Method and device for determining target false alarm type, and terminal

Abstract

The embodiment of the invention provides a target false alarm type determination method and device and a terminal, and is applied to automatic driving or auxiliary driving, and the method comprises the steps: obtaining data collected by a camera device and data collected by a radar, and the data collected by the camera device comprises the information of a guardrail; target indication information of a first target is determined based on the data collected by the camera device and the data collected by the radar, and the target indication information is used for indicating the false alarm type of the first target; the false alarm type of the first target comprises at least one of the first target being a false alarm target outside the guardrail, the first target being a false alarm target on the guardrail, the first target being a false alarm target in the guardrail or the first target being a non-false alarm target. The embodiment of the invention can be applied to an intelligent automobile or an electric automobile, and is helpful for improving the accuracy of identifying the false alarm target, thereby being helpful for improving the safety of the terminal.

Description

Method, device and terminal for determining target false alarm type Technical Field

[0001] The present application relates to the field of intelligent driving, and more specifically, to a method, device, and terminal for determining a target false alarm type. Background Art

[0002] With the development of society and advancements in technology, smart cars are gradually becoming part of people's daily lives. Environmental perception is a crucial component of autonomous and intelligent driving, and a key component in ensuring the safety and intelligence of smart cars. Smart cars typically use sensors such as millimeter-wave radar, lidar, ultrasonic radar, and cameras to perform environmental perception and target measurement, such as measuring the target's position, distance, and speed.

[0003] When a vehicle travels on the road, it uses radar to emit electromagnetic waves and receive echo signals reflected from the targets to identify them. During the process of identifying real targets, the radar's electromagnetic waves experience multipath reflections due to stationary objects on the road. This can make it difficult for the radar to accurately distinguish the echo signals reflected from real targets, resulting in false alarms. These false alarms can negatively impact the accuracy of environmental perception.

[0004] Summary of the Invention

[0005] The present application provides a method, device, and terminal for determining the false alarm type of a target, which are used to identify false alarm targets.

[0006] In the embodiments of the present application, the terminal may include one or more different types of transportation vehicles or movable objects that operate or move on land (e.g., roads, highways, railways, etc.), water (e.g., waterways, rivers, oceans, etc.), or space. For example, the transportation vehicle may include a car, a bicycle, a motorcycle, a train, a subway, an airplane, a ship, an aircraft, a robot, or other types of transportation vehicles or movable objects.

[0007] In a first aspect, a method for determining a target false alarm type is provided, the method comprising: obtaining first data collected by a camera device and second data collected by a radar, the first data including information about a guardrail; determining target indication information of a first target based on the first data and the second data, the target indication information being used to indicate a false alarm type of the first target, the false alarm type of the first target including at least one of the following: the first target being a false alarm target outside the guardrail, the first target being a false alarm target on the guardrail, the first target being a false alarm target inside the guardrail, or the first target being a non-false alarm target.

[0008] In an embodiment of the present application, the first data collected by the camera device and the second data collected by the radar can determine the false alarm type of the first target as at least one of a false alarm target outside the guardrail, a false alarm target on the guardrail, a false alarm target inside the guardrail, and a non-false alarm target. By identifying the false alarm type of the target, it helps to improve the accuracy of identifying the false alarm target, thereby helping to improve the security of the terminal.

[0009] By determining the false alarm type of the target through the first data collected by the camera and the data collected by the radar, it is possible to avoid the accuracy of environmental perception being affected due to the false alarm target being identified by the radar.

[0010] In the embodiments of the present application, the first data includes information about a guardrail as an example for illustration. The first data may also include information about other stationary objects, such as information about a median strip. Thus, the false alarm type of the first target may include at least one of the following: the first target is a false alarm target outside the median strip, the first target is a false alarm target on the median strip, the first target is a false alarm target within the median strip, or the first target is a non-false alarm target.

[0011] In combination with the first aspect, in some implementations of the first aspect, the method further includes: outputting the target indication information.

[0012] In the embodiment of the present application, by outputting the false alarm type of the first target, the functional module can perform corresponding operations according to the false alarm type of the first target, reducing the impact of the false alarm target on the functional module, thereby helping to improve the security of the terminal.

[0013] In some possible implementations, the target indication information includes a first field, where the first field is used to indicate a false alarm type of the first target.

[0014] In an embodiment of the present application, by adding a field for indicating the false alarm type of the first target in the output target indication information, the functional module that receives the target indication information can determine the false alarm type of the first target through the first field, thereby reducing the impact of the false alarm target on the functional module, thereby helping to improve the security of the terminal.

[0015] In some possible implementations, the functional module includes but is not limited to an automatic emergency brake (AEB) module, an adaptive cruise control (ACC) module, or an advanced driver-assistance system (ADAS).

[0016] In combination with the first aspect, in certain implementations of the first aspect, the first target is a target identified by the second data and a target not identified by the first data; wherein, the target indication information of the first target is determined based on the first data and the second data, including: determining the false alarm type of the first target according to the area where the first target is located and the potential false alarm area, the potential false alarm area is determined by the area where the second target is located and the position of the guardrail, or, the potential false alarm area is determined by the position of the guardrail, and the second target is a real target.

[0017] In the embodiment of the present application, the first target may be a target that is not identified by the data collected by the camera device and is identified by the data collected by the radar. The false alarm type of the first target can be determined based on the area where the first target is located and the potential false alarm area determined by the position of the real target and the guardrail. In this way, false alarm targets can be screened out from targets identified only by the data collected by the radar, which helps to improve the accuracy of false alarm target identification, thereby helping to enhance the security of the terminal.

[0018] Since the targets identified only through data collected by the radar include real targets and false alarm targets, when the false alarm type of the first target is output to the functional module, it can help the functional module perform accurate operations and avoid the impact of false alarm targets on the functional module; at the same time, it can also enable the functional module to correctly respond to real targets, thereby enhancing the advantages of using radar sensors.

[0019] In some possible implementations, when the potential false alarm area is determined by the area where the second target is located and the position of the guardrail, the target indication information of the first target is determined based on the first data and the second data, including: determining whether the false alarm type of the first target is a false alarm target outside the guardrail or a false alarm target inside the guardrail based on the area where the first target is located and the potential false alarm area.

[0020] In some possible implementations, when the potential false alarm area is determined by the position of the guardrail, the target indication information of the first target is determined based on the first data and the second data, including: determining whether the false alarm type of the first target is a false alarm target on the guardrail based on the area where the first target is located and the potential false alarm area.

[0021] In combination with the first aspect, in certain implementations of the first aspect, the potential false alarm area includes a mirror image area of ​​the area where the second target is located relative to the guardrail, the area where the guardrail is located, or the area between the guardrail and the area where the second target is located.

[0022] In the embodiment of the present application, the potential false alarm area determined by the area where the second target is located and the position of the guardrail includes the mirror image area of ​​the area where the second target is located relative to the guardrail, the area where the guardrail is located, or the area between the guardrail and the area where the second target is located. In this way, when the terminal is traveling on a road including a guardrail, the false alarm target can be accurately identified by the area where the first target is located and the potential false alarm area, which helps to reduce the impact of false alarm targets caused by guardrails and multipath reflection phenomena on the terminal, helps to improve the accuracy of false alarm target identification, and thus helps to enhance the safety of the terminal.

[0023] In combination with the first aspect, in certain implementations of the first aspect, the false alarm type of the first target is determined based on the area where the first target is located and the potential false alarm area, including: when the first target is outside the guardrail and the area where the first target is located partially overlaps or completely overlaps with the potential false alarm area, the first target is determined as a false alarm target outside the guardrail; or, when the first target is on the guardrail and the area where the first target is located partially overlaps or completely overlaps with the potential false alarm area, the first target is determined as a false alarm target on the guardrail; or, when the first target is inside the guardrail and the area where the first target is located partially overlaps or completely overlaps with the potential false alarm area, the first target is determined as a false alarm target inside the guardrail; or, when the area where the first target is located does not overlap with the potential false alarm area, the first target is determined as a non-false alarm target.

[0024] In the embodiment of the present application, the potential false alarm area can be determined based on the information of the guardrail identified in the data collected by the camera and the location of the second target, thereby determining the false alarm type of the first target based on the area where the first target is located and the potential false alarm area. In this way, false alarm targets can be screened out from targets identified only by data collected by the radar, which helps to improve the accuracy of false alarm target identification and thus helps to enhance the security of the terminal.

[0025] In some possible implementations, the false alarm type of the first target is determined based on the area where the first target is located and the potential false alarm area, including: when the first target is outside the guardrail and the area where the first target is located partially overlaps or completely overlaps with the mirror area, the first target is determined as a false alarm target outside the guardrail; or, when the first target is on the guardrail and the area where the first target is located partially overlaps or completely overlaps with the area where the guardrail is located, the first target is determined as a false alarm target on the guardrail; or, when the first target is inside the guardrail and the area where the first target is located partially overlaps or completely overlaps with the area between the guardrail and the area where the second target is located, the first target is determined as a false alarm target inside the guardrail.

[0026] In some possible implementations, when the first target is outside the guardrail and the area where the first target is located partially or completely overlaps with the mirror area, the first target is determined as a false alarm target outside the guardrail, including: when the first target is outside the guardrail and the degree of overlap between the area where the first target is located and the mirror area is greater than or equal to a preset threshold, the first target is determined as a false alarm target outside the guardrail.

[0027] In some possible implementations, when the first target is located on the guardrail and the area where the first target is located partially or completely overlaps with the area where the guardrail is located, the first target is determined as a false alarm target on the guardrail, including: when the first target is located on the guardrail and the degree of overlap between the area where the first target is located and the area where the guardrail is located is greater than or equal to a preset threshold, the first target is determined as a false alarm target on the guardrail.

[0028] In some possible implementations, when the first target is located within the guardrail and the area where the first target is located partially or completely overlaps with the area between the guardrail and the area where the second target is located, the first target is determined to be a false alarm target within the guardrail, including: when the first target is located within the guardrail and the degree of overlap between the area where the first target is located and the area between the guardrail and the area where the second target is located is greater than or equal to a preset threshold, the first target is determined to be a false alarm target within the guardrail.

[0029] In combination with the first aspect, in certain implementations of the first aspect, the first target is located outside the guardrail, and the second target corresponds to the first target; or, the degree of motion state matching between the second target and the first target is greater than or equal to a first threshold; or, the degree of mirroring between the second target and the first target is greater than or equal to a second threshold.

[0030] In an embodiment of the present application, when a first target is located outside a guardrail, a real target corresponding to the first target can be selected from multiple real targets on the road, or a real target matching the motion state of the first target can be selected from multiple real targets, or a real target whose mirror image degree with the first target is greater than or equal to a second threshold can be selected from multiple real targets, thereby determining a potential false alarm area based on the location of the real target and the guardrail. In this way, false alarm targets located outside the guardrail can be screened out from targets identified only by radar data, which helps improve the accuracy of identifying false alarm targets outside the guardrail, thereby helping to improve the safety of the terminal.

[0031] In combination with the first aspect, in certain implementations of the first aspect, the first target is located within the guardrail, and the second target includes multiple real targets.

[0032] In this embodiment of the present application, when the first target is located within the guardrail, multiple real targets on the road can be identified as second targets, thereby determining a potential false alarm area based on the locations of the multiple real targets and the guardrail. In this way, false alarm targets located within the guardrail can be screened out from targets identified solely through radar data, helping to improve the accuracy of false alarm target identification within the guardrail, thereby helping to enhance terminal safety.

[0033] In combination with the first aspect, in certain implementations of the first aspect, the target indication information further includes a false alarm probability of the first target.

[0034] In an embodiment of the present application, the false alarm probability of the first target can also be output to the functional module. The functional module can perform corresponding operations based on the false alarm type and false alarm probability of the first target, which helps to further reduce the impact of the false alarm target on the functional module, thereby helping to improve the security of the terminal.

[0035] In some possible implementations, the target indication information includes a second field, and the second field is used to indicate the false alarm probability of the first target.

[0036] In an embodiment of the present application, by adding a field for indicating the false alarm probability of the first target in the output target indication information, the functional module that receives the target indication information can determine the false alarm probability of the first target through the second field, which helps to further reduce the impact of the false alarm target on the functional module, thereby helping to improve the security of the terminal.

[0037] In combination with the first aspect, in certain implementations of the first aspect, the first target is located outside the guardrail, and the method further includes: determining the false alarm probability based on at least one of the existence probability of the first target, the degree of overlap between the area where the first target is located and the potential false alarm area, the degree of matching between the motion state of the first target and the motion state of the second target, and the degree of mirroring between the first target and the second target.

[0038] In an embodiment of the present application, the probability that the first target is a false alarm target outside the guardrail can be determined based on at least one of the probability of the first target existing, the degree of overlap between the area where the first target is located and the potential false alarm area, the degree of matching between the motion state of the first target and the motion state of the second target, and the degree of mirroring between the first target and the second target. This helps improve the accuracy of calculating the false alarm probability of the first target. At the same time, the functional module can perform corresponding operations based on the false alarm type and false alarm probability of the first target, which helps further reduce the impact of false alarm targets on the functional module, thereby helping to improve the security of the terminal.

[0039] In combination with the first aspect, in certain implementations of the first aspect, the first target is located within the guardrail, and the method further includes: determining the false alarm probability based on at least one of the probability of existence of the first target, the degree of overlap between the area where the first target is located and the potential false alarm area, and the degree to which the first target is obscured.

[0040] In the embodiment of the present application, the probability that the first target is a false alarm target within the guardrail can be determined based on at least one of the probability of the first target existing, the degree of overlap between the area where the first target is located and the potential false alarm area, and the degree to which the first target is obscured. This helps improve the accuracy of calculating the false alarm probability of the first target. Furthermore, the functional module can perform corresponding operations based on the false alarm type and false alarm probability of the first target, helping to further reduce the impact of false alarm targets on the functional module, thereby helping to improve the security of the terminal.

[0041] In combination with the first aspect, in certain implementations of the first aspect, the first target is located on the guardrail, and the method further includes: determining the false alarm probability based on the existence probability of the first target and at least one of the overlap between the area where the first target is located and the potential false alarm area.

[0042] In the embodiment of the present application, the probability that the first target is a false alarm target on the guardrail is determined based on at least one of the probability of the first target existing and the overlap between the area where the first target is located and the potential false alarm area. This helps improve the accuracy of calculating the false alarm probability of the first target. At the same time, the functional module can perform corresponding operations based on the false alarm type and false alarm probability of the first target, which helps further reduce the impact of false alarm targets on the functional module, thereby helping to improve the security of the terminal.

[0043] In combination with the first aspect, in certain implementations of the first aspect, the second target includes a target identified through the first data, or a target continuously identified through the second data within a preset time period.

[0044] In a second aspect, a device for determining a target false alarm type is provided, the device comprising: an acquisition unit for acquiring first data collected by a camera device and second data collected by a radar, the first data including information about a guardrail; a determination unit for determining target indication information of a first target based on the first data and the second data, the target indication information being used to indicate a false alarm type of the first target, the false alarm type of the first target including at least one of the following: the first target being a false alarm target outside the guardrail, the first target being a false alarm target on the guardrail, the first target being a false alarm target inside the guardrail, or the first target being a non-false alarm target.

[0045] In combination with the second aspect, in some implementations of the second aspect, the device further includes: an output unit, configured to output the target indication information.

[0046] In combination with the second aspect, in certain implementations of the second aspect, the first target is a target identified by the second data and a target not identified by the first data; wherein the determination unit is specifically used to: determine the false alarm type of the first target based on the area where the first target is located and the potential false alarm area, the potential false alarm area is determined by the area where the second target is located and the position of the guardrail, or the potential false alarm area is determined by the position of the guardrail, and the second target is a real target.

[0047] In combination with the second aspect, in certain implementations of the second aspect, the potential false alarm area includes a mirror image area of ​​the area where the second target is located relative to the guardrail, the area where the guardrail is located, or the area between the guardrail and the area where the second target is located.

[0048] In combination with the second aspect, in certain implementations of the second aspect, the determination unit is specifically used to: when the first target is outside the guardrail and the area where the first target is located partially overlaps or completely overlaps with the potential false alarm area, determine the first target as a false alarm target outside the guardrail; or, when the first target is on the guardrail and the area where the first target is located partially overlaps or completely overlaps with the potential false alarm area, determine the first target as a false alarm target on the guardrail; or, when the first target is inside the guardrail and the area where the first target is located partially overlaps or completely overlaps with the potential false alarm area, determine the first target as a false alarm target inside the guardrail; or, when the area where the first target is located does not overlap with the potential false alarm area, determine the first target as a non-false alarm target.

[0049] In combination with the second aspect, in certain implementations of the second aspect, the first target is located outside the guardrail, and the second target corresponds to the first target; or, the degree of motion state matching between the second target and the first target is greater than or equal to a first threshold; or, the degree of mirroring between the second target and the first target is greater than or equal to a second threshold.

[0050] In combination with the second aspect, in certain implementations of the second aspect, the first target is located within the guardrail, and the second target includes multiple real targets.

[0051] In combination with the second aspect, in certain implementations of the second aspect, the target indication information further includes a false alarm probability of the first target.

[0052] In combination with the second aspect, in certain implementations of the second aspect, the first target is located outside the guardrail, and the determination unit is further used to determine the false alarm probability based on at least one of the existence probability of the first target, the degree of overlap between the area where the first target is located and the potential false alarm area, the degree of matching between the motion state of the first target and the motion state of the second target, and the degree of mirroring between the first target and the second target.

[0053] In combination with the second aspect, in certain implementations of the second aspect, the first target is located within the guardrail, and the determination unit is further used to determine the false alarm probability based on at least one of the existence probability of the first target, the degree of overlap between the area where the first target is located and the potential false alarm area, and the degree to which the first target is obscured.

[0054] In combination with the second aspect, in certain implementations of the second aspect, the first target is located on the guardrail, and the determination unit is further used to determine the false alarm probability based on the existence probability of the first target and at least one of the overlap between the area where the first target is located and the potential false alarm area.

[0055] In combination with the second aspect, in some implementations of the second aspect, the second target includes a target identified through the first data, or a target continuously identified through the second data within a preset time period.

[0056] In a third aspect, a device is provided, comprising: a memory for storing computer instructions; and a processor for executing the computer instructions stored in the memory, so that the device executes the method in the first aspect.

[0057] In a fourth aspect, a terminal is provided, which includes the apparatus described in any one of the second or third aspects above.

[0058] In combination with the fourth aspect, in some implementations of the fourth aspect, the terminal is a vehicle.

[0059] In some possible implementations, the terminal may include a camera and a radar.

[0060] In some possible implementations, the terminal may include a functional module.

[0061] In a fifth aspect, a computer program product is provided, comprising: a computer program code, which, when executed on a computer, enables the computer to execute the method in the first aspect.

[0062] The above-mentioned computer program code can be stored in whole or in part on the first storage medium, where the first storage medium can be packaged together with the processor or separately from the processor, and the embodiments of the present application do not specifically limit this.

[0063] In a sixth aspect, a computer-readable medium is provided, wherein the computer-readable medium stores a program code, and when the computer program code is run on a computer, the computer executes the method in the first aspect.

[0064] In a seventh aspect, an embodiment of the present application provides a chip system, which includes a processor for calling a computer program or computer instructions stored in a memory so that the processor executes the method described in the first aspect above.

[0065] In combination with the seventh aspect, in a possible implementation, the processor is coupled to the memory through an interface.

[0066] In combination with the seventh aspect, in a possible implementation, the chip system also includes a memory, in which a computer program or computer instructions are stored.

[0067] In an eighth aspect, a server is provided, which includes the device described in any one of the second or third aspects above.

[0068] In some possible implementations, the server may be a physical server, or the server may be a virtual server.

[0069] In a ninth aspect, a system is provided, which includes the device described in any one of the second or third aspects above.

[0070] In some possible implementations, the system also includes a camera and a radar.

[0071] In some possible implementations, the system further includes a functional module.

[0072] Based on the implementation methods provided in the above aspects, this application can also be further combined to provide more implementation methods. BRIEF DESCRIPTION OF THE DRAWINGS

[0073] FIG1 is a functional block diagram of a vehicle provided in an embodiment of the present application.

[0074] FIG2 is a schematic diagram of a scenario in which a false alarm target is generated according to an embodiment of the present application.

[0075] FIG3 is a schematic block diagram of a system provided in an embodiment of the present application.

[0076] FIG4 is a schematic flowchart of a method for determining a target false alarm type provided in an embodiment of the present application.

[0077] FIG5 is a schematic diagram of a potential false alarm area provided by an embodiment of the present application.

[0078] FIG6 is a schematic diagram of determining the false alarm type of a target by using a potential false alarm area according to an embodiment of the present application.

[0079] FIG7 is another schematic diagram of determining the false alarm type of a target by using a potential false alarm area according to an embodiment of the present application.

[0080] FIG8 is another schematic diagram of determining the false alarm type of a target by using a potential false alarm area according to an embodiment of the present application.

[0081] FIG9 is a schematic flow chart of a method for calculating the false alarm probability of a first target provided in an embodiment of the present application.

[0082] FIG10 is another schematic diagram of an application scenario provided by an embodiment of the present application.

[0083] FIG11 is a schematic block diagram of a device for determining a target false alarm type provided in an embodiment of the present application. DETAILED DESCRIPTION

[0084] The following describes the technical solutions in the embodiments of the present application in conjunction with the accompanying drawings. In the description of the embodiments of the present application, unless otherwise specified, " / " represents "or." For example, A / B can represent A or B. "And / or" in this document is merely a description of the association relationship between associated objects, indicating that three relationships can exist. For example, A and / or B can represent: A exists alone, A and B exist simultaneously, or B exists alone.

[0085] In the embodiments of the present application, prefixes such as "first" and "second" are used only to distinguish different description objects and have no limiting effect on the position, order, priority, quantity or content of the described objects. The use of prefixes such as ordinal numbers to distinguish description objects in the embodiments of the present application does not constitute a restriction on the described objects. For the statement of the described objects, please refer to the description in the context of the claims or embodiments, and the use of such prefixes should not constitute an unnecessary restriction. In addition, in the description of this embodiment, unless otherwise specified, the meaning of "plurality" is two or more.

[0086] FIG1 is a functional block diagram of a vehicle 100 provided in an embodiment of the present application. The vehicle 100 may include a perception system 110 and a computing platform 120, wherein the perception system 110 may include several sensors for sensing information about the environment surrounding the vehicle 100. For example, the perception system 110 may include a positioning system, which may be a global positioning system (GPS), a BeiDou system or other positioning systems, or an inertial measurement unit (IMU). For another example, the perception system 110 may also include one or more of a laser radar, a millimeter-wave radar, an ultrasonic radar, and a camera device.

[0087] Some or all functions of the vehicle 100 may be controlled by a computing platform 120. The computing platform 120 may include processors 121 to 12n (n is a positive integer). A processor is a circuit capable of processing signals. In one implementation, the processor may be a circuit capable of reading and executing instructions, such as a central processing unit (CPU), a microprocessor, a graphics processing unit (GPU) (which can be understood as a microprocessor), or a digital signal processor (DSP). In another implementation, the processor may implement certain functions through the logical relationships of a hardware circuit. The logical relationships of the hardware circuit may be fixed or reconfigurable. For example, the processor may be a hardware circuit implemented by an application-specific integrated circuit (ASIC) or a programmable logic device (PLD), such as a field programmable gate array (FPGA). In a reconfigurable hardware circuit, the process of the processor loading a configuration file to implement the hardware circuit configuration can be understood as the process of the processor loading instructions to implement the functions of some or all of the above units. In addition, it can also be a hardware circuit designed for artificial intelligence, which can be understood as an ASIC, such as a neural network processing unit (NPU), a tensor processing unit (TPU), a deep learning processing unit (DPU), etc. In addition, the computing platform 120 can also include a memory for storing instructions. Some or all of the processors 121 to 12n can call the instructions in the memory and execute the instructions to achieve corresponding functions.

[0088] The above computing platform 120 and perception system 110 may be located in different devices, or the computing platform 120 and perception system 110 may be located in the same device.

[0089] First, the relevant terms involved in this application are introduced.

[0090] Radar false alarm targets, also known as false alarm targets, are targets reported by the radar that do not actually exist. These targets are those that do not exist in the actual application scenario. For example, in the case of radar road detection, real targets can include various vehicles (cars, trucks, buses, etc.), bicycles, electric vehicles, motorcycles, pedestrians, and obstacles. For example, a vehicle traveling on a highway may detect an obstacle on the road ahead based on radar data. However, in reality, the obstacle does not exist on the road ahead. In this case, the obstacle is a false alarm target.

[0091] As previously mentioned, when a vehicle travels on the road, it uses radar to emit electromagnetic waves and receive echo signals reflected from the targets to identify targets on the road. During this process, stationary objects on the road reflect radar electromagnetic waves through multipath reflection, making it impossible for the radar to accurately distinguish the echo signals reflected from real targets, resulting in false alarms.

[0092] FIG2 is a schematic diagram showing a scenario in which a false alarm target is generated according to an embodiment of the present application.

[0093] As shown in Figure 2(a), when there is a guardrail on the road, electromagnetic waves reflected by multipath from a real target may be reflected by the guardrail and thus received by the vehicle. This may cause the vehicle to identify targets outside the guardrail using radar data, including false alarm targets. These false alarm targets outside the guardrail can also be referred to as multipath false alarm targets outside the guardrail or mirror false alarm targets.

[0094] As shown in Figure 2(b), when there is a guardrail on the road, electromagnetic interference exists in the area between the real target and the guardrail. This may cause the target identified by the vehicle through radar data to include a false alarm target within the guardrail. This false alarm target within the guardrail can also be called a multipath false alarm target within the guardrail.

[0095] As shown in Figure 2 (c), for stationary targets, the radar cannot accurately determine whether the echo signal originates from a real target on the road or from other stationary objects in the environment (such as guardrails or medians). Therefore, these stationary objects may be reported as targets on the road, resulting in false alarms. This can cause the vehicle to identify the false alarm target on the guardrail among the targets identified by the radar data.

[0096] In an embodiment of the present application, a method, device, and terminal for determining the false alarm type of a target are provided. By using data collected by a camera and data collected by a radar, the false alarm type of the target can be determined as at least one of a false alarm target outside a guardrail, a false alarm target on a guardrail, a false alarm target inside a guardrail, and a non-false alarm target. By identifying the false alarm type of the target, it is helpful to improve the accuracy of false alarm target identification, thereby helping to improve the security of the terminal.

[0097] Fig. 3 shows the schematic block diagram of the system 300 that the embodiment of the application provides.Comprise camera 301, radar 302, the determining device 303 of target false alarm type among this system 300, optionally, can also comprise function module 304.Wherein, device 303 can receive the data that camera 301 collects and the data that radar 302 collects, wherein, comprise target and road detection information (for example, lane line and guardrail) in the data that camera 301 collects, and the data that radar 302 collects comprise the information of target.Device 303 can merge the data that camera 301 collects and radar 302 collect, thereby can determine target as at least one of the false alarm target outside road isolation facility (for example, guardrail), the false alarm target on road isolation facility, the false alarm target in road isolation facility and the non-false alarm target.Device 303 can also output the false alarm type of target to function module 304, thereby function module 304 can perform corresponding regulation and control operation according to the false alarm type of target.

[0098] In a possible implementation, the device 303 may be located in a cloud server, and the camera device 301 , the radar 302 , and the functional module 304 may be located in a terminal.

[0099] In a possible implementation, the functional module 304 includes but is not limited to an ACC module, an AEB module, an ADAS controller module, or a domain controller module.

[0100] In a possible implementation, the camera device 301 and the radar 302 may be located in the device 303 .

[0101] In a possible implementation, the functional module 304 may be located in the device 303. In this way, the device 303 may perform corresponding regulatory control operations after obtaining the false alarm type of the target.

[0102] In a possible implementation, the camera device 301 , the radar 302 , the device 303 and the functional module 304 may also be provided separately.

[0103] FIG4 shows a schematic flow chart of a method 400 for determining a target false alarm type according to an embodiment of the present application. The method can be performed by the apparatus 303 described above, and the method 400 includes:

[0104] S401, acquiring first data collected by a camera device and second data collected by a radar.

[0105] In a possible implementation, the first data includes information about a guardrail.

[0106] The above first data may be data obtained by a camera when collecting information about the vehicle's surroundings. In addition to the information about the guardrail, the first data may also include information about other targets on the road, such as other vehicles, pedestrians, obstacles, etc.

[0107] The second data may be data obtained by the radar when collecting information about the vehicle's surrounding environment. The second data may include information about targets such as guardrails, other vehicles, pedestrians, and obstacles on the road.

[0108] The above first data may include image data, and the second data may include point cloud data.

[0109] It should be understood that the embodiment of the present application is described by taking the example of identifying the guardrail through the first data collected by the camera device, and the embodiment of the present application is not limited thereto. For example, the guardrail can also be identified by the second data collected by the radar.

[0110] The first data and the second data may be data collected simultaneously by the camera and the radar, or data collected at intervals. The first data and the second data may be data collected by the camera and the radar respectively on the same environment around the vehicle.

[0111] S402, determining target indication information of the first target based on the first data and the second data, the target indication information being used to indicate a false alarm type of the first target, the false alarm type of the first target including at least one of the following: the first target being a false alarm target outside the guardrail, the first target being a false alarm target on the guardrail, the first target being a false alarm target inside the guardrail, or the first target being a non-false alarm target.

[0112] In one possible implementation, the target identified by the first data and the target identified by the second data have the following association results:

[0113] (1) Some targets can be identified by both the first data and the second data. These targets can be called dual-sensor targets.

[0114] (2) Some targets can be identified by the first data but not by the second data. Such targets can be called single-camera targets.

[0115] (3) Some targets can be identified by the second data but not by the first data. Such targets can be called single radar targets.

[0116] In one possible implementation, if the first target is a dual-sensor target or a single-camera target, the false alarm type of the first target can be determined to be a non-false alarm target. In the embodiment of the present application, the target identified by the data collected by the camera can be considered a real target.

[0117] In a possible implementation, if the first target is a single radar target, the true targets and false alarm targets in the single radar target may be further screened.

[0118] In one possible implementation, the target indication information of the first target is determined based on the first data and the second data, including: determining the false alarm type of the first target according to the area where the first target is located and the potential false alarm area, the potential false alarm area is determined by the area where the second target is located and the position of the guardrail, or the potential false alarm area is determined by the position of the guardrail, and the second target is a real target.

[0119] In the embodiment of the present application, the potential false alarm region can be determined by the area where the real target is located and the position of the guardrail, or the potential false alarm region can be determined by the position of the guardrail, and the potential false alarm region can be considered as an area where a false alarm target may exist. In this way, the false alarm type of the first target can be determined based on the area where the first target is located and the potential false alarm region. By identifying the false alarm type of the target, it is helpful to improve the accuracy of false alarm target identification, thereby helping to enhance the security of the terminal.

[0120] In a possible implementation, the second target includes a target identified through the first data, or a target continuously identified through the second data within a preset time period.

[0121] Exemplarily, the second target can be the above-mentioned dual-sensor target; or, the second target can be the above-mentioned single-camera device target; or, the second target can be the target stably tracked by the above-mentioned device 303 within a preset time period, that is, although the second target has not been determined by the camera device, the device 303 has tracked it for a long time and has been confirmed as a real target.

[0122] In a possible implementation, the potential false alarm area includes a mirror image area of ​​the area where the second target is located relative to the guardrail, the area where the guardrail is located, or an area between the guardrail and the area where the second target is located.

[0123] As can be seen from (a) in Figure 2 above, when there is a guardrail on the road, the targets identified by the vehicle through radar data collection include false alarm targets outside the guardrail, and the area where the false alarm target outside the guardrail is located has a mirror image relationship with the area where the real target is located. In this way, the area where the second target is located relative to the mirror image area of ​​the guardrail can be used as a potential false alarm area to determine whether the first target is a false alarm target outside the guardrail, which helps to improve the accuracy of false alarm target identification outside the guardrail, thereby helping to improve the safety of the terminal.

[0124] The outside of the guardrail mentioned above can also be understood as the side of the guardrail facing away from the vehicle or the side of the guardrail away from the vehicle (for example, the outside of the guardrail shown in (a) of Figure 2).

[0125] As shown in Figure 2(b), electromagnetic interference exists in the area between the true target and the guardrail. This may cause the vehicle to identify a false alarm target within the guardrail among the targets identified through radar data. This false alarm target is located between the area where the true target is located and the guardrail. In this way, the area between the area where the second target is located and the guardrail can be used to determine whether the first target is a false alarm target within the guardrail, helping to improve the accuracy of false alarm target identification within the guardrail, thereby contributing to improved terminal safety.

[0126] The inside of the guardrail mentioned above can also be understood as the side of the guardrail facing the vehicle or the side of the guardrail close to the vehicle (for example, the inside of the guardrail shown in (b) of FIG. 2 ).

[0127] In Figure 2 (a) and (b), the potential false alarm region can be determined by the position of the guardrail and the area where the real target is located on the road. For example, the potential false alarm region includes a mirror image of the area where the real target is located relative to the guardrail, or the area between the area where the real target is located and the guardrail. In this way, the potential false alarm region determined by the position of the guardrail and the area where the real target is located on the road can be used to determine whether the first target is a false alarm target outside the guardrail or a false alarm target inside the guardrail.

[0128] As shown in Figure 2(c), the targets identified by the vehicle through radar data include a false alarm target on the guardrail. This allows the area surrounding the guardrail to be used to determine whether the first target is a false alarm target on the guardrail, helping to improve the accuracy of false alarm target identification on the guardrail and thus enhancing terminal safety.

[0129] The above guardrail can also be understood as overlapping with the guardrail, or partially or completely overlapping with the area where the guardrail is located, and the distance between the guardrail and the guardrail is less than or equal to the preset distance.

[0130] In FIG. 2 (c), the potential false alarm area can be determined by the location of the guardrail. For example, the potential false alarm area can include the area where the guardrail is located. In this way, the area where the guardrail is located can be used to determine whether the first target is a false alarm target on the guardrail.

[0131] FIG5 shows a schematic diagram of a potential false alarm area provided by an embodiment of the present application.

[0132] As shown in (a) of Figure 5 , vehicle 1 is traveling on a road. Vehicle 1 identifies multiple real targets on the road (e.g., vehicle 2, vehicle 3, and vehicle 4). Vehicles 2 and 4 may be targets identified by data collected by a camera and by radar, and vehicle 3 may be a target continuously identified by radar data. At this point, vehicle 1 can determine, based on the areas and guardrails where vehicles 2, 3, and 4 are located, that potential false alarm areas outside the guardrail include potential false alarm area 1, potential false alarm area 2, and potential false alarm area 3. The area where vehicle 3 is located may have a mirror image relationship with potential false alarm area 1, the area where vehicle 2 is located may have a mirror image relationship with potential false alarm area 2, and the area where vehicle 4 is located may have a mirror image relationship with potential false alarm area 3. In one possible embodiment, the area where the second target is located may be an area including the projection area of ​​the second target on the ground. For example, the area where the second target is located may be the projection area of ​​the second target on the ground; alternatively, the area where the second target is located may be an area extending outward from the projection area of ​​the second target on the ground by a preset distance (e.g., 1 meter).

[0133] In a possible implementation, the real target may be a target continuously identified through data collected by radar.

[0134] For example, when the duration of vehicle 3 being identified by the data collected by the radar is greater than or equal to a first preset duration (for example, the first preset duration may be 0.5 seconds), vehicle 1 may consider vehicle 3 to be a target continuously identified by the radar data or vehicle 3 to be a real target.

[0135] For another example, if the duration of identifying a pedestrian through data collected by the radar is greater than or equal to a second preset duration (for example, the second preset duration may be 1 second), then vehicle 1 may consider the pedestrian to be a target continuously identified through data collected by the radar or the pedestrian to be a real target.

[0136] In a possible implementation, the real target may also be a target intermittently identified through data collected by the radar.

[0137] For example, if vehicle 1 continuously identifies a target on the road through radar data from time t1 to time t2, does not identify the target through radar data from time t2 to time t3, and continuously identifies the target through radar data from time t3 to time t4, vehicle 1 may consider the target to be a real target if the duration between time t2 and time t3 is less than or equal to a third preset duration (for example, the third preset duration may be 0.05 seconds) and the sum of the duration between time t1 and time t2 and the duration between time t3 and time t4 is greater than or equal to a fourth preset duration.

[0138] It should be understood that in (a) of FIG. 5 above, the area where vehicle 1 is located, the area where vehicle 2 is located, and the area where vehicle 3 is located are rectangular areas for illustration. When the area where vehicle 1 is located, the area where vehicle 2 is located, and the area where vehicle 3 is located are rectangular areas, potential false alarm area 1, potential false alarm area 2, and potential false alarm area 3 may also be rectangular areas. The embodiments of the present application are not limited thereto. For example, the area where vehicle 1 is located may also be a trapezoidal area, a circular area, an elliptical area, a triangular area, or an area of ​​other irregular shapes, and accordingly, potential false alarm area 1 may be a trapezoidal area, a circular area, an elliptical area, a triangular area, or an area of ​​other irregular shapes.

[0139] As shown in FIG5(b), vehicle 1 can also determine potential false alarm areas within the guardrail, including potential false alarm area 4, potential false alarm area 5, and potential false alarm area 6, based on the areas and guardrail where vehicles 2, 3, and 4 are located. Potential false alarm area 4 is the area between the area where vehicle 3 is located and the guardrail, potential false alarm area 5 is the area between the area where vehicle 2 is located and the guardrail, and potential false alarm area 6 is the area between the area where vehicle 4 is located and the guardrail.

[0140] In one possible implementation, taking the second target as vehicle 3 as an example, the area between the area where vehicle 3 is located and the guardrail can be the area formed by the right side contour line of vehicle 3, the guardrail, the right extension line of the front side contour line of vehicle 3, and the right extension line of the rear side contour line of vehicle 3.

[0141] In a possible implementation, the size of the area between the area where the vehicle 3 is located and the guardrail in the second direction may also be smaller than the distance between the right side contour line of the vehicle 3 and the guardrail.

[0142] In a possible implementation manner, the size of the area between the area where the vehicle 3 is located and the guardrail in the first direction may also be greater than the distance between the front side contour line and the rear side contour line of the vehicle 3 .

[0143] In one possible implementation, as shown in (c) of FIG5 , the area where the vehicle 3 is located may also be a rectangular area ABCD, and the potential false alarm area 4 may be the area enclosed by the straight line AB, the guardrail, the straight line BC, and the straight line AD.

[0144] In a possible implementation, as shown in (d) of FIG5 , the size of the potential false alarm area 4 in the second direction may be smaller than the distance between the straight line AB and the guardrail.

[0145] In a possible implementation manner, as shown in (e) of FIG. 5 , the size of the potential false alarm area 4 in the first direction may be greater than the length of AB.

[0146] It should be understood that the description of the potential false alarm region 5 and the potential false alarm region 6 can also refer to the potential false alarm region 4 described above, and for the sake of brevity, they are not repeated here.

[0147] It should also be understood that in (b) to (e) of FIG. 5 above, the area between the area where vehicle 2 is located and the guardrail, the area between the area where vehicle 3 is located and the guardrail, or the area between the area where vehicle 4 is located and the guardrail are all described using rectangular areas as examples, and the embodiments of the present application are not limited thereto. For example, the area between the area where vehicle 2 is located and the guardrail, the area between the area where vehicle 3 is located and the guardrail, or the area between the area where vehicle 4 is located and the guardrail may also be areas of other shapes (e.g., circular areas, triangular areas, trapezoidal areas, diamond areas, or other irregular shapes).

[0148] The vehicle 1 may also determine the area where the guardrail is located as a potential false alarm area on the guardrail. As shown in FIG5(f), the vehicle 1 may determine the potential false alarm area 7 as a potential false alarm area on the guardrail.

[0149] In a possible implementation, the potential false alarm area 7 may be symmetrical about the guardrail axis.

[0150] In a possible implementation, the size of the potential false alarm area 7 in the first direction and the size in the second direction may be preset sizes. For example, the size in the first direction may be 50 meters, and the size in the second direction may be 5 meters.

[0151] In a possible implementation manner, the size of the potential false alarm area 7 in the first direction may also be determined according to the length of the guardrail sensed by the camera device.

[0152] It should be understood that the potential false alarm area 7 shown in FIG5(f) can be a rectangular area or an area of ​​other shapes. For example, the potential false alarm area 7 can also be a trapezoidal area or an elliptical area. For example, when the potential false alarm area 7 is a trapezoidal area, the length of the lower base of the trapezoidal area close to the vehicle in the second direction can be greater than the length of the upper base away from the vehicle.

[0153] In a possible implementation, the size of the potential false alarm area 7 in the first direction may be determined by the distance between the vehicle 1 and an object that is farthest from the vehicle 1 among the objects that can be identified by the vehicle 1 .

[0154] In one possible implementation, the first target is located outside the guardrail, and the false alarm type of the first target is determined based on the area where the first target is located and the potential false alarm area, including: when the area where the first target is located and the potential false alarm area partially overlap or completely overlap, the first target is determined as a false alarm target outside the guardrail.

[0155] FIG6 shows a schematic diagram of determining the false alarm type of a target by using a potential false alarm area according to an embodiment of the present application.

[0156] As shown in Figure 6, Target 1 and Target 2 are targets identified by radar data but not by camera data. If the area where Target 1 is located partially overlaps with Potential False Alarm Area 1, Target 1 can be identified as a false alarm target outside the guardrail. If the area where Target 2 is located completely overlaps with Potential False Alarm Area 2, Target 2 can be identified as a false alarm target outside the guardrail.

[0157] As shown in FIG6 , the partial overlap between the area where the target 1 is located and the potential false alarm area 1 can be understood as a partial area in the rectangular area where the target 1 is located overlapping with a partial area in the potential false alarm area 1 and another partial area in the rectangular area where the target 1 is located does not overlap with the potential false alarm area 1, or, it can also be understood as the potential false alarm area 1 only includes a partial area in the rectangular area where the target 1 is located. In one possible embodiment, the area where the first target is located can be an area including the projection area of ​​the first target on the ground. For example, the area where the first target is located can be the projection area of ​​the first target on the ground; or, the area where the first target is located can be an area after the projection area of ​​the first target on the ground is extended outward by a preset distance (for example, 1 meter). For example, the rectangular area corresponding to the target 1 shown in FIG6 can be the projection area of ​​the target 1 on the ground, or, it can be an area including the projection area of ​​the target 1 on the ground.

[0158] In one possible implementation, the first target is located outside the guardrail, and the second target corresponds to the first target; or, the degree of motion state matching between the second target and the first target is greater than or equal to a first threshold; or, the degree of mirroring between the second target and the first target is greater than or equal to a second threshold.

[0159] When vehicle 1 identifies multiple real targets on the road (for example, vehicle 2, vehicle 3, and vehicle 4), when determining whether the first target is a false alarm target outside the guardrail, it can first determine a real target corresponding to the first target from the multiple real targets.

[0160] For example, when determining whether target 1 is a false alarm target outside the guardrail, vehicle 1 can first determine a real target corresponding to target 1 based on the degree of motion state matching between target 1 and vehicle 2, the degree of motion state matching between target 1 and vehicle 3, and the degree of motion state matching between target 1 and vehicle 4. If the degree of motion state matching between target 1 and vehicle 3 is greater than the degree of motion state matching between target 1 and vehicle 2 and the degree of motion state matching between target 1 and vehicle 4, vehicle 1 can determine that target 1 corresponds to vehicle 3. Thus, vehicle 1 can determine whether target 1 is a false alarm target outside the guardrail by comparing the area where target 1 is located with potential false alarm area 1.

[0161] After determining that the motion state matching degree of target 1 and vehicle 3 is the highest, vehicle 1 can also continue to judge the matching degree of vehicle 3 and above-mentioned potential false alarm areas 1-7. For example, the potential false alarm areas that are higher with the vehicle 3 matching degree include potential false alarm area 1 (the mirror image area of ​​the region at vehicle 3 about the guardrail), potential false alarm area 4 (the region between the region at vehicle 3 and the guardrail) and potential false alarm area 7 (the region on the guardrail). Vehicle 1 can match the region at target 1 with potential false alarm area 1, potential false alarm area 4 and potential false alarm area 7 respectively. For example, when the region at target 1 partially overlaps with potential false alarm area 1 and the region at target 1 and potential false alarm area 4 and potential false alarm area 7 do not overlap, vehicle 1 can determine that target 1 is a false alarm target outside the guardrail.

[0162] In a possible implementation, the degree of motion state matching between target 1 and each real target includes but is not limited to one or more of a speed matching degree, an acceleration matching degree, and a heading angle matching degree between target 1 and each real target.

[0163] For example, the speed matching degree between target 1 and the real target can be calculated by the following formula (1):

[0164]

[0165] Among them, S is the speed matching degree between target 1 and the real target, v1 is the speed of target 1 at time T1, and v2 is the speed of the real target at time T1.

[0166] For example, if target 1's speed at time T1 is 80 km / h, vehicle 2's speed at time T1 is 110 km / h, vehicle 3's speed at time T1 is 85 km / h, and vehicle 4's speed at time T1 is 120 km / h, vehicle 1 can determine that the speed match between target 1 and vehicle 3 is greater than the speed match between target 1 and vehicle 2 and the speed match between target 1 and vehicle 4. Therefore, vehicle 3 can be selected from vehicles 2, 3, and 4 as the true target corresponding to target 1.

[0167] For example, if the speed of target 2 at time T1 is 105 km / h, vehicle 1 can determine that the speed match between target 2 and vehicle 2 is greater than the speed match between target 2 and vehicle 3 and the speed match between target 2 and vehicle 4. Therefore, vehicle 2 can be selected as the true target corresponding to target 2 from among vehicles 2, 3, and 4.

[0168] For example, vehicle 1 can select a real target corresponding to target 1 from multiple real targets based on the relationship between the speed matching degree between target 1 and each real target and a preset threshold. For example, according to the above formula (1), the speed matching degree between target 1 and vehicle 2 is 62.5%, the speed matching degree between target 1 and vehicle 3 is 93.75%, and the speed matching degree between vehicle 1 and vehicle 4 is 50%. If the preset threshold is 90%, then vehicle 1 can determine that vehicle 3 is the real target corresponding to target 1.

[0169] In one possible implementation, the degree of speed matching between target 1 and each real target includes the degree of speed matching between target 1 and each real target within a preset duration. The degree of acceleration matching between target 1 and each real target includes the degree of acceleration matching between target 1 and each real target within a preset duration. The degree of heading angle matching between target 1 and each real target includes the degree of heading angle matching between target 1 and each real target within a preset duration.

[0170] For example, the speed of target 1 increases from 80 km / h to 90 km / h from time T1 to time T2, the speed of vehicle 2 decreases from 110 km / h to 100 km / h from time T1 to time T2, the speed of vehicle 3 increases from 85 km / h to 90 km / h from time T1 to time T2, and the speed of vehicle 4 decreases from 120 km / h to 110 km / h from time T1 to time T2. Then, vehicle 1 can determine that the speed matching degree between target 1 and vehicle 3 is greater than the speed matching degree between target 1 and vehicle 2 and the speed matching degree between target 1 and vehicle 4.

[0171] For example, when determining whether target 1 is a false alarm target outside the guardrail, vehicle 1 can first determine a real target corresponding to target 1 based on the degree of mirror image between target 1 and vehicle 2, the degree of mirror image between target 1 and vehicle 3, and the degree of mirror image between target 1 and vehicle 4. If the degree of mirror image between target 1 and vehicle 3 is greater than the degree of mirror image between target 1 and vehicle 2 and the degree of mirror image between target 1 and vehicle 4, vehicle 1 can determine that target 1 corresponds to vehicle 3. Thus, vehicle 1 can determine whether target 1 is a false alarm target outside the guardrail by comparing the area where target 1 is located with potential false alarm area 1.

[0172] It should be understood that the degree of mirroring between target 1 and each real target can be understood as the degree of symmetry between the area where target 1 is located and the area where the real target is located with respect to the guardrail; or, it can also be understood as the degree of overlap between the mirrored area of ​​the area where the real target is located with respect to the guardrail and the area where target 1 is located.

[0173] In one possible implementation, the first target is located within the guardrail, and the false alarm type of the first target is determined based on the area where the first target is located and the potential false alarm area, including: when the first target is located within the guardrail and the area where the first target is located partially or completely overlaps with the potential false alarm area, the first target is determined as a false alarm target within the guardrail.

[0174] FIG7 shows another schematic diagram of determining the false alarm type of a target by using a potential false alarm area according to an embodiment of the present application.

[0175] As shown in Figure 7, targets 3 and 4 are targets identified by the data collected by the radar and are not identified by the data collected by the camera. When the area where target 3 is located partially overlaps with potential false alarm area 4, target 3 can be determined as a false alarm target within the guardrail. When the area where target 4 is located completely overlaps with potential false alarm area 6, target 4 can be determined as a false alarm target within the guardrail.

[0176] In a possible implementation manner, the first target is located within the guardrail, and the second target includes multiple real targets.

[0177] When vehicle 1 identifies multiple real targets on the road (for example, vehicle 2, vehicle 3, and vehicle 4), it can determine whether the first target is a false alarm target within the guardrail by comparing the area where the first target is located with the area between the area where the multiple real targets are located and the guardrail.

[0178] For example, when determining whether target 3 is a false alarm target within the guardrail, vehicle 1 can directly determine whether the area where target 3 is located overlaps with potential false alarm area 4, potential false alarm area 5, and potential false alarm area 6. If the area where target 3 is located partially or completely overlaps with potential false alarm area 4, potential false alarm area 5, and potential false alarm area 6, target 3 can be determined to be a false alarm target within the guardrail.

[0179] It should be understood that in the embodiment of the present application, the fact that the area where the first target is located and the potential false alarm area completely overlap can be understood as the area where the first target is located being within the potential false alarm area.

[0180] In one possible implementation, the first target is located on the guardrail, and the false alarm type of the first target is determined based on the area where the first target is located and the potential false alarm area, including: when the area where the first target is located and the potential false alarm area partially overlap or completely overlap, the first target is determined as a false alarm target on the guardrail.

[0181] FIG8 shows another schematic diagram of determining the false alarm type of a target by using a potential false alarm area according to an embodiment of the present application.

[0182] As shown in Figure 8, targets 5 and 6 are targets identified by radar data but not by camera data. When the area where target 5 is located partially overlaps with potential false alarm area 7, target 5 can be determined as a false alarm target on the guardrail. When the area where target 6 is located completely overlaps with potential false alarm area 7, target 6 can be determined as a false alarm target on the guardrail.

[0183] In the embodiment of the present application, the first target may be a target that is not identified by the data collected by the camera and is identified by the data collected by the radar. The false alarm type of the first target can be determined based on the area where the first target is located and the potential false alarm area determined by the position of the real target and the guardrail. In this way, false alarm targets among the targets identified only by the data collected by the radar can be screened out, which helps to improve the accuracy of false alarm target identification, thereby helping to enhance the security of the terminal.

[0184] In a possible implementation manner, the target indication information further includes a false alarm probability of the first target.

[0185] In one possible embodiment, the first target is located outside the guardrail, and the method further includes: determining the false alarm probability based on at least one of the existence probability of the first target, the degree of overlap between the area where the first target is located and the potential false alarm area, the degree of matching between the motion state of the first target and the motion state of the second target, and the degree of mirroring between the first target and the second target.

[0186] In a possible implementation, when the first target is outside the guardrail, the false alarm probability of the first target can be determined based on the existence probability of the first target.

[0187] In an embodiment of the present application, the existence probability of the first target can be calculated by a probabilistic data association (PDA) algorithm or an integrated probabilistic data association (IPDA) algorithm, or can be calculated by other algorithms, which is not specifically limited in the embodiment of the present application.

[0188] In a possible implementation, when the first target is outside the guardrail, the false alarm probability of the first target may also be determined based on the degree of overlap between the area where the first target is located and the potential false alarm area.

[0189] As shown in Figure 6, if the overlap between target 1 and potential false alarm region 1 is 30%, the false alarm probability of target 1 can be determined to be 30%. If the overlap between target 2 and potential false alarm region 2 is 100%, the false alarm probability of target 2 can be determined to be 100%.

[0190] In a possible implementation, the false alarm probability of the first target may also be determined based on the degree of matching between the motion state of the first target and the motion state of the second target.

[0191] For example, the false alarm probability of the first target can be determined based on the speed matching of the first target and the second target. For example, if the speed of target 1 at time T1 is 80 km / h and the speed of vehicle 3 at time T1 is 85 km / h, then the speed matching degree of target 1 and vehicle 3 can be determined to be 93.75% according to formula (1); if the speed of target 2 at time T1 is 105 km / h and the speed of vehicle 2 at time T1 is 110 km / h, then the speed matching degree of target 2 and vehicle 2 can be determined to be 95.2% according to formula (1). Thus, the false alarm probability of target 1 can be determined to be 93.75% and the false alarm probability of target 2 can be determined to be 95.2%.

[0192] In a possible implementation, when the first target is outside the guardrail, the false alarm probability of the first target may be determined based on the degree of mirror image between the first target and the second target.

[0193] It should be understood that the degree of mirror image between the first target and the second target can also be understood as the degree of symmetry between the first target and the second target with respect to the guardrail.

[0194] In one possible implementation, the first target is located outside the guardrail, and the false alarm probability can also be determined based on at least two of the probability of existence of the first target, the degree of overlap between the area where the first target is located and the potential false alarm area, the degree of matching between the motion state of the first target and the motion state of the second target, and the degree of mirroring between the first target and the second target.

[0195] For example, the false alarm probability of the first target can be determined based on the existence probability of the first target and the degree of mirroring between the first target and the second target. Table 1 shows a corresponding relationship between the existence probability of the first target, the degree of mirroring between the first target and the second target, and the false alarm probability of the first target.

[0196] Table 1

[0197]

[0198] In Table 1 above, the degree of mirroring is represented by a numerical value from 0 to 3, where 0 represents a very low degree of mirroring and 3 represents a very high degree of mirroring.

[0199] For example, the false alarm probability of the first target can be determined based on the existence probability of the first target and the degree of match between the motion state of the first target and the motion state of the second target. Table 2 shows a corresponding relationship between the existence probability of the first target, the degree of match between the motion state of the first target and the motion state of the second target, and the false alarm probability of the first target.

[0200] Table 2

[0201]

[0202] It should be understood that the numerical values ​​in the above table are merely illustrative and are not intended to limit the present invention in any way.

[0203] FIG9 shows a schematic flow chart of a method 900 for calculating the false alarm probability of a first target in an embodiment of the present application. As shown in FIG9 , the method 900 includes:

[0204] S901: Based on the existence probability of the first target at time K-1, predict the existence probability of the first target at time K. Time K-1 and time K are two adjacent time points, and time K-1 is a time point before time K.

[0205] In the embodiment of the present application, the probability of the first target existing at time K-1 is the probability that the first target is on the road at time K-1. The value of the probability of the first target existing at time K-1 ranges from 0 to 1. The method for determining the probability of the first target existing at time K-1 is not specifically limited.

[0206] In one possible implementation, predicting the existence probability of the first target at time K based on the existence probability of the first target at time K-1 includes predicting the existence probability of the first target at time K using the following formula (2):

[0207]

[0208] In the above formula (2), P{X K|K-1} represents the predicted probability of the first target existing at time K; P{X K-1} represents the probability of the first target existing at time K-1; represents the probability that the first target exists at time K-1 and exists at time K; represents the probability that the first target does not exist at time K-1 and exists at time K. and The value range is from 0 to 1. and The specific value of can be set according to the application scenario or experience, or, and It can be a preset probability value.

[0209] In one possible implementation, the K-1 moment is the moment when the first target is determined to be a single radar target. In this implementation, P{X K-1}=P0, where P0 can be understood as the existence probability of the first target after the first target is determined to be a single radar target for the first time or the first time. At this time, P0 is also called the initial existence probability of the first target.

[0210] Exemplarily, the initial existence probability of the first target can be determined based on the motion characteristics of the first target at time K-1. The motion characteristics of a target include one or more of the following: the motion state of the target, the standard deviation of the motion state of the target, the variance of the motion state of the target, and the average value of the motion state of the target. The motion state of the target can include the direction, speed, and acceleration of the target's motion. Exemplarily, the initial existence probability of the first target can be expressed by the following formula (3):

[0211]

[0212] In the above formula (3), P0 represents the initial existence probability of the first target, σ represents the standard deviation of the motion state of the first target at time K-1, and σ 2represents the variance of the motion state of the first target at time K-1, X represents the motion state of the first target at time K-1, and μ represents the mean of the motion state of the first target at time K-1. Here, X = (x, vx, ax, y, vy, ay), where x represents the x-axis component of the distance between the vehicle and the first target at time K-1, y represents the y-axis component of the distance between the vehicle and the first target at time K-1, vx represents the x-axis component of the velocity of the first target at time K-1, ax represents the x-axis component of the acceleration of the first target at time K-1, vy represents the y-axis component of the velocity of the first target at time K-1, and ay represents the y-axis component of the acceleration of the first target at time K-1.

[0213] S902 : Determine the existence probability of the first target at time K according to the existence probability update coefficient of the first target at time K and the predicted existence probability of the first target at time K.

[0214] For example, the existence probability of the first target at time K can be determined by the following formula (4):

[0215]

[0216] In the above formula (4), represents the probability of the first target existing at time K, δ k represents the probability update coefficient of the first target at time K, P{X K|K-1} represents the predicted probability of the first target existing at time K.

[0217] Among them, δ k It can be expressed by the following formula (5):

[0218]

[0219] In the above formula (5), P D and P W The value of P is related to the performance of sensors (e.g., cameras and radars). D Indicates the probability of the target being detected by the sensor when the target exists; P W Indicates the probability that the reported status falls within the preset range when the sensor detects the target; V k Indicates the capacity of the preset range of the sensor at time K; m k Indicates the number of targets detected by the sensor at time K that fall within the preset range; Represents the association probability density and at time K.

[0220] For example, based on the above formulas (4) and (5), the existence probability of the first target at time K can be determined. Thus, the existence probability of the first target at time K can be determined as the false alarm probability of the first target at time K.

[0221] In one possible embodiment, the first target is located within the guardrail, and the method further includes: determining the false alarm probability based on at least one of the existence probability of the first target, the degree of overlap between the area where the first target is located and the potential false alarm area, and the degree to which the first target is obscured.

[0222] It should be understood that the process of determining the false alarm probability of the first target based on the existence probability of the first target when the first target is inside the guardrail can refer to the process of determining the false alarm probability of the first target based on the existence probability of the first target when the first target is outside the guardrail in the above embodiment, and will not be repeated here.

[0223] It should also be understood that the process of determining the false alarm probability of the first target based on the degree of overlap between the area where the first target is located and the potential false alarm area when the first target is inside the guardrail can refer to the process of determining the false alarm probability of the first target based on the degree of overlap between the area where the first target is located and the potential false alarm area when the first target is outside the guardrail in the above embodiment, and will not be repeated here.

[0224] In one possible implementation, when the first target is within the guardrail, the false alarm probability of the first target can be determined based on the degree of obstruction of the first target. For example, when the first target is completely obstructed by other targets, the false alarm probability of the first target can be determined to be 0. When 50% of the volume of the first target is completely obstructed by other targets, the false alarm probability of the first target can be determined to be 50%.

[0225] Exemplarily, the first target is located within the guardrail, and the false alarm probability can also be determined based on at least two of the existence probability of the first target, the degree of overlap between the area where the first target is located and the potential false alarm area, and the degree to which the first target is blocked.

[0226] For example, the false alarm probability of the first target can be determined according to the existence probability of the first target and the degree to which the first target is blocked. Table 3 shows the corresponding relationship between the existence probability of the first target, the degree to which the first target is blocked, and the false alarm probability of the first target.

[0227] Table 3

[0228]

[0229] In a possible implementation, the first target is located on the guardrail, and the method further includes: determining the false alarm probability based on at least one of the existence probability of the first target and the degree of overlap between the area where the first target is located and the potential false alarm area.

[0230] It should be understood that the process of determining the false alarm probability of the first target based on the existence probability of the first target when the first target is on the guardrail can refer to the process of determining the false alarm probability of the first target based on the existence probability of the first target when the first target is outside the guardrail in the above embodiment, and will not be repeated here.

[0231] It should also be understood that the process of determining the false alarm probability of the first target based on the degree of overlap between the area where the first target is located and the potential false alarm area when the first target is on the guardrail can refer to the process of determining the false alarm probability of the first target based on the degree of overlap between the area where the first target is located and the potential false alarm area when the first target is outside the guardrail in the above embodiment, and will not be repeated here.

[0232] In one possible implementation, after determining the false alarm type and false alarm probability of the first target, the false alarm target and false alarm probability of the first target may also be output. Exemplarily, the false alarm type and false alarm probability of the first target may be output to a functional module (e.g., an ACC module, an AEB module, an ADAS module, or a domain controller module).

[0233] Exemplarily, the false alarm type and false alarm probability of the first target can be output via a controller area network (CAN) bus, a controller area network with flexible data rate (CANFD) bus, or an Ethernet bus. Table 4 shows a method for outputting the false alarm type and false alarm probability via a signal output.

[0234] Table 4

[0235]

[0236]

[0237] As shown in Table 4 above, the output signals may include Signal 1 and Signal 2. Signal 1 is named "false alarm type," and its value can be any of 0, 1, 2, 3, or 4. Signal 2 is named "false alarm probability," and its value ranges from 0 to 100%. For example, when the false alarm type of the first target is a false alarm target outside the guardrail and the false alarm probability is 80%, when outputting Signal 1 and Signal 2, the value of Signal 1 can be set to 1, and the value of Signal 2 can be set to 80%.

[0238] Exemplarily, signal 1 and signal 2 may be carried in a CAN message, a CAN FD message, or an Ethernet message. For example, CAN message 1 may be output to a functional module, and the CAN message 1 may include signal 1 and signal 2. For another example, CAN message 1 and CAN message 2 may be output to a functional module, where CAN message 1 may include signal 1 and CAN message 2 may include signal 2.

[0239] In a possible embodiment, the values ​​of signal 1 and signal 2 can also be multiple. Figure 10 shows another schematic diagram of the application scenario provided by the embodiment of the present application. It can be seen that the target 5 identified by vehicle 1 and potential false alarm area 4 and potential false alarm area 7 all overlap. If the probability that target 5 is a false alarm target on the guardrail is 80% and the probability that target 5 is a false alarm target in the guardrail is 20% according to the method of the above-described embodiment. Like this, when outputting signals to the function module, the value of signal 1 can be 2 and 3 and the value of signal 2 can be 80% and 20%, when the value of signal 1 is 2, the value of corresponding signal 2 is 80%, and when the value of signal 1 is 3, the value of corresponding signal 2 is 20%.

[0240] It should be understood that the above Table 4 is merely illustrative and is not specifically limited in the present embodiment. For example, Table 5 shows another method of outputting the false alarm type and false alarm probability by outputting a signal.

[0241] Table 5

[0242]

[0243] Device 303 can agree with the functional module on the signal name corresponding to the signal identifier, so that when the functional module receives signal 1 and signal 2, it can directly determine the false alarm type of the first target by the value of signal 1 and directly determine the false alarm probability of the first target by the value of signal 2.

[0244] In a possible implementation, if the target indication information only includes information about the false alarm type of the first target, the false alarm type of the first target may also be output to the functional module by signal output. For example, Table 6 shows a method for outputting the false alarm type by signal output.

[0245] Table 6

[0246]

[0247]

[0248] In this way, the functional module can learn the false alarm type of the first target after receiving signal 1. Optionally, when the false alarm type of the first target is a false alarm target outside the guardrail, a false alarm target on the guardrail, or a false alarm target inside the guardrail, the functional module can default the false alarm probability of the first target to 100%.

[0249] Exemplarily, Table 7 shows another way of outputting the false alarm type and false alarm probability by outputting a signal.

[0250] Table 7

[0251]

[0252] As shown in Table 7, the output signals may include signals 1 to 6. For example, when the false alarm type of the first target is a false alarm target outside the guardrail and the false alarm probability of the first target is 80%, the value of signal 1 is 1, the value of signal 2 is 80%, the value of signal 3 is 0, the value of signal 4 is 0%, the value of signal 5 is 0, and the value of signal 6 is 0%.

[0253] For another example, when the probability that the first target is a false alarm target on the guardrail is 80% and the probability that the first target is a false alarm target inside the guardrail is 20%, the value of signal 1 is 0, the value of signal 2 is 0%; the value of signal 3 is 1, the value of signal 4 is 80%; the value of signal 5 is 1, and the value of signal 6 is 20%.

[0254] The embodiments of the present application also provide an apparatus for implementing any of the above methods. For example, an apparatus is provided that includes units (or means) for implementing each step performed by the terminal in any of the above methods.

[0255] FIG11 is a schematic block diagram of a device 1100 for determining a target false alarm type according to an embodiment of the present application. As shown in FIG11 , the device 1100 includes: an acquisition unit 1110 for acquiring first data collected by a camera and second data collected by a radar, the first data including guardrail information; and a determination unit 1120 for determining target indication information of a first target based on the first and second data. The target indication information indicates a false alarm type of the first target, where the false alarm type of the first target includes at least one of the following: the first target being a false alarm target outside the guardrail, the first target being a false alarm target on the guardrail, the first target being a false alarm target inside the guardrail, or the first target being a non-false alarm target.

[0256] Optionally, the device 1100 further includes: an output unit, configured to output the target indication information.

[0257] Optionally, the first target is a target identified by the second data and a target not identified by the first data; wherein the determination unit 1120 is specifically used to: determine the false alarm type of the first target based on the area where the first target is located and the potential false alarm area, the potential false alarm area is determined by the area where the second target is located and the position of the guardrail, or the potential false alarm area is determined by the position of the guardrail, and the second target is a real target.

[0258] Optionally, the potential false alarm area includes a mirror image area of ​​the area where the second target is located relative to the guardrail, the area where the guardrail is located, or an area between the guardrail and the area where the second target is located.

[0259] Optionally, the determination unit 1120 is specifically used to: when the first target is outside the guardrail and the area where the first target is located partially overlaps or completely overlaps with the potential false alarm area, determine the first target as a false alarm target outside the guardrail; or, when the first target is on the guardrail and the area where the first target is located partially overlaps or completely overlaps with the potential false alarm area, determine the first target as a false alarm target on the guardrail; or, when the first target is inside the guardrail and the area where the first target is located partially overlaps or completely overlaps with the potential false alarm area, determine the first target as a false alarm target inside the guardrail; or, when the area where the first target is located does not overlap with the potential false alarm area, determine the first target as a non-false alarm target.

[0260] Optionally, the first target is located outside the guardrail, and the second target corresponds to the first target; or, the degree of motion state matching between the second target and the first target is greater than or equal to a first threshold; or, the degree of mirroring between the second target and the first target is greater than or equal to a second threshold.

[0261] Optionally, the first target is located within the guardrail, and the second target includes multiple real targets.

[0262] Optionally, the target indication information also includes a false alarm probability of the first target.

[0263] Optionally, the determination unit 1120 is further used to determine the false alarm probability based on at least one of the existence probability of the first target, the degree of overlap between the area where the first target is located and the potential false alarm area, the degree of matching between the motion state of the first target and the motion state of the second target, and the degree of mirroring between the first target and the second target.

[0264] Optionally, the first target is located within the guardrail, and the determination unit 1120 is further used to determine the false alarm probability based on at least one of the existence probability of the first target, the degree of overlap between the area where the first target is located and the potential false alarm area, and the degree to which the first target is blocked.

[0265] Optionally, the first target is located on the guardrail, and the determining unit 1120 is further configured to determine the false alarm probability based on at least one of the existence probability of the first target and the degree of overlap between the area where the first target is located and the potential false alarm area.

[0266] Optionally, the second target includes a target identified through the first data, or a target continuously identified through the second data within a preset time period.

[0267] An embodiment of the present application also provides a device, which includes a processing unit and a storage unit, wherein the storage unit is used to store instructions, and the processing unit executes the instructions stored in the storage unit so that the device executes the method or steps performed by the above embodiment.

[0268] Optionally, if the device is located in a vehicle, the processing unit may be the processors 121 - 12n shown in FIG. 1 .

[0269] An embodiment of the present application further provides a terminal, which may include the above-mentioned device 303 or device 1100.

[0270] Optionally, the terminal may be a vehicle.

[0271] An embodiment of the present application further provides a server, which may include the above-mentioned device 303 or device 1100.

[0272] An embodiment of the present application further provides a system, which may include the above-mentioned device 303 or device 1100.

[0273] Optionally, the system may also include cameras and radar.

[0274] Optionally, the system may further include a functional module.

[0275] An embodiment of the present application further provides a computer program product, which includes: computer program code, which enables the computer to execute the above method when the computer program code is run on a computer.

[0276] An embodiment of the present application further provides a computer-readable medium, wherein the computer-readable medium stores a program code. When the computer program code is run on a computer, the computer executes the above method.

[0277] During implementation, each step of the above method can be completed by an integrated logic circuit of the hardware in the processor or by instructions in the form of software. The method disclosed in conjunction with the embodiments of the present application can be directly embodied as being executed by a hardware processor, or can be executed by a combination of hardware and software modules in the processor. The software module can be located in a storage medium mature in the art, such as a random access memory, a flash memory, a read-only memory, a programmable read-only memory, or an electrically erasable programmable memory, a register, etc. The storage medium is located in the memory, and the processor reads the information in the memory and completes the steps of the above method in combination with its hardware. To avoid repetition, it will not be described in detail here.

[0278] It should be understood that in the embodiment of the present application, the memory may include a read-only memory and a random access memory, and provide instructions and data to the processor.

[0279] It should also be understood that in the various embodiments of the present application, the size of the serial numbers of the above-mentioned processes does not mean the order of execution. The execution order of each process should be determined by its function and internal logic, and should not constitute any limitation on the implementation process of the embodiments of the present application.

[0280] Those skilled in the art will appreciate that the units and algorithm steps of each example described in conjunction with the embodiments disclosed herein can be implemented in electronic hardware, or a combination of computer software and electronic hardware. Whether these functions are performed in hardware or software depends on the specific application and design constraints of the technical solution. Professional and technical personnel can use different methods to implement the described functions for each specific application, but such implementation should not be considered beyond the scope of this application.

[0281] If the functions are implemented in the form of software functional units and sold or used as independent products, they can be stored in a computer-readable storage medium. Based on this understanding, the technical solution of the present application, 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. The computer software product is stored in a storage medium and includes several instructions for enabling a computer device (which can be a personal computer, a server, or a network device, etc.) to execute all or part of the steps of the method described in each embodiment of the present application. The aforementioned storage medium includes various media that can store program codes, such as a USB flash drive, a mobile hard disk, a read-only memory (ROM), a random access memory (RAM), a magnetic disk or an optical disk.

[0282] The above description is merely a specific embodiment of the present application, but the scope of protection of the present application is not limited thereto. Any changes or substitutions that can be easily conceived by a person skilled in the art within the technical scope disclosed in the present application should be covered and fall within the scope of protection of the present application. Therefore, the scope of protection of the present application should be based on the scope of protection of the claims.

Claims

1. A method for determining a target false alarm type, characterized in that: include: Acquire first data collected by a camera device and second data collected by a radar, wherein the first data includes information about a guardrail; Target indication information of the first target is determined based on the first data and the second data, where the target indication information is used to indicate a false alarm type of the first target, the false alarm type of the first target including at least one of the following: the first target is a false alarm target outside the guardrail, the first target is a false alarm target on the guardrail, the first target is a false alarm target inside the guardrail, or the first target is a non-false alarm target.

2. The method according to claim 1, characterized in that The method further comprises: The target indication information is output.

3. The method according to claim 1 or 2, characterized in that The first target is a target identified by the second data and not identified by the first data; The determining of target indication information of the first target based on the first data and the second data includes: The false alarm type of the first target is determined based on the area where the first target is located and the potential false alarm area, where the potential false alarm area is determined by the area where the second target is located and the position of the guardrail, or the potential false alarm area is determined by the position of the guardrail, and the second target is a real target.

4. The method according to claim 3, characterized in that The potential false alarm area includes a mirror image area of ​​the area where the second target is located relative to the guardrail, the area where the guardrail is located, or an area between the guardrail and the area where the second target is located.

5. The method according to claim 3 or 4, characterized in that The determining, based on the area where the first target is located and the potential false alarm area, the false alarm type of the first target includes: When the first target is outside the guardrail and the area where the first target is located partially or completely overlaps with the potential false alarm area, determining the first target as a false alarm target outside the guardrail; or When the first target is located on the guardrail and the area where the first target is located partially or completely overlaps with the potential false alarm area, determining the first target as a false alarm target on the guardrail; or When the first target is located within the guardrail and the area where the first target is located partially or completely overlaps with the potential false alarm area, determining the first target as a false alarm target within the guardrail; or When the area where the first target is located does not overlap with the potential false alarm area, the first target is determined as a non-false alarm target.

6. The method according to any one of claims 3 to 5, characterized in that The first target is located outside the guardrail, and the second target corresponds to the first target; or The degree of matching between the motion state of the second target and the motion state of the first target is greater than or equal to a first threshold; or The degree of mirror image between the second object and the first object is greater than or equal to a second threshold.

7. The method according to any one of claims 3 to 5, characterized in that The first target is located within the guardrail, and the second target includes a plurality of real targets.

8. The method according to any one of claims 1 to 7, characterized in that The target indication information also includes a false alarm probability of the first target.

9. The method according to claim 8, characterized in that The first target is located outside the guardrail, and the method further includes: The false alarm probability is determined based on at least one of the existence probability of the first target, the degree of overlap between the area where the first target is located and the potential false alarm area, the degree of matching between the motion state of the first target and the motion state of the second target, and the degree of mirroring between the first target and the second target.

10. The method according to claim 8, characterized in that The first target is located within the guardrail, and the method further includes: The false alarm probability is determined according to at least one of the existence probability of the first target, the degree of overlap between the area where the first target is located and the potential false alarm area, and the degree to which the first target is blocked.

11. The method according to claim 8, characterized in that The first target is located on the guardrail, and the method further includes: The false alarm probability is determined according to at least one of the existence probability of the first target and the overlap degree between the area where the first target is located and the potential false alarm area.

12. The method according to any one of claims 1 to 11, characterized in that The second target includes a target identified through the first data, or a target continuously identified through the second data within a preset time period.

13. A device for determining target false alarm type, characterized in that: include: an acquiring unit, configured to acquire first data acquired by a camera and second data acquired by a radar, wherein the first data includes information about a guardrail; a determination unit, configured to determine target indication information of a first target based on the first data and the second data, wherein the target indication information is used to indicate a false alarm type of the first target, the false alarm type of the first target including at least one of the following: the first target is a false alarm target outside a guardrail, the first target is a false alarm target on a guardrail, the first target is a false alarm target inside a guardrail, or the first target is a non-false alarm target.

14. The device according to claim 13, characterized in that The device further comprises: An output unit is used to output the target indication information.

15. The device according to claim 13 or 14, characterized in that The first target is a target identified by the second data and not identified by the first data; The determining unit is specifically configured to: The false alarm type of the first target is determined based on the area where the first target is located and the potential false alarm area, where the potential false alarm area is determined by the area where the second target is located and the position of the guardrail, or the potential false alarm area is determined by the position of the guardrail, and the second target is a real target.

16. The device according to claim 15, characterized in that The potential false alarm area includes a mirror image area of ​​the area where the second target is located relative to the guardrail, the area where the guardrail is located, or an area between the guardrail and the area where the second target is located.

17. The device according to claim 15 or 16, characterized in that The determining unit is specifically configured to: When the first target is outside the guardrail and the area where the first target is located partially or completely overlaps with the potential false alarm area, determining the first target as a false alarm target outside the guardrail; or, When the first target is located on the guardrail and the area where the first target is located partially or completely overlaps with the potential false alarm area, determining the first target as a false alarm target on the guardrail; or, When the first target is located within the guardrail and the area where the first target is located partially or completely overlaps with the potential false alarm area, determining the first target as a false alarm target within the guardrail; or When the area where the first target is located does not overlap with the potential false alarm area, the first target is determined as a non-false alarm target.

18. The device according to any one of claims 15 to 17, characterized in that The first target is located outside the guardrail, and the second target corresponds to the first target; or The degree of matching between the motion state of the second target and the motion state of the first target is greater than or equal to a first threshold; or The degree of mirror image between the second object and the first object is greater than or equal to a second threshold.

19. The device according to any one of claims 15 to 17, characterized in that The first target is located within the guardrail, and the second target includes a plurality of real targets.

20. The device according to any one of claims 13 to 19, characterized in that The target indication information also includes a false alarm probability of the first target.

21. The device according to claim 20, characterized in that The first target is located outside the guardrail, and the determination unit is further used to determine the false alarm probability based on at least one of the existence probability of the first target, the degree of overlap between the area where the first target is located and the potential false alarm area, the degree of matching between the motion state of the first target and the motion state of the second target, and the degree of mirroring between the first target and the second target.

22. The device according to claim 20, characterized in that The first target is located within the guardrail, and the determination unit is further used to determine the false alarm probability based on at least one of the existence probability of the first target, the degree of overlap between the area where the first target is located and the potential false alarm area, and the degree to which the first target is blocked.

23. The device according to claim 20, characterized in that The first target is located on the guardrail, and the determining unit is further configured to determine the false alarm probability based on at least one of a probability of existence of the first target and an overlap degree between an area where the first target is located and the potential false alarm area.

24. The device according to any one of claims 13 to 23, characterized in that The second target includes a target identified through the first data, or a target continuously identified through the second data within a preset time period.

25. A device for determining target false alarm type, characterized in that: The device includes a processor and a memory, wherein the memory is used to store program instructions, and the processor is used to call the program instructions to execute the method according to any one of claims 1 to 12.

26. A terminal, characterized in that: The terminal comprises the apparatus according to any one of claims 13 to 25.

27. The terminal according to claim 26, wherein: The terminal also includes a camera and a radar.

28. The terminal according to claim 26 or 27, characterized in that The terminal is a vehicle.

29. A computer-readable storage medium, characterized in that The computer-readable medium stores a program code, and when the program code is run on a computer, the computer is caused to perform the method according to any one of claims 1 to 12.

30. A chip, characterized in that: The chip includes a processor and a data interface, and the processor reads instructions stored in a memory through the data interface to execute the method according to any one of claims 1 to 12.

Images