Vision-based method for acquiring intersection traffic plan and related device
By obtaining the vehicle's road condition image and combining the neural network model to estimate the pass time and combining the intersection information to optimize the pass solution, the congestion problem caused by the delay in the navigation system information is solved, and the traffic efficiency and driver experience are improved.
Patent Information
- Application Number
- CN202310091515.6
- Authority / Receiving Office
- CN · China
- Patent Type
- Patents(China)
- Current Assignee / Owner
- Filing Date
- 2023-02-09
- Publication Date
- 2024-11-22
- Estimated Expiration
- 2043-02-09
AI Technical Summary
Due to information delays, the existing navigation system has poor planning paths during peak traffic, which further worsens congestion, especially in main road intersections and travel peak scenarios.
By obtaining the off-road condition image of the target vehicle, input the neural network model to estimate the pass time of each lane, and combining the road condition information of the intersection ahead, determine the optimal pass plan, including the evaluation value calculation of the initial pass plan to select the shortest time and driving Optimize the pass plan for staff preference.
The selection of pass plans based on real-time road conditions is realized, which avoids poor navigation planning path effects caused by information delay, greatly improves the traffic efficiency of congested intersections, and takes into account the passage time and driver's operating preferences.
Smart Images

Figure CN116153124B_ABST
Abstract
Description
Technical Field
[0001] The present application relates to the field of road traffic technology, and in particular to a method for acquiring a vision-based intersection traffic plan and a related device. Background Art
[0002] Since the current road traffic system is not designed based on intelligent solutions, congestion is bound to occur when the traffic volume reaches a certain level, especially at main road intersections and during peak travel times, where the design flow of some lanes is far below the peak demand. Although the application of variable lanes and other designs has alleviated congestion to a certain extent, scenes where some lanes are crowded with people and other lanes are empty still occur from time to time.
[0003] The commonly used navigation system currently uses advance planning to shorten the journey. Since the current traffic information is generated based on the previous traffic of other vehicles on this road section, there is a certain delay. Therefore, even if time saving priority preference and real-time traffic update settings are added, the congestion will be further aggravated by planning to the congested lane due to delays and route selection strategies. Summary of the invention
[0004] The present application provides a method and related device for obtaining a vision-based intersection traffic plan to solve the problem of poor planning path effect caused by navigation information delay in the prior art.
[0005] In a first aspect, the present application provides a method for obtaining a traffic plan for an intersection based on vision, comprising:
[0006] Acquire the road condition image outside the target vehicle;
[0007] Inputting the road condition image outside the vehicle into a neural network model, and outputting the estimated travel time of each lane of the road section where the target vehicle is located;
[0008] Based on the estimated passing time of each lane of the road section where the target vehicle is located and the road condition information of the intersection ahead of the target vehicle, a passage plan for the target vehicle to pass the intersection ahead is determined.
[0009] In a possible implementation, the road condition information includes traffic light information at the intersection ahead of the target vehicle, the allowed travel direction of each lane, and the estimated travel time of lanes on other sections except the section where the target vehicle is located;
[0010] The method of determining a traffic plan for the target vehicle to pass through the front intersection based on the estimated travel time of each lane of the road section where the target vehicle is located and the road condition information of the front intersection of the target vehicle includes:
[0011] Determine, based on the navigation path of the target vehicle, the road section that the target vehicle will enter through the front intersection;
[0012] Determine at least one initial traffic plan according to the road section where the target vehicle is located, the road section to be entered, and the allowed traffic direction of the front intersection;
[0013] Determine the estimated travel time of each initial travel plan according to the estimated travel time of the lane corresponding to each initial travel plan and the traffic light information at the intersection ahead;
[0014] A traffic plan for the target vehicle to pass the front intersection is selected based on the estimated travel time of each initial travel plan.
[0015] In a possible implementation, the selecting of a traffic plan for the target vehicle to pass through the front intersection based on the estimated travel time of each initial traffic plan includes:
[0016] The initial traffic plan with the shortest estimated travel time is used as the traffic plan for the target vehicle to pass the front intersection.
[0017] In a possible implementation, the selecting of a traffic plan for the target vehicle to pass through the front intersection based on the estimated travel time of each initial traffic plan includes:
[0018] According to the estimated travel time of each initial travel plan and the driver's operation preference information, a travel plan for the target vehicle to pass the front intersection is selected.
[0019] In a possible implementation, the operation preference information is an operation preference value; and selecting a traffic plan for the target vehicle to pass through the front intersection according to the estimated travel time of each initial traffic plan and the operation preference information of the driver includes:
[0020] Determine the direction of travel of the target vehicle at the front intersection according to the navigation path of the target vehicle; the travel direction includes straight ahead, left turn, right turn and U-turn;
[0021] Count the number of times the driver has executed each initial travel plan for the current direction of travel in the historical time period;
[0022] Determine a corresponding operation preference value based on the number of executions of each initial traffic plan for the current travel direction by the driver in a historical time period; and the number of executions is inversely correlated with the operation preference value;
[0023] The estimated travel time of each initial travel plan and the driver's operation preference value for the corresponding initial travel plan are input into the first formula to obtain a comprehensive evaluation value of each initial travel plan;
[0024] The first formula is:
[0025]
[0026] Wherein, Mi represents the evaluation value of the i-th initial traffic plan, Ti represents the estimated travel time of the i-th initial traffic plan, Ri represents the operation preference value of the i-th initial traffic plan, a and b are weight coefficients respectively, and a+b=1;
[0027] The initial traffic plan with the largest comprehensive evaluation value is used as the traffic plan for the target vehicle to pass the front intersection.
[0028] In a possible implementation, the step of acquiring the road condition image outside the target vehicle includes:
[0029] If it is monitored that the distance between the current position of the target vehicle and the front intersection is less than or equal to a first preset distance, then obtaining an image of the road condition outside the target vehicle;
[0030] Alternatively, if it is monitored that the traffic volume of the road section where the target vehicle is located is greater than a preset traffic volume threshold, an image of the road condition outside the target vehicle is obtained.
[0031] In a possible embodiment, after determining the traffic plan for the target vehicle to pass through the front intersection, the method further includes:
[0032] When the vehicle is in the automatic driving mode, controlling the vehicle to pass through the front intersection according to the traffic plan;
[0033] When the vehicle is in the assisted driving mode, the traffic plan is broadcasted through the navigation system.
[0034] When the vehicle is in the automatic driving mode, controlling the vehicle to pass through the front intersection according to the traffic plan;
[0035] When the vehicle is in the assisted driving mode, the traffic plan is broadcasted through the navigation system.
[0036] In a second aspect, the present application provides a terminal comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein when the processor executes the computer program, the steps of the method described in any possible implementation of the first aspect are implemented.
[0037] In a third aspect, an embodiment of the present application provides a computer-readable storage medium, wherein the computer-readable storage medium stores a computer program, and when the computer program is executed by a processor, the steps of the method described in any possible implementation of the first aspect above are implemented.
[0038] In a fourth aspect, an embodiment of the present application provides a vehicle, comprising the terminal as described in the second aspect above.
[0039] The embodiment of the present application provides a method and related device for obtaining a traffic plan for an intersection based on vision, which first obtains an image of the road condition outside the target vehicle; then inputs the image of the road condition outside the vehicle into a neural network model, and outputs the estimated travel time of each lane of the section where the target vehicle is located; finally, based on the estimated travel time of each lane of the section where the target vehicle is located and the road condition information of the intersection ahead of the target vehicle, determines the traffic plan for the target vehicle to pass through the intersection ahead. This embodiment can determine the traffic plan for the vehicle to pass through the intersection ahead based on the real-time road condition of the section where the vehicle is located, avoids the problem of poor navigation planning path effect caused by information delay, and greatly improves the traffic efficiency of congested intersections. BRIEF DESCRIPTION OF THE DRAWINGS
[0040] In order to more clearly illustrate the technical solutions in the embodiments of the present application, the drawings required for use in the embodiments or the description of the prior art will be briefly introduced below. Obviously, the drawings described below are only some embodiments of the present application. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying creative labor.
[0041] Figure 1 It is a flowchart of the implementation of the method for obtaining a vision-based intersection traffic plan provided in an embodiment of the present application;
[0042] Figure 2 is a schematic diagram of a crossroad provided in an embodiment of the present application;
[0043] Figure 3 It is a structural schematic diagram of a device for acquiring a vision-based intersection traffic plan provided in an embodiment of the present application;
[0044] Figure 4 It is a schematic diagram of a terminal provided in an embodiment of the present application. DETAILED DESCRIPTION
[0045] In the following description, specific details such as specific system structures, technologies, etc. are provided for the purpose of illustration rather than limitation, so as to provide a thorough understanding of the embodiments of the present application. However, it should be clear to those skilled in the art that the present application may also be implemented in other embodiments without these specific details. In other cases, detailed descriptions of well-known systems, devices, circuits, and methods are omitted to prevent unnecessary details from obstructing the description of the present application.
[0046] In order to make the purpose, technical solutions and advantages of the present application clearer, specific embodiments will be described below in conjunction with the accompanying drawings.
[0047] See also Figure 1 , which shows a flowchart of the method for obtaining a vision-based intersection traffic solution provided in an embodiment of the present application, which is described in detail as follows:
[0048] S101: Acquire an image of the road condition outside the target vehicle.
[0049] Specifically, the execution subject of this embodiment may be a vehicle-mounted terminal or other terminal equipment. The solution provided by this embodiment is described below using the vehicle-mounted terminal as an example.
[0050] Specifically, when the vehicle-mounted terminal detects that a vehicle is about to arrive at an intersection, it collects the external road condition images of the section where the target vehicle is located through multiple cameras outside the target vehicle.
[0051] S102: Input the external road condition image into a neural network model, and output the estimated travel time of each lane of the road section where the target vehicle is located.
[0052] Specifically, the neural network model can be a convolutional neural network. After the on-board terminal obtains the image of the road condition outside the vehicle, the image of the road condition outside the vehicle is input into the neural network model. The neural network model identifies the number of lanes in the image and the number of motor vehicles in each lane, and determines the estimated passing time of each lane based on the number of motor vehicles. The more motor vehicles in the lane, the longer the estimated passing time.
[0053] Before executing this method, a training sample set is first created. The training sample is a road image, and the label is the number of lanes in the road image and the estimated travel time of each lane. In this embodiment, the neural network model can be trained through the training sample set.
[0054] S103: Based on the estimated travel time of each lane of the road section where the target vehicle is located and the road condition information of the intersection ahead of the target vehicle, determine a travel plan for the target vehicle to pass through the intersection ahead.
[0055] Normally, the navigation system will use the shortest path as the target to plan the traffic plan at the intersection, such as Figure 2 As shown in the figure, when a vehicle is on section A and is about to enter section B, the traffic plan corresponding to its shortest path is that the vehicle turns left at the intersection ahead and enters section B. However, to enter section B, the target vehicle can also enter section B through the traffic plan of going straight -> turning around -> turning right, or turning right -> going straight -> turning around. When an experienced driver encounters a scene where the current lane at an intersection is crowded with people and other lanes are empty, he will choose other traffic plans to pass the intersection, thereby shortening the time to pass the intersection.
[0056] In this embodiment, the vehicle-mounted terminal determines the section of road that the target is about to enter at the intersection ahead based on the navigation path, determines multiple initial traffic plans for passing the intersection ahead based on the current section, the section to be entered, and the traffic conditions of the intersection ahead, and determines the traffic plan based on the estimated travel time of the section corresponding to each traffic plan.
[0057] In a possible implementation, the road condition information includes traffic light information at the intersection ahead of the target vehicle, the allowed travel direction of each lane, and the estimated travel time of lanes of other sections except the section where the target vehicle is located; the specific implementation process of S103 includes:
[0058] S201: Determine, according to the navigation path of the target vehicle, a road section that the target vehicle will enter after passing through a front intersection;
[0059] S202: Determine at least one initial traffic plan according to the road section where the target vehicle is located, the road section to be entered, and the allowed traffic direction of the front intersection;
[0060] S203: Determine the estimated travel time of each initial travel plan according to the estimated travel time of the lane corresponding to each initial travel plan and the traffic light information at the front intersection;
[0061] S204: Selecting a traffic plan for the target vehicle to pass the intersection ahead based on the estimated travel time of each initial traffic plan.
[0062] Specifically, the vehicle terminal obtains the traffic information of the intersection ahead according to the navigation system. The traffic information may include the color of the traffic light, the remaining time of the current color of the traffic light, the allowed direction of the intersection ahead, etc. Among them, the allowed direction of travel is the direction operation allowed for the vehicle at the intersection, such as left turn, right turn, straight ahead and U-turn. The vehicle terminal determines at least one initial traffic plan according to the section where the target vehicle is located, the section to be entered and the allowed direction of the intersection ahead, and determines the expected travel time of each initial traffic plan according to the expected travel time of the lane involved in each initial traffic plan, the color of the traffic light of the corresponding lane and the remaining time.
[0063] Exemplarily, if an initial traffic plan for the target vehicle passing through the intersection ahead is to go straight, then it is necessary to obtain the traffic light color and remaining time corresponding to the straight lane. If the traffic light color is green, and the remaining time T1 is greater than the estimated travel time T0 of the lane, then the estimated travel time of the "straight" plan is the estimated travel time T0 of the lane where the target vehicle is currently located. If the traffic light color is red, the remaining time is T2, the total travel time when the traffic light color is green is T3, and the estimated travel time T0 of the lane is less than T3, then the estimated travel time of the "straight" plan is T0+T2; if the traffic light color is red, the remaining time is T2, the total travel time when the traffic light color is green is T3, and the estimated travel time T0 of the lane is greater than or equal to T3, then the estimated travel time of the "straight" plan is T0+T2+T3.
[0064] In a possible implementation manner, the specific implementation process of S204 includes:
[0065] The initial traffic plan with the shortest estimated travel time is used as the traffic plan for the target vehicle to pass the front intersection.
[0066] In this embodiment, if the time difference between the initial traffic plan with the shortest estimated passage time and the original traffic plan given by the navigation system is less than or equal to a preset time difference, the original plan will not be changed, and the original traffic plan given by the navigation system will be used as the traffic plan for the target vehicle to pass through the intersection ahead; if the time difference between the initial traffic plan with the shortest estimated passage time and the original traffic plan given by the navigation system is greater than the preset time difference, the initial traffic plan with the shortest estimated passage time will be used as the traffic plan for the target vehicle to pass through the intersection ahead.
[0067] Exemplarily, the preset time difference may be 10s.
[0068] In a possible implementation manner, another specific implementation process of S204 includes:
[0069] According to the estimated travel time of each initial travel plan and the driver's operation preference information, a travel plan for the target vehicle to pass the front intersection is selected.
[0070] In a possible implementation manner, the operation preference information is an operation preference value; the specific implementation process of the above S204 further includes:
[0071] Determine the direction of travel of the target vehicle at the front intersection according to the navigation path of the target vehicle; the travel direction includes straight ahead, left turn, right turn and U-turn;
[0072] Count the number of times the driver has executed each initial travel plan for the current direction of travel in the historical time period;
[0073] Determine a corresponding operation preference value based on the number of executions of each initial traffic plan for the current travel direction by the driver in a historical time period; and the number of executions is inversely correlated with the operation preference value;
[0074] The estimated travel time of each initial travel plan and the driver's operation preference value for the corresponding initial travel plan are input into the first formula to obtain a comprehensive evaluation value of each initial travel plan;
[0075] The first formula is:
[0076]
[0077] Wherein, Mi represents the evaluation value of the i-th initial traffic plan, Ti represents the estimated travel time of the i-th initial traffic plan, Ri represents the operation preference value of the i-th initial traffic plan, a and b are weight coefficients respectively, and a+b=1;
[0078] The initial traffic plan with the largest comprehensive evaluation value is used as the traffic plan for the target vehicle to pass the front intersection.
[0079] In this embodiment, the more times the driver executes a certain initial passage plan, the smaller the operation preference value. Substituting it into the first formula, it can be seen that the smaller the operation preference value, the greater the comprehensive evaluation value of the initial passage plan. In addition, the shorter the estimated passage time of the initial passage plan, the greater the comprehensive evaluation value of the initial passage plan. Therefore, the initial passage plan with the largest comprehensive evaluation value can be selected as the passage plan for the target vehicle to pass through the intersection ahead. This not only takes into account the length of the passage time, but also takes into account the driver's operation preference, providing the best personalized experience.
[0080] In a possible implementation manner, the specific implementation process of S101 includes:
[0081] If it is monitored that the distance between the current position of the target vehicle and the front intersection is less than or equal to a first preset distance, then obtaining an image of the road condition outside the target vehicle;
[0082] Alternatively, if it is monitored that the traffic volume of the road section where the target vehicle is located is greater than a preset traffic volume threshold, an image of the road condition outside the target vehicle is obtained.
[0083] In this embodiment, when it is monitored that the vehicle is about to reach the intersection ahead or encounters congestion, the communication plan for passing the intersection ahead is determined based on the real-time acquired outside vehicle road condition information, which can avoid the problem of poor navigation effect caused by delays in the navigation system and ensure the real-time and accuracy of road condition information. At the same time, this embodiment comprehensively considers the driver's operating preferences, road condition information at the intersection, and the estimated travel time of each lane of the section where the target vehicle is located, etc. to determine the final road condition passage plan, which can not only improve navigation accuracy, but also optimize personal experience.
[0084] Specifically, the first preset distance may be 50m.
[0085] The traffic flow of the road section where the target vehicle is located can be obtained through real-time image recognition of road conditions outside the vehicle, avoiding the delay problem caused by obtaining traffic flow from the navigation system.
[0086] In a possible embodiment, after S103, the method provided in this embodiment further includes:
[0087] When the vehicle is in the automatic driving mode, controlling the vehicle to pass through the front intersection according to the traffic plan;
[0088] When the vehicle is in the assisted driving mode, the traffic plan is broadcasted through the navigation system.
[0089] In this embodiment, if the vehicle is in automatic driving mode, the on-board terminal can automatically control the vehicle's driving according to the final traffic plan so that the vehicle can quickly pass the intersection ahead; when the vehicle is in assisted driving mode, the on-board terminal can broadcast the traffic plan through the navigation system, or display the traffic plan on the on-board display screen, so that the driver can refer to the traffic plan to drive the vehicle through the intersection ahead.
[0090] It can be seen from the above embodiments that the present technical solution optimizes the traditional advance planning navigation and combines real-time visual information with more reasonable operation planning, which can greatly improve the traffic efficiency at congested intersections.
[0091] It should be understood that the size of the serial numbers of the steps in the above embodiments does not mean the order of execution. The execution order of each process should be determined by its function and internal logic, and should not constitute any limitation on the implementation process of the embodiments of the present application.
[0092] The following is an embodiment of the device of the present application. For details not described in detail, please refer to the corresponding method embodiment described above.
[0093] Figure 3 A schematic diagram of the structure of a device for acquiring a vision-based intersection traffic solution provided in an embodiment of the present application is shown. For ease of explanation, only the parts related to the embodiment of the present application are shown, which are described in detail as follows:
[0094] like Figure 3 As shown, the device 100 for acquiring a traffic plan for an intersection based on vision includes:
[0095] An image acquisition module 110 is used to acquire an image of the road condition outside the target vehicle;
[0096] The estimated travel time calculation module 120 is used to input the external road condition image into a neural network model and output the estimated travel time of each lane of the road section where the target vehicle is located;
[0097] The traffic plan determination module 130 is used to determine the traffic plan for the target vehicle to pass the front intersection based on the estimated passing time of each lane of the road section where the target vehicle is located and the road condition information of the front intersection of the target vehicle.
[0098] In a possible implementation, the road condition information includes traffic light information at the intersection ahead of the target vehicle, the allowed travel direction of each lane, and the estimated travel time of lanes of other sections except the section where the target vehicle is located; the traffic plan determination module 130 includes:
[0099] A road section confirmation unit, used to determine the road section that the target vehicle will enter through the front intersection according to the navigation path of the target vehicle;
[0100] An initial plan acquisition unit, used to determine at least one initial traffic plan according to the road section where the target vehicle is located, the road section to be entered and the allowed traffic direction of the front intersection;
[0101] A travel time calculation unit, used to determine the estimated travel time of each initial travel plan according to the estimated travel time of the lane corresponding to each initial travel plan and the traffic light information of the front intersection;
[0102] A traffic plan selection unit is used to select a traffic plan for the target vehicle to pass the front intersection based on the estimated travel time of each initial traffic plan.
[0103] In a possible implementation, the traffic plan selection unit includes:
[0104] The initial traffic plan with the shortest estimated travel time is used as the traffic plan for the target vehicle to pass the front intersection.
[0105] In a possible implementation, the traffic plan selection unit includes:
[0106] According to the estimated travel time of each initial travel plan and the driver's operation preference information, a travel plan for the target vehicle to pass the front intersection is selected.
[0107] In a possible implementation, the operation preference information is an operation preference value; and the traffic plan selection unit specifically includes:
[0108] Determine the direction of travel of the target vehicle at the front intersection according to the navigation path of the target vehicle; the travel direction includes straight ahead, left turn, right turn and U-turn;
[0109] Count the number of times the driver has executed each initial travel plan for the current direction of travel in the historical time period;
[0110] Determine a corresponding operation preference value based on the number of executions of each initial traffic plan for the current travel direction by the driver in a historical time period; and the number of executions is inversely correlated with the operation preference value;
[0111] The estimated travel time of each initial travel plan and the driver's operation preference value for the corresponding initial travel plan are input into the first formula to obtain a comprehensive evaluation value of each initial travel plan;
[0112] The first formula is:
[0113]
[0114] Wherein, Mi represents the evaluation value of the i-th initial traffic plan, Ti represents the estimated travel time of the i-th initial traffic plan, Ri represents the operation preference value of the i-th initial traffic plan, a and b are weight coefficients respectively, and a+b=1;
[0115] The initial traffic plan with the largest comprehensive evaluation value is used as the traffic plan for the target vehicle to pass the front intersection.
[0116] In a possible implementation, the image acquisition module 110 includes:
[0117] If it is monitored that the distance between the current position of the target vehicle and the front intersection is less than or equal to a first preset distance, then obtaining an image of the road condition outside the target vehicle;
[0118] Alternatively, if it is monitored that the traffic volume of the road section where the target vehicle is located is greater than a preset traffic volume threshold, an image of the road condition outside the target vehicle is obtained.
[0119] In a possible embodiment, the device for acquiring a traffic plan for an intersection based on vision further includes a traffic control module, which is used to:
[0120] When the vehicle is in the automatic driving mode, controlling the vehicle to pass through the front intersection according to the traffic plan;
[0121] When the vehicle is in the assisted driving mode, the traffic plan is broadcasted through the navigation system.
[0122] The vision-based intersection traffic plan acquisition device provided in the embodiment of the present application first acquires the road condition image outside the target vehicle; then the road condition image outside the vehicle is input into the neural network model, and the estimated travel time of each lane of the section where the target vehicle is located is output; finally, based on the estimated travel time of each lane of the section where the target vehicle is located and the road condition information of the intersection ahead of the target vehicle, the traffic plan of the target vehicle passing through the intersection ahead is determined. This embodiment can determine the traffic plan of the vehicle passing through the intersection ahead based on the real-time road condition of the section where the vehicle is located, avoid the problem of poor navigation planning path effect caused by information delay, and greatly improve the traffic efficiency of congested intersections.
[0123] The present application also provides a computer program product having a program code, which executes the steps of any of the above-mentioned methods for obtaining a vision-based intersection traffic plan when the program code is run in a corresponding processor, controller, computing device or terminal, such as Figure 1 Steps S101 to S103 shown. It will be appreciated by those skilled in the art that the method and the device proposed in the embodiment of the present application can be implemented in various forms of hardware, software, firmware, a dedicated processor or a combination thereof. The dedicated processor may include an application specific integrated circuit (ASIC), a reduced instruction set computer (RISC) and / or a field programmable gate array (FPGA). The proposed method and device are preferably implemented as a combination of hardware and software. The software is preferably installed on a program storage device as an application. It is typically based on a machine with a computer platform having hardware, such as one or more central processing units (CPUs), random access memories (RAMs) and one or more input / output (I / O) interfaces. An operating system is typically also installed on the computer platform. The various processes and functions described herein may be part of an application, or a part thereof may be executed by an operating system.
[0124] Figure 4 is a schematic diagram of a terminal provided in an embodiment of the present application. Figure 4 As shown, the terminal 4 of this embodiment includes: a processor 40, a memory 41, and a computer program 42 stored in the memory 41 and executable on the processor 40. When the processor 40 executes the computer program 42, the steps in the above-mentioned various vision-based intersection traffic scheme acquisition method embodiments are implemented, for example Figure 1 Alternatively, when the processor 40 executes the computer program 42, the functions of each module / unit in the above-mentioned device embodiments are realized, for example Figure 3 The functions of the modules 110 to 130 are shown.
[0125] Exemplarily, the computer program 42 may be divided into one or more modules / units, which are stored in the memory 41 and executed by the processor 40 to complete / implement the solution provided by the present application. The one or more modules / units may be a series of computer program instruction segments capable of completing specific functions, which are used to describe the execution process of the computer program 42 in the terminal 4.
[0126] The terminal 4 may be a computing device such as a desktop computer, a notebook, a PDA, or a cloud server. The terminal 4 may include, but is not limited to, a processor 40 and a memory 41. Those skilled in the art will appreciate that Figure 4 It is only an example of terminal 4 and does not constitute a limitation on terminal 4. It may include more or fewer components than shown in the figure, or a combination of certain components, or different components. For example, the terminal may also include input and output devices, network access devices, buses, etc.
[0127] The processor 40 may be a central processing unit (CPU), or other general-purpose processors, digital signal processors (DSP), application-specific integrated circuits (ASIC), field-programmable gate arrays (FPGA) or other programmable logic devices, discrete gate or transistor logic devices, discrete hardware components, etc. A general-purpose processor may be a microprocessor or any conventional processor, etc.
[0128] The memory 41 may be an internal storage unit of the terminal 4, such as a hard disk or memory of the terminal 4. The memory 41 may also be an external storage device of the terminal 4, such as a plug-in hard disk, a smart media card (SMC), a secure digital (SD) card, a flash card, etc. equipped on the terminal 4. Further, the memory 41 may also include both an internal storage unit and an external storage device of the terminal 4. The memory 41 is used to store the computer program and other programs and data required by the terminal. The memory 41 may also be used to temporarily store data that has been output or is to be output.
[0129] An embodiment of the present application provides a vehicle, comprising the terminal 4 as described above.
[0130] The technicians in the relevant field can clearly understand that for the convenience and simplicity of description, only the division of the above-mentioned functional units and modules is used as an example for illustration. In practical applications, the above-mentioned function allocation can be completed by different functional units and modules as needed, that is, the internal structure of the device can be divided into different functional units or modules to complete all or part of the functions described above. The functional units and modules in the embodiment can be integrated in a processing unit, or each unit can exist physically separately, or two or more units can be integrated in one unit. The above-mentioned integrated unit can be implemented in the form of hardware or in the form of software functional units. In addition, the specific names of the functional units and modules are only for the convenience of distinguishing each other, and are not used to limit the scope of protection of this application. The specific working process of the units and modules in the above-mentioned system can refer to the corresponding process in the aforementioned method embodiment, which will not be repeated here.
[0131] In the above embodiments, the description of each embodiment has its own emphasis. For parts that are not described or recorded in detail in a certain embodiment, reference can be made to the relevant descriptions of other embodiments.
[0132] Those of ordinary skill in the art will appreciate that the units and algorithm steps of each example described in conjunction with the embodiments disclosed herein can be implemented in electronic hardware, or a combination of computer software and electronic hardware. Whether these functions are performed in hardware or software depends on the specific application and design constraints of the technical solution. Professional and technical personnel can use different methods to implement the described functions for each specific application, but such implementation should not be considered to be beyond the scope of this application.
[0133] In the embodiments provided in the present application, it should be understood that the disclosed devices / terminals and methods can be implemented in other ways. For example, the device / terminal embodiments described above are only schematic. For example, the division of the modules or units is only a logical function division. There may be other division methods in actual implementation, such as multiple units or components can be combined or integrated into another system, or some features can be ignored or not executed. Another point is that the mutual coupling or direct coupling or communication connection shown or discussed can be through some interfaces, indirect coupling or communication connection of devices or units, which can be electrical, mechanical or other forms.
[0134] The units described as separate components may or may not be physically separated, and the components shown as units may or may not be physical units, that is, they may be located in one place or distributed on multiple network units. Some or all of the units may be selected according to actual needs to achieve the purpose of the solution of this embodiment.
[0135] In addition, each functional unit in each embodiment of the present application may be integrated into one processing unit, or each unit may exist physically separately, or two or more units may be integrated into one unit. The above-mentioned integrated unit may be implemented in the form of hardware or in the form of software functional units.
[0136] If the integrated module / unit is implemented in the form of a software functional unit and sold or used as an independent product, it can be stored in a computer-readable storage medium. Based on this understanding, the present application implements all or part of the processes in the above-mentioned embodiment method, and can also be completed by instructing the relevant hardware through a computer program. The computer program can be stored in a computer-readable storage medium. When the computer program is executed by the processor, it can implement the steps of the above-mentioned various vision-based intersection traffic scheme acquisition method embodiments. Among them, the computer program includes computer program code, and the computer program code can be in source code form, object code form, executable file or some intermediate form. The computer-readable medium may include: any entity or device that can carry the computer program code, recording medium, U disk, mobile hard disk, disk, optical disk, computer memory, read-only memory (ROM), random access memory (RAM), electrical carrier signal, telecommunication signal and software distribution medium. It should be noted that the content contained in the computer-readable medium can be appropriately increased or decreased according to the requirements of legislation and patent practices in the jurisdiction. For example, in some jurisdictions, according to legislation and patent practices, computer-readable media does not include electrical carrier signals and telecommunication signals.
[0137] In addition, the embodiments shown in the drawings of the present application or the features of the various embodiments mentioned in this specification are not necessarily understood as independent embodiments. Instead, each feature described in one example of an embodiment can be combined with one or more other desired features from other embodiments to produce other embodiments not described in words or with reference to the drawings.
[0138] The embodiments described above are only used to illustrate the technical solutions of the present application, rather than to limit them. Although the present application has been described in detail with reference to the aforementioned embodiments, a person skilled in the art should understand that the technical solutions described in the aforementioned embodiments may still be modified, or some of the technical features may be replaced by equivalents. Such modifications or replacements do not deviate the essence of the corresponding technical solutions from the spirit and scope of the technical solutions of the embodiments of the present application, and should all be included in the protection scope of the present application.
Claims
1. A method for obtaining a traffic plan at an intersection based on vision, characterized in that: include: Acquire the road condition image outside the target vehicle; Input the road condition image outside the vehicle into a neural network model, and output the estimated travel time of each lane of the road section where the target vehicle is located; Determine a traffic plan for the target vehicle to pass the intersection ahead based on the estimated travel time of each lane of the road section where the target vehicle is located and the road condition information of the intersection ahead of the target vehicle; The road condition information includes the traffic light information at the intersection ahead of the target vehicle, the allowed travel direction of each lane, and the estimated travel time of lanes in other sections except the section where the target vehicle is located; The method of determining a traffic plan for the target vehicle to pass through the front intersection based on the estimated travel time of each lane of the road section where the target vehicle is located and the road condition information of the front intersection of the target vehicle includes: Determine, based on the navigation path of the target vehicle, the road section that the target vehicle will enter through the front intersection; Determine at least one initial traffic plan according to the road section where the target vehicle is located, the road section to be entered, and the allowed traffic direction of the front intersection; Determine the estimated travel time of each initial travel plan according to the estimated travel time of the lane corresponding to each initial travel plan and the traffic light information at the front intersection; Selecting a traffic plan for the target vehicle to pass the intersection ahead based on the estimated travel time of each initial traffic plan; The method of selecting a traffic plan for the target vehicle to pass through the front intersection based on the estimated traffic time of each initial traffic plan includes: Determine the direction of travel of the target vehicle at the front intersection according to the navigation path of the target vehicle; the travel direction includes straight ahead, left turn, right turn and U-turn; Count the number of times the driver has executed each initial travel plan for the current direction of travel in the historical time period; Determine a corresponding operation preference value based on the number of executions of each initial traffic plan for the current travel direction by the driver in a historical time period; and the number of executions is inversely correlated with the operation preference value; The estimated travel time of each initial travel plan and the driver's operation preference value for the corresponding initial travel plan are input into the first formula to obtain a comprehensive evaluation value of each initial travel plan; The first formula is: Wherein, Mi represents the evaluation value of the i-th initial traffic plan, Ti represents the estimated travel time of the i-th initial traffic plan, Ri represents the operation preference value of the i-th initial traffic plan, a and b are weight coefficients respectively, and a+b=1; The initial traffic plan with the largest comprehensive evaluation value is used as the traffic plan for the target vehicle to pass the front intersection.
2. The method for obtaining a vision-based intersection traffic plan according to claim 1, characterized in that: The method of selecting a traffic plan for the target vehicle to pass through the front intersection based on the estimated traffic time of each initial traffic plan includes: The initial traffic plan with the shortest estimated travel time is used as the traffic plan for the target vehicle to pass the front intersection.
3. The method for obtaining a vision-based intersection traffic plan according to claim 1, characterized in that: The step of obtaining the road condition image outside the target vehicle includes: If it is monitored that the distance between the current position of the target vehicle and the front intersection is less than or equal to a first preset distance, then obtaining an image of the road condition outside the target vehicle; Alternatively, if it is monitored that the traffic volume of the road section where the target vehicle is located is greater than a preset traffic volume threshold, an image of the road condition outside the target vehicle is obtained.
4. The method for obtaining a vision-based intersection traffic plan according to claim 1, characterized in that: After determining the traffic plan for the target vehicle to pass the front intersection, the method further includes: When the vehicle is in the automatic driving mode, controlling the vehicle to pass through the front intersection according to the traffic plan; When the vehicle is in the assisted driving mode, the traffic plan is broadcasted through the navigation system.
5. A terminal comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, characterized in that: When the processor executes the computer program, the steps of the method for acquiring a vision-based intersection traffic plan as described in any one of claims 1 to 4 above are implemented.
6. A computer-readable storage medium storing a computer program, characterized in that: When the computer program is executed by a processor, the steps of the method for acquiring a vision-based intersection traffic plan as described in any one of claims 1 to 4 above are implemented.
7. A vehicle, characterized in that: Comprising the terminal as claimed in claim 5.
