Object recognition method, millimeter wave radar and vehicle
By acquiring and analyzing the detection information of millimeter wave radar, especially the distance-reflection intensity slope and the evaluation value of ground metal reflectors, and using a state machine to identify it, the accuracy problem of vehicle-mounted radars in distinguishing ground metal reflectors from stationary vehicles is solved, and the accuracy problem of on-board radars is achieved. Higher recognition accuracy and system reliability.
Patent Information
- Application Number
- CN201980030581.4
- Authority / Receiving Office
- CN · China
- Patent Type
- Patents(China)
- Current Assignee / Owner
- Filing Date
- 2019-06-28
- Publication Date
- 2024-12-06
- Estimated Expiration
- 2039-06-28
AI Technical Summary
Existing on-board mmWave radars are difficult to accurately distinguish ground metal reflectors from stationary vehicles, resulting in the problem of false triggering of automatic emergency braking systems, and the solution to increase hardware cost or complexity to improve accuracy is limited.
By obtaining the detection information of the object to be identified, it determines its characteristic information, such as the distance-reflection intensity slope of the radar transmitting wave and the evaluation value of the metal reflector on the ground, use these characteristic information to identify, and use a state machine to determine whether the object to be identified is a static vehicle or a static vehicle or a meter Metal reflectors on the ground, avoiding additional hardware.
Improve the accuracy of identifying objects in front of the vehicle without increasing hardware costs, reduce the false triggering of the automatic emergency braking system, and enhance the scientificity and rigor of the recognition.
Smart Images

Figure CN112119329B_ABST
Abstract
Description
Technical Field
[0001] The present invention relates to the field of assisted driving technology, and in particular to an object recognition method, a millimeter wave radar and a vehicle. Background Art
[0002] In recent years, the Advanced Driver Assistant System (ADAS) technology and Autonomous Driving (AD) technology have developed rapidly. Millimeter-wave radar has been widely used in these fields due to its advantages of all-day, all-weather, long-range, and high speed measurement accuracy. However, distinguishing between ground metal reflectors (such as manhole covers, metal cracks on viaducts, etc.) and stationary vehicles has always been a problem and difficulty for vehicle-mounted millimeter-wave radars. At present, the millimeter-wave radars produced by most vehicle-mounted radar manufacturers have the disadvantage of being unable to accurately distinguish between ground metal reflectors and stationary vehicles. Ground metal reflectors, represented by manhole covers and metal cracks on viaducts, have strong reflections on radar transmission waves and are stationary relative to the ground, so they are easily detected and mistakenly identified as stationary vehicles, resulting in problems such as the erroneous activation of the Autonomous Emergency Braking (AEB) system.
[0003] At present, in order to accurately identify ground metal reflectors and stationary vehicles, the following solutions can usually be adopted: Solution 1: Add a pitch receiving channel so that the radar has the ability to measure angles in pitch. However, this will increase the complexity of antenna design and algorithm complexity, and require increasing the radar size and selecting a chip with stronger computing power, which will significantly increase the hardware cost of the radar and reduce the convenience of radar installation. Moreover, since the pitch angle between the ground metal reflector and the vehicle-mounted radar is very small, even if the above solution is used, it will be more accurate at a very close distance, and the use scenario is relatively limited; Solution 2: Distinguish ground metal reflectors and stationary vehicles by adding a camera and radar fusion solution, but this will greatly increase the cost, and the reliability of the camera will also be greatly reduced in bad weather and poor light conditions, so it has certain limitations. It can be seen that how to improve the accuracy of identifying objects in front of the vehicle without increasing the hardware cost to reduce the false triggering of the automatic emergency braking system has become an urgent problem to be solved. Summary of the invention
[0004] The embodiments of the present invention disclose an object recognition method, a millimeter wave radar and a vehicle, which are used to improve the accuracy of recognizing objects in front of a vehicle without increasing hardware costs, so as to reduce false triggering of an automatic emergency braking system.
[0005] A first aspect of an embodiment of the present invention discloses an object recognition method, which is applied to a millimeter wave radar. The method includes:
[0006] Obtain detection information of the object to be identified;
[0007] Determine characteristic information of the object to be identified according to the detection information, wherein the characteristic information includes at least one of the following: a distance-reflection intensity slope of a radar transmission wave, an evaluation value of a ground metal reflector, and a reflection intensity attenuation value of a radar transmission wave;
[0008] The object to be identified is identified using the feature information.
[0009] A second aspect of an embodiment of the present invention discloses a millimeter wave radar, the millimeter wave radar comprising: a processor and a memory, wherein:
[0010] The memory is used to store a computer program, wherein the computer program includes program instructions;
[0011] When the processor calls the program instructions, it is used to execute:
[0012] Obtain detection information of the object to be identified;
[0013] Determine characteristic information of the object to be identified according to the detection information, wherein the characteristic information includes at least one of the following: a distance-reflection intensity slope of a radar transmission wave, an evaluation value of a ground metal reflector, and a reflection intensity attenuation value of a radar transmission wave;
[0014] The object to be identified is identified using the feature information.
[0015] A third aspect of an embodiment of the present invention discloses an object recognition device, which is applied to a millimeter wave radar. The device includes:
[0016] An acquisition module, used to acquire detection information of an object to be identified;
[0017] A determination module, configured to determine characteristic information of the object to be identified according to the detection information, wherein the characteristic information includes at least one of the following: a distance-reflection intensity slope of a radar transmission wave, an evaluation value of a ground metal reflector, and a reflection intensity attenuation value of a radar transmission wave;
[0018] The recognition module is used to recognize the object to be recognized by using the feature information.
[0019] A fourth aspect of an embodiment of the present invention discloses a computer-readable storage medium, wherein the computer-readable storage medium stores a computer program, and when the computer program is executed by a processor, the object recognition method described in the first aspect is implemented.
[0020] The embodiment of the present invention can obtain detection information of an object to be identified, and determine feature information of the object to be identified based on the detection information. The feature information of the object to be identified may include at least one of the following: a distance-reflection intensity slope of a radar transmission wave, an evaluation value of a ground metal reflector, and a reflection intensity attenuation value of a radar transmission wave. The object to be identified can be identified using the feature information, thereby improving the accuracy of identifying objects in front of the vehicle without adding additional hardware, thereby reducing false triggering of the automatic emergency braking system. BRIEF DESCRIPTION OF THE DRAWINGS
[0021] In order to more clearly illustrate the technical solutions in the embodiments of the present invention, the drawings required for use in the embodiments will be briefly introduced below. Obviously, the drawings described below are only some embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without creative work.
[0022] Figure 1 is a flow chart of an object recognition method disclosed in an embodiment of the present invention;
[0023] Figure 2a It is a schematic diagram of a reflection path of a radar transmission wave disclosed in an embodiment of the present invention;
[0024] Figure 2b is a schematic diagram of a distance-reflection intensity characteristic curve disclosed in an embodiment of the present invention;
[0025] Figure 2c It is a schematic diagram of another reflection path of a radar transmission wave disclosed in an embodiment of the present invention;
[0026] Figure 2d is a schematic diagram of another distance-reflection intensity characteristic curve disclosed in an embodiment of the present invention;
[0027] Figure 2e It is a schematic diagram of a process of using a state machine to perform object recognition disclosed in an embodiment of the present invention;
[0028] Figure 3 is a structural schematic diagram of an object recognition device disclosed in an embodiment of the present invention;
[0029] Figure 4 It is a schematic diagram of the structure of a millimeter wave radar disclosed in an embodiment of the present invention. DETAILED DESCRIPTION
[0030] The following will be combined with the drawings in the embodiments of the present invention to clearly and completely describe the technical solutions in the embodiments of the present invention. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present invention.
[0031] The object recognition method provided by the embodiment of the present invention can be applied to scenarios such as advanced driver assistance and automatic driving to improve the accuracy of identifying objects in front of the vehicle to reduce false triggering of the automatic emergency braking system without adding additional hardware.
[0032] The millimeter wave radar described in the embodiment of the present invention may specifically be a vehicle-mounted control terminal.
[0033] See also Figure 1 , is a flow chart of an object recognition method provided by an embodiment of the present invention. The object recognition method described in this embodiment may include the following steps:
[0034] 101. Obtain detection information of the object to be identified.
[0035] The detection information includes at least one of the following: the reflection intensity of the radar transmission wave of the object to be identified, and the distance to the object to be identified.
[0036] Specifically, the millimeter wave radar can periodically detect the object to be identified, for example, once every 500 ms, that is, it transmits a millimeter wave to the object to be identified once every 500 ms for detection, and receives the reflected wave of the object to be identified. According to the reflection of the radar transmitted wave by the object to be identified, the reflection intensity of the radar transmitted wave by the object to be identified and / or the distance to the object to be identified and other detection information can be determined.
[0037] 102. Determine characteristic information of the object to be identified based on the detection information, wherein the characteristic information includes at least one of the following: a distance-reflection intensity slope of a radar transmission wave, an evaluation value of a ground metal reflector, and a reflection intensity attenuation value of a radar transmission wave.
[0038] Specifically, the millimeter wave radar can obtain the characteristic information of the object to be identified by using the detection information of the object to be identified. The characteristic information reflects the inherent characteristics of the object to be identified when reflecting the radar transmission wave. The characteristic information can specifically include: at least one of the distance-reflection intensity slope of the radar transmission wave, the evaluation value of the ground metal reflector and the reflection intensity attenuation value of the radar transmission wave.
[0039] For a stationary vehicle, Figure 2aThe figure shows the reflection path of radar transmission waves from a stationary vehicle. It can be seen that for a stationary vehicle in front of the radar, since the vehicle is at a certain height from the ground, its radar reflection wave has two paths: one is returned along the direction of the radar transmission wave, and the other is returned to the radar after being refracted by the ground. This phenomenon is called the ground multipath effect.
[0040] Accordingly, if Figure 2b The figure shows a schematic diagram of the distance-reflection intensity characteristic curve of a stationary vehicle. It can be seen that due to the ground multipath effect of the vehicle, the energy of the two reflection paths is vector superposition. Therefore, as the distance varies, there is an obvious reflection intensity fading area in the distance-reflection intensity characteristic curve of a stationary vehicle.
[0041] For ground metal reflectors, Figure 2c The figure shows a schematic diagram of the reflection path of the radar transmission wave by the ground metal reflector. It can be seen that since there is almost no height difference between the ground metal reflector and the ground, there is only one reflection path, that is, there is only one path returning along the direction of the transmission wave, and there is no reflection path refracted by the ground.
[0042] Accordingly, if Figure 2d As shown, it is a schematic diagram of the distance-reflection intensity characteristic curve of the ground metal reflector. It can be seen that since the ground metal reflector does not have the ground multipath effect, the distance-reflection intensity characteristic curve of the ground metal reflector is an obvious straight line, and there is no reflection intensity fading area.
[0043] It can be seen that due to the existence of ground multipath effect, there is a significant difference between the reflection characteristics of the radar transmission wave when the object to be identified is a stationary vehicle and the reflection characteristics of the radar transmission wave when the object to be identified is a ground metal reflector. Therefore, characteristic information such as the distance-reflection intensity slope of the radar transmission wave, the evaluation value of the ground metal reflector, and the reflection intensity attenuation value of the radar transmission wave can be used to accurately identify whether the object to be identified is a stationary vehicle or a ground metal reflector.
[0044] 103. Use the feature information to identify the object to be identified.
[0045] Specifically, the millimeter wave radar uses characteristic information such as the distance-reflection intensity slope of the object to be identified to the radar transmission wave, the evaluation value of the ground metal reflector, and the reflection intensity attenuation value of the radar transmission wave to identify whether the object to be identified is a stationary vehicle or a ground metal reflector.
[0046] In an embodiment of the present invention, a millimeter wave radar can obtain detection information of an object to be identified, and determine characteristic information of the object to be identified based on the detection information. The characteristic information of the object to be identified may include at least one of the following: a distance-reflection intensity slope of a radar transmission wave, an evaluation value of a ground metal reflector, and a reflection intensity attenuation value of a radar transmission wave. The object to be identified can be identified using the characteristic information, and the different characteristics of the ground multipath effect of a ground metal reflector and a stationary vehicle can be used to distinguish between ground metal reflectors and stationary vehicles, thereby improving the accuracy of identifying objects in front of the vehicle without adding additional hardware, thereby reducing false triggering of the automatic emergency braking system.
[0047] Optionally, the specific way in which the millimeter-wave radar uses the feature information to identify the object to be identified can be: the millimeter-wave radar introduces a state machine, and uses the feature information and the state machine to determine whether the object to be identified is a stationary vehicle. The state machine includes four states: stationary vehicle pending, stationary vehicle confirmed, ground metal reflector pending, and ground metal reflector confirmed. That is to say, based on the feature information, determine which state of the state machine the object to be identified satisfies, and then make a determination whether the object to be identified is a stationary vehicle. The four states include "pending" and "confirmed". Assuming that the object to be identified is a stationary vehicle, it is at least necessary to go through the determination process of stationary vehicle pending -> stationary vehicle confirmed. It can be seen that the determination process is more scientific and rigorous, which further improves the accuracy of identifying objects in front of the vehicle.
[0048] Optionally, the specific method for the millimeter wave radar to determine the distance-reflection intensity slope of the object to be identified to the radar transmitted wave and the evaluation value of the ground metal reflector can be: the millimeter wave radar calculates the distance-reflection intensity slope of the object to be identified to the radar transmitted wave based on the reflection intensity of the object to be identified to the radar transmitted wave and the distance to the object to be identified, and then determines the ground metal reflector evaluation value of the object to be identified based on the distance-reflection intensity slope of the object to be identified to the radar transmitted wave and the first slope threshold.
[0049] Specifically, the slope of the distance-reflection intensity of the radar transmission wave of the object to be identified is recorded as k d-p , the distance between the i-th detection and the object to be identified is recorded as D i The reflection intensity of the radar transmission wave of the object to be identified obtained by the i-th detection is recorded as P i , the number of detections up to the current time is recorded as n, that is, this detection is the nth detection, then k d-p The calculation formula is as follows:
[0050]
[0051] Furthermore, the ground metal reflector evaluation value obtained after this detection is recorded as Manhole nThe ground metal reflector evaluation value obtained after the last detection is recorded as Manhole n-1 , the increase in the evaluation value of ground metal reflectors is recorded as Manhole add , the maximum evaluation value of the ground metal reflector is recorded as Manhole max , the first slope threshold is denoted as k add_cri , the reduction in the evaluation value of the ground metal reflector is recorded as Manhole minus , then the specific method for the millimeter wave radar to determine the ground metal reflector evaluation value of the object to be identified according to the distance-reflection intensity slope of the object to be identified to the radar transmission wave and the first slope threshold can be:
[0052] If the distance-reflection intensity slope k of the radar transmission wave of the object to be identified d-p Less than the first slope threshold k add_cri , the millimeter-wave radar can use the historical evaluation value of the ground metal reflector (that is, the ground metal reflector evaluation value Manhole obtained after the last detection) n-1 ), ground metal reflector evaluation value increase Manhole add and the maximum evaluation value of ground metal reflectors Manhole max Calculate the Manhole value of the ground metal reflector of the object to be identified n Among them, the ground metal reflector evaluation value of the object to be identified is Manhole n Specifically, it can be the historical evaluation value of the ground metal reflector Manhole n-1 Manhole add The sum of the ground metal reflector and the maximum evaluation value Manhole max The larger value in .
[0053] If the distance-reflection intensity slope k of the radar transmission wave of the object to be identified d-p Greater than or equal to the first slope threshold k add_cri , then the millimeter wave radar can use the historical evaluation value of ground metal reflectors Manhole n-1 And the reduction of the evaluation value of ground metal reflectors Manhole minus Calculate the Manhole value of the ground metal reflector of the object to be identified n Among them, the ground metal reflector evaluation value of the object to be identified is Manhole n Specifically, it can be the historical evaluation value of the ground metal reflector Manhole n-1 Manhole minus and 0, whichever is smaller.
[0054] In addition, combined Figure 2b and Figure 2d It can be seen that the distance-reflection intensity slope of the radar transmission wave to the ground metal reflector is relatively gentle and stable, while the distance-reflection intensity slope of the radar transmission wave to the stationary vehicle is relatively steep and varies greatly.
[0055] Among them, the ground metal reflector evaluation value Manhole of the object to be identified n The specific calculation formula can be as follows:
[0056] Manhole n =max(Manhole n-1 +|Manhole add |,Manhole max )if k d-p <k add_cri
[0057] Manhole n =min(Manhole n-1 -|Manhole minus |,0)otherwise
[0058] Understandably, according to Manhole n The specific calculation formula of is: if (if) the distance-reflection intensity slope k of the radar transmission wave to be identified is d-p Smaller, such as k d-p Less than the first slope threshold k add_cri , then according to the ground metal reflector evaluation value increase amount Manhole add Added the historical evaluation value of ground metal reflectors Manhole n-1 , and compare the added result with the maximum evaluation value of the ground metal reflector Manhole max Compare and take the larger value, that is, increase the score of the object to be identified as a ground metal reflector; otherwise, if the distance-reflection intensity slope k of the radar transmission wave to the object to be identified is d-p Larger, such as k d-p Greater than or equal to the first slope threshold k add_cri , then according to the ground metal reflector evaluation value reduction amount Manhole minus Reduce the historical evaluation value of ground metal reflectors Manhole n-1 , compare the reduced result with 0, and take the smaller value, that is, the score of the object to be identified as a metal reflector on the ground, the distance-reflection intensity slope k d-p When the value is larger, the ground metal reflector evaluation value is reduced to 0 or a value less than 0.
[0059] The initial value of the ground metal reflector evaluation value can be set to 0. If the ground metal reflector evaluation value of an object is 0 or less than 0, it can be regarded that the object is not a ground metal reflector. add_cri The specific value of depends on the characteristics of the radar used. add Can be set to 3 points, Manhole max Can be set to 7 points, Manhole minus It can be set to 1 point. These values can be set according to actual needs and / or radar characteristics.
[0060] Optionally, the specific method for the millimeter wave radar to determine the reflection intensity attenuation value of the radar transmission wave of the object to be identified can be: the millimeter wave radar obtains the maximum reflection intensity of the radar transmission wave of the object to be identified, and then calculates the reflection intensity attenuation value of the radar transmission wave of the object to be identified based on the reflection intensity of the radar transmission wave of the object to be identified and the maximum reflection intensity.
[0061] Specifically, the maximum reflection intensity refers to the maximum value among the multiple reflection intensities that have been detected. The maximum reflection intensity obtained after this detection is recorded as Pmax. n , the maximum reflection intensity obtained after the last detection is recorded as Pmax n-1 The reflection intensity obtained in this test is recorded as P n , then the maximum reflection intensity Pmax n The specific calculation formula can be as follows:
[0062] Pmax n =P n if Pmax n-1 <P n
[0063] Pmax n =Pmax n-1 otherwise
[0064] It can be seen that if (if) the maximum reflection intensity obtained after the last detection is recorded as Pmax n-1 Less than the reflection intensity P obtained in this test n , then P n As Pmax n ; otherwise, Pmax n-1 Greater than or equal to P n , then Pmax n-1 As Pmax n , so that the maximum reflection intensity Pmax obtained after this detection can be calculated n .
[0065] Furthermore, the maximum reflection intensity Pmax obtained after this detection is n The reflection intensity P obtained in this test n The reflection intensity attenuation value of the radar transmission wave of the object to be identified can be obtained by subtracting it. The reflection intensity attenuation value obtained after this detection is recorded as Pgap n , then the reflection intensity attenuation value Pgap n The specific calculation formula can be as follows:
[0066] Pgap n =Pmax n -P n
[0067] Optionally, the millimeter wave radar uses the characteristic information and the state machine to determine whether the object to be identified is a stationary vehicle. The specific method may be: the millimeter wave radar sets the initial state of the state machine to the stationary vehicle pending state. If the reflection intensity attenuation value Pgap n Greater than the reflection intensity attenuation threshold (denoted as Pgap cri ), or, the distance-reflection intensity slope k d-p Greater than the second slope threshold (denoted as k car_cri ), the millimeter-wave radar switches the state of the state machine from stationary vehicle pending to stationary vehicle determined, and determines that the object to be identified is a stationary vehicle.
[0068] Optionally, the millimeter wave radar sets the initial state of the state machine to a stationary vehicle pending. If the ground metal reflector evaluation value is Manhole n Greater than the first evaluation threshold (denoted as Manhole on ), the millimeter-wave radar switches the state of the state machine from the stationary vehicle to be determined to the ground metal reflector to be determined. If the distance (denoted as D n ) is less than the distance threshold (denoted as D cri ), the millimeter-wave radar switches the state of the state machine from ground metal reflector pending to ground metal reflector determined, and determines that the object to be identified is a ground metal reflector.
[0069] Optionally, the millimeter wave radar sets the initial state of the state machine to a stationary vehicle pending. If the ground metal reflector evaluation value is Manhole n Greater than the first evaluation threshold Manhole on , the millimeter-wave radar switches the state of the state machine from the stationary vehicle pending to the ground metal reflector pending, and the millimeter-wave radar updates the ground metal reflector evaluation value. If the updated ground metal reflector evaluation value is less than the second evaluation threshold (recorded as Manhole off), the state of the state machine is switched from ground metal reflector pending to stationary vehicle pending, and then the reflection intensity decay value and distance-reflection intensity slope are updated. If the updated reflection intensity decay value is greater than the reflection intensity decay threshold Pgap cri , or, the updated distance-reflection intensity slope is greater than the second slope threshold k car_cri , the state of the state machine is switched from stationary vehicle pending to stationary vehicle determined, and the object to be identified is determined to be a stationary vehicle.
[0070] Optional, such as Figure 2e The figure is a flow chart of object recognition using a state machine, and the corresponding conversion conditions are shown in the following table.
[0071]
[0072] Among them, the reflection intensity attenuation threshold Pgap cri Can be set to 20dB, distance threshold D cri It can be set to 10m. The conversion condition d means that if the distance between the radar and the object to be identified is very close, only 10m, but it is still not certain that the object to be identified is a stationary vehicle, the object to be identified will be determined as a ground metal reflector.
[0073] Of course, Pgap cri and D cri These values can be set according to actual needs and / or radar characteristics.
[0074] It can be seen that through the four states of the state machine and the set conversion conditions, the different characteristics of the ground multipath effect of ground metal reflectors and stationary vehicles can be fully utilized to distinguish ground metal reflectors from stationary vehicles, thereby improving the accuracy of identifying objects in front of the vehicle without adding additional hardware, thereby reducing the false triggering of the automatic emergency braking system.
[0075] See also Figure 3 , is a schematic diagram of the structure of an object recognition device provided by an embodiment of the present invention. The object recognition device comprises:
[0076] An acquisition module 301 is used to acquire detection information of an object to be identified;
[0077] A determination module 302 is used to determine characteristic information of the object to be identified according to the detection information, wherein the characteristic information includes at least one of the following: a distance-reflection intensity slope of a radar transmission wave, an evaluation value of a ground metal reflector, and a reflection intensity attenuation value of a radar transmission wave;
[0078] The identification module 303 is used to identify the object to be identified by using the feature information.
[0079] Optionally, the detection information includes at least one of the following: the reflection intensity of the object to be identified to the radar transmission wave, and the distance from the object to be identified.
[0080] Optionally, the identification module 303 is specifically used to:
[0081] The feature information and a state machine are used to determine whether the object to be identified is a stationary vehicle. The state machine includes four states: stationary vehicle pending, stationary vehicle confirmed, ground metal reflector pending, and ground metal reflector confirmed.
[0082] Optionally, the determining module 302 is specifically configured to:
[0083] Calculate the distance-reflection intensity slope of the object to be identified to the radar transmission wave according to the reflection intensity and the distance;
[0084] The ground metal reflector evaluation value of the object to be identified is determined according to the distance-reflection intensity slope of the object to be identified to the radar transmission wave and a first slope threshold.
[0085] Optionally, the determining module 302 is specifically configured to:
[0086] If the distance-reflection intensity slope of the object to be identified to the radar transmission wave is less than the first slope threshold, the ground metal reflector evaluation value of the object to be identified is calculated using the historical evaluation value of the ground metal reflector, the increase in the ground metal reflector evaluation value and the maximum evaluation value of the ground metal reflector.
[0087] Optionally, the ground metal reflector evaluation value of the object to be identified is the larger value of the sum of the ground metal reflector historical evaluation value and the ground metal reflector evaluation value increase and the ground metal reflector maximum evaluation value.
[0088] Optionally, the determining module 302 is specifically configured to:
[0089] If the distance-reflection intensity slope of the object to be identified to the radar transmission wave is greater than or equal to the first slope threshold, the ground metal reflector evaluation value of the object to be identified is calculated using the ground metal reflector historical evaluation value and the ground metal reflector evaluation value reduction.
[0090] Optionally, the ground metal reflector evaluation value of the object to be identified is the smaller value of the difference between the historical evaluation value of the ground metal reflector and the reduction amount of the ground metal reflector evaluation value and 0.
[0091] Optionally, the determining module 302 is specifically configured to:
[0092] Obtaining the maximum reflection intensity of the radar transmission wave of the object to be identified;
[0093] The reflection intensity fading value of the object to be identified to the radar transmission wave is calculated according to the reflection intensity of the object to be identified to the radar transmission wave and the maximum reflection intensity.
[0094] Optionally, the identification module 303 is specifically used to:
[0095] Set the initial state of the state machine to a stationary vehicle pending;
[0096] If the reflection intensity attenuation value is greater than the reflection intensity attenuation threshold, or the distance-reflection intensity slope is greater than the second slope threshold, the state of the state machine is switched from stationary vehicle pending to stationary vehicle determined, and the object to be identified is determined to be a stationary vehicle.
[0097] Optionally, the identification module 303 is further configured to:
[0098] If the ground metal reflector evaluation value is greater than a first evaluation threshold, switching the state of the state machine from stationary vehicle pending to ground metal reflector pending;
[0099] If the distance is less than the distance threshold, the state of the state machine is switched from ground metal reflector pending to ground metal reflector determined, and the object to be identified is determined to be a ground metal reflector.
[0100] Optionally, the identification module 303 is further configured to:
[0101] If the ground metal reflector evaluation value is greater than a first evaluation threshold, switching the state of the state machine from stationary vehicle pending to ground metal reflector pending;
[0102] updating the ground metal reflector evaluation value, and if the updated ground metal reflector evaluation value is less than a second evaluation threshold, switching the state of the state machine from ground metal reflector pending to stationary vehicle pending;
[0103] Update the reflection intensity attenuation value and the distance-reflection intensity slope. If the updated reflection intensity attenuation value is greater than the reflection intensity attenuation threshold, or the updated distance-reflection intensity slope is greater than the second slope threshold, switch the state of the state machine from stationary vehicle pending to stationary vehicle determined, and determine that the object to be identified is a stationary vehicle.
[0104] It can be understood that the functions of the various functional modules of the object recognition device of the embodiment of the present invention can be specifically implemented according to the method in the above method embodiment, and its specific implementation process can refer to the relevant description of the above method embodiment, which will not be repeated here.
[0105] In an embodiment of the present invention, the acquisition module 301 can acquire detection information of the object to be identified, and the determination module 302 determines the characteristic information of the object to be identified based on the detection information. The characteristic information of the object to be identified may include at least one of the following: the distance-reflection intensity slope of the radar transmission wave, the evaluation value of the ground metal reflector, and the reflection intensity attenuation value of the radar transmission wave. Then, the identification module 303 can use the characteristic information to identify the object to be identified, thereby improving the accuracy of identifying the object in front of the vehicle without adding additional hardware, so as to reduce the false triggering of the automatic emergency braking system.
[0106] See also Figure 4 , is a schematic diagram of the structure of a millimeter wave radar provided in an embodiment of the present invention. The millimeter wave radar described in this embodiment includes: a processor 401 and a memory 402. The processor 401 and the memory 402 are connected via a bus.
[0107] The processor 401 may be a central processing unit (CPU), or other general-purpose processors, digital signal processors (DSP), application-specific integrated circuits (ASIC), field-programmable gate arrays (FPGA) or other programmable logic devices, discrete gate or transistor logic devices, discrete hardware components, etc. A general-purpose processor may be a microprocessor or any conventional processor, etc.
[0108] The memory 402 may include a read-only memory and a random access memory, and provide program instructions and data to the processor 401. A portion of the memory 402 may also include a non-volatile random access memory. When the processor 401 calls the program instructions, it is used to execute:
[0109] Obtain detection information of the object to be identified;
[0110] Determine characteristic information of the object to be identified according to the detection information, wherein the characteristic information includes at least one of the following: a distance-reflection intensity slope of a radar transmission wave, an evaluation value of a ground metal reflector, and a reflection intensity attenuation value of a radar transmission wave;
[0111] The object to be identified is identified using the feature information.
[0112] Optionally, the detection information includes at least one of the following: the reflection intensity of the object to be identified to the radar transmission wave, and the distance from the object to be identified.
[0113] Optionally, the processor 401 is specifically configured to:
[0114] The feature information and a state machine are used to determine whether the object to be identified is a stationary vehicle. The state machine includes four states: stationary vehicle pending, stationary vehicle confirmed, ground metal reflector pending, and ground metal reflector confirmed.
[0115] Optionally, the processor 401 is specifically configured to:
[0116] Calculate the distance-reflection intensity slope of the object to be identified to the radar transmission wave according to the reflection intensity and the distance;
[0117] The ground metal reflector evaluation value of the object to be identified is determined according to the distance-reflection intensity slope of the object to be identified to the radar transmission wave and a first slope threshold.
[0118] Optionally, the processor 401 is specifically configured to:
[0119] If the distance-reflection intensity slope of the object to be identified to the radar transmission wave is less than the first slope threshold, the ground metal reflector evaluation value of the object to be identified is calculated using the historical evaluation value of the ground metal reflector, the increase in the ground metal reflector evaluation value and the maximum evaluation value of the ground metal reflector.
[0120] Optionally, the ground metal reflector evaluation value of the object to be identified is the larger value of the sum of the ground metal reflector historical evaluation value and the ground metal reflector evaluation value increase and the ground metal reflector maximum evaluation value.
[0121] Optionally, the processor 401 is specifically configured to:
[0122] If the distance-reflection intensity slope of the object to be identified to the radar transmission wave is greater than or equal to the first slope threshold, the ground metal reflector evaluation value of the object to be identified is calculated using the ground metal reflector historical evaluation value and the ground metal reflector evaluation value reduction.
[0123] Optionally, the ground metal reflector evaluation value of the object to be identified is the smaller value of the difference between the historical evaluation value of the ground metal reflector and the reduction amount of the ground metal reflector evaluation value and 0.
[0124] Optionally, the processor 401 is specifically configured to:
[0125] Obtaining the maximum reflection intensity of the radar transmission wave of the object to be identified;
[0126] The reflection intensity fading value of the object to be identified to the radar transmission wave is calculated according to the reflection intensity of the object to be identified to the radar transmission wave and the maximum reflection intensity.
[0127] Optionally, the processor 401 is specifically configured to:
[0128] Set the initial state of the state machine to a stationary vehicle pending;
[0129] If the reflection intensity attenuation value is greater than the reflection intensity attenuation threshold, or the distance-reflection intensity slope is greater than the second slope threshold, the state of the state machine is switched from stationary vehicle pending to stationary vehicle determined, and the object to be identified is determined to be a stationary vehicle.
[0130] Optionally, the processor 401 is specifically configured to:
[0131] If the ground metal reflector evaluation value is greater than a first evaluation threshold, switching the state of the state machine from stationary vehicle pending to ground metal reflector pending;
[0132] If the distance is less than the distance threshold, the state of the state machine is switched from ground metal reflector pending to ground metal reflector determined, and the object to be identified is determined to be a ground metal reflector.
[0133] Optionally, the processor 401 is specifically configured to:
[0134] If the ground metal reflector evaluation value is greater than a first evaluation threshold, switching the state of the state machine from stationary vehicle pending to ground metal reflector pending;
[0135] updating the ground metal reflector evaluation value, and if the updated ground metal reflector evaluation value is less than a second evaluation threshold, switching the state of the state machine from ground metal reflector pending to stationary vehicle pending;
[0136] Update the reflection intensity attenuation value and the distance-reflection intensity slope. If the updated reflection intensity attenuation value is greater than the reflection intensity attenuation threshold, or the updated distance-reflection intensity slope is greater than the second slope threshold, switch the state of the state machine from stationary vehicle pending to stationary vehicle determined, and determine that the object to be identified is a stationary vehicle.
[0137] In a specific implementation, the processor 401 and the memory 402 described in the embodiment of the present invention can execute the embodiment of the present invention. Figure 1 The implementation described in the object recognition method provided can also be used to implement the embodiments of the present invention. Figure 3 The implementation of the described object recognition device will not be described in detail here.
[0138] In an embodiment of the present invention, the processor 401 can obtain detection information of the object to be identified, and determine characteristic information of the object to be identified based on the detection information. The characteristic information of the object to be identified may include at least one of the following: a distance-reflection intensity slope of a radar transmission wave, an evaluation value of a ground metal reflector, and a reflection intensity attenuation value of a radar transmission wave. The object to be identified can be identified using the characteristic information, thereby improving the accuracy of identifying objects in front of the vehicle without adding additional hardware, thereby reducing false triggering of the automatic emergency braking system.
[0139] An embodiment of the present invention further provides a vehicle, including a vehicle body and a millimeter-wave radar installed on the vehicle body. The millimeter-wave radar can adopt the structure of each of the above embodiments.
[0140] The embodiment of the present invention further provides a computer storage medium in which program instructions are stored. When the program is executed, the following may be included: Figure 1 Part or all of the steps of the object recognition method in the corresponding embodiment.
[0141] It should be noted that, for the above-mentioned various method embodiments, for the sake of simplicity of description, they are all expressed as a series of action combinations, but those skilled in the art should know that the present invention is not limited by the described order of actions, because according to the present application, some steps can be performed in other orders or simultaneously. Secondly, those skilled in the art should also know that the embodiments described in the specification are all preferred embodiments, and the actions and modules involved are not necessarily required by the present application.
[0142] A person skilled in the art may understand that all or part of the steps in the various methods of the above embodiments may be completed by instructing related hardware through a program, and the program may be stored in a computer-readable storage medium, and the storage medium may include: a flash drive, a read-only memory (ROM), a random access memory (RAM), a magnetic disk or an optical disk, etc.
[0143] The above is a detailed introduction to an object recognition method, millimeter wave radar and vehicle provided in an embodiment of the present invention. Specific examples are used in this article to illustrate the principles and implementation methods of the present invention. The description of the above embodiments is only used to help understand the method of the present invention and its core idea; at the same time, for those skilled in the art, according to the idea of the present invention, there will be changes in the specific implementation method and application scope. In summary, the content of this specification should not be understood as a limitation on the present invention.
Claims
1. An object recognition method, applied to millimeter wave radar, characterized in that: The method comprises: Acquire detection information of the object to be identified; the detection information includes at least one of the following: the reflection intensity of the radar transmission wave of the object to be identified, and the distance to the object to be identified; Determine characteristic information of the object to be identified according to the detection information, wherein the characteristic information includes at least one of the following: a distance-reflection intensity slope of a radar transmission wave, an evaluation value of a ground metal reflector, and a reflection intensity attenuation value of a radar transmission wave; Using the feature information to identify the object to be identified; Wherein, the identifying the object to be identified by using the feature information includes: Determine whether the object to be identified is a stationary vehicle by using the feature information and a state machine, wherein the state machine includes four states: stationary vehicle pending, stationary vehicle confirmed, ground metal reflector pending, and ground metal reflector confirmed; The millimeter-wave radar sets the initial state of the state machine to stationary vehicle pending. If the ground metal reflector evaluation value is greater than the first evaluation threshold, the state of the state machine is switched from stationary vehicle pending to ground metal reflector pending. If the distance is less than the distance threshold, the state of the state machine is switched from ground metal reflector pending to ground metal reflector determined, and the object to be identified is determined to be a ground metal reflector.
2. The method according to claim 1, characterized in that The determining the feature information of the object to be identified according to the detection information includes: Calculate the distance-reflection intensity slope of the object to be identified to the radar transmission wave according to the reflection intensity and the distance; The ground metal reflector evaluation value of the object to be identified is determined according to the distance-reflection intensity slope of the object to be identified to the radar transmission wave and a first slope threshold.
3. The method according to claim 2, characterized in that The step of determining the ground metal reflector evaluation value of the object to be identified according to the distance-reflection intensity slope of the radar transmission wave of the object to be identified and a first slope threshold comprises: If the distance-reflection intensity slope of the object to be identified to the radar transmission wave is less than the first slope threshold, the ground metal reflector evaluation value of the object to be identified is calculated using the historical evaluation value of the ground metal reflector, the increase in the ground metal reflector evaluation value and the maximum evaluation value of the ground metal reflector.
4. The method according to claim 3, characterized in that The ground metal reflector evaluation value of the object to be identified is the larger value of the sum of the ground metal reflector historical evaluation value and the ground metal reflector evaluation value increase and the ground metal reflector maximum evaluation value.
5. The method according to claim 2, characterized in that: The step of determining the ground metal reflector evaluation value of the object to be identified according to the distance-reflection intensity slope of the radar transmission wave of the object to be identified and a first slope threshold comprises: If the distance-reflection intensity slope of the object to be identified to the radar transmission wave is greater than or equal to the first slope threshold, the ground metal reflector evaluation value of the object to be identified is calculated using the ground metal reflector historical evaluation value and the ground metal reflector evaluation value reduction.
6. The method according to claim 5, characterized in that The ground metal reflector evaluation value of the object to be identified is the smaller value of the difference between the ground metal reflector historical evaluation value and the reduction amount of the ground metal reflector evaluation value and 0.
7. The method according to claim 1, characterized in that The determining the feature information of the object to be identified according to the detection information includes: Obtaining the maximum reflection intensity of the radar transmission wave of the object to be identified; The reflection intensity fading value of the object to be identified to the radar transmission wave is calculated according to the reflection intensity of the object to be identified to the radar transmission wave and the maximum reflection intensity.
8. The method according to claim 1, characterized in that The step of using the feature information and the state machine to determine whether the object to be identified is a stationary vehicle includes: Set the initial state of the state machine to a stationary vehicle pending; If the reflection intensity attenuation value is greater than the reflection intensity attenuation threshold, or the distance-reflection intensity slope is greater than the second slope threshold, the state of the state machine is switched from stationary vehicle pending to stationary vehicle determined, and the object to be identified is determined to be a stationary vehicle.
9. The method according to claim 8, characterized in that The method further comprises: If the ground metal reflector evaluation value is greater than a first evaluation threshold, switching the state of the state machine from stationary vehicle pending to ground metal reflector pending; updating the ground metal reflector evaluation value, and if the updated ground metal reflector evaluation value is less than a second evaluation threshold, switching the state of the state machine from ground metal reflector pending to stationary vehicle pending; Update the reflection intensity attenuation value and the distance-reflection intensity slope. If the updated reflection intensity attenuation value is greater than the reflection intensity attenuation threshold, or the updated distance-reflection intensity slope is greater than the second slope threshold, switch the state of the state machine from stationary vehicle pending to stationary vehicle determined, and determine that the object to be identified is a stationary vehicle.
10. A millimeter wave radar, characterized in that: The millimeter wave radar includes: a processor and a memory, wherein: The memory is used to store a computer program, wherein the computer program includes program instructions; When the processor calls the program instructions, it is used to execute: Acquire detection information of the object to be identified; the detection information includes at least one of the following: the reflection intensity of the radar transmission wave of the object to be identified, and the distance to the object to be identified; Determine characteristic information of the object to be identified according to the detection information, wherein the characteristic information includes at least one of the following: a distance-reflection intensity slope of a radar transmission wave, an evaluation value of a ground metal reflector, and a reflection intensity attenuation value of a radar transmission wave; Using the feature information to identify the object to be identified; Wherein, the processor is specifically used for: Determine whether the object to be identified is a stationary vehicle by using the feature information and a state machine, wherein the state machine includes four states: stationary vehicle pending, stationary vehicle confirmed, ground metal reflector pending, and ground metal reflector confirmed; The millimeter-wave radar sets the initial state of the state machine to stationary vehicle pending. If the ground metal reflector evaluation value is greater than the first evaluation threshold, the state of the state machine is switched from stationary vehicle pending to ground metal reflector pending. If the distance is less than the distance threshold, the state of the state machine is switched from ground metal reflector pending to ground metal reflector determined, and the object to be identified is determined to be a ground metal reflector.
11. The millimeter wave radar according to claim 10, characterized in that: The processor is specifically used for: Calculate the distance-reflection intensity slope of the object to be identified to the radar transmission wave according to the reflection intensity and the distance; The ground metal reflector evaluation value of the object to be identified is determined according to the distance-reflection intensity slope of the object to be identified to the radar transmission wave and a first slope threshold.
12. The millimeter wave radar according to claim 11, characterized in that: The processor is specifically used for: If the distance-reflection intensity slope of the object to be identified to the radar transmission wave is less than the first slope threshold, the ground metal reflector evaluation value of the object to be identified is calculated using the historical evaluation value of the ground metal reflector, the increase in the ground metal reflector evaluation value and the maximum evaluation value of the ground metal reflector.
13. The millimeter wave radar according to claim 12, characterized in that: The ground metal reflector evaluation value of the object to be identified is the larger value of the sum of the ground metal reflector historical evaluation value and the ground metal reflector evaluation value increase and the ground metal reflector maximum evaluation value.
14. The millimeter wave radar according to claim 11, characterized in that: The processor is specifically used for: If the distance-reflection intensity slope of the object to be identified to the radar transmission wave is greater than or equal to the first slope threshold, the ground metal reflector evaluation value of the object to be identified is calculated using the ground metal reflector historical evaluation value and the ground metal reflector evaluation value reduction.
15. The millimeter wave radar according to claim 14, characterized in that: The ground metal reflector evaluation value of the object to be identified is the smaller value of the difference between the ground metal reflector historical evaluation value and the reduction amount of the ground metal reflector evaluation value and 0.
16. The millimeter wave radar according to claim 10, characterized in that: The processor is specifically used for: Obtaining the maximum reflection intensity of the radar transmission wave of the object to be identified; The reflection intensity fading value of the object to be identified to the radar transmission wave is calculated according to the reflection intensity of the object to be identified to the radar transmission wave and the maximum reflection intensity.
17. The millimeter wave radar according to claim 10, characterized in that: The processor is specifically used for: Set the initial state of the state machine to a stationary vehicle pending; If the reflection intensity attenuation value is greater than the reflection intensity attenuation threshold, or the distance-reflection intensity slope is greater than the second slope threshold, the state of the state machine is switched from stationary vehicle pending to stationary vehicle determined, and the object to be identified is determined to be a stationary vehicle.
18. The millimeter wave radar according to claim 17, characterized in that: The processor is further configured to: If the ground metal reflector evaluation value is greater than a first evaluation threshold, switching the state of the state machine from stationary vehicle pending to ground metal reflector pending; updating the ground metal reflector evaluation value, and if the updated ground metal reflector evaluation value is less than a second evaluation threshold, switching the state of the state machine from ground metal reflector pending to stationary vehicle pending; Update the reflection intensity attenuation value and the distance-reflection intensity slope. If the updated reflection intensity attenuation value is greater than the reflection intensity attenuation threshold, or the updated distance-reflection intensity slope is greater than the second slope threshold, switch the state of the state machine from stationary vehicle pending to stationary vehicle determined, and determine that the object to be identified is a stationary vehicle.
19. A vehicle, applied to millimeter wave radar, characterized in that: The vehicle comprises: Vehicle body; The millimeter wave radar according to any one of claims 1 to 18 is installed on the vehicle body.
