequent influence of the congestion event according to the three-dimensional event model, and generating a new signal control scheme.
The congestion events caused by road traffic in urban traffic are many, including traffic accidents, traffic violations, traffic control and the like. Three traditional stations (110/119/122) report traffic events and front-end video identification, internet events are main sources, and real-time data of the traffic events are acquired by front-end road side equipment microwave/laser radar and videos, so that traffic jam is caused by the emergency events. In the embodiment, the traffic state of the congestion point, such as key indexes of basic vehicle information, lane information, intersection traffic, saturation, parking times, queuing length, space occupancy and the like, is restored through a three-dimensional visualization technology, and then the traffic flow and the congestion condition of the upstream and downstream intersections are associated to construct a three-dimensional event model on the high-precision map. Finally, the traffic situation can be predicted by utilizing the model data, the collision of the early warning intersection is monitored, for example, a lane-level flow index is provided for a signal machine, and a signal control scheme of the current intersection and the related nearby intersections is adjusted, wherein the signal control scheme is used for adjusting the duration time of red light and green light of the intersection; and then sending a signal control optimization scheme to the signal control platform to realize the signal control optimization effect of the intersection and the trunk line.
The above three steps are described in detail below:
in one embodiment, the front end roadside device detection data of step S1 is: a flow detector, radar traffic flow data, comprising: equipment number, intersection name, intersection position, lane number, lane flow direction, vehicle speed, flow, average time occupancy, average vehicle length, queuing length and event occurrence time;
the internet traffic event data includes: event type, road name, line coordinate, longitude and latitude, authority issue, time picture, event occurrence time, event description and data source;
the three reported data include: the method comprises the following steps of road/intersection, occurrence place, longitude and latitude, event occurrence time, event type, time picture, event detailed description, reporter and event type.
The step of S1 includes:
and S11, when a traffic event occurs, carrying out de-coincidence and processing on the acquired front-end road side equipment detection data, the internet traffic event data and the three reported data according to the event occurrence time, the occurrence place and the reporting frequency. In practical situations, after a traffic event often occurs, for example, there may be three reporting situations for multiple times, or there may be an internet traffic event reported for multiple times; therefore, for the same event, if three reporting conditions exist twice, when the occurrence time and the occurrence location information of the two events are consistent, the two events can be combined into one event, and the two pieces of information are integrated to realize de-coincidence and processing.
S12, filtering the data after de-coincidence and processing by adopting a limiting condition; the limiting conditions include: (1) selecting data within a preset kilometer range of a traffic incident occurrence point radius; selecting the following conditions by taking the distance as a condition: for example, only data fusion is carried out within the range of 0-1.5 kilometers of the radius of the occurrence point of the traffic incident, and the incident beyond the distance is not processed;
(2) when the event occurrence time detected by the front-end road side equipment exists, selecting data of each data source within x minutes before and after the reference time; when the event occurrence time detected by the front-end road side equipment does not exist, selecting data of each data source within x minutes before and after the event occurrence time in the three reported data is taken as reference time;
selecting the following components by taking time as a condition: for example, if there is an event occurrence time detected by the front-end road side equipment, the data reported by each data source is fused within 5 minutes before and after the reference time; if the event occurrence time detected by the front-end road side equipment does not exist, fusing within 5 minutes before and after the reference time of the three reported data;
(3) event type: and classifying according to traffic accidents, traffic jams and traffic violations.
And S13, fusing the filtered data according to a preset rule to generate complete standard structured data.
And (3) fusion process: event data reported for multiple times are subjected to de-duplication and combination according to time, place and reporting frequency, event description and picture analysis are carried out according to the radius of an event occurrence position, such as within the range of 1.5 kilometers, event judgment is carried out by combining peripheral monitoring videos, and complete standard structured data are generated;
the step S13 includes:
s131, describing front-end road side equipment detection data, internet traffic event data and three reported data which are included in the filtered data by adopting unified traffic event related parameters; the traffic event related parameters include: the method comprises the steps of information type, information source, event occurrence road, occurrence road section, occurrence time, specific position, longitude and latitude, detailed description, reporter and reporter telephone. Taking the specific position field as an example, the front-end roadside device detects the device number, the intersection name and the intersection position in the data, and the specific position can be obtained according to the field such as the position of the device number, the intersection name and the intersection position; the concrete position can be obtained through fields such as road names, line coordinates, longitude and latitude and the like in the internet traffic event data; the concrete positions can be obtained by fields of roads/intersections, places of occurrence, longitude and latitude and the like in the three reported data. Namely: the data of three different data sources are described according to a uniform format.
S132, if any two detection results exist simultaneously and are consistent, the result is taken as the standard in the detection data of the road side equipment at the current end, the Internet traffic event data and the three reported data; the detection result refers to any field in the related parameters of the traffic incident; taking the section of the occurrence section as an example: the occurrence road section described by the detection data of the road side equipment at the front end is as follows: the road sections of the vintage road and the internet traffic incident data are also as follows: when the road is a Changchun road, the 'occurring road section is the Changchun road' is accurate information.
S133, only two detection results exist in the current roadside device detection data, the internet traffic event data and the three reported data, and if the two detection results are inconsistent, D-S fusion is carried out on the two detection results;
and S134, if the detection results of the current-side road side equipment detection data, the Internet traffic event data and the three reported data are inconsistent, performing D-S fusion.
When the three data sources are described according to a uniform format, only one type of information exists in a certain field, and the method is based on the principle, and when two or three types of different information exist, D-S fusion is adopted, and the information with high selection possibility is based on the principle.
The multi-criterion fusion algorithm applying the D-S evidence theory is as follows:
1. recognizing the frame:
assuming that a problem needing to be judged exists at present, solving the problem, and representing a complete set formed by all the possible results which can be recognized by theta by using theta, wherein all elements in theta have mutual exclusion relations, and the number of the elements is limited and enumerable; at any one time, the answer value of the question can only be an element in Θ, and a set Θ composed of such incompatible events is called an identification framework, which can be expressed as:
wherein the content of the first and second substances,
an event or element called the recognition framework Θ;
to identify the nth event or element of the framework Θ. Next, the concept of power set is introduced, i.e. a set of all subsets of the framework Θ is identified, denoted 2ΘThe power set can be expressed as:
in the recognition framework Θ, any subset a thereof corresponds to a proposition of an answer to a question, which can be said to be "a is an answer to a question".
2. After the recognition framework is determined, evidence information needs to be established, namely, a probability distribution problem corresponding to the proposition set. Generally, for a proposition, after the information is comprehensively analyzed, a more appropriate decision can be made, a specific number can be put forward, the support degree of a certain proposition can be reasonably described, and the number represents the trust degree given to the proposition. Thus, initial distribution of basic trust values of propositions in the identification framework is established, and the evidence theory systematically summarizes distribution results finally determined by all propositions by using a basic trust distribution function.
Let Θ be an identification framework, and the basic trust distribution function m on the identification framework Θ is a mapping of 2 Θ → [0, 1], and the function satisfies the following condition:
m (A) embodies the support degree of the evidence for proposition A, and the value of the support degree is the basic trust assignment value of the proposition. The basic trust value of the empty set is zero and the sum of the trust values of all other subsets is equal to 1. If the value of m (A) is greater than 0, then A may be referred to as a focal element.
3. Then applying DS evidence theory to carry out fusion calculation,
for the synthesis of multiple evidences, multiple m1,m2,…, mnThe function can also be processed using an orthogonal sum to generate a new m-function, which can be expressed as m1⨁m2⨁…⨁mn. If m1⨁m2⨁…⨁mnIf the sequences exist, the sequences have no influence on the result in the calculation process, and the exchange rate and the combination rate are satisfied.
Given the same recognition framework Θ, there are n sets of evidence E1,E2,…, En，m1,m2,…, mnDistributing functions for the corresponding basic trusts, wherein the focal elements are respectively A1,A2,…, AnThen the Dempster synthesis rule is:
wherein the content of the first and second substances,Kis a normalization constant.
Calculation example:
synthetic calculation of evidence using D-S evidence theory
Evidence E1、E2、E3The corresponding basic trust distribution functions are m1、m2、m3
At E1M under evidence1(A1)=0.6, m1(A2)=0.2, m1(A3)=0.2
At E2M under evidence2(A1)=0.4 ，m2(A2)=0.5, m2(A3)=0.1
At E3M under evidence3(A1)=0.1 ，m3(A2)=0.2, m3(A3)=0.7
(1) Firstly, the normalization coefficient K is calculated
K= m1(A1)* m2(A1)* m3(A1)+ m1(A2)* m2(A2)* m3(A2)+ m1(A3)* m2(A3)* m3(A3)=0.058
(2) Calculation Using Dempster Synthesis rule
m(A1)=1/K*( m1(A1)* m2(A1)* m3(A1))=0.6*0.4*0.1/0.058=0.413
m(A2)=1/K*( m1(A2)* m2(A2)* m3(A2))=0.02/0.058=0.345
m(A3)=1/K*( m1(A3)* m2(A3)* m3(A3))=0.014/0.058=0.241
So the final data is the front-end detection data result: incident occurrence road A1。
In one embodiment, the step of S2 includes:
s21, establishing a three-dimensional model based on the acquisition and analysis of vector data and picture data according to the result of data fusion;
and S22, correlating traffic flow data and congestion conditions of upstream and downstream intersections, inquiring and counting traffic congestion conditions caused by the same type of traffic event data, analyzing intersection flow, saturation, parking times and queuing length, and constructing a three-dimensional event model based on a high-precision map.
The step of S3 includes:
and generating an improved signal control scheme according to the three-dimensional event model by taking the current period phase difference and the signal period as optimization parameters and taking the average vehicle queuing, the lane length ratio and the system traffic capacity as optimization targets.
In this embodiment, in steps S2 and S3, the full-element restoration is performed on the high-precision map according to the fusion data, an independent traffic event algorithm model is established without being affected by severe weather, the subsequent impact of the occurrence of the congestion event is predicted, and a new signaling control scheme is generated according to the prediction and is issued to the signaling machine.
The specific process is as follows:
(1) manual annotation of map data, import of an attribute database and cross-platform recovery of the database. The map data manual marking means that in the geographic information GIS software of map making software, a high-resolution orthographic image is taken as a map layer, and data required by a map, such as roads, lane lines and the like, are marked in a manual mode; the attribute database import refers to a process of importing data into a database for storage and maintenance after manual data annotation is completed;
(2) establishing a full-automatic signal timing scheme combining microcosmic traffic environment construction and signal optimization, firstly combining urban traffic and grid map characteristics, realizing automatic extraction of a trunk network by utilizing an image processing technology, constructing a microcosmic traffic simulation environment, then adding a longitude and latitude position of a vehicle, modeling dynamic behaviors of urban traffic vehicles by restoring the processes of vehicle traveling and lane changing, and predicting values of subsequent traveling routes and traffic flow of the vehicles;
(3) and finally, providing an improved signal optimization scheme taking the phase difference and the signal period of the current period as optimization parameters and taking average queuing of vehicles, the lane length ratio and the system traffic capacity as optimization targets.
According to the three-dimensional visualization analysis method for the road traffic event, provided by the embodiment of the invention, aiming at the traffic jam caused by the urban road traffic event, the front-end equipment information, the basic vehicle information, the traffic flow information and the current signal control scheme are collected, and a three-dimensional visualization tool is utilized to carry out modeling analysis on the jam cause and the subsequent traffic delay condition. And obtaining a signal control optimization scheme of the intersection according to the calculation modeling data, and providing the signal control optimization scheme for the signal control platform to adjust, so that the signal control schemes of the event intersection and the upstream and downstream intersections are adjusted according to the set traffic signal control plan, and the effect of reducing congestion is achieved.
Based on the same inventive concept, the embodiment of the invention also provides a three-dimensional visual analysis system for the road traffic incident, and as the principle of the problem solved by the system is similar to that of the three-dimensional visual analysis method for the road traffic incident, the implementation of the system can refer to the implementation of the method, and repeated parts are not repeated.
A three-dimensional visualization analysis system for road traffic events, as shown in fig. 2, includes:
the acquisition and fusion module is used for acquiring detection data of front-end road side equipment, Internet traffic event data and three reported data for fusion when a traffic event occurs;
the association building module is used for associating traffic flow data and congestion conditions of the upstream and downstream intersections according to the result of data fusion and building a three-dimensional event model based on a high-precision map;
and the prediction generation module is used for predicting the subsequent influence of the congestion event according to the three-dimensional event model and generating a new signal control scheme. And generating an improved signal control scheme according to the three-dimensional event model by taking the current period phase difference and the signal period as optimization parameters and taking the average vehicle queuing, the lane length ratio and the system traffic capacity as optimization targets.
Further, wherein, the front-end roadside device detection data in the collection and fusion module is: a flow detector, radar traffic flow data, comprising: equipment number, intersection name, intersection position, lane number, lane flow direction, vehicle speed, flow, average time occupancy, average vehicle length, queuing length and event occurrence time;
the internet traffic event data includes: event type, road name, line coordinate, longitude and latitude, authority issue, time picture, event occurrence time, event description and data source;
the three reported data include: the method comprises the following steps of road/intersection, occurrence place, longitude and latitude, event occurrence time, event type, time picture, event detailed description, reporter and event type.
Further, the acquisition fusion module specifically includes:
the de-coincidence unit is used for de-coincidence and processing the acquired front-end roadside device detection data, the internet traffic event data and the three reported data according to the event occurrence time, the occurrence place and the reporting frequency when a traffic event occurs;
the filtering unit is used for filtering the data subjected to de-coincidence and processing by adopting a limiting condition; the limiting conditions include: (1) selecting data within a preset kilometer range of the radius of the traffic incident occurrence point;
(2) when the event occurrence time detected by the front-end road side equipment exists, selecting data of each data source within x minutes before and after the reference time; when the event occurrence time detected by the front-end road side equipment does not exist, selecting data of each data source within x minutes before and after the event occurrence time in the three reported data is taken as reference time;
(3) and classifying according to the traffic accident, the traffic jam and the traffic violation to determine the event type.
And the generating unit is used for fusing the filtered data according to a preset rule to generate complete standard structured data. In particular for:
describing front-end road side equipment detection data, internet traffic event data and three reported data which are included in the filtered data by adopting unified traffic event related parameters; the traffic event related parameters include: the method comprises the following steps of (1) information type, information source, event occurrence road, occurrence road section, occurrence time, specific position, longitude and latitude, detailed description, reporter and reporter telephone;
when any two detection results exist simultaneously and are consistent in the front-end road side equipment detection data, the internet traffic event data and the three reported data, the result is taken as the standard; the detection result is any field in the related parameters of the traffic incident;
when only two detection results exist in the front-end roadside device detection data, the internet traffic event data and the three reported data and are inconsistent, performing D-S fusion on the two detection results;
and when the detection results of the front-end road side equipment detection data, the internet traffic event data and the three reported data are inconsistent, performing D-S fusion.
Further, the association building module comprises:
the establishing unit is used for establishing a three-dimensional model based on the acquisition and analysis of vector data and picture data according to the result of data fusion;
the construction unit is used for correlating traffic flow data and congestion conditions of upstream and downstream intersections, inquiring and counting traffic congestion conditions caused by the same type of traffic event data, analyzing intersection flow, saturation, parking times and queuing length, and constructing a three-dimensional event model based on a high-precision map.
The foregoing shows and describes the general principles and broad features of the present invention and advantages thereof. It will be understood by those skilled in the art that the present invention is not limited to the embodiments described above, which are given by way of illustration of the principles of the present invention, and that various changes and modifications may be made without departing from the scope of the invention as claimed. The scope of the invention is defined by the appended claims and equivalents thereof.
Claims (8)
1. A three-dimensional visual analysis method for road traffic events is characterized by comprising the following steps:
s1, when a traffic event occurs, acquiring detection data of front-end road side equipment, internet traffic event data and three reported data for fusion;
s2, according to the result of data fusion, associating traffic flow data and congestion conditions of the upstream and downstream intersections, and constructing a three-dimensional event model based on a high-precision map;
and S3, predicting the subsequent influence of the congestion event according to the three-dimensional event model, and generating a new signal control scheme.
2. The three-dimensional visualization analysis method for road traffic events according to claim 1, wherein the front-end roadside device detection data in the step of S1 is: a flow detector, radar traffic flow data, comprising: equipment number, intersection name, intersection position, lane number, lane flow direction, vehicle speed, flow, average time occupancy, average vehicle length, queuing length and event occurrence time;
the internet traffic event data includes: event type, road name, line coordinate, longitude and latitude, authority issue, time picture, event occurrence time, event description and data source;
the three reported data include: the method comprises the following steps of road/intersection, occurrence place, longitude and latitude, event occurrence time, event type, time picture, event detailed description, reporter and event type.
3. The three-dimensional visualization analysis method for road traffic events according to claim 2, wherein the step of S1 comprises:
s11, when a traffic event occurs, de-overlapping and processing the collected front-end roadside device detection data, the Internet traffic event data and the three reported data according to the event occurrence time, the occurrence place and the reporting frequency;
s12, filtering the data after de-coincidence and processing by adopting a limiting condition;
and S13, fusing the filtered data according to a preset rule to generate complete standard structured data.
4. The three-dimensional visualization analysis method for road traffic events according to claim 3, wherein the limiting conditions in the step S12 include:
(1) selecting data within a preset kilometer range of the radius of the traffic incident occurrence point;
(2) when the event occurrence time detected by the front-end road side equipment exists, selecting data of each data source within x minutes before and after the reference time; when the event occurrence time detected by the front-end road side equipment does not exist, selecting data of each data source within x minutes before and after the event occurrence time in the three reported data is taken as reference time;
(3) and classifying according to the traffic accident, the traffic jam and the traffic violation to determine the event type.
5. The three-dimensional visualization analysis method for road traffic events according to claim 4, wherein the step of S13 comprises:
s131, describing front-end road side equipment detection data, internet traffic event data and three reported data which are included in the filtered data by adopting unified traffic event related parameters; the traffic event related parameters include: the method comprises the following steps of (1) information type, information source, event occurrence road, occurrence road section, occurrence time, specific position, longitude and latitude, detailed description, reporter and reporter telephone;
s132, if any two detection results exist simultaneously and are consistent in the front-end road side equipment detection data, the Internet traffic event data and the three reported data, the result is taken as the standard; the detection result is any field in the related parameters of the traffic incident;
s133, when only two detection results exist in the front-end road side equipment detection data, the internet traffic event data and the three reported data and are inconsistent, performing D-S fusion on the two detection results;
and S134, when the detection results of the front-end road side equipment detection data, the Internet traffic event data and the three reported data are inconsistent, performing D-S fusion.
6. The three-dimensional visualization analysis method for road traffic events according to claim 5, wherein the step of S2 comprises:
s21, establishing a three-dimensional model based on the acquisition and analysis of vector data and picture data according to the result of data fusion;
and S22, correlating traffic flow data and congestion conditions of upstream and downstream intersections, inquiring and counting traffic congestion conditions caused by the same type of traffic event data, analyzing intersection flow, saturation, parking times and queuing length, and constructing a three-dimensional event model based on a high-precision map.
7. The three-dimensional visualization analysis method for road traffic events according to claim 6, wherein the step of S3 comprises:
and generating an improved signal control scheme according to the three-dimensional event model by taking the current period phase difference and the signal period as optimization parameters and taking the average vehicle queuing, the lane length ratio and the system traffic capacity as optimization targets.
8. A three-dimensional visual analysis system for road traffic events, comprising:
the acquisition and fusion module is used for acquiring detection data of front-end road side equipment, Internet traffic event data and three reported data for fusion when a traffic event occurs;
the association building module is used for associating traffic flow data and congestion conditions of the upstream and downstream intersections according to the result of data fusion and building a three-dimensional event model based on a high-precision map;
and the prediction generation module is used for predicting the subsequent influence of the congestion event according to the three-dimensional event model and generating a new signal control scheme.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202111296981.5A CN113724499A (en) | 2021-11-01 | 2021-11-01 | Three-dimensional visual analysis method and system for road traffic events |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202111296981.5A CN113724499A (en) | 2021-11-01 | 2021-11-01 | Three-dimensional visual analysis method and system for road traffic events |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN113724499A true CN113724499A (en) | 2021-11-30 |
Family
ID=78686708
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202111296981.5A Pending CN113724499A (en) | 2021-11-01 | 2021-11-01 | Three-dimensional visual analysis method and system for road traffic events |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN113724499A (en) |
Cited By (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN114363316A (en) * | 2022-01-28 | 2022-04-15 | 交通运输部路网监测与应急处置中心 | Intelligent networking monitoring and supervision system for cross-regional road infrastructure |
| CN115290146A (en) * | 2022-10-09 | 2022-11-04 | 承德华文水利工程有限公司 | Remote online monitoring method for water resource monitoring |
Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN103092924A (en) * | 2012-12-28 | 2013-05-08 | 深圳先进技术研究院 | Real-time data driven traffic data three-dimensional visualized analysis system and method |
| US20130151135A1 (en) * | 2010-11-15 | 2013-06-13 | Image Sensing Systems, Inc. | Hybrid traffic system and associated method |
| CN104103176A (en) * | 2013-04-15 | 2014-10-15 | 杭州斯玛特维科技有限公司 | Adaptive traffic state estimation method |
| CN113178069A (en) * | 2021-04-20 | 2021-07-27 | 宁波德尔菲信息科技有限公司 | Traffic early warning system based on big data machine learning technology |
| CN113409593A (en) * | 2021-06-25 | 2021-09-17 | 阿波罗智联(北京)科技有限公司 | Traffic signal lamp control signal generation method and device, electronic equipment and medium |
-
2021
- 2021-11-01 CN CN202111296981.5A patent/CN113724499A/en active Pending
Patent Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20130151135A1 (en) * | 2010-11-15 | 2013-06-13 | Image Sensing Systems, Inc. | Hybrid traffic system and associated method |
| CN103092924A (en) * | 2012-12-28 | 2013-05-08 | 深圳先进技术研究院 | Real-time data driven traffic data three-dimensional visualized analysis system and method |
| CN104103176A (en) * | 2013-04-15 | 2014-10-15 | 杭州斯玛特维科技有限公司 | Adaptive traffic state estimation method |
| CN113178069A (en) * | 2021-04-20 | 2021-07-27 | 宁波德尔菲信息科技有限公司 | Traffic early warning system based on big data machine learning technology |
| CN113409593A (en) * | 2021-06-25 | 2021-09-17 | 阿波罗智联(北京)科技有限公司 | Traffic signal lamp control signal generation method and device, electronic equipment and medium |
Cited By (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN114363316A (en) * | 2022-01-28 | 2022-04-15 | 交通运输部路网监测与应急处置中心 | Intelligent networking monitoring and supervision system for cross-regional road infrastructure |
| CN115290146A (en) * | 2022-10-09 | 2022-11-04 | 承德华文水利工程有限公司 | Remote online monitoring method for water resource monitoring |
| CN115290146B (en) * | 2022-10-09 | 2022-12-06 | 承德华文水利工程有限公司 | Remote online monitoring method for water resource monitoring |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN111524357B (en) | Method for fusing multiple data required for safe driving of vehicle | |
| D'Andrea et al. | Detection of traffic congestion and incidents from GPS trace analysis | |
| JP7371157B2 (en) | Vehicle monitoring method, device, electronic device, storage medium, computer program, cloud control platform and roadway coordination system | |
| CN104200659B (en) | Whether a kind of emphasis vehicle is by the decision method of regulation link travel | |
| CN113724499A (en) | Three-dimensional visual analysis method and system for road traffic events | |
| TWI649729B (en) | System and method for automatically proving traffic violation vehicles | |
| CN113259900B (en) | Distributed multi-source heterogeneous traffic data fusion method and device | |
| CN115547084A (en) | Road traffic condition prediction method and device, electronic equipment and computer program product | |
| CN115762120A (en) | Holographic sensing early warning system based on whole highway section | |
| Fyfe | Safety evaluation of connected vehicle applications using micro-simulation | |
| Bock et al. | What are the potentialities of crowdsourcing for dynamic maps of on-street parking spaces? | |
| CN109658693B (en) | Road condition information acquisition and processing method and device | |
| Robinson | The development and application of an urban link travel time model using data derived from inductive loop detectors | |
| Kim | Assessment of vehicle-to-vehicle communication based applications in an urban network | |
| Yang et al. | Road hazard assessment using pothole and traffic data in South Korea | |
| CN117058872A (en) | Method, system and storage medium for publishing information on expressway | |
| Imani | The use of real-time connected vehicles and HERE data in developing an automated freeway incident detection algorithm | |
| Chepuri et al. | Examining performance of an urban corridor using microscopic traffic simulation model under mixed traffic environment in India | |
| KR102400842B1 (en) | Service methods for providing information on traffic accidents | |
| Kim | Simultaneous calibration of a microscopic traffic simulation model and OD matrix | |
| CN114519500A (en) | Method, device and equipment for determining road safety risk level and storage medium | |
| Soloka | Simulation Exploration of the Potential of Connected Vehicles in Mitigating Secondary Crashes | |
| Carlson et al. | Safety in numbers: Pedestrian and bicyclist activity and safety in Minneapolis | |
| Oskarbski et al. | Possible directions for development of C-ITS services in cities on the example of the TRISTAR System | |
| Pinal | Crash Rate as a Function of Access Point Density and Traffic Flow |
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 |