Blind area prompting method and device, electronic equipment and storage medium

Abstract

The invention discloses a blind area prompting method and device, electronic equipment and a storage medium, and belongs to the technical field of vehicle application, and the method comprises the steps: determining a target blind area of a target vehicle according to a to-be-driven route of the target vehicle; acquiring a first environment image shot by an environment camera corresponding to the target blind area; performing target detection based on the first environment image, and generating first state information of each traffic participant in the target blind area; and based on the first state information of the traffic participant, generating an environment modeling image containing the traffic participant and displaying the environment modeling image. The target vehicle can notice traffic participants in the blind area in time, the driving safety of the target vehicle can be improved, target detection is carried out on the target blind area determined by the to-be-driven route of the target vehicle, the target vehicle can be prevented from processing images of all environment cameras in the current environment, and the driving safety of the target vehicle is improved. The data volume needing to be processed in the blind area detection process is reduced, and the blind area reminding efficiency and speed of the target vehicle can be improved.

Description

Technical Field

[0001] The present application relates to the field of vehicle application technology, and in particular to a blind spot warning method, device, electronic device and storage medium. Background Art

[0002] With the rapid development of vehicle technology, more and more vehicles are put into use, and the traffic environment is becoming more and more complex. Due to the complex vehicle use environment, many blind spots will inevitably be encountered during daily driving, affecting the driving safety of the vehicle.

[0003] In related technologies, it is usually determined whether there is a blind spot in the direction of vehicle travel based on the vehicle's position and map data. If there is a blind spot, the blind spot will be marked on the navigation screen or map screen and a blind spot reminder will be issued to the driver, prompting the driver to pay attention to the blind spot ahead and to slow down in advance.

[0004] However, the above-mentioned blind spot warning scheme is based on historical map data and can only remind the driver to pay attention to possible blind spot areas, and the accuracy of blind spot warning is poor. Summary of the invention

[0005] The purpose of the embodiments of the present application is to provide a blind spot prompt method, device, electronic device and storage medium, which can solve the problem of poor accuracy of blind spot prompts in related technologies.

[0006] In a first aspect, an embodiment of the present application provides a blind spot prompting method, the method comprising:

[0007] Determining a target blind spot of the target vehicle according to the route to be traveled by the target vehicle;

[0008] Acquire a first environmental image captured by an environmental camera corresponding to the target blind spot;

[0009] Performing target detection based on the first environmental image to generate first status information of each traffic participant in the target blind spot;

[0010] Based on the first status information of the traffic participant, an environment modeling image including the traffic participant is generated and displayed.

[0011] Optionally, determining a target blind spot of the target vehicle according to a route to be traveled by the target vehicle comprises:

[0012] When the memory parking function of the target vehicle is activated, obtaining a memory parking route of the target vehicle;

[0013] Determining the route to be traveled according to the memorized parking route;

[0014] The target blind spot is determined based on the route to be traveled.

[0015] Optionally, determining the target blind spot based on the route to be traveled includes:

[0016] Determine a first ground area within a preset range of the route to be traveled;

[0017] Determining a second ground area according to a second environmental image taken by the target vehicle;

[0018] Acquire a ground area that does not overlap with the second ground area from the first ground area to obtain a third ground area;

[0019] The target blind area is determined based on the third ground area.

[0020] Optionally, the determining a first ground area within a preset range of the route to be traveled includes:

[0021] Get the complete environment image of the current environment scene captured by the environment camera;

[0022] Identify the complete ground area of ​​the current environment scene based on the complete environment image;

[0023] The first ground area is determined from the complete ground area based on the to-be-traveled route and the preset range.

[0024] Optionally, the acquiring a first environment image captured by an environment camera corresponding to the target blind spot includes:

[0025] Obtaining first position information corresponding to each environmental camera and second position information of the target blind spot;

[0026] Based on the first position information and the second position information, determining first distances respectively corresponding to the target blind spot and the environment camera;

[0027] According to the first distance, determining a target camera from the environment cameras whose first distance meets a preset condition;

[0028] A first environment image captured by the target camera is acquired.

[0029] Optionally, obtaining the first environment image captured by the target camera includes:

[0030] Based on the target blind area and the first shooting area of ​​the target camera, generating an adjustment instruction for the target camera; wherein the adjustment instruction includes a focal length adjustment parameter and / or a framing orientation adjustment parameter;

[0031] Sending the adjustment instruction to the target camera to adjust the first shooting area of ​​the target camera to the second shooting area;

[0032] A first environment image captured by the target camera based on the second shooting area is obtained.

[0033] Optionally, generating and displaying an environment modeling image including the traffic participant based on the first state information of the traffic participant includes:

[0034] Determining a collision probability between the target vehicle and the traffic participant based on the first state information of the traffic participant and the second state information of the target vehicle;

[0035] determining a rendering parameter of the traffic participant based on the collision probability;

[0036] Based on the rendering parameters, the participant model of the traffic participant is rendered in the environment model to obtain the environment modeling image.

[0037] In a second aspect, an embodiment of the present application provides a blind spot prompting device, the device comprising:

[0038] A blind spot module, used to determine a target blind spot of the target vehicle according to the route to be driven by the target vehicle;

[0039] An imaging module, used for acquiring a first environmental image captured by an environmental camera corresponding to the target blind spot;

[0040] a parameter module, configured to perform target detection based on the first environmental image and generate first status information of each traffic participant in the target blind spot;

[0041] A display module is used to generate and display an environment modeling image containing the traffic participant based on the first state information of the traffic participant.

[0042] Optionally, the blind area module includes:

[0043] A parking route submodule, used for obtaining a memory parking route of the target vehicle when the memory parking function of the target vehicle is activated;

[0044] A route to be traveled submodule, used to determine the route to be traveled according to the memorized parking route;

[0045] The blind spot determination submodule is used to determine the target blind spot based on the route to be traveled.

[0046] Optionally, the target blind area determination submodule includes:

[0047] A first ground area unit, used to determine a first ground area within a preset range of the to-be-traveled route;

[0048] A second ground area unit, used to determine a second ground area according to a second environment image taken by the target vehicle;

[0049] A third ground area unit is used to obtain a ground area that does not overlap with the second ground area from the first ground area to obtain a third ground area;

[0050] A target blind area determining unit is configured to determine the target blind area based on the third ground area.

[0051] Optionally, the first ground area unit includes:

[0052] The complete environment image subunit is used to obtain the complete environment image of the current environment scene captured by the environment camera;

[0053] A complete ground area subunit, configured to identify a complete ground area of ​​the current environment scene based on the complete environment image;

[0054] The first ground area determining subunit is used to determine the first ground area from the complete ground area based on the to-be-traveled route and the preset range.

[0055] Optionally, the imaging module includes:

[0056] A position information submodule, used to obtain first position information corresponding to each environmental camera and second position information of the target blind spot;

[0057] A first distance submodule, configured to determine first distances respectively corresponding to the target blind spot and the environment camera based on the first position information and the second position information;

[0058] A target camera submodule, configured to determine, according to the first distance, a target camera from among the environment cameras whose first distance satisfies a preset condition;

[0059] The environmental image acquisition submodule is used to acquire the first environmental image taken by the target camera.

[0060] Optionally, the first environmental image acquisition submodule includes:

[0061] An adjustment instruction unit, configured to generate an adjustment instruction for the target camera based on the target blind area and the first shooting area of ​​the target camera; wherein the adjustment instruction includes a focal length adjustment parameter and / or a framing orientation adjustment parameter;

[0062] An instruction sending unit, used for sending the adjustment instruction to the target camera to adjust the first shooting area of ​​the target camera to the second shooting area;

[0063] The first environment image acquisition unit is used to acquire a first environment image captured by the target camera based on the second shooting area.

[0064] Optionally, the display module includes:

[0065] A collision probability submodule, for determining a collision probability between the target vehicle and the traffic participant based on the first state information of the traffic participant and the second state information of the target vehicle;

[0066] A rendering parameter submodule, used to determine the rendering parameters of the traffic participant based on the collision probability;

[0067] The rendering submodule is used to render the participant model of the traffic participant in the environment model based on the rendering parameters to obtain the environment modeling image.

[0068] In a third aspect, an embodiment of the present application provides an electronic device, comprising a processor; a memory for storing instructions executable by the processor; wherein the processor is configured to execute the instructions to implement the above-mentioned blind spot prompt method.

[0069] In a fourth aspect, an embodiment of the present application provides a readable storage medium, on which a program or instruction is stored, and when the program or instruction is executed by a processor, any blind spot prompt method as described above is implemented.

[0070] In a fifth aspect, a vehicle controller is provided, comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor implements the above-mentioned blind spot warning method when executing the computer program.

[0071] In a sixth aspect, a vehicle comprises the above-mentioned vehicle controller.

[0072] In an embodiment of the present application, a blind spot prompting method is provided, including: determining a target blind spot of a target vehicle according to a route to be driven by the target vehicle; obtaining a first environmental image captured by an environmental camera corresponding to the target blind spot; performing target detection based on the first environmental image, generating first state information of each traffic participant in the target blind spot; generating and displaying an environmental modeling image containing traffic participants based on the first state information of traffic participants. The target vehicle can promptly notice traffic participants in the blind spot, which helps to improve the driving safety of the target vehicle, and by performing target detection on the target blind spot determined by the route to be driven by the target vehicle and identifying traffic participants in the blind spot, the target vehicle can avoid processing images of all environmental cameras in the current environment, which reduces the amount of data that needs to be processed during the blind spot detection process to a certain extent, and helps to improve the efficiency and speed of blind spot prompting for the target vehicle. BRIEF DESCRIPTION OF THE DRAWINGS

[0073] Figure 1 It is a flowchart of the steps of a blind spot prompt method provided by an embodiment of the present application;

[0074] Figure 2 is a flowchart of another blind spot prompting method provided by an embodiment of the present application;

[0075] Figure 3 This is a schematic diagram of adjusting the framing orientation provided in an embodiment of the present application;

[0076] Figure 4 is a focal length adjustment schematic diagram provided in an embodiment of the present application;

[0077] Figure 5 is a schematic diagram of an environment modeling image provided by an embodiment of the present application;

[0078] Figure 6 It is a logic block diagram of a blind spot prompt device provided in an embodiment of the present application;

[0079] Figure 7 It is a structural schematic diagram of an electronic device provided in an embodiment of the present application. DETAILED DESCRIPTION

[0080] The following will be combined with the drawings in the embodiments of the present application to clearly describe the technical solutions in the embodiments of the present application. Obviously, the described embodiments are part of the embodiments of the present application, rather than all the embodiments. All other embodiments obtained by ordinary technicians in this field based on the embodiments in the present application belong to the scope of protection of this application.

[0081] The terms "first", "second", etc. in the specification and claims of the present application are used to distinguish similar objects, and are not used to describe a specific order or sequence. It should be understood that the data used in this way can be interchangeable under appropriate circumstances, so that the embodiments of the present application can be implemented in an order other than those illustrated or described here, and the objects distinguished by "first", "second", etc. are generally of one type, and the number of objects is not limited. For example, the first object can be one or more. In addition, "and / or" in the specification and claims represents at least one of the connected objects, and the character " / " generally indicates that the objects associated with each other are in an "or" relationship.

[0082] The blind spot prompt method provided by the embodiment of the present application is described in detail below through specific embodiments and application scenarios in conjunction with the accompanying drawings.

[0083] Reference Figure 1 , Figure 1 A flowchart of a blind spot prompting method provided by an embodiment of the present application is shown. Figure 1 As shown, the method may specifically include the following steps:

[0084] Step 101, determining a target blind spot of a target vehicle according to a route to be traveled by the target vehicle.

[0085] In an embodiment of the present application, the route to be driven of the target vehicle can be obtained, and the target blind spot of the target vehicle can be determined based on the route to be driven. Among them, the route to be driven of the target vehicle can be determined based on the navigation route, automatic driving route and other routes of the target vehicle. For example, the driver of the target vehicle can start the automatic driving system by setting the destination, and the automatic driving system can plan the automatic driving route according to the current position and destination of the target vehicle, and can intercept a section of the route of preset length from the automatic driving route in the driving direction of the target vehicle as the above-mentioned route to be driven. In addition, the route to be driven can also be predicted based on information such as the vehicle position and driving direction of the target vehicle. For example, if the target vehicle is currently in the middle of a certain road, a section of the route of preset length can be intercepted from the extension line of the driving direction of the target vehicle on the road as the above-mentioned route to be driven. It should be noted that the embodiment of the present application does not specifically limit the length of the above-mentioned route to be driven. The length of the route to be driven can be a preset length, or it can be the same as the length of the automatic driving route or the navigation route. The above-mentioned preset length can also change dynamically according to the driving speed of the target vehicle, so that the higher the driving speed of the target vehicle, the longer the corresponding preset length.

[0086] The target blind spot of the target vehicle can be determined according to the route to be driven, and the target blind spot of the target vehicle can be determined from the periphery of the route to be driven. The visual blind spot can refer to an area where it is difficult to clearly observe the whole picture from the perspective of the target vehicle. The visual blind spot can include but is not limited to the road area, the drivable area, the ground area, etc., and the embodiments of the present application do not specifically limit it.

[0087] Specifically, in one embodiment, the target blind spot can be determined from the road that intersects the route to be traveled, and a section whose road curvature deviates from the road curvature at the location of the target vehicle by more than or equal to a preset difference can be determined from the road corresponding to the route to be traveled, as the target blind spot, so that a blind bend section can be determined from the road corresponding to the route to be traveled.

[0088] In another embodiment, the target vehicle can detect the surrounding road surface based on the visual image and / or point cloud map taken by the vehicle to obtain a first road surface area, and then extract a map area within a preset range near the route to be traveled from the road map, and match the first road surface area with a second ground area in the above map area to obtain a road surface area in the second ground area that is not covered by the above first road surface area, and this road surface area can be used as the target blind spot of the target vehicle.

[0089] In addition, the target blind spot of the target vehicle can also be determined by other methods, for example, a three-dimensional environmental model of the current environment is obtained, a local environmental model within a preset range is extracted from the three-dimensional environmental model according to the route to be driven, and then the drivable area in the local environmental model is gridded, and the blind spot grid is determined according to the line of sight obstruction relationship between each grid and the target vehicle, and finally the collection of all blind spot grids is used as the target blind spot of the target vehicle.

[0090] Step 102: Acquire a first environment image captured by an environment camera corresponding to the target blind spot.

[0091] In the embodiment of the present application, after determining the target blind spot, the first environment image captured by the environment camera corresponding to the target blind spot can be obtained. The environment camera refers to a camera set in the external environment where the target vehicle is located. The environment camera may include but is not limited to any camera that may be set in the external environment, such as a surveillance camera, a license plate recognition camera, and a panoramic camera. The external environment may include but is not limited to open-air parking lots, underground parking lots, municipal roads, communities, etc., which are not specifically limited in the embodiment of the present application.

[0092] The environmental camera corresponding to the target blind spot indicates the environmental camera whose viewing range overlaps with the target blind spot. In the embodiment of the present application, the environmental images captured by all environmental cameras in the external environment of the target vehicle can be obtained, and then the viewing range thereof can be identified based on the environmental images, and the viewing range can be matched with the target blind spot, and the first environmental image whose viewing range overlaps with the target blind spot can be determined from all environmental images. It is also possible to obtain the viewing range information of each environmental camera, directly determine the environmental camera corresponding to the target blind spot based on the viewing range information, and then obtain the first environmental images captured by these environmental cameras, thereby improving the acquisition efficiency and avoiding unnecessary image transmission.

[0093] Exemplarily, the external environment may be an underground parking lot, and the environmental camera may be a surveillance camera in the underground parking lot. After the target vehicle enters the underground parking lot area, a "video image extraction" button may be displayed on the central control screen of the target vehicle. After the user clicks the button, the target vehicle discovers and identifies the surveillance camera in the underground parking lot through the V2X (Vehicle to Everything) vehicle network protocol, and establishes a communication connection with it. The communication connection may be a direct connection or relayed by a server. Then, the target vehicle may directly read the viewing range information from the surveillance camera, or obtain the viewing range information of each surveillance camera from the server based on the identification information of the surveillance camera, determine the surveillance camera corresponding to the target blind spot according to the viewing range information and the target blind spot, and then send a data request to the surveillance camera corresponding to the target blind spot, thereby obtaining the real-time image or video stream of the surveillance camera corresponding to the target blind spot.

[0094] Step 103: Perform target detection based on the first environmental image to generate first status information of each traffic participant in the target blind spot.

[0095] After obtaining the first environmental image, target detection can be performed based on the first environmental image to determine the first state information of each traffic participant in the target blind spot. The first state information may include but is not limited to the participant type, participant speed, participant position, participant size, participant posture, etc. The above target detection method can be performed based on a target detection model, which may include a YOLO series model, a DETR model, a RetinaNet model, etc. Traffic participants may include but are not limited to other motor vehicles, non-motor vehicles, pedestrians, animals, etc., and the embodiments of this application do not make specific limitations.

[0096] In one embodiment, target detection can be performed for each first environment image separately, and each first environment image is input into a target detection model to obtain a target detection result corresponding to each first environment image, and then the target detection results corresponding to each first environment image are merged, and duplicate targets are removed to obtain the first state information of each traffic participant in the target blind spot. In another embodiment, each first environment image is panoramically stitched to obtain a panoramic image corresponding to the target blind spot, and then the panoramic image is input into a target detection model to obtain a target detection result, and the first state information of each traffic participant in the target blind spot is directly determined according to the target detection result, thereby improving the efficiency of obtaining the first state information.

[0097] Step 104: Based on the first status information of the traffic participant, generate and display an environment modeling image including the traffic participant.

[0098] In an embodiment of the present application, an environmental modeling image including traffic participants can be generated based on the first status information of traffic participants and the environmental modeling image can be displayed on the screen of the target vehicle, thereby reminding the driver of the target vehicle to pay attention to traffic participants in the target blind spot through the environmental modeling image, thereby improving driving safety.

[0099] Among them, the environmental modeling image refers to an image of a two-dimensional model or a three-dimensional model of the environment established by the target vehicle based on the surrounding environment data collected by its sensor system (such as a camera, radar, lidar, etc.), and the environmental modeling image can provide visual environmental information to the driver or passengers on the display screen of the target vehicle. It should be noted that the above-mentioned surrounding environment data can be derived from the target vehicle's perception of the surrounding environment, or from high-precision map data, three-dimensional map data, etc., and the embodiments of this application do not specifically limit it.

[0100] It should be noted that the surrounding environment data used to establish the above-mentioned two-dimensional environmental model or the three-dimensional environmental model may include scene information detected based on the above-mentioned first environmental image, and the scene information may include but is not limited to obstacles, drivable areas, etc., so that the environmental modeling image can not only include traffic participants in the target blind spot, but also the environmental structure of the target blind spot, thereby further improving the accuracy of the environmental modeling image.

[0101] In addition, the above-mentioned environmental modeling images can also be used in the target vehicle's assisted driving system or autonomous driving system, thereby providing the target vehicle's assisted driving system or autonomous driving system with a blind spot vision of the target blind spot, thereby improving the safety and accuracy of the assisted driving system or autonomous driving system.

[0102] In an embodiment of the present application, the target blind spot of the target vehicle is determined according to the route to be driven by the target vehicle; the first environmental image captured by the environmental camera corresponding to the target blind spot is obtained; target detection is performed based on the first environmental image to generate the first state information of each traffic participant in the target blind spot; based on the first state information of the traffic participant, an environmental modeling image including the traffic participant is generated and displayed. The target vehicle can promptly notice the traffic participants in the blind spot, which helps to improve the driving safety of the target vehicle. By performing target detection on the target blind spot determined by the route to be driven by the target vehicle and identifying the traffic participants in the blind spot, the target vehicle can avoid processing the images of all environmental cameras in the current environment, which reduces the amount of data that needs to be processed during the blind spot detection process to a certain extent, and helps to improve the efficiency and speed of blind spot reminders for the target vehicle.

[0103] like Figure 2 As shown, Figure 2 A flowchart of another blind spot prompting method provided in an embodiment of the present application, the method may include:

[0104] Step 201 , when the memory parking function of the target vehicle is activated, obtaining the memory parking route of the target vehicle.

[0105] The Memory Parking Function is an intelligent vehicle assistance system designed to help drivers park more easily in narrow or complex parking environments (such as underground parking lots). This function is mainly achieved by recording the vehicle's previous parking paths and operations. The Memory Parking Function can help users automatically cruise and park in a parking space according to the memorized route, or automatically park out of the parking space and cruise to the starting point of the route. After the user turns on the route learning function of the target vehicle, he can drive the target vehicle from the starting point of the route (such as the entrance to the underground parking lot) to park in the parking space. After the target vehicle completes the learning, the user comes to the starting point of the route again and can automatically park through the automatic parking function of the target vehicle.

[0106] The memory parking function can usually be used in underground parking lots, open-air parking lots, scenic spots, communities, parks and other scenes. These scenes are usually complex in structure and may have many ups and downs, turns and intersections. Especially at night or in certain indoor areas, there may be dim light and poor visual effects, which can easily lead to visual blind spots and cause safety accidents.

[0107] In the embodiment of the present application, the state of the memory parking function can be detected, and when the memory parking function is in an activated state, the memory parking route of the target vehicle is obtained. Specifically, when it is detected that the target vehicle is traveling on the memory parking route or in the target parking space memorized by the memory parking function, the memory parking function can be activated.

[0108] Step 202, determining the route to be traveled according to the memorized parking route.

[0109] In the embodiment of the present application, after obtaining the memory parking route of the target vehicle, the memory parking route can be directly used as the route to be driven, thereby realizing the blind spot reminder of the entire memory parking route. Alternatively, a section of the memory parking route within a preset distance from the target vehicle can be used as the route to be driven. The embodiment of the present application is not specifically limited.

[0110] Step 203: determining the target blind spot based on the route to be traveled.

[0111] By obtaining the target vehicle's memory parking route when the target vehicle's memory parking function is activated, determining the route to be driven based on the memory parking route, and determining the target blind spot based on the route to be driven, it is possible to determine whether the vehicle is in a place where blind spots appear frequently based on whether the memory parking function is activated, thereby detecting the blind spot in this case, improving the accuracy of blind spot detection, and improving the safety of the vehicle when executing the automatic parking function. In addition, when the automatic parking function is activated, the blind spot on the parking route can be detected through images taken by an external camera, and dangerous traffic participants in the blind spot can be determined, which helps to improve the driving safety of the vehicle during the execution of the automatic parking function.

[0112] Optionally, step 203 may include:

[0113] Sub-step 2031, determining a first ground area within a preset range of the route to be traveled.

[0114] In the embodiment of the present application, the first ground area can be determined according to the route to be traveled. Specifically, the route to be traveled can be firstly projected onto a map or an environmental model, and then a preset range can be expanded to both sides of the route to be traveled to obtain a target area, and a ground area can be extracted from the target area of ​​the map or environmental model to obtain the first ground area.

[0115] Optionally, sub-step 2031 may include:

[0116] Sub-step 20311, obtaining the complete environment image of the current environment scene captured by the environment camera.

[0117] In the embodiment of the present application, a complete environment image of the current environment scene captured by the environment camera can be obtained. Specifically, the environment images captured by all environment cameras in the current environment scene can be obtained, and all environment images can be panoramically stitched to obtain a complete environment image.

[0118] Exemplarily, the current environment scene may be an underground parking lot, and the environment images captured by all surveillance cameras in the underground parking lot may be acquired, and these environment images may be panoramically stitched to obtain a complete environment image of the underground parking lot.

[0119] Among them, the above-mentioned environmental model can be pre-collected, or it can be obtained by performing environmental recognition on the environmental image taken by the environmental camera and real-time modeling based on the recognition result. The embodiment of the present application does not make specific limitations on this.

[0120] Sub-step 20312, identifying the complete ground area of ​​the current environment scene based on the complete environment image.

[0121] After the complete environment image is obtained, the complete ground area of ​​the current environment scene can be identified according to the complete environment image. Specifically, the complete environment image can be input into a ground detection model constructed based on a neural network model to obtain the complete ground area output by the ground detection model.

[0122] Sub-step 20313: determining the first ground area from the complete ground area based on the route to be traveled and the preset range.

[0123] After obtaining the complete ground area, the route to be driven and the complete ground area can be projected into the same coordinate system, and the route to be driven is expanded by a preset range in the coordinate system to obtain a target area, and then the ground area in the target area is extracted to obtain a first ground area. The preset range can be described by a preset expansion direction and a preset expansion distance. For example, the preset direction can be both sides of the route, and the preset distance can be 20 meters.

[0124] By acquiring the complete environmental image of the current environmental scene captured by the environmental camera; identifying the complete ground area of ​​the current environmental scene based on the complete environmental image; and determining the first ground area from the complete ground area based on the route to be driven and the preset range. Being able to perform ground detection through the environmental camera image to obtain the complete ground area and determine the first ground area from the complete ground area helps to improve the accuracy of determining the first ground area in an environment with many blind spots.

[0125] Sub-step 2032, determining a second ground area according to the second environment image taken by the target vehicle.

[0126] In an embodiment of the present application, the second environment image can be captured by a camera mounted on the target vehicle, and based on the second environment image, the second ground area can be determined. Since the second environment image is captured by the target vehicle, that is, the second environment image can reflect the field of view of the target vehicle, the second ground area determined by the second environment image can represent the non-blind ground area of ​​the target vehicle. Among them, the second environment image can be captured by the surround view camera of the target vehicle, and can also be captured by the front view camera of the target vehicle, which is not specifically limited in the embodiment of the present application.

[0127] Specifically, the second ground area can be input into the road surface detection model constructed based on the neural network model to obtain the second ground area output by the road surface detection model. It should be noted that the road surface detection can be performed only on the second environmental image to determine the second ground area, or multimodal fusion road surface detection can be performed based on the second environmental image and the environmental point cloud captured by the target vehicle to obtain the second ground area, or road surface detection can be performed only based on the environmental point cloud to obtain the second ground area, which is not specifically limited in the embodiments of the present application.

[0128] Sub-step 2033: acquiring a ground area that does not overlap with the second ground area from the first ground area to obtain a third ground area.

[0129] In an embodiment of the present application, the first ground area may represent a ground area near the route to be traveled, and the second ground area may represent a road surface area that can be directly observed from the perspective of the target vehicle. In order to accurately determine the blind spot near the route to be traveled, the first ground area may be compared with the second ground area, and the portion that does not overlap with the second ground area may be obtained from the first ground area to obtain a third ground area.

[0130] Specifically, the first ground area and the second ground area can be projected to the same coordinate system, which can be a vehicle coordinate system or a world coordinate system, and then the ground area in the first ground area that does not overlap with the second ground area is extracted to obtain a third ground area. The third ground area can accurately reflect the ground area that the target vehicle cannot directly observe near the route to be driven.

[0131] Sub-step 2034, determining the target blind area based on the third ground area.

[0132] In the embodiment of the present application, after obtaining the third ground area, the third ground area can be directly determined as the target blind spot. By determining the first ground area within the preset range of the route to be traveled; determining the second ground area according to the second environmental image taken by the target vehicle; obtaining the ground area that does not overlap with the second ground area from the first ground area to obtain the third ground area, and determining the target blind spot based on the third ground area, the target blind spot can be determined by identifying the ground area that the target vehicle cannot observe, so that the target blind spot can accurately reflect the area where objects that may be in danger of collision are located, thereby improving the reference value of the target blind spot.

[0133] Step 204: Acquire a first environment image captured by an environment camera corresponding to the target blind spot.

[0134] This step can be referred to as step 102, and will not be described in detail in this embodiment of the present application.

[0135] Optionally, step 204 may include:

[0136] Sub-step 2041, obtaining first position information corresponding to each environmental camera and second position information of the target blind spot.

[0137] In an embodiment of the present application, since the scene usually includes a large number of cameras, processing the images generated by these cameras simultaneously requires high computing resources. In order to improve processing efficiency, fewer target cameras can be selected from more environmental cameras, and the first environmental image can be obtained based on the target cameras, thereby improving processing efficiency.

[0138] Specifically, the first position information corresponding to each environmental camera in the current scene and the second position information of the target blind spot can be obtained. The above position information can be a world position, such as longitude and latitude, or a scene position, such as a coordinate position in a parking lot. The first position information of the environmental camera indicates the installation position, shooting position or framing position of the environmental camera, which is not specifically limited in the embodiments of the present application.

[0139] In the embodiment of the present application, the target blind spot may correspond to one second position information, namely, the center point position of the target blind spot. The target blind spot may also correspond to multiple second position information, namely, the vertex positions corresponding to multiple vertices of the target blind spot.

[0140] Sub-step 2042: determining first distances respectively corresponding to the target blind spot and the environment camera based on the first position information and the second position information.

[0141] After obtaining the first position information and the second position information, the first distances respectively corresponding to the target blind spot and each environment camera can be calculated according to the first position information and the second position information. It should be noted that, when the target blind spot corresponds to only one second position information, the first distance between the target blind spot and the environment camera may be the distance between the second position information and the first position information of the environment camera; when the target blind spot corresponds to multiple second position information, the first distance between the target blind spot and the environment camera may be the distance between the first position information of the environment camera and the closest second position information.

[0142] Sub-step 2043: determining, based on the first distance, a target camera from the environmental cameras whose first distance satisfies a preset condition.

[0143] In the embodiment of the present application, the preset condition may include a distance condition, that is, a second distance may be set, such as 50 meters, and the environment camera corresponding to the first distance less than or equal to the second distance is used as the target camera. The preset condition may also include a distance condition and a quantity condition, that is, a second distance and a preset quantity may be set, and the environment cameras corresponding to the smallest preset number of first distances among the first distances less than or equal to the second distance are used as the target cameras.

[0144] Sub-step 2044, obtaining a first environment image captured by the target camera.

[0145] The target camera can be selected from the environmental cameras in the above manner, and then the first environmental image captured by the target camera can be obtained. Specifically, an image transmission instruction can be sent to the target camera based on the V2X vehicle network protocol, so that the target camera can transmit the first environmental image captured in real time to the target vehicle in real time.

[0146] By obtaining the first position information corresponding to each environmental camera and the second position information of the target blind spot; based on the first position information and the second position information, determining the first distances corresponding to the target blind spot and the environmental camera; according to the first distance, determining the target camera whose first distance meets the preset conditions from the environmental cameras; obtaining the first environmental image taken by the target camera. It is possible to filter out fewer target cameras from more environmental cameras, collect the environmental images taken by the target cameras, and obtain fewer first environmental images with higher accuracy, which helps to improve the processing efficiency of subsequent steps.

[0147] Optionally, the first shooting areas corresponding to each environmental camera can be obtained, the first shooting areas can be matched with the target blind spots, the environmental camera whose first shooting areas overlap with the target blind spots can be used as the target camera, and the first environmental image taken by the target camera can be obtained, thereby further improving the accuracy of determining the target camera.

[0148] Optionally, sub-step 2044 may include:

[0149] Sub-step 20441, based on the target blind area and the first shooting area of ​​the target camera, generating an adjustment instruction for the target camera; wherein the adjustment instruction includes a focal length adjustment parameter and / or a framing orientation adjustment parameter.

[0150] In an embodiment of the present application, a first shooting area of ​​a target camera can be obtained, the first shooting area can be matched with a target blind spot, an offset and an offset direction between the first shooting area and the target blind spot can be determined, and an adjustment instruction for the target camera can be generated based on the offset and the offset direction. The adjustment instruction can include a focal length adjustment parameter and / or a framing orientation adjustment parameter, wherein the focal length adjustment parameter can be used to adjust the focal length of the target camera, thereby enlarging or reducing the framing range of the target camera, and the framing orientation adjustment parameter can be used to adjust the shooting angle of the target camera.

[0151] Specifically, in one embodiment, the target blind spot and the first shooting area of ​​the target camera can be projected to the same coordinate system, and the offset direction can be determined based on the non-overlapping area between the first shooting area and the target blind spot and the positional relationship with the target blind spot. The offset amount can be determined based on the size of the non-overlapping area in the offset direction. The framing adjustment direction and direction adjustment amount for the target camera can be determined respectively based on the offset direction and the offset amount to obtain the framing orientation adjustment parameters.

[0152] Reference Figure 3 , Figure 3 A schematic diagram of adjusting the viewing orientation provided by an embodiment of the present application is shown. Figure 3 As shown, the non-overlapping area 33 between the first shooting area 31 and the target blind area 32 captured by the target camera is in the a direction of the target blind area 32, and the size of the non-overlapping area 33 in the a direction is h1. It can be determined that the non-overlapping area is offset by a distance h1 in the a direction, so that the framing adjustment direction can be determined as -a according to the a direction, and then the direction adjustment amount is calculated as r according to the offset h1, so that the target camera is controlled to rotate to the direction -a by an angle r through the framing orientation adjustment parameters including the framing adjustment direction -a and the direction adjustment amount r, so that the target camera is aligned with the target blind area. Among them, the direction adjustment amount can be calculated according to the offset h1, the focal length of the target camera, and the distance between the target camera and the first shooting area.

[0153] In another embodiment, the target blind spot and the first shooting area of ​​the target camera can be projected into the same coordinate system, and the target focal length for the target camera is determined according to the edge distance between the first shooting area and the target blind spot in the coordinate system and the current focal length of the target camera, so that the edge distance between the projection of the image captured by the target camera at the target focal length and the target blind spot in the above coordinate system is 0. The edge distance between the first shooting area and the target blind spot in the coordinate system represents the distance between the closest edges of the first shooting area and the target blind spot in the coordinate system.

[0154] Reference Figure 4 , Figure 4 A schematic diagram of focal length adjustment provided in an embodiment of the present application is shown. Figure 4 As shown, the edge distance between the first shooting area 41 photographed by the target camera and the target blind area 42 is h2. The target focal length can be calculated based on the edge distance h2 and the current focal length of the target camera so that the target camera can obtain a larger first shooting area 43 under the target focal length.

[0155] Sub-step 20442, sending the adjustment instruction to the target camera to adjust the first shooting area of ​​the target camera to the second shooting area.

[0156] In the embodiment of the present application, the target vehicle may send an adjustment instruction to the target camera, so that the target camera controls its own framing direction and / or shooting focal length according to the adjustment instruction, and adjusts the first shooting area to the second shooting area. It should be noted that in the embodiment of the present application, the overlap rate between the second shooting area and the target blind area is greater than or equal to the overlap rate between the first shooting area and the target blind area.

[0157] Sub-step 20443, obtaining the first environment image captured by the target camera based on the second shooting area.

[0158] In the embodiment of the present application, an adjustment instruction for the target camera can be generated based on the target blind spot and the first shooting area of ​​the target camera; wherein the adjustment instruction includes a focal length adjustment parameter and / or a framing orientation adjustment parameter; an adjustment instruction is sent to the target camera to adjust the first shooting area of ​​the target camera to the second shooting area; and a first environment image captured by the target camera based on the second shooting area is obtained. This improves the matching degree between the obtained first environment image and the target blind spot, which helps to improve the efficiency and accuracy of subsequent target detection of the target blind spot based on the first environment image.

[0159] Step 205: Perform target detection based on the first environmental image to generate first status information of each traffic participant in the target blind spot.

[0160] This step can refer to step 103, and will not be described in detail in this embodiment of the present application.

[0161] Exemplarily, after the user drives the target vehicle into the underground parking lot, the vehicle detects that it is currently on an automatic parking route, the automatic parking function is activated, and the automatic driving vehicle begins to drive along the automatic parking route. At this time, the "Video Image Extraction" button can be displayed on the central control screen of the target vehicle. After the user clicks the button, it starts to obtain the route to be driven and determine the target blind spot based on the route to be driven. At the same time, the environmental cameras in the underground parking lot are discovered and identified through the V2X (Vehicle to Everything) vehicle network protocol, the target camera is determined from the environmental cameras, the first environmental image taken in real time by the target camera is obtained, the traffic participants in the target blind spot are identified in real time, and the first status information of each traffic participant in the target blind spot is generated.

[0162] Step 206 : determining a collision probability between the target vehicle and the traffic participant based on the first state information of the traffic participant and the second state information of the target vehicle.

[0163] In the embodiment of the present application, the collision probability between the target vehicle and each traffic participant can be calculated based on the first state information of each traffic participant and the second state information of the target vehicle. The first state information and the second state information may include a variety of motion parameters, and the above motion parameters may include but are not limited to direction, speed, posture, etc.

[0164] In one embodiment, the first motion trajectory of the traffic participant can be predicted based on the first state information, and the second motion trajectory of the target vehicle can be predicted based on the second state information. The collision probability between the traffic participant and the target vehicle is determined according to the closest distance between the first motion trajectory and the second motion trajectory. The smaller the closest distance between the first motion trajectory and the second motion trajectory, the smaller the collision probability, and vice versa. The above motion trajectory can be obtained by a motion trajectory prediction model constructed based on a neural network model.

[0165] In another embodiment, the historical motion trajectory of the traffic participant can be determined based on the first state information and the historical first state information of the traffic participant, and the first motion trajectory of the traffic participant in the future can be predicted based on the historical motion trajectory of the traffic participant, and then the closest distance between the first motion trajectory and the target vehicle's to-be-traveled trajectory, as well as the first trajectory point corresponding to the closest distance in the first motion trajectory, and the second trajectory point corresponding to the closest distance on the to-be-traveled trajectory, and then the first time when the traffic participant arrives at the first trajectory point is predicted based on the first state information, and the second time when the target vehicle arrives at the second trajectory point is predicted based on the second state information of the target vehicle, and the time difference between the first time and the second time is determined, and the collision probability between the traffic participant and the target vehicle is calculated based on the above-mentioned closest distance and time difference, the smaller the closest distance, the higher the collision probability, and the smaller the time difference, the higher the collision probability. For example, the above-mentioned collision probability can be calculated using the following formula:

[0166]

[0167] Among them, P collision represents the collision probability, d min represents the closest distance, Δt represents the time difference, α and β represent the positive parameters that control the weights of the distance and time difference, respectively, and exp() represents the exponential function.

[0168] In yet another embodiment, the target distance between the traffic participant and the target vehicle can be calculated based on the first position of the traffic participant in the target blind spot and the second position of the target vehicle, and the collision probability can be determined based on the first speed of the traffic participant and the above target distance. The closer the target distance and the higher the first speed of the traffic participant, the higher the corresponding collision probability.

[0169] Step 207 : determining rendering parameters of the traffic participant based on the collision probability.

[0170] In the embodiment of the present application, the rendering parameters of the traffic participants can be determined based on the collision probability, so that different traffic participants can be rendered with different rendering parameters, and thus presented in different ways in the environmental modeling image to achieve the purpose of reminder. Among them, the rendering parameters may include but are not limited to at least one of color parameters, size parameters, brightness parameters, and stroke parameters. The technicians can flexibly set the rendering parameters corresponding to different collision probabilities according to actual business needs, and the embodiment of the present application does not make specific limitations.

[0171] Exemplarily, when the rendering parameters include colors, the correspondence between different collision probabilities and different colors can be preset, for example, a collision probability greater than a first probability corresponds to red; a collision probability less than or equal to the first probability and greater than the second probability corresponds to yellow; a collision probability less than or equal to the third probability corresponds to gray; wherein the first probability is greater than the second probability, and the second probability is greater than the third probability.

[0172] Step 208 , based on the rendering parameters, rendering the participant model of the traffic participant in the environment model to obtain the environment modeling image.

[0173] The rendering parameters corresponding to each traffic participant determined above can be used to render the participant model corresponding to the traffic participant in the environment model, and obtain an environment modeling image containing the participant model. Traffic participants with different collision probabilities can be presented in different ways in the environment modeling image, thereby increasing the probability of users noticing traffic participants with high collision probabilities, thereby improving the driving safety of the target vehicle.

[0174] Among them, the above-mentioned environmental model can be generated based on the environmental image taken by the environmental camera, and can also be generated based on the map information that has been collected; the above-mentioned environmental model can be a two-dimensional model or a three-dimensional model, and the dimensions of the above-mentioned participant model and the environmental model can be the same.

[0175] It should be noted that the collision reminder based on the above collision probability may include not only the environment modeling image, but also sound, vibration, etc. For example, when a traffic participant with a collision probability greater than the above second probability is detected, a reminder may be issued to the driver through steering wheel vibration.

[0176] In addition, the first state information, collision probability and other information of the above-mentioned traffic participants can also be provided to the automatic driving module or the automatic emergency braking system (Autonomous Emergency Braking, AEB), so that the automatic driving module can avoid the traffic participants and the automatic emergency braking system can brake in time to avoid collision.

[0177] Based on the first state information of the traffic participant and the second state information of the target vehicle, the collision probability between the target vehicle and the traffic participant is determined; based on the collision probability, the rendering parameters of the traffic participant are determined; based on the rendering parameters, the participant model of the traffic participant is rendered in the environment model to obtain the environment modeling image, which enables traffic participants with different collision probabilities to be presented in different ways in the environment modeling image, thereby helping to improve the effectiveness of blind spot reminders, thereby improving the driving safety of the target vehicle.

[0178] Reference Figure 5 , Figure 5A schematic diagram of an environment modeling image provided by an embodiment of the present application is shown. Figure 5 As shown, a target blind spot 52 is determined according to a route 51 to be traveled, and a traffic participant 53 is included in the target blind spot 52. If it is detected that the probability of collision between the traffic participant 53 and the target vehicle 54 is high, the traffic participant 53 can be rendered in red to remind the driver to pay attention to the collision risk.

[0179] In an embodiment of the present application, the target blind spot of the target vehicle is determined according to the route to be driven by the target vehicle; the first environmental image captured by the environmental camera corresponding to the target blind spot is obtained; target detection is performed based on the first environmental image to generate the first state information of each traffic participant in the target blind spot; based on the first state information of the traffic participant, an environmental modeling image including the traffic participant is generated and displayed. The target vehicle can promptly notice the traffic participants in the blind spot, which helps to improve the driving safety of the target vehicle. By performing target detection on the target blind spot determined by the route to be driven by the target vehicle and identifying the traffic participants in the blind spot, the target vehicle can avoid processing the images of all environmental cameras in the current environment, which reduces the amount of data that needs to be processed during the blind spot detection process to a certain extent, and helps to improve the efficiency and speed of blind spot reminders for the target vehicle.

[0180] like Figure 6 As shown, Figure 6 A logic block diagram of a blind spot warning device provided in an embodiment of the present application, the blind spot warning device 600 may include:

[0181] The blind spot module 601 is used to determine the target blind spot of the target vehicle according to the route to be driven by the target vehicle;

[0182] An image module 602 is used to obtain a first environment image captured by an environment camera corresponding to the target blind spot;

[0183] A parameter module 603 is used to perform target detection based on the first environmental image and generate first status information of each traffic participant in the target blind spot;

[0184] The display module 604 is used to generate and display an environment modeling image including the traffic participant based on the first state information of the traffic participant.

[0185] Optionally, the blind area module includes:

[0186] A parking route submodule, used for obtaining a memory parking route of the target vehicle when the memory parking function of the target vehicle is activated;

[0187] A route to be traveled submodule, used to determine the route to be traveled according to the memorized parking route;

[0188] The blind spot determination submodule is used to determine the target blind spot based on the route to be traveled.

[0189] Optionally, the target blind area determination submodule includes:

[0190] A first ground area unit, used to determine a first ground area within a preset range of the to-be-traveled route;

[0191] A second ground area unit, used to determine a second ground area according to a second environment image taken by the target vehicle;

[0192] A third ground area unit is used to obtain a ground area that does not overlap with the second ground area from the first ground area to obtain a third ground area;

[0193] A target blind area determining unit is configured to determine the target blind area based on the third ground area.

[0194] Optionally, the first ground area unit includes:

[0195] The complete environment image subunit is used to obtain the complete environment image of the current environment scene captured by the environment camera;

[0196] A complete ground area subunit, configured to identify a complete ground area of ​​the current environment scene based on the complete environment image;

[0197] The first ground area determining subunit is used to determine the first ground area from the complete ground area based on the to-be-traveled route and the preset range.

[0198] Optionally, the imaging module includes:

[0199] A position information submodule, used to obtain first position information corresponding to each environmental camera and second position information of the target blind spot;

[0200] A first distance submodule, configured to determine first distances respectively corresponding to the target blind spot and the environment camera based on the first position information and the second position information;

[0201] A target camera submodule, configured to determine, according to the first distance, a target camera from among the environment cameras whose first distance satisfies a preset condition;

[0202] The environmental image acquisition submodule is used to acquire the first environmental image taken by the target camera.

[0203] Optionally, the first environmental image acquisition submodule includes:

[0204] An adjustment instruction unit, configured to generate an adjustment instruction for the target camera based on the target blind area and the first shooting area of ​​the target camera; wherein the adjustment instruction includes a focal length adjustment parameter and / or a framing orientation adjustment parameter;

[0205] An instruction sending unit, used for sending the adjustment instruction to the target camera to adjust the first shooting area of ​​the target camera to the second shooting area;

[0206] The first environment image acquisition unit is used to acquire a first environment image captured by the target camera based on the second shooting area.

[0207] Optionally, the display module includes:

[0208] A collision probability submodule, for determining a collision probability between the target vehicle and the traffic participant based on the first state information of the traffic participant and the second state information of the target vehicle;

[0209] A rendering parameter submodule, used to determine the rendering parameters of the traffic participant based on the collision probability;

[0210] The rendering submodule is used to render the participant model of the traffic participant in the environment model based on the rendering parameters to obtain the environment modeling image.

[0211] In summary, a blind spot warning device provided by an embodiment of the present application includes: a blind spot module, which is used to determine the target blind spot of a target vehicle according to the route to be driven by the target vehicle; an image module, which is used to obtain a first environmental image captured by an environmental camera corresponding to the target blind spot; a parameter module, which is used to perform target detection based on the first environmental image and generate first state information of each traffic participant in the target blind spot; and a display module, which is used to generate and display an environmental modeling image containing traffic participants based on the first state information of traffic participants. The target vehicle can promptly notice the traffic participants in the blind spot, which helps to improve the driving safety of the target vehicle. By performing target detection on the target blind spot determined by the route to be driven by the target vehicle and identifying the traffic participants in the blind spot, the target vehicle can avoid processing the images of all environmental cameras in the current environment, which reduces the amount of data that needs to be processed during the blind spot detection process to a certain extent, and helps to improve the efficiency and speed of blind spot warnings for the target vehicle.

[0212] The blind spot prompt device in the embodiment of the present application can be an electronic device, or a component in the electronic device, such as an integrated circuit or a chip. The electronic device can be a terminal, or it can be other devices other than the terminal. Exemplarily, the electronic device can be a GPU BOX, a mobile phone, a tablet computer, a laptop computer, a PDA, a vehicle-mounted electronic device, a mobile Internet device (Mobile Internet Device, MID), an augmented reality (augmented reality, AR) / virtual reality (virtual reality, VR) device, a robot, a wearable device, an ultra-mobile personal computer (ultra-mobile personal computer, UMPC), a netbook or a personal digital assistant (personal digital assistant, PDA), etc., and can also be a server, a network attached storage (Network Attached Storage, NAS), a personal computer (personal computer, PC), a television (television, TV), a teller machine or a self-service machine, etc., which is not specifically limited in the embodiment of the present application.

[0213] The blind spot warning device in the embodiment of the present application may be a device having an operating system. The operating system may be an Android operating system, a Linux operating system, a Windows operating system, or other possible operating systems, which are not specifically limited in the embodiment of the present application.

[0214] The blind spot warning device provided in the embodiment of the present application can achieve Figures 1 to 5 To avoid repetition, the various processes implemented by the method embodiment are not described here.

[0215] Alternatively, if Figure 7 As shown, an embodiment of the present application also provides an electronic device M00, including a processor M01 and a memory M02, wherein the memory M02 stores programs or instructions that can be run on the processor M01, and when the program or instructions are executed by the processor M01, the various steps of the above-mentioned blind spot prompt method embodiment are implemented, and the same technical effect can be achieved. To avoid repetition, they will not be repeated here.

[0216] In an embodiment of the present application, the memory M02 can be used to store software programs and various data. The memory M02 may mainly include a first storage area for storing programs or instructions and a second storage area for storing data, wherein the first storage area may store an operating system, an application program or instructions required for at least one function (such as a sound playback function, an image playback function, etc.), etc. In addition, the memory M02 may include a volatile memory or a non-volatile memory, or the memory x09 may include both volatile and non-volatile memories. Among them, the non-volatile memory may be a read-only memory (ROM), a programmable read-only memory (PROM), an erasable programmable read-only memory (EPROM), an electrically erasable programmable read-only memory (EEPROM), or a flash memory. The volatile memory may be a random access memory (RAM), a static random access memory (SRAM), a dynamic random access memory (DRAM), a synchronous dynamic random access memory (SDRAM), a double data rate synchronous dynamic random access memory (DDRSDRAM), an enhanced synchronous dynamic random access memory (ESDRAM), a synchronous link dynamic random access memory (SLDRAM) and a direct memory bus random access memory (DRRAM). The memory M02 in the embodiment of the present application includes but is not limited to these and any other suitable types of memories.

[0217] The processor M01 may include one or more processing units; optionally, the processor M01 integrates an application processor and a modem processor, wherein the application processor mainly processes operations related to an operating system, a user interface, and application programs, and the modem processor mainly processes wireless communication signals, such as a baseband processor. It is understandable that the modem processor may not be integrated into the processor M01.

[0218] An embodiment of the present application also provides a readable storage medium, on which a program or instruction is stored. When the program or instruction is executed by a processor, the various processes of the above-mentioned blind spot prompt method embodiment are implemented, and the same technical effect can be achieved. To avoid repetition, it will not be repeated here.

[0219] The processor is the processor in the electronic device described in the above embodiment. The readable storage medium includes a computer readable storage medium, such as a computer read-only memory ROM, a random access memory RAM, a magnetic disk or an optical disk.

[0220] An embodiment of the present application further provides a chip, which includes a processor and a communication interface, wherein the communication interface is coupled to the processor, and the processor is used to run programs or instructions to implement the various processes of the above-mentioned blind spot prompt method embodiment, and can achieve the same technical effect. To avoid repetition, it will not be repeated here.

[0221] It should be understood that the chip involved in the embodiments of the present application can also be called a system-level chip, a system chip, a chip system or a system-on-chip chip, etc.

[0222] An embodiment of the present application provides a computer program product, which is stored in a storage medium. The program product is executed by at least one processor to implement the various processes of the blind spot prompt method embodiment described above, and can achieve the same technical effect. To avoid repetition, it will not be repeated here.

[0223] An embodiment of the present application also provides a vehicle controller, which includes a memory, a processor, and a computer program stored in the memory and executable on the processor. When the processor executes the computer program, each process of the blind spot warning method embodiment described above is implemented, and the same technical effect can be achieved. To avoid repetition, it will not be described here.

[0224] An embodiment of the present application also provides a vehicle, comprising the above-mentioned vehicle controller.

[0225] It should be noted that, in this article, the terms "comprise", "include" or any other variant thereof are intended to cover non-exclusive inclusion, so that the process, method, article or device including a series of elements includes not only those elements, but also includes other elements not explicitly listed, or also includes elements inherent to such process, method, article or device. In the absence of further restrictions, the elements defined by the sentence "comprise one..." do not exclude the presence of other identical elements in the process, method, article or device including the element. In addition, it should be pointed out that the scope of the methods and devices in the embodiments of the present application is not limited to performing functions in the order shown or discussed, and may also include performing functions in a substantially simultaneous manner or in reverse order according to the functions involved, for example, the described method may be performed in an order different from that described, and various steps may also be added, omitted, or combined. In addition, the features described with reference to certain examples may be combined in other examples.

[0226] Through the description of the above implementation methods, those skilled in the art can clearly understand that the above-mentioned embodiment methods can be implemented by means of software plus a necessary general hardware platform, and of course by hardware, but in many cases the former is a better implementation method. Based on such an understanding, the technical solution of the present application, or the part that contributes to the relevant technology, can be embodied in the form of a computer software product, which is stored in a storage medium (such as ROM / RAM, a disk, or an optical disk), and includes a number of instructions for a terminal (which can be a mobile phone, a computer, a server, or a network device, etc.) to execute the methods described in each embodiment of the present application.

[0227] The embodiments of the present application are described above in conjunction with the accompanying drawings, but the present application is not limited to the above-mentioned specific implementation methods. The above-mentioned specific implementation methods are merely illustrative and not restrictive. Under the guidance of the present application, ordinary technicians in this field can also make many forms without departing from the purpose of the present application and the scope of protection of the claims, all of which are within the protection of the present application.

Claims

1. A blind spot prompting method, characterized in that: The method comprises: Determining a target blind spot of the target vehicle according to the route to be traveled by the target vehicle; Acquire a first environmental image captured by an environmental camera corresponding to the target blind spot; Performing target detection based on the first environmental image to generate first status information of each traffic participant in the target blind spot; Based on the first status information of the traffic participant, an environment modeling image including the traffic participant is generated and displayed.

2. The method according to claim 1, characterized in that The step of determining a target blind spot of the target vehicle according to the route to be traveled by the target vehicle comprises: When the memory parking function of the target vehicle is activated, obtaining a memory parking route of the target vehicle; Determining the route to be traveled according to the memorized parking route; The target blind spot is determined based on the route to be traveled.

3. The method according to claim 2, characterized in that The step of determining the target blind spot based on the route to be traveled comprises: Determine a first ground area within a preset range of the route to be traveled; Determining a second ground area according to a second environmental image taken by the target vehicle; Acquire a ground area that does not overlap with the second ground area from the first ground area to obtain a third ground area; The target blind area is determined based on the third ground area.

4. The method according to claim 3, characterized in that The step of determining a first ground area within a preset range of the route to be traveled comprises: Get the complete environment image of the current environment scene captured by the environment camera; Identify the complete ground area of ​​the current environment scene based on the complete environment image; The first ground area is determined from the complete ground area based on the to-be-traveled route and the preset range.

5. The method according to claim 1, characterized in that: The step of obtaining a first environment image captured by an environment camera corresponding to the target blind spot includes: Obtaining first position information corresponding to each environmental camera and second position information of the target blind spot; Based on the first position information and the second position information, determining first distances respectively corresponding to the target blind spot and the environment camera; According to the first distance, determining a target camera from the environment cameras whose first distance meets a preset condition; A first environment image captured by the target camera is acquired.

6. The method according to claim 5, characterized in that The step of obtaining a first environment image captured by the target camera includes: Based on the target blind area and the first shooting area of ​​the target camera, generating an adjustment instruction for the target camera; wherein the adjustment instruction includes a focal length adjustment parameter and / or a framing orientation adjustment parameter; Sending the adjustment instruction to the target camera to adjust the first shooting area of ​​the target camera to the second shooting area; A first environment image captured by the target camera based on the second shooting area is obtained.

7. The method according to claim 1, characterized in that The step of generating and displaying an environment modeling image including the traffic participant based on the first state information of the traffic participant includes: Determining a collision probability between the target vehicle and the traffic participant based on the first state information of the traffic participant and the second state information of the target vehicle; determining rendering parameters of the traffic participant based on the collision probability; Based on the rendering parameters, the participant model of the traffic participant is rendered in the environment model to obtain the environment modeling image.

8. A blind spot warning device, characterized in that: The device comprises: A blind spot module, used to determine a target blind spot of the target vehicle according to the route to be driven by the target vehicle; An imaging module, used for acquiring a first environmental image captured by an environmental camera corresponding to the target blind spot; a parameter module, configured to perform target detection based on the first environmental image and generate first status information of each traffic participant in the target blind spot; A display module is used to generate and display an environment modeling image containing the traffic participant based on the first state information of the traffic participant.

9. An electronic device, characterized in that: The electronic device comprises a processor; and a memory for storing instructions executable by the processor; wherein the processor is configured to execute the instructions to implement the blind spot prompt method according to any one of claims 1 to 7.

10. A storage medium, characterized in that: The readable storage medium stores a program or instruction, and when the program or instruction is executed by the processor, the blind spot prompt method described in any one of claims 1 to 7 is implemented.

Images