CN112382097A - Urban road supervision method and system based on dynamic traffic flow and readable storage medium - Google Patents
Urban road supervision method and system based on dynamic traffic flow and readable storage medium Download PDFInfo
- Publication number
- CN112382097A CN112382097A CN202011364609.9A CN202011364609A CN112382097A CN 112382097 A CN112382097 A CN 112382097A CN 202011364609 A CN202011364609 A CN 202011364609A CN 112382097 A CN112382097 A CN 112382097A
- Authority
- CN
- China
- Prior art keywords
- information
- traffic
- road
- traffic flow
- congestion
- 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.)
- Withdrawn
Links
Images
Classifications
-
- G—PHYSICS
- G08—SIGNALLING
- G08G—TRAFFIC CONTROL SYSTEMS
- G08G1/00—Traffic control systems for road vehicles
- G08G1/01—Detecting movement of traffic to be counted or controlled
- G08G1/0104—Measuring and analyzing of parameters relative to traffic conditions
- G08G1/0108—Measuring and analyzing of parameters relative to traffic conditions based on the source of data
- G08G1/012—Measuring and analyzing of parameters relative to traffic conditions based on the source of data from other sources than vehicle or roadside beacons, e.g. mobile networks
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01C—MEASURING DISTANCES, LEVELS OR BEARINGS; SURVEYING; NAVIGATION; GYROSCOPIC INSTRUMENTS; PHOTOGRAMMETRY OR VIDEOGRAMMETRY
- G01C21/00—Navigation; Navigational instruments not provided for in groups G01C1/00 - G01C19/00
- G01C21/26—Navigation; Navigational instruments not provided for in groups G01C1/00 - G01C19/00 specially adapted for navigation in a road network
- G01C21/34—Route searching; Route guidance
- G01C21/3407—Route searching; Route guidance specially adapted for specific applications
- G01C21/3415—Dynamic re-routing, e.g. recalculating the route when the user deviates from calculated route or after detecting real-time traffic data or accidents
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/24—Classification techniques
- G06F18/241—Classification techniques relating to the classification model, e.g. parametric or non-parametric approaches
- G06F18/2413—Classification techniques relating to the classification model, e.g. parametric or non-parametric approaches based on distances to training or reference patterns
- G06F18/24133—Distances to prototypes
- G06F18/24137—Distances to cluster centroïds
- G06F18/2414—Smoothing the distance, e.g. radial basis function networks [RBFN]
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V10/00—Arrangements for image or video recognition or understanding
- G06V10/20—Image preprocessing
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V20/00—Scenes; Scene-specific elements
- G06V20/10—Terrestrial scenes
- G06V20/13—Satellite images
-
- 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
- G08G1/0133—Traffic data processing for classifying traffic situation
-
- 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
Abstract
The invention relates to a method, a system and a readable storage medium for supervising an urban road based on dynamic traffic flow, wherein the method comprises the following steps: collecting traffic image information through an aerial photography unmanned aerial vehicle, and preprocessing the image information to obtain traffic flow data; extracting traffic flow data vector characteristics, and identifying the traffic event category by using a network model; and generating guidance information according to the traffic incident categories, guiding the vehicle path in real time through the guidance information, and transmitting result information to the platform.
Description
Technical Field
The invention relates to an urban road supervision method, in particular to an urban road supervision method and system based on dynamic traffic flow and a readable storage medium.
Background
The handling and treatment of traffic jam are always the focus areas of attention of all the circles in the world. Intersection signal control and route guidance are becoming more and more widely used as important components in intelligent traffic systems in increasingly severe traffic environments. However, while hardware facilities are rapidly developed and improved, the problem of low intelligentization degree of a traffic management system still exists, and a traffic management department faces the problems of acquiring hidden intrinsic information from mass traffic flow data, particularly data with non-repetitive characteristics generated by sudden traffic congestion, making full use of information advantages to formulate a scientific dredging strategy and the like. Therefore, on the basis of massive traffic data, dynamic traffic flow information processing and congestion control and induction strategy research is developed, and the method has important significance for relieving urban traffic congestion.
In order to realize accurate control to urban road supervision, a section needs to be developed to control with a system matched with the section, the system acquires traffic image information through an aerial unmanned aerial vehicle, traffic flow data is obtained, a network model is utilized to identify traffic incident categories, induction information is generated according to the traffic incident categories, and vehicle paths are guided in real time, but in the control process, when accurate control is realized, the problem that the road accurate dynamic supervision is urgent to solve is solved.
Disclosure of Invention
The invention overcomes the defects of the prior art and provides a dynamic traffic flow-based urban road supervision method, a dynamic traffic flow-based urban road supervision system and a readable storage medium.
In order to achieve the purpose, the invention adopts the technical scheme that: an urban road supervision method based on dynamic traffic flow comprises the following steps:
collecting traffic image information through an aerial photography unmanned aerial vehicle, and preprocessing the image information to obtain traffic flow data;
extracting traffic flow data vector characteristics, and identifying the traffic event category by using a network model;
generating the inducement information according to the traffic event category,
and guiding the vehicle path in real time through the guidance information, and transmitting result information to the platform.
In a preferred embodiment of the present invention, acquiring traffic image information by an aerial photography unmanned aerial vehicle, and preprocessing the image information to obtain traffic flow data specifically includes:
acquiring traffic image information, performing marginalization processing on the image information,
extracting the path dividing line and the path track in the image information to generate road network information,
comparing the road network information with the actual traffic path information to obtain the unmanned aerial vehicle aerial photography attitude angle,
judging whether the aerial photography attitude angle of the unmanned aerial vehicle is larger than a preset aerial photography attitude angle or not,
if the value is larger than the preset value, generating compensation information, adjusting the aerial photography attitude angle of the unmanned aerial vehicle according to the compensation information,
and shooting the traffic image information again through the unmanned aerial vehicle, and generating traffic flow data.
In a preferred embodiment of the present invention, the method for pre-processing the traffic image information by collecting the traffic image information through the aerial photography unmanned aerial vehicle further comprises:
carrying out thresholding on the traffic image, wherein the non-lane line area is processed into black, and the lane line area is processed into white;
removing image noise points by a local minimum method, and performing compensation processing on a white area by a local maximum method;
setting the elimination width, carrying out fixed width processing on the white area, establishing polar angle constraint conditions according to the polar angle characteristics of the lane lines,
and generating compensation information according to the polar angle constraint condition, and adjusting the aerial photography attitude angle of the unmanned aerial vehicle according to the compensation information.
In a preferred embodiment of the present invention, the traffic flow data vector features are extracted, and the traffic event category is identified by using a network model, specifically:
constructing a traffic flow prediction model by utilizing a deep learning algorithm, and carrying out classification training on traffic flow data;
solving traffic jam information and road condition states by adopting an optimization algorithm;
carrying out shortest path optimization according to the traffic congestion information and carrying out alternative path search;
the unmanned aerial vehicle node acquires the alternative path and carries out simulated flight along the alternative path to obtain road condition information of the alternative path;
acquiring the adjustment information according to the road condition information of the alternative path,
the alternative path is adjusted in real time through the adjustment information to obtain result information,
and transmitting the result information to the platform.
In a preferred embodiment of the present invention, the generating of the guidance information according to the traffic event category comprises:
acquiring traffic flow information, identifying an emergent congestion road section caused by an emergent event, and generating congestion information;
comparing the congestion information with a congestion judging threshold value, and judging congestion degree and congestion level;
dividing the jammed road section into a plurality of running road sections with equal distances, and searching a vehicle set on all the running road sections and allowing the original route to pass through the running road sections;
selecting a route according to the probability distribution to generate a new planned route,
the new planned route is recursively assigned to selected vehicles within the vehicle collection and the road network information is updated.
In a preferred embodiment of the present invention, the traffic event category includes one or more of road congestion, traffic accident, road construction, road closure, and road weather anomaly;
the road congestion comprises periodic congestion or aperiodic congestion, and the periodic congestion comprises congestion which often occurs at a road intersection or a road section within a preset time period; the aperiodic congestion includes congestion caused by random or unexpected conditions.
The second aspect of the present invention also provides an urban road supervision system based on dynamic traffic flow, the system comprising: the dynamic traffic flow-based urban road supervision method comprises a memory and a processor, wherein the memory comprises a dynamic traffic flow-based urban road supervision method program, and when the dynamic traffic flow-based urban road supervision method program is executed by the processor, the following steps are realized:
collecting traffic image information through an aerial photography unmanned aerial vehicle, and preprocessing the image information to obtain traffic flow data;
extracting traffic flow data vector characteristics, and identifying the traffic event category by using a network model;
generating the inducement information according to the traffic event category,
and guiding the vehicle path in real time through the guidance information, and transmitting result information to the platform.
In a preferred embodiment of the present invention, acquiring traffic image information by an aerial photography unmanned aerial vehicle, and preprocessing the image information to obtain traffic flow data specifically includes:
acquiring traffic image information, performing marginalization processing on the image information,
extracting the path dividing line and the path track in the image information to generate road network information,
comparing the road network information with the actual traffic path information to obtain the unmanned aerial vehicle aerial photography attitude angle,
judging whether the aerial photography attitude angle of the unmanned aerial vehicle is larger than a preset aerial photography attitude angle or not,
if the value is larger than the preset value, generating compensation information, adjusting the aerial photography attitude angle of the unmanned aerial vehicle according to the compensation information,
and shooting the traffic image information again through the unmanned aerial vehicle, and generating traffic flow data.
In a preferred embodiment of the present invention, the generating of the guidance information according to the traffic event category comprises:
acquiring traffic flow information, identifying an emergent congestion road section caused by an emergent event, and generating congestion information;
comparing the congestion information with a congestion judging threshold value, and judging congestion degree and congestion level;
dividing the jammed road section into a plurality of running road sections with equal distances, and searching a vehicle set on all the running road sections and allowing the original route to pass through the running road sections;
selecting a route according to the probability distribution to generate a new planned route,
the new planned route is recursively assigned to selected vehicles within the vehicle collection and the road network information is updated.
The third aspect of the present invention provides a computer-readable storage medium, where the computer-readable storage medium includes a dynamic traffic flow-based urban road supervision method program, and when the dynamic traffic flow-based urban road supervision method program is executed by a processor, the steps of the dynamic traffic flow-based urban road supervision method described in any one of the above are implemented.
The invention solves the defects in the background technology, and has the following beneficial effects:
(1) the method comprises the steps of aerial photographing road image information through the unmanned aerial vehicle, acquiring traffic flow data in real time, automatically identifying traffic event categories according to a model, making corresponding decisions according to different traffic event categories, and carrying out real-time picture transmission on a congested area by an unmanned aerial vehicle node to realize real-time monitoring of urban roads.
(2) The traffic event type generates induction information, the vehicle path is guided in real time through the induction information, the vehicle is ensured to be in the optimal path, due to the fact that the traffic event type has the possibility of instantaneous occurrence, the platform automatically searches for alternative paths while the optimal path is driven, then the unmanned aerial vehicle node conducts simulated flight along the alternative paths, real-time pictures are transmitted to the platform, traffic flow information of the alternative paths is analyzed, the alternative paths are adjusted in real time, and traffic efficiency of the alternative paths is ensured.
(3) When a traffic accident or casualties of people occur on a road, the number of the optimal unmanned aerial vehicle nodes is selected according to the standby state of the unmanned aerial vehicles in the nearby area to fly to a preset area, the unmanned aerial vehicle nodes are matched and jointly photographed by adjusting the aerial photographing attitude angles of the unmanned aerial vehicle nodes, the on-site pictures transmitted by the unmanned aerial vehicle nodes are clear, and the unmanned aerial vehicle nodes are interconnected with a hospital to remotely guide temporary self-rescue service.
Drawings
The invention is further illustrated with reference to the following figures and examples.
FIG. 1 is a flow chart illustrating a dynamic traffic flow based urban road supervision method according to the present invention;
FIG. 2 illustrates a flow chart of a method of obtaining traffic flow data;
FIG. 3 shows a flow chart of an image pre-processing method;
FIG. 4 illustrates a flow chart of a method of identifying a traffic event;
FIG. 5 is a flow chart of a method for updating road network information;
FIG. 6 shows a block diagram of an urban road supervision system based on dynamic traffic flow;
Detailed Description
In order that the above objects, features and advantages of the present invention can be more clearly understood, a more particular description of the invention will be rendered by reference to the appended drawings. It should be noted that the embodiments and features of the embodiments of the present application may be combined with each other without conflict.
In the following description, numerous specific details are set forth in order to provide a thorough understanding of the present invention, however, the present invention may be practiced in other ways than those specifically described herein, and therefore the scope of the present invention is not limited by the specific embodiments disclosed below.
Fig. 1 shows a flow chart of an urban road supervision method based on dynamic traffic flow according to the invention.
As shown in fig. 1, a first aspect of the present invention provides a dynamic traffic flow-based urban road supervision method, including:
s102, collecting traffic image information through an aerial photography unmanned aerial vehicle, and preprocessing the image information to obtain traffic flow data;
s104, extracting traffic flow data vector characteristics, and identifying the traffic event category by using a network model;
s106, generating induction information according to the traffic incident category,
and S108, guiding the vehicle path in real time through the guidance information, and transmitting the result information to the platform.
It should be noted that various indexes reflecting traffic flow states include traffic volume, average speed of vehicles, and lane occupancy, it should be noted that the traffic volume and the average speed of vehicles and the lane occupancy are in a nonlinear correlation relationship, and the dynamic traffic flow parameters have obvious characteristics of space-time data, and the space-time autocorrelation is the most core and essential characteristic thereof and is used for describing intrinsic attributes in a time domain and a space domain. The spatio-temporal autocorrelation can be divided into temporal autocorrelation and spatial autocorrelation, and a time sequence generally has a characteristic that values are correlated at adjacent times (or in a time period), that is, temporal autocorrelation. The traffic flow parameter data such as traffic volume, vehicle average speed, lane occupancy rate and the like have time autocorrelation attribute, namely, correlation exists at adjacent time (or in time period), and the autocorrelation coefficient is
Wherein, λ represents the time autocorrelation coefficient, n is the time delay period number, and T is the total number of the sampling time points; x is the number oftFor the value of the study attribute at time t, xt+nValue of study attribute, x, at time t + nt+2nFor the value of the study attribute at time t +2n,
the average value of all research attribute values in T moments; the value range of the autocorrelation coefficient is in the range of [ -1,1 [)]Within, a closer to 1 indicates a higher degree of autocorrelation of the time series.
As shown in FIG. 2, the present invention discloses a flow chart of a method for obtaining traffic flow data;
according to the embodiment of the invention, traffic image information is acquired by an aerial photography unmanned aerial vehicle, and the image information is preprocessed to obtain traffic flow data, which specifically comprises the following steps:
s202, acquiring traffic image information, performing marginalization processing on the image information,
s204, extracting the path dividing line and the path track in the image information to generate road network information,
s206, comparing the road network information with the actual traffic path information to obtain an unmanned aerial vehicle aerial photography attitude angle,
s208, judging whether the aerial photography attitude angle of the unmanned aerial vehicle is larger than a preset aerial photography attitude angle,
s210, if the angle is larger than the preset value, generating compensation information, adjusting the unmanned aerial vehicle aerial photography attitude angle according to the compensation information,
and S212, shooting the traffic image information again through the unmanned aerial vehicle, and generating traffic flow data.
The method includes the steps that road image information is aerial photographed by an unmanned aerial vehicle, traffic flow data are obtained in real time, traffic event categories are automatically identified according to models, corresponding decisions are made according to different traffic event categories, real-time picture transmission is carried out on unmanned aerial vehicle nodes aiming at areas with congestion, real-time monitoring of urban roads is achieved, when traffic accidents or casualties of people occur on the roads, the number of the best unmanned aerial vehicle nodes is selected according to the standby state of unmanned aerial vehicles in nearby areas to fly to a preset area, multi-unmanned aerial vehicle nodes are matched and jointly photographed by adjusting aerial photographing attitude angles of the unmanned aerial vehicle nodes, the scene pictures transmitted by the unmanned aerial vehicle nodes are clear, the unmanned aerial vehicle nodes are interconnected with hospitals, and temporary self-rescue service is remotely.
As shown in FIG. 3, the present invention discloses a flow chart of an image preprocessing method;
according to the embodiment of the invention, the traffic image information is collected by the aerial photography unmanned aerial vehicle, and the image information is preprocessed, and the method further comprises the following steps:
s302, carrying out thresholding on the traffic image, wherein the non-lane line area is processed into black and the lane line area is processed into white;
s304, removing image noise by a local minimum method, and performing compensation processing on a white area by a local maximum method;
s306, setting the elimination width, carrying out fixed width processing on the white area, establishing polar angle constraint conditions according to the polar angle characteristics of the lane line,
and S308, generating compensation information according to the polar angle constraint condition, and adjusting the aerial photography attitude angle of the unmanned aerial vehicle according to the compensation information.
As shown in FIG. 4, the present invention discloses a flow chart of a method for identifying a traffic event;
according to the embodiment of the invention, the traffic flow data vector characteristics are extracted, and the traffic event category is identified by using a network model, which specifically comprises the following steps:
s402, constructing a traffic flow prediction model by using a deep learning algorithm, and carrying out classification training on traffic flow data;
s404, solving traffic jam information and road condition states by adopting an optimization algorithm;
s406, carrying out shortest path optimization according to the traffic jam information and carrying out alternative path search;
s408, the unmanned aerial vehicle node acquires the alternative path and carries out simulated flight along the alternative path to obtain road condition information of the alternative path;
s410, obtaining adjustment information according to the alternative path road condition information,
and S412, adjusting the alternative path in real time through the adjustment information to obtain result information, and transmitting the result information to the platform.
As shown in fig. 5, the present invention discloses a flow chart of a method for updating road network information;
according to the embodiment of the invention, the generation of the induction information according to the traffic event category comprises the following steps:
s502, acquiring traffic flow information, identifying an emergency congestion road section caused by an emergency, and generating congestion information;
s504, comparing the congestion information with a congestion judging threshold value, and judging congestion degree and congestion level;
s506, dividing the jammed road section into a plurality of running road sections with equal distances, and searching vehicle sets on all the running road sections and enabling the original route to pass through the running road sections;
s508, selecting the route according to the probability distribution to generate a new planning route,
s510, the new planned route is recursively distributed to the selected vehicles in the vehicle set, and road network information is updated.
It should be noted that the traffic event category generates guidance information, the vehicle route is guided in real time through the guidance information, and it is ensured that the vehicle is in the optimal route, because the traffic event category has a possibility of instantaneous occurrence, the platform automatically searches for the alternative route while the optimal route is being driven, then the unmanned aerial vehicle node performs simulated flight along the alternative route, and transmits a real-time picture to the platform, analyzes the traffic flow information of the alternative route, and adjusts the alternative route in real time, so as to ensure the traffic efficiency of the alternative route.
According to the embodiment of the invention, the traffic event category comprises one or more of road congestion, traffic accidents, road construction, road closure and road weather abnormity;
the road congestion comprises periodic congestion or aperiodic congestion, and the periodic congestion comprises congestion which often occurs at a road intersection or a road section within a preset time period; the aperiodic congestion includes congestion caused by random or unexpected conditions.
As shown in FIG. 6, the present invention discloses a block diagram of an urban road supervision system based on dynamic traffic flow;
the second aspect of the present invention also provides an urban road supervision system based on dynamic traffic flow, where the system 6 includes: a memory 61 and a processor 62, wherein the memory includes a dynamic traffic flow-based urban road supervision method program, and when executed by the processor, the dynamic traffic flow-based urban road supervision method program implements the following steps:
collecting traffic image information through an aerial photography unmanned aerial vehicle, and preprocessing the image information to obtain traffic flow data;
extracting traffic flow data vector characteristics, and identifying the traffic event category by using a network model;
generating the inducement information according to the traffic event category,
and guiding the vehicle path in real time through the guidance information, and transmitting result information to the platform.
It should be noted that the various indexes reflecting the traffic flow state include the traffic volume, the average speed of the vehicle, and the lane occupancy, it should be noted that the traffic volume and the average speed of the vehicle and the lane occupancy have a nonlinear correlation, the dynamic traffic flow parameter has the obvious characteristics of the spatio-temporal data, and the spatio-temporal autocorrelation is the most core and essential characteristic thereof, and is used to describe the intrinsic attributes in the time domain and the space domain. The spatio-temporal autocorrelation can be divided into temporal autocorrelation and spatial autocorrelation, and a time sequence generally has a characteristic that values are correlated at adjacent times (or in a time period), that is, temporal autocorrelation. The traffic flow parameter data such as traffic volume, vehicle average speed, lane occupancy rate and the like have time autocorrelation attribute, namely, correlation exists at adjacent time (or in time period), and the autocorrelation coefficient is
Wherein, λ represents the time autocorrelation coefficient, n is the time delay period number, and T is the total number of the sampling time points; x is the number oftFor the value of the study attribute at time t, xt+nValue of study attribute, x, at time t + nt+2nFor the value of the study attribute at time t +2n,
the average value of all research attribute values in T moments; the value range of the autocorrelation coefficient is in the range of [ -1,1 [)]Within, a closer to 1 indicates a higher degree of autocorrelation of the time series.
According to the embodiment of the invention, traffic image information is acquired by an aerial photography unmanned aerial vehicle, and the image information is preprocessed to obtain traffic flow data, which specifically comprises the following steps:
acquiring traffic image information, performing marginalization processing on the image information,
extracting the path dividing line and the path track in the image information to generate road network information,
comparing the road network information with the actual traffic path information to obtain the unmanned aerial vehicle aerial photography attitude angle,
judging whether the aerial photography attitude angle of the unmanned aerial vehicle is larger than a preset aerial photography attitude angle or not,
if the value is larger than the preset value, generating compensation information, adjusting the aerial photography attitude angle of the unmanned aerial vehicle according to the compensation information,
and shooting the traffic image information again through the unmanned aerial vehicle, and generating traffic flow data.
The method includes the steps that road image information is aerial photographed by an unmanned aerial vehicle, traffic flow data are obtained in real time, traffic event categories are automatically identified according to models, corresponding decisions are made according to different traffic event categories, real-time picture transmission is carried out on unmanned aerial vehicle nodes aiming at areas with congestion, real-time monitoring of urban roads is achieved, when traffic accidents or casualties of people occur on the roads, the number of the best unmanned aerial vehicle nodes is selected according to the standby state of unmanned aerial vehicles in nearby areas to fly to a preset area, multi-unmanned aerial vehicle nodes are matched and jointly photographed by adjusting aerial photographing attitude angles of the unmanned aerial vehicle nodes, the scene pictures transmitted by the unmanned aerial vehicle nodes are clear, the unmanned aerial vehicle nodes are interconnected with hospitals, and temporary self-rescue service is remotely.
According to the embodiment of the invention, the generation of the induction information according to the traffic event category comprises the following steps:
acquiring traffic flow information, identifying an emergent congestion road section caused by an emergent event, and generating congestion information;
comparing the congestion information with a congestion judging threshold value, and judging congestion degree and congestion level;
dividing the jammed road section into a plurality of running road sections with equal distances, and searching a vehicle set on all the running road sections and allowing the original route to pass through the running road sections;
selecting a route according to the probability distribution to generate a new planned route,
the new planned route is recursively assigned to selected vehicles within the vehicle collection and the road network information is updated.
It should be noted that the traffic event category generates guidance information, the vehicle route is guided in real time through the guidance information, and it is ensured that the vehicle is in the optimal route, because the traffic event category has a possibility of instantaneous occurrence, the platform automatically searches for the alternative route while the optimal route is being driven, then the unmanned aerial vehicle node performs simulated flight along the alternative route, and transmits a real-time picture to the platform, analyzes the traffic flow information of the alternative route, and adjusts the alternative route in real time, so as to ensure the traffic efficiency of the alternative route.
According to the embodiment of the invention, the traffic image information is collected by the aerial photography unmanned aerial vehicle, and the image information is preprocessed, and the method further comprises the following steps:
carrying out thresholding on the traffic image, wherein the non-lane line area is processed into black, and the lane line area is processed into white;
removing image noise points by a local minimum method, and performing compensation processing on a white area by a local maximum method;
setting the elimination width, carrying out fixed width processing on the white area, establishing polar angle constraint conditions according to the polar angle characteristics of the lane lines,
and generating compensation information according to the polar angle constraint condition, and adjusting the aerial photography attitude angle of the unmanned aerial vehicle according to the compensation information.
According to the embodiment of the invention, the traffic flow data vector characteristics are extracted, and the traffic event category is identified by using a network model, which specifically comprises the following steps:
constructing a traffic flow prediction model by utilizing a deep learning algorithm, and carrying out classification training on traffic flow data;
solving traffic jam information and road condition states by adopting an optimization algorithm;
carrying out shortest path optimization according to the traffic congestion information and carrying out alternative path search;
the unmanned aerial vehicle node acquires the alternative path and carries out simulated flight along the alternative path to obtain road condition information of the alternative path;
acquiring the adjustment information according to the road condition information of the alternative path,
the alternative path is adjusted in real time through the adjustment information to obtain result information,
and transmitting the result information to the platform.
According to the embodiment of the invention, the traffic event category comprises one or more of road congestion, traffic accidents, road construction, road closure and road weather abnormity;
the road congestion comprises periodic congestion or aperiodic congestion, and the periodic congestion comprises congestion which often occurs at a road intersection or a road section within a preset time period; the aperiodic congestion includes congestion caused by random or unexpected conditions.
The third aspect of the present invention provides a computer-readable storage medium, where the computer-readable storage medium includes a dynamic traffic flow-based urban road supervision method program, and when the dynamic traffic flow-based urban road supervision method program is executed by a processor, the steps of the dynamic traffic flow-based urban road supervision method described in any one of the above are implemented.
In conclusion, the unmanned aerial vehicle is used for aerial photography of road image information, traffic flow data are obtained in real time, traffic event categories are automatically identified according to the models, corresponding decisions are made according to different traffic event categories, and the unmanned aerial vehicle nodes are used for real-time picture transmission aiming at congested areas, so that real-time monitoring of urban roads is achieved.
The traffic event type generates induction information, the vehicle path is guided in real time through the induction information, the vehicle is ensured to be in the optimal path, due to the fact that the traffic event type has the possibility of instantaneous occurrence, the platform automatically searches for alternative paths while the optimal path is driven, then the unmanned aerial vehicle node conducts simulated flight along the alternative paths, real-time pictures are transmitted to the platform, traffic flow information of the alternative paths is analyzed, the alternative paths are adjusted in real time, and traffic efficiency of the alternative paths is ensured.
When a traffic accident or casualties of people occur on a road, the number of the optimal unmanned aerial vehicle nodes is selected according to the standby state of the unmanned aerial vehicles in the nearby area to fly to a preset area, the unmanned aerial vehicle nodes are matched and jointly photographed by adjusting the aerial photographing attitude angles of the unmanned aerial vehicle nodes, the on-site pictures transmitted by the unmanned aerial vehicle nodes are clear, and the unmanned aerial vehicle nodes are interconnected with a hospital to remotely guide temporary self-rescue service.
In the several embodiments provided in the present application, it should be understood that the disclosed apparatus and method may be implemented in other ways. The above-described device embodiments are merely illustrative, for example, the division of a unit is only one logical function division, and there may be other division ways in actual implementation, such as: multiple units or components may be combined, or may be integrated into another system, or some features may be omitted, or not implemented. In addition, the coupling, direct coupling or communication connection between the components shown or discussed may be through some interfaces, and the indirect coupling or communication connection between the devices or units may be electrical, mechanical or other forms.
The units described as separate parts may or may not be physically separate, and parts displayed as units may or may not be physical units; can be located in one place or distributed on a plurality of network units; some or all of the units can be selected according to actual needs to achieve the purpose of the solution of the embodiment.
In addition, all the functional units in the embodiments of the present invention may be integrated into one processing unit, or each unit may be separately regarded as one unit, or two or more units may be integrated into one unit; the integrated unit can be realized in a form of hardware, or in a form of hardware plus a software functional unit.
Those of ordinary skill in the art will understand that: all or part of the steps for realizing the method embodiments can be completed by hardware related to program instructions, the program can be stored in a computer readable storage medium, and the program executes the steps comprising the method embodiments when executed; and the aforementioned storage medium includes: a mobile storage device, a Read-Only Memory (ROM), a Random Access Memory (RAM), a magnetic disk or an optical disk, and other various media capable of storing program codes.
Alternatively, the integrated unit of the present invention may be stored in a computer-readable storage medium if it is implemented in the form of a software functional module and sold or used as a separate product. Based on such understanding, the technical solutions of the embodiments of the present invention may be essentially implemented or a part contributing to the prior art may be embodied in the form of a software product, which is stored in a storage medium and includes several instructions for enabling a computer device (which may be a personal computer, a server, or a network device) to execute all or part of the methods of the embodiments of the present invention. And the aforementioned storage medium includes: a removable storage device, a ROM, a RAM, a magnetic or optical disk, or various other media that can store program code.
The above description is only for the specific embodiments of the present invention, but the scope of the present invention is not limited thereto, and any person skilled in the art can easily conceive of the changes or substitutions within the technical scope of the present invention, and the changes or substitutions should be covered within the scope of the present invention. Therefore, the protection scope of the present invention shall be subject to the protection scope of the claims.
Claims (10)
1. An urban road supervision method based on dynamic traffic flow is characterized by comprising the following steps:
collecting traffic image information through an aerial photography unmanned aerial vehicle, and preprocessing the image information to obtain traffic flow data;
extracting traffic flow data vector characteristics, and identifying the traffic event category by using a network model;
generating the inducement information according to the traffic event category,
and guiding the vehicle path in real time through the guidance information, and transmitting result information to the platform.
2. The method for supervising the urban roads based on the dynamic traffic flow according to claim 1, wherein the traffic flow data is obtained by acquiring traffic image information through an aerial unmanned aerial vehicle and preprocessing the image information, and specifically comprises:
acquiring traffic image information, performing marginalization processing on the image information,
extracting the path dividing line and the path track in the image information to generate road network information,
comparing the road network information with the actual traffic path information to obtain the unmanned aerial vehicle aerial photography attitude angle,
judging whether the aerial photography attitude angle of the unmanned aerial vehicle is larger than a preset aerial photography attitude angle or not,
if the value is larger than the preset value, generating compensation information, adjusting the aerial photography attitude angle of the unmanned aerial vehicle according to the compensation information,
and shooting the traffic image information again through the unmanned aerial vehicle, and generating traffic flow data.
3. The method for supervising the urban roads based on the dynamic traffic flow according to claim 1, wherein traffic image information is collected by an aerial unmanned aerial vehicle, and the image information is preprocessed, further comprising:
carrying out thresholding on the traffic image, wherein the non-lane line area is processed into black, and the lane line area is processed into white;
removing image noise points by a local minimum method, and performing compensation processing on a white area by a local maximum method;
setting the elimination width, carrying out fixed width processing on the white area, establishing polar angle constraint conditions according to the polar angle characteristics of the lane lines,
and generating compensation information according to the polar angle constraint condition, and adjusting the aerial photography attitude angle of the unmanned aerial vehicle according to the compensation information.
4. The method for supervising the urban roads based on the dynamic traffic flow according to claim 1, wherein the traffic flow data vector features are extracted, and a network model is used for identifying the traffic event categories, specifically:
constructing a traffic flow prediction model by utilizing a deep learning algorithm, and carrying out classification training on traffic flow data;
solving traffic jam information and road condition states by adopting an optimization algorithm;
carrying out shortest path optimization according to the traffic congestion information and carrying out alternative path search;
the unmanned aerial vehicle node acquires the alternative path and carries out simulated flight along the alternative path to obtain road condition information of the alternative path;
acquiring the adjustment information according to the road condition information of the alternative path,
the alternative path is adjusted in real time through the adjustment information to obtain result information,
and transmitting the result information to the platform.
5. The method for supervising the urban road based on the dynamic traffic flow according to claim 1, wherein the generation of the induction information according to the traffic event category comprises:
acquiring traffic flow information, identifying an emergent congestion road section caused by an emergent event, and generating congestion information;
comparing the congestion information with a congestion judging threshold value, and judging congestion degree and congestion level;
dividing the jammed road section into a plurality of running road sections with equal distances, and searching a vehicle set on all the running road sections and allowing the original route to pass through the running road sections;
selecting a route according to the probability distribution to generate a new planned route,
the new planned route is recursively assigned to selected vehicles within the vehicle collection and the road network information is updated.
6. The method of claim 1, wherein the traffic event category includes one or more of road congestion, traffic accident, road construction, road closure, and road weather anomaly;
the road congestion comprises periodic congestion or aperiodic congestion, and the periodic congestion comprises congestion which often occurs at a road intersection or a road section within a preset time period; the aperiodic congestion includes congestion bursts caused by random or unexpected conditions.
7. An urban road supervision system based on dynamic traffic flow, characterized in that the system comprises: the dynamic traffic flow-based urban road supervision method comprises a memory and a processor, wherein the memory comprises a dynamic traffic flow-based urban road supervision method program, and when the dynamic traffic flow-based urban road supervision method program is executed by the processor, the following steps are realized: collecting traffic image information through an aerial photography unmanned aerial vehicle, and preprocessing the image information to obtain traffic flow data;
extracting traffic flow data vector characteristics, and identifying the traffic event category by using a network model;
generating the inducement information according to the traffic event category,
and guiding the vehicle path in real time through the guidance information, and transmitting result information to the platform.
8. The system of claim 7, wherein traffic image information is collected by an aerial unmanned aerial vehicle, and the image information is preprocessed to obtain traffic flow data, and the system specifically comprises:
acquiring traffic image information, performing marginalization processing on the image information,
extracting the path dividing line and the path track in the image information to generate road network information,
comparing the road network information with the actual traffic path information to obtain the unmanned aerial vehicle aerial photography attitude angle,
judging whether the aerial photography attitude angle of the unmanned aerial vehicle is larger than a preset aerial photography attitude angle or not,
if the current value is larger than the preset value, generating compensation information, adjusting the aerial photographing attitude angle of the unmanned aerial vehicle according to the compensation information, shooting traffic image information again through the unmanned aerial vehicle, and generating traffic flow data.
9. The system of claim 7, wherein the generation of inducement information according to the traffic event category comprises:
acquiring traffic flow information, identifying an emergent congestion road section caused by an emergent event, and generating congestion information;
comparing the congestion information with a congestion judging threshold value, and judging congestion degree and congestion level;
dividing the jammed road section into a plurality of running road sections with equal distances, and searching a vehicle set on all the running road sections and allowing the original route to pass through the running road sections;
selecting a route according to the probability distribution to generate a new planned route,
the new planned route is recursively assigned to selected vehicles within the vehicle collection and the road network information is updated.
10. A computer-readable storage medium, characterized in that the computer-readable storage medium comprises therein a dynamic traffic flow based urban road supervision method program, which when executed by a processor, implements the steps of the dynamic traffic flow based urban road supervision method according to any one of claims 1 to 6.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202011364609.9A CN112382097A (en) | 2020-11-27 | 2020-11-27 | Urban road supervision method and system based on dynamic traffic flow and readable storage medium |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202011364609.9A CN112382097A (en) | 2020-11-27 | 2020-11-27 | Urban road supervision method and system based on dynamic traffic flow and readable storage medium |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN112382097A true CN112382097A (en) | 2021-02-19 |
Family
ID=74588847
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202011364609.9A Withdrawn CN112382097A (en) | 2020-11-27 | 2020-11-27 | Urban road supervision method and system based on dynamic traffic flow and readable storage medium |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN112382097A (en) |
Cited By (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN113850297A (en) * | 2021-08-31 | 2021-12-28 | 北京百度网讯科技有限公司 | Road data monitoring method and device, electronic equipment and storage medium |
| CN114500102A (en) * | 2022-03-09 | 2022-05-13 | 绍兴文理学院 | Sampling-based intrusion detection system and method for edge computing architecture Internet of things |
| CN114944072A (en) * | 2022-07-22 | 2022-08-26 | 中关村科学城城市大脑股份有限公司 | Method and device for generating guidance prompt voice |
-
2020
- 2020-11-27 CN CN202011364609.9A patent/CN112382097A/en not_active Withdrawn
Cited By (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN113850297A (en) * | 2021-08-31 | 2021-12-28 | 北京百度网讯科技有限公司 | Road data monitoring method and device, electronic equipment and storage medium |
| CN113850297B (en) * | 2021-08-31 | 2023-10-27 | 北京百度网讯科技有限公司 | Road data monitoring method and device, electronic equipment and storage medium |
| CN114500102A (en) * | 2022-03-09 | 2022-05-13 | 绍兴文理学院 | Sampling-based intrusion detection system and method for edge computing architecture Internet of things |
| CN114500102B (en) * | 2022-03-09 | 2024-02-13 | 绍兴文理学院 | Sampling-based edge computing architecture Internet of things intrusion detection system and method |
| CN114944072A (en) * | 2022-07-22 | 2022-08-26 | 中关村科学城城市大脑股份有限公司 | Method and device for generating guidance prompt voice |
| CN114944072B (en) * | 2022-07-22 | 2022-11-01 | 中关村科学城城市大脑股份有限公司 | Method and device for generating guidance prompt voice |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN112382097A (en) | Urban road supervision method and system based on dynamic traffic flow and readable storage medium | |
| CN112462774A (en) | Urban road supervision method and system based on unmanned aerial vehicle navigation following and readable storage medium | |
| WO2020034903A1 (en) | Smart navigation method and system based on topological map | |
| CN111612206A (en) | Street pedestrian flow prediction method and system based on space-time graph convolutional neural network | |
| US20080095435A1 (en) | Video segmentation using statistical pixel modeling | |
| CN108898520B (en) | Student safety monitoring method and system based on trajectory data | |
| CN112509322A (en) | Unmanned aerial vehicle-based high-speed traffic accident supervision method and system and readable storage medium | |
| CN112433539A (en) | Unmanned aerial vehicle scheduling method and system for processing high-speed traffic accidents and readable storage medium | |
| CN113642403B (en) | Crowd abnormal intelligent safety detection system based on edge calculation | |
| CN112669596B (en) | Traffic safety situation distinguishing system and method based on big data | |
| CN108256447A (en) | A kind of unmanned plane video analysis method based on deep neural network | |
| KR20220146670A (en) | Traffic anomaly detection methods, devices, devices, storage media and programs | |
| CN113673311A (en) | Traffic abnormal event detection method, equipment and computer storage medium | |
| Zhu et al. | Spatio-temporal point processes with attention for traffic congestion event modeling | |
| CN114926791A (en) | Method and device for detecting abnormal lane change of vehicles at intersection, storage medium and electronic equipment | |
| CN111881786B (en) | Store operation behavior management method, store operation behavior management device and storage medium | |
| Abbas et al. | Real-time traffic jam detection and congestion reduction using streaming graph analytics | |
| CN115511280A (en) | Urban flood toughness evaluation method based on multi-mode data fusion | |
| KR102566525B1 (en) | Method and apparatus for analyzing traffic situation | |
| CN114399910A (en) | Traffic control method and related equipment | |
| Aremu et al. | Towards smart city security: Violence and weaponized violence detection using dcnn | |
| Kweon et al. | Proposed placement model for public CCTV systems in student safety zones considering surveillance probability on pedestrian streets | |
| Hubner et al. | Audio-video sensor fusion for the detection of security critical events in public spaces | |
| Meshram et al. | Dynamic Traffic Scheduling Using Emergency Vehicle Detection | |
| CN117475628B (en) | Expressway operation method and information system based on risk theory |
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 | ||
| WW01 | Invention patent application withdrawn after publication |
Application publication date: 20210219 |
|
| WW01 | Invention patent application withdrawn after publication |