WO2023029468A1 - 车辆行驶提示 - Google Patents
车辆行驶提示 Download PDFInfo
- Publication number
- WO2023029468A1 WO2023029468A1 PCT/CN2022/084330 CN2022084330W WO2023029468A1 WO 2023029468 A1 WO2023029468 A1 WO 2023029468A1 CN 2022084330 W CN2022084330 W CN 2022084330W WO 2023029468 A1 WO2023029468 A1 WO 2023029468A1
- Authority
- WO
- WIPO (PCT)
- Prior art keywords
- target vehicle
- target
- vehicle
- state information
- target object
- Prior art date
Links
- 238000000034 method Methods 0.000 claims abstract description 46
- 238000004590 computer program Methods 0.000 claims description 10
- 238000004891 communication Methods 0.000 claims description 4
- 238000001514 detection method Methods 0.000 description 22
- 238000003062 neural network model Methods 0.000 description 9
- 230000008569 process Effects 0.000 description 6
- 238000012545 processing Methods 0.000 description 5
- 238000010586 diagram Methods 0.000 description 4
- 230000006870 function Effects 0.000 description 4
- 238000003384 imaging method Methods 0.000 description 4
- 230000008878 coupling Effects 0.000 description 3
- 238000010168 coupling process Methods 0.000 description 3
- 238000005859 coupling reaction Methods 0.000 description 3
- 230000003068 static effect Effects 0.000 description 3
- 238000005516 engineering process Methods 0.000 description 2
- 238000012216 screening Methods 0.000 description 2
- 230000009286 beneficial effect Effects 0.000 description 1
- 238000004364 calculation method Methods 0.000 description 1
- 230000007547 defect Effects 0.000 description 1
- 230000000694 effects Effects 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 230000003287 optical effect Effects 0.000 description 1
- 238000011160 research Methods 0.000 description 1
- 230000001629 suppression Effects 0.000 description 1
Images
Classifications
-
- B—PERFORMING OPERATIONS; TRANSPORTING
- B60—VEHICLES IN GENERAL
- B60Q—ARRANGEMENT OF SIGNALLING OR LIGHTING DEVICES, THE MOUNTING OR SUPPORTING THEREOF OR CIRCUITS THEREFOR, FOR VEHICLES IN GENERAL
- B60Q9/00—Arrangement or adaptation of signal devices not provided for in one of main groups B60Q1/00 - B60Q7/00, e.g. haptic signalling
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N3/00—Computing arrangements based on biological models
- G06N3/02—Neural networks
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N3/00—Computing arrangements based on biological models
- G06N3/02—Neural networks
- G06N3/08—Learning methods
Definitions
- the present disclosure relates to the technical field of image processing, and in particular, to a vehicle driving prompt method, device, electronic equipment, and storage medium.
- the automatic reminder technology for vehicle running status adjustment can automatically remind the driver to adjust the running status of the vehicle to avoid collisions, congestion, etc. congestion.
- the automatic reminder technology for vehicle operation status adjustment is generally implemented based on millimeter-wave radar, which has low detection accuracy for vehicles and other objects, resulting in low accuracy in prompting vehicles to adjust their operation status.
- Embodiments of the present disclosure at least provide a vehicle driving prompt method, device, electronic equipment, and computer-readable storage medium.
- an embodiment of the present disclosure provides a vehicle driving prompt method, including: acquiring at least one driving image related to the target vehicle; identifying the driving image, and determining the target that affects the running state of the target vehicle The state information of the object; based on the state information of the target object and the current running state information of the target vehicle, prompting the target vehicle to adjust the running state.
- the present disclosure provides a vehicle driving prompt device, including: an image acquisition module, used for at least one driving image related to the target vehicle; a state recognition module, used for identifying the driving image and determining the impact The state information of the target object of the running state of the target vehicle; a prompting module, configured to prompt the target vehicle to adjust the running state based on the state information of the target object and the current running state information of the target vehicle.
- an embodiment of the present disclosure further provides an electronic device, including: a processor, a memory, and a bus, the memory stores machine-readable instructions executable by the processor, and when the electronic device is running, the processing
- the processor communicates with the memory through a bus, and when the machine-readable instructions are executed by the processor, the above-mentioned first aspect, or the steps in any possible implementation manner of the first aspect are executed.
- embodiments of the present disclosure further provide a computer-readable storage medium, on which a computer program is stored, and when the computer program is executed by a processor, the above-mentioned first aspect, or any of the first aspects of the first aspect, may be executed. Steps in one possible implementation.
- FIG. 1 shows a flow chart of a vehicle driving prompt method provided by an embodiment of the present disclosure
- Fig. 2 shows a flow chart of identifying the driving image and determining the state information of the target object that affects the running state of the target vehicle in another vehicle driving prompt method provided by an embodiment of the present disclosure
- Fig. 3 shows a schematic diagram of a vehicle driving prompt device provided by an embodiment of the present disclosure
- Fig. 4 shows a schematic diagram of an electronic device provided by an embodiment of the present disclosure.
- the present disclosure provides a vehicle driving prompt method, device, Electronic devices and computer-readable storage media, the present disclosure can accurately identify the target object that affects the running state of the target vehicle by processing the driving image related to the target vehicle, and determine the state information of the target object, and then use the target object
- the state information of the target vehicle can accurately prompt the operating state of the target vehicle to be adjusted, which not only improves the accuracy of prompting the adjustment of the vehicle operating state, but also improves the driving safety of the vehicle.
- the vehicle driving prompt method provided by the embodiment of the present disclosure will be described below by taking the executing subject as a device with computing capability as an example.
- the vehicle driving prompt method provided by the present disclosure may include the following steps:
- the above-mentioned driving image can be an image taken by a camera installed on the target vehicle, an image taken by an imaging device near the target vehicle, and the imaging equipment near the target vehicle includes a camera installed on the side of the road, and other vehicles near the target vehicle. camera etc. If the driving image is an image captured by a camera installed on the target vehicle, the driving image does not include the target vehicle, but only includes a plurality of objects near the target vehicle. If the driving image is an image captured by an imaging device near the target vehicle, the driving image may include the target vehicle and/or multiple objects around the target vehicle.
- the aforementioned objects may be objects such as pedestrians, vehicles, traffic lights, and non-motorized vehicles.
- the aforementioned target object affecting the running state of the target vehicle may be an object adjacent to the target vehicle and located in front of the target vehicle, or may be a traffic signal light located in front of the target vehicle.
- the state information may be the running state information of the target object.
- the state information of the target object may indicate that the target object starts to move from a standstill, the target object moves from an adjacent lane into the lane where the target vehicle is located, and the target object moves out of the lane where the target vehicle is currently located. wait.
- the target object is a traffic signal light located in front of the target vehicle
- a currently acquired driving image of the target object can be identified, so as to determine the state information of the target object.
- the status information at this time can be the color information of the target object.
- the status information of the target object can include that the target object is red, green or yellow; when the status information of the target object includes that the target object is green, the status information of the target object indicates The target vehicle can pass, and when the state information of the target object includes that the target object is red or yellow, the state information of the target object indicates that the target vehicle is prohibited from passing.
- the above current running state information of the target vehicle may include the current speed of the target vehicle and the like. Before performing this step, the current speed of the target vehicle can be obtained. When obtaining the current vehicle speed of the target vehicle, it can be determined by the information in the CAN (Controller Area Network) bus of the target vehicle itself, or by a plurality of consecutive images including the target vehicle, wherein the above-mentioned continuous images include The last image of the images of the target vehicle may be a currently captured image.
- CAN Controller Area Network
- this step combining the current state information of the target object and the current running state information of the target vehicle, it can be determined whether the target object affects the current running state of the target vehicle, and when it is determined that the target object affects the current running state of the target vehicle, prompt The target vehicle adjusts an operating state.
- the recognition of the driving image mentioned in this article can specifically use the trained neural network model to recognize the driving image, determine the target object and the state information of the target object, this method can improve the accuracy of identifying the target object, and the determined state Accuracy of Information.
- the state information of the target object can be used to accurately prompt the target vehicle to adjust the running state, which not only improves the accuracy of prompting the vehicle to adjust the running state, but also improves the safety of the vehicle.
- the state information of the target object includes the running state information of the target object
- the above-mentioned Recognizing the driving image and determining the state information of the target object that affects the running state of the target vehicle can be specifically achieved by the following steps:
- S210 Recognize each of the driving images respectively, and determine position information of objects in each driving image.
- each driving image can be input into the trained neural network model, and the input driving image can be processed by the neural network model, and the information of each object in the driving image can be output, and the information of each object can include a detection frame, The position information of each detection frame, the confidence degree of each detection frame, the type of each detection frame and other information.
- non-maximum value suppression can be added to eliminate redundant detection frames, and the detection frame with the highest confidence degree can be determined as the detection frame of the corresponding object.
- the detection frame in each driving image is matched with the object, and the object existing in at least two driving images at the same time is determined according to the matching result.
- the position information of the object in the physical world obtained through the matching is determined.
- the driving image can be taken by a camera installed on the target vehicle.
- the driving image does not include the target vehicle, and only includes objects in front of the target vehicle. Therefore, the above steps can be directly used to determine The position information of the object in the physical world that exists in at least two driving images at the same time.
- the driving image may also be an image taken by an imaging device near the target vehicle. In this embodiment, the driving image includes the target vehicle and multiple objects around the target vehicle.
- the trained neural network model determines the detection frame of the target vehicle and the detection frames of other objects, and based on the position of the detection frame of the target vehicle and the positions of the detection frames of each other object, filter out the objects located in front of the target vehicle Then match the detection frames of other objects in each driving image with the objects in the other objects, and determine the objects that simultaneously exist in at least two driving images according to the matching results. Finally, according to the internal and external parameter calibration information of the camera that captures the driving image and the position of the object in the driving image obtained through the matching, the position information of the object in the physical world obtained through the matching is determined.
- the aforementioned target objects include objects located in front of the target vehicle and in the same lane as the target vehicle, and objects located in front of the target vehicle and in a lane adjacent to the lane where the target vehicle is located.
- Sub-step 1 For each driving image, identify the driving image, and determine the position information of each lane line in the driving image.
- the trained neural network model can also be used to process the driving image to obtain information such as the detection frame of each object, and then determine the detection frame belonging to the lane line based on the type of the detection frame. After that, according to the internal and external parameter calibration information of the camera that captures the driving image and the position of the lane line in the driving image, the position information of the lane line in the physical world is determined.
- Sub-step 2 Based on the position information of each object in the driving image and the position information of each lane line in the driving image, determine the first lane where each object is located.
- Sub-step 3 Determine the second lane where the target vehicle is located.
- the trained neural network model can be used to process the driving image, determine the position information of the target vehicle, and then determine the second lane where the target vehicle is located according to the position information of the target vehicle and the position information of each lane line.
- the driving image is an image captured by a camera installed on the target vehicle
- the position information of the target vehicle may be the position information of the camera installed on the target vehicle.
- Sub-step 4 Based on the second lane where the target vehicle is located and the first lane where each object is located, select from each object those that are adjacent to the target vehicle and located in the same lane as the target vehicle, and a target object located in front of the target vehicle.
- the above sub-steps can accurately determine the target object adjacent to the target vehicle, in the same lane as the target vehicle, and in front of the target vehicle by identifying and locating each lane line in the driving image.
- the operating state of the vehicle has a direct impact, therefore, accurately identifying the target object is conducive to improving the accuracy of prompting the adjustment of the operating state of the vehicle.
- the following sub-steps can be used to filter the target object:
- Sub-step 1 For each driving image, identify the driving image, and determine the position information of each lane line in the driving image.
- Sub-step 2 Based on the position information of each object in the driving image and the position information of each lane line in the driving image, determine the first lane where each object is located.
- Sub-step 3 Determine the second lane where the target vehicle is located.
- Sub-step 4 Based on the second lane where the target vehicle is located and the first lane where each object is located, select from each object those that are adjacent to the target vehicle and that are located adjacent to the lane where the target vehicle is located. A target object within a lane and located in front of the target vehicle.
- the motion state information of the above-mentioned target object may include a starting state, a cut-in state, a cut-out state, a static state, and the like. Specifically, according to the position information of the target object, when it is determined that the target object starts to move from stillness, the motion state information of the target object is the start state; when according to the position information of the target object, it is determined that the target object moves into the When the target vehicle is in the lane, the motion state information of the target object is cut-in state; when the target object is determined to move from the lane where the target vehicle is located to the adjacent lane according to the position information of the target object, the motion state information of the target object is cut-out State: when it is determined that the position of the target object has not changed according to the position information of the target object, the motion state information of the target object is a static state.
- the position information of each object can be accurately determined, based on the position information of each object, the target object that has an impact on the running state of the target vehicle can be accurately screened out, and at the same time, based on the position information of each object, it can be accurately Determine the running status information of the target object.
- Accurately obtaining the running state information of the target object and the location information of the target object is beneficial to improving the accuracy of reminding the vehicle to adjust the running state.
- the target object When the target object is adjacent to the target vehicle, in the same lane as the target vehicle and in front of the target vehicle, if the running state information of the target object indicates that the target object starts to move from a standstill, that is, the running state information of the target object is in an active state, And the current running status information of the target vehicle indicates that the current speed of the target vehicle is zero, and at this time, the target vehicle needs to be prompted to start driving, that is, the target vehicle needs to be reminded to follow up.
- the running state information of the target object located directly in front of the target vehicle's running direction it can be determined whether the target object located directly in front of the target vehicle's running direction is activated. Accurate follow-up reminders for vehicles can also improve the traffic efficiency of target vehicles and help avoid or relieve road congestion.
- the distance information between the target object and the target vehicle may include the distance between the target object and the target vehicle.
- the distance of the vehicle, the movement distance of the target object from rest to movement, etc. can be used to determine whether to issue a follow-up reminder to the target vehicle:
- the target vehicle Based on the position information of the target object in each driving image and the position information of the target vehicle, determine the distance information between the target object and the target vehicle; where the distance information indicates the distance between the target object and the When the minimum distance of the target vehicle is greater than the first distance threshold, the running state information of the target object indicates that the target object starts to move from rest and the moving distance is greater than the second distance threshold, and the current speed of the target vehicle is zero, To prompt the target vehicle to start driving, that is, to issue a follow-up reminder to the target vehicle.
- the minimum distance between the target object and the target vehicle may refer to the minimum distance between the rear end of the target object and the front end of the target vehicle when the target object is located directly in front of the target vehicle running direction.
- the moving distance refers to the running distance of the target object starting to move from a static state.
- determining the distance information between the target object and the target vehicle it may specifically be determined by determining the position information of the target object and the position information of the target vehicle according to the above embodiments.
- the above-mentioned first distance threshold and second distance threshold can be flexibly set according to actual application scenarios, for example, the second distance threshold can be set to 3 meters, and the first distance threshold can be set to 20 meters.
- a parameter setting page can also be set, and the user can set or modify the above-mentioned first distance threshold and the second distance threshold on the parameter setting page.
- the target vehicle When the target object and the target vehicle are in the same lane, if the running state information of the target object indicates that the target object moves out of the current lane, that is, the running state information of the target object is a cut-out state, and the current speed of the target vehicle is less than a preset If the vehicle speed threshold is exceeded, the target vehicle is prompted to increase its driving speed.
- the above method sends a speed-up reminder to the target vehicle, and in practical applications, the user can also set or modify the above-mentioned preset vehicle speed threshold in the parameter setting page.
- prompting the target vehicle to increase the driving speed not only improves the accuracy of prompting the vehicle to adjust the running state, but also helps to improve the traffic efficiency of the target vehicle.
- the target vehicle When the target object is located in the adjacent lane of the lane where the target vehicle is located, if the operating state information of the target object indicates that the target object moves from the adjacent lane to the lane where the target vehicle is located, that is, the operating state of the target object If the information is in the cut-in state, and the speed of the target object is lower than the current speed of the target vehicle, then the target vehicle is prompted to reduce the driving speed.
- the above method sends a speed-down reminder to the target vehicle.
- the target object moves into the lane where the target vehicle is located from other lanes, and the speed of the target object is lower than the speed of the target vehicle, prompting the target vehicle to reduce the driving speed not only improves the accuracy of prompting the vehicle to adjust its running state, but also facilitates Improve the operational safety of the target vehicle.
- the target object can also be a traffic signal light located in front of the target vehicle, at this time, the following steps can be used to prompt the target vehicle to adjust its running state:
- the traffic signal light When the current speed of the target vehicle is zero and the status information of the traffic signal light indicates that the vehicle can pass, that is, the traffic signal light is green, prompting the target vehicle to start driving.
- the trained neural network model can also be used to process the driving image, and according to the type of the obtained detection frame, the object belonging to the traffic signal type can be determined, and by extracting the features of the pixels of the traffic lights in the driving image, Determine the color of the traffic light, that is, determine the status information of the traffic light.
- the trained neural network model to detect the state information of traffic lights improves the detection accuracy.
- the above method combined with the status information of the traffic signal light can accurately follow the target vehicle to remind the target vehicle, which not only improves the accuracy of prompting the vehicle to adjust the running state, but also helps to improve the traffic efficiency of the target vehicle.
- the trained neural network model is used to detect each object in the driving image and determine the state information of each object, which effectively improves the accuracy of object detection and the accuracy of the determined state information.
- parameters such as the first distance threshold and the second distance threshold can be flexibly changed, which realizes the flexible prompting of the target vehicle to adjust the running state and improves the user experience.
- the writing order of each step does not mean a strict execution order and constitutes any limitation on the implementation process.
- the specific execution order of each step should be based on its function and possible
- the inner logic is OK.
- the embodiment of the present disclosure also provides a vehicle driving prompting device corresponding to the vehicle driving prompting method. Since the problem-solving principle of the device in the present disclosure embodiment is similar to the above-mentioned vehicle driving prompting method in the present disclosure embodiment, therefore For the implementation of the device, reference may be made to the implementation of the method, and repeated descriptions will not be repeated.
- FIG. 3 it is a schematic structural diagram of a vehicle driving prompt device provided by an embodiment of the present disclosure.
- the device includes:
- An image acquisition module 310 configured to acquire at least one driving image related to the target vehicle.
- the state identification module 320 is configured to identify the driving image and determine the state information of the target object that affects the running state of the target vehicle.
- the prompt module 330 is configured to prompt the target vehicle to adjust the running state based on the state information of the target object and the current running state information of the target vehicle.
- the target object includes an object adjacent to the target vehicle and located in front of the target vehicle; the state information of the target object includes operating state information of the target object;
- the state identification module 320 identifies the driving image and determines the state information of the target object that affects the running state of the target vehicle, it is used to:
- each object Based on the determined position information of each object, select from each object a target object that is adjacent to the target vehicle and located in front of the target vehicle;
- the running state information of the target object is determined by using the position information of the target object in at least two driving images.
- the target object includes an object located in the same lane as the target vehicle
- the state identification module 320 is configured to: when screening target objects adjacent to the target vehicle and located in front of the target vehicle from various objects based on the determined position information of each object:
- For each driving image identify the driving image, and determine the position information of each lane line in the driving image;
- the current running state information of the target vehicle includes the current speed of the target vehicle
- the prompting module 330 is configured to: when prompting the target vehicle to adjust the running state based on the state information of the target object and the current running state information of the target vehicle:
- the prompt module 330 indicates that the target object starts to move from a standstill when the running state information of the target object indicates that the target vehicle's current running state information indicates that the current speed of the target vehicle is zero. In the case of prompting the target vehicle to start driving, it is also used for:
- the running state information of the target object indicates that the target object starts to move from rest and the moving distance is greater than a second distance threshold
- the current running state information of the target vehicle includes the current speed of the target vehicle
- the prompting module 330 is configured to: when prompting the target vehicle to adjust the running state based on the state information of the target object and the current running state information of the target vehicle:
- the target object includes an object located in a lane adjacent to the lane where the target vehicle is located; the current running state information of the target vehicle includes the current speed of the target vehicle;
- the prompting module 330 is configured to: when prompting the target vehicle to adjust the running state based on the state information of the target object and the current running state information of the target vehicle:
- the running state information of the target object indicates that the target object moves into the lane where the target vehicle is located from a lane adjacent to the lane where the target vehicle is located, and the speed of the target object is less than the current speed of the target vehicle If the vehicle speed is low, prompt the target vehicle to reduce the driving speed.
- the target object includes a traffic signal light;
- the current running state information of the target vehicle includes the current speed of the target vehicle;
- the prompting module 330 is configured to: when prompting the target vehicle to adjust the running state based on the state information of the target object and the current running state information of the target vehicle:
- an embodiment of the present disclosure also provides an electronic device.
- FIG. 4 it is a schematic structural diagram of an electronic device 400 provided by an embodiment of the present disclosure, including a processor 41 , a memory 42 , and a bus 43 .
- the memory 42 is used to store execution instructions, including a memory 421 and an external memory 422; the memory 421 here is also called an internal memory, and is used to temporarily store the calculation data in the processor 41 and the data exchanged with the external memory 422 such as a hard disk,
- the processor 41 exchanges data with the external memory 422 through the memory 421.
- the processor 41 communicates with the memory 42 through the bus 43, so that the processor 41 executes the following instructions:
- Acquire at least one driving image related to the target vehicle identify the driving image, and determine the state information of the target object that affects the running state of the target vehicle; based on the state information of the target object and the current state of the target vehicle running state information, prompting the target vehicle to adjust the running state.
- Embodiments of the present disclosure further provide a computer-readable storage medium, on which a computer program is stored, and when the computer program is run by a processor, the steps of the vehicle driving prompt method described in the above-mentioned method embodiments are executed.
- the storage medium may be a volatile or non-volatile computer-readable storage medium.
- the computer program product of the vehicle driving prompt method provided by the embodiments of the present disclosure includes a computer-readable storage medium storing program codes, and the instructions included in the program code can be used to execute the vehicle driving prompt method described in the above method embodiments
- the computer program product can be specifically realized by means of hardware, software or a combination thereof.
- the computer program product is embodied as a computer storage medium, and in another optional embodiment, the computer program product is embodied as a software product, such as a software development kit (Software Development Kit, SDK) etc. wait.
- 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 may be distributed to multiple network units. Part or all of the units can be selected according to actual needs to achieve the purpose of the solution of this embodiment.
- each functional unit in each embodiment of the present disclosure may be integrated into one processing unit, each unit may exist separately physically, or two or more units may be integrated into one unit.
- the functions are realized in the form of software function units and sold or used as independent products, they can be stored in a non-volatile computer-readable storage medium executable by a processor.
- the technical solution of the present disclosure is essentially or the part that contributes to the prior art or the part of the technical solution can be embodied in the form of a software product, and the computer software product is stored in a storage medium, including Several instructions are used to make a computer device (which may be a personal computer, a server, or a network device, etc.) execute all or part of the steps of the methods described in various embodiments of the present disclosure.
- the aforementioned storage media include: U disk, mobile hard disk, read-only memory (Read-Only Memory, ROM), random access memory (Random Access Memory, RAM), magnetic disk or optical disc and other media that can store program codes. .
Landscapes
- Engineering & Computer Science (AREA)
- Theoretical Computer Science (AREA)
- Physics & Mathematics (AREA)
- General Health & Medical Sciences (AREA)
- Computing Systems (AREA)
- Biomedical Technology (AREA)
- Biophysics (AREA)
- Computational Linguistics (AREA)
- Data Mining & Analysis (AREA)
- Evolutionary Computation (AREA)
- Life Sciences & Earth Sciences (AREA)
- Molecular Biology (AREA)
- Artificial Intelligence (AREA)
- General Engineering & Computer Science (AREA)
- General Physics & Mathematics (AREA)
- Mathematical Physics (AREA)
- Software Systems (AREA)
- Health & Medical Sciences (AREA)
- Human Computer Interaction (AREA)
- Mechanical Engineering (AREA)
- Traffic Control Systems (AREA)
Abstract
本公开提供了一种车辆行驶提示方法、装置、电子设备以及计算机可读存储介质,其中,首先获取与目标车辆相关的至少一张行驶图像;之后,对所述行驶图像进行识别,确定影响所述目标车辆的运行状态的目标对象的状态信息;最后,基于所述目标对象的状态信息和所述目标车辆当前的运行状态信息,提示所述目标车辆调整运行状态。
Description
相关申请的交叉引用
本申请要求在2021年8月30日提交至中国专利局、申请号为2021110034659的中国专利申请的优先权,其全部内容通过引用结合在本公开中。
本公开涉及图像处理技术领域,具体而言,涉及一种车辆行驶提示方法、装置、电子设备以及存储介质。
车辆运行状态调整的自动提醒技术能够自动提醒司机调整车辆的运行状态,以免碰撞、拥堵等状况的发生,例如,在交通信号灯处等待通行时,跟车自动提醒技术能够提醒司机及时起步,以免发生拥堵。但是,车辆运行状态调整的自动提醒技术一般基于毫米波雷达实现,其对车辆等对象的检测精度较低,导致提示车辆调整运行状态的准确度不高。
发明内容
本公开实施例至少提供一种车辆行驶提示方法、装置、电子设备以及计算机可读存储介质。
第一方面,本公开实施例提供了一种车辆行驶提示方法,包括:获取与目标车辆相关的至少一张行驶图像;对所述行驶图像进行识别,确定影响所述目标车辆的运行状态的目标对象的状态信息;基于所述目标对象的状态信息和所述目标车辆当前的运行状态信息,提示所述目标车辆调整运行状态。
第二方面,本公开提供了一种车辆行驶提示装置,包括:图像获取模块,用于与目标车辆相关的至少一张行驶图像;状态识别模块,用于对所述行驶图像进行识别,确定影响所述目标车辆的运行状态的目标对象的状态信息;提示模块,用于基于所述目标对象的状态信息和所述目标车辆当前的运行状态信息,提示所述目标车辆调整运行状态。
第三方面,本公开实施例还提供一种电子设备,包括:处理器、存储器和总线,所 述存储器存储有所述处理器可执行的机器可读指令,当电子设备运行时,所述处理器与所述存储器之间通过总线通信,所述机器可读指令被所述处理器执行时执行上述第一方面,或第一方面中任一种可能的实施方式中的步骤。
第四方面,本公开实施例还提供一种计算机可读存储介质,该计算机可读存储介质上存储有计算机程序,该计算机程序被处理器运行时执行上述第一方面,或第一方面中任一种可能的实施方式中的步骤。
关于上述车辆行驶提示装置、电子设备、及计算机可读存储介质的效果描述参见上述车辆行驶提示方法的说明,这里不再赘述。
为使本公开的上述目的、特征和优点能更明显易懂,下文特举较佳实施例,并配合所附附图,作详细说明如下。
为了更清楚地说明本公开实施例的技术方案,下面将对实施例中所需要使用的附图作简单地介绍,此处的附图被并入说明书中并构成本说明书中的一部分,这些附图示出了符合本公开的实施例,并与说明书一起用于说明本公开的技术方案。应当理解,以下附图仅示出了本公开的某些实施例,因此不应被看作是对范围的限定,对于本领域普通技术人员来讲,在不付出创造性劳动的前提下,还可以根据这些附图获得其他相关的附图。
图1示出了本公开实施例所提供的一种车辆行驶提示方法的流程图;
图2示出了本公开实施例所提供的另一种车辆行驶提示方法中对所述行驶图像进行识别,确定影响所述目标车辆的运行状态的目标对象的状态信息的流程图;
图3示出了本公开实施例所提供的一种车辆行驶提示装置的示意图;
图4示出了本公开实施例所提供的一种电子设备的示意图。
为使本公开实施例的目的、技术方案和优点更加清楚,下面将结合本公开实施例中附图,对本公开实施例中的技术方案进行清楚、完整地描述,显然,所描述的实施例仅仅是本公开一部分实施例,而不是全部的实施例。通常在此处附图中描述和示出的本公开实施例的组件可以以各种不同的配置来布置和设计。因此,以下对在附图中提供的本 公开的实施例的详细描述并非旨在限制要求保护的本公开的范围,而是仅仅表示本公开的选定实施例。基于本公开的实施例,本领域技术人员在没有做出创造性劳动的前提下所获得的所有其他实施例,都属于本公开保护的范围。
经研究发现,在对车辆的运行状态调整进行提示的技术方案中,存在对象的检测精度低以及提示的准确度低的缺陷,本公开针对上述技术缺陷提供了一种车辆行驶提示方法、装置、电子设备以及计算机可读存储介质,本公开通过对目标车辆相关的行驶图像进行处理,能够准确地识别出影响目标车辆的运行状态的目标对象,并确定目标对象的状态信息,之后,利用目标对象的状态信息能够准确的提示目标车辆的运行状态进行调整,这样不仅提高了对车辆运行状态调整进行提示的准确度,还提高了车辆行驶的安全性。
下面以执行主体为具有计算能力的设备为例对本公开实施例提供的车辆行驶提示方法加以说明。
如图1所示,本公开提供的车辆行驶提示方法可以包括如下步骤:
S110、获取与目标车辆相关的至少一张行驶图像。
上述行驶图像可以是安装在目标车辆上的摄像头拍摄的图像,目标车辆附近的摄像设备拍摄的图像,所述目标车辆附近的摄像设备包括安装在道路旁边的摄像头、目标车辆附近的其他车辆上的摄像头等。若行驶图像是安装在目标车辆上的摄像头拍摄的图像,则,行驶图像中不包括目标车辆,只包括位于目标车辆附近的多个对象。若行驶图像是目标车辆附近的摄像设备拍摄的图像,则行驶图像中可以包括目标车辆和/或目标车辆周围的多个对象。上述对象可以是行人、车辆、交通信号灯、非机动车等对象。
S120、对所述行驶图像进行识别,确定影响所述目标车辆的运行状态的目标对象的状态信息。
上述影响目标车辆的运行状态的目标对象可以是与目标车辆相邻并且位于目标车辆前方的对象,也可以是位于目标车辆前方的交通信号灯等。
在目标对象为与目标车辆相邻并且位于目标车辆前方的对象时,可以获取关于目标对象的连续的多张行驶图像,并分别对这些行驶图像进行识别,从而确定目标对象的状态信息。该状态信息可以是目标对象的运行状态信息,例如,目标对象的状态信息可以指示目标对象由静止开始运动、目标对象由相邻车道移入目标车辆所在的车道、目标对象移出目标车辆当前所在的车道等。
在目标对象为位于目标车辆前方的交通信号灯时,可以对当前获取的关于目标对象的一张行驶图像进行识别,从而确定目标对象的状态信息。此时的状态信息可以是目标对象的颜色信息,例如,目标对象的状态信息可以包括目标对象为红色、绿色或黄色;在目标对象的状态信息包括目标对象为绿色时,目标对象的状态信息指示目标车辆可以通行,在目标对象的状态信息包括目标对象为红色或黄色时,目标对象的状态信息指示目标车辆禁止通行。
S130、基于所述目标对象的状态信息和所述目标车辆当前的运行状态信息,提示所述目标车辆调整运行状态。
上述目标车辆当前的运行状态信息可以包括目标车辆当前的车速等。在执行此步骤之前可以获取目标车辆当前的车速。在获取目标车辆当前的车速时,可以通过目标车辆自身的CAN(Controller Area Network)总线中的信息来确定,也可以通过连续的多张包括目标车辆的图像来确定,其中上述连续的多张包括目标车辆的图像的最后一张图像可以是当前拍摄的一张图像。
在利用连续的多张包括目标车辆的图像来确定目标车辆当前的车速时,首先需要从连续的多张图像中识别出目标车辆,再基于拍摄上述连续的多张图像的摄像头的内外参标定信息,和目标车辆在每张图像中的位置,确定目标车辆在每张图像的拍摄时间的物理世界中的多个位置,最后,基于目标车辆在每张图像的拍摄时间的物理世界中的多个位置和每张图像的拍摄时间,确定目标车辆当前的车速。
此步骤中,结合所述目标对象当前的状态信息和目标车辆当前的运行状态信息,能够确定目标对象是否影响目标车辆当前的运行状态,并在确定目标对象影响目标车辆当前的运行状态时,提示所述目标车辆调整运行状态。
本文提到的对行驶图像进行识别,具体可以利用训练好的神经网络模型对行驶图像进行识别,确定目标对象以及目标对象的状态信息,该方式能够提高识别目标对象的精确度,以及确定的状态信息的准确度。之后,利用目标对象的状态信息能够准确的提示目标车辆调整运行状态,这样不仅提高了提示车辆调整运行状态的精确度,还提高了车辆行驶的安全性。
在一些实施例中,如图2所示,在目标对象包括与所述目标车辆相邻并且位于所述目标车辆前方的对象;所述目标对象的状态信息包括目标对象的运行状态信息时,上述对所述行驶图像进行识别,确定影响所述目标车辆的运行状态的目标对象的状态信息, 具体可以利用如下步骤实现:
S210、分别对每张所述行驶图像进行识别,确定每张行驶图像中的对象的位置信息。
示例性地,可以将各张行驶图像输入训练好的神经网络模型中,由神经网络模型对输入的行驶图像进行处理,输出行驶图像中的各个对象的信息,各个对象的信息可以包括检测框、各个检测框的位置信息、各个检测框的置信度、各个检测框的类型等信息。这里,在确定各个对象对应的检测框时,可以基于置信度,添加非极大值抑制,消除冗余的检测框,将置信度最高的检测框确定为对应的对象的检测框。
之后,将各张行驶图像中的检测框与对象进行匹配,根据匹配结果,确定同时存在于至少两张行驶图像中的对象。
之后,根据拍摄行驶图像的摄像头的内外参标定信息和经过所述匹配得到的对象在行驶图像中的位置,确定经过所述匹配得到的对象在物理世界中的位置信息。
在一个例子中,行驶图像可以是安装在目标车辆上的摄像头拍摄的,在本实施例中,行驶图像中不包括目标车辆,并且只包括目标车辆前方的对象,因此,可以直接利用上述步骤确定同时存在于至少两张行驶图像中的对象在物理世界中的位置信息。在另一个例子中,行驶图像还可以是目标车辆附近的摄像设备拍摄的图像,在本实施例中,行驶图像中包括目标车辆和目标车辆周围的多个对象。因此,首先需要利用训练好的神经网络模型确定目标车辆的检测框和其他对象的检测框,基于目标车辆的检测框的位置和各个其他对象的检测框的位置,筛选出位于目标车辆前方的对象的检测框,之后再将各张行驶图像中其他对象的检测框与所述其他对象中的对象进行匹配,根据匹配结果,确定同时存在于至少两张行驶图像中的对象。最后根据拍摄行驶图像的摄像头的内外参标定信息和经过所述匹配得到的对象在行驶图像中的位置,确定经过所述匹配得到的对象在物理世界中的位置信息。
S220、基于确定的各个对象的位置信息,从各个对象中筛选与所述目标车辆相邻并且位于所述目标车辆前方的目标对象。
上述目标对象包括位于目标车辆前方,并且与目标车辆位于同一车道内的对象,也包括位于目标车辆前方,并且位于与目标车辆所在的车道相邻的车道内的对象。
在筛选与目标车辆位于同一车道内的目标对象时,具体可利用如下子步骤实现:
子步骤一、针对每张行驶图像,对该行驶图像进行识别,确定该行驶图像中的各车道线的位置信息。
这里同样可以利用训练好的神经网络模型对行驶图像进行处理,得到各个对象的检测框等信息,再基于检测框的类型,确定属于车道线的检测框。之后,根据拍摄行驶图像的摄像头的内外参标定信息和车道线在行驶图像中的位置,确定车道线在物理世界中的位置信息。
子步骤二、基于该行驶图像中各个对象的位置信息,和该行驶图像中各车道线的位置信息,确定各个对象所位于的第一车道。
子步骤三、确定所述目标车辆所位于的第二车道。
可以利用训练好的神经网络模型对行驶图像进行处理,确定目标车辆的位置信息,再根据目标车辆的位置信息,和各个车道线的位置信息,确定目标车辆所位于的第二车道,其中,当所述行驶图像为安装在目标车辆上的摄像头拍摄的图像时,目标车辆的位置信息可以是安装在目标车辆上的摄像头的位置信息。
子步骤四、基于所述目标车辆所位于的第二车道,和各个对象所位于的第一车道,从各个对象中筛选与所述目标车辆相邻的、与所述目标车辆位于同一车道的、并且位于所述目标车辆前方的目标对象。
上述子步骤通过对行驶图像中各车道线的识别和定位,能够准确地确定与目标车辆相邻的、与目标车辆位于同一车道的、并且位于目标车辆前方的目标对象,该目标对象对目标车辆的运行状态有直接的影响,因此,准确地识别出该目标对象有利于提高对车辆的运行状态调整进行提示的精确度。
在目标对象为位于目标车辆前方,并且位于与目标车辆所在的车道相邻的车道内的对象时,具体可利用如下子步骤筛选目标对象:
子步骤一、针对每张行驶图像,对该行驶图像进行识别,确定该行驶图像中的各车道线的位置信息。
子步骤二、基于该行驶图像中各个对象的位置信息,和该行驶图像中各车道线的位置信息,确定各个对象所位于的第一车道。
子步骤三、确定所述目标车辆所位于的第二车道。
子步骤四、基于所述目标车辆所位于的第二车道,和各个对象所位于的第一车道,从各个对象中筛选与所述目标车辆相邻的、位于与目标车辆所在的车道相邻的车道内的、并且位于所述目标车辆前方的目标对象。
S230、针对每个目标对象,利用该目标对象在至少两张行驶图像中的所述位置信息,确定所述目标对象的运行状态信息。
上述目标对象的运动状态信息可以包括启动状态、切入状态、切出状态、静止状态等。具体地,在根据目标对象的位置信息,确定所述目标对象由静止开始运动时,目标对象的运动状态信息为启动状态;在根据目标对象的位置信息,确定目标对象由相邻的车道移入到目标车辆所在的车道时,目标对象的运动状态信息为切入状态;在根据目标对象的位置信息,确定目标对象由目标车辆所在的车道移入相邻的车道时,目标对象的运动状态信息为切出状态;在根据目标对象的位置信息,确定目标对象的位置未发生改变时,目标对象的运动状态信息为静止状态。
上述通过对行驶图像进行处理,能够精确地确定各个对象的位置信息,基于各个对象的位置信息能够精确地筛选出对目标车辆的运行状态有影响目标对象,同时基于各个对象的位置信息能够精确地确定出目标对象的运行状态信息。精确地目标对象的运行状态信息和目标对象的位置信息,有利于提高提醒车辆调整运行状态的精确度。
在目标对象与目标车辆相邻,与目标车辆位于同一车道并且位于目标车辆前方时,如果目标对象的运行状态信息指示所述目标对象由静止开始运动,即目标对象的运行状态信息为启动状态,并且所述目标车辆当前的运行状态信息指示所述目标车辆当前的车速为零,此时需要提示所述目标车辆启动行驶,即需要对目标车辆进行跟车提醒。
根据位于目标车辆运行方向的正前方的目标对象的运行状态信息,能够确定位于目标车辆运行方向的正前方的目标对象是否启动,如果目标对象启动,则及时提醒目标车辆启动行驶,不仅实现对目标车辆进行准确地跟车提醒,还能够提高目标车辆的通行效率,有利于避免或疏解道路拥堵。
在进行跟车提醒时,为了提高跟车提醒的精确度,还需要结合目标对象与目标车辆的距离信息来确定是否对目标车辆发出跟车提醒,其中,所述距离信息可以包括目标对象与目标车辆的距离、目标对象的由静止开始运动的运动距离等。具体地,可以利用如下步骤确定是否对目标车辆发出跟车提醒:
基于所述目标对象在每张行驶图像中的位置信息和所述目标车辆的位置信息,确定所述目标对象与所述目标车辆的距离信息;在所述距离信息指示所述目标对象与所述目标车辆的最小距离大于第一距离阈值、所述目标对象的运行状态信息指示所述目标对象由静止开始运动并且运动距离大于第二距离阈值、所述目标车辆当前的车速为零的情况 下,提示所述目标车辆启动行驶,即对目标车辆发出跟车提醒。其中,所述目标对象与目标车辆的最小距离可以是指,当目标对象位于目标车辆运行方向的正前方时,目标对象的最后端与目标车辆的最前端之间的最小距离。所述运动距离是指目标对象由静止状态开始运动的行驶距离。
在确定目标对象与所述目标车辆的距离信息时,具体可以根据上述实施例确定目标对象的位置信息和目标车辆的位置信息来确定。
上述第一距离阈值、第二距离阈值可以根据实际应用场景灵活设定,例如,第二距离阈值可以设置为3米,第一距离阈值可以设置为20米。在实际应用中还可以设置参数设置页面,由用户在该参数设置页面中对上述第一距离阈值、第二距离阈值进行设置或修改。
在目标对象与目标车辆位于同一车道时,如果目标对象的运行状态信息指示所述目标对象移出当前车道,即目标对象的运行状态信息为切出状态,并且所述目标车辆当前的车速小于预设车速阈值,则提示所述目标车辆提高行驶速度。
上述方式给目标车辆发出了一个提速提醒,在实际应用中还可以由用户在该参数设置页面中对上述预设车速阈值进行设置或修改。
在目标对象移出当前车道,并且目标车辆当前的车速较小时,提示目标车辆提高行驶速度,不仅提高了提示车辆调整运行状态的精确度,还有利于提高目标车辆的通行效率。
在目标对象位于目标车辆所在的车道的相邻的车道时,如果目标对象的运行状态信息指示所述目标对象由所述相邻的车道移入所述目标车辆所在的车道,即目标对象的运行状态信息为切入状态,并且所述目标对象的速度小于所述目标车辆当前的车速,则提示所述目标车辆降低行驶速度。
上述方式给目标车辆发出了一个降速提醒。在目标对象从其他车道移入目标车辆所在的车道,并且目标对象的速度小于目标车辆的车速时,对目标车辆进行降低行驶速度的提示,不仅提高了提示车辆调整运行状态的精确度,还有利于提高目标车辆的运行安全性。
在一个例子中,目标对象还可以是位于目标车辆前方的交通信号灯,此时可以利用如下步骤对所述目标车辆进行运行状态调整的提示:
在所述目标车辆当前的车速为零,并且所述交通信号灯的状态信息指示车辆能够 通行,即交通信号灯为绿色的情况下,提示所述目标车辆启动行驶。
在识别交通信号灯时,同样可以利用训练好的神经网络模型对行驶图像进行处理,并根据得到的检测框的类型确定属于交通信号灯类型的对象,并通过提取行驶图像中交通信号灯的像素的特征,确定交通信号灯的颜色,即确定交通信号灯的状态信息。利用训练好的神经网络模型检测交通信号灯的状态信息提高了检测精度。
上述方式结合交通信号灯的状态信息,能够对目标车辆进行准确地跟车提醒,不仅提高了提示车辆调整运行状态的精确度,还有利于提高目标车辆的通行效率。
上述实施例中利用训练好的神经网络模型检测行驶图像中的各个对象,确定各个对象的状态信息,有效提高了对象检测的精度,以及确定的状态信息的准确度。通过参数设置页面能够灵活地改变第一距离阈值、第二距离阈值等参数,实现了灵活地提示目标车辆调整运行状态,提高了用户体验。
本领域技术人员可以理解,在具体实施方式的上述方法中,各步骤的撰写顺序并不意味着严格的执行顺序而对实施过程构成任何限定,各步骤的具体执行顺序应当以其功能和可能的内在逻辑确定。
基于同一发明构思,本公开实施例中还提供了与车辆行驶提示方法对应的车辆行驶提示装置,由于本公开实施例中的装置解决问题的原理与本公开实施例上述车辆行驶提示方法相似,因此装置的实施可以参见方法的实施,重复之处不再赘述。
参照图3所示,为本公开实施例提供的一种车辆行驶提示装置的架构示意图,所述装置包括:
图像获取模块310,用于获取与目标车辆相关的至少一张行驶图像。
状态识别模块320,用于对所述行驶图像进行识别,确定影响所述目标车辆的运行状态的目标对象的状态信息。
提示模块330,用于基于所述目标对象的状态信息和所述目标车辆当前的运行状态信息,提示所述目标车辆调整运行状态。
在一些实施例中,所述目标对象包括与所述目标车辆相邻并且位于所述目标车辆前方的对象;所述目标对象的状态信息包括目标对象的运行状态信息;
所述状态识别模块320在对所述行驶图像进行识别,确定影响所述目标车辆的运行状态的目标对象的状态信息时,用于:
分别对每张所述行驶图像进行识别,确定每张行驶图像中的对象的位置信息;
基于确定的各个对象的位置信息,从各个对象中筛选与所述目标车辆相邻的、并且位于所述目标车辆前方的目标对象;
针对所述目标对象,利用该目标对象在至少两张行驶图像中的所述位置信息,确定所述目标对象的运行状态信息。
在一些实施例中,所述目标对象包括与所述目标车辆位于同一车道内的对象;
所述状态识别模块320在基于确定的各个对象的位置信息,从各个对象中筛选与所述目标车辆相邻的、并且位于所述目标车辆前方的目标对象时,用于:
针对每张行驶图像,对该行驶图像进行识别,确定该行驶图像中的各车道线的位置信息;
基于该行驶图像中各个对象的位置信息,和该行驶图像中的各车道线的位置信息,确定各个对象所位于的第一车道;
确定所述目标车辆所位于的第二车道;
基于所述目标车辆所位于的第二车道,和各个对象所位于的第一车道,从各个对象中筛选与所述目标车辆相邻的、与所述目标车辆位于同一车道的、并且位于所述目标车辆前方的目标对象。
在一些实施例中,所述目标车辆当前的运行状态信息包括所述目标车辆当前的车速;
所述提示模块330在基于所述目标对象的状态信息和所述目标车辆当前的运行状态信息,提示所述目标车辆调整运行状态时,用于:
在所述目标对象的运行状态信息指示所述目标对象由静止开始运动,并且所述目标车辆当前的运行状态信息指示所述目标车辆当前的车速为零的情况下,提示所述目标车辆启动行驶。
在一些实施例中,所述提示模块330在所述目标对象的运行状态信息指示所述目标对象由静止开始运动,并且所述目标车辆当前的运行状态信息指示所述目标车辆当前的车速为零的情况下,提示所述目标车辆启动行驶时,还用于:
基于所述目标对象在每张行驶图像中的位置信息和所述目标车辆的位置信息,确定所述目标对象与所述目标车辆的距离信息;
在所述距离信息指示所述目标对象与所述目标车辆的最小距离大于第一距离阈值、所述目标对象的运行状态信息指示所述目标对象由静止开始运动并且运动距离大于第二距离阈值、所述目标车辆当前的车速为零的情况下,提示所述目标车辆启动行驶。
在一些实施例中,所述目标车辆当前的运行状态信息包括所述目标车辆当前的车速;
所述提示模块330在基于所述目标对象的状态信息和所述目标车辆当前的运行状态信息,提示所述目标车辆调整运行状态时,用于:
在所述目标对象的运行状态信息指示所述目标对象移出当前车道,并且所述目标车辆当前的车速小于预设车速阈值的情况下,提示所述目标车辆提高行驶速度。
在一些实施例中,所述目标对象包括位于与所述目标车辆所在的车道相邻的车道的对象;所述目标车辆当前的运行状态信息包括所述目标车辆当前的车速;
所述提示模块330在基于所述目标对象的状态信息和所述目标车辆当前的运行状态信息,提示所述目标车辆调整运行状态时,用于:
在所述目标对象的运行状态信息指示所述目标对象由与所述目标车辆所在的车道相邻的车道移入所述目标车辆所在的车道,并且所述目标对象的速度小于所述目标车辆当前的车速的情况下,提示所述目标车辆降低行驶速度。
在一些实施例中,所述目标对象包括交通信号灯;所述目标车辆当前的运行状态信息包括所述目标车辆当前的车速;
所述提示模块330在基于所述目标对象的状态信息和所述目标车辆当前的运行状态信息,提示所述目标车辆调整运行状态时,用于:
在所述目标车辆当前的车速为零,并且所述交通信号灯的状态信息指示车辆能够通行的情况下,提示所述目标车辆启动行驶。
基于同一技术构思,本公开实施例还提供了一种电子设备。参照图4所示,为本公开实施例提供的电子设备400的结构示意图,包括处理器41、存储器42、和总线43。其中,存储器42用于存储执行指令,包括内存421和外部存储器422;这里的内存421也称内存储器,用于暂时存放处理器41中的运算数据,以及与硬盘等外部存储器422交换的数据,处理器41通过内存421与外部存储器422进行数据交换,当电子设备400运行时,处理器41与存储器42之间通过总线43通信,使得处理器41在执行以下指令:
获取与目标车辆相关的至少一张行驶图像;对所述行驶图像进行识别,确定影响所述目标车辆的运行状态的目标对象的状态信息;基于所述目标对象的状态信息和所述目标车辆当前的运行状态信息,提示所述目标车辆调整运行状态。
本公开实施例还提供一种计算机可读存储介质,该计算机可读存储介质上存储有计算机程序,该计算机程序被处理器运行时执行上述方法实施例中所述的车辆行驶提示方法的步骤。其中,该存储介质可以是易失性或非易失的计算机可读取存储介质。
本公开实施例所提供的车辆行驶提示方法的计算机程序产品,包括存储了程序代码的计算机可读存储介质,所述程序代码包括的指令可用于执行上述方法实施例中所述的车辆行驶提示方法的步骤,具体可参见上述方法实施例,在此不再赘述。该计算机程序产品可以具体通过硬件、软件或其结合的方式实现。在一个可选实施例中,所述计算机程序产品具体体现为计算机存储介质,在另一个可选实施例中,计算机程序产品具体体现为软件产品,例如软件开发包(Software Development Kit,SDK)等等。
所属领域的技术人员可以清楚地了解到,为描述的方便和简洁,上述描述的***和装置的具体工作过程,可以参考前述方法实施例中的对应过程,在此不再赘述。在本公开所提供的几个实施例中,应该理解到,所揭露的***、装置和方法,可以通过其它的方式实现。以上所描述的装置实施例仅仅是示意性的,例如,所述单元的划分,仅仅为一种逻辑功能划分,实际实现时可以有另外的划分方式,又例如,多个单元或组件可以结合或者可以集成到另一个***,或一些特征可以忽略,或不执行。另一点,所显示或讨论的相互之间的耦合或直接耦合或通信连接可以是通过一些通信接口,装置或单元的间接耦合或通信连接,可以是电性,机械或其它的形式。
所述作为分离部件说明的单元可以是或者也可以不是物理上分开的,作为单元显示的部件可以是或者也可以不是物理单元,即可以位于一个地方,或者也可以分布到多个网络单元上。可以根据实际的需要选择其中的部分或者全部单元来实现本实施例方案的目的。
另外,在本公开各个实施例中的各功能单元可以集成在一个处理单元中,也可以是各个单元单独物理存在,也可以两个或两个以上单元集成在一个单元中。
所述功能如果以软件功能单元的形式实现并作为独立的产品销售或使用时,可以存储在一个处理器可执行的非易失的计算机可读取存储介质中。基于这样的理解,本公开的技术方案本质上或者说对现有技术做出贡献的部分或者该技术方案的部分可以以 软件产品的形式体现出来,该计算机软件产品存储在一个存储介质中,包括若干指令用以使得一台计算机设备(可以是个人计算机,服务器,或者网络设备等)执行本公开各个实施例所述方法的全部或部分步骤。而前述的存储介质包括:U盘、移动硬盘、只读存储器(Read-Only Memory,ROM)、随机存取存储器(Random Access Memory,RAM)、磁碟或者光盘等各种可以存储程序代码的介质。
最后应说明的是:以上所述实施例,仅为本公开的具体实施方式,用以说明本公开的技术方案,而非对其限制,本公开的保护范围并不局限于此,尽管参照前述实施例对本公开进行了详细的说明,本领域的普通技术人员应当理解:任何熟悉本技术领域的技术人员在本公开揭露的技术范围内,其依然可以对前述实施例所记载的技术方案进行修改或可轻易想到变化,或者对其中部分技术特征进行等同替换;而这些修改、变化或者替换,并不使相应技术方案的本质脱离本公开实施例技术方案的精神和范围,都应涵盖在本公开的保护范围之内。因此,本公开的保护范围应所述以权利要求的保护范围为准。
Claims (11)
- 一种车辆行驶提示方法,其特征在于,包括:获取与目标车辆相关的至少一张行驶图像;对所述行驶图像进行识别,确定影响所述目标车辆的运行状态的目标对象的状态信息;基于所述目标对象的状态信息和所述目标车辆当前的运行状态信息,提示所述目标车辆调整运行状态。
- 根据权利要求1所述的方法,其特征在于,所述目标对象包括与所述目标车辆相邻并且位于所述目标车辆前方的对象;所述目标对象的状态信息包括目标对象的运行状态信息;对所述行驶图像进行识别,确定影响所述目标车辆的运行状态的目标对象的状态信息,包括:分别对每张所述行驶图像进行识别,确定每张行驶图像中的对象的位置信息;基于确定的各个对象的位置信息,从各个对象中筛选与所述目标车辆相邻并且位于所述目标车辆前方的目标对象;针对所述目标对象,利用该目标对象在至少两张行驶图像中的所述位置信息,确定所述目标对象的运行状态信息。
- 根据权利要求2所述的方法,其特征在于,所述目标对象包括与所述目标车辆位于同一车道内的对象;基于确定的各个对象的位置信息,从各个对象中筛选与所述目标车辆相邻并且位于所述目标车辆前方的目标对象,包括:针对每张行驶图像,对该行驶图像进行识别,确定该行驶图像中的各车道线的位置信息;基于该行驶图像中各个对象的位置信息,和该行驶图像中的各车道线的位置信息,确定各个对象所位于的第一车道;确定所述目标车辆所位于的第二车道;基于所述目标车辆所位于的第二车道,和各个对象所位于的第一车道,从各个对象中筛选与所述目标车辆相邻的、与所述目标车辆位于同一车道的、并且位于所述目标车辆前方的目标对象。
- 根据权利要求1-3任一项所述的方法,其特征在于,所述目标车辆当前的运行状态信息包括所述目标车辆当前的车速;基于所述目标对象的状态信息和所述目标车辆当前的运行状态信息,提示所述目标车辆调整运行状态,包括:在所述目标对象的运行状态信息指示所述目标对象由静止开始运动,并且所述目标车辆当前的运行状态信息指示所述目标车辆当前的车速为零的情况下,提示所述目标车辆启动行驶。
- 根据权利要求4所述的方法,其特征在于,在所述目标对象的运行状态信息指示所述目标对象由静止开始运动,并且所述目标车辆当前的运行状态信息指示所述目标车辆当前的车速为零的情况下,提示所述目标车辆启动行驶,包括:基于所述目标对象在每张行驶图像中的位置信息和所述目标车辆的位置信息,确定所述目标对象与所述目标车辆的距离信息;在所述距离信息指示所述目标对象与所述目标车辆的最小距离大于第一距离阈值、所述目标对象的运行状态信息指示所述目标对象由静止开始运动并且运动距离大于第二距离阈值、所述目标车辆当前的车速为零的情况下,提示所述目标车辆启动行驶。
- 根据权利要求1-3任一项所述的方法,其特征在于,所述目标车辆当前的运行状态信息包括所述目标车辆当前的车速;基于所述目标对象的状态信息和所述目标车辆当前的运行状态信息,提示所述目标车辆调整运行状态,包括:在所述目标对象的运行状态信息指示所述目标对象移出当前车道,并且所述目标车辆当前的车速小于预设车速阈值的情况下,提示所述目标车辆提高行驶速度。
- 根据权利要求1-3任一项所述的方法,其特征在于,所述目标对象包括位于与 所述目标车辆所在的车道相邻的车道的对象;所述目标车辆当前的运行状态信息包括所述目标车辆当前的车速;基于所述目标对象的状态信息和所述目标车辆当前的运行状态信息,提示所述目标车辆调整运行状态,包括:在所述目标对象的运行状态信息指示所述目标对象由与所述目标车辆所在的车道相邻的车道移入所述目标车辆所在的车道,并且所述目标对象的速度小于所述目标车辆当前的车速的情况下,提示所述目标车辆降低行驶速度。
- 根据权利要求1所述的方法,其特征在于,所述目标对象包括交通信号灯;所述目标车辆当前的运行状态信息包括所述目标车辆当前的车速;基于所述目标对象的状态信息和所述目标车辆当前的运行状态信息,提示所述目标车辆调整运行状态,包括:在所述目标车辆当前的车速为零,并且所述交通信号灯的状态信息指示车辆能够通行的情况下,提示所述目标车辆启动行驶。
- 一种车辆行驶提示装置,其特征在于,包括:图像获取模块,用于获取与目标车辆相关的至少一张行驶图像;状态识别模块,用于对所述行驶图像进行识别,确定影响所述目标车辆的运行状态的目标对象的状态信息;提示模块,用于基于所述目标对象的状态信息和所述目标车辆当前的运行状态信息,提示所述目标车辆调整运行状态。
- 一种电子设备,其特征在于,包括:处理器、存储器和总线,所述存储器存储有所述处理器可执行的机器可读指令,当电子设备运行时,所述处理器与所述存储器之间通过总线通信,所述机器可读指令被所述处理器执行时执行如权利要求1至8任一项所述的车辆行驶提示方法的步骤。
- 一种计算机可读存储介质,其特征在于,该计算机可读存储介质上存储有计算机程序,该计算机程序被处理器运行时执行如权利要求1至8任一项所述的车辆行驶提示方法的步骤。
Applications Claiming Priority (2)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN202111003465.9 | 2021-08-30 | ||
CN202111003465.9A CN113723282B (zh) | 2021-08-30 | 2021-08-30 | 车辆行驶提示方法、装置、电子设备以及存储介质 |
Publications (1)
Publication Number | Publication Date |
---|---|
WO2023029468A1 true WO2023029468A1 (zh) | 2023-03-09 |
Family
ID=78678973
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
PCT/CN2022/084330 WO2023029468A1 (zh) | 2021-08-30 | 2022-03-31 | 车辆行驶提示 |
Country Status (2)
Country | Link |
---|---|
CN (1) | CN113723282B (zh) |
WO (1) | WO2023029468A1 (zh) |
Families Citing this family (1)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN113723282B (zh) * | 2021-08-30 | 2024-03-22 | 上海商汤临港智能科技有限公司 | 车辆行驶提示方法、装置、电子设备以及存储介质 |
Citations (6)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN105691390A (zh) * | 2016-02-04 | 2016-06-22 | 长安大学 | 一种车辆预警装置和预警方法 |
CN105882511A (zh) * | 2015-11-11 | 2016-08-24 | 乐卡汽车智能科技(北京)有限公司 | 前方车辆行驶状态的提示方法和装置 |
CN106297410A (zh) * | 2016-08-25 | 2017-01-04 | 深圳市元征科技股份有限公司 | 车辆监测方法及装置 |
US9896107B1 (en) * | 2016-09-30 | 2018-02-20 | Denso International America, Inc. | Digital lane change confirmation projection systems and methods |
CN109830116A (zh) * | 2018-12-15 | 2019-05-31 | 深圳壹账通智能科技有限公司 | 基于图像识别的信息提示方法、装置及相关设备 |
CN113723282A (zh) * | 2021-08-30 | 2021-11-30 | 上海商汤临港智能科技有限公司 | 车辆行驶提示方法、装置、电子设备以及存储介质 |
Family Cites Families (6)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN102509067B (zh) * | 2011-09-22 | 2014-04-02 | 西北工业大学 | 一种车道边界和主车方位检测方法 |
CN102785661B (zh) * | 2012-08-20 | 2015-05-13 | 深圳先进技术研究院 | 车道偏离控制***及方法 |
CN106529530A (zh) * | 2016-10-28 | 2017-03-22 | 上海大学 | 一种基于单目视觉的前方车辆检测方法 |
JP6500887B2 (ja) * | 2016-12-26 | 2019-04-17 | トヨタ自動車株式会社 | 車両用注意喚起装置 |
AU2018282316B2 (en) * | 2017-06-19 | 2020-07-16 | Beijing Didi Infinity Technology And Development Co., Ltd. | Systems and methods for displaying movement of vehicle on map |
CN107862287A (zh) * | 2017-11-08 | 2018-03-30 | 吉林大学 | 一种前方小区域物体识别及车辆预警方法 |
-
2021
- 2021-08-30 CN CN202111003465.9A patent/CN113723282B/zh active Active
-
2022
- 2022-03-31 WO PCT/CN2022/084330 patent/WO2023029468A1/zh unknown
Patent Citations (6)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN105882511A (zh) * | 2015-11-11 | 2016-08-24 | 乐卡汽车智能科技(北京)有限公司 | 前方车辆行驶状态的提示方法和装置 |
CN105691390A (zh) * | 2016-02-04 | 2016-06-22 | 长安大学 | 一种车辆预警装置和预警方法 |
CN106297410A (zh) * | 2016-08-25 | 2017-01-04 | 深圳市元征科技股份有限公司 | 车辆监测方法及装置 |
US9896107B1 (en) * | 2016-09-30 | 2018-02-20 | Denso International America, Inc. | Digital lane change confirmation projection systems and methods |
CN109830116A (zh) * | 2018-12-15 | 2019-05-31 | 深圳壹账通智能科技有限公司 | 基于图像识别的信息提示方法、装置及相关设备 |
CN113723282A (zh) * | 2021-08-30 | 2021-11-30 | 上海商汤临港智能科技有限公司 | 车辆行驶提示方法、装置、电子设备以及存储介质 |
Also Published As
Publication number | Publication date |
---|---|
CN113723282A (zh) | 2021-11-30 |
CN113723282B (zh) | 2024-03-22 |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
US20220292845A1 (en) | Brake Light Detection | |
CN108725440B (zh) | 前向碰撞控制方法和装置、电子设备、程序和介质 | |
WO2020001223A1 (zh) | 交通信号灯检测及智能驾驶方法和装置、车辆、电子设备 | |
US9721460B2 (en) | In-vehicle surrounding environment recognition device | |
CN106647776B (zh) | 车辆变道趋势的判断方法、判断装置和计算机存储介质 | |
US10532695B2 (en) | Vehicle monitoring device, vehicle monitoring method and vehicle monitoring program | |
JP4654163B2 (ja) | 車両の周囲環境認識装置及びシステム | |
KR20220000977A (ko) | 횡단보도 인식 결과를 이용한 안내 정보 제공 장치 및 방법 | |
US9904860B2 (en) | Vehicle exterior environment recognition apparatus | |
US8848980B2 (en) | Front vehicle detecting method and front vehicle detecting apparatus | |
Fossati et al. | Real-time vehicle tracking for driving assistance | |
JP7185419B2 (ja) | 車両のための、対象物を分類するための方法および装置 | |
JP2016148962A (ja) | 物体検知装置 | |
JP6569385B2 (ja) | 車両検出装置、車両検出システム、車両検出方法、及び車両検出プログラム | |
WO2022161139A1 (zh) | 行驶朝向检测方法、装置、计算机设备及存储介质 | |
JP2020052647A (ja) | 物体検出装置、物体検出方法、物体検出用コンピュータプログラム及び車両制御システム | |
JP2014192770A (ja) | 車両用周辺監視制御装置 | |
WO2023029468A1 (zh) | 车辆行驶提示 | |
WO2023092982A1 (zh) | 状态检测方法、装置、计算机设备、存储介质和程序产品 | |
US11106214B2 (en) | Artificial neural network-based projection information recognition apparatus and method thereof | |
JP6335037B2 (ja) | 車外環境認識装置 | |
KR101374653B1 (ko) | 차량의 움직임을 검출하는 장치 및 방법 | |
Satzoda et al. | Vision-based front and rear surround understanding using embedded processors | |
US20150178577A1 (en) | Image processing apparatus, and image processing method | |
JP2014203196A (ja) | 危険度判定装置、危険度判定方法、警報装置、及び運転支援装置 |
Legal Events
Date | Code | Title | Description |
---|---|---|---|
NENP | Non-entry into the national phase |
Ref country code: DE |