Target detection method and device
Patent Information
- Application Number
- CN202280093470.X
- Authority / Receiving Office
- CN · China
- Patent Type
- Applications(China)
- Current Assignee / Owner
- Filing Date
- 2022-04-27
- Publication Date
- 2024-11-08
AI Technical Summary
The accuracy of environmental perception of intelligent driving vehicles is low during driving, making it difficult to make safe driving decisions.
By obtaining the first sensing information and the second sensing information of the environment, combined with the lane information and target location information, the congestion level of the environment is determined, so that appropriate target detection strategies can be adopted to improve detection accuracy.
The accuracy of target detection results in the environment is achieved, the safe driving decision-making ability of intelligent driving vehicles is improved, and the risk of collision is reduced.
Smart Images

Figure CN118922873A_ABST
Abstract
Description
Target detection method and device Technical Field
[0001] The present application relates to the field of perception, and in particular to target detection methods and devices. Background Art
[0002] With the continuous development of computer and internet technologies, intelligent driving has garnered widespread attention. Intelligent driving can include autonomous driving (also known as unmanned driving) or assisted driving. Autonomous driving refers to the ability of the vehicle's autonomous driving system to safely operate the vehicle without the need for driver involvement. Assisted driving refers to the use of an auxiliary driving device in the vehicle to assist the driver in driving safely.
[0003] While driving, intelligent vehicles need to perceive their environment and make decisions based on this perception, such as determining speed and direction, to prevent collisions and ensure safe driving. Accurate environmental perception is crucial for intelligent driving. However, current methods for environmental perception are relatively simple and have low accuracy.
[0004] Summary of the Invention
[0005] The embodiments of the present application provide a target detection method and apparatus, which can determine the congestion level of an environment to obtain more accurate detection results.
[0006] To achieve the above objectives, the embodiments of the present application adopt the following technical solutions:
[0007] In a first aspect, a target detection method is provided. The device executing this method may be a target detection device or a module implemented in the target detection device, such as a chip or chip system. The following description uses the target detection device as an example. The method includes: obtaining first information, the first information including first perceived information about an environment; obtaining second information, the second information including second perceived information about the environment; and determining a congestion level of the environment based on the first and second information. The congestion level of the environment is used to detect at least one target in the environment.
[0008] Based on the method provided in the first aspect, the target detection device can obtain first and second perception information of the environment and determine the congestion level of the environment, so that the congestion level of the environment can be used to detect targets in the environment. In other words, using the method provided in the first aspect, it is possible to detect targets in the environment based on the congestion level of the environment. For example, different target detection strategies can be used for different congestion levels, resulting in more accurate target detection results.
[0009] In one possible implementation, the first perception information includes information of at least one lane; the second perception information includes position information of at least one target on the at least one lane, or the second perception information includes position information of at least one target on the at least one lane and speed information of at least one target on the at least one lane.
[0010] Based on the above possible implementations, the target detection device can obtain information about at least one lane and position information about at least one target in the at least one lane, so that the target detection device can divide lanes for the targets in the second perception information and know which targets are in which lanes. Alternatively, the target detection device can obtain information about at least one lane, position information about at least one target in the at least one lane, and speed information about at least one target in the at least one lane, so that the target detection device can divide lanes for the targets in the second perception information and know which targets are in which lanes and the speed of each target.
[0011] In a possible implementation, the method further includes: dividing the at least one target into lanes based on the first perception information and the second perception information.
[0012] Based on the above possible implementation methods, the target detection device can divide lanes for the targets in the second perception information and know which targets are on which lanes, so that the target detection device can determine the congestion level based on the lanes and know the congestion level of each lane, and then determine the target detection strategy with the lane as the granularity to obtain more accurate detection results.
[0013] In one possible implementation, determining the congestion level of the environment based on the first information and the second information includes: determining information of a target on a first lane of at least one lane based on the first perception information and the second perception information, the first lane being any one of the at least one lane, the information of the target on the first lane including at least one of the following: the number of targets on the first lane, the speed of the target on the first lane, the average distance between two adjacent targets on the first lane, the minimum distance between two adjacent targets on the first lane, or the traffic density of the first lane; determining the congestion level of the first lane based on the information of the target on the first lane.
[0014] Based on the above possible implementations, the target detection device can determine information about targets in the first lane based on the first perception information and the second perception information. The information about targets in the first lane includes parameters such as the number of targets in the first lane, the speed of targets in the first lane, the average spacing between two adjacent targets in the first lane, the minimum spacing between two adjacent targets in the first lane, or the traffic density in the first lane, all of which can reflect the congestion situation in the first lane. Therefore, based on the information about targets in the first lane, a more accurate congestion level can be determined.
[0015] In one possible implementation, the method further includes: obtaining at least one threshold value, the at least one threshold value including at least one of the following: a speed threshold value or a spacing threshold value; the speed threshold value is the median of the speeds of the multiple targets on the first lane, the minimum value of the speeds of the multiple targets on the first lane, or the maximum value of the speeds of the multiple targets on the first lane, or the speed threshold value is preset; the spacing threshold value is obtained based on the speed threshold value and the time interval, and the time interval is preset.
[0016] Based on the possible implementations described above, the target detection device can determine at least one threshold value based on the information about the target in the first lane, or pre-set the at least one threshold value, so that the target detection device can determine the congestion level of the first lane based on the information about the target in the first lane and the at least one threshold value. It will be appreciated that if the threshold value is pre-set, the operation of the target detection device can be simplified. If the threshold value is calculated based on the information about the target in the first lane, the robustness of the target detection method can be improved, making it more adaptable.
[0017] In a possible implementation, determining the congestion level of the first lane according to the information of the target on the first lane includes: determining the congestion level of the first lane according to the information of the target on the first lane and the at least one threshold.
[0018] Based on the above possible implementation methods, the target detection device can compare the parameters in the information of the target on the first lane with at least one threshold to determine the congestion level of the first lane. The calculation amount is small, and it is relatively easy to implement and the cost is low.
[0019] In a possible implementation, the congestion level of the first lane includes 4 levels, 5 levels, or 6 levels.
[0020] Based on the above possible implementation methods, the congestion level of the first lane can be set as needed to suit different scenarios.
[0021] In one possible implementation, if the congestion level of the first lane includes six levels, the congestion level of the first lane is determined based on the information of the objects on the first lane and the at least one threshold, including: if the number of objects on the first lane is greater than or equal to a first number threshold and the speed of the objects on the first lane is less than or equal to the speed threshold, the congestion level of the first lane is level 5; or, if the number of objects on the first lane is greater than or equal to the first number threshold, the congestion level of the first lane is level 4; or, if the average spacing between two adjacent objects on the first lane is less than or equal to the spacing threshold, the congestion level of the first lane is level 3; or, if the minimum spacing between two adjacent objects on the first lane is less than or equal to the spacing threshold, the congestion level of the first lane is level 2; if the minimum spacing between two adjacent objects on the first lane is greater than the spacing threshold and the number of objects on the first lane is greater than or equal to a second number threshold, the congestion level of the first lane is level 1; or, if the number of objects on the first lane is less than the second number threshold, the congestion level of the first lane is level 0.
[0022] Based on the possible implementation described above, the information about the targets in the first lane includes multiple parameters, such as the number of targets in the first lane, the speed of the targets in the first lane, the average spacing between two adjacent targets in the first lane, and the minimum spacing between two adjacent targets in the first lane. The target detection device can determine the congestion level of the first lane based on these multiple parameters and their corresponding thresholds. In the above process, the target detection device comprehensively considers multiple parameters, resulting in a more accurate determination of the congestion level of the first lane.
[0023] In one possible implementation, if the congestion level of the first lane includes six levels, the congestion level of the first lane is determined based on the information of the objects on the first lane and the at least one threshold, including: if the traffic density of the first lane is greater than or equal to a first density threshold and the speed of the objects on the first lane is less than or equal to the speed threshold, the congestion level of the first lane is level 5; or, if the traffic density of the first lane is greater than or equal to the first density threshold, the congestion level of the first lane is level 4; or, if the average spacing between two adjacent objects on the first lane is less than or equal to the spacing threshold, the congestion level of the first lane is level 3; or, if the minimum spacing between two adjacent objects on the first lane is less than or equal to the spacing threshold, the congestion level of the first lane is level 2; if the minimum spacing between two adjacent objects on the first lane is greater than the spacing threshold and the traffic density of the first lane is greater than or equal to a second density threshold, the congestion level of the first lane is level 1; or, if the traffic density of the first lane is less than the second density threshold, the congestion level of the first lane is level 0.
[0024] Based on the possible implementations described above, the information about the targets in the first lane includes multiple parameters, such as the traffic density in the first lane, the speed of the targets in the first lane, the average spacing between two adjacent targets in the first lane, and the minimum spacing between two adjacent targets in the first lane. The target detection device can determine the congestion level of the first lane based on these multiple parameters and their corresponding thresholds. In the above process, the target detection device comprehensively considers multiple parameters, resulting in a more accurate determination of the congestion level of the first lane.
[0025] In a possible implementation, the method further includes: determining a sensor fusion strategy for the first lane according to the congestion level of the first lane, where the sensor fusion strategy for the first lane is used to estimate an actual position of an object on the first lane.
[0026] Based on the above possible implementation methods, the target detection device can determine a suitable sensor fusion strategy according to the congestion level of the first lane, which not only makes the position of the target estimated according to the sensor fusion strategy more accurate, but also enables a more accurate number of targets to be determined when determining the number of targets.
[0027] In one possible implementation, a sensor fusion strategy for the first lane is determined based on the congestion level of the first lane, including: if the congestion level of the first lane is greater than or equal to the first level, the sensor fusion strategy for the first lane is the first fusion strategy; or if the congestion level of the first lane is less than the first level, the sensor fusion strategy for the first lane is the second fusion strategy.
[0028] Based on the above possible implementation methods, different congestion levels can correspond to different sensor fusion strategies, so that when the first lane is at different congestion levels, the position of the target can be estimated using the sensor fusion strategy corresponding to the congestion level to obtain accurate results.
[0029] In one possible implementation, the first perception information also includes the position information of at least one target on the at least one lane. The position information in the first perception information includes the first distance of the first target, the first angle of the first target, the horizontal coordinate of the first target and the vertical coordinate of the first target. The first target is any target in the first lane. The first target is different from the target where the target detection device is located. The first distance is the distance between the target detection device and the first target. The first angle is the angle between the forward direction of the target detection device and the first line. The first line is the line between the target detection device and the first target. The position information in the second perception information includes the horizontal coordinate of the second target and the vertical coordinate of the second target. The second target is the target corresponding to the first target among the at least one target corresponding to the second perception information.
[0030] Based on the above possible implementation, the first perception information also includes the first distance to the first target, the first angle to the first target, the horizontal coordinate of the first target, and the vertical coordinate of the first target; the second perception information includes the horizontal coordinate of the second target and the vertical coordinate of the second target. When the target detection device determines that the sensor fusion strategy for the first lane is the first fusion strategy, the horizontal coordinate of the first target, the vertical coordinate of the first target, the horizontal coordinate of the second target, and the vertical coordinate of the second target can be used to determine the actual position of the target in the first lane. When the target detection device determines that the sensor fusion strategy for the first lane is the second fusion strategy, the first angle, the first distance, the horizontal coordinate of the second target, and the vertical coordinate of the second target are fused to determine the actual position of the target in the first lane. This allows the use of different sensor fusion strategies to estimate the target position when the first lane is at different congestion levels.
[0031] In one possible implementation, the first fusion strategy is to fuse the horizontal coordinate of the first target, the vertical coordinate of the first target, the horizontal coordinate of the second target and the vertical coordinate of the second target to obtain the actual position of the target on the first lane; the second fusion strategy is to fuse the first angle, the first distance, the horizontal coordinate of the second target and the vertical coordinate of the second target to obtain the actual position of the target on the first lane.
[0032] Based on the above possible implementation methods, when the congestion level of the first lane is low (i.e., the first lane is less congested), the first angle and the first distance perceived by the first sensing device are relatively accurate (e.g., by performing image recognition on the photos taken by the camera device, a relatively accurate first angle and first distance can be obtained). Therefore, by fusing the first angle, the first distance, the horizontal coordinate of the second target, and the vertical coordinate of the second target (i.e., through the second fusion strategy), a relatively accurate position can be estimated. When the congestion level of the first lane is high (i.e., the first lane is more congested), the first angle and the first distance perceived by the first sensing device have large errors (e.g., the first angle and the first distance obtained by image recognition technology have large errors). By fusing the first angle, the first distance, the horizontal coordinate of the second target, and the vertical coordinate of the second target (i.e., through the second fusion strategy), the estimated position is inaccurate. Therefore, the horizontal coordinate of the first target, the vertical coordinate of the first target, the horizontal coordinate of the second target, and the vertical coordinate of the second target can be fused (i.e., through the first fusion strategy) to estimate a more accurate position.
[0033] In a possible implementation, the method further includes: determining a strategy for sensing targets in the first lane according to a congestion level of the first lane, wherein the strategy for sensing targets in the first lane is used to sense whether a target exists in the first lane.
[0034] Based on the above possible implementation methods, the target detection device can determine a suitable strategy for sensing targets in the first lane according to the congestion level of the first lane to prevent the occurrence of missed sensing targets or the determination of false targets.
[0035] In one possible implementation, a strategy for sensing targets in the first lane is determined based on the congestion level of the first lane, including: if the congestion level of the first lane is greater than or equal to a second level, using a first sensing method to sense whether there is a target in the first lane; or, if the congestion level of the first lane is less than the second level, using a second sensing method to sense whether there is a target in the first lane.
[0036] Based on the possible implementations described above, different congestion levels correspond to different strategies for sensing targets in the first lane. For example, the higher the congestion level in the first lane (i.e., the more congested the first lane), the more relaxed the target sensing strategy in the first lane is to prevent missed targets; the lower the congestion level in the first lane (i.e., the less congested the first lane is), the stricter the target sensing strategy in the first lane is to prevent false detection of targets.
[0037] In one possible implementation, the first perception method is to determine the target obtained by sensor fusion based on the first perception information and the second perception information, the target not subjected to sensor fusion in the first perception information, and the target not subjected to sensor fusion in the second perception information as the target on the first lane; the second perception method is to determine the target obtained by sensor fusion based on the first perception information and the second perception information as the target on the first lane.
[0038] Based on the above possible implementations, when the congestion level of the first lane is high (i.e., the first lane is relatively congested), in order to prevent collisions, the strategy for sensing targets in the first lane can be set to be relatively loose. For example, the acquired targets (e.g., targets obtained through sensor fusion of the first and second perception information, targets not subjected to sensor fusion in the first perception information, and targets not subjected to sensor fusion in the second perception information) are not screened, but the acquired targets are directly determined as targets in the first lane. When the congestion level of the first lane is low (i.e., the first lane is relatively uncongested), the strategy for sensing targets in the first lane can be set to be relatively strict. For example, the acquired targets can be screened, and the screened targets (e.g., targets obtained through sensor fusion of the first and second perception information) are determined as targets in the first lane to prevent the determination of false targets.
[0039] In a possible implementation, the first information and the second information are acquired by different types of sensing devices; or, the first information and the second information are acquired by the same type of sensing devices.
[0040] Based on the above possible implementation methods, if the first information and the second information are obtained by different types of sensing devices, the first information can be obtained by a sensing device that is sensitive to graphics (such as lane lines), and the second information can be obtained by a sensing device that is sensitive to targets (such as vehicles, pedestrians, trees, or road test devices) to obtain more accurate first information and second information. If the first information and the second information are obtained by the same type of sensing device, the first information and the second information include similar information, which is more convenient to process and easy to implement. In addition, multiple low-cost sensing devices can be set in different locations to obtain the first information and the second information, thereby reducing costs.
[0041] In one possible implementation, the sensing device for acquiring the first information is a camera, a laser radar, a millimeter-wave radar, or a sonar; the sensing device for acquiring the second information is a millimeter-wave radar, a laser radar, or a sonar.
[0042] Based on the possible implementations described above, the first information can be acquired using a camera, lidar, millimeter-wave radar, or sonar device sensitive to the first information, resulting in relatively accurate first information. The second information can be acquired using a millimeter-wave radar, lidar, or sonar device sensitive to the second information, resulting in relatively accurate second information. In this way, a relatively accurate congestion level can be determined based on the first and second information.
[0043] In a possible implementation manner, the method further includes: sending information on the congestion level of the environment.
[0044] Based on the above possible implementations, the target detection device can transmit information about the congestion level of the environment to other devices or modules so that the other devices or modules can use the congestion level of the environment. For example, the target detection device can transmit information about the congestion level of the environment to an intelligent driving vehicle so that the intelligent driving vehicle can select a more optimal road planning solution and / or vehicle control strategy based on the information, and / or so that multiple vehicles can share the congestion level of the environment, thereby forming a regional congestion map to facilitate each vehicle's own driving planning and / or regional traffic flow control (e.g., traffic light control) on the road. For another example, if the target detection device includes an ADAS, after the sensor fusion module in the ADAS determines the congestion level of the environment based on the first information and the second information, it can transmit the information about the congestion level of the environment to the target selection module so that the target selection module can adjust its target selection algorithm based on the information, and / or transmit the information about the congestion level of the environment to the control module so that the control module can adjust parameters of the functions controlled by the control module based on the information (e.g., adjusting parameters of the AEB function to make braking more sensitive and shorten braking time when the congestion level is high).
[0045] In a second aspect, a target detection device is provided for implementing the above method. The target detection device may be the target detection device of the first aspect, or a device including the target detection device. The target detection device includes modules, units, or means corresponding to the above method. The modules, units, or means may be implemented by hardware, software, or by hardware executing corresponding software implementations. The hardware or software includes one or more modules or units corresponding to the above functions.
[0046] In conjunction with the above second aspect, in one possible implementation, the target detection device may include a processing module. The processing module may be used to implement the processing functions of the above first aspect and any possible implementation thereof. The processing module may be, for example, a processor.
[0047] In conjunction with the above second aspect, in one possible implementation, the target detection device may further include a transceiver module. The transceiver module, which may also be referred to as a transceiver unit, is configured to implement the sending and / or receiving functions described in the above first aspect and any possible implementation thereof. The transceiver module may be composed of a transceiver circuit, a transceiver, a transceiver, or a communication interface.
[0048] In combination with the above second aspect, in a possible implementation, the transceiver module includes a sending module and a receiving module, which are respectively used to implement the sending and receiving functions in the above first aspect and any possible implementation thereof.
[0049] In a third aspect, a target detection device is provided, comprising: a processor; the processor is coupled to a memory, and after reading instructions from the memory, executes the method described in the first aspect according to the instructions. The target detection device may be the target detection device described in the first aspect, or a device including the target detection device described above.
[0050] In combination with the third aspect above, in a possible implementation, the target detection device further includes a memory, and the memory is used to store necessary program instructions and data.
[0051] In conjunction with the third aspect above, in one possible implementation, the target detection device is a chip or a chip system. Optionally, when the target detection device is a chip system, it can be composed of a chip or include a chip and other discrete devices.
[0052] In a fourth aspect, a target detection device is provided, comprising: a processor and an interface circuit; the interface circuit is used to receive a computer program or instruction and transmit it to the processor; the processor is used to execute the computer program or instruction so that the target detection device executes the method described in the first aspect above.
[0053] In conjunction with the fourth aspect above, in one possible implementation, the target detection device is a chip or a chip system. Optionally, when the target detection device is a chip system, it can be composed of a chip or include a chip and other discrete devices.
[0054] In a fifth aspect, a computer-readable storage medium is provided, wherein instructions are stored in the computer-readable storage medium. When the computer-readable storage medium is run on a computer, the computer can execute the method described in the first aspect.
[0055] In a sixth aspect, a computer program product comprising instructions is provided, which, when executed on a computer, enables the computer to execute the method described in the first aspect above.
[0056] In a seventh aspect, an intelligent driving vehicle is provided, which includes a target detection device for executing the method described in the first aspect above.
[0057] Among them, the technical effects brought about by any possible implementation method of the second to seventh aspects can be referred to the technical effects brought about by the above-mentioned first aspect or different possible implementation methods of the first aspect, and will not be repeated here. BRIEF DESCRIPTION OF THE DRAWINGS
[0058] FIG1 is a schematic diagram of the target detection system architecture provided by an embodiment of the present application;
[0059] FIG2 is a schematic diagram of the hardware structure of the target detection device provided in an embodiment of the present application;
[0060] FIG3 is a schematic diagram of a flow chart of a target detection method provided in an embodiment of the present application;
[0061] FIG4 is a schematic diagram of a lane provided in an embodiment of the present application;
[0062] FIG5 is a schematic diagram of the structure of the target detection device provided in an embodiment of the present application. DETAILED DESCRIPTION
[0063] The following describes in detail the implementation of the embodiments of the present application with reference to the accompanying drawings.
[0064] The method provided in the embodiments of the present application can be used in various target detection systems to sense the congestion level of an environment. For example, the congestion level of a road or lane can be sensed, so that the congestion level of the environment can be used to detect targets in the environment to obtain more accurate detection results. The method provided in the embodiments of the present application is described below using the target detection system 10 shown in Figure 1 as an example.
[0065] As shown in Figure 1, it is a schematic diagram of the architecture of the target detection system 10 provided in an embodiment of the present application. In Figure 1, the target detection system 10 may include a target detection device 101. The target detection device 101 can be used to implement the target detection method provided in an embodiment of the present application. For example, the target detection device 101 can obtain first information and second information, and determine the congestion level of the environment based on the first information and the second information, so that the congestion level of the environment can be used to detect targets in the environment to obtain more accurate detection results. This process will be specifically described in the embodiment shown in Figure 3 below and will not be repeated here. Figure 1 is only a schematic diagram and does not constitute a limitation on the applicable scenarios of the technical solution provided in this application.
[0066] The target detection device in the embodiment of the present application, for example, the target detection device 101, can be any device with computing capabilities. Exemplarily, the target detection device may include a handheld device, a vehicle-mounted device, a sensing device, a computing device, or an intelligent driving vehicle. For example, the target detection device may include an advanced driver-assistance system (ADAS), various devices with computing capabilities in the vehicle, a sensing device in the vehicle (such as a camera device in the vehicle, etc.), or an intelligent driving vehicle with an automatic driving function or an assisted driving function.
[0067] In an embodiment of the present application, the ADAS may include a sensor perception module, a sensor fusion module, a target selection module and a control module. The sensor perception module is used to perceive information about the surrounding environment, or obtain information about the surrounding environment from other devices. For example, the sensor perception module can obtain first information and second information. The sensor fusion module can be used to fuse information about the surrounding environment, for example, to determine the congestion level of the environment based on the first information and the second information. The target selection module can be used to select a target, for example, to select a target to be tracked or to select a target to be prevented from collision. The control module can be used to control at least one of the following functions: automatic emergency brake (AEB) function, adaptive cruise control (ACC) function or forward collision warning (FCW) function.
[0068] In an embodiment of the present application, various devices with computing capabilities in the vehicle may include: a gateway, an on-board T-Box (telematics box), a body control module (BCM), a smart cockpit domain controller (CDC), a multi-domain controller (MDC), a vehicle control unit (VCU), an electronic control unit (ECU), a vehicle domain controller (VDC) or a vehicle integrated / integration unit (VIU), etc.
[0069] Optionally, the target detection device 101 further has a sensing capability for sensing the first information and / or the second information.
[0070] Optionally, the target detection system 10 further includes a perception device 102 and / or a perception device 103 communicatively connected to the target detection device 101. The perception device 102 can obtain first information and send the first information to the target detection device 101. The perception device 103 can obtain second information and send the second information to the target detection device 101.
[0071] The sensing device in the embodiments of the present application, for example, sensing device 102 or sensing device 103, can be any device with sensing capabilities. For example, the sensing device can include a camera, radar, or sonar. The camera can include a monocular camera, a binocular camera, a trinocular camera, or a depth camera. The radar can include a lidar or a millimeter-wave radar.
[0072] The target detection system 10 shown in FIG1 is for illustrative purposes only and is not intended to limit the technical solutions of this application. Those skilled in the art will appreciate that, in a specific implementation, the target detection system 10 may also include other devices, and the number of target detection devices or sensing devices may be determined based on specific needs and is not limited.
[0073] Optionally, each device in Figure 1 of the embodiment of the present application (for example, a target detection device or a perception device, etc.) can be a general device or a dedicated device, and the embodiment of the present application does not make specific limitations on this.
[0074] Optionally, the relevant functions of each device in Figure 1 of the embodiment of the present application (for example, a target detection device or a perception device, etc.) can be implemented by a single device, or by multiple devices together, or by one or more functional modules within a device, and the embodiment of the present application does not specifically limit this. It is understandable that the above functions can be network elements in hardware devices, software functions running on dedicated hardware, or a combination of hardware and software, or virtualization functions instantiated on a platform (for example, a cloud platform).
[0075] In a specific implementation, each device in FIG1 of the embodiment of the present application (for example, a target detection device or a perception device, etc.) can adopt the composition structure shown in FIG2, or include the components shown in FIG2. FIG2 is a schematic diagram of the hardware structure of a target detection device applicable to the embodiment of the present application. The target detection device 20 includes at least one processor 201 and at least one communication interface 204 for implementing the method provided in the embodiment of the present application. The target detection device 20 may also include a communication line 202 and a memory 203.
[0076] The processor 201 may be a general-purpose central processing unit (CPU), a microprocessor, an application-specific integrated circuit (ASIC), or one or more integrated circuits for controlling the execution of the program of the present application.
[0077] The communication link 202 may include a path for transmitting information between the above components, such as a bus.
[0078] Communication interface 204 is used to communicate with other devices or communication networks. Communication interface 204 can be any transceiver-like device, such as an Ethernet interface, a radio access network (RAN) interface, a wireless local area network (WLAN) interface, a transceiver, a pin, a bus, or a transceiver circuit.
[0079] The memory 203 is used to store computer-executable instructions involved in executing the solution provided by the embodiment of the present application, and the execution is controlled by the processor 201. The processor 201 is used to execute the computer-executable instructions stored in the memory 203, thereby implementing the method provided by the embodiment of the present application.
[0080] Optionally, the computer-executable instructions in the embodiments of the present application may also be referred to as application code, which is not specifically limited in the embodiments of the present application.
[0081] The coupling in the embodiments of the present application is an indirect coupling or communication connection between devices, units or modules, which can be electrical, mechanical or other forms, and is used for information exchange between devices, units or modules.
[0082] As an embodiment, the processor 201 may include one or more CPUs, such as CPU0 and CPU1 in FIG. 2 .
[0083] As an embodiment, the target detection device 20 may include multiple processors, such as the processor 201 and the processor 207 in Figure 2. Each of these processors may be a single-core (single-CPU) processor or a multi-core (multi-CPU) processor.
[0084] As an embodiment, the object detection apparatus 20 may further include an output device 205 and / or an input device 206. The output device 205 is coupled to the processor 201.
[0085] Optionally, the target detection device 20 further includes a perception module (not shown in FIG2 ) for perceiving the first information and / or the second information. The perception module may include at least one of the following: a camera, a radar, or a sonar.
[0086] It is understandable that the composition structure shown in Figure 2 does not constitute a limitation on the target detection device. In addition to the components shown in Figure 2, the target detection device may include more or fewer components than shown in the figure, or combine certain components, or arrange the components differently.
[0087] The method provided by the embodiment of the present application will be described below with reference to the accompanying drawings. Each network element in the following embodiment may include the components shown in FIG2 , which will not be described in detail.
[0088] It can be understood that the method provided in the embodiments of the present application can be applied to multiple fields, such as: unmanned driving, automatic driving, assisted driving, intelligent driving, connected driving, intelligent connected driving, car sharing, etc.
[0089] As shown in FIG3 , a target detection method provided in an embodiment of the present application may include steps S301 to S303:
[0090] S301: The target detection device obtains first information.
[0091] The target detection device in S301 may be the target detection device 101 shown in FIG1 .
[0092] In an embodiment of the present application, the first information may include first perception information of the environment. The environment may be the environment in which the target detection device is located, or the environment around the target detection device. Taking the target detection device as an intelligent driving vehicle as an example, the environment may include the lane in which the intelligent driving vehicle is located. It is understandable that the embodiment of the present application is described by taking the environment including at least one lane as an example. The case where the environment includes other scenes is similar to the case where the environment includes at least one lane. Please refer to the corresponding description in the embodiment of the present application and do not elaborate on it.
[0093] In an embodiment of the present application, the first perception information may include information about at least one lane. For example, the first perception information includes information about lane 1, or the first perception information includes information about lane 1 and lane 2.
[0094] In this embodiment of the present application, the information about any lane may include the location information of the lane. For example, the information about a lane may include a function indicating the location of the lane. For another example, the information about a lane may include the location information of a road curb. In this case, the entire road may be considered a lane. Optionally, the information about any lane may also indicate the width of the lane.
[0095] For example, taking the three lanes (lane 401, lane 402, and lane 403) shown in FIG4 as an example, for lane 402, the information of lane 402 may include a function representing lane line 405 (e.g., y=c3x 3 +c2x 2 +c1x+c0) and a function representing lane line 406 (e.g., y=a3x 3 +a2x 2 +a1x+a0). Wherein, x is the ordinate in the coordinate system where the target detection device is located, and y is the abscissa in the coordinate system. The coordinate system where the target detection device is located may be a coordinate system with the target detection device as the origin. After the target detection device obtains the information of lane 402, it can determine the position of lane 402 based on the information of lane 402. For lane 403, the information of lane 403 may include a function representing lane line 406 (e.g., y=a3x 3 +a2x 2 +a1x+a0) and the width information of lane 403. After the target detection device obtains the information of lane 403, it can determine the position of lane 403 according to the information of lane 403.
[0096] It is understandable that the above functions for representing lane line 405 and lane line 406 are merely exemplary. In practical applications, lane lines may also be represented by other functions, without limitation.
[0097] It will be appreciated that in the above example, lanes 401, 402, and 403 are each considered a single lane. In specific applications, all lanes on a road may be considered a single lane. For example, lanes 401, 402, and 403 may be considered a single lane. In this case, the lane information may indicate the location of the entire road. For example, the lane information may include the location of the roadside. Optionally, the lane information may also include road width information.
[0098] S302: The target detection device obtains second information.
[0099] In an embodiment of the present application, the second information may include second perception information of the environment. The environment may be the environment in which the target detection device is located, or the environment around the target detection device. The second perception information may include the position information of at least one target on at least one lane, or the second perception information may include the position information of at least one target on at least one lane, and the speed information of at least one target on at least one lane. The position information of at least one target on at least one lane may indicate the position of the at least one target. The speed information of at least one target may indicate the speed of the at least one target. In an embodiment of the present application, the position information of at least one target may include the coordinates of the target in a rectangular coordinate system, or include the coordinates of the target in a polar coordinate system, without limitation. The above-mentioned rectangular coordinate system or polar coordinate system is the coordinate system where the target detection device is located.
[0100] It is understandable that the target detection device may obtain the first information and the second information in a variety of ways, which will be described in detail below.
[0101] (1) The method for the target detection device to obtain the first information:
[0102] In one possible implementation, the first information is obtained by the target detection device from a first perception device. That is, the first perception device may obtain the first information and transmit it to the target detection device. The first perception device may be perception device 102 shown in FIG1 . For example, the first perception device may be a camera, a laser radar, a millimeter-wave radar, or a sonar.
[0103] In one possible design, if the first sensing device is a camera, lidar, or sonar, the lane information may include a function indicating the lane's position, or alternatively, the lane information may include a function indicating the lane's position and information indicating the lane's width. If the first sensing device is a millimeter-wave radar, since millimeter-wave radars may not be able to "see" or detect lane markings but can "see" or detect roadside curbs, the lane information may include the position of the roadside curb, or alternatively, the lane information may include the position of the roadside curb and road width information.
[0104] In another possible implementation, the first information is locally acquired by the target detection device. That is, the target detection device may have a sensing capability. For example, the target detection device may be equipped with a sensing device, such as a camera, lidar, millimeter-wave radar, or sonar, and acquire the first information through the sensing device.
[0105] (2) The method for the target detection device to obtain the second information:
[0106] In one possible implementation, the second information is obtained by the target detection device from a second perception device. That is, the second perception device may obtain the second information and transmit it to the target detection device. The second perception device may be perception device 103 shown in FIG1 . For example, the second perception device may be a millimeter-wave radar, a lidar, or a sonar.
[0107] In another possible implementation, the second information is locally acquired by the target detection device. That is, the target detection device may have a sensing capability. For example, the target detection device may be equipped with a sensing device such as a lidar, millimeter-wave radar, or sonar, and acquire the second information through the sensing device.
[0108] It can be understood that the specific forms of the above-mentioned first sensing device and second sensing device are only exemplary. In specific applications, the first sensing device and / or the second sensing device can also be other devices that can detect or "see" objects such as targets, lane lines or curbs, without limitation.
[0109] For example, taking the three lanes (lane 401, lane 402 and lane 403) shown in Figure 4 as an example, if the target detection device or the second perception device is configured on target 4022, the second perception information includes the position information of target 4011, the position information of target 4012, the position information of target 4021 and the position information of target 4031, or, the second perception information includes the position information of target 4011, the speed information of target 4011, the position information of target 4012, the speed information of target 4012, the position information of target 4021, the speed information of target 4021, the position information of target 4031 and the speed information of target 4031.
[0110] It is understandable that the types of the first sensing device and the second sensing device may be the same or different, which will be explained in detail below.
[0111] In one possible design, the first and second sensing devices are different types of sensing devices. That is, the first and second information are acquired by different types of sensing devices. For example, the first sensing device is a camera, and the second sensing device is a millimeter-wave radar. In this case, the first information can be acquired by a sensing device that is sensitive to graphics (such as lane markings), and the second information can be acquired by a sensing device that is sensitive to targets (such as vehicles, pedestrians, trees, or road test devices), thereby obtaining more accurate first and second information.
[0112] Another possible design is that the first sensing device and the second sensing device are of the same type. That is, the first information and the second information are acquired by the same type of sensing device. For example, the first sensing device and the second sensing device are both millimeter-wave radars. In this case, the first information and the second information contain similar information, which is convenient and easy to process. In addition, multiple low-cost sensing devices (such as millimeter-wave radars) are placed in different locations to acquire the first information and the second information, thereby reducing costs.
[0113] It is understandable that the embodiment of the present application does not limit the execution order of S301 and S302. For example, the embodiment of the present application can execute S301 first and then S302, or execute S302 first and then S301, or execute S301 and S302 simultaneously, without limitation.
[0114] It is understandable that after the target detection device obtains the first information and the second information, it can determine the congestion level of the environment based on the first information and the second information. However, considering that in actual applications, targets usually travel according to certain rules, for example, according to lanes, the congestion conditions in different lanes may be different. Therefore, the method provided in the embodiments of the present application can determine the congestion level based on the lane, so that targets in the lane can be detected based on the congestion level of the lane.
[0115] In one possible implementation, after S302, the target detection device may divide at least one target into lanes based on the first perception information and the second perception information, so that the target detection device knows which targets are on which lanes.
[0116] In one possible design, the target detection device determines in which lane each of the at least one target is located based on the position of at least one lane indicated by the first perception information and the position of at least one target indicated by the second perception information. Specifically, if the position of the target indicated by the second perception information overlaps with the position of a lane indicated by the first perception information, the target detection device determines that the target is in this lane; if the position of the target indicated by the second perception information does not overlap with the position of the lane indicated by the first perception information, the target perception device determines that the target is not in this lane. It will be understood that if the second perception information also includes speed information of at least one target on at least one lane, the target detection device can also determine the speed of the target in at least one lane.
[0117] For example, taking the three lanes (lane 401, lane 402 and lane 403) shown in Figure 4 as an example, if the first perception information includes information of lane 401, information of lane 402 and information of lane 403, and the second perception information includes position information of target 4011, position information of target 4012, position information of target 4021 and position information of target 4031, then the target detection device can determine that the position of lane 401 overlaps with the position of target 4011, and the position of lane 401 also overlaps with the position of target 4012, so target 4011 and target 4012 are located on lane 401, the target detection device can determine that the position of lane 402 overlaps with the position of target 4021, so target 4021 is located on lane 402, and the target detection device can determine that the position of lane 403 overlaps with the position of target 4031, so target 4031 is located on lane 403.
[0118] S303: The target detection device determines the congestion level of the environment according to the first information and the second information.
[0119] In an embodiment of the present application, the congestion level of the environment can be used to detect at least one target in the environment. For example, the congestion level of the environment can be used to determine a sensor fusion strategy so that the first device estimates the actual position of one or more targets in the environment, and / or, the congestion level of the environment can be used to determine a strategy for perceiving targets so that the second device senses whether there are targets in the environment. The first device and the second device can be the same device or different devices. It is understandable that the first device and / or the second device can also be target detection devices. The process by which the target detection device determines the sensor fusion strategy based on the congestion level of the environment will be introduced in S304 below, and the process by which the target detection device determines the strategy for perceiving targets based on the congestion level of the environment will be introduced in S305 below, which will not be described in detail here.
[0120] The following describes the specific process by which an object detection device determines the congestion level of the environment based on the first information and the second information, using an environment including a first lane as an example. It will be appreciated that if the environment includes multiple lanes, the object detection device may repeatedly perform the following process to determine the congestion level of each lane, thereby obtaining the congestion level of the environment.
[0121] In one possible implementation, the target detection device determines information of a target on a first lane of at least one lane based on the first perception information and the second perception information, and determines a congestion level of the first lane based on the information of the target on the first lane.
[0122] In the embodiment of the present application, the first lane is any lane of at least one lane, or in other words, the first lane is any lane in the environment.
[0123] In an embodiment of the present application, the information of the targets on the first lane includes at least one of the following: the number of targets on the first lane, the speed of the targets on the first lane, the average distance between two adjacent targets on the first lane, the minimum distance between two adjacent targets on the first lane, or the traffic density of the first lane.
[0124] In this embodiment of the present application, the speed of the objects in the first lane can be the average speed of the objects in the first lane, the minimum speed of the objects in the first lane, or the maximum speed of the objects in the first lane. The traffic density of the first lane can represent the number of objects within a preset distance of the first lane. For example, if the preset distance is 50 meters and the traffic density of the first lane is 10, the traffic density of the first lane indicates that there are 10 objects within 50 meters of the first lane.
[0125] It is understandable that after the target detection device divides at least one target into lanes based on the first perception information and the second perception information, the target detection device can determine which targets are in the first lane, that is, obtain the number of targets in the first lane. If the second perception information includes speed information of at least one target in at least one lane, the target detection device can also directly obtain the speed of the target in the first lane. If the second perception information does not include speed information of at least one target in at least one lane, the target detection device can obtain the second perception information multiple times over a period of time, determine the speed of each target in the first lane based on the second perception information obtained multiple times, and then obtain the speed of the target in the first lane.
[0126] It can be understood that the target detection device can obtain the average distance between two adjacent targets on the first lane, the minimum distance between two adjacent targets on the first lane, or the traffic density of the first lane based on the position information of the two adjacent targets on the first lane.
[0127] It is understood that after the object detection device obtains information about the object in the first lane, it can determine the congestion level of the first lane based on the information about the object in the first lane. For example, the object detection device determines the congestion level of the first lane based on the information about the object in the first lane and at least one threshold value.
[0128] In an embodiment of the present application, at least one threshold value may include at least one of the following: a speed threshold value, a spacing threshold value, a quantity threshold value (such as a first quantity threshold value, and / or a second quantity threshold value) or a density threshold value (such as a first density threshold value, and / or a second density threshold value). It is understandable that the above threshold values may be pre-set or calculated based on the information of the target on the first lane. If the above threshold values are pre-set, the operation of the target detection device can be simplified. If the above threshold values are calculated based on the information of the target on the first lane, the robustness of the target detection method provided in the embodiment of the present application can be improved, making it more adaptable.
[0129] In one possible design, before the target detection device determines the congestion level of the first lane based on the information of the target on the first lane and at least one threshold, the target detection device obtains at least one threshold. For example, the target detection device determines the speed threshold based on the speeds of multiple targets on the first lane. The speed threshold is the median of the speeds of multiple targets on the first lane, the minimum speed of multiple targets on the first lane, or the maximum speed of multiple targets on the first lane. For another example, the target detection device obtains a spacing threshold based on the speed threshold and the time interval. The speed threshold can be preset, or determined by the target detection device based on the speeds of multiple targets on the first lane. The time interval is preset.
[0130] It is understood that in specific applications, the congestion level of the first lane can be set as needed to suit different scenarios. For example, the congestion level of the first lane can include 2 levels, 3 levels, 4 levels, 5 levels, 6 levels, or more levels, without limitation.
[0131] The following uses Case 1 and Case 2 as examples to describe the specific process by which the target detection device determines the congestion level of the first lane based on the information of the target on the first lane and at least one threshold value. In Case 1, the information of the target on the first lane includes one parameter, and the target detection device can determine the congestion level of the first lane based on the one parameter and the threshold value corresponding to the one parameter. Because the target detection device in Case 1 does not need to combine multiple parameters in the information of the target on the first lane for processing, it is relatively simple to implement and has low complexity. In Case 2, the information of the target on the first lane includes multiple parameters, and the target detection device determines the congestion level of the first lane based on the multiple parameters and the threshold values corresponding to the multiple parameters. Compared with Case 1, the target detection device in Case 2 is slightly more complicated to implement, but because the target detection device comprehensively considers multiple parameters, the determined congestion level of the first lane is more accurate. A detailed introduction is given below.
[0132] Case 1: The information of the target on the first lane includes a parameter, and the target detection device determines the congestion level of the first lane according to the parameter and a threshold value corresponding to the parameter.
[0133] Exemplarily, taking the case where the information of the target on the first lane includes the speed of the target on the first lane, the at least one threshold includes a speed threshold, and the congestion of the first lane is equal to 2 levels, if the speed of the target on the first lane is greater than or equal to the speed threshold, the congestion level of the first lane is level 1; or, if the speed of the target on the first lane is less than the speed threshold, the congestion level of the first lane is level 0.
[0134] For example, taking the case where the information of the targets on the first lane includes the average distance between two adjacent targets on the first lane, at least one threshold includes a distance threshold 1 and a distance threshold 2, and the congestion of the first lane includes three levels, if the average distance between two adjacent targets on the first lane is greater than or equal to the distance threshold 1, the congestion level of the first lane is level 2; or, if the average distance between two adjacent targets on the first lane is less than the distance threshold 1 and greater than or equal to the distance threshold 2, the congestion level of the first lane is level 1; or, if the average distance between two adjacent targets on the first lane is less than the distance threshold 2, the congestion level of the first lane is level 0.
[0135] For example, taking the case where the information of the targets on the first lane includes the minimum distance between two adjacent targets on the first lane, at least one threshold includes a distance threshold 3 and a distance threshold 4, and the congestion of the first lane is equal to 3 levels, if the minimum distance between two adjacent targets on the first lane is greater than or equal to the distance threshold 3, the congestion level of the first lane is level 2; or, if the minimum distance between two adjacent targets on the first lane is less than the distance threshold 3 and greater than or equal to the distance threshold 4, the congestion level of the first lane is level 1; or, if the minimum distance between two adjacent targets on the first lane is less than the distance threshold 4, the congestion level of the first lane is level 0.
[0136] Exemplarily, taking the case where the information of targets on the first lane includes the number of targets on the first lane, at least one threshold includes number threshold 1, number threshold 2 and number threshold 3, and the congestion of the first lane is equal to 4 levels, if the number of targets on the first lane is greater than or equal to number threshold 1, the congestion level of the first lane is level 3; or, if the number of targets on the first lane is less than number threshold 1 and greater than or equal to number threshold 2, the congestion level of the first lane is level 2; or, if the number of targets on the first lane is less than number threshold 2 and greater than or equal to number threshold 3, the congestion level of the first lane is level 1; or, if the number of targets on the first lane is less than number threshold 3, the congestion level of the first lane is level 0.
[0137] Exemplarily, taking the case where the information of the target on the first lane includes the traffic density of the first lane, at least one threshold includes density threshold 1, density threshold 2, density threshold 3 and density threshold 4, and the congestion of the first lane includes 5 levels, if the traffic density of the first lane is greater than or equal to density threshold 1, the congestion level of the first lane is level 4; or, if the traffic density of the first lane is less than density threshold 1 and greater than or equal to density threshold 2, the congestion level of the first lane is level 3; or, if the traffic density of the first lane is less than density threshold 2 and greater than or equal to density threshold 3, the congestion level of the first lane is level 2; or, if the traffic density of the first lane is less than density threshold 3 and greater than or equal to density threshold 4, the congestion level of the first lane is level 1; or, if the traffic density of the first lane is less than density threshold 4, the congestion level of the first lane is level 0.
[0138] Case 2: The information of the target on the first lane includes multiple parameters, and the target detection device determines the congestion level of the first lane according to the multiple parameters and thresholds corresponding to the multiple parameters.
[0139] For example, if the information of the targets on the first lane includes the number of targets on the first lane, the speed of the targets on the first lane, the average distance between two adjacent targets on the first lane, and the minimum distance between two adjacent targets on the first lane, and at least one threshold includes a first number threshold, a speed threshold, a distance threshold, and a second number threshold, and the congestion of the first lane is equal to 6 levels, for example, if the number of targets on the first lane is greater than or equal to the first number threshold, and the speed of the targets on the first lane is less than or equal to the speed threshold, then the congestion level of the first lane is level 5; or if the number of targets on the first lane is greater than or equal to the first number threshold, then the congestion level of the first lane is level 5. threshold, the congestion level of the first lane is level 4; or, if the average spacing between two adjacent targets on the first lane is less than or equal to the spacing threshold, the congestion level of the first lane is level 3; or, if the minimum spacing between two adjacent targets on the first lane is less than or equal to the spacing threshold, the congestion level of the first lane is level 2; if the minimum spacing between two adjacent targets on the first lane is greater than the spacing threshold, and the number of targets on the first lane is greater than or equal to the second number threshold, the congestion level of the first lane is level 1; or, if the number of targets on the first lane is less than the second number threshold, the congestion level of the first lane is level 0.
[0140] For example, the information of the target on the first lane includes the speed of the target on the first lane, the average distance between two adjacent targets on the first lane, the minimum distance between two adjacent targets on the first lane and the traffic density of the first lane, and at least one threshold includes a first density threshold, a speed threshold, a distance threshold and a second density threshold. The congestion level of the first lane includes 6 levels. For example, if the traffic density of the first lane is greater than or equal to the first density threshold, and the speed of the target on the first lane is less than or equal to the speed threshold, the congestion level of the first lane is level 5; or, if the traffic density of the first lane is greater than or equal to the first density threshold, the congestion level of the first lane is level 6. value, the congestion level of the first lane is level 4; or, if the average spacing between two adjacent targets on the first lane is less than or equal to the spacing threshold, the congestion level of the first lane is level 3; or, if the minimum spacing between two adjacent targets on the first lane is less than or equal to the spacing threshold, the congestion level of the first lane is level 2; if the minimum spacing between two adjacent targets on the first lane is greater than the spacing threshold and the traffic density of the first lane is greater than or equal to the second density threshold, the congestion level of the first lane is level 1; or, if the traffic density of the first lane is less than the second density threshold, the congestion level of the first lane is level 0.
[0141] It is understandable that the examples in the above-mentioned Case 1 or Case 2 are merely exemplary. In specific applications, the target detection device may also determine the congestion level of the first lane in other ways without limitation.
[0142] Optionally, after S303, the target detection device sends information about the congestion level of the environment. The information about the congestion level of the environment may indicate the congestion level of the environment. For example, the target detection device may send information about the congestion level of the environment to an intelligent driving vehicle so that the intelligent driving vehicle can select a more optimal road planning solution and / or vehicle control strategy based on the information, and / or so that multiple vehicles can share the congestion level of the environment, thereby forming a regional congestion map to facilitate each vehicle's own driving planning and / or regional traffic flow control (e.g., traffic light control) on the road. For another example, if the target detection device includes an ADAS, after the sensor fusion module in the ADAS determines the congestion level of the environment based on the first information and the second information, it may send the information about the congestion level of the environment to a target selection module so that the target selection module can adjust its target selection algorithm based on the information, and / or send the information about the congestion level of the environment to a control module so that the control module can adjust parameters of functions controlled by the control module based on the information (e.g., in the case of high congestion levels, adjusting parameters in the AEB function to make braking more sensitive and shorten braking time).
[0143] Based on the method shown in FIG3 , the target detection device can obtain first information including first perception information of the environment and second information including second perception information of the environment, and determine the congestion level of the environment based on the first information and the second information, so that the congestion level of the environment can be used to detect targets in the environment. In other words, using the method shown in FIG3 , it is possible to detect targets in the environment based on the congestion level of the environment. For example, different target detection strategies can be used for different congestion levels, resulting in more accurate target detection results.
[0144] The following uses the example of using the congestion level of the environment to determine the sensor fusion strategy and / or the congestion level of the environment to determine the strategy for sensing the target to introduce how the congestion level of the environment is used to detect at least one target in the environment.
[0145] Optionally, the method shown in FIG3 further includes S304 and / or S305.
[0146] S304: The target detection device determines a sensor fusion strategy for the first lane according to the congestion level of the first lane.
[0147] In the embodiment of the present application, the sensor fusion strategy of the first lane can be used to estimate the actual position of the object in the first lane. It is understandable that different congestion levels can correspond to different sensor fusion strategies.
[0148] In one possible implementation, if the congestion level of the first lane is greater than or equal to the first level, the sensor fusion strategy for the first lane is the first fusion strategy; alternatively, if the congestion level of the first lane is less than the first level, the sensor fusion strategy for the first lane is the second fusion strategy. It is understood that the first level can be set as needed. For example, if the congestion level of the first lane is categorized into six levels, the first level can be Level 2, Level 3, Level 4, or Level 5. The sensor fusion strategy can also include three or more fusion strategies, without limitation.
[0149] Before S304, the target detection device obtains third information from a perception device different from the second perception device, such as the first perception device. The third information may include the position information of at least one target on at least one lane. It is understandable that the third information may also be included in the first perception information. That is to say, the above-mentioned third information may also be obtained in S301. It is understandable that the first fusion strategy and the second fusion strategy may use different algorithms to fuse the position information in the third information and the position information in the second perception information to estimate the actual position of the target on the first lane. First, the position information in the third information and the position information in the second perception information are introduced.
[0150] In one possible design, the position information in the third information includes the first distance to the first target, the first angle of the first target, the horizontal coordinate of the first target, and the vertical coordinate of the first target. The position information in the second perception information includes the horizontal coordinate of the second target and the vertical coordinate of the second target.
[0151] In the embodiment of the present application, the first target is any target in the first lane, and the first target is different from the target where the target detection device is located. For example, if the first target and the target where the target detection device is located are both vehicles, the vehicle corresponding to the first target and the vehicle corresponding to the target where the target detection device is located are different vehicles.
[0152] In an embodiment of the present application, the first distance is the distance between the target detection device and the first target, the first angle is the angle between the forward direction of the target detection device and the first connecting line, and the first connecting line is the connecting line between the target detection device and the first target. Among them, the forward direction of the target detection device can be described as the forward direction of the target where the target detection device is located. For example, if the target where the target detection device is located is a vehicle, the forward direction is the direction pointed by the front of the vehicle. The second target is the target corresponding to the first target among the at least one target corresponding to the second perception information.
[0153] For example, taking the lanes shown in FIG4 as an example, if the first lane is lane 401, the target detection device is target 4013, and the first target is target 4012, then the abscissa of the first target is the abscissa of target 4012 perceived by the first sensing device, the ordinate of the first target is the ordinate of target 4012 perceived by the first sensing device, the first distance of the first target is the distance between target 4013 and target 4012 perceived by the first sensing device, and the first angle α of the first target is the angle between the forward direction of target 4013 perceived by the first sensing device and the line connecting target 4013 and target 4012. The abscissa of the second target is the abscissa of target 4012 perceived by the second sensing device, and the ordinate of the second target is the ordinate of target 4012 perceived by the second sensing device.
[0154] One possible design is that the first fusion strategy is to fuse the horizontal coordinate of the first target, the vertical coordinate of the first target, the horizontal coordinate of the second target, and the vertical coordinate of the second target to obtain the actual position of the target on the first lane; the second fusion strategy is to fuse the first angle, the first distance, the horizontal coordinate of the second target, and the vertical coordinate of the second target to obtain the actual position of the target on the first lane.
[0155] It can be understood that when the congestion level of the first lane is low (i.e., the first lane is less congested), the first angle and the first distance perceived by the first perception device are relatively accurate (e.g., by performing image recognition on the photos taken by the camera device, a relatively accurate first angle and first distance can be obtained). Therefore, by fusing the first angle, the first distance, the horizontal coordinate of the second target, and the vertical coordinate of the second target (i.e., through the second fusion strategy), a relatively accurate position can be estimated. When the congestion level of the first lane is high (i.e., the first lane is more congested), the first angle and the first distance perceived by the first perception device have large errors (e.g., the first angle and the first distance obtained by image recognition technology have large errors). By fusing the first angle, the first distance, the horizontal coordinate of the second target, and the vertical coordinate of the second target (i.e., through the second fusion strategy), the estimated position is inaccurate. Therefore, the horizontal coordinate of the first target, the vertical coordinate of the first target, the horizontal coordinate of the second target, and the vertical coordinate of the second target can be fused (i.e., through the first fusion strategy) to estimate a more accurate position.
[0156] It is understandable that, ideally, the at least one target corresponding to the third information corresponds one-to-one to the at least one target corresponding to the second perception information. That is, if the first perception device perceives three targets, the second perception device should also perceive these three targets. However, in actual applications, due to various reasons, such as: the accuracy of the first perception device or the second perception device is different, or the principle of the first perception device perceiving the target (such as perceiving the target through image recognition technology) is different from the principle of the second perception device perceiving the target (such as perceiving the target through radar), the at least one target corresponding to the third information does not correspond one-to-one to the at least one target corresponding to the second perception information. For example, if the first perception device detects multiple targets or the second perception device misses a detection, the number of targets perceived by the first perception device is greater than the number of targets perceived by the second perception device. Alternatively, if the first perception device misses a detection or the second perception device detects multiple targets, the number of targets perceived by the first perception device is less than the number of targets perceived by the second perception device.
[0157] In the embodiments of the present application, regardless of whether the at least one target corresponding to the third information corresponds to the at least one target corresponding to the second perception information, the first device can determine the target corresponding to the first target based on the third information and the second perception information. For example, the first device can determine, as the second target, a target among the at least one target corresponding to the second perception information that is less than or equal to the second distance from the first target. The first device is a device for estimating the actual location of one or more targets in an environment.
[0158] It can be understood that if there is no target whose distance to the first target is less than or equal to the second distance among the at least one target corresponding to the second perception information, the fusion strategy will not be executed on the first target, that is, the first target will not be fused with the target corresponding to the second perception information. Alternatively, the target closest to the first target among the at least one target corresponding to the second perception information can be determined as the second target, and the fusion strategy will be executed on the first target and the second target according to the congestion level of the first lane.
[0159] It can be understood that through S304, the target detection device can determine a suitable sensor fusion strategy based on the congestion level of the first lane, which not only makes the position of the target estimated according to the sensor fusion strategy more accurate, but also enables a more accurate number of targets to be determined when determining the number of targets.
[0160] S305: The target detection device determines a strategy for sensing targets in the first lane according to the congestion level of the first lane.
[0161] In the embodiment of the present application, the strategy for sensing targets in the first lane can be used to sense whether there is a target in the first lane. It is understandable that different congestion levels correspond to different strategies for sensing targets in the first lane. The higher the congestion level of the first lane (i.e., the more congested the first lane is), the more relaxed the strategy for sensing targets in the first lane is to prevent missed targets; the lower the congestion level of the first lane (i.e., the less congested the first lane is), the stricter the strategy for sensing targets in the first lane is to prevent false targets from being identified.
[0162] One possible implementation method is to use a first perception method to perceive whether there is a target in the first lane if the congestion level of the first lane is greater than or equal to the second level; or, if the congestion level of the first lane is less than the second level, use a second perception method to perceive whether there is a target in the first lane.
[0163] It is understood that the second level can be set as needed. Taking the six congestion levels for the first lane as an example, the second level can be level 2, level 3, level 4, or level 5. The second level and the first level can be the same or different. The target perception strategy can also include three or more perception methods without limitation.
[0164] In an embodiment of the present application, the first perception method is to determine the target obtained by sensor fusion based on the third information and the second perception information, and the target that has not been sensor fused in the third information and the target that has not been sensor fused in the second perception information, as the target on the first lane; the second perception method is to determine the target obtained by sensor fusion based on the third information and the second perception information as the target on the first lane.
[0165] As described in S304, in actual applications, at least one target corresponding to the third information does not correspond one-to-one with at least one target corresponding to the second perception information, and the first perception device or the second perception device may miss or detect multiple targets. Therefore, when fusing the targets corresponding to the third information and the targets corresponding to the second perception information according to the sensor fusion strategy, the following three types of targets may appear: targets obtained by sensor fusion of the third information and the second perception information; targets in the third information that are not sensor fused; and targets in the second perception information that are not sensor fused.
[0166] For example, if the third information includes the location information of target 1, target 2, and target 3, and the second perception information includes the location information of target 4, target 5, and target 6, then if target 2 corresponds to target 5, and target 3 corresponds to target 6, then the targets obtained by sensor fusion based on the third information and the second perception information include the targets obtained by sensor fusion based on the location information of target 2 and target 5, and the targets obtained by sensor fusion based on the location information of target 3 and target 6. Targets not subjected to sensor fusion in the third information include target 1. Targets not subjected to sensor fusion in the second perception information include target 4.
[0167] It is understandable that when the congestion level of the first lane is high (i.e., the first lane is more congested), in order to prevent collisions, the strategy for sensing targets in the first lane can be set to be relatively loose. For example, the acquired targets (such as targets obtained by sensor fusion based on the first perception information and the second perception information, targets that are not sensor fused in the first perception information, and targets that are not sensor fused in the second perception information) are not screened, but the acquired targets are directly determined as targets in the first lane. When the congestion level of the first lane is low (i.e., the first lane is less congested), the strategy for sensing targets in the first lane can be set to be relatively strict. For example, the acquired targets can be screened, and the screened targets (such as targets obtained by sensor fusion based on the first perception information and the second perception information) are determined as targets in the first lane to prevent the determination of false targets.
[0168] It can be understood that through S305, the target detection device can determine a suitable strategy for sensing targets in the first lane according to the congestion level of the first lane. When the first lane is more congested, it can prevent collisions, and when the first lane is less congested, it can prevent false targets from being determined.
[0169] Among them, the actions of the target detection device in the above S301-S305 can be executed by the processor 201 in the target detection device 20 shown in Figure 2 calling the application code stored in the memory 203, and the embodiment of the present application does not impose any limitation on this.
[0170] The various embodiments mentioned above in this application can be combined without limitation if there is no contradiction between the solutions.
[0171] It can be understood that in the above embodiments, the methods and / or steps implemented by the target detection device can also be implemented by components (such as chips or circuits) that can be used in the target detection device, without limitation.
[0172] The above mainly describes the target detection method provided by the embodiment of the present application. The embodiment of the present application also provides a target detection device, which can be the target detection device in the above method embodiment, or a device including the above target detection device, or a component that can be used for the target detection device. It can be understood that in order to achieve the above functions, the above target detection device includes hardware structures and / or software modules corresponding to the execution of each function. Those skilled in the art should easily realize that, in combination with the units and algorithm operations of the various examples described in the embodiments disclosed herein, the present application can be implemented in the form of hardware or a combination of hardware and computer software. Whether a function is executed in the form of hardware or computer software driving hardware depends on the specific application and design constraints of the technical solution. Professional and technical personnel can use different methods to implement the described functions for each specific application, but such implementation should not be considered to be beyond the scope of this application.
[0173] The embodiment of the present application can divide the target detection device into functional modules according to the above method example. For example, each functional module can be divided according to each function, or two or more functions can be integrated into one processing module. The above integrated modules can be implemented in the form of hardware or in the form of software functional modules. It is understandable that the division of modules in the embodiment of the present application is schematic and is only a logical function division. In actual implementation, there may be other division methods.
[0174] For example, FIG5 shows a schematic diagram of the structure of a target detection device 50, where the functional modules are divided in an integrated manner. The target detection device 50 includes a processing module 501. Optionally, the target detection device 50 also includes a transceiver module 502. The processing module 501, which may also be referred to as a processing unit, is configured to perform operations other than transceiver operations and may, for example, be a processing circuit or processor. The transceiver module 502, which may also be referred to as a transceiver unit, is configured to perform transceiver operations and may, for example, be a transceiver circuit, a transceiver, a transceiver, or a communication interface.
[0175] In some embodiments, the target detection device 50 may further include a storage module (not shown in FIG. 5 ) for storing program instructions and data.
[0176] Exemplarily, the target detection device 50 is used to implement the functions of the target detection device in the above method embodiment. The target detection device 50 is, for example, the target detection device described in the embodiment shown in FIG3 .
[0177] The processing module 501 is configured to obtain first information, wherein the first information includes first perception information of the environment. For example, the processing module 501 may be configured to execute S301.
[0178] The processing module 501 is further configured to obtain second information, wherein the second information includes second perception information of the environment. For example, the processing module 501 may also be configured to execute S302.
[0179] The processing module 501 is further configured to determine a congestion level of the environment based on the first information and the second information. The congestion level of the environment is used to detect at least one target in the environment. For example, the processing module 501 can also be configured to execute S303.
[0180] In one possible implementation, the first perception information includes information of at least one lane; the second perception information includes position information of at least one target on at least one lane, or the second perception information includes position information of at least one target on at least one lane and speed information of at least one target on at least one lane.
[0181] In a possible implementation, the processing module 501 is further configured to divide the at least one target into lanes according to the first perception information and the second perception information.
[0182] In one possible implementation, the processing module 501 is specifically used to determine information of a target on a first lane of at least one lane based on the first perception information and the second perception information, where the first lane is any lane of the at least one lane, and the information of the target on the first lane includes at least one of the following: the number of targets on the first lane, the speed of the target on the first lane, the average distance between two adjacent targets on the first lane, the minimum distance between two adjacent targets on the first lane, or the traffic density of the first lane; the processing module 501 is also specifically used to determine the congestion level of the first lane based on the information of the target on the first lane.
[0183] In one possible implementation, the processing module 501 is further used to obtain at least one threshold value, and the at least one threshold value includes at least one of the following: a speed threshold value or a spacing threshold value; the speed threshold value is the median of the speeds of multiple targets on the first lane, the minimum value of the speeds of multiple targets on the first lane, or the maximum value of the speeds of multiple targets on the first lane, or the speed threshold value is preset; the spacing threshold value is obtained based on the speed threshold value and the time interval, and the time interval is preset.
[0184] In a possible implementation, the processing module 501 is specifically configured to determine a congestion level of the first lane according to information of the target in the first lane and at least one threshold.
[0185] In a possible implementation, the congestion level of the first lane includes 4 levels, 5 levels, or 6 levels.
[0186] In one possible implementation, the congestion level of the first lane includes 6 levels. If the number of targets on the first lane is greater than or equal to a first number threshold and the speed of the targets on the first lane is less than or equal to a speed threshold, the congestion level of the first lane is level 5; or, if the number of targets on the first lane is greater than or equal to the first number threshold, the congestion level of the first lane is level 4; or, if the average spacing between two adjacent targets on the first lane is less than or equal to a spacing threshold, the congestion level of the first lane is level 3; or, if the minimum spacing between two adjacent targets on the first lane is less than or equal to a spacing threshold, the congestion level of the first lane is level 2; if the minimum spacing between two adjacent targets on the first lane is greater than the spacing threshold and the number of targets on the first lane is greater than or equal to a second number threshold, the congestion level of the first lane is level 1; or, if the number of targets on the first lane is less than the second number threshold, the congestion level of the first lane is level 0.
[0187] In one possible implementation, the congestion level of the first lane includes 6 levels. If the traffic density of the first lane is greater than or equal to the first density threshold, and the speed of the target on the first lane is less than or equal to the speed threshold, the congestion level of the first lane is level 5; or, if the traffic density of the first lane is greater than or equal to the first density threshold, the congestion level of the first lane is level 4; or, if the average spacing between two adjacent targets on the first lane is less than or equal to the spacing threshold, the congestion level of the first lane is level 3; or, if the minimum spacing between two adjacent targets on the first lane is less than or equal to the spacing threshold, the congestion level of the first lane is level 2; if the minimum spacing between two adjacent targets on the first lane is greater than the spacing threshold and the traffic density of the first lane is greater than or equal to the second density threshold, the congestion level of the first lane is level 1; or, if the traffic density of the first lane is less than the second density threshold, the congestion level of the first lane is level 0.
[0188] In a possible implementation, the processing module 501 is configured to determine a sensor fusion strategy for the first lane according to a congestion level of the first lane, where the sensor fusion strategy for the first lane is used to estimate an actual position of an object on the first lane.
[0189] In one possible implementation, if the congestion level of the first lane is greater than or equal to the first level, the sensor fusion strategy of the first lane is the first fusion strategy; or, if the congestion level of the first lane is less than the first level, the sensor fusion strategy of the first lane is the second fusion strategy.
[0190] In one possible implementation, the first perception information also includes the position information of at least one target on at least one lane. The position information in the first perception information includes the first distance of the first target, the first angle of the first target, the horizontal coordinate of the first target and the vertical coordinate of the first target. The first target is any target in the first lane. The first target is different from the target where the target detection device 50 is located. The first distance is the distance between the target detection device 50 and the first target. The first angle is the angle between the forward direction of the target detection device 50 and the first line. The first line is the line between the target detection device 50 and the first target. The position information in the second perception information includes the horizontal coordinate of the second target and the vertical coordinate of the second target. The second target is the target corresponding to the first target among the at least one target corresponding to the second perception information.
[0191] In one possible implementation, the first fusion strategy is to fuse the horizontal coordinate of the first target, the vertical coordinate of the first target, the horizontal coordinate of the second target, and the vertical coordinate of the second target to obtain the actual position of the target on the first lane; the second fusion strategy is to fuse the first angle, the first distance, the horizontal coordinate of the second target, and the vertical coordinate of the second target to obtain the actual position of the target on the first lane.
[0192] In a possible implementation, the processing module 501 is further configured to determine a strategy for sensing a target in the first lane according to a congestion level of the first lane, where the strategy for sensing a target in the first lane is configured to sense whether a target exists in the first lane.
[0193] In one possible implementation, if the congestion level of the first lane is greater than or equal to the second level, the first perception method is used to perceive whether there is a target in the first lane; or, if the congestion level of the first lane is less than the second level, the second perception method is used to perceive whether there is a target in the first lane.
[0194] In one possible implementation, the first perception method is to determine the target obtained by sensor fusion based on the first perception information and the second perception information, the target not subjected to sensor fusion in the first perception information and the target not subjected to sensor fusion in the second perception information as the target on the first lane; the second perception method is to determine the target obtained by sensor fusion based on the first perception information and the second perception information as the target on the first lane.
[0195] In a possible implementation, the first information and the second information are acquired by different types of sensing devices; or, the first information and the second information are acquired by the same type of sensing devices.
[0196] In one possible implementation, the sensing device for acquiring the first information is a camera, a laser radar, a millimeter-wave radar, or a sonar; and the sensing device for acquiring the second information is a millimeter-wave radar, a laser radar, or a sonar.
[0197] In a possible implementation, the transceiver module 502 is configured to send information about the congestion level of the environment.
[0198] When used to implement the functions of the target detection device in the above method embodiment, for other functions that can be implemented by the target detection device 50, reference can be made to the relevant introduction of the embodiment shown in Figure 3, and no further details will be given.
[0199] In a simple embodiment, those skilled in the art can imagine that the target detection device 50 can adopt the form shown in Figure 2. For example, the processor 201 in Figure 2 can call the computer-executable instructions stored in the memory 203 to enable the target detection device 50 to perform the method described in the above method embodiment.
[0200] Exemplarily, the functions / implementation processes of the processing module 501 and the transceiver module 502 in FIG5 can be implemented by the processor 201 in FIG2 calling computer-executable instructions stored in the memory 203. Alternatively, the functions / implementation processes of the processing module 501 in FIG5 can be implemented by the processor 201 in FIG2 calling computer-executable instructions stored in the memory 203, and the functions / implementation processes of the transceiver module 502 in FIG5 can be implemented by the communication interface 204 in FIG2.
[0201] It is understandable that one or more of the above modules or units can be implemented by software, hardware or a combination of the two. When any of the above modules or units is implemented by software, the software exists in the form of computer program instructions and is stored in a memory, and a processor can be used to execute the program instructions and implement the above method flow. The processor can be built into an SoC (system on chip) or an ASIC, or it can be an independent semiconductor chip. In addition to the core used to execute software instructions to perform calculations or processing within the processor, it can further include necessary hardware accelerators, such as field programmable gate arrays (FPGAs), PLDs (programmable logic devices), or logic circuits that implement dedicated logic operations.
[0202] When the above modules or units are implemented in hardware, the hardware can be any one or any combination of a CPU, a microprocessor, a digital signal processing (DSP) chip, a microcontroller unit (MCU), an artificial intelligence processor, an ASIC, a SoC, an FPGA, a PLD, a dedicated digital circuit, a hardware accelerator or a non-integrated discrete device, which can run the necessary software or not rely on the software to execute the above method flow.
[0203] Optionally, an embodiment of the present application further provides a chip system, comprising: at least one processor and an interface, wherein the at least one processor is coupled to a memory via the interface, and when the at least one processor executes a computer program or instruction in the memory, the method in any of the above method embodiments is executed. In one possible implementation, the chip system also includes a memory. Optionally, the chip system can be composed of a chip, or can include a chip and other discrete devices, which is not specifically limited in the embodiment of the present application.
[0204] Optionally, an embodiment of the present application further provides a computer-readable storage medium. All or part of the processes in the above-mentioned method embodiments can be completed by a computer program to instruct the relevant hardware, and the program can be stored in the above-mentioned computer-readable storage medium. When the program is executed, it can include the processes of the above-mentioned method embodiments. The computer-readable storage medium can be an internal storage unit of the target detection device of any of the aforementioned embodiments, such as a hard disk or memory of the target detection device. The above-mentioned computer-readable storage medium can also be an external storage device of the above-mentioned target detection device, such as a plug-in hard disk equipped on the above-mentioned target detection device, a smart memory card (smart media card, SMC), a secure digital (secure digital, SD) card, a flash card (flash card), etc. Further, the above-mentioned computer-readable storage medium can also include both the internal storage unit of the above-mentioned target detection device and an external storage device. The above-mentioned computer-readable storage medium is used to store the above-mentioned computer program and other programs and data required by the above-mentioned target detection device. The above-mentioned computer-readable storage medium can also be used to temporarily store data that has been output or is to be output.
[0205] Optionally, embodiments of the present application further provide a computer program product. All or part of the processes in the above method embodiments may be completed by a computer program instructing the relevant hardware. The program may be stored in the above computer program product, and when executed, the program may include the processes of the above method embodiments.
[0206] Optionally, an embodiment of the present application further provides a computer instruction. All or part of the processes in the above method embodiments can be completed by computer instructions to instruct related hardware (such as a computer, a processor, an access network device, a mobility management network element, or a session management network element). The program can be stored in the above computer-readable storage medium or in the above computer program product.
[0207] Optionally, an embodiment of the present application further provides an intelligent driving vehicle, comprising the target detection device in the above embodiment.
[0208] Through the description of the above implementation methods, technical personnel in the relevant field can clearly understand that for the convenience and simplicity of description, only the division of the above-mentioned functional modules is used as an example. In actual applications, the above-mentioned functions can be assigned to different functional modules as needed, that is, the internal structure of the device can be divided into different functional modules to complete all or part of the functions described above.
[0209] In the several embodiments provided in this application, it should be understood that the disclosed devices and methods can be implemented in other ways. For example, the device embodiments described above are merely schematic. For example, the division of the modules or units is merely a logical function division. In actual implementation, there may be other division methods, such as multiple units or components can be combined or integrated into another device, or some features can be ignored or not executed. Another point is that the mutual coupling or direct coupling or communication connection shown or discussed can be through some interfaces, indirect coupling or communication connection of devices or units, which can be electrical, mechanical or other forms.
[0210] The units described as separate components may or may not be physically separate, and the components shown as units may be one physical unit or multiple physical units, that is, they may be located in one place or distributed in multiple places. Some or all of the units may be selected according to actual needs to achieve the purpose of the solution of this embodiment.
[0211] In addition, the functional units in the various embodiments of the present application may be integrated into a single processing unit, or each unit may exist physically separately, or two or more units may be integrated into a single unit. The aforementioned integrated units may be implemented in the form of hardware or software functional units.
[0212] The above is only a specific embodiment of the present application, but the scope of protection of this application is not limited to this. Any changes or substitutions within the technical scope disclosed in this application should be included in the scope of protection of this application. Therefore, the scope of protection of this application should be based on the scope of protection of the claims.
Claims
1. A target detection method, characterized in that: The method comprises: Acquiring first information, where the first information includes first perception information of an environment; Acquiring second information, where the second information includes second perception information of the environment; A congestion level of the environment is determined according to the first information and the second information, and the congestion level of the environment is used to detect at least one target in the environment.
2. The method according to claim 1, characterized in that The first perception information includes information of at least one lane; The second perception information includes position information of at least one target on the at least one lane, or the second perception information includes position information of at least one target on the at least one lane and speed information of at least one target on the at least one lane.
3. The method according to claim 2, characterized in that The method further comprises: According to the first perception information and the second perception information, the at least one target is divided into lanes.
4. The method according to claim 2 or 3, characterized in that The determining the congestion level of the environment according to the first information and the second information includes: determining, based on the first perception information and the second perception information, information about objects in a first lane of at least one lane, where the first lane is any one of the at least one lane, the information about objects in the first lane comprising at least one of the following: the number of objects in the first lane, the speed of objects in the first lane, an average spacing between two adjacent objects in the first lane, a minimum spacing between two adjacent objects in the first lane, or a traffic density in the first lane; A congestion level of the first lane is determined according to information about the target on the first lane.
5. The method according to claim 4, characterized in that The method further comprises: Acquire at least one threshold value, wherein the at least one threshold value comprises at least one of the following: a speed threshold value or a distance threshold value; The speed threshold is a median of the speeds of the multiple objects on the first lane, a minimum value of the speeds of the multiple objects on the first lane, or a maximum value of the speeds of the multiple objects on the first lane, or the speed threshold is preset; The distance threshold is obtained according to the speed threshold and a time interval, and the time interval is preset.
6. The method according to claim 5, characterized in that The determining the congestion level of the first lane according to the information of the target on the first lane includes: A congestion level of the first lane is determined based on information about the target on the first lane and the at least one threshold value.
7. The method according to claim 6, characterized in that The congestion level of the first lane includes 4 levels, 5 levels or 6 levels.
8. The method according to claim 7, characterized in that If the congestion level of the first lane includes six levels, determining the congestion level of the first lane according to the information of the object on the first lane and the at least one threshold value includes: If the number of objects on the first lane is greater than or equal to a first number threshold, and the speed of the objects on the first lane is less than or equal to the speed threshold, the congestion level of the first lane is level 5; or, If the number of objects on the first lane is greater than or equal to a first number threshold, the congestion level of the first lane is level 4; or, If the average distance between two adjacent objects on the first lane is less than or equal to the distance threshold, the congestion level of the first lane is level 3; or, If the minimum distance between two adjacent objects on the first lane is less than or equal to the distance threshold, the congestion level of the first lane is level 2; If the minimum distance between two adjacent objects on the first lane is greater than a distance threshold, and the number of objects on the first lane is greater than or equal to a second number threshold, the congestion level of the first lane is level 1; or If the number of objects on the first lane is less than a second number threshold, the congestion level of the first lane is level 0.
9. The method according to claim 7, characterized in that If the congestion level of the first lane includes six levels, determining the congestion level of the first lane according to the information of the object on the first lane and the at least one threshold value includes: If the traffic density of the first lane is greater than or equal to a first density threshold, and the speed of the object in the first lane is less than or equal to the speed threshold, the congestion level of the first lane is level 5; or, If the traffic density of the first lane is greater than or equal to the first density threshold, the congestion level of the first lane is level 4; or, If the average distance between two adjacent objects on the first lane is less than or equal to the distance threshold, the congestion level of the first lane is level 3; or, If the minimum distance between two adjacent objects on the first lane is less than or equal to the distance threshold, the congestion level of the first lane is level 2; If the minimum distance between two adjacent objects on the first lane is greater than the distance threshold, and the traffic density of the first lane is greater than or equal to the second density threshold, the congestion level of the first lane is level 1; or If the traffic density of the first lane is less than the second density threshold, the congestion level of the first lane is level 0.
10. The method according to any one of claims 4 to 9, characterized in that The method further comprises: A sensor fusion strategy for the first lane is determined according to the congestion level of the first lane, where the sensor fusion strategy for the first lane is used to estimate an actual position of an object on the first lane.
11. The method according to claim 10, characterized in that The determining, according to the congestion level of the first lane, a sensor fusion strategy for the first lane includes: If the congestion level of the first lane is greater than or equal to the first level, the sensor fusion strategy of the first lane is the first fusion strategy; or, If the congestion level of the first lane is less than the first level, the sensor fusion strategy of the first lane is the second fusion strategy.
12. The method according to claim 11, characterized in that The method is applied to a target detection device; The first perception information further includes position information of at least one target on the at least one lane, the position information in the first perception information including a first distance to the first target, a first angle of the first target, a horizontal coordinate of the first target, and a vertical coordinate of the first target, the first target being any target in the first lane, the first target being different from the target where the target detection device is located, the first distance being the distance between the target detection device and the first target, the first angle being the angle between the forward direction of the target detection device and a first connecting line, the first connecting line being the connecting line between the target detection device and the first target; The location information in the second perception information includes the horizontal coordinate and the vertical coordinate of the second target, and the second target is the target corresponding to the first target among the at least one target corresponding to the second perception information.
13. The method according to claim 12, characterized in that The first fusion strategy is to fuse the horizontal coordinate of the first target, the vertical coordinate of the first target, the horizontal coordinate of the second target, and the vertical coordinate of the second target to obtain the actual position of the target on the first lane; The second fusion strategy is to fuse the first angle, the first distance, the horizontal coordinate of the second target, and the vertical coordinate of the second target to obtain the actual position of the target on the first lane.
14. The method according to any one of claims 4 to 13, characterized in that The method further comprises: A strategy for sensing an object in the first lane is determined according to a congestion level of the first lane, where the strategy for sensing an object in the first lane is used to sense whether an object exists in the first lane.
15. The method according to claim 14, characterized in that The determining, based on the congestion level of the first lane, a strategy for sensing a target in the first lane includes: If the congestion level of the first lane is greater than or equal to the second level, using a first sensing method to sense whether there is an object in the first lane; or If the congestion level of the first lane is lower than the second level, a second sensing method is used to sense whether there is a target in the first lane.
16. The method according to claim 15, characterized in that The first sensing method is to determine a target obtained by performing sensor fusion based on the first sensing information and the second sensing information, and a target in the first sensing information that has not been sensor fused and a target in the second sensing information that has not been sensor fused as a target on the first lane; The second perception method is to determine a target obtained by sensor fusion based on the first perception information and the second perception information as a target on the first lane.
17. The method according to any one of claims 1 to 16, characterized in that The first information and the second information are acquired by different types of sensing devices; or, The first information and the second information are acquired by the same type of sensing device.
18. The method according to claim 17, characterized in that The sensing device for acquiring the first information is a camera, a laser radar, a millimeter-wave radar, or a sonar; The sensing device for acquiring the second information is a millimeter wave radar, a laser radar or a sonar.
19. The method according to any one of claims 1 to 18, characterized in that The method further comprises: Information on the congestion level of the environment is transmitted.
20. A target detection device, characterized in that: The target detection device includes: a processing module; The processing module is configured to obtain first information, where the first information includes first perception information of the environment; The processing module is further configured to obtain second information, where the second information includes second perception information of the environment; The processing module is further configured to determine a congestion level of the environment based on the first information and the second information, where the congestion level of the environment is used to detect at least one target in the environment.
21. The target detection device according to claim 20, characterized in that: The first perception information includes information of at least one lane; The second perception information includes position information of at least one target on the at least one lane, or the second perception information includes position information of at least one target on the at least one lane and speed information of at least one target on the at least one lane.
22. The target detection device according to claim 21, wherein: The processing module is further used to divide the at least one target into lanes based on the first perception information and the second perception information.
23. The target detection device according to claim 21 or 22, characterized in that: The processing module is specifically configured to determine, based on the first perception information and the second perception information, information about a target on a first lane of at least one lane, where the first lane is any one of the at least one lane, and the information about the target on the first lane includes at least one of the following: the number of targets on the first lane, the speed of the targets on the first lane, the average spacing between two adjacent targets on the first lane, the minimum spacing between two adjacent targets on the first lane, or the traffic density of the first lane; The processing module is further specifically configured to determine a congestion level of the first lane based on information about the target on the first lane.
24. The target detection device according to claim 23, wherein: The processing module is further configured to obtain at least one threshold value, wherein the at least one threshold value includes at least one of the following: a speed threshold value or a spacing threshold value; The speed threshold is a median of the speeds of the multiple objects on the first lane, a minimum value of the speeds of the multiple objects on the first lane, or a maximum value of the speeds of the multiple objects on the first lane, or the speed threshold is preset; The distance threshold is obtained according to the speed threshold and a time interval, and the time interval is preset.
25. The target detection device according to claim 24, wherein: The processing module is specifically configured to determine a congestion level of the first lane based on information of the target on the first lane and the at least one threshold value.
26. The target detection device according to claim 25, characterized in that The congestion level of the first lane includes 4 levels, 5 levels or 6 levels.
27. The target detection device according to claim 26, wherein: The congestion level of the first lane includes 6 levels: If the number of objects on the first lane is greater than or equal to a first number threshold, and the speed of the objects on the first lane is less than or equal to the speed threshold, the congestion level of the first lane is level 5; or, If the number of objects on the first lane is greater than or equal to a first number threshold, the congestion level of the first lane is level 4; or, If the average distance between two adjacent objects on the first lane is less than or equal to the distance threshold, the congestion level of the first lane is level 3; or, If the minimum distance between two adjacent objects on the first lane is less than or equal to the distance threshold, the congestion level of the first lane is level 2; If the minimum distance between two adjacent objects on the first lane is greater than a distance threshold, and the number of objects on the first lane is greater than or equal to a second number threshold, the congestion level of the first lane is level 1; or If the number of objects on the first lane is less than a second number threshold, the congestion level of the first lane is level 0.
28. The target detection device according to claim 26, wherein: The congestion level of the first lane includes 6 levels: If the traffic density of the first lane is greater than or equal to a first density threshold, and the speed of the object in the first lane is less than or equal to the speed threshold, the congestion level of the first lane is level 5; or, If the traffic density of the first lane is greater than or equal to the first density threshold, the congestion level of the first lane is level 4; or, If the average distance between two adjacent objects on the first lane is less than or equal to the distance threshold, the congestion level of the first lane is level 3; or, If the minimum distance between two adjacent objects on the first lane is less than or equal to the distance threshold, the congestion level of the first lane is level 2; If the minimum distance between two adjacent objects on the first lane is greater than the distance threshold, and the traffic density of the first lane is greater than or equal to the second density threshold, the congestion level of the first lane is level 1; or If the traffic density of the first lane is less than the second density threshold, the congestion level of the first lane is level 0.
29. The target detection device according to any one of claims 23 to 28, characterized in that: The processing module is used to determine a sensor fusion strategy for the first lane according to the congestion level of the first lane, where the sensor fusion strategy for the first lane is used to estimate the actual position of the target on the first lane.
30. The target detection device according to claim 29, wherein: If the congestion level of the first lane is greater than or equal to the first level, the sensor fusion strategy of the first lane is the first fusion strategy; or, If the congestion level of the first lane is less than the first level, the sensor fusion strategy of the first lane is the second fusion strategy.
31. The target detection device according to claim 30, characterized in that The first perception information further includes position information of at least one target on the at least one lane, the position information in the first perception information including a first distance to the first target, a first angle of the first target, a horizontal coordinate of the first target, and a vertical coordinate of the first target, the first target being any target in the first lane, the first target being different from the target where the target detection device is located, the first distance being the distance between the target detection device and the first target, the first angle being the angle between the forward direction of the target detection device and a first connecting line, the first connecting line being the connecting line between the target detection device and the first target; The location information in the second perception information includes the horizontal coordinate and the vertical coordinate of the second target, and the second target is the target corresponding to the first target among the at least one target corresponding to the second perception information.
32. The target detection device according to claim 31, wherein: The first fusion strategy is to fuse the horizontal coordinate of the first target, the vertical coordinate of the first target, the horizontal coordinate of the second target, and the vertical coordinate of the second target to obtain the actual position of the target on the first lane; The second fusion strategy is to fuse the first angle, the first distance, the horizontal coordinate of the second target, and the vertical coordinate of the second target to obtain the actual position of the target on the first lane.
33. The target detection device according to any one of claims 23 to 32, characterized in that: The processing module is further configured to determine a strategy for sensing targets in the first lane according to the congestion level of the first lane, wherein the strategy for sensing targets in the first lane is configured to sense whether a target exists in the first lane.
34. The target detection device according to claim 33, wherein: If the congestion level of the first lane is greater than or equal to the second level, using a first sensing method to sense whether there is an object in the first lane; or If the congestion level of the first lane is lower than the second level, a second sensing method is used to sense whether there is a target in the first lane.
35. The target detection device according to claim 34, wherein: The first sensing method is to determine a target obtained by performing sensor fusion based on the first sensing information and the second sensing information, and a target in the first sensing information that has not been sensor fused and a target in the second sensing information that has not been sensor fused as a target on the first lane; The second perception method is to determine a target obtained by sensor fusion based on the first perception information and the second perception information as a target on the first lane.
36. The target detection device according to any one of claims 20 to 35, characterized in that: The first information and the second information are acquired by different types of sensing devices; or, The first information and the second information are acquired by the same type of sensing device.
37. The target detection device according to claim 36, wherein: The sensing device for acquiring the first information is a camera, a laser radar, a millimeter-wave radar, or a sonar; The sensing device for acquiring the second information is a millimeter wave radar, a laser radar or a sonar.
38. The target detection device according to any one of claims 20 to 37, characterized in that: The target detection device further includes: a transceiver module; The transceiver module is used to send information about the congestion level of the environment.
39. An intelligent driving vehicle, characterized in that: include: The target detection device according to any one of claims 20 to 38.
40. A target detection device, characterized in that include: A processor is coupled to a memory, wherein the memory is used to store programs or instructions, and when the programs or instructions are executed by the processor, the device performs the method according to any one of claims 1 to 19.
41. A chip, characterized in that: include: A processor is coupled to a memory, wherein the memory is used to store programs or instructions, and when the programs or instructions are executed by the processor, the chip executes the method according to any one of claims 1 to 19.
42. A computer-readable storage medium having a computer program or instruction stored thereon, characterized in that: When the computer program or instructions are executed, the computer is caused to perform the method according to any one of claims 1 to 19.
Citation Information
Cited By
Traffic jam judgment method and device based on traffic flow density
CN120564426A
Traffic congestion judgment method and device based on traffic density
CN120564426B
