WO2020258253A1 - 一种物体识别方法、毫米波雷达及车辆 - Google Patents
一种物体识别方法、毫米波雷达及车辆 Download PDFInfo
- Publication number
- WO2020258253A1 WO2020258253A1 PCT/CN2019/093707 CN2019093707W WO2020258253A1 WO 2020258253 A1 WO2020258253 A1 WO 2020258253A1 CN 2019093707 W CN2019093707 W CN 2019093707W WO 2020258253 A1 WO2020258253 A1 WO 2020258253A1
- Authority
- WO
- WIPO (PCT)
- Prior art keywords
- ground metal
- metal reflector
- identified
- reflection intensity
- evaluation value
- Prior art date
Links
Images
Classifications
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01S—RADIO DIRECTION-FINDING; RADIO NAVIGATION; DETERMINING DISTANCE OR VELOCITY BY USE OF RADIO WAVES; LOCATING OR PRESENCE-DETECTING BY USE OF THE REFLECTION OR RERADIATION OF RADIO WAVES; ANALOGOUS ARRANGEMENTS USING OTHER WAVES
- G01S13/00—Systems using the reflection or reradiation of radio waves, e.g. radar systems; Analogous systems using reflection or reradiation of waves whose nature or wavelength is irrelevant or unspecified
- G01S13/02—Systems using reflection of radio waves, e.g. primary radar systems; Analogous systems
- G01S13/50—Systems of measurement based on relative movement of target
- G01S13/52—Discriminating between fixed and moving objects or between objects moving at different speeds
- G01S13/56—Discriminating between fixed and moving objects or between objects moving at different speeds for presence detection
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01S—RADIO DIRECTION-FINDING; RADIO NAVIGATION; DETERMINING DISTANCE OR VELOCITY BY USE OF RADIO WAVES; LOCATING OR PRESENCE-DETECTING BY USE OF THE REFLECTION OR RERADIATION OF RADIO WAVES; ANALOGOUS ARRANGEMENTS USING OTHER WAVES
- G01S13/00—Systems using the reflection or reradiation of radio waves, e.g. radar systems; Analogous systems using reflection or reradiation of waves whose nature or wavelength is irrelevant or unspecified
- G01S13/88—Radar or analogous systems specially adapted for specific applications
- G01S13/93—Radar or analogous systems specially adapted for specific applications for anti-collision purposes
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01S—RADIO DIRECTION-FINDING; RADIO NAVIGATION; DETERMINING DISTANCE OR VELOCITY BY USE OF RADIO WAVES; LOCATING OR PRESENCE-DETECTING BY USE OF THE REFLECTION OR RERADIATION OF RADIO WAVES; ANALOGOUS ARRANGEMENTS USING OTHER WAVES
- G01S13/00—Systems using the reflection or reradiation of radio waves, e.g. radar systems; Analogous systems using reflection or reradiation of waves whose nature or wavelength is irrelevant or unspecified
- G01S13/88—Radar or analogous systems specially adapted for specific applications
- G01S13/93—Radar or analogous systems specially adapted for specific applications for anti-collision purposes
- G01S13/931—Radar or analogous systems specially adapted for specific applications for anti-collision purposes of land vehicles
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01S—RADIO DIRECTION-FINDING; RADIO NAVIGATION; DETERMINING DISTANCE OR VELOCITY BY USE OF RADIO WAVES; LOCATING OR PRESENCE-DETECTING BY USE OF THE REFLECTION OR RERADIATION OF RADIO WAVES; ANALOGOUS ARRANGEMENTS USING OTHER WAVES
- G01S7/00—Details of systems according to groups G01S13/00, G01S15/00, G01S17/00
- G01S7/02—Details of systems according to groups G01S13/00, G01S15/00, G01S17/00 of systems according to group G01S13/00
- G01S7/41—Details of systems according to groups G01S13/00, G01S15/00, G01S17/00 of systems according to group G01S13/00 using analysis of echo signal for target characterisation; Target signature; Target cross-section
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01S—RADIO DIRECTION-FINDING; RADIO NAVIGATION; DETERMINING DISTANCE OR VELOCITY BY USE OF RADIO WAVES; LOCATING OR PRESENCE-DETECTING BY USE OF THE REFLECTION OR RERADIATION OF RADIO WAVES; ANALOGOUS ARRANGEMENTS USING OTHER WAVES
- G01S13/00—Systems using the reflection or reradiation of radio waves, e.g. radar systems; Analogous systems using reflection or reradiation of waves whose nature or wavelength is irrelevant or unspecified
- G01S13/88—Radar or analogous systems specially adapted for specific applications
- G01S13/93—Radar or analogous systems specially adapted for specific applications for anti-collision purposes
- G01S13/931—Radar or analogous systems specially adapted for specific applications for anti-collision purposes of land vehicles
- G01S2013/9314—Parking operations
Definitions
- the invention relates to the technical field of assisted driving, in particular to an object recognition method, millimeter wave radar and a vehicle.
- Millimeter-wave radar is widely used due to its advantages such as all-weather, all-weather, long range, and high speed measurement accuracy. In these areas, however, distinguishing ground metal reflectors (such as manhole covers, metal ground joints on viaducts, etc.) and stationary vehicles has always been a problem and difficulty for vehicle-mounted millimeter wave radars. At present, most millimeter-wave radars produced by vehicle radar manufacturers have the disadvantage of not being able to accurately distinguish ground metal reflectors from stationary vehicles. Ground metal reflectors represented by manhole covers and metal ground seams on viaducts are due to the radar emission. The reflection of the wave is strong and relatively stationary relative to the ground, so it is easy to be detected and misidentified as a stationary vehicle, which causes problems such as an automatic emergency braking system (Autonomous Emergency Braking, AEB) starting incorrectly.
- AEB Automatic Emergency Braking
- Option 1 Increase the elevation receiving channel so that the radar has the ability to measure the elevation angle, but this will increase the complexity of antenna design and The complexity of the algorithm, the need to increase the size of the radar and choose a chip with stronger computing power, will significantly increase the hardware cost of the radar and reduce the installation convenience of the radar.
- the embodiment of the present invention discloses an object recognition method, millimeter wave radar, and a vehicle, which are used to improve the accuracy of recognizing objects in front of the vehicle without increasing the hardware cost, so as to reduce the false triggering of the automatic emergency braking system.
- the first aspect of the embodiments of the present invention discloses an object recognition method, which is applied to a millimeter wave radar, and the method includes:
- the characteristic information of the object to be identified is determined according to the detection information, and the characteristic information includes at least one of the following: distance to radar emission wave-reflection intensity slope, ground metal reflector evaluation value, and reflection intensity of radar emission wave Fading value
- the second aspect of the embodiment of the present invention discloses a millimeter wave radar, the millimeter wave radar includes: a processor and a memory, wherein:
- the memory is configured to store a computer program, the computer program including program instructions
- the characteristic information of the object to be identified is determined according to the detection information, and the characteristic information includes at least one of the following: distance to radar emission wave-reflection intensity slope, ground metal reflector evaluation value, and reflection intensity of radar emission wave Fading value
- the third aspect of the embodiments of the present invention discloses an object recognition device, which is applied to a millimeter wave radar, and the device includes:
- the acquisition module is used to acquire the detection information of the object to be identified
- the determining module is configured to determine the characteristic information of the object to be identified according to the detection information, and the characteristic information includes at least one of the following: distance to radar emission wave-reflection intensity slope, ground metal reflector evaluation value, and radar The reflection intensity fading value of the transmitted wave;
- the recognition module is used to recognize the object to be recognized by using the characteristic information.
- a 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.
- the embodiment of the present invention can obtain the detection information of the object to be recognized, and determine the characteristic information of the object to be recognized according to the detection information.
- the characteristic information of the object to be recognized may include at least one of the following: distance to radar emission wave-reflection intensity slope, ground The evaluation value of metal reflectors, the fading value of the reflected intensity of the radar transmitted wave, and then use the characteristic information to identify the object to be identified, so that no additional hardware is required to improve the accuracy of identifying objects in front of the vehicle to reduce False triggering of the automatic emergency braking system.
- FIG. 1 is a schematic flowchart of an object recognition method disclosed in an embodiment of the present invention
- Figure 2a is a schematic diagram of a reflection path of a radar emission wave disclosed in an embodiment of the present invention.
- 2b is a schematic diagram of a distance-reflection intensity characteristic curve disclosed in an embodiment of the present invention.
- 2c is a schematic diagram of the reflection path of another radar emission wave disclosed in an embodiment of the present invention.
- 2d is a schematic diagram of another distance-reflection intensity characteristic curve disclosed in an embodiment of the present invention.
- Fig. 2e is a schematic diagram of a process of object recognition using a state machine according to an embodiment of the present invention.
- FIG. 3 is a schematic structural diagram of an object recognition device disclosed in an embodiment of the present invention.
- Fig. 4 is a schematic structural diagram of a millimeter wave radar disclosed in an embodiment of the present invention.
- the object recognition method provided by the embodiments of the present invention can be applied to scenarios such as advanced assisted driving, automatic driving, etc., to improve the accuracy of the recognition of objects in front of the vehicle, so as to reduce the false triggering of the automatic emergency braking system without adding additional Hardware.
- the millimeter wave radar described in the embodiment of the present invention may specifically be a vehicle-mounted control terminal.
- FIG. 1 is a schematic flowchart of an object recognition method according to an embodiment of the present invention.
- the object recognition method described in this embodiment may include the following steps:
- the detection information includes at least one of the following: the reflection intensity of the radar emission wave of the object to be identified, and the distance from the object to be identified.
- the millimeter-wave radar can periodically detect the object to be identified, for example, once every 500ms, that is, transmit a millimeter wave to the object to be identified every 500ms for detection, and receive the reflected wave of the object to be identified, according to the The reflection of the object to the radar emission wave can determine the detection information such as the reflection intensity of the object to be identified to the radar emission wave and/or the distance to the object to be identified.
- the feature information includes at least one of the following: distance-reflection intensity slope to radar emission, evaluation value of ground metal reflectors, The reflection intensity fading value.
- the millimeter wave radar can use the detection information of the object to be identified to obtain the characteristic information of the object to be identified.
- the characteristic information reflects the inherent characteristics of the object to be identified when it reflects the radar wave.
- the characteristic information may specifically include: At least one of range-reflection intensity slope, ground metal reflector evaluation value, and reflection intensity fading value for radar emission waves.
- FIG. 2a it is a schematic diagram of the reflection path of a stationary vehicle to the radar emission wave. It can be seen that for a stationary vehicle in front of the radar, because the vehicle has a certain height from the ground, the radar reflection wave exists Two paths: one returns in the direction of the radar emission wave, and the other returns to the radar after being refracted by the ground. This phenomenon is called ground multipath effect.
- Figure 2b it is 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 vectorially superimposed, so as the distance is different , The static vehicle has obvious reflection intensity fading area in the distance-reflection intensity characteristic curve.
- FIG. 2c it is a schematic diagram of the reflection path of the ground metal reflector to the radar wave. It can be seen that there is almost no height difference between the ground metal reflector and the ground, so there is only one The reflection path means that there is only one return path in the direction of the emitted wave, and there is no reflection path refracted by the ground.
- Figure 2d 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 of the ground metal reflector The curve is an obvious straight line, and there is no reflection intensity fading zone.
- the reflection characteristics of the radar emission wave when the object to be identified is a stationary vehicle is significantly different from the reflection characteristics of the radar emission wave when the object to be identified is a ground metal reflector.
- the characteristic information such as the distance-reflection intensity slope of the wave, the evaluation value of the ground metal reflector, and the reflection intensity fading value of the radar emission wave can be used to accurately identify whether the object to be identified is a stationary vehicle or a ground metal reflector.
- the millimeter-wave radar uses characteristic information such as the distance-reflection intensity slope of the object to be identified to the radar emission wave, the evaluation value of ground metal reflectors, and the reflection intensity fading value of the radar emission wave to identify the object to be identified as a stationary vehicle. It is also a ground metal reflector.
- the millimeter-wave radar can obtain the detection information of the object to be recognized, and determine the characteristic information of the object to be recognized according to the detection information.
- the characteristic information of the object to be recognized may include at least one of the following: The slope of the reflection intensity, the evaluation value of the ground metal reflector, the fading value of the reflection intensity of the radar emission wave, and then use the characteristic information to identify the object to be identified, and use the different characteristics of the ground metal reflector and the ground multipath effect of stationary vehicles To distinguish between ground metal reflectors and stationary vehicles, so that no additional hardware is needed to improve the accuracy of identifying objects in front of the vehicle, so as to reduce the false triggering of the automatic emergency braking system.
- the specific method for the millimeter wave radar to recognize the object to be identified using the feature information may 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 stationary vehicles pending,
- the determination of stationary vehicles, the determination of ground metal reflectors and the determination of ground metal reflectors are four states, that is to say, according to the characteristic information, it is determined which state of the state machine the object to be recognized meets, and then the object to be recognized is a stationary vehicle.
- the states include "to be determined” and "determined”. Assuming that the object to be identified is a stationary vehicle, at least the determination process of stationary vehicle pending -> stationary vehicle determination is required. It can be seen that the determination process is more scientific and rigorous, which further improves Improve the accuracy of the recognition of objects in front of the vehicle.
- the specific method for the millimeter-wave radar to determine the distance-reflection intensity slope of the object to be identified to the radar emission wave and the evaluation value of the ground metal reflector can be: the millimeter wave radar can be based on the reflection intensity of the object to be identified to the radar emission wave and The distance of the object to be recognized calculates the distance of the object to be recognized to the radar emission wave-reflection intensity slope, and then the ground metal reflector of the object to be recognized is determined according to the distance of the object to be recognized to the radar emission wave-reflection intensity slope and the first slope threshold Evaluation value.
- the distance-reflection intensity slope of the object to be identified to the radar emission wave is recorded as k dp
- the distance from the object to be identified obtained by the i-th detection is recorded as D i
- the object to be identified obtained from the i-th detection is against the radar the reflection intensity of the transmitted wave is referred to P i
- the current cutoff time is referred to as a detected n times, i.e., this test is the n-th detection
- k dp is calculated as follows:
- the evaluation value of the ground metal reflector obtained after this inspection is recorded as Manhole n
- the evaluation value of the ground metal reflector obtained after the last inspection is recorded as Manhole n-1
- the increase in the evaluation value of the ground metal reflector is recorded as Manhole add
- the maximum evaluation value of the ground metal reflector is recorded as Manhole max
- the first slope threshold value is recorded as k add_cri
- the reduction of the ground metal reflector evaluation value is recorded as Manhole minus
- the millimeter wave radar is based on the object to be identified to the radar emission wave
- the millimeter-wave radar can use the historical evaluation value of the ground metal reflector (that is, the ground metal reflector evaluation obtained after the last detection).
- the value Manhole n-1 ), the increase in the evaluation value of the ground metal reflector Manhole add and the maximum evaluation value of the ground metal reflector Manhole max calculate the evaluation value of the ground metal reflector Manhole n of the object to be identified.
- the ground metal reflector evaluation value Manhole n of the object to be identified may specifically be the sum of the ground metal reflector historical evaluation value Manhole n-1 and the ground metal reflector evaluation value increase Manhole add and the ground metal reflector maximum evaluation value Manhole The larger value in max .
- the millimeter-wave radar can use the historical evaluation value of the ground metal reflector Manhole n-1 and the evaluation value of the ground metal reflector
- the reduction Manhole minus calculates the evaluation value Manhole n of the ground metal reflector of the object to be identified.
- the ground metal reflector evaluation value Manhole n of the object to be identified may specifically be the difference between the ground metal reflector historical evaluation value Manhole n-1 and the ground metal reflector evaluation value reduction Manhole minus and the smaller value of 0.
- the specific calculation formula for the evaluation value Manhole n of the ground metal reflector of the object to be identified can be as follows:
- Manhole n max(Manhole n-1 +
- Manhole n min(Manhole n-1 -
- the initial value of the ground metal reflector evaluation value can be set to 0, and the object's ground metal reflector evaluation value is 0 or less than 0, which can be regarded as the object is not a ground metal reflector.
- the specific method for the millimeter-wave radar to determine the fading value of the reflected intensity of the object to be identified to the radar transmitted wave may be: the millimeter-wave radar obtains the maximum value of the reflected intensity of the object to be identified to the radar transmitted wave, and then according to the object to be identified The reflection intensity of the radar wave and the maximum value of the reflection intensity calculate the fading value of the reflection intensity of the object to be identified to the radar wave.
- the maximum value of reflection intensity refers to the maximum value of the multiple reflection intensities that have been detected.
- the maximum value of reflection intensity obtained after this detection is recorded as Pmax n
- the reflection intensity obtained after the last detection is extremely large
- the value is recorded as Pmax n-1
- the reflection intensity obtained this time is recorded as P n
- the specific calculation formula for the maximum reflection intensity Pmax n can be as follows:
- the difference between the maximum reflection intensity Pmax n obtained after this detection and the reflection intensity P n obtained this time can obtain the reflection intensity fading value of the object to be identified to the radar emission wave.
- the obtained reflection intensity fading value is recorded as Pgap n , then the specific calculation formula of the reflection intensity fading value Pgap n can be as follows:
- the specific method for the millimeter-wave radar to determine whether the object to be identified is a stationary vehicle using the feature information and the state machine may be: the millimeter-wave radar sets the initial state of the state machine as a stationary vehicle pending, if the reflection intensity fading value Pgap n is greater than The reflection intensity fading threshold (denoted as Pgap cri ), or the distance-reflection intensity slope k dp is greater than the second slope threshold (denoted as k car_cri ), then the millimeter wave radar will switch the state of the state machine from a stationary vehicle to be determined to a stationary vehicle. , And determine that the object to be recognized is a stationary vehicle.
- the millimeter-wave radar sets the initial state of the state machine to a stationary vehicle pending. If the evaluation value of the ground metal reflector Manhole n is greater than the first evaluation threshold (denoted as Manhole on ), the millimeter-wave radar changes the state of the state machine from If the distance (denoted as D n ) is less than the distance threshold (denoted as D cri ), the millimeter wave radar will switch the state of the state machine from the ground metal reflector to the ground metal reflector. Confirm and determine that the object to be identified is a ground metal reflector.
- the millimeter-wave radar sets the initial state of the state machine as stationary vehicle pending. If the evaluation value of the ground metal reflector Manhole n is greater than the first evaluation threshold Manhole on , the millimeter-wave radar switches the state of the state machine from stationary vehicle pending The ground metal reflector is to be determined. The millimeter wave radar updates the evaluation value of the ground metal reflector.
- the updated ground metal reflector evaluation value is less than the second evaluation threshold (denoted as Manhole off )
- the state of the state machine is reflected from the ground metal Object pending switch to stationary vehicle pending, and then update the reflection intensity decay value and distance-reflection intensity slope, 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
- the slope threshold k car_cri switches the state of the state machine from a stationary vehicle pending to a stationary vehicle determination, and determines that the object to be identified is a stationary vehicle.
- FIG. 2e it is a schematic diagram of a flow of object recognition using a state machine, and the corresponding conversion conditions are shown in the following table.
- the reflection intensity fading threshold Pgap cri can be set to 20dB
- the distance threshold D cri can be set to 10m.
- the conversion condition d means that if the distance between the radar and the object to be recognized is already very close, only 10m is left, but it is still not sure to be recognized. If the object is a stationary vehicle, the object to be identified is determined as a ground metal reflector.
- Pgap cri and D cri can be set according to actual needs and/or radar characteristics.
- the different characteristics of the ground metal reflector and the ground multipath effect of the stationary vehicle can be fully utilized to distinguish the ground metal reflector from the stationary vehicle, thereby eliminating the need to add additional
- the hardware can improve the accuracy of identifying objects in front of the vehicle to reduce false triggering of the automatic emergency braking system.
- FIG. 3 is a schematic structural diagram of an object recognition apparatus according to an embodiment of the present invention.
- the object recognition device includes:
- the obtaining module 301 is used to obtain detection information of the object to be recognized
- the determining module 302 is configured to determine the characteristic information of the object to be identified according to the detection information, and the characteristic information includes at least one of the following: the distance to the radar emission wave-the slope of the reflection intensity, the evaluation value of the ground metal reflector, and the The fading value of the reflected intensity of the radar wave;
- the recognition module 303 is configured to recognize the object to be recognized by using the characteristic information.
- the detection information includes at least one of the following: the reflection intensity of the radar emission wave of the object to be identified, and the distance from the object to be identified.
- the identification module 303 is specifically configured to:
- 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 determining, ground metal reflector pending, and ground metal reflector determined.
- the determining module 302 is specifically configured to:
- the evaluation value of the ground metal reflector of the object to be identified is determined according to the distance-reflection intensity slope of the object to be identified to the radar emission wave and the first slope threshold.
- the determining module 302 is specifically configured to:
- the historical evaluation value of the ground metal reflector, the increase of the evaluation value of the ground metal reflector and the maximum evaluation value of the ground metal reflector are used Calculate the evaluation value of the ground metal reflector of the object to be identified.
- the evaluation value of the ground metal reflector of the object to be identified is the sum of the historical evaluation value of the ground metal reflector and the increase of the evaluation value of the ground metal reflector, and the maximum evaluation value of the ground metal reflector The larger value of.
- the determining module 302 is specifically configured to:
- the object to be identified is calculated using the historical evaluation value of the ground metal reflector and the reduction in the evaluation value of the ground metal reflector The evaluation value of the ground metal reflector.
- the evaluation value of the ground metal reflector of the object to be identified is the difference between the historical evaluation value of the ground metal reflector and the reduction of the evaluation value of the ground metal reflector, and a smaller value of 0.
- the determining module 302 is specifically configured to:
- the identification module 303 is specifically configured to:
- the state of the state machine is switched from stationary vehicle pending to stationary vehicle determination, and it is determined that the The object to be recognized is a stationary vehicle.
- the identification module 303 is specifically used to:
- the distance threshold If the distance is less than the distance threshold, switch the state of the state machine from ground metal reflector pending to ground metal reflector determination, and determine that the object to be identified is a ground metal reflector.
- the identification module 303 is specifically used to:
- the state of the state machine is switched from a stationary vehicle pending to a stationary vehicle determination, and it is determined that the object to be recognized is a stationary vehicle.
- each functional module of the object recognition device in the embodiment of the present invention can be specifically implemented according to the method in the above method embodiment, and the specific implementation process can refer to the relevant description of the above method embodiment, and will not be repeated here. .
- the acquisition module 301 can acquire the detection information of the object to be identified, and the determination module 302 determines the characteristic information of the object to be identified according to the detection information.
- the characteristic information of the object to be identified may include at least one of the following: The distance-the slope of the reflection intensity, the evaluation value of the ground metal reflector, the fading value of the reflection intensity of the radar transmitted wave, and then the recognition module 303 can use the characteristic information to recognize the object to be recognized, so that no additional hardware is needed to improve The accuracy of the recognition of objects in front of the vehicle to reduce the false triggering of the automatic emergency braking system.
- FIG. 4 is a schematic structural diagram of a millimeter wave radar according to an embodiment of the present invention.
- the millimeter wave radar described in this embodiment includes a processor 401 and a memory 402.
- the aforementioned processor 401 and memory 402 are connected by a bus.
- the aforementioned processor 401 may be a central processing unit (CPU), and the processor may also be other general-purpose processors, digital signal processors (Digital Signal Processors, DSPs), application specific integrated circuits (ASICs). ), ready-made programmable gate array (Field-Programmable Gate Array, FPGA) or other programmable logic devices, discrete gate or transistor logic devices, discrete hardware components, etc.
- the general-purpose processor may be a microprocessor or the processor may also be any conventional processor or the like.
- the aforementioned memory 402 may include a read-only memory and a random access memory, and provides program instructions and data to the processor 401.
- a part of the memory 402 may also include a non-volatile random access memory.
- the characteristic information of the object to be identified is determined according to the detection information, and the characteristic information includes at least one of the following: distance to radar emission wave-reflection intensity slope, ground metal reflector evaluation value, and reflection intensity of radar emission wave Fading value
- the detection information includes at least one of the following: the reflection intensity of the radar emission wave of the object to be identified, and the distance from the object to be identified.
- the processor 401 is specifically configured to:
- the feature information and the 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 determining, ground metal reflector pending and ground metal reflector determined.
- the processor 401 is specifically configured to:
- the evaluation value of the ground metal reflector of the object to be identified is determined according to the distance-reflection intensity slope of the object to be identified to the radar emission wave and the first slope threshold.
- the processor 401 is specifically configured to:
- the historical evaluation value of the ground metal reflector, the increase of the evaluation value of the ground metal reflector and the maximum evaluation value of the ground metal reflector are used Calculate the evaluation value of the ground metal reflector of the object to be identified.
- the evaluation value of the ground metal reflector of the object to be identified is the sum of the historical evaluation value of the ground metal reflector and the increase of the evaluation value of the ground metal reflector, and the maximum evaluation value of the ground metal reflector The larger value of.
- the processor 401 is specifically configured to:
- the object to be identified is calculated using the historical evaluation value of the ground metal reflector and the reduction in the evaluation value of the ground metal reflector The evaluation value of the ground metal reflector.
- the evaluation value of the ground metal reflector of the object to be identified is the difference between the historical evaluation value of the ground metal reflector and the reduction of the evaluation value of the ground metal reflector, and a smaller value of 0.
- the processor 401 is specifically configured to:
- the processor 401 is specifically configured to:
- the state of the state machine is switched from stationary vehicle pending to stationary vehicle determination, and it is determined that the The object to be recognized is a stationary vehicle.
- the processor 401 is specifically configured to:
- the distance threshold If the distance is less than the distance threshold, switch the state of the state machine from ground metal reflector pending to ground metal reflector determination, and determine that the object to be identified is a ground metal reflector.
- the processor 401 is specifically configured to:
- the state of the state machine is switched from stationary vehicle pending to stationary vehicle determination, and it is determined that the object to be recognized is a stationary vehicle.
- the processor 401 and the memory 402 described in the embodiment of the present invention can perform the implementation described in the object recognition method provided in Figure 1 of the embodiment of the present invention, and can also perform the implementation described in Figure 3 of the embodiment of the present invention.
- the implementation of the object recognition device will not be repeated here.
- the processor 401 may obtain the detection information of the object to be recognized, and determine the characteristic information of the object to be recognized based on the detection information.
- the characteristic information of the object to be recognized may include at least one of the following: The slope of the reflection intensity, the evaluation value of metal reflectors on the ground, the fading value of the reflection intensity of the radar transmitted wave, and then use the characteristic information to identify the object to be identified, so that no additional hardware is needed to improve the identification of objects in front of the vehicle Accuracy to reduce false triggering of the automatic emergency braking system.
- An embodiment of the present invention also provides a vehicle, including a vehicle body and a millimeter wave radar installed on the vehicle body, and the millimeter wave radar may adopt the structure of each of the foregoing embodiments.
- the embodiment of the present invention also provides a computer storage medium in which program instructions are stored, and the program execution may include part or all of the steps of the object recognition method in the embodiment corresponding to FIG. 1.
- the program can be stored in a computer-readable storage medium, and the storage medium can include: Flash disk, read-only memory (Read-Only Memory, ROM), random access device (Random Access Memory, RAM), magnetic disk or optical disk, etc.
Landscapes
- Engineering & Computer Science (AREA)
- Radar, Positioning & Navigation (AREA)
- Remote Sensing (AREA)
- Physics & Mathematics (AREA)
- Computer Networks & Wireless Communication (AREA)
- General Physics & Mathematics (AREA)
- Electromagnetism (AREA)
- Radar Systems Or Details Thereof (AREA)
Abstract
提供了一种物体识别方法、毫米波雷达及车辆,其中物体识别方法包括:获取待识别物体的检测信息(101);根据该检测信息确定待识别物体的特征信息,该特征信息包括如下至少一种:对雷达发射波的距离-反射强度斜率,地面金属反射物评价值,对雷达发射波的反射强度衰落值(102);利用特征信息对待识别物体进行识别(103),可见,不需要增加额外的硬件即可提高对车辆前方物体识别的准确度,以减少自动紧急制动***的误触发。
Description
本发明涉及辅助驾驶技术领域,尤其涉及一种物体识别方法、毫米波雷达及车辆。
近年来高级辅助驾驶(Advanced Driver Assistant System,ADAS)技术和自动驾驶(Autonomous Driving,AD)技术发展迅速,毫米波雷达因其全天时、全天候、作用距离远、测速精度高等优点而被广泛使用到这些领域,然而区分地面金属反射物(例如窨井盖、高架桥上的金属地缝等)和静止车辆一直是车载毫米波雷达的问题与难点。目前绝大部分车载雷达厂商所生产的毫米波雷达都存在无法准确的区分地面金属反射物和静止车辆的弊端,以窨井盖和高架桥上的金属地缝为代表的地面金属反射物由于对雷达发射波的反射强烈且相对地面静止,因而很容易被检测到并被误识别为静止车辆,从而造成自动紧急制动***(Autonomous Emergency Braking,AEB)错误地启动等问题。
目前,为了准确地识别出地面金属反射物和静止车辆,通常可以采用如下方案,方案一:增加俯仰向接收通道,使得雷达具备俯仰向的测角能力,然而这样会增加天线设计的复杂度以及算法复杂度,需要增加雷达尺寸并选择计算能力更强的芯片,会显著增加雷达的硬件成本,降低雷达的安装便利性,而且由于地面金属反射物与车载雷达的俯仰夹角很小,因此即使使用上述方案也要在很近的距离才比较准确,使用场景较为受限;方案二:通过增加摄像头和雷达融合的方案来区分地面金属反射物和静止车辆,但是这样将大幅增加成本,并且摄像头在恶劣天气和光线不佳的环境下可靠性也会大幅下降,因此具有一定的局限性。可见,如何在不增加硬件成本的前提下,提高对车辆前方物体识别的准确度,以减少自动紧急制动***的误触发已成为亟待解决的问题。
发明内容
本发明实施例公开了一种物体识别方法、毫米波雷达及车辆,用于在不 增加硬件成本的前提下,提高对车辆前方物体识别的准确度,以减少自动紧急制动***的误触发。
本发明实施例第一方面公开了一种物体识别方法,应用于毫米波雷达,所述方法包括:
获取待识别物体的检测信息;
根据所述检测信息确定所述待识别物体的特征信息,所述特征信息包括如下至少一种:对雷达发射波的距离-反射强度斜率,地面金属反射物评价值,对雷达发射波的反射强度衰落值;
利用所述特征信息对所述待识别物体进行识别。
本发明实施例第二方面公开了一种毫米波雷达,所述毫米波雷达包括:处理器和存储器,其中:
所述存储器,用于存储有计算机程序,所述计算机程序包括程序指令;
所述处理器调用所述程序指令时用于执行:
获取待识别物体的检测信息;
根据所述检测信息确定所述待识别物体的特征信息,所述特征信息包括如下至少一种:对雷达发射波的距离-反射强度斜率,地面金属反射物评价值,对雷达发射波的反射强度衰落值;
利用所述特征信息对所述待识别物体进行识别。
本发明实施例第三方面公开了一种物体识别装置,应用于毫米波雷达,所述装置包括:
获取模块,用于获取待识别物体的检测信息;
确定模块,用于根据所述检测信息确定所述待识别物体的特征信息,所述特征信息包括如下至少一种:对雷达发射波的距离-反射强度斜率,地面金属反射物评价值,对雷达发射波的反射强度衰落值;
识别模块,用于利用所述特征信息对所述待识别物体进行识别。
本发明实施例第四方面公开了一种计算机可读存储介质,所述计算机可读存储介质存储有计算机程序,所述计算机程序被处理器执行时实现上述第一方面所述的物体识别方法。
本发明实施例可以获取待识别物体的检测信息,根据该检测信息确定待识 别物体的特征信息,待识别物体的特征信息可以包括如下至少一种:对雷达发射波的距离-反射强度斜率,地面金属反射物评价值,对雷达发射波的反射强度衰落值,进而利用该特征信息即可对待识别物体进行识别,从而不需要增加额外的硬件即可提高对车辆前方物体识别的准确度,以减少自动紧急制动***的误触发。
为了更清楚地说明本发明实施例中的技术方案,下面将对实施例中所需要使用的附图作简单地介绍,显而易见地,下面描述中的附图仅仅是本发明的一些实施例,对于本领域普通技术人员来讲,在不付出创造性劳动性的前提下,还可以根据这些附图获得其他的附图。
图1是本发明实施例公开的一种物体识别方法的流程示意图;
图2a是本发明实施例公开的一种雷达发射波的反射路径示意图;
图2b是本发明实施例公开的一种距离-反射强度特性曲线的示意图;
图2c是本发明实施例公开的另一种雷达发射波的反射路径示意图;
图2d是本发明实施例公开的另一种距离-反射强度特性曲线的示意图;
图2e是本发明实施例公开的一种利用状态机进行物体识别的流程示意图;
图3是本发明实施例公开的一种物体识别装置的结构示意图;
图4是本发明实施例公开的一种毫米波雷达的结构示意图。
下面将结合本发明实施例中的附图,对本发明实施例中的技术方案进行清楚、完整地描述,显然,所描述的实施例仅是本发明一部分实施例,而不是全部的实施例。基于本发明中的实施例,本领域普通技术人员在没有做出创造性劳动前提下所获得的所有其他实施例,都属于本发明保护的范围。
本发明实施例提供的物体识别方法可以应用到高级辅助驾驶、自动驾驶等场景中,用于提高对车辆前方物体识别的准确度,以减少自动紧急制动***的 误触发,并且不需要增加额外的硬件。
本发明实施例所描述的毫米波雷达具体可以是车载控制终端。
请参阅图1,为本发明实施例提供的一种物体识别方法的流程示意图。本实施例中所描述的物体识别方法可以包括以下步骤:
101、获取待识别物体的检测信息。
其中,该检测信息包括如下至少一种:待识别物体对雷达发射波的反射强度,与待识别物体的距离。
具体的,毫米波雷达可以对待识别物体周期性地进行检测,例如每隔500ms检测一次,即每隔500ms向待识别物体发射一次毫米波进行检测,并接收待识别物体的反射波,根据待识别物体对雷达发射波的反射情况可以确定待识别物体对雷达发射波的反射强度和/或与待识别物体的距离等检测信息。
102、根据所述检测信息确定所述待识别物体的特征信息,所述特征信息包括如下至少一种:对雷达发射波的距离-反射强度斜率,地面金属反射物评价值,对雷达发射波的反射强度衰落值。
具体的,毫米波雷达利用待识别物体的检测信息可以得到待识别物体的特征信息,特征信息反映了待识别物体在反射雷达发射波时的固有特性,特征信息具体可以包括:对雷达发射波的距离-反射强度斜率,地面金属反射物评价值和对雷达发射波的反射强度衰落值中的至少一种。
对于静止车辆而言,如图2a所示,是静止车辆对雷达发射波的反射路径示意图,可以看出,对于处于雷达前方的静止车辆,由于车辆离地面具有一定高度,所以其雷达反射波存在两条路径:一条沿着雷达发射波的方向返回,另一条经过地面折射后返回雷达,这一现象称为地面多径效应。
相应地,如图2b所示,是静止车辆的距离-反射强度特性曲线的示意图,可以看出,由于车辆存在地面多径效应,两条反射路径的能量是矢量叠加,因此随着距离的不同,静止车辆在距离-反射强度特性曲线中存在明显的反射强度衰落区。
对于地面金属反射物而言,如图2c所示,是地面金属反射物对雷达发射波的反射路径示意图,可以看出,由于地面金属反射物和地面之间几乎没有高度 差,所以只存在一条反射路径,即只有一条沿发射波的方向返回的路径,不存在经地面折射的反射路径。
相应地,如图2d所示,是地面金属反射物的距离-反射强度特性曲线的示意图,可以看出,由于地面金属反射物不存在地面多径效应,地面金属反射物的距离-反射强度特性曲线为明显的一条直线,不存在反射强度衰落区。
可见,由于地面多径效应的存在,待识别物体是静止车辆时对雷达发射波的反射特性,与待识别物体是地面金属反射物时对雷达发射波的反射特性存在明显差异,使得对雷达发射波的距离-反射强度斜率,地面金属反射物评价值,对雷达发射波的反射强度衰落值等特征信息能够用于对待识别物体是静止车辆还是地面金属反射物的准确识别。
103、利用所述特征信息对所述待识别物体进行识别。
具体的,毫米波雷达利用待识别物体对雷达发射波的距离-反射强度斜率,地面金属反射物评价值,对雷达发射波的反射强度衰落值等特征信息即可识别出待识别物体是静止车辆还是地面金属反射物。
本发明实施例中,毫米波雷达可以获取待识别物体的检测信息,根据该检测信息确定待识别物体的特征信息,待识别物体的特征信息可以包括如下至少一种:对雷达发射波的距离-反射强度斜率,地面金属反射物评价值,对雷达发射波的反射强度衰落值,进而利用该特征信息即可对待识别物体进行识别,利用地面金属反射物与静止车辆的地面多径效应的不同特性来区分地面金属反射物与静止车辆,从而不需要增加额外的硬件即可提高对车辆前方物体识别的准确度,以减少自动紧急制动***的误触发。
可选的,毫米波雷达利用特征信息对待识别物体进行识别的具体方式可以是:毫米波雷达引入状态机,利用特征信息和状态机判定待识别物体是否为静止车辆,状态机包括静止车辆待定、静止车辆确定、地面金属反射物待定和地面金属反射物确定四种状态,也就说根据特征信息确定待识别物体满足状态机的哪个状态,进而做出待识别物体是否是静止车辆的判定,四种状态中包括“待定”和“确定”,假设待识别物体是静止车辆,则至少需要经过静止车辆待定—>静止车辆确定这一判定过程,可见,判定过程更为科学、严谨,这进一步 提高了对车辆前方物体识别的准确度。
可选的,毫米波雷达确定待识别物体对雷达发射波的距离-反射强度斜率以及地面金属反射物评价值的具体方式可以是:毫米波雷达根据待识别物体对雷达发射波的反射强度以及与待识别物体的距离计算待识别物体对雷达发射波的距离-反射强度斜率,再根据待识别物体对雷达发射波的距离-反射强度斜率和第一斜率阈值确定出待识别物体的地面金属反射物评价值。
具体的,将待识别物体对雷达发射波的距离-反射强度斜率记为k
d-p,第i次检测得到的与待识别物体的距离记为D
i,第i次检测得到的待识别物体对雷达发射波的反射强度记为P
i,截止到当前时间已检测的次数记为n,即本次检测是第n次检测,则k
d-p的计算公式如下:
进一步的,将本次检测后得到的地面金属反射物评价值记为Manhole
n,上一次检测后得到的地面金属反射物评价值记为Manhole
n-1,地面金属反射物评价值增加量记为Manhole
add,地面金属反射物最大评价值记为Manhole
max,第一斜率阈值记为k
add_cri,地面金属反射物评价值减少量记为Manhole
minus,则毫米波雷达根据待识别物体对雷达发射波的距离-反射强度斜率和第一斜率阈值确定待识别物体的地面金属反射物评价值的具体方式可以是:
如果待识别物体对雷达发射波的距离-反射强度斜率k
d-p小于第一斜率阈值k
add_cri,则毫米波雷达可以利用地面金属反射物历史评价值(即上一次检测后得到的地面金属反射物评价值Manhole
n-1)、地面金属反射物评价值增加量Manhole
add和地面金属反射物最大评价值Manhole
max计算待识别物体的地面金属反射物评价值Manhole
n。其中,待识别物体的地面金属反射物评价值Manhole
n具体可以是地面金属反射物历史评价值Manhole
n-1与地面金属反射物评价值增加量Manhole
add之和以及地面金属反射物最大评价值Manhole
max中的较大值。
如果待识别物体对雷达发射波的距离-反射强度斜率k
d-p大于或等于第一斜率阈值k
add_cri,则毫米波雷达可以利用地面金属反射物历史评价值Manhole
n-1 和地面金属反射物评价值减少量Manhole
minus计算待识别物体的地面金属反射物评价值Manhole
n。其中,待识别物体的地面金属反射物评价值Manhole
n具体可以是地面金属反射物历史评价值Manhole
n-1与地面金属反射物评价值减少量Manhole
minus之差以及0中的较小值。
另外,结合图2b和图2d可知,地面金属反射物对雷达发射波的距离-反射强度斜率较为平缓、稳定,而静止车辆对雷达发射波的距离-反射强度斜率则较为陡峭、变化较大。
其中,待识别物体的地面金属反射物评价值Manhole
n的具体计算公式可以如下:
Manhole
n=max(Manhole
n-1+|Manhole
add|,Manhole
max)if k
d-p<k
add_cri
Manhole
n=min(Manhole
n-1-|Manhole
minus|,0)otherwise
可以理解的是,根据Manhole
n的具体计算公式可知,如果(if)待识别物体对雷达发射波的距离-反射强度斜率k
d-p较小,例如k
d-p小于第一斜率阈值k
add_cri,则按照地面金属反射物评价值增加量Manhole
add增加地面金属反射物历史评价值Manhole
n-1,将增加后的结果与地面金属反射物最大评价值Manhole
max比较,并取其中的较大值,即增加待识别物体是地面金属反射物的评分;否则(otherwise),即如果待识别物体对雷达发射波的距离-反射强度斜率k
d-p较大,例如k
d-p大于或等于第一斜率阈值k
add_cri,则按照地面金属反射物评价值减少量Manhole
minus减少地面金属反射物历史评价值Manhole
n-1,将减少后的结果与0比较,并取其中的较小值,即较少待识别物体是地面金属反射物的评分,距离-反射强度斜率k
d-p较大时将地面金属反射物评价值减小为0或者小于0的一个值。
其中,地面金属反射物评价值的初始值可以设为0,物体的地面金属反射物评价值为0或者小于0可视为该物体不是地面金属反射物,k
add_cri的具体取值与使用的雷达的特性相关,Manhole
add可以设为3分,Manhole
max可以设为7分,Manhole
minus可以设为1分,这些数值都可以根据实际需求和/或雷达特性进行设置。
可选的,毫米波雷达确定待识别物体对雷达发射波的反射强度衰落值的具 体方式可以是:毫米波雷达获取待识别物体对雷达发射波的反射强度极大值,再根据待识别物体对雷达发射波的反射强度和反射强度极大值计算待识别物体对雷达发射波的反射强度衰落值。
具体的,反射强度极大值是指已经检测到的多个反射强度中的最大值,将本次检测后得到的反射强度极大值记为Pmax
n,上一次检测后得到的反射强度极大值记为Pmax
n-1,本次检测得到的反射强度记为P
n,则反射强度极大值Pmax
n的具体计算公式可以如下:
Pmax
n=P
n if Pmax
n-1<P
n
Pmax
n=Pmax
n-1otherwise
可见,如果(if)上一次检测后得到的反射强度极大值记为Pmax
n-1小于本次检测得到的反射强度P
n,则将P
n作为Pmax
n;否则(otherwise),即Pmax
n-1大于或等于P
n,则将Pmax
n-1作为Pmax
n,从而可以计算出本次检测后得到的反射强度极大值Pmax
n。
进一步的,将本次检测后得到的反射强度极大值Pmax
n与本次检测得到的反射强度P
n作差即可得到待识别物体对雷达发射波的反射强度衰落值,将本次检测后得到的反射强度衰落值记为Pgap
n,则反射强度衰落值Pgap
n的具体计算公式可以如下:
Pgap
n=Pmax
n-P
n
可选的,毫米波雷达利用特征信息和状态机判定待识别物体是否为静止车辆的具体方式可以是:毫米波雷达将状态机的初始状态设为静止车辆待定,如果反射强度衰落值Pgap
n大于反射强度衰落阈值(记为Pgap
cri),或者,距离-反射强度斜率k
d-p大于第二斜率阈值(记为k
car_cri),则毫米波雷达将状态机的状态从静止车辆待定切换为静止车辆确定,并判定待识别物体为静止车辆。
可选的,毫米波雷达将状态机的初始状态设为静止车辆待定,如果地面金属反射物评价值Manhole
n大于第一评价阈值(记为Manhole
on),则毫米波雷达将状态机的状态从静止车辆待定切换为地面金属反射物待定,如果距离(记为D
n)小于距离阈值(记为D
cri),则毫米波雷达将状态机的状态从地面金属反射物待定切换为地面金属反射物确定,并判定待识别物体为地面金属反射物。
可选的,毫米波雷达将状态机的初始状态设为静止车辆待定,如果地面金属反射物评价值Manhole
n大于第一评价阈值Manhole
on,则毫米波雷达将状态机的状态从静止车辆待定切换为地面金属反射物待定,毫米波雷达更新地面金属反射物评价值,若更新后的地面金属反射物评价值小于第二评价阈值(记为Manhole
off),则将状态机的状态从地面金属反射物待定切换为静止车辆待定,接着更新反射强度衰落值和距离-反射强度斜率,若更新后的反射强度衰落值大于反射强度衰落阈值Pgap
cri,或者,更新后的距离-反射强度斜率大于第二斜率阈值k
car_cri,则将状态机的状态从静止车辆待定切换为静止车辆确定,并判定待识别物体为静止车辆。
可选的,如图2e所示,是一种利用状态机进行物体识别的流程示意图,对应的转换条件如下表所示。
其中,反射强度衰落阈值Pgap
cri可以设为20dB,距离阈值D
cri可以设为10m,转换条件d意味着如果雷达与待识别物体的距离已经很近,只剩10m了,但仍不能确定待识别物体是静止车辆,则将待识别物体判定为地面金属反射物。
当然,Pgap
cri和D
cri这些数值都可以根据实际需求和/或雷达特性进行设置。
可见,通过状态机的四种状态以及设置的转换条件,可以重充分利用地面金属反射物与静止车辆的地面多径效应的不同特性来区分地面金属反射物与静止车辆,从而不需要增加额外的硬件即可提高对车辆前方物体识别的准确度,以减少自动紧急制动***的误触发。
请参阅图3,为本发明实施例提供的一种物体识别装置的结构示意图。所述物体识别装置包括:
获取模块301,用于获取待识别物体的检测信息;
确定模块302,用于根据所述检测信息确定所述待识别物体的特征信息,所述特征信息包括如下至少一种:对雷达发射波的距离-反射强度斜率,地面金属反射物评价值,对雷达发射波的反射强度衰落值;
识别模块303,用于利用所述特征信息对所述待识别物体进行识别。
可选的,所述检测信息包括如下至少一种:所述待识别物体对雷达发射波的反射强度,与所述待识别物体的距离。
可选的,所述识别模块303,具体用于:
利用所述特征信息和状态机判定所述待识别物体是否为静止车辆,所述状态机包括静止车辆待定、静止车辆确定、地面金属反射物待定和地面金属反射物确定四种状态。
可选的,所述确定模块302,具体用于:
根据所述反射强度和所述距离计算所述待识别物体对所述雷达发射波的距离-反射强度斜率;
根据所述待识别物体对所述雷达发射波的距离-反射强度斜率和第一斜率阈值确定所述待识别物体的地面金属反射物评价值。
可选的,所述确定模块302,具体用于:
若所述待识别物体对所述雷达发射波的距离-反射强度斜率小于第一斜率阈值,则利用地面金属反射物历史评价值、地面金属反射物评价值增加量和地面金属反射物最大评价值计算所述待识别物体的地面金属反射物评价值。
可选的,所述待识别物体的地面金属反射物评价值为所述地面金属反射物历史评价值与所述地面金属反射物评价值增加量之和以及所述地面金属反射物最大评价值中的较大值。
可选的,所述确定模块302,具体用于:
若所述待识别物体对所述雷达发射波的距离-反射强度斜率大于或等于第一斜率阈值,则利用地面金属反射物历史评价值和地面金属反射物评价值减少量计算所述待识别物体的地面金属反射物评价值。
可选的,所述待识别物体的地面金属反射物评价值为所述地面金属反射物历史评价值与所述地面金属反射物评价值减少量之差以及0中的较小值。
可选的,所述确定模块302,具体用于:
获取所述待识别物体对雷达发射波的反射强度极大值;
根据所述待识别物体对雷达发射波的反射强度和所述反射强度极大值计算所述待识别物体对雷达发射波的反射强度衰落值。
可选的,所述识别模块303,具体用于:
将状态机的初始状态设为静止车辆待定;
若所述反射强度衰落值大于反射强度衰落阈值,或者,所述距离-反射强度斜率大于第二斜率阈值,则将所述状态机的状态从静止车辆待定切换为静止车辆确定,并判定所述待识别物体为静止车辆。
可选的,所述识别模块303,具体还用于:
若所述地面金属反射物评价值大于第一评价阈值,则将所述状态机的状态从静止车辆待定切换为地面金属反射物待定;
若所述距离小于距离阈值,则将所述状态机的状态从地面金属反射物待定切换为地面金属反射物确定,并判定所述待识别物体为地面金属反射物。
可选的,所述识别模块303,具体还用于:
若所述地面金属反射物评价值大于第一评价阈值,则将所述状态机的状态从静止车辆待定切换为地面金属反射物待定;
更新所述地面金属反射物评价值,若更新后的地面金属反射物评价值小于第二评价阈值,则将所述状态机的状态从地面金属反射物待定切换为静止车辆待定;
更新所述反射强度衰落值和所述距离-反射强度斜率,若更新后的反射强度衰落值大于所述反射强度衰落阈值,或者,更新后的距离-反射强度斜率大于所述第二斜率阈值,则将所述状态机的状态从静止车辆待定切换为静止车辆确定,并判定所述待识别物体为静止车辆。
可以理解的是,本发明实施例的物体识别装置的各功能模块的功能可根据上述方法实施例中的方法具体实现,其具体实现过程可以参照上述方法实施例的相关描述,此处不再赘述。
本发明实施例中,获取模块301可以获取待识别物体的检测信息,确定模块302根据该检测信息确定待识别物体的特征信息,待识别物体的特征信息可以包括如下至少一种:对雷达发射波的距离-反射强度斜率,地面金属反射物评价值,对雷达发射波的反射强度衰落值,进而识别模块303利用该特征信息即可对待识别物体进行识别,从而不需要增加额外的硬件即可提高对车辆前方物体识别的准确度,以减少自动紧急制动***的误触发。
请参阅图4,为本发明实施例提供的毫米波雷达的结构示意图。本实施例中所描述的毫米波雷达,包括:处理器401和存储器402。上述处理器401和存储器402通过总线连接。
上述处理器401可以是中央处理单元(Central Processing Unit,CPU),该处理器还可以是其他通用处理器、数字信号处理器(Digital Signal Processor,DSP)、专用集成电路(Application Specific Integrated Circuit,ASIC)、现成可编程门阵列(Field-Programmable Gate Array,FPGA)或者其他可编程逻辑器件、分立门或者晶体管逻辑器件、分立硬件组件等。通用处理器可以是微处理器或者该处理器也可以是任何常规的处理器等。
上述存储器402可以包括只读存储器和随机存取存储器,并向处理器401提供程序指令和数据。存储器402的一部分还可以包括非易失性随机存取存储器。其中,所述处理器401调用所述程序指令时用于执行:
获取待识别物体的检测信息;
根据所述检测信息确定所述待识别物体的特征信息,所述特征信息包括如下至少一种:对雷达发射波的距离-反射强度斜率,地面金属反射物评价值,对雷达发射波的反射强度衰落值;
利用所述特征信息对所述待识别物体进行识别。
可选的,所述检测信息包括如下至少一种:所述待识别物体对雷达发射波的反射强度,与所述待识别物体的距离。
可选的,所述处理器401,具体用于:
利用所述特征信息和状态机判定所述待识别物体是否为静止车辆,所述状态机包括静止车辆待定、静止车辆确定、地面金属反射物待定和地面金属反射 物确定四种状态。
可选的,所述处理器401,具体用于:
根据所述反射强度和所述距离计算所述待识别物体对所述雷达发射波的距离-反射强度斜率;
根据所述待识别物体对所述雷达发射波的距离-反射强度斜率和第一斜率阈值确定所述待识别物体的地面金属反射物评价值。
可选的,所述处理器401,具体用于:
若所述待识别物体对所述雷达发射波的距离-反射强度斜率小于第一斜率阈值,则利用地面金属反射物历史评价值、地面金属反射物评价值增加量和地面金属反射物最大评价值计算所述待识别物体的地面金属反射物评价值。
可选的,所述待识别物体的地面金属反射物评价值为所述地面金属反射物历史评价值与所述地面金属反射物评价值增加量之和以及所述地面金属反射物最大评价值中的较大值。
可选的,所述处理器401,具体用于:
若所述待识别物体对所述雷达发射波的距离-反射强度斜率大于或等于第一斜率阈值,则利用地面金属反射物历史评价值和地面金属反射物评价值减少量计算所述待识别物体的地面金属反射物评价值。
可选的,所述待识别物体的地面金属反射物评价值为所述地面金属反射物历史评价值与所述地面金属反射物评价值减少量之差以及0中的较小值。
可选的,所述处理器401,具体用于:
获取所述待识别物体对雷达发射波的反射强度极大值;
根据所述待识别物体对雷达发射波的反射强度和所述反射强度极大值计算所述待识别物体对雷达发射波的反射强度衰落值。
可选的,所述处理器401,具体用于:
将状态机的初始状态设为静止车辆待定;
若所述反射强度衰落值大于反射强度衰落阈值,或者,所述距离-反射强度斜率大于第二斜率阈值,则将所述状态机的状态从静止车辆待定切换为静止车辆确定,并判定所述待识别物体为静止车辆。
可选的,所述处理器401,具体用于:
若所述地面金属反射物评价值大于第一评价阈值,则将所述状态机的状态从静止车辆待定切换为地面金属反射物待定;
若所述距离小于距离阈值,则将所述状态机的状态从地面金属反射物待定切换为地面金属反射物确定,并判定所述待识别物体为地面金属反射物。
可选的,所述处理器401,具体用于:
若所述地面金属反射物评价值大于第一评价阈值,则将所述状态机的状态从静止车辆待定切换为地面金属反射物待定;
更新所述地面金属反射物评价值,若更新后的地面金属反射物评价值小于第二评价阈值,则将所述状态机的状态从地面金属反射物待定切换为静止车辆待定;
更新所述反射强度衰落值和所述距离-反射强度斜率,若更新后的反射强度衰落值大于所述反射强度衰落阈值,或者,更新后的距离-反射强度斜率大于所述第二斜率阈值,则将所述状态机的状态从静止车辆待定切换为静止车辆确定,并判定所述待识别物体为静止车辆。
具体实现中,本发明实施例中所描述的处理器401和存储器402可执行本发明实施例图1提供的物体识别方法中所描述的实现方式,也可执行本发明实施例图3所描述的物体识别装置的实现方式,在此不再赘述。
本发明实施例中,处理器401可以获取待识别物体的检测信息,根据该检测信息确定待识别物体的特征信息,待识别物体的特征信息可以包括如下至少一种:对雷达发射波的距离-反射强度斜率,地面金属反射物评价值,对雷达发射波的反射强度衰落值,进而利用该特征信息即可对待识别物体进行识别,从而不需要增加额外的硬件即可提高对车辆前方物体识别的准确度,以减少自动紧急制动***的误触发。
本发明实施例还提供了一种车辆,包括车体以及安装在所述车体的毫米波雷达,所述毫米波雷达可以采用上述各个实施例的构造。
本发明实施例还提供了一种计算机存储介质,该计算机存储介质中存储有程序指令,所述程序执行时可包括如图1对应实施例中的物体识别方法的部分或全部步骤。
需要说明的是,对于前述的各个方法实施例,为了简单描述,故将其都表述为一系列的动作组合,但是本领域技术人员应该知悉,本发明并不受所描述的动作顺序的限制,因为依据本申请,某一些步骤可以采用其他顺序或者同时进行。其次,本领域技术人员也应该知悉,说明书中所描述的实施例均属于优选实施例,所涉及的动作和模块并不一定是本申请所必须的。
本领域普通技术人员可以理解上述实施例的各种方法中的全部或部分步骤是可以通过程序来指令相关的硬件来完成,该程序可以存储于一计算机可读存储介质中,存储介质可以包括:闪存盘、只读存储器(Read-Only Memory,ROM)、随机存取器(Random Access Memory,RAM)、磁盘或光盘等。
以上对本发明实施例所提供的一种物体识别方法、毫米波雷达及车辆进行了详细介绍,本文中应用了具体个例对本发明的原理及实施方式进行了阐述,以上实施例的说明只是用于帮助理解本发明的方法及其核心思想;同时,对于本领域的一般技术人员,依据本发明的思想,在具体实施方式及应用范围上均会有改变之处,综上所述,本说明书内容不应理解为对本发明的限制。
Claims (25)
- 一种物体识别方法,应用于毫米波雷达,其特征在于,所述方法包括:获取待识别物体的检测信息;根据所述检测信息确定所述待识别物体的特征信息,所述特征信息包括如下至少一种:对雷达发射波的距离-反射强度斜率,地面金属反射物评价值,对雷达发射波的反射强度衰落值;利用所述特征信息对所述待识别物体进行识别。
- 根据权利要求1所述的方法,其特征在于,所述检测信息包括如下至少一种:所述待识别物体对雷达发射波的反射强度,与所述待识别物体的距离。
- 根据权利要求1或2所述的方法,其特征在于,所述利用所述特征信息对所述待识别物体进行识别,包括:利用所述特征信息和状态机判定所述待识别物体是否为静止车辆,所述状态机包括静止车辆待定、静止车辆确定、地面金属反射物待定和地面金属反射物确定四种状态。
- 根据权利要求2或3所述的方法,其特征在于,所述根据所述检测信息确定所述待识别物体的特征信息,包括:根据所述反射强度和所述距离计算所述待识别物体对所述雷达发射波的距离-反射强度斜率;根据所述待识别物体对所述雷达发射波的距离-反射强度斜率和第一斜率阈值确定所述待识别物体的地面金属反射物评价值。
- 根据权利要求4所述的方法,其特征在于,所述根据所述待识别物体对所述雷达发射波的距离-反射强度斜率和第一斜率阈值确定所述待识别物体的地面金属反射物评价值,包括:若所述待识别物体对所述雷达发射波的距离-反射强度斜率小于第一斜率阈值,则利用地面金属反射物历史评价值、地面金属反射物评价值增加量和地 面金属反射物最大评价值计算所述待识别物体的地面金属反射物评价值。
- 根据权利要求5所述的方法,其特征在于,所述待识别物体的地面金属反射物评价值为所述地面金属反射物历史评价值与所述地面金属反射物评价值增加量之和以及所述地面金属反射物最大评价值中的较大值。
- 根据权利要求4所述的方法,其特征在于,所述根据所述待识别物体对所述雷达发射波的距离-反射强度斜率和第一斜率阈值确定所述待识别物体的地面金属反射物评价值,包括:若所述待识别物体对所述雷达发射波的距离-反射强度斜率大于或等于第一斜率阈值,则利用地面金属反射物历史评价值和地面金属反射物评价值减少量计算所述待识别物体的地面金属反射物评价值。
- 根据权利要求7所述的方法,其特征在于,所述待识别物体的地面金属反射物评价值为所述地面金属反射物历史评价值与所述地面金属反射物评价值减少量之差以及0中的较小值。
- 根据权利要求2或3所述的方法,其特征在于,所述根据所述检测信息确定所述待识别物体的特征信息,包括:获取所述待识别物体对雷达发射波的反射强度极大值;根据所述待识别物体对雷达发射波的反射强度和所述反射强度极大值计算所述待识别物体对雷达发射波的反射强度衰落值。
- 根据权利要求3所述的方法,其特征在于,所述利用所述特征信息和状态机判定所述待识别物体是否为静止车辆,包括:将状态机的初始状态设为静止车辆待定;若所述反射强度衰落值大于反射强度衰落阈值,或者,所述距离-反射强度斜率大于第二斜率阈值,则将所述状态机的状态从静止车辆待定切换为静止车辆确定,并判定所述待识别物体为静止车辆。
- 根据权利要求10所述的方法,其特征在于,所述方法还包括:若所述地面金属反射物评价值大于第一评价阈值,则将所述状态机的状态从静止车辆待定切换为地面金属反射物待定;若所述距离小于距离阈值,则将所述状态机的状态从地面金属反射物待定切换为地面金属反射物确定,并判定所述待识别物体为地面金属反射物。
- 根据权利要求10所述的方法,其特征在于,所述方法还包括:若所述地面金属反射物评价值大于第一评价阈值,则将所述状态机的状态从静止车辆待定切换为地面金属反射物待定;更新所述地面金属反射物评价值,若更新后的地面金属反射物评价值小于第二评价阈值,则将所述状态机的状态从地面金属反射物待定切换为静止车辆待定;更新所述反射强度衰落值和所述距离-反射强度斜率,若更新后的反射强度衰落值大于所述反射强度衰落阈值,或者,更新后的距离-反射强度斜率大于所述第二斜率阈值,则将所述状态机的状态从静止车辆待定切换为静止车辆确定,并判定所述待识别物体为静止车辆。
- 一种毫米波雷达,其特征在于,所述毫米波雷达包括:处理器和存储器,其中:所述存储器,用于存储有计算机程序,所述计算机程序包括程序指令;所述处理器调用所述程序指令时用于执行:获取待识别物体的检测信息;根据所述检测信息确定所述待识别物体的特征信息,所述特征信息包括如下至少一种:对雷达发射波的距离-反射强度斜率,地面金属反射物评价值,对雷达发射波的反射强度衰落值;利用所述特征信息对所述待识别物体进行识别。
- 根据权利要求13所述的毫米波雷达,其特征在于,所述检测信息包括 如下至少一种:所述待识别物体对雷达发射波的反射强度,与所述待识别物体的距离。
- 根据权利要求13或14所述的毫米波雷达,其特征在于,所述处理器,具体用于:利用所述特征信息和状态机判定所述待识别物体是否为静止车辆,所述状态机包括静止车辆待定、静止车辆确定、地面金属反射物待定和地面金属反射物确定四种状态。
- 根据权利要求14或15所述的毫米波雷达,其特征在于,所述处理器,具体用于:根据所述反射强度和所述距离计算所述待识别物体对所述雷达发射波的距离-反射强度斜率;根据所述待识别物体对所述雷达发射波的距离-反射强度斜率和第一斜率阈值确定所述待识别物体的地面金属反射物评价值。
- 根据权利要求16所述的毫米波雷达,其特征在于,所述处理器,具体用于:若所述待识别物体对所述雷达发射波的距离-反射强度斜率小于第一斜率阈值,则利用地面金属反射物历史评价值、地面金属反射物评价值增加量和地面金属反射物最大评价值计算所述待识别物体的地面金属反射物评价值。
- 根据权利要求17所述的毫米波雷达,其特征在于,所述待识别物体的地面金属反射物评价值为所述地面金属反射物历史评价值与所述地面金属反射物评价值增加量之和以及所述地面金属反射物最大评价值中的较大值。
- 根据权利要求16所述的毫米波雷达,其特征在于,所述处理器,具体用于:若所述待识别物体对所述雷达发射波的距离-反射强度斜率大于或等于第 一斜率阈值,则利用地面金属反射物历史评价值和地面金属反射物评价值减少量计算所述待识别物体的地面金属反射物评价值。
- 根据权利要求19所述的毫米波雷达,其特征在于,所述待识别物体的地面金属反射物评价值为所述地面金属反射物历史评价值与所述地面金属反射物评价值减少量之差以及0中的较小值。
- 根据权利要求14或15所述的毫米波雷达,其特征在于,所述处理器,具体用于:获取所述待识别物体对雷达发射波的反射强度极大值;根据所述待识别物体对雷达发射波的反射强度和所述反射强度极大值计算所述待识别物体对雷达发射波的反射强度衰落值。
- 根据权利要求15所述的毫米波雷达,其特征在于,所述处理器,具体用于:将状态机的初始状态设为静止车辆待定;若所述反射强度衰落值大于反射强度衰落阈值,或者,所述距离-反射强度斜率大于第二斜率阈值,则将所述状态机的状态从静止车辆待定切换为静止车辆确定,并判定所述待识别物体为静止车辆。
- 根据权利要求22所述的毫米波雷达,其特征在于,所述处理器,具体还用于:若所述地面金属反射物评价值大于第一评价阈值,则将所述状态机的状态从静止车辆待定切换为地面金属反射物待定;若所述距离小于距离阈值,则将所述状态机的状态从地面金属反射物待定切换为地面金属反射物确定,并判定所述待识别物体为地面金属反射物。
- 根据权利要求22所述的毫米波雷达,其特征在于,所述处理器,具体还用于:若所述地面金属反射物评价值大于第一评价阈值,则将所述状态机的状态从静止车辆待定切换为地面金属反射物待定;更新所述地面金属反射物评价值,若更新后的地面金属反射物评价值小于第二评价阈值,则将所述状态机的状态从地面金属反射物待定切换为静止车辆待定;更新所述反射强度衰落值和所述距离-反射强度斜率,若更新后的反射强度衰落值大于所述反射强度衰落阈值,或者,更新后的距离-反射强度斜率大于所述第二斜率阈值,则将所述状态机的状态从静止车辆待定切换为静止车辆确定,并判定所述待识别物体为静止车辆。
- 一种车辆,应用于毫米波雷达,其特征在于,所述车辆包括:车体;权利要求1~24任一项所述的毫米波雷达,安装在所述车体上。
Priority Applications (2)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
PCT/CN2019/093707 WO2020258253A1 (zh) | 2019-06-28 | 2019-06-28 | 一种物体识别方法、毫米波雷达及车辆 |
CN201980030581.4A CN112119329A (zh) | 2019-06-28 | 2019-06-28 | 一种物体识别方法、毫米波雷达及车辆 |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
PCT/CN2019/093707 WO2020258253A1 (zh) | 2019-06-28 | 2019-06-28 | 一种物体识别方法、毫米波雷达及车辆 |
Publications (1)
Publication Number | Publication Date |
---|---|
WO2020258253A1 true WO2020258253A1 (zh) | 2020-12-30 |
Family
ID=73799392
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
PCT/CN2019/093707 WO2020258253A1 (zh) | 2019-06-28 | 2019-06-28 | 一种物体识别方法、毫米波雷达及车辆 |
Country Status (2)
Country | Link |
---|---|
CN (1) | CN112119329A (zh) |
WO (1) | WO2020258253A1 (zh) |
Families Citing this family (2)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
KR20220010900A (ko) * | 2020-07-20 | 2022-01-27 | 현대모비스 주식회사 | 차량용 레이더 장치 및 제어방법 |
CN113030976B (zh) * | 2021-03-10 | 2023-06-06 | 奥特酷智能科技(南京)有限公司 | 一种利用激光雷达消除金属井盖对毫米波雷达干扰的方法 |
Citations (9)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
US6377205B1 (en) * | 1997-11-21 | 2002-04-23 | Celsiustech Electronics A.B. | Method and device for classifying overhead objects |
US6404328B1 (en) * | 2000-10-24 | 2002-06-11 | Delphi Technologies, Inc. | Discrimination of detected objects in a vehicle path |
CN1459028A (zh) * | 2001-03-19 | 2003-11-26 | 富士通天株式会社 | 雷达的路上静止物体探测方法 |
CN102725653A (zh) * | 2010-01-28 | 2012-10-10 | 丰田自动车株式会社 | 障碍物检测装置 |
JP2012215489A (ja) * | 2011-04-01 | 2012-11-08 | Mitsubishi Electric Corp | レーダ装置 |
CN103424740A (zh) * | 2012-05-18 | 2013-12-04 | 丰田自动车株式会社 | 物体判定设备、防撞辅助设备及物体判定方法 |
CN103832438A (zh) * | 2012-11-20 | 2014-06-04 | 株式会社电装 | 对象类型确定设备 |
CN104115027A (zh) * | 2012-01-30 | 2014-10-22 | 丰田自动车株式会社 | 周边物体检测设备和周边物体检测方法 |
CN107615090A (zh) * | 2015-05-29 | 2018-01-19 | 三菱电机株式会社 | 雷达信号处理装置 |
-
2019
- 2019-06-28 CN CN201980030581.4A patent/CN112119329A/zh active Pending
- 2019-06-28 WO PCT/CN2019/093707 patent/WO2020258253A1/zh active Application Filing
Patent Citations (9)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
US6377205B1 (en) * | 1997-11-21 | 2002-04-23 | Celsiustech Electronics A.B. | Method and device for classifying overhead objects |
US6404328B1 (en) * | 2000-10-24 | 2002-06-11 | Delphi Technologies, Inc. | Discrimination of detected objects in a vehicle path |
CN1459028A (zh) * | 2001-03-19 | 2003-11-26 | 富士通天株式会社 | 雷达的路上静止物体探测方法 |
CN102725653A (zh) * | 2010-01-28 | 2012-10-10 | 丰田自动车株式会社 | 障碍物检测装置 |
JP2012215489A (ja) * | 2011-04-01 | 2012-11-08 | Mitsubishi Electric Corp | レーダ装置 |
CN104115027A (zh) * | 2012-01-30 | 2014-10-22 | 丰田自动车株式会社 | 周边物体检测设备和周边物体检测方法 |
CN103424740A (zh) * | 2012-05-18 | 2013-12-04 | 丰田自动车株式会社 | 物体判定设备、防撞辅助设备及物体判定方法 |
CN103832438A (zh) * | 2012-11-20 | 2014-06-04 | 株式会社电装 | 对象类型确定设备 |
CN107615090A (zh) * | 2015-05-29 | 2018-01-19 | 三菱电机株式会社 | 雷达信号处理装置 |
Also Published As
Publication number | Publication date |
---|---|
CN112119329A (zh) | 2020-12-22 |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
CN109870680B (zh) | 一种目标分类方法及装置 | |
JP5870908B2 (ja) | 車両の衝突判定装置 | |
US20180162392A1 (en) | Vehicle control apparatus and vehicle control method | |
JP5835243B2 (ja) | 物標認識装置 | |
US8514124B2 (en) | Method for operating a radar system in the event of possible concealment of the target object and radar system for performing the method | |
US11119210B2 (en) | Vehicle control device and vehicle control method | |
WO2021207954A1 (zh) | 一种目标识别的方法和装置 | |
WO2020186420A1 (zh) | 一种目标检测方法、设备、毫米波雷达及可移动平台 | |
US10539418B2 (en) | Target detection apparatus and method | |
US7714769B2 (en) | Method for estimating the width of radar objects | |
WO2020258253A1 (zh) | 一种物体识别方法、毫米波雷达及车辆 | |
US10482332B2 (en) | Pedestrian determining apparatus for determining whether an object is a pedestrian crossing ahead of an own vehicle | |
JP6557923B2 (ja) | 車載レーダ装置及び領域検出方法 | |
CN113536850B (zh) | 基于77g毫米波雷达的目标物体大小测试方法和装置 | |
JPWO2007015288A1 (ja) | 軸ずれ量推定方法及び軸ずれ量推定装置 | |
US11892536B2 (en) | Object-detecting device | |
KR20210002959A (ko) | 자율주행차량의 차선변경 제어 장치 및 그 방법 | |
WO2017164337A1 (ja) | 搭載角度学習装置 | |
US6686868B2 (en) | Radar ranging device for performing merging process on a plurality of detected targets | |
WO2021056434A1 (zh) | 一种探测对象的检测方法、探测设备及毫米波雷达 | |
US11841419B2 (en) | Stationary and moving object recognition apparatus | |
US20230168369A1 (en) | Driver Assistance System and Device and Method for Determining Object Status Parameter for Driver Assistance System | |
CN116699596A (zh) | 一种车辆的毫米波雷达的速度修正方法及装置 | |
US20220012492A1 (en) | Object detection device | |
US11983937B2 (en) | Intersecting road estimation device |
Legal Events
Date | Code | Title | Description |
---|---|---|---|
121 | Ep: the epo has been informed by wipo that ep was designated in this application |
Ref document number: 19935075 Country of ref document: EP Kind code of ref document: A1 |
|
NENP | Non-entry into the national phase |
Ref country code: DE |
|
122 | Ep: pct application non-entry in european phase |
Ref document number: 19935075 Country of ref document: EP Kind code of ref document: A1 |