CN113033030A - Congestion simulation method and system based on real road scene - Google Patents
Congestion simulation method and system based on real road scene Download PDFInfo
- Publication number
- CN113033030A CN113033030A CN202110569716.3A CN202110569716A CN113033030A CN 113033030 A CN113033030 A CN 113033030A CN 202110569716 A CN202110569716 A CN 202110569716A CN 113033030 A CN113033030 A CN 113033030A
- Authority
- CN
- China
- Prior art keywords
- lane
- vehicle
- road
- roadblock
- simulated
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Granted
Links
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F30/00—Computer-aided design [CAD]
- G06F30/20—Design optimisation, verification or simulation
-
- 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
-
- 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
-
- Y—GENERAL TAGGING OF NEW TECHNOLOGICAL DEVELOPMENTS; GENERAL TAGGING OF CROSS-SECTIONAL TECHNOLOGIES SPANNING OVER SEVERAL SECTIONS OF THE IPC; TECHNICAL SUBJECTS COVERED BY FORMER USPC CROSS-REFERENCE ART COLLECTIONS [XRACs] AND DIGESTS
- Y02—TECHNOLOGIES OR APPLICATIONS FOR MITIGATION OR ADAPTATION AGAINST CLIMATE CHANGE
- Y02T—CLIMATE CHANGE MITIGATION TECHNOLOGIES RELATED TO TRANSPORTATION
- Y02T10/00—Road transport of goods or passengers
- Y02T10/10—Internal combustion engine [ICE] based vehicles
- Y02T10/40—Engine management systems
Abstract
The invention relates to the technical field of roadblock simulation, in particular to a congestion simulation method and a congestion simulation system based on a real road scene, which comprise the following steps: dividing the three-dimensional scene road into a plurality of lanes and storing the position information of each lane; mapping traffic flow in the traffic monitoring video in a three-dimensional scene road to generate a plurality of vehicles; randomly clicking in a three-dimensional scene road to generate a roadblock, calculating position information of the roadblock, determining a lane where the roadblock is located according to the position information, and marking the lane where the roadblock is located as a non-passable lane; when an obstacle is detected around the vehicle, cutting off the mapping relation between the vehicle and the traffic monitoring video, and marking the vehicle as a simulated vehicle; and determining the driving path of the simulated vehicle according to the driving path of the vehicle in the passable lane. The method is used for solving the technical problems that the vehicle generation in the existing simulation scene is a completely simulated state and how to rapidly and reasonably plan the path of the vehicle.
Description
Technical Field
The invention relates to the technical field of roadblock simulation, in particular to a congestion simulation method and system based on a real road scene.
Background
In the urban traffic planning and designing process, with the increasing number of automobiles, due to the randomness and unpredictability of the driving behaviors of the automobiles, a traffic management department is difficult to establish an accurate mathematical model to predict the vehicle congestion, and therefore how to solve the problem that the huge pressure brought by the vehicle congestion to road traffic becomes a great problem for the traffic management department.
With the occurrence of automatic driving, a virtual simulation test is established in the field of automatic driving and is commonly used for carrying out simulation test on an automatic driving vehicle, congestion simulation and a vehicle running path after congestion occurs can be intuitively demonstrated in the simulation test, and a mathematical model is replaced to predict vehicle congestion so as to solve the problems.
Applying simulation tests to vehicle congestion prediction will face some technical barriers: 1. in the prior art, in order to ensure the authenticity of a simulation scene, a simulation scene consistent with a real road is built, but the vehicle generation in the simulation scene is in a completely simulated state, so the rationality of the vehicle generation needs to be examined urgently; 2. when congestion occurs, how to rapidly and reasonably plan a path of the vehicle is closer to the real scene.
Disclosure of Invention
The invention aims to provide a congestion simulation method and a congestion simulation system based on a real road scene so as to solve the problems.
In order to achieve the above object, the embodiments of the present application provide the following technical solutions:
a congestion simulation method based on a real road scene comprises the following steps:
s1, dividing a three-dimensional scene road into a plurality of lanes, and storing position information of each lane;
s2, mapping the traffic flow in the traffic monitoring video in a three-dimensional scene road to generate a plurality of vehicles;
s3, randomly clicking in a three-dimensional scene road to generate a roadblock, calculating position information of the roadblock, determining a lane where the roadblock is located according to the position information, marking the lane where the roadblock is located as a non-passable lane, and marking other lanes as passable lanes;
s4, in the impassable lane, when an obstacle in front of a vehicle is detected, cutting off the mapping relation between the vehicle and the traffic monitoring video, and marking the vehicle as a simulated vehicle, wherein the obstacle comprises a road block and the vehicle;
and S5, determining a target lane into which the simulated vehicle enters in a lane changing manner, and planning a running path of the simulated vehicle.
Further, the S1 specifically includes the following steps:
s11, accessing openmapsheet data of a road in the traffic monitoring video, wherein the openmapsheet data comprises a path and a width of each lane in the road;
s12, constructing a three-dimensional scene road according to the openmapstreet data, and dividing to obtain a plurality of lanes.
Further, the S2 specifically includes the following steps:
s21, cutting the traffic monitoring video according to the number of frames to obtain a plurality of frame images;
s22, recording the position information of the vehicle in each frame of image,
s23, reading the position information of the vehicle in each frame of image according to the time sequence, and generating a corresponding vehicle at a corresponding position in the three-dimensional scene road;
and S24, generating a continuous three-dimensional scene video stream.
Further, the S3 specifically includes the following steps:
s31, continuously clicking three times at different points in the three-dimensional scene road to generate a curve path;
s32, detecting position information of three clicks by using rays, calculating the curve path by using a Bezier curve formula, and generating a roadblock on the curve path;
s33, determining a lane where the roadblock is located according to the position information of the path and the lane, marking the lane where the roadblock is located as an impassable lane, and marking other lanes as passable lanes;
and S34, sending the position information of the impassable lane and the passable lane to the vehicle.
Further, the S4 includes the following steps:
s41, adding an obstacle detection frame in front of the vehicle in the impassable lane;
s42, when an obstacle exists in an obstacle detection frame of the vehicle, judging that an obstacle exists in front of the vehicle;
s43, cutting off the mapping relation between the vehicle and the traffic monitoring video, marking the vehicle as a simulated vehicle, and enabling the simulated vehicle to enter an obstacle avoidance mode.
Further, the S5 specifically includes the following steps:
s51, when the obstacle in front of the simulated vehicle is a road block, taking a passable lane closest to the lane where the simulated vehicle is as a target lane;
s52, determining a target vehicle in the target lane, and acquiring a running path of the target vehicle;
s53, determining a lane change starting point of the simulated vehicle;
s54, determining a lane change terminal point of the simulated vehicle after lane change;
s55, fitting according to preset Dubings parameters to obtain a Dubings curve, and taking the Dubings curve as a second preset path of the simulated vehicle;
and S56, under the condition that the second preset path and the running path of the target vehicle keep a safe distance, the simulated vehicle runs to a lane changing terminal along the second preset path.
Further, the step S51 is preceded by the steps of:
s50, when an intermediate lane exists between the target lane and the lane where the simulation vehicle is located, the target vehicle firstly changes the lane to the intermediate lane and then changes the lane from the intermediate lane to the target lane.
Further, the S56 specifically includes the following steps:
s561, enabling the simulated vehicle to run at a constant speed, wherein the speed is equal to the speed of a lane change starting point;
s562, calculating the total time required by the simulated vehicle to pass through the second preset path in the future according to a speed-displacement formula, and calculating the number of traversed frames in the future total time;
s563, calculating the coordinate position of the simulated vehicle in each frame of image in the future;
s564, acquiring the coordinate position of the target vehicle in each frame of image traversed in the future;
s565, calculating the relative distance between the simulated vehicle and the target vehicle in each frame of image traversed in the future;
and S566, when the relative distance is smaller than a preset safe distance, the simulated vehicle runs along the second preset path.
Further, the S5 further includes:
when the obstacle in front of the simulated vehicle is a vehicle, the simulated vehicle decelerates to run along the current road.
A congestion simulation system based on a real road scene comprises:
lane division module: dividing a three-dimensional scene road into a plurality of lanes, and storing position information of each lane;
a mapping module: mapping traffic flow in the traffic monitoring video in a three-dimensional scene road to generate a plurality of vehicles;
roadblock generation module: randomly clicking in a three-dimensional scene road to generate a roadblock, calculating position information of the roadblock, determining a lane where the roadblock is located according to the position information, marking the lane where the roadblock is located as a non-passable lane, and marking other lanes as passable lanes;
obstacle detection module: in the impassable lane, when an obstacle in front of a vehicle is detected, cutting off the mapping relation between the vehicle and a traffic monitoring video, and marking the vehicle as a simulated vehicle;
a path planning module: and determining a target lane into which the simulated vehicle enters in a lane changing manner, and planning a driving path of the simulated vehicle.
The invention has the beneficial effects that:
1. according to the method and the device, the three-dimensional scene road is built according to the road information in the real traffic monitoring video, the vehicle running path in the monitoring video is obtained, and a plurality of vehicles are generated in the three-dimensional scene road according to the real vehicle running path, so that the vehicle number and the authenticity of the running path are ensured, test data are provided for subsequent congestion simulation, and the simulation result is more real and has reference value.
2. The method and the device utilize real vehicle data as test data, firstly store the driving path of each vehicle in the data table, drive in the road according to the set driving path when no obstacle appears, facilitate the simulated vehicle to quickly obtain the driving paths of other related vehicles in a subsequent obstacle avoidance mode, determine whether the simulated vehicle changes the road or not based on the driving paths, reduce the prediction process of the future driving paths of other related vehicles, and obtain real data of the driving paths.
3. The method generates the roadblock by randomly clicking in the three-dimensional scene road, and the position and the width of the roadblock can be freely set; after the roadblock is generated and a vehicle coming from the rear detects the roadblock, starting an obstacle avoidance mode, and obtaining a Dubings curve through the fitting of preset Dubings parameters, namely a preset path of lane changing; and at the moment, the stopped vehicle is used as an obstacle by the coming vehicle behind, the coming vehicle behind is also started to avoid the obstacle mode, and the process is repeated. And recording the congestion process and the congestion degree, and providing reference and guidance for subsequent traffic planning.
Additional features and advantages of the invention will be set forth in the description which follows, and in part will be obvious from the description, or may be learned by the practice of the embodiments of the invention. The objectives and other advantages of the invention will be realized and attained by the structure particularly pointed out in the written description and claims hereof as well as the appended drawings.
Drawings
In order to more clearly illustrate the technical solutions of the embodiments of the present invention, the drawings needed to be used in the embodiments will be briefly described below, it should be understood that the following drawings only illustrate some embodiments of the present invention and therefore should not be considered as limiting the scope, and for those skilled in the art, other related drawings can be obtained according to the drawings without inventive efforts.
FIG. 1 is a schematic flow chart of a congestion simulation method based on a real road scene according to an embodiment of the present invention;
FIG. 2 is a flowchart illustrating the steps of S4 and S5 according to an embodiment of the present invention;
FIG. 3 is a first schematic diagram of a three-dimensional scene road according to an embodiment of the invention;
FIG. 4 is a schematic diagram of a road in a three-dimensional scene according to an embodiment of the present invention;
fig. 5 is a block diagram of a congestion simulation system based on a real road scene according to an embodiment of the present invention.
Detailed Description
In order to make the objects, technical solutions and advantages of the embodiments of the present invention clearer, the technical solutions in the embodiments of the present invention will be clearly and completely described below with reference to the drawings in the embodiments of the present invention, and it is obvious that the described embodiments are some, but not all, embodiments of the present invention. The components of embodiments of the present invention generally described and illustrated in the figures herein may be arranged and designed in a wide variety of different configurations. Thus, the following detailed description of the embodiments of the present invention, presented in the figures, is not intended to limit the scope of the invention, as claimed, but is merely representative of selected embodiments of the invention. All other embodiments, which can be derived by a person skilled in the art from the embodiments given herein without making any creative effort, shall fall within the protection scope of the present invention.
It should be noted that: like reference numbers or letters refer to like items in the following figures, and thus, once an item is defined in one figure, it need not be further defined or explained in subsequent figures. Meanwhile, in the description of the present invention, the terms "first", "second", and the like are used only for distinguishing the description, and are not to be construed as indicating or implying relative importance.
Example 1
As shown in fig. 1, the present embodiment provides a congestion simulation method based on a real road scene, where the method includes:
s1, dividing a three-dimensional scene road into a plurality of lanes, and storing position information of each lane;
based on the above embodiment, the S1 specifically includes the following steps:
s11, accessing openmapsheet data of a road in a traffic monitoring video, wherein the openmapsheet data comprises a path and a width of each lane in the road;
and S12, constructing a three-dimensional scene road according to the openmapstreet data, dividing the three-dimensional scene road into a plurality of lanes, and numbering the lanes in sequence.
Specifically, the three-dimensional scene road is built in a development platform in the embodiment, where the development platform includes UE4, Unity, and OSG, and preferably, a UE4 development platform is adopted in the embodiment.
The three-dimensional scene road comprises lanes in two directions, and a road object is created in the UE4 platform and used for storing the number of each lane, the boundary line of each lane and the middle line path information.
S2, mapping the traffic flow in the traffic monitoring video in a three-dimensional scene road to generate a plurality of vehicles;
specifically, the S2 specifically includes the following steps:
s21, cutting the traffic monitoring video according to the number of frames to obtain a plurality of frame images;
specifically, the monitoring video is divided into a plurality of frame images by using an AI identification algorithm, specifically, the monitoring video is input into the AI identification algorithm, the AI identification algorithm automatically divides the monitoring video into single frame images and stores the single frame images according to a time sequence, specifically, each frame image can be continuously obtained or a plurality of frame images can be obtained at intervals in the obtained single frame image, and then the obtained plurality of frame images are stored for the next identification operation;
s22, recording the position information of the vehicle in each frame of image;
recognizing the vehicle in each frame of image and the coordinate position of the vehicle in the image by using AI, and calculating the speed of the vehicle, wherein it needs to be noted that the method for acquiring the position information of the vehicle is the prior art which is disclosed, and is not described herein again;
storing the acquired position information of each vehicle into a data table;
s23, reading the position information of the vehicle in each frame of image according to the time sequence, and generating a corresponding vehicle at a corresponding position in the three-dimensional scene road;
specifically, a vehicle identification control object is created for reading associated vehicle information in a data table; and circularly traversing the data table by utilizing a SetTimerbyEvent node in the UE4, identifying a corresponding coordinate position of a control object in a three-dimensional scene road by the vehicle to generate the vehicle when traversing to a frame of image, and displaying the current speed of the vehicle.
S24, generating a continuous three-dimensional scene video stream;
in this embodiment, data in the data table is continuously read, and the coordinate position of the vehicle is continuously updated in the three-dimensional scene road to form a continuous three-dimensional scene video stream.
S3, randomly clicking in a three-dimensional scene road to generate a roadblock, calculating position information of the roadblock, determining a lane where the roadblock is located according to the position information, marking the lane where the roadblock is located as an impassable road, and marking other lanes as passable lanes;
specifically, a roadblock generating object and a roadblock storing object are created in the UE4, and the roadblock generating object is used for generating roadblocks and transmitting roadblock information; the roadblock storage object is used for storing lane information where the roadblock is located.
In this embodiment, the S3 specifically includes the following steps:
s31, continuously clicking three times at different points in the three-dimensional scene road to generate a curve path;
specifically, a mouse click event is added to the road block generation object, and the click is controlled three times by using a MultiGate node in the UE4 as a cycle.
S32, detecting position information of three clicks by using rays, calculating the curve path by using a Bezier curve formula, and generating a roadblock on the curve path;
the Bezier curve formula is as follows:
wherein, the P0, the P1 and the P2 are three control points respectively, and t is a parameter;
specifically, a curve path is calculated by using a Bezier curve formula in a way that three points form a curve, the maximum number of roadblocks which can be generated is calculated according to the length of the path, and a plurality of roadblocks are generated on the curve path, wherein the types of the roadblocks include but are not limited to road piles, fences, road cones, isolation guardrails and the like.
And when the road block is clicked for the fourth time, destroying the generated road block, marking the click as the first click, and restarting to construct a curve path.
S33, determining a lane where the roadblock is located according to the position information of the path and the lane, marking the lane where the roadblock is located as an impassable lane, and marking other lanes as passable lanes;
specifically, the S33 includes:
s331, acquiring starting point position information and end point position information of the roadblock and position information of each lane;
s332, determining lanes where the starting point position and the end point position are located, marking the lanes where the starting point position and the end point position are located and the middle lanes of the two lanes as impassable lanes, and marking the rest lanes as passable lanes, referring to FIG. 3, wherein the impassable lanes are 3 and 4 lanes, referring to FIG. 4, and the impassable lanes are 2, 3 and 4 lanes;
referring to fig. 3 and 4, the three-dimensional scene road in the figure is a bidirectional eight-lane road, and includes 8 main lanes (4 lanes in one direction) and 2 auxiliary lanes, and a separation zone or a green belt is arranged between the main lanes and the auxiliary lanes;
s34, sending the position information of the impassable lane and the passable lane to a vehicle;
specifically, an event distributor is used to transmit information of roadblocks and lanes to a vehicle recognition control object.
Referring to fig. 2, s4, in the impassable lane, when an obstacle is detected in front of a vehicle, cutting off a mapping relationship between the vehicle and a traffic monitoring video, and marking the vehicle as a simulated vehicle, wherein the obstacle includes a road block and a vehicle;
in this embodiment, the vehicles in the passable lane are obtained by mapping the vehicles in the traffic monitoring video, and the traveling path and the speed of the vehicles are consistent with those in the traffic monitoring video, so that the vehicles in the passable lane can travel at a predetermined speed without detecting surrounding obstacles by using an obstacle detection frame.
Specifically, the S4 includes the following steps:
s41, adding an obstacle detection frame in front of the vehicle in the impassable lane, wherein the detection distance d of the obstacle detection frame is related to the driving parameters and the vehicle type of the vehicle, and the specific calculation formula is as follows:
wherein V is a speed parameter, T is a vehicle model parameter, and 10 is a coefficient;
wherein v is a traveling speed (m/s);
s42, when an obstacle exists in an obstacle detection frame of the vehicle, judging that an obstacle exists in front of the vehicle;
s43, cutting off the mapping relation between the vehicle and the traffic monitoring video, marking the vehicle as a simulated vehicle, and enabling the simulated vehicle to enter an obstacle avoidance mode;
in this embodiment, when the simulated vehicle appears in the obstacle detection frame of the coming vehicle behind, it is indicated that the coming vehicle behind also detects an obstacle, the coming vehicle behind is also marked as the simulated vehicle, and other vehicles run according to the path and speed in the data table before being not marked as the simulated vehicle.
S5, determining a target lane into which the simulated vehicle enters in a lane changing manner, and planning a running path of the simulated vehicle;
specifically, the judgment of the target lane is added in the vehicle identification control object, the passable lane closest to the lane where the simulated vehicle is located is preferentially searched and is used as the target lane, and the passable lane closest to the simulated vehicle has two conditions: firstly, the nearest passable lane and the lane where the simulated vehicle is located are adjacent lanes; and secondly, an impassable lane, namely a middle lane, exists between the passable lane closest to the simulation vehicle and the lane where the simulation vehicle is located.
Based on the above embodiment, the S5 specifically includes the following steps:
s50, when an intermediate lane exists between the target lane and the lane where the simulation vehicle is located, the target vehicle firstly changes the lane to the intermediate lane and then changes the lane from the intermediate lane to the target lane.
Specifically, the S50 specifically includes the following steps:
s501, dividing a safety frame which arrives at the middle lane after the simulated vehicle changes lanes, and referring to FIG. 4;
specifically, a longitudinal coordinate value Y of the head of the simulated vehicle is obtained1On the middle lane with said ordinate Y1For reference, the area of Am is divided in the direction of travel of the simulated vehicle as a safety box, the value of a being determined according to the type of vehicle, typically 1.5-2 times the length of the vehicle, e.g. the safety box of a car is [6.5,9 ]]m；
S502, enabling the central point of the safety frame to be a target point O;
s503, fitting according to preset Dubings parameters to obtain a Dubings curve, and taking the Dubings curve as a first preset path of a simulated vehicle, wherein the Dubings parameters comprise preset turning radius, a starting point and a terminal point, the terminal point is a target point, and the turning radius is preset according to the vehicle type and the running speed;
s504, calculating a time period required by the simulated vehicle to reach the target point according to a first preset path;
s505, under the condition that no other vehicle enters a safety frame in the time period, the simulated vehicle drives along the first preset path to change the lane to a middle lane;
it should be noted that, when another vehicle enters the safety box in the time period, the simulated vehicle decelerates along the original lane, and the position of the safety box is continuously updated in the driving process until the simulated vehicle changes lane when no other vehicle exists in the safety box.
S51, when the obstacle in front of the simulated vehicle is a road block, taking a passable lane closest to the lane where the simulated vehicle is as a target lane;
s52, determining a target vehicle in the target lane, and acquiring a running path of the target vehicle from a data table;
specifically, the vehicle closest to the simulated vehicle in the target lane is marked as the target vehicle, and it should be noted that the vehicle traveling in front of the simulated vehicle in the closest target lane is not considered here, and only the vehicle traveling in the rear of the simulated vehicle is considered;
s53, taking a point of a distance barrier B (m) as a lane change starting point of the simulated vehicle, wherein B is a safe lane change distance, and belongs to [1,3], preferably, B =1.3m in the embodiment, please refer to FIG. 3;
the simulated vehicle runs at a reduced speed according to a preset running path in the data table from the position where the obstacle is detected to the starting point of the lane change, so that the speed v is less than or equal to 5m/s when the simulated vehicle reaches the starting point of the lane change;
s54, determining a lane change terminal point of the simulated vehicle after lane change;
based on the above embodiment, the longitudinal coordinate value Y of the end point of the road block close to the target lane is obtained2The central line of the target lane is matched with the longitudinal coordinate value Y2Is determined as the lane change end point.
S55, fitting according to preset Dubings parameters to obtain a Dubings curve, and taking the Dubings curve as a second preset path of the simulated vehicle;
specifically, the Dubings parameters comprise a turning radius of the vehicle, a lane change starting point and a lane change ending point, wherein the turning radius is set according to the radius of the roadblock, so that the simulated vehicle can run along the curve of the roadblock to change the lane;
s56, when the second preset path keeps a safe distance from the driving path of the vehicle in the target lane, the simulated vehicle drives to the lane change destination along the second preset path, and S56 specifically includes the following steps:
s561, enabling the simulated vehicle to run at a constant speed, wherein the speed is equal to the speed v of the lane change starting point;
s562, calculating the total time t required by the simulated vehicle to pass through the second preset path in the future according to a speed-displacement formula, and calculating the number of traversed frames in the total time t in the future;
s563, calculating the coordinate position of the simulated vehicle in each frame of image in the future;
s564, acquiring the coordinate position of the target vehicle in the nearest target lane in each frame image traversed in the future;
s565, calculating the relative distance between the simulated vehicle and the target vehicle in each frame of image traversed in the future;
and S566, comparing the relative distance with a preset safe distance, wherein the preset safe distance is set according to the shape and the size of the vehicle, preferably, the safe distance is the distance between two vehicle bodies, and preferably, the safe distance is set to be 0.7m in the embodiment.
Specifically, when the relative distance is greater than the safe distance, it is indicated that the simulated vehicle travels along the second preset path without colliding with the target vehicle, that is, the simulated vehicle travels along the second preset path at a speed v.
In this embodiment, since the vehicle travel route in the passable lane is stored in the data table, the vehicle recognition control target can directly acquire the route information of each vehicle.
Based on the above embodiment, S56 further includes the steps of:
and when the second preset path and the driving path of the vehicle in the passable lane can not keep a safe distance, taking the position of the lane change starting point as a parking position, decelerating and driving the simulated vehicle along the current road, and setting the speed of the simulated vehicle to be 0 when the simulated vehicle reaches the parking position.
Based on the above embodiment, the S5 further includes the following steps:
when the obstacle in front of the simulated vehicle is a vehicle, the simulated vehicle decelerates along the current road to a parking position.
Specifically, the parking point coordinates of the front vehicle are acquired (if the front vehicle is in the driving process, the coordinates of the parking point to be parked of the front vehicle are acquired), the lane change distance b (m) is added to the parking point coordinates of the front vehicle, namely the parking position of the simulated vehicle, and the acceleration and the speed of the simulated vehicle are calculated according to the parking point coordinates and the current speed of the simulated vehicle, so that the speed of the simulated vehicle reaching the parking position is 0.
The embodiment makes a judgment rule according to a straight-going priority principle in the traffic right, calculates whether the driving path of a straight-going vehicle in a passable lane is disturbed or not before the lane change of a simulated vehicle needing the lane change, and executes a lane change strategy under the condition that the driving path is not disturbed.
Example 2
Corresponding to the above method embodiment, the embodiment of the present disclosure further provides a congestion simulation system based on a real road scene, and the congestion simulation system based on a real road scene described below and the congestion simulation method based on a real road scene described above may be referred to correspondingly.
Referring to fig. 5, the system includes the following modules:
lane division module: dividing a three-dimensional scene road into a plurality of lanes, and storing position information of each lane;
a mapping module: mapping traffic flow in the traffic monitoring video in a three-dimensional scene road to generate a plurality of vehicles;
roadblock generation module: randomly clicking in a three-dimensional scene road to generate a roadblock, calculating position information of the roadblock, determining a lane where the roadblock is located according to the position information, marking the lane where the roadblock is located as a non-passable lane, and marking other lanes as passable lanes;
obstacle detection module: in the impassable lane, when an obstacle in front of a vehicle is detected, cutting off the mapping relation between the vehicle and a traffic monitoring video, and marking the vehicle as a simulated vehicle;
a path planning module: and determining a target lane into which the simulated vehicle enters in a lane changing manner, and planning a driving path of the simulated vehicle.
It should be noted that, regarding the system in the above embodiment, the specific manner in which each module performs the operation has been described in detail in the embodiment related to the method, and will not be elaborated herein.
Example 3
Corresponding to the above method embodiment, the embodiment of the present disclosure further provides a congestion simulation device based on a real road scene, and a congestion simulation device based on real-time traffic data described below and a congestion simulation method based on a real road scene described above may be referred to correspondingly.
The electronic device may include: a processor, a memory. The electronic device may also include one or more of a multimedia component, an input/output (I/O) interface, and a communication component.
The processor is used for controlling the overall operation of the electronic device to complete all or part of the steps in the congestion simulation method based on the real road scene. The memory is used to store various types of data to support operation at the electronic device, which may include, for example, instructions for any application or method operating on the electronic device, as well as application-related data such as contact data, messaging, pictures, audio, video, and so forth. The memory may be implemented by any type of volatile or non-volatile memory device or combination thereof, such as Static Random Access Memory (SRAM), electrically erasable programmable Read-only memory (EEPROM), erasable programmable Read-only memory (EPROM), programmable Read-only memory (PROM), Read-only memory (ROM), magnetic memory, flash memory, magnetic or optical disk. The multimedia components may include a screen and an audio component. Wherein the screen may be, for example, a touch screen and the audio component is used for outputting and/or inputting audio signals. For example, the audio component may include a microphone for receiving external audio signals. The received audio signal may further be stored in a memory or transmitted through a communication component. The audio assembly also includes at least one speaker for outputting audio signals. The I/O interface provides an interface between the processor and other interface modules, such as a keyboard, mouse, buttons, etc. These buttons may be virtual buttons or physical buttons. The communication component is used for carrying out wired or wireless communication between the electronic equipment and other equipment. Wireless communication, such as Wi-Fi, bluetooth, Near Field Communication (NFC), 2G, 3G or 4G, or a combination of one or more of them, so that the corresponding communication component may include: Wi-Fi module, bluetooth module, NFC module.
In an exemplary embodiment, the electronic device may be implemented by one or more Application Specific Integrated Circuits (ASICs), Digital Signal Processors (DSPs), Digital Signal Processing Devices (DSPDs), Programmable Logic Devices (PLDs), Field Programmable Gate Arrays (FPGAs), controllers, microcontrollers, microprocessors, or other electronic components, for performing the above-described congestion simulation method based on a real road scene.
In another exemplary embodiment, a computer readable storage medium is also provided, which comprises program instructions, which when executed by a processor, implement the steps of the above-described congestion simulation method based on a real road scene. For example, the computer readable storage medium may be the above-mentioned memory including program instructions executable by a processor of an electronic device to perform the above-mentioned congestion simulation method based on a real road scene.
Example 4
Corresponding to the above method embodiment, the embodiment of the present disclosure further provides a readable storage medium, and a readable storage medium described below and a congestion simulation method based on a real road scene described above may be referred to correspondingly.
A readable storage medium, on which a computer program is stored, which, when being executed by a processor, carries out the steps of the method for congestion simulation based on a real road scene of the above-mentioned method embodiments.
The readable storage medium may be a usb disk, a removable hard disk, a Read-only memory (ROM), a Random Access Memory (RAM), a magnetic disk or an optical disk, and may store various program codes.
The above description is only a preferred embodiment of the present invention and is not intended to limit the present invention, and various modifications and changes may be made by those skilled in the art. Any modification, equivalent replacement, or improvement made within the spirit and principle of the present invention should be included in the protection scope of the present invention.
Claims (10)
1. A congestion simulation method based on a real road scene is characterized by comprising the following steps:
s1, dividing a three-dimensional scene road into a plurality of lanes, and storing position information of each lane;
s2, mapping the traffic flow in the traffic monitoring video in a three-dimensional scene road to generate a plurality of vehicles;
s3, randomly clicking in a three-dimensional scene road to generate a roadblock, calculating position information of the roadblock, determining a lane where the roadblock is located according to the position information, marking the lane where the roadblock is located as a non-passable lane, and marking other lanes as passable lanes;
s4, in the impassable lane, when an obstacle in front of a vehicle is detected, cutting off the mapping relation between the vehicle and the traffic monitoring video, and marking the vehicle as a simulated vehicle, wherein the obstacle comprises a road block and the vehicle;
and S5, determining a target lane into which the simulated vehicle enters in a lane changing manner, and planning a running path of the simulated vehicle.
2. The method for simulating congestion based on a real road scene as claimed in claim 1, wherein the step S1 specifically comprises the following steps:
s11, accessing openmapsheet data of a road in the traffic monitoring video, wherein the openmapsheet data comprises a path and a width of each lane in the road;
s12, constructing a three-dimensional scene road according to the openmapstreet data, and dividing to obtain a plurality of lanes.
3. The method for simulating congestion based on a real road scene as claimed in claim 1, wherein the step S2 specifically comprises the following steps:
s21, cutting the traffic monitoring video according to the number of frames to obtain a plurality of frame images;
s22, recording the position information of the vehicle in each frame of image,
s23, reading the position information of the vehicle in each frame of image according to the time sequence, and generating a corresponding vehicle at a corresponding position in the three-dimensional scene road;
and S24, generating a continuous three-dimensional scene video stream.
4. The method for simulating congestion based on a real road scene as claimed in claim 1, wherein the step S3 specifically comprises the following steps:
s31, continuously clicking three times at different points in the three-dimensional scene road to generate a curve path;
s32, detecting position information of three clicks by using rays, calculating the curve path by using a Bezier curve formula, and generating a roadblock on the curve path;
s33, determining a lane where the roadblock is located according to the position information of the path and the lane, marking the lane where the roadblock is located as an impassable lane, and marking other lanes as passable lanes;
and S34, sending the position information of the impassable lane and the passable lane to the vehicle.
5. The method for simulating congestion based on real road scene as claimed in claim 1, wherein said S4 comprises the following steps:
s41, adding an obstacle detection frame in front of the vehicle in the impassable lane;
s42, when an obstacle exists in an obstacle detection frame of the vehicle, judging that an obstacle exists in front of the vehicle;
s43, cutting off the mapping relation between the vehicle and the traffic monitoring video, marking the vehicle as a simulated vehicle, and enabling the simulated vehicle to enter an obstacle avoidance mode.
6. The method for simulating congestion based on a real road scene as claimed in claim 1, wherein the step S5 specifically comprises the following steps:
s51, when the obstacle in front of the simulated vehicle is a road block, taking a passable lane closest to the lane where the simulated vehicle is as a target lane;
s52, determining a target vehicle in the target lane, and acquiring a running path of the target vehicle;
s53, determining a lane change starting point of the simulated vehicle;
s54, acquiring a longitudinal coordinate value Y of a roadblock endpoint close to the target lane2The central line of the target lane is matched with the longitudinal coordinate value Y2The point of (2) is taken as a lane change terminal point;
s55, fitting according to preset Dubings parameters to obtain a Dubings curve, and taking the Dubings curve as a second preset path of the simulated vehicle;
and S56, under the condition that the second preset path and the running path of the target vehicle keep a safe distance, the simulated vehicle runs to a lane changing terminal along the second preset path.
7. The method for simulating congestion based on real road scene as claimed in claim 6, wherein said step S51 is preceded by the steps of:
s50, when an intermediate lane exists between the target lane and the lane where the simulation vehicle is located, the target vehicle firstly changes the lane to the intermediate lane and then changes the lane from the intermediate lane to the target lane.
8. The method for simulating congestion based on a real road scene as claimed in claim 6, wherein the step S56 specifically comprises the following steps:
s561, enabling the simulated vehicle to run at a constant speed, wherein the speed is equal to the speed of a lane change starting point;
s562, calculating the total time required by the simulated vehicle to pass through the second preset path in the future according to a speed-displacement formula, and calculating the number of traversed frames in the future total time;
s563, calculating the coordinate position of the simulated vehicle in each frame of image in the future;
s564, acquiring the coordinate position of the target vehicle in each frame of image traversed in the future;
s565, calculating the relative distance between the simulated vehicle and the target vehicle in each frame of image traversed in the future;
and S566, when the relative distance is smaller than a preset safe distance, the simulated vehicle runs along the second preset path.
9. The method for simulating congestion based on a real road scene as claimed in claim 1, wherein said S5 further comprises:
and when the obstacle in front of the simulated vehicle is the vehicle, taking the current lane of the simulated vehicle as a simulated lane, and enabling the simulated vehicle to run along the current road in a decelerating manner.
10. A congestion simulation system based on a real road scene is characterized by comprising:
lane division module: dividing a three-dimensional scene road into a plurality of lanes, and storing position information of each lane;
a mapping module: mapping traffic flow in the traffic monitoring video in a three-dimensional scene road to generate a plurality of vehicles;
roadblock generation module: randomly clicking in a three-dimensional scene road to generate a roadblock, calculating position information of the roadblock, determining a lane where the roadblock is located according to the position information, marking the lane where the roadblock is located as a non-passable lane, and marking other lanes as passable lanes;
obstacle detection module: in the impassable lane, when an obstacle in front of a vehicle is detected, cutting off the mapping relation between the vehicle and a traffic monitoring video, and marking the vehicle as a simulated vehicle;
a path planning module: and determining a target lane into which the simulated vehicle enters in a lane changing manner, and planning a driving path of the simulated vehicle.
Priority Applications (2)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202110822308.4A CN113486531B (en) | 2021-05-25 | 2021-05-25 | Vehicle driving path planning method, device and system |
| CN202110569716.3A CN113033030B (en) | 2021-05-25 | 2021-05-25 | Congestion simulation method and system based on real road scene |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202110569716.3A CN113033030B (en) | 2021-05-25 | 2021-05-25 | Congestion simulation method and system based on real road scene |
Related Child Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202110822308.4A Division CN113486531B (en) | 2021-05-25 | 2021-05-25 | Vehicle driving path planning method, device and system |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN113033030A true CN113033030A (en) | 2021-06-25 |
| CN113033030B CN113033030B (en) | 2021-08-03 |
Family
ID=76455671
Family Applications (2)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202110569716.3A Active CN113033030B (en) | 2021-05-25 | 2021-05-25 | Congestion simulation method and system based on real road scene |
| CN202110822308.4A Active CN113486531B (en) | 2021-05-25 | 2021-05-25 | Vehicle driving path planning method, device and system |
Family Applications After (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202110822308.4A Active CN113486531B (en) | 2021-05-25 | 2021-05-25 | Vehicle driving path planning method, device and system |
Country Status (1)
| Country | Link |
|---|---|
| CN (2) | CN113033030B (en) |
Cited By (8)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN113391368A (en) * | 2021-06-30 | 2021-09-14 | 山东国瑞新能源有限公司 | Road exploration method and equipment based on virtual imaging technology |
| CN113569759A (en) * | 2021-07-29 | 2021-10-29 | 沭阳新辰公路仪器有限公司 | Road falling object identification method and system based on artificial intelligence |
| CN113781786A (en) * | 2021-11-11 | 2021-12-10 | 中移(上海)信息通信科技有限公司 | Method, device and equipment for confirming unviable area and readable storage medium |
| CN113885771A (en) * | 2021-12-09 | 2022-01-04 | 北京车网科技发展有限公司 | Visual processing method of track information |
| CN113990106A (en) * | 2021-11-10 | 2022-01-28 | 河海大学 | Highway lane distribution system |
| CN115116231A (en) * | 2022-08-26 | 2022-09-27 | 深圳市城市交通规划设计研究中心股份有限公司 | Vehicle-road cooperative microscopic simulation system and method, electronic device and storage medium |
| CN115206090A (en) * | 2022-06-07 | 2022-10-18 | 安徽超清科技股份有限公司 | Traffic situation estimation system based on traffic big data |
| CN117131581A (en) * | 2023-10-26 | 2023-11-28 | 乘木科技(珠海)有限公司 | Digital twin urban road construction system and method |
Families Citing this family (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN114379576B (en) * | 2021-12-15 | 2022-11-11 | 禾多科技（北京）有限公司 | Lane change information prompting method and device, electronic equipment and computer readable medium |
| CN114103957B (en) * | 2021-12-22 | 2024-02-06 | 阿波罗智联(北京)科技有限公司 | Lane change control method, apparatus, electronic device and storage medium |
| CN114543828A (en) * | 2022-02-21 | 2022-05-27 | 中国第一汽车股份有限公司 | Vehicle cut-in scene generation method and device, electronic equipment and storage medium |
| CN114580797B (en) * | 2022-05-09 | 2022-07-29 | 湖南省交通科学研究院有限公司 | Small-radius precast beam erection path planning method based on BIM simulation |
| CN114879705B (en) * | 2022-07-13 | 2022-10-28 | 智道网联科技(北京)有限公司 | Method, apparatus and computer-readable storage medium for optimizing path for lane change of unmanned vehicle |
| CN115158363B (en) * | 2022-08-16 | 2024-03-08 | 广州小鹏自动驾驶科技有限公司 | Vehicle lane change processing method and vehicle |
| CN116476840B (en) * | 2023-06-21 | 2023-09-01 | 北京斯年智驾科技有限公司 | Variable-lane driving method, device, equipment and storage medium |
Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20140278052A1 (en) * | 2013-03-15 | 2014-09-18 | Caliper Corporation | Lane-level vehicle navigation for vehicle routing and traffic management |
| US10012991B1 (en) * | 2012-03-16 | 2018-07-03 | Waymo Llc | Approach for consolidating observed vehicle trajectories into a single representative trajectory |
| CN110406535A (en) * | 2018-04-27 | 2019-11-05 | 本田技研工业株式会社 | System and method for being expected lane changing |
| CN111796587A (en) * | 2019-03-21 | 2020-10-20 | 北京京东尚科信息技术有限公司 | Automatic driving method, storage medium and electronic device |
| CN112347829A (en) * | 2019-08-08 | 2021-02-09 | 辉达公司 | Determining lane allocation of objects in an environment using obstacle and lane detection |
Family Cites Families (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN107393074B (en) * | 2017-07-21 | 2019-01-18 | 北京图森未来科技有限公司 | Realize the automatic method and system for crossing card of vehicle, relevant device |
| CN110356401B (en) * | 2018-04-05 | 2020-06-16 | 北京图森未来科技有限公司 | Automatic driving vehicle and lane changing control method and system thereof |
| CN112362074B (en) * | 2020-10-30 | 2024-03-19 | 重庆邮电大学 | Intelligent vehicle local path planning method under structured environment |
-
2021
- 2021-05-25 CN CN202110569716.3A patent/CN113033030B/en active Active
- 2021-05-25 CN CN202110822308.4A patent/CN113486531B/en active Active
Patent Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US10012991B1 (en) * | 2012-03-16 | 2018-07-03 | Waymo Llc | Approach for consolidating observed vehicle trajectories into a single representative trajectory |
| US20140278052A1 (en) * | 2013-03-15 | 2014-09-18 | Caliper Corporation | Lane-level vehicle navigation for vehicle routing and traffic management |
| CN110406535A (en) * | 2018-04-27 | 2019-11-05 | 本田技研工业株式会社 | System and method for being expected lane changing |
| CN111796587A (en) * | 2019-03-21 | 2020-10-20 | 北京京东尚科信息技术有限公司 | Automatic driving method, storage medium and electronic device |
| CN112347829A (en) * | 2019-08-08 | 2021-02-09 | 辉达公司 | Determining lane allocation of objects in an environment using obstacle and lane detection |
Non-Patent Citations (2)
| Title |
|---|
| ROY, D等: "Defining Traffic States using Spatio-temporal Traffic Graphs", 《ARXIV》 * |
| 张玉新等: "自动驾驶汽车安全技术专利分析综述", 《中国科学:信息科学》 * |
Cited By (13)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN113391368A (en) * | 2021-06-30 | 2021-09-14 | 山东国瑞新能源有限公司 | Road exploration method and equipment based on virtual imaging technology |
| CN113569759B (en) * | 2021-07-29 | 2022-06-10 | 沭阳新辰公路仪器有限公司 | Road falling object identification method and system based on artificial intelligence |
| CN113569759A (en) * | 2021-07-29 | 2021-10-29 | 沭阳新辰公路仪器有限公司 | Road falling object identification method and system based on artificial intelligence |
| CN113990106B (en) * | 2021-11-10 | 2023-08-29 | 河海大学 | Highway lane distribution system |
| CN113990106A (en) * | 2021-11-10 | 2022-01-28 | 河海大学 | Highway lane distribution system |
| CN113781786A (en) * | 2021-11-11 | 2021-12-10 | 中移(上海)信息通信科技有限公司 | Method, device and equipment for confirming unviable area and readable storage medium |
| CN113781786B (en) * | 2021-11-11 | 2022-02-22 | 中移(上海)信息通信科技有限公司 | Method, device and equipment for confirming unviable area and readable storage medium |
| CN113885771B (en) * | 2021-12-09 | 2022-03-18 | 北京车网科技发展有限公司 | Visual processing method of track information |
| CN113885771A (en) * | 2021-12-09 | 2022-01-04 | 北京车网科技发展有限公司 | Visual processing method of track information |
| CN115206090A (en) * | 2022-06-07 | 2022-10-18 | 安徽超清科技股份有限公司 | Traffic situation estimation system based on traffic big data |
| CN115116231A (en) * | 2022-08-26 | 2022-09-27 | 深圳市城市交通规划设计研究中心股份有限公司 | Vehicle-road cooperative microscopic simulation system and method, electronic device and storage medium |
| CN117131581A (en) * | 2023-10-26 | 2023-11-28 | 乘木科技(珠海)有限公司 | Digital twin urban road construction system and method |
| CN117131581B (en) * | 2023-10-26 | 2024-02-13 | 乘木科技(珠海)有限公司 | Digital twin urban road construction system and method |
Also Published As
| Publication number | Publication date |
|---|---|
| CN113033030B (en) | 2021-08-03 |
| CN113486531A (en) | 2021-10-08 |
| CN113486531B (en) | 2023-08-25 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN113033030B (en) | Congestion simulation method and system based on real road scene | |
| US11714413B2 (en) | Planning autonomous motion | |
| CN110364008B (en) | Road condition determining method and device, computer equipment and storage medium | |
| US11138349B2 (en) | System and method for simulating traffic flow distributions with approximated vehicle behavior near intersections | |
| CN110287276A (en) | High-precision map updating method, device and storage medium | |
| JP2019194071A5 (en) | ||
| CN112991742B (en) | Visual simulation method and system for real-time traffic data | |
| CN113272838A (en) | Virtual scene generation method and device, computer equipment and storage medium | |
| US20210191394A1 (en) | Systems and methods for presenting curated autonomy-system information of a vehicle | |
| US20210381846A1 (en) | Methods and apparatuses for navigation guidance and establishing a three-dimensional real scene model, device and medium | |
| KR102580095B1 (en) | Scenario-based behavior specification and validation | |
| CN104884899A (en) | Method of determining trajectories through one or more junctions of a transportation network | |
| JP7220169B2 (en) | Information processing method, device, storage medium, and program | |
| EP4089659A1 (en) | Map updating method, apparatus and device | |
| WO2021227586A1 (en) | Traffic accident analysis method, apparatus, and device | |
| CN115221722B (en) | Simulation test method, model training method and equipment for automatic driving vehicle | |
| CN114929543A (en) | Predicting the probability of jamming of surrounding factors | |
| CN113665570A (en) | Method and device for automatically sensing driving signal and vehicle | |
| CN113867367B (en) | Processing method and device for test scene and computer program product | |
| CN113538909A (en) | Traffic incident prediction method and device for automatic driving vehicle | |
| US20230159052A1 (en) | Method for processing behavior data, method for controlling autonomous vehicle, and autonomous vehicle | |
| CN112418081A (en) | Method and system for air-ground joint rapid investigation of traffic accidents | |
| US20220340167A1 (en) | Predicted Moving Trajectory Processing Method And Apparatus, And Constraint Barrier Display Method And Apparatus | |
| CN116358584A (en) | Automatic driving vehicle path planning method, device, equipment and medium | |
| CN114969004A (en) | Track fusion method, device, equipment, medium and product |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |