WO2020133217A1 - 连续障碍物检测方法、设备、系统及存储介质 - Google Patents

连续障碍物检测方法、设备、系统及存储介质 Download PDF

Info

Publication number
WO2020133217A1
WO2020133217A1 PCT/CN2018/124887 CN2018124887W WO2020133217A1 WO 2020133217 A1 WO2020133217 A1 WO 2020133217A1 CN 2018124887 W CN2018124887 W CN 2018124887W WO 2020133217 A1 WO2020133217 A1 WO 2020133217A1
Authority
WO
WIPO (PCT)
Prior art keywords
cluster
current time
radar
continuous obstacle
target point
Prior art date
Application number
PCT/CN2018/124887
Other languages
English (en)
French (fr)
Inventor
王宇
林立
陈配涛
Original Assignee
深圳市大疆创新科技有限公司
Priority date (The priority date is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the date listed.)
Filing date
Publication date
Application filed by 深圳市大疆创新科技有限公司 filed Critical 深圳市大疆创新科技有限公司
Priority to CN201880069474.8A priority Critical patent/CN111316128A/zh
Priority to PCT/CN2018/124887 priority patent/WO2020133217A1/zh
Publication of WO2020133217A1 publication Critical patent/WO2020133217A1/zh
Priority to US17/202,322 priority patent/US20210261154A1/en

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
    • G01S13/88—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
    • B—PERFORMING OPERATIONS; TRANSPORTING
    • B60—VEHICLES IN GENERAL
    • B60W—CONJOINT CONTROL OF VEHICLE SUB-UNITS OF DIFFERENT TYPE OR DIFFERENT FUNCTION; CONTROL SYSTEMS SPECIALLY ADAPTED FOR HYBRID VEHICLES; ROAD VEHICLE DRIVE CONTROL SYSTEMS FOR PURPOSES NOT RELATED TO THE CONTROL OF A PARTICULAR SUB-UNIT
    • B60W30/00—Purposes of road vehicle drive control systems not related to the control of a particular sub-unit, e.g. of systems using conjoint control of vehicle sub-units
    • B60W30/18—Propelling the vehicle
    • B—PERFORMING OPERATIONS; TRANSPORTING
    • B60—VEHICLES IN GENERAL
    • B60W—CONJOINT CONTROL OF VEHICLE SUB-UNITS OF DIFFERENT TYPE OR DIFFERENT FUNCTION; CONTROL SYSTEMS SPECIALLY ADAPTED FOR HYBRID VEHICLES; ROAD VEHICLE DRIVE CONTROL SYSTEMS FOR PURPOSES NOT RELATED TO THE CONTROL OF A PARTICULAR SUB-UNIT
    • B60W60/00—Drive control systems specially adapted for autonomous road vehicles
    • B60W60/001—Planning or execution of driving tasks
    • 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
    • G01S13/58—Velocity or trajectory determination systems; Sense-of-movement determination systems
    • G01S13/583—Velocity or trajectory determination systems; Sense-of-movement determination systems using transmission of continuous unmodulated waves, amplitude-, frequency-, or phase-modulated waves and based upon the Doppler effect resulting from movement of targets
    • G01S13/584—Velocity or trajectory determination systems; Sense-of-movement determination systems using transmission of continuous unmodulated waves, amplitude-, frequency-, or phase-modulated waves and based upon the Doppler effect resulting from movement of targets adapted for simultaneous range and velocity measurements
    • 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
    • G01S13/58—Velocity or trajectory determination systems; Sense-of-movement determination systems
    • G01S13/60—Velocity or trajectory determination systems; Sense-of-movement determination systems wherein the transmitter and receiver are mounted on the moving object, e.g. for determining ground speed, drift angle, ground track
    • 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
    • G01S7/415—Identification of targets based on measurements of movement associated with the target
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06F—ELECTRIC DIGITAL DATA PROCESSING
    • G06F18/00—Pattern recognition
    • G06F18/20—Analysing
    • G06F18/23—Clustering techniques
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
    • G06V10/00—Arrangements for image or video recognition or understanding
    • G06V10/70—Arrangements for image or video recognition or understanding using pattern recognition or machine learning
    • G06V10/762—Arrangements for image or video recognition or understanding using pattern recognition or machine learning using clustering, e.g. of similar faces in social networks
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
    • G06V20/00—Scenes; Scene-specific elements
    • G06V20/50—Context or environment of the image
    • G06V20/56—Context or environment of the image exterior to a vehicle by using sensors mounted on the vehicle
    • G06V20/58—Recognition of moving objects or obstacles, e.g. vehicles or pedestrians; Recognition of traffic objects, e.g. traffic signs, traffic lights or roads
    • B—PERFORMING OPERATIONS; TRANSPORTING
    • B60—VEHICLES IN GENERAL
    • B60W—CONJOINT CONTROL OF VEHICLE SUB-UNITS OF DIFFERENT TYPE OR DIFFERENT FUNCTION; CONTROL SYSTEMS SPECIALLY ADAPTED FOR HYBRID VEHICLES; ROAD VEHICLE DRIVE CONTROL SYSTEMS FOR PURPOSES NOT RELATED TO THE CONTROL OF A PARTICULAR SUB-UNIT
    • B60W2420/00—Indexing codes relating to the type of sensors based on the principle of their operation
    • B60W2420/40—Photo, light or radio wave sensitive means, e.g. infrared sensors
    • B60W2420/403—Image sensing, e.g. optical camera
    • B—PERFORMING OPERATIONS; TRANSPORTING
    • B60—VEHICLES IN GENERAL
    • B60W—CONJOINT CONTROL OF VEHICLE SUB-UNITS OF DIFFERENT TYPE OR DIFFERENT FUNCTION; CONTROL SYSTEMS SPECIALLY ADAPTED FOR HYBRID VEHICLES; ROAD VEHICLE DRIVE CONTROL SYSTEMS FOR PURPOSES NOT RELATED TO THE CONTROL OF A PARTICULAR SUB-UNIT
    • B60W2420/00—Indexing codes relating to the type of sensors based on the principle of their operation
    • B60W2420/40—Photo, light or radio wave sensitive means, e.g. infrared sensors
    • B60W2420/408—Radar; Laser, e.g. lidar
    • 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
    • G01S13/06—Systems determining position data of a target
    • G01S13/42—Simultaneous measurement of distance and other co-ordinates
    • 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
    • G01S2013/9316—Radar or analogous systems specially adapted for specific applications for anti-collision purposes of land vehicles combined with communication equipment with other vehicles or with base stations
    • 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
    • G01S2013/932—Radar or analogous systems specially adapted for specific applications for anti-collision purposes of land vehicles using own vehicle data, e.g. ground speed, steering wheel direction

Definitions

  • Embodiments of the present invention relate to the field of vehicles, and in particular, to a continuous obstacle detection method, device, system, and storage medium.
  • millimeter wave radar is increasingly used in vehicles.
  • the vehicle is provided with a millimeter wave radar, and the millimeter wave radar is used to detect the environment around the vehicle.
  • millimeter wave radar presents the obstacles it detects in the form of dots. This form of presentation does not properly determine the continuous obstacles around the vehicle, such as roadsides, guardrails, fences, continuous stone piles, and so on. Therefore, it is necessary to provide a method to enable the millimeter wave radar to judge such boundary characteristics on the road.
  • Embodiments of the present invention provide a continuous obstacle detection method, device, system, and storage medium, so as to realize detection of continuous obstacles around a vehicle.
  • a first aspect of an embodiment of the present invention is to provide a continuous obstacle detection method, which is applied to a vehicle provided with a radar, the radar includes at least an antenna, and the antenna is used to receive an echo signal, and the method includes :
  • the continuous obstacle trajectory at the current time is determined according to the stationary target point detected by the radar at the current time.
  • a second aspect of an embodiment of the present invention is to provide a continuous obstacle detection system, including: a memory, a processor, and a radar; the radar includes at least an antenna, and the antenna is used to receive an echo signal;
  • the memory is used to store program codes
  • the processor calls the program code, and when the program code is executed, it is used to perform the following operations:
  • the continuous obstacle trajectory at the current time is determined according to the stationary target point detected by the radar at the current time.
  • a third aspect of the embodiments of the present invention is to provide a vehicle, including:
  • the power system is installed on the vehicle body to provide power
  • a fourth aspect of the embodiments of the present invention is to provide a computer-readable storage medium on which a computer program is stored, and the computer program is executed by a processor to implement the method of the first aspect.
  • the continuous obstacle detection method, device, system, and storage medium obtained the detection signal of the current time by acquiring the echo signal at the current time, and generate detection data at the current time according to the echo signal, according to the current time.
  • the detection data and the vehicle information of the vehicle at the current moment determine the stationary target point detected by the radar at the current moment, based on the stationary target point detected by the radar at the current moment , Determine the continuous obstacle trajectory at the current moment, thereby realizing the detection of continuous obstacles around the vehicle.
  • FIG. 1 is a schematic diagram of an application scenario provided by an embodiment of the present invention.
  • FIG. 2 is a flowchart of a continuous obstacle detection method provided by an embodiment of the present invention.
  • FIG. 3 is a schematic diagram of two-dimensional data provided by an embodiment of the present invention.
  • FIG. 4 is a flowchart of a filter process for a vehicle speed provided by an embodiment of the present invention.
  • FIG. 5 is a flowchart of detecting a stationary target point provided by an embodiment of the present invention.
  • FIG. 6 is a schematic diagram of a stationary target point provided by an embodiment of the present invention.
  • FIG. 7 is a schematic diagram of another stationary target point provided by an embodiment of the present invention.
  • FIG. 8 is a flowchart of a continuous obstacle detection method according to another embodiment of the present invention.
  • FIG. 9 is a schematic diagram of a vehicle own coordinate system provided by an embodiment of the present invention.
  • FIG. 10 is a schematic diagram of a clustering provided by an embodiment of the present invention.
  • FIG. 11 is a schematic diagram of a continuous obstacle track provided by an embodiment of the present invention.
  • FIG. 13 is a schematic diagram of a continuous obstacle trajectory at a current moment and a historical moment provided by another embodiment of the present invention.
  • FIG. 14 is a schematic diagram of a continuous obstacle trajectory at a current moment and a historical moment provided by another embodiment of the present invention.
  • 15 is a schematic diagram of another continuous obstacle track provided by an embodiment of the present invention.
  • 16 is a schematic diagram of another continuous obstacle track provided by an embodiment of the present invention.
  • 17 is a schematic diagram of a historical track point of a cluster point at a current moment and a continuous obstacle track at a historical moment provided by an embodiment of the present invention
  • FIG. 18 is a schematic diagram of another continuous obstacle track provided by an embodiment of the present invention.
  • FIG. 19 is a structural diagram of a continuous obstacle detection system provided by an embodiment of the present invention.
  • a component when a component is said to be “fixed” to another component, it can be directly on another component or there can also be a centered component. When a component is considered to be “connected” to another component, it can be directly connected to another component or there may be a centered component at the same time.
  • An embodiment of the present invention provides a continuous obstacle detection method.
  • the method is applied to a vehicle.
  • the vehicle is provided with a radar.
  • the radar includes at least an antenna, and the antenna is used to receive an echo signal.
  • the radar is a millimeter wave radar.
  • the vehicle 11 is driving in the right lane, and the vehicle 11 is provided with a radar, which may specifically be a millimeter wave radar.
  • the millimeter-wave radar may be a rear-mounted millimeter-wave radar, or a front-mounted millimeter-wave radar, or the millimeter-wave radar may also be integrated in the entire vehicle.
  • the radar may specifically be a frequency modulated continuous wave (FMCW) radar.
  • the FMCW radar may include an antenna, a radio frequency front end, a modulation module, and a signal processing unit.
  • the radio frequency front end is used to transmit a detection signal
  • the detection signal is a linear frequency modulation continuous wave, that is to say, the frequency of the detection signal transmitted by the FMCW radar is linearly modulated.
  • the modulation module is used to linearly modulate the frequency of the detection signal transmitted by the FMCW radar.
  • the antenna of the FMCW radar will receive the echo signal reflected by the object.
  • the signal processing unit of the FMCW radar can process the echo signal to obtain detection data.
  • the detection data includes at least one of the following: the energy of the target point detected by the radar, the distance, speed, and angle of the target point relative to the radar.
  • the FMCW radar can also be connected to a vehicle-mounted processor. After the antenna receives the echo signal, the signal processing unit of the FMCW radar performs analog-to-digital conversion on the echo signal, that is, the echo The wave signal is digitally sampled, and further, the sampled echo signal is sent to a vehicle-mounted processor, and the sampled echo signal is processed by the vehicle-mounted processor to obtain detection data.
  • the detection data may also be sent to the on-board processor.
  • the signal processing unit of the FMCW radar or the on-board processor can also determine continuous obstacles on the lane where the vehicle is located based on the detection data, and the continuous obstacles can be fences, guardrails, shoulders, and continuous stone piles on the lane Wait.
  • the execution subject of the continuous obstacle detection method is not limited, and may be a radar signal processing unit, a vehicle-mounted processor, or other than the radar signal processing unit and the vehicle-mounted processor
  • the device with data processing function such as the server 12 shown in FIG. 1, optionally, the vehicle 11 is further provided with a communication module, which may be a wired communication module or a wireless communication module.
  • the signal processing unit of the FMCW radar performs analog-to-digital conversion on the echo signal, that is, the echo signal
  • the vehicle 11 can send the echo signal sampled by the signal processing unit to the server 12 through the wireless communication module, and the server 12 processes the sampled echo signal to obtain probe data, and then obtains the probe data according to the probe data Identify continuous obstacles in the lane where the vehicle is located.
  • the vehicle 11 sends the detection data to the server 12 through the wireless communication module, and the server 12 determines the continuous obstacle in the lane where the vehicle is located based on the detection data Thing.
  • the continuous obstacle detection method will be described in detail below in conjunction with specific embodiments.
  • FIG. 2 is a flowchart of a continuous obstacle detection method provided by an embodiment of the present invention. As shown in FIG. 2, the method in this embodiment may include:
  • Step S201 Acquire the echo signal at the current time, and generate detection data at the current time according to the echo signal.
  • the execution subject of the method in this embodiment may be a radar signal processing unit, a vehicle-mounted processor, or a server 12 as shown in FIG. 1.
  • the radar signal processing unit is used as an example to introduce the continuous obstacle detection method in detail .
  • the antenna of the radar can receive echo signals in real time, and the signal processing unit of the radar can generate real-time detection data of the radar according to the echo signals received by the antenna in real time.
  • the signal processing unit obtains Receive the echo signal at all times, and perform analog-to-digital conversion on the echo signal, that is, digitally sample the echo signal, and further perform Fast Fourier Transformation (FFT) on the sampled echo signal.
  • FFT Fast Fourier Transformation
  • the signal processing unit may perform a two-dimensional FFT on the sampled echo signal, that is, an FFT in the velocity dimension and an FFT in the distance dimension, to obtain the detection data at the current moment.
  • the echo signals received by the antenna at different times are different. Therefore, the signal processing unit generates detection data at different times according to the echo signals received by the antenna at different times. Since the target points detected by the radar at different times may be different, the detection data at different times may be different.
  • the detection data includes at least one of the following: the energy of the target point detected by the radar, the distance, speed, and angle of the target point relative to the radar.
  • the detection data is two-dimensional data composed of a distance dimension and a velocity dimension.
  • the FMCW radar has multiple antennas.
  • each antenna of the multiple antennas may receive an echo signal.
  • the signal processing unit may Perform analog-to-digital conversion and two-dimensional FFT on the echo signals received by each antenna, to obtain two-dimensional data corresponding to each antenna composed of the distance dimension and speed dimension.
  • the corresponding two-dimensional data The two-dimensional data composed of the velocity dimension is multi-channel non-coherently accumulated to obtain detection data.
  • one antenna corresponds to one channel, and the detection data obtained after multi-channel incoherent accumulation is still two-dimensional data composed of a distance dimension and a velocity dimension.
  • the two-dimensional data obtained at different times may be different.
  • the two-dimensional data may specifically be an N*M matrix, that is, a matrix of N rows and M columns.
  • N*M matrix that is, a matrix of N rows and M columns.
  • the horizontal dimension represents the distance dimension
  • the vertical dimension represents the velocity dimension.
  • the velocity dimension includes N velocity units
  • the distance dimension includes M distance units, where N and M can be equal or unequal, and N and M are both greater than 1.
  • a point on the matrix can be used to represent a target point detected by the radar, the corresponding speed of the target point in the velocity dimension represents the movement speed of the target point relative to the radar, and the corresponding distance of the target point in the distance dimension represents The distance of the target point relative to the radar.
  • Step S202 Determine a stationary target point detected by the radar at the current time according to the detection data at the current time and vehicle information of the vehicle at the current time.
  • the energy of the target points at different positions is different, where the points in the black part represent the target points with energy greater than the preset energy threshold, and among the target points with energy greater than the preset energy threshold ,
  • Some target points may be stationary target points, and some target points may be moving target points or noise points, where the static target point may specifically be a target point that is stationary relative to the ground, and the moving target point may be specifically relative to the ground The target point of the movement.
  • the stationary target point in the target point may be determined according to the target point detected by the radar at the current moment, for example, the distance and speed of the target point with an energy greater than a preset energy threshold relative to the radar, and the vehicle information of the vehicle at the current moment .
  • the vehicle information of the vehicle includes at least one of the following: speed, steering, and yaw rate of the vehicle.
  • Radar is usually connected to the electronic and electrical systems on the vehicle through a communication bus to obtain vehicle information such as vehicle speed, steering, yaw rate, etc.
  • the radar can be connected to the vehicle through the (Controller Area Network, CAN) bus and obtain vehicle information from the CAN bus.
  • the radar can also process the echo signals received by the antenna to obtain vehicle information, such as the vehicle speed.
  • the radar obtains vehicle information through the CAN bus or through signal processing.
  • the acquired vehicle speed may also be filtered.
  • the specific filtering process is shown in FIG. 4 and includes the following steps S401- Step S411:
  • Step S401 It is determined whether it is timed out to obtain the vehicle speed from the CAN bus at the current moment. If yes, step S402 is executed; otherwise, step S403 is executed.
  • the radar obtains the vehicle speed from the CAN bus at the current time, and determines whether it is overtime to obtain the vehicle speed from the CAN bus at the current time.
  • Step S402 Perform signal processing on the echo signal at the current time to obtain a vehicle speed, and use the vehicle speed as a valid input.
  • the radar acquires the vehicle speed from the CAN bus at the current time, it will process the echo signal at the current time to obtain the vehicle speed, and use the vehicle speed as a valid input.
  • Step S403 The vehicle speed acquired from the CAN bus at the current time is used as a valid input.
  • the radar does not time out to obtain the vehicle speed from the CAN bus at the current time, the vehicle speed obtained from the CAN bus at the current time is used as a valid input.
  • Step S404 Calculate the error of the vehicle speed at the current moment.
  • step S405 it is judged whether the error exceeds the error threshold. If yes, step S406 is executed; otherwise, step S410 is executed.
  • Step S406 the counter is increased by 1.
  • Step S407. Determine whether the value of the counter is greater than or equal to N. If yes, perform step S408; otherwise, perform step S409.
  • Step S408 Report an error and reset the trusted vehicle speed.
  • Step S409 Keep the credible vehicle speed unchanged.
  • Step S410 the counter is cleared.
  • Step S411 Filter the vehicle speed at the current time to update the reliable vehicle speed.
  • the effective input of the vehicle speed at time T0 is 10.5, and the error of 10.5 is less than the error threshold, then filtering is performed on 10.5 to obtain the reliable vehicle speed at time T0, for example 10.
  • the effective input of vehicle speed at time T1 is 10.3, and the error of 10.3 is less than the error threshold, then filter processing is performed on 10.3.
  • the credibility at T1 The vehicle speed is 10.2 and the counter is cleared at T1.
  • the counter is increased by 1, the counter value at T2 is 1, and 1 is less than N, and the trusted vehicle speed of 10.2 is maintained at this time.
  • the effective input of the vehicle speed at time T3 is 14, and the error of 14 exceeds the error threshold, and the counter is incremented again.
  • the counter value at time T3 is 2, and 2 is less than N. At this time, the trusted vehicle speed 10.2 is maintained unchanged.
  • the effective input of the vehicle speed at time T4 is 15, the error of 15 exceeds the error threshold, the counter is incremented by 1, the counter value at time T4 is 3, 3 is equal to N, at this time an error is reported and the trusted vehicle speed is reset, for example, it will be trusted The vehicle speed is reset to 15 as the valid input of the vehicle speed at T4. Subsequent processes are analogized in turn, and will not be repeated here.
  • the counter is cleared, and the newly input vehicle speed is filtered to obtain a new trusted vehicle speed.
  • the effective input of vehicle speed at time T4 is 10.4
  • the error of 10.4 is less than the error threshold
  • the counter is cleared, and 10.4 is filtered.
  • the credible vehicle speed at T4 is calculated, for example, 10.3, as shown in Table 2 below.
  • the credible vehicle speeds at different moments determined through the above steps may be used as the real vehicle speeds of the vehicles at different moments, and the true vehicle speeds of the vehicles may be used to determine the stationary target point.
  • the determining the stationary target point detected by the radar at the current time according to the detection data at the current time and the vehicle information of the vehicle at the current time includes: according to the vehicle at the current time The speed and the distance and speed of the target point detected by the radar at the current time relative to the radar determine the stationary target point detected by the radar at the current time.
  • the vehicle speed of the vehicle at the current moment may specifically be the reliable vehicle speed at the current moment determined by the method shown in FIG. 4, or may be an effective input of the vehicle speed at the current moment as shown in FIG. 4.
  • the stationary target point detected at the current moment includes: if the distance of the target point detected by the radar at the current moment relative to the radar is greater than a preset distance, comparing the speed of the target point relative to the radar And the speed of the vehicle at the current moment; if the difference between the speed of the target point relative to the radar and the speed of the vehicle at the current moment is less than a first preset difference, the target point It is determined as a stationary target point detected by the radar at the current time.
  • the target point Taking the point in the black part shown in FIG. 3, that is, the target point whose energy is greater than the preset energy threshold as an example, as shown in FIG. 5, first determine whether the distance of the target point from the radar is greater than the preset distance, if the target point is relatively If the distance to the radar is greater than the preset distance, the speed of the target point relative to the radar and the speed of the vehicle at the current time are compared, and further, the difference between the speed of the target point relative to the radar and the speed of the vehicle at the current time is determined Whether it is less than the first preset difference, if the difference between the speed of the target point relative to the radar and the speed of the vehicle at the current moment is less than the first preset difference, the target point is determined to be a stationary target point, otherwise, discarded The target point.
  • the distance and speed of the target point detected by the radar at the current time relative to the radar determine that the radar is in the
  • the stationary target point detected at the current time includes: if the distance of the target point detected by the radar at the current time relative to the radar is less than or equal to a preset distance, then according to the target point The angle of the radar to determine the equivalent ground speed of the target point; compare the equivalent ground speed of the target point and the speed of the vehicle at the current moment; if the equivalent ground speed of the target point and the current At the moment, the difference in the speed of the vehicle is less than the second preset difference, and then the target point is determined as a stationary target point detected by the radar at the current time.
  • the radar first determine whether the distance of the target point from the radar is greater than the preset distance, if the distance of the target point from the radar is less than or equal to the preset distance, then obtain the angle of the target point from the radar, and Based on the angle of the target point relative to the radar, the equivalent ground speed of the target point is calculated.
  • the velocity of the target point in the detected two-dimensional data is the component of the equivalent velocity in the radial direction with respect to the radar, so it can be calculated according to the detection speed of the target point and its angle with the radar Equivalent ground speed.
  • the target point is determined to be a stationary target point, otherwise, the target point is discarded.
  • a stationary target point among the target points whose energy is greater than the preset energy threshold may be determined.
  • the stationary target point is specifically shown in FIG. 6, wherein the stationary target point in the solid line frame 61 is a stationary target point closer to the radar. 62 indicates the speed line.
  • the stationary target point may be further filtered.
  • the stationary target point may be filtered according to the distance of the stationary target point relative to the radar. For example, removing stationary target points whose distance to the radar is less than the minimum distance threshold, and removing stationary target points whose distance to the radar is greater than the maximum distance threshold.
  • different radars have different field of view (FOV)
  • FOV field of view
  • different radars have different credibility at the same target point in the distance. For radars with narrower detection signal beams, they detect The reliability of the distant target point is high. For a radar with a wide detection signal beam, the reliability of the distant target point detected is low.
  • a maximum distance threshold can be set To remove stationary target points whose distance to the radar is greater than the maximum distance threshold.
  • a minimum distance threshold can be set to remove the distance from the radar that is less than the minimum distance threshold The stationary target point.
  • the stationary target point may be filtered according to the speed of the stationary target point relative to the radar.
  • the distance of the stationary target point in the solid line frame 61 with respect to the radar is less than the minimum distance threshold.
  • the distance between the stationary target point 63 and the stationary target point 64 shown in FIG. 6 with respect to the radar is greater than the maximum distance threshold.
  • a stationary target point as shown in FIG. 7 is obtained. It can be seen that by filtering the stationary target points, not only can the storage space required by the stationary target point and the amount of calculation be reduced, but also the probability of misjudgment of the stationary target point can be reduced, and the fitting of the continuous obstacle track can be improved. Precision.
  • the signal processing unit of the radar may also perform multiple frames on the stationary target point accumulation. For example, the signal processing unit determines 7 stationary target points at time t1 and 8 stationary target points at time t2 after time t1, and performs the stationary target point at time t1 according to the displacement of the vehicle from time t1 to time t2 Compensate and accumulate the static target point after compensation and the static target point determined at time t2 to increase the density of the static target point.
  • seven stationary target points are in order at 80 meters, 81 meters, 82 meters, 83 meters, 84 meters, 85 meters, and 86 meters in front of the vehicle.
  • the vehicle has moved 10 meters forward from time t1 to time t2, then the seven stationary target points are in front of the vehicle at time 70 meters, 71 meters, 72 meters, 73 meters, 74 meters, 75 meters, 76 meters Therefore, it is possible to accumulate the 7 stationary target points at time t1 after performing position compensation and the stationary target points determined at time t2.
  • Step S203 Determine the continuous obstacle track at the current time according to the stationary target point detected by the radar at the current time.
  • the stationary target points determined in the above steps can be used as the target points for fitting continuous obstacles. Specifically, according to the stationary target point determined at the current time, the continuous obstacle track at the current time is determined.
  • the determining the continuous obstacle track at the current time according to the stationary target point detected by the radar at the current time includes: according to the radar at the current time The detected stationary target point generates a continuous obstacle track at the current moment.
  • the continuous continuity at the current moment can be generated according to the stationary target point detected by the radar at the current moment. Obstacle track.
  • the determining the continuous obstacle trajectory at the current time according to the stationary target point detected by the radar at the current time includes: according to the radar at the current time The stationary target point detected at any time updates the continuous obstacle trajectory at the historical time to obtain the continuous obstacle trajectory at the current time.
  • a new trajectory is determined based on the stationary target point detected by the radar at the current moment, and the new trajectory and historical moment can be calculated
  • the matching degree of the continuous obstacle trajectory if the matching degree of the new trajectory and the continuous obstacle trajectory at the historical moment is greater than the preset matching degree, the new trajectory and the continuous obstacle trajectory at the historical moment can be carried out Correlation, so as to update the continuous obstacle trajectory at the historical moment to obtain the continuous obstacle trajectory at the current moment.
  • the method further includes: according to the current time Track of continuous obstacles to determine the boundary of the lane where the vehicle is located at the current moment.
  • the boundary of the lane where the vehicle is located can be further applied to the field of assisted driving or automatic driving.
  • Embodiments of the present invention provide a continuous obstacle detection method.
  • 8 is a flowchart of a continuous obstacle detection method according to another embodiment of the present invention. As shown in FIG. 8, on the basis of the foregoing embodiment, the generation of the continuous obstacle track at the current time according to the stationary target point detected by the radar at the current time may include:
  • Step S801 Perform clustering processing on the stationary target point detected by the radar at the current time to obtain a cluster at the current time.
  • clustering is performed on the stationary target points selected at the current time to obtain the cluster at the current time, and cluster 1 and cluster 2 shown in FIG. 7 are obtained.
  • the clustering algorithm may be a density-based clustering algorithm (Density-Based Spatial Clustering of Applications with Noise, DBSCAN, or Ordering Points to Identify The Clustering Structure, OPTICS, or DENsity-based CLUstEring (DENCLUE), Random Sampling Consensus Algorithm (Random Sample Consensus), etc.
  • DENCLUE Density-based CLUstEring
  • Random Sampling Consensus Algorithm Random Sampling Consensus Algorithm
  • Step S802 If the quality of the cluster at the current time is greater than a preset quality threshold, generate a continuous obstacle track at the current time according to the cluster at the current time.
  • the method further includes: according to at least one of the number of cluster points in the cluster at the current time, the length of the cluster, and the degree of matching between the cluster and vehicle information of the vehicle, The quality of the cluster at the current moment is determined.
  • the scoring basis may be the number of cluster points in the cluster, the length of the cluster, the vehicle information of the cluster and the vehicle At least one of the matching degrees, the higher the score, the better the quality of the cluster.
  • cluster 1 is scored according to at least one of the number of cluster points in cluster 1, the length of cluster 1, and the degree of matching between cluster 1 and vehicle information of the vehicle to obtain a score of 1.
  • the score 2 of cluster 2 is calculated.
  • the length of cluster 1 is larger than the length of cluster 2, and the cluster points of cluster 1 are relative to the radar
  • the speed is closer to the speed of the vehicle, so the score 1 of cluster 1 is greater than the score 2 of cluster 2, indicating that the quality of cluster 1 is higher than the quality of cluster 2, and the credibility of cluster 1 is higher than The credibility of cluster 2.
  • the target point detected by the radar can also be converted from the matrix composed of the distance dimension and the speed dimension into the vehicle's own coordinate system, as shown in Figure 9 is a schematic diagram of the vehicle's own coordinate system, where, X The axis direction indicates the traveling front of the vehicle, the Y axis direction indicates the right side direction of the vehicle, the Z axis direction indicates the direction perpendicular to the ground toward the center of the earth, or the Z axis direction indicates the direction perpendicular to the ground away from the center of the earth.
  • FIG. 10 The schematic diagram after converting the target point detected by the radar from the matrix composed of the distance dimension and the speed dimension to the vehicle's own coordinate system is specifically shown in Figure 10, where the black dots represent the stationary target points, and the stationary target points are clustered After the classification, two clusters as shown in FIG. 10 are obtained. After scoring the two clusters respectively according to the above method, a good cluster and an unqualified cluster can be determined. Among them, a good cluster is The score after scoring is greater than the preset score, that is, the cluster whose quality is greater than the preset quality threshold.
  • the unqualified cluster is a cluster whose score is less than the preset score, that is, the quality is less than the preset quality threshold. Among them, the cluster with larger score is also the cluster with higher credibility.
  • a good cluster shown in FIG. 10 is a cluster whose detection points are relatively continuous for the first time, and a continuous obstacle track at the current time can be generated according to the good cluster at the current time.
  • the continuous obstacle track That is the initial trajectory of the continuous obstacle.
  • the radar signal processing unit can continuously filter out new stationary target points and cluster the new stationary target points to obtain The new track of the continuous obstacle.
  • a possible implementation method of generating a continuous obstacle trajectory at the current time according to the good cluster at the current time is to perform parameter fitting on the current good cluster to obtain the parameters of the continuous obstacle trajectory at the current time Information, the parameter information can uniquely describe the continuous obstacle trajectory at the current moment, and the schematic diagram of the continuous obstacle trajectory can be specifically shown as the dotted line 110 shown in FIG. 11.
  • a polynomial fitting method is used to perform parameter fitting on the current good cluster, or a radius arc fitting method is used to perform parameter fitting on the current good cluster.
  • polynomial fitting methods can be divided into first-order fitting, second-order fitting, third-order fitting and so on.
  • the parameter information obtained after fitting the good cluster at the current time includes: 0-order coefficient, first-order coefficient, second-order coefficient, closest distance information and farthest distance information, among which Both the distance information and the farthest distance information refer to the distance relative to the radar or the vehicle.
  • the radius-arc fitting method is used to perform parameter fitting on the good cluster at the current moment, the parameter information obtained after the fitting includes: the position of the center of the circle, the radius, the starting radian, and the ending radian.
  • the continuous obstacle trajectory at the current time and/or parameters of the continuous obstacle trajectory may also be output.
  • the information displays the continuous obstacle trajectory such as the dashed line 110 in the display component on the vehicle or the display component of the server, and/or displays the parameter information of the continuous obstacle trajectory. Since the continuous obstacle trajectory at different times may be changed, the continuous obstacle trajectory displayed on the display component and/or the parameter information of the continuous obstacle trajectory are also constantly changing.
  • the cluster at the current time is obtained, if the quality of the cluster at the current time is greater than a preset For the quality threshold, a continuous obstacle trajectory at the current time is generated according to the cluster at the current time, and a method for establishing a continuous obstacle trajectory at the initial stage of detecting the continuous obstacle is realized.
  • Embodiments of the present invention provide a continuous obstacle detection method.
  • 12 is a flowchart of a continuous obstacle detection method according to another embodiment of the present invention.
  • the continuous obstacle trajectory may have been established at a historical moment. If the echo signal received by the radar antenna at the current moment is determined, the stationary target point detected by the radar at the current moment is determined Then, according to the stationary target point detected by the radar at the current time, the continuous obstacle trajectory at the historical time may be updated to obtain the continuous obstacle trajectory at the current time, as shown in FIG. 12 , Based on the stationary target point detected by the radar at the current time, updating the continuous obstacle trajectory at the historical time to obtain the continuous obstacle trajectory at the current time, which may include:
  • Step S1201 Perform clustering processing on the stationary target point detected by the radar at the current time to obtain the cluster at the current time.
  • the clustering in the dashed frame 130 is to cluster the stationary target points detected by the radar at the current time After the class is processed, the current cluster is obtained.
  • Step S1202 Calculate the matching degree between the cluster point in the cluster at the current time and the continuous obstacle track at the historical time.
  • the method before calculating the matching degree between the cluster point in the cluster at the current time and the continuous obstacle track at the historical time, the method further includes: according to the current time At least one of the number of cluster points in the cluster, the length of the cluster, and the degree of matching between the cluster and the vehicle information of the vehicle to determine the cluster’s Quality; correspondingly, the calculation of the matching degree between the cluster point in the cluster at the current time and the continuous obstacle track at the historical time includes: if the cluster at the current time If the quality is greater than the preset quality threshold, the matching degree between the cluster point in the cluster at the current time and the continuous obstacle track at the historical time is calculated.
  • the number of cluster points in the cluster and the cluster At least one of the length and the degree of matching between the cluster and the vehicle information of the vehicle, the cluster is scored, and if the score after the score is greater than the preset score, the quality of the cluster is greater than the preset quality threshold, further , Calculate the matching degree between the cluster and the continuous obstacle track at historical time.
  • the calculating the matching degree between the cluster point in the cluster at the current time and the continuous obstacle track at the historical time includes: according to the current time The distance of the cluster point in the cluster relative to the radar and the distance of the historical track point in the continuous obstacle trajectory at the historical time relative to the radar are calculated in the cluster at the current time The degree of matching between the cluster point of the and the continuous obstacle track at the historical moment; and/or according to the speed of the cluster point in the cluster at the current moment relative to the radar and the historical moment The historical track point in the continuous obstacle track is relative to the speed of the radar, and the matching degree between the cluster point in the cluster at the current time and the continuous obstacle track in the historical time is calculated.
  • the average distance of each cluster point from the radar is calculated. Based on the distance of each historical track point in the broken line 110 with respect to the radar from a continuous obstacle track at a historical moment, the average distance of each historical track point with respect to the radar is calculated. Further compare the average distance of each cluster point in the dashed box 130 with respect to the radar and the average distance of each historical track point with respect to the radar. If the difference between the two is less than the preset value, determine the cluster in the dashed box 130 The matching degree between the category point and the continuous obstacle track at the historical moment is greater than the preset matching degree.
  • a continuous obstacle track at a historical moment may be selected, for example, a plurality of historical track points in the dotted line 110 near the dotted frame 130.
  • the multiple historical track points are specifically points in white parts shown in FIG.
  • the The matching degree between the cluster point and the continuous obstacle track at the historical moment is not limited to calculating the dashed line by comparing the average speed of each cluster point in the dashed box 130 with respect to the radar and the continuous obstacle track of the historical moment, such as the average speed of each historical track point in the dashed line 110 with respect to the radar. The matching degree between the cluster point in block 130 and the continuous obstacle track at the historical moment.
  • the calculating the matching degree between the cluster point in the cluster at the current time and the continuous obstacle track at the historical time includes: The clustering performs parameter fitting to obtain the parameter information of the new trajectory corresponding to the cluster at the current time; according to the parameter information of the new trajectory corresponding to the cluster at the current time and the continuity of the historical time The parameter information of the obstacle trajectory calculates the matching degree between the cluster point in the cluster at the current time and the continuous obstacle trajectory at the historical time.
  • the cluster in the dotted frame 130 shown in FIG. 13 is obtained, and it is determined that the quality of the cluster is greater than the preset quality threshold It may be further possible to perform parameter fitting on the clusters in the dashed frame 130 to obtain parameter information of the new trajectory corresponding to the clusters in the dashed frame 130.
  • the new trajectory is specifically shown in the curve 150 shown in FIG. 15.
  • the parameter fitting of the cluster at the current time includes at least one of the following: a polynomial fitting method is used to perform parameter fitting on the cluster at the current time; a radius circle is used The arc fitting method performs parameter fitting on the cluster at the current time.
  • the process of parameter fitting the clusters in the dotted box 130 is the same as the process of fitting the dotted line 110, and will not be repeated here.
  • the second-order fitting method is used to perform parameter fitting on the clusters in the dotted frame 130, and the parameter information corresponding to the curve 150 may be obtained. Further, according to the parameter information corresponding to the curve 150 and the continuous obstacle trajectory at the historical time, such as the parameter information of the dashed line 110, the matching degree between the cluster point in the dashed frame 130 and the continuous obstacle trajectory at the historical time is calculated.
  • the parameter information corresponding to curve 150 includes 0th order coefficient, 1st order coefficient, 2nd order coefficient, nearest distance information and farthest distance information.
  • the parameter information of the continuous obstacle track at this historical moment also includes 0th order coefficient and first order Coefficient, second-order coefficient, closest distance information and farthest distance information, calculate the difference between the 0-order coefficient corresponding to curve 150 and the 0-order coefficient corresponding to the continuous obstacle track at this historical moment, and the first-order coefficient corresponding to curve 150
  • the difference between the first-order coefficient corresponding to the continuous obstacle trajectory at this historical moment, the difference between the second-order coefficient corresponding to the curve 150 and the second-order coefficient corresponding to the continuous obstacle trajectory at this historical moment, the closest corresponding to the curve 150 The difference between the distance information and the closest distance information corresponding to the continuous obstacle track at this historical moment, the difference between the longest distance information corresponding to the curve 150 and the longest distance information corresponding to the continuous obstacle track at this historical moment, if If the aforementioned difference values are all within the preset range, it is determined that the matching degree between the cluster point in the dotted frame 130 and the continuous obstacle track at the historical moment is greater than the preset matching degree.
  • Step S1203 If the matching degree between the cluster point in the cluster at the current moment and the continuous obstacle track at the historical moment is greater than a preset matching degree, then the cluster at the current moment The cluster point of is associated with the continuous obstacle track at the historical moment to obtain the continuous obstacle track at the current moment.
  • the cluster point in the dotted box 130 and the continuous obstacle track at the historical moment are, for example
  • the dotted line 110 is associated to obtain the continuous obstacle track at the current time.
  • the cluster point in the cluster at the current time is associated with the continuous obstacle track at the historical time to obtain the continuous obstacle track at the current time Including: obtaining the new trajectory corresponding to the cluster at the current time according to the cluster points in the cluster at the current time; and comparing the new trajectory and the location corresponding to the cluster at the current time Associating the continuous obstacle trajectory at the historical time to obtain the continuous obstacle trajectory at the current time, the continuous obstacle trajectory at the current time includes the new trajectory and the continuous obstacle trajectory at the historical time .
  • the curve 150 is a new track obtained from the cluster points in the dotted box 130, and the new track is continuous with the historical time Obstacle tracks such as dotted line 110 are associated to obtain a continuous obstacle track at the current time.
  • the continuous obstacle track at the current time includes the new track, that is, curve 150 and the continuous obstacle track at the historical time For example, the dotted line 110.
  • the new track is connected to the continuous obstacle track at the historical moment.
  • the continuous obstacles are not interrupted, or the continuous obstacles are not blocked.
  • the new trajectory, curve 150, and the continuous obstacle trajectory, such as the dashed line 110 at the historical time, are directly Connected, as shown in Figure 15.
  • the new track and the continuous obstacle track at the historical moment are not connected.
  • the new trajectory obtained according to the clustering of the current moment may not be consistent with the continuous obstacle trajectory of the historical moment Direct connection, as shown in Figure 16, but in this case, the new trajectory and the continuous obstacle trajectory at the historical moment are also related, but the continuous obstacle trajectory appears broken, the new trajectory is the curve 150 and The continuous obstacle track at the historical time, for example, the dashed line 110 together constitutes the continuous obstacle track at the current time.
  • the cluster point in the cluster at the current time and the continuous obstacle trajectory at the historical time are associated to obtain the continuous obstacle voyage at the current time
  • the track includes: associating the cluster point in the cluster at the current time with the historical track point in the continuous obstacle track at the historical time to obtain the continuous obstacle track at the current time
  • the track point of the current obstacle determine the track of the continuous obstacle at the current time according to the track point of the continuous obstacle at the current time.
  • the dots in the white part represent the continuous obstacle trajectory at the historical time, such as each historical trajectory point in the dotted line 110, and the cluster point in the dotted frame 130 and the continuous obstacle trajectory at the historical time
  • the cluster points in the dashed frame 130 and the continuous obstacle trajectories at historical times such as the historical trajectory points in the dashed line 110
  • the fitting method performs parameter fitting on the points in the set to obtain the parameter information of a new trajectory.
  • the new trajectory is the trajectory composed of curve 150 and dashed line 110 as shown in FIG. 15, A track can be used as a continuous obstacle track at the current moment.
  • the cluster obtained by clustering the static target points detected by the radar at the current time may not match the continuous obstacle track at historical time, and the quality of the cluster is greater than the preset quality Threshold, as shown in FIG. 18, the clustering in the dotted frame 180 is the clustering obtained by performing clustering on the stationary target point detected by the radar at the current time, and the dotted line 110 represents the continuous obstacle trajectory at historical time.
  • the matching degree between the cluster point in the dashed box 180 and the continuous obstacle track at the historical moment if the matching degree is determined to be less than the preset matching degree, the cluster point in the dashed box 180 and the continuous obstacle track at the historical moment cannot Correlation, at this time, a new track can be generated according to the cluster points in the dotted frame 180, for example, the dotted line 110 is the fence on the right, and the new track is the fence on the left.
  • the matching degree between the cluster and the continuous obstacle track at the historical moment it is necessary to calculate the matching degree between the cluster and the continuous obstacle track at the historical moment, and the new track corresponding to the cluster point in the dotted frame 180 To determine the association between the cluster and the continuous obstacle track at the historical moment or the new track.
  • the continuous obstacle trajectory at the historical moment cannot be associated with a new trajectory corresponding to the cluster at each moment in multiple moments after the historical moment, the The part of the continuous obstacle track that exceeds the radar detection range will gradually disappear.
  • the dashed line 110 represents the continuous obstacle trajectory at the historical time.
  • the new trajectory corresponding to the cluster point in the dashed frame 180 determined at the current time cannot be associated with the continuous obstacle trajectory at the historical time.
  • the continuous obstacle trajectory at this historical moment for example, the dashed line 110 has not been associated with the new trajectory many times, the dashed line 110 will gradually disappear as the vehicle continuously moves forward.
  • ⁇ represents the detection range of the radar. As the vehicle continues to move forward, the point in the dashed line 110 will gradually exceed the detection range of the radar. If the dashed line 110 is not associated with the new track multiple times, the dashed line 110 will gradually disappear.
  • the new trajectory corresponding to the cluster point in the dashed frame 180 will also continue with the vehicle Drive forward and disappear gradually.
  • the cluster at the current time is obtained, and the cluster point in the cluster at the current time is calculated The degree of matching with the continuous obstacle trajectory at the historical moment, if the matching degree between the cluster point in the cluster at the current moment and the continuous obstacle trajectory at the historical moment is greater than a preset matching degree, Then, the cluster point in the cluster at the current time is associated with the continuous obstacle track at the historical time to obtain the continuous obstacle track at the current time, so that the continuous obstacle track can be The vehicle is constantly updated as it travels.
  • An embodiment of the present invention provides a continuous obstacle detection system.
  • 19 is a structural diagram of a continuous obstacle detection system provided by an embodiment of the present invention.
  • the continuous obstacle detection system 190 includes: a memory 191, a processor 192, and a radar 193; wherein, the radar 193 is provided on the vehicle .
  • the continuous obstacle detection system 190 is specifically a radar system, and in this case, the processor 192 may specifically be a signal processing unit in the radar 193.
  • the continuous obstacle detection system 190 is specifically a radar-mounted vehicle.
  • the processor 192 may be an on-board processor.
  • the continuous obstacle detection system 190 is specifically a system composed of a vehicle equipped with radar and the server 12 shown in FIG. 1, and at this time, the processor 192 may be specifically shown in FIG. The processor of the server 12 shown.
  • the radar 193 includes at least an antenna, the antenna is used to receive an echo signal; the memory 191 is used to store the program code; the processor 192, calls the program code, and when the program code is executed, it is used to perform the following operations: Obtain the echo signal at the current time, and generate the detection data at the current time according to the echo signal; according to the detection data at the current time and the vehicle information of the vehicle at the current time, determine A stationary target point detected by the radar at the current time; and a continuous obstacle track at the current time is determined according to the stationary target point detected by the radar at the current time.
  • the processor 192 is also used to: according to the continuous obstacle at the current time Object track, determining the boundary of the lane where the vehicle is at the current moment.
  • the detection data includes at least one of the following: the energy of the target point detected by the radar, the distance, speed, and angle of the target point relative to the radar.
  • the vehicle information of the vehicle includes at least one of the following: speed, steering, and yaw rate of the vehicle.
  • the processor 192 determines, based on the detection data at the current time and the vehicle information of the vehicle at the current time, a stationary target point detected by the radar at the current time, specifically: The stationary target point detected by the radar at the current time is determined according to the speed of the vehicle at the current time and the distance and speed of the target point detected by the radar at the current time relative to the radar.
  • the processor 192 determines the radar at the current time according to the speed of the vehicle at the current time, the distance and speed of the target point detected by the radar at the current time relative to the radar When a stationary target point is detected, it is specifically used to: if the distance of the target point detected by the radar at the current time relative to the radar is greater than a preset distance, compare the target point to the radar Speed and the speed of the vehicle at the current moment; if the difference between the speed of the target point relative to the radar and the speed of the vehicle at the current moment is less than a first preset difference, the target The point is determined as a stationary target point detected by the radar at the current time.
  • the processor 192 determines the radar at the current time according to the speed of the vehicle at the current time, the distance and speed of the target point detected by the radar at the current time relative to the radar
  • a stationary target point it is specifically used to: if the distance of the target point detected by the radar at the current time with respect to the radar is less than or equal to a preset distance, according to the target point The angle of the radar to determine the equivalent ground speed of the target point; compare the equivalent ground speed of the target point and the speed of the vehicle at the current moment; if the equivalent ground speed of the target point and the current At the moment, the difference in the speed of the vehicle is less than the second preset difference, and then the target point is determined as a stationary target point detected by the radar at the current time.
  • the equivalent ground speed of the target point is the radial speed of the target point relative to the radar.
  • the processor 192 determines the continuous obstacle track at the current time according to the stationary target point detected by the radar at the current time, it is specifically used to: according to the radar at the current time The stationary target point detected at a time generates the continuous obstacle track at the current time.
  • the processor 192 when the processor 192 generates a continuous obstacle track at the current time according to the stationary target point detected by the radar at the current time, it is specifically used to: Performing clustering processing on the stationary target point detected at the time to obtain the cluster at the current time; if the quality of the cluster at the current time is greater than a preset quality threshold, according to the current time Clustering generates the continuous obstacle track at the current time.
  • the processor 192 before the processor 192 generates a continuous obstacle track at the current time according to the cluster at the current time, it is also used to: according to the number of cluster points in the cluster at the current time At least one of the number, the length of the cluster, and the degree of matching between the cluster and the vehicle information of the vehicle to determine the quality of the cluster at the current time.
  • the processor 192 determines the continuous obstacle track at the current time according to the stationary target point detected by the radar at the current time, it is specifically used to: according to the radar at the current time
  • the stationary target point detected at any time updates the continuous obstacle trajectory at the historical time to obtain the continuous obstacle trajectory at the current time.
  • the processor 192 updates the continuous obstacle trajectory at the historical time according to the static target point detected by the radar at the current time, to obtain the continuous obstacle trajectory at the current time, Specifically, it is used to perform clustering processing on the stationary target point detected by the radar at the current time to obtain a cluster at the current time; calculate a clustering point in the cluster at the current time The matching degree with the continuous obstacle track at the historical moment; if the matching degree between the cluster point in the cluster at the current moment and the continuous obstacle track at the historical moment is greater than a preset matching degree, Then, the cluster point in the cluster at the current time is associated with the continuous obstacle track at the historical time to obtain the continuous obstacle track at the current time.
  • the processor 192 calculates the matching degree between the cluster point in the cluster at the current time and the continuous obstacle track at the historical time, it is further used to: according to the At least one of the number of cluster points in the cluster, the length of the cluster, and the degree of matching between the cluster and the vehicle information of the vehicle to determine the quality of the cluster at the current moment; processing When calculating the matching degree between the cluster point in the cluster at the current time and the continuous obstacle track at the historical time, the device 192 is specifically used: if the quality of the cluster at the current time is greater than A preset quality threshold is calculated, and the matching degree between the cluster point in the cluster at the current time and the continuous obstacle track at the historical time is calculated.
  • the processor 192 calculates the matching degree between the cluster point in the cluster at the current time and the continuous obstacle track at the historical time, it is specifically used to: according to the The distance of the cluster point in the cluster relative to the radar and the distance of the historical track point in the continuous obstacle trajectory at the historical time relative to the radar are calculated in the cluster at the current time The degree of matching between the cluster point of the and the continuous obstacle track at the historical moment; and/or according to the speed of the cluster point in the cluster at the current moment relative to the radar and the historical moment The historical track point in the continuous obstacle track is relative to the speed of the radar, and the matching degree between the cluster point in the cluster at the current time and the continuous obstacle track in the historical time is calculated.
  • the processor 192 calculates the matching degree between the cluster point in the cluster at the current time and the continuous obstacle track at the historical time, it is specifically used to: Clustering to perform parameter fitting to obtain the parameter information of the new trajectory corresponding to the cluster at the current time; according to the parameter information of the new trajectory corresponding to the cluster at the current time and the continuous obstacle at the historical time The parameter information of the object trajectory calculates the matching degree between the cluster point in the cluster at the current time and the continuous obstacle trajectory at the historical time.
  • the processor 192 when the processor 192 performs parameter fitting on the cluster at the current time, it is specifically used for at least one of the following: a polynomial fitting method is used to perform parameter fitting on the cluster at the current time ; Using a radius arc fitting method to perform parameter fitting on the cluster at the current time.
  • the processor 192 associates the cluster point in the cluster at the current time with the continuous obstacle trajectory at the historical time to obtain the continuous obstacle trajectory at the current time, specifically It is used to: according to the cluster point in the cluster at the current time, obtain a new trajectory corresponding to the cluster at the current time; compare the new trajectory and all locations corresponding to the cluster at the current time Associating the continuous obstacle trajectory at the historical time to obtain the continuous obstacle trajectory at the current time, the continuous obstacle trajectory at the current time includes the new trajectory and the continuous obstacle trajectory at the historical time .
  • the new track is connected to the continuous obstacle track at the historical moment.
  • the new track and the continuous obstacle track at the historical moment are not connected.
  • the processor 192 associates the cluster point in the cluster at the current time with the continuous obstacle trajectory at the historical time to obtain the continuous obstacle trajectory at the current time, specifically Used to: associate the cluster point in the cluster at the current time with the historical track point in the continuous obstacle track at the historical time to obtain the continuous obstacle track at the current time Track point; determine the continuous obstacle track at the current time according to the track point of the continuous obstacle track at the current time.
  • the continuous obstacle trajectory at the historical time cannot be associated with a new trajectory corresponding to the cluster at each time in multiple times after the historical time, the continuous obstacle at the historical time The part of the track that exceeds the radar detection range will gradually disappear.
  • the radar is a millimeter wave radar.
  • An embodiment of the present invention provides a vehicle.
  • the vehicle includes a body, a power system, and the continuous obstacle detection system described in the above embodiments.
  • the power system is installed on the body to provide power.
  • the implementation mode and specific principle of the continuous obstacle detection system are consistent with the above embodiments, and will not be repeated here.
  • this embodiment also provides a computer-readable storage medium on which a computer program is stored, which is executed by a processor to implement the continuous obstacle detection method described in the above embodiment.
  • the disclosed device and method may be implemented in other ways.
  • the device embodiments described above are only schematic.
  • the division of the units is only a logical function division, and there may be other divisions in actual implementation, for example, multiple units or components may be combined or Can be integrated into another system, or some features can be ignored, or not implemented.
  • the displayed or discussed mutual coupling or direct coupling or communication connection may be indirect coupling or communication connection through some interfaces, devices or units, and may be in electrical, mechanical, or other forms.
  • the units described as separate components may or may not be physically separated, and the components displayed as units may or may not be physical units, that is, they may be located in one place, or may be distributed on multiple network units. Some or all of the units may be selected according to actual needs to achieve the purpose of the solution of this embodiment.
  • each functional unit in each embodiment of the present invention may be integrated into one processing unit, or each unit may exist alone physically, or two or more units may be integrated into one unit.
  • the above integrated unit can be implemented in the form of hardware, or in the form of hardware plus software functional units.
  • the above integrated unit implemented in the form of a software functional unit may be stored in a computer-readable storage medium.
  • the above software functional unit is stored in a storage medium, and includes several instructions to enable a computer device (which may be a personal computer, a server, or a network device, etc.) or a processor (processor) to perform the methods described in the embodiments of the present invention Partial steps.
  • the aforementioned storage media include: U disk, mobile hard disk, read-only memory (Read-Only Memory, ROM), random access memory (Random Access Memory, RAM), magnetic disk or optical disk and other media that can store program code .

Landscapes

  • Engineering & Computer Science (AREA)
  • Radar, Positioning & Navigation (AREA)
  • Remote Sensing (AREA)
  • Physics & Mathematics (AREA)
  • General Physics & Mathematics (AREA)
  • Theoretical Computer Science (AREA)
  • Computer Networks & Wireless Communication (AREA)
  • Multimedia (AREA)
  • Artificial Intelligence (AREA)
  • Computer Vision & Pattern Recognition (AREA)
  • Data Mining & Analysis (AREA)
  • Evolutionary Computation (AREA)
  • Electromagnetism (AREA)
  • Mechanical Engineering (AREA)
  • Transportation (AREA)
  • Automation & Control Theory (AREA)
  • Health & Medical Sciences (AREA)
  • Software Systems (AREA)
  • Medical Informatics (AREA)
  • General Health & Medical Sciences (AREA)
  • Databases & Information Systems (AREA)
  • Computing Systems (AREA)
  • Human Computer Interaction (AREA)
  • Life Sciences & Earth Sciences (AREA)
  • Bioinformatics & Cheminformatics (AREA)
  • Bioinformatics & Computational Biology (AREA)
  • Evolutionary Biology (AREA)
  • General Engineering & Computer Science (AREA)
  • Traffic Control Systems (AREA)
  • Radar Systems Or Details Thereof (AREA)

Abstract

一种连续障碍物检测方法、设备、系统及存储介质。所述方法通过获取当前时刻的所述回波信号，并根据所述回波信号生成所述当前时刻的探测数据（S201），根据所述当前时刻的所述探测数据和所述当前时刻所述车辆的车辆信息，确定所述雷达在所述当前时刻探测到的静止目标点（S202），根据所述雷达在所述当前时刻探测到的所述静止目标点，确定所述当前时刻的连续障碍物航迹（S203），从而实现了对车辆周围连续障碍物的检测。

Description

连续障碍物检测方法、设备、系统及存储介质 技术领域
本发明实施例涉及车辆领域，尤其涉及一种连续障碍物检测方法、设备、系统及存储介质。
背景技术
随着驾驶辅助技术、自动驾驶技术的发展，毫米波雷达越来越多地被使用在车辆上。毫米波雷达全天时、全天候、作用距离远、测速精度高等优点，弥补了超声波、摄像头等其他传感器的不足。现有技术中，车辆设置有毫米波雷达，毫米波雷达用于探测车辆周围的环境。
但是，目前还未出现能够使用毫米波雷达探测车辆周围连续障碍物的技术。通常毫米波雷达以点状的形式来呈现其探测到的障碍物，这种呈现形式并不能很好地判断车辆周围的连续障碍物，例如路沿、护栏、栅栏、连续石桩等等。因此，有必要提供一种方法，以使得毫米波雷达能够判断道路上这种边界性的特征。
发明内容
本发明实施例提供一种连续障碍物检测方法、设备、系统及存储介质，以实现对车辆周围连续障碍物的检测。
本发明实施例的第一方面是提供一种连续障碍物检测方法，应用于车辆，所述车辆设置有雷达，所述雷达至少包括天线，所述天线用于接收回波信号，所述方法包括：
获取当前时刻的所述回波信号，并根据所述回波信号生成所述当前时刻的探测数据；
根据所述当前时刻的所述探测数据和所述当前时刻所述车辆的车辆信息，确定所述雷达在所述当前时刻探测到的静止目标点；
根据所述雷达在所述当前时刻探测到的所述静止目标点，确定所述当前时刻的连续障碍物航迹。
本发明实施例的第二方面是提供一种连续障碍物检测系统，包括：存储器、处理器和雷达；所述雷达至少包括天线，所述天线用于接收回波信号；
所述存储器用于存储程序代码；
所述处理器，调用所述程序代码，当程序代码被执行时，用于执行以下操作：
获取当前时刻的所述回波信号，并根据所述回波信号生成所述当前时刻的探测数据；
根据所述当前时刻的所述探测数据和所述当前时刻所述车辆的车辆信息，确定所述雷达在所述当前时刻探测到的静止目标点；
根据所述雷达在所述当前时刻探测到的所述静止目标点，确定所述当前时刻的连续障碍物航迹。
本发明实施例的第三方面是提供一种车辆，包括：
车身；
动力系统，安装在所述车身，用于提供动力；
以及第二方面所述的连续障碍物检测系统。
本发明实施例的第四方面是提供一种计算机可读存储介质，其上存储有计算机程序，所述计算机程序被处理器执行以实现第一方面所述的方法。
本实施例提供的连续障碍物检测方法、设备、系统及存储介质，通过获取当前时刻的所述回波信号，并根据所述回波信号生成所述当前时刻的探测数据，根据所述当前时刻的所述探测数据和所述当前时刻所述车辆的车辆信息，确定所述雷达在所述当前时刻探测到的静止目标点，根据所述雷达在所述当前时刻探测到的所述静止目标点，确定所述当前时刻的连续障碍物航迹，从而实现了对车辆周围连续障碍物的检测。
附图说明
为了更清楚地说明本发明实施例中的技术方案，下面将对实施例描述中所需要使用的附图作一简单地介绍，显而易见地，下面描述中的附图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为本发明实施例提供的一种应用场景的示意图；
图2为本发明实施例提供的连续障碍物检测方法的流程图；
图3为本发明实施例提供的二维数据的示意图；
图4为本发明实施例提供的对车速进行滤波处理的流程图；
图5为本发明实施例提供的检测静止目标点的流程图；
图6为本发明实施例提供的一种静止目标点的示意图；
图7为本发明实施例提供的另一种静止目标点的示意图；
图8为本发明另一实施例提供的连续障碍物检测方法的流程图；
图9为本发明实施例提供的一种车辆自身坐标系的示意图；
图10为本发明实施例提供的一种聚类的示意图；
图11为本发明实施例提供的一种连续障碍物航迹的示意图；
图12为本发明另一实施例提供的连续障碍物检测方法的流程图；
图13为本发明另一实施例提供的当前时刻的聚类和历史时刻的连续障碍物航迹的示意图；
图14为本发明另一实施例提供的当前时刻的聚类和历史时刻的连续障碍物航迹的示意图；
图15为本发明实施例提供的另一种连续障碍物航迹的示意图；
图16为本发明实施例提供的再一种连续障碍物航迹的示意图；
图17为本发明实施例提供的当前时刻的聚类点和历史时刻的连续障碍物航迹的历史航迹点的示意图；
图18为本发明实施例提供的又一种连续障碍物航迹的示意图；
图19为本发明实施例提供的连续障碍物检测系统的结构图。
附图标记：
11：车辆；       12：服务器；        61：实线框；
62：车速线；     63：静止目标点；    64：静止目标点；
1：聚类；        2：聚类；           110：虚线；
130：虚线框；    150：曲线；         180：虚线框；
190：连续障碍物检测系统；            191：存储器；
192：处理器；    193：雷达。
具体实施方式
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地描述，显然，所描述的实施例仅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。
需要说明的是，当组件被称为“固定于”另一个组件，它可以直接在另一个组件上或者也可以存在居中的组件。当一个组件被认为是“连接”另一个组件，它可以是直接连接到另一个组件或者可能同时存在居中组件。
除非另有定义，本文所使用的所有的技术和科学术语与属于本发明的技术领域的技术人员通常理解的含义相同。本文中在本发明的说明书中所使用的术语只是为了描述具体的实施例的目的，不是旨在于限制本发明。本文所使用的术语“及/或”包括一个或多个相关的所列项目的任意的和所有的组合。
下面结合附图，对本发明的一些实施方式作详细说明。在不冲突的情况下，下述的实施例及实施例中的特征可以相互组合。
本发明实施例提供一种连续障碍物检测方法，该方法应用于车辆，所述车辆设置有雷达，所述雷达至少包括天线，所述天线用于接收回波信号。可选的，所述雷达为毫米波雷达。如图1所示，车辆11行驶在右侧车道中，该车辆11设置有雷达，该雷达具体可以是毫米波雷达。该毫米波雷达可以是后装的毫米波雷达，也可以是前装的毫米波雷达，或者，该毫米波雷达还可以集成在整车中。
在本实施例中，所述雷达具体可以是调频连续波(frequency modulated continuous wave，FMCW)雷达。FMCW雷达可包括天线、射频前端、调制模块及信号处理单元。其中，射频前端用于发射探测信号，该探测信号为线性调频连续波，也就是说，该FMCW雷达发射的探测信号的频率是被线性调制的。具体的，调制模块用于对该FMCW雷达发射的探测信号的频率进行线性调制。当FMCW雷达发射的探测信号被该车辆周围的物体反射后，该FMCW雷达的天线将接收到该物体反射的回波信号。该FMCW雷达的信号处理单元可以对该回波信号进行处理，得到探测数据。可选的， 所述探测数据包括如下至少一种：所述雷达探测到的目标点的能量、所述目标点相对于所述雷达的距离、速度、角度。
在一些实施例中，该FMCW雷达还可以与车载的处理器通信连接，当天线接收到回波信号后，由该FMCW雷达的信号处理单元对该回波信号进行模数转换，即对该回波信号进行数字采样，进一步，将采样后的回波信号发送给车载的处理器，由该车载的处理器对该采样后的回波信号进行处理，得到探测数据。
在另一些实施例中，当该FMCW雷达的信号处理单元对该回波信号进行处理，得到探测数据之后，还可以将该探测数据发送给车载的处理器。
进一步，该FMCW雷达的信号处理单元或车载的处理器还可以根据该探测数据，确定该车辆所在车道上的连续障碍物，该连续障碍物可以是车道上的栅栏、护栏、路肩、连续石桩等。
在其他实施例中，并不限定连续障碍物检测方法的执行主体，可以是雷达的信号处理单元，也可以是车载的处理器，还可以是除雷达的信号处理单元、车载的处理器之外的具有数据处理功能的设备，例如图1所示的服务器12，可选的，车辆11还设置有通信模块，该通信模块可以是有线通信模块，也可以是无线通信模块。以无线通信模块为例，当车辆11上的雷达例如FMCW雷达的天线接收到物体反射的回波信号后，FMCW雷达的信号处理单元对该回波信号进行模数转换，即对该回波信号进行数字采样，车辆11可将该信号处理单元采样后的回波信号通过该无线通信模块发送给服务器12，服务器12对该采样后的回波信号进行处理，得到探测数据之后，根据该探测数据确定该车辆所在车道上的连续障碍物。或者，FMCW雷达的信号处理单元或车载的处理器得到探测数据后，该车辆11将该探测数据通过该无线通信模块发送给服务器12，服务器12根据该探测数据确定该车辆所在车道上的连续障碍物。下面将结合具体的实施例对连续障碍物检测方法进行详细介绍。
图2为本发明实施例提供的连续障碍物检测方法的流程图。如图2所示，本实施例中的方法，可以包括：
步骤S201、获取当前时刻的所述回波信号，并根据所述回波信号生成 所述当前时刻的探测数据。
本实施例方法的执行主体可以是雷达的信号处理单元、车载的处理器或如图1所示的服务器12，可选的，以雷达的信号处理单元为例对连续障碍物检测方法进行详细介绍。
具体的，该雷达的天线可实时接收回波信号，该雷达的信号处理单元可根据该天线实时接收的回波信号，生成该雷达实时的探测数据，例如，该信号处理单元获取该天线在当前时刻接收到的回波信号，并对该回波信号进行模数转换，即对该回波信号进行数字采样，进一步对采样后的回波信号进行快速傅氏变换(Fast Fourier Transformation，FFT)，具体的，该信号处理单元可对该采样后的回波信号进行二维的FFT，即速度维的FFT和距离维的FFT，得到当前时刻的探测数据。可以理解，天线在不同时刻接收到的回波信号不同，因此，信号处理单元根据天线在不同时刻接收到的回波信号生成不同时刻的探测数据。由于雷达在不同时刻探测到的目标点可能是不同的，因此不同时刻的探测数据可能是不同的。
可选的，所述探测数据包括如下至少一种：所述雷达探测到的目标点的能量、所述目标点相对于所述雷达的距离、速度、角度。可选的，所述探测数据是由距离维度和速度维度构成的二维数据。
在一些实施例中，FMCW雷达的天线可能不止一个，例如，该FMCW雷达有多个天线，在同一时刻，该多个天线中的每个天线可能都会接收到回波信号，该信号处理单元可以对每个天线接收到的回波信号分别进行模数转换、二维FFT，得到每个天线对应的由距离维度和速度维度构成的二维数据，进一步，对每个天线对应的由距离维度和速度维度构成的二维数据进行多通道非相干累加，得到探测数据。可选的，一个天线对应一个通道，经过多通道非相干累加后得到的探测数据还是由距离维度和速度维度构成的二维数据。另外，不同时刻得到的二维数据可能是不同的。
在本实施例中，该二维数据具体可以是一个N*M的矩阵即N行M列的矩阵，如图3所示，横向表示距离维度，纵向表示速度维度，速度维度包括N个速度单元，距离维度包括M个距离单元，其中，N和M可以相等，也可以不等，N和M均大于1。该矩阵上的一个点可用于表示该雷达探测到的一个目标点，该目标点在速度维度上对应的速度表示该目标点相对于 雷达的运动速度，该目标点在距离维度上对应的距离表示该目标点相对于雷达的距离。
步骤S202、根据所述当前时刻的所述探测数据和所述当前时刻所述车辆的车辆信息，确定所述雷达在所述当前时刻探测到的静止目标点。
如图3所示，在该矩阵中，不同位置上的目标点的能量不同，其中，黑色部分的点表示能量大于预设能量门限的目标点，在该能量大于预设能量门限的目标点中，有些目标点可能是静止目标点，而有些目标点可能是运动目标点、或者是噪声点，其中，静止目标点具体可以是相对于地面静止的目标点，运动目标点具体可以是相对于地面运动的目标点。本实施例可根据当前时刻雷达探测到的目标点，例如能量大于预设能量门限的目标点相对于雷达的距离和速度，以及当前时刻该车辆的车辆信息，确定该目标点中的静止目标点。
可选的，所述车辆的车辆信息包括如下至少一种：所述车辆的速度、转向、横摆角速度。
雷达通常通过通信总线与车辆上的电子电气系统相连接以获取车辆车辆信息，例如，车辆的速度、转向、横摆角速度等。例如，该雷达可通过(Controller Area Network,CAN)总线接入车辆，并从CAN总线获取车辆的车辆信息。另外，该雷达也可以对天线接收到的回波信号进行信号处理得到车辆信息，例如车辆的车速。在本实施例中，雷达通过CAN总线或通过信号处理获取车辆信息，例如车速的过程中，还可以对获取到的车速进行滤波处理，具体滤波处理过程如图4所示，包括如下步骤S401-步骤S411：
步骤S401、判断当前时刻从CAN总线获取车速是否超时，如果是，则执行步骤S402，否则，执行步骤S403。
例如，该雷达在当前时刻从CAN总线获取车速，并判断当前时刻从CAN总线获取车速是否超时。
步骤S402、对当前时刻的回波信号进行信号处理得到车速，并将该车速作为有效输入。
如果该雷达当前时刻从CAN总线获取车速超时，则对当前时刻的回波信号进行信号处理得到车速，并将该车速作为有效输入。
步骤S403、将当前时刻从CAN总线获取的车速作为有效输入。
如果该雷达当前时刻从CAN总线获取车速不超时，则将当前时刻从CAN总线获取的车速作为有效输入。
步骤S404、计算当前时刻车速的误差。
步骤S405、判断该误差是否超出误差门限，是则执行步骤S406，否则执行步骤S410。
步骤S406、计数器加1。
步骤S407、判断计数器的值是否大于或等于N，是则执行步骤S408，否则执行步骤S409。
步骤S408、报错并重置可信的车速。
步骤S409、保持可信的车速不变。
步骤S410、计数器清零。
步骤S411、对当前时刻车速进行滤波处理，更新可信的车速。
例如，根据上述步骤S401-步骤S403确定的不同时刻车速的有效输入、以及不同时刻可信的车速之间的对应关系如下表1或表2所示：
表1
Figure PCTCN2018124887-appb-000001
例如，T0时刻车速的有效输入为10.5，10.5的误差小于误差门限，则对10.5进行滤波处理得到T0时刻的可信车速，例如为10。T1时刻车速的有效输入为10.3，10.3的误差小于误差门限，则对10.3进行滤波处理，具体的，根据T0时刻的可信车速10和T1时刻车速的有效输入10.3，计算得到T1时刻的可信车速10.2，T1时刻计数器清零。假设N＝3，T2时刻车速的有效输入为13，13的误差超出了误差门限，则计数器加1，T2时刻的计数器值为1，1小于N，此时保持可信车速10.2不变。T3时刻车速的有效输入为14，14的误差超出了误差门限，则计数器再加1，T3时刻的计数器值为2，2小于N，此时继续保持可信车速10.2不变。T4时刻车速的有效输入为15,15的误差超出了误差门限，则计数器再加1，T4时 刻的计数器值为3,3等于N，此时报错并重置可信车速，例如，将可信车速重置为T4时刻车速的有效输入即15。后续过程依次类推，不再赘述。
另外，如果计数器的值还未到N，输入了误差小于误差门限的车速，则计数器清零，并对新输入的车速进行滤波，得到新的可信车速。例如，T4时刻车速的有效输入为10.4，10.4的误差小于误差门限，则计数器清零，并对10.4进行滤波处理，具体的，根据T3时刻保持的可信车速10.2和T4时刻车速的有效输入10.4，计算得到T4时刻的可信车速，例如10.3，具体如下表2所示。
表2
Figure PCTCN2018124887-appb-000002
可选的，经过上述步骤确定出的不同时刻的可信车速，可作为不同时刻车辆的真实车速，该车辆的真实车速可用于确定静止目标点。
所述根据所述当前时刻的所述探测数据和所述当前时刻所述车辆的车辆信息，确定所述雷达在所述当前时刻探测到的静止目标点，包括：根据所述当前时刻所述车辆的速度、所述雷达在所述当前时刻探测到的目标点相对于所述雷达的距离和速度，确定所述雷达在所述当前时刻探测到的静止目标点。
如图3所示，根据当前时刻雷达探测到的目标点，例如能量大于预设能量门限的目标点相对于雷达的距离和速度，以及当前时刻该车辆的车速，确定该目标点中的静止目标点。其中，当前时刻该车辆的车速具体可以是通过如图4所示的方法确定的当前时刻的可信车速，也可以是如图4所示的当前时刻的车速的有效输入。
作为一种可能的方式，所述根据所述当前时刻所述车辆的速度、所述雷达在所述当前时刻探测到的目标点相对于所述雷达的距离和速度，确定所述雷达在所述当前时刻探测到的静止目标点，包括：若所述雷达在所述当前时刻探测到的目标点相对于所述雷达的距离大于预设距离，则比较所述目标点相对于所述雷达的速度和所述当前时刻所述车辆的速度；若所述 目标点相对于所述雷达的速度和所述当前时刻所述车辆的速度的差值小于第一预设差值，则将所述目标点确定为所述雷达在所述当前时刻探测到的静止目标点。
以图3所示的黑色部分的点即能量大于预设能量门限的目标点为例，如图5所示，先判断该目标点相对于雷达的距离是否大于预设距离，如果该目标点相对于雷达的距离大于预设距离，则比较该目标点相对于雷达的速度和当前时刻所述车辆的速度，进一步，判断该目标点相对于雷达的速度和当前时刻所述车辆的速度的差值是否小于第一预设差值，如果该目标点相对于雷达的速度和当前时刻所述车辆的速度的差值小于第一预设差值，则确定该目标点为静止目标点，否则，丢弃该目标点。
作为另一种可能的方式：所述根据所述当前时刻所述车辆的速度、所述雷达在所述当前时刻探测到的目标点相对于所述雷达的距离和速度，确定所述雷达在所述当前时刻探测到的静止目标点，包括：若所述雷达在所述当前时刻探测到的目标点相对于所述雷达的距离小于或等于预设距离，则根据所述目标点相对于所述雷达的角度，确定所述目标点的等效地速；比较所述目标点的等效地速和所述当前时刻所述车辆的速度；若所述目标点的等效地速和所述当前时刻所述车辆的速度的差值小于第二预设差值，则将所述目标点确定为所述雷达在所述当前时刻探测到的静止目标点。
如图5所示，先判断该目标点相对于雷达的距离是否大于预设距离，如果该目标点相对于雷达的距离小于或等于预设距离，则获取该目标点相对于雷达的角度，并根据该目标点相对于雷达的角度，计算该目标点的等效地速。可选的，所述目标点在探测得到的二维数据中的速度是等效地速在相对于所述雷达径向上的分量，因此可以根据目标点的探测速度与其与雷达的角度来计算其等效地速。进一步，比较该目标点的等效地速和当前时刻所述车辆的速度，并判断该目标点的等效地速和当前时刻所述车辆的速度的差值是否小于第二预设差值，如果该目标点的等效地速和当前时刻所述车辆的速度的差值小于第二预设差值，则确定该目标点为静止目标点，否则，丢弃该目标点。
例如，根据如图5所示的方法对图3所示的能量大于预设能量门限的每个目标点进行检测之后，可确定出该能量大于预设能量门限的目标点中 的静止目标点，该静止目标点具体如图6所示，其中，实线框61中的静止目标点是距离该雷达较近的静止目标点。62表示车速线。
在一些实施例中，在图6的基础上，还可以进一步对静止目标点进行过滤，具体的，可以根据静止目标点相对于雷达的距离，对静止目标点进行过滤。例如，去除相对于雷达的距离小于最小距离阈值的静止目标点，以及去除相对于雷达的距离大于最大距离阈值的静止目标点。由于不同的雷达，其视场角(Field of view，FOV)不同，因此，不同的雷达探测到的远处的同一目标点的可信度不同，对于探测信号波束较窄的雷达，其探测到的远处的目标点的可信度较高，对于探测信号波束较宽的雷达，其探测到的远处的目标点的可信度较低，因此，本实施例可设定一个最大距离阈值，去除相对于雷达的距离大于最大距离阈值的静止目标点。另外，当静止目标点相对于雷达的距离较近时，雷达接收到的回波信号中的杂波较多，本实施例可设定一个最小距离阈值，去除相对于雷达的距离小于最小距离阈值的静止目标点。此外，在其他实施例中，还可以根据静止目标点相对于雷达的速度，对静止目标点进行过滤。
如图6所示，实线框61中的静止目标点相对于雷达的距离小于最小距离阈值。如图6所示的静止目标点63和静止目标点64相对于雷达的距离大于最大距离阈值。去除实线框61中的静止目标点，以及静止目标点63和静止目标点64之后，得到如图7所示的静止目标点。可见，通过对静止目标点的过滤，不仅可以减小静止目标点所需的存储空间、降低计算量，还可以减小对静止目标点的误判概率，提高对连续障碍物航迹拟合的精度。
在另外一些实施例中，如果雷达的信号处理单元根据天线当前时刻接收到的回波信号，确定出的静止目标点的个数较少，则该信号处理单元还可以对静止目标点进行多帧累积。例如，信号处理单元在t1时刻确定出7个静止目标点，在t1时刻之后的t2时刻确定出8个静止目标点，根据该车辆从t1时刻到t2时刻的位移对t1时刻的静止目标点进行补偿，并将补偿后的静止目标点和t2时刻确定出的静止目标点进行累积，以提高静止目标点的密度。例如，在t1时刻7个静止目标点依次在车辆前方的80米、81米、82米、83米、84米、85米、86米处。该车辆从t1时刻到t2 时刻向前移动了10米，则在t2时刻该7个静止目标点依次在车辆前方的70米、71米、72米、73米、74米、75米、76米处，因此，可以将t1时刻的7个静止目标点进行位置补偿后和t2时刻确定出的静止目标点进行累积。
步骤S203、根据所述雷达在所述当前时刻探测到的所述静止目标点，确定所述当前时刻的连续障碍物航迹。
由于车道上的栅栏、护栏、路肩、连续石桩、或绿化带等连续障碍物是相对于地面静止的物体，因此，上述步骤确定出的静止目标点可作为拟合连续障碍物的目标点。具体的，根据当前时刻确定的静止目标点，确定当前时刻的连续障碍物航迹。
作为一种可能的方式，所述根据所述雷达在所述当前时刻探测到的所述静止目标点，确定所述当前时刻的连续障碍物航迹，包括：根据所述雷达在所述当前时刻探测到的所述静止目标点，生成所述当前时刻的连续障碍物航迹。
例如，在连续障碍物航迹建立的初期，还没有历史时刻的连续障碍物航迹，此时，可根据雷达在所述当前时刻探测到的所述静止目标点，生成所述当前时刻的连续障碍物航迹。
作为另一种可能的方式，所述根据所述雷达在所述当前时刻探测到的所述静止目标点，确定所述当前时刻的连续障碍物航迹，包括：根据所述雷达在所述当前时刻探测到的所述静止目标点，对历史时刻的连续障碍物航迹进行更新，得到所述当前时刻的连续障碍物航迹。
例如，在历史时刻已经建立该连续障碍物航迹，根据雷达在所述当前时刻探测到的所述静止目标点，确定出一段新的航迹，则可以计算该新的航迹和历史时刻的连续障碍物航迹的匹配度，如果该新的航迹和历史时刻的连续障碍物航迹的匹配度大于预设匹配度，则可以将新的航迹和历史时刻的连续障碍物航迹进行关联，从而对历史时刻的连续障碍物航迹进行更新，得到当前时刻的连续障碍物航迹。
在一些实施例中，所述根据所述雷达在所述当前时刻探测到的所述静止目标点，确定所述当前时刻的连续障碍物航迹之后，所述方法还包括：根据所述当前时刻的连续障碍物航迹，确定所述当前时刻所述车辆所在车 道的边界。该车辆所在车道的边界可进一步应用到辅助驾驶或自动驾驶领域中。
本实施例通过获取当前时刻的所述回波信号，并根据所述回波信号生成所述当前时刻的探测数据，根据所述当前时刻的所述探测数据和所述当前时刻所述车辆的车辆信息，确定所述雷达在所述当前时刻探测到的静止目标点，根据所述雷达在所述当前时刻探测到的所述静止目标点，确定所述当前时刻的连续障碍物航迹，从而实现了对车辆周围连续障碍物的检测。
本发明实施例提供一种连续障碍物检测方法。图8为本发明另一实施例提供的连续障碍物检测方法的流程图。如图8所示，在上述实施例的基础上，所述根据所述雷达在所述当前时刻探测到的所述静止目标点，生成所述当前时刻的连续障碍物航迹，可以包括：
步骤S801、对所述雷达在所述当前时刻探测到的所述静止目标点进行聚类处理，得到所述当前时刻的聚类。
例如，在图7的基础上，对当前时刻筛选出的静止目标点进行聚类处理，可得到当前时刻的聚类，得到如图7所示的聚类1和聚类2。
本实施例不限定聚类处理所采用的聚类算法，例如，聚类算法可以是基于密度的聚类算法(Density-Based Spatial Clustering of Applications with Noise，DBSCAN,或Ordering Points To Identify The Clustering Structure，OPTICS，或DENsity-based CLUstEring，DENCLUE)、随机抽样一致算法(Random Sample Consensus)等。
步骤S802、若所述当前时刻的所述聚类的质量大于预设质量门限，则根据所述当前时刻的所述聚类生成所述当前时刻的连续障碍物航迹。
在一些实施例中，所述若所述当前时刻的所述聚类的质量大于预设质量门限，则根据所述当前时刻的所述聚类生成所述当前时刻的连续障碍物航迹之前，所述方法还包括：根据所述当前时刻的所述聚类中聚类点的个数、所述聚类的长度、所述聚类与所述车辆的车辆信息的匹配度中的至少一个，确定所述当前时刻的所述聚类的质量。
例如，针对图7所示的聚类1和聚类2，分别进行打分，打分的依据可以是该聚类中聚类点的个数、该聚类的长度、该聚类与车辆的车辆信息 的匹配度中的至少一个，当该打分越高时，说明该聚类的质量越好。具体的，根据聚类1中的聚类点个数、聚类1的长度、聚类1与车辆的车辆信息的匹配度中的至少一个，对聚类1进行打分，得到分值1。同理，计算聚类2的分值2。由于聚类1中的聚类点的个数比聚类2中的聚类点的个数多，聚类1的长度比聚类2的长度大，聚类1的聚类点相对于雷达的速度更接近于车辆的车速，因此，聚类1的分值1大于聚类2的分值2，说明聚类1的质量要高于聚类2的质量，聚类1的可信度高于聚类2的可信度。
在一些实施例中，还可以将雷达探测到的目标点从由距离维度和速度维度构成的矩阵中转换到车辆自身坐标系中，如图9所示为车辆自身坐标系的示意图，其中，X轴方向表示车辆的行驶前方，Y轴方向表示车辆的右侧方向，Z轴方向表示垂直于地面指向地心的方向，或Z轴方向表示垂直于地面远离地心的方向。将雷达探测到的目标点从由距离维度和速度维度构成的矩阵中转换到车辆自身坐标系后的示意图具体如图10所示，其中，黑色的点表示静止目标点，对静止目标点进行聚类后得到如图10所示的两个聚类，根据上述方法对两个聚类分别进行打分后，可确定出一个好的聚类和一个不合格的聚类，其中，好的聚类是打分后的分值大于预设分值，即质量大于预设质量门限的聚类。不合格的聚类是打分后的分值小于预设分值，即质量小于预设质量门限的聚类。其中，分值越大的聚类也是可信度越高的聚类。例如图10所示的好的聚类是首次检测到的一个聚类点较为连续的聚类，则可以根据当前时刻好的聚类生成当前时刻的连续障碍物航迹，该连续障碍物航迹即为该连续障碍物的初始航迹，随着雷达天线不断的接收回波信号，雷达的信号处理单元可以不断的筛选出新的静止目标点，并对新的静止目标点进行聚类后得到该连续障碍物的新航迹。
具体的，根据当前时刻好的聚类生成当前时刻的连续障碍物航迹的一种可能实现方式是：对当前时刻好的聚类进行参数拟合，得到当前时刻的连续障碍物航迹的参数信息，该参数信息可唯一的描述当前时刻的连续障碍物航迹，该连续障碍物航迹的示意图具体可如图11所示的虚线110。
可选的，采用多项式拟合方法对当前时刻好的聚类进行参数拟合，或者采用半径圆弧拟合方法对当前时刻好的聚类进行参数拟合。其中，多项 式拟合方法可分为一阶拟合、二阶拟合、三阶拟合等。以二阶拟合为例，对当前时刻好的聚类进行参数拟合后得到的参数信息包括：0阶系数、一阶系数、二阶系数、最近距离信息和最远距离信息，其中，最近距离信息和最远距离信息均是指相对于雷达或车辆的距离。若采用半径圆弧拟合方法对当前时刻好的聚类进行参数拟合，则拟合后得到的参数信息包括：圆心位置、半径、起始弧度、终止弧度。
可选的，在根据所述当前时刻的所述聚类生成所述当前时刻的连续障碍物航迹之后，还可以输出当前时刻的连续障碍物航迹和/或该连续障碍物航迹的参数信息，如图11所示，在车载的显示组件或服务器的显示组件中显示该连续障碍物航迹例如虚线110，和/或显示该连续障碍物航迹的参数信息。由于不同时刻的连续障碍物航迹可能是变化的，则显示组件上显示的连续障碍物航迹和/或该连续障碍物航迹的参数信息也是不断变化的。
本实施例通过对所述雷达在所述当前时刻探测到的所述静止目标点进行聚类处理，得到所述当前时刻的聚类，若所述当前时刻的所述聚类的质量大于预设质量门限，则根据所述当前时刻的所述聚类生成所述当前时刻的连续障碍物航迹，实现了在检测到连续障碍物的初期，建立连续障碍物航迹的方法。
本发明实施例提供一种连续障碍物检测方法。图12为本发明另一实施例提供的连续障碍物检测方法的流程图。在上述实施例的基础上，历史时刻可能已经建立有该连续障碍物航迹，若根据当前时刻雷达天线接收到的回波信号，确定出雷达在所述当前时刻探测到的所述静止目标点后，可根据所述雷达在所述当前时刻探测到的所述静止目标点，对历史时刻的连续障碍物航迹进行更新，得到所述当前时刻的连续障碍物航迹，如图12所示，所述根据所述雷达在所述当前时刻探测到的所述静止目标点，对历史时刻的连续障碍物航迹进行更新，得到所述当前时刻的连续障碍物航迹，可以包括：
步骤S1201、对所述雷达在所述当前时刻探测到的所述静止目标点进行聚类处理，得到所述当前时刻的聚类。
如图13所示，假设虚线110所示的连续障碍物航迹是在历史时刻建立的连续障碍物航迹，虚线框130中的聚类是对雷达在当前时刻探测到的静止目标点进行聚类处理后，得到的当前时刻的聚类。
步骤S1202、计算所述当前时刻的所述聚类中的聚类点与所述历史时刻的连续障碍物航迹的匹配度。
在一些实施例中，所述计算所述当前时刻的所述聚类中的聚类点与所述历史时刻的连续障碍物航迹的匹配度之前，所述方法还包括：根据所述当前时刻的所述聚类中聚类点的个数、所述聚类的长度、所述聚类与所述车辆的车辆信息的匹配度中的至少一个，确定所述当前时刻的所述聚类的质量；相应的，所述计算所述当前时刻的所述聚类中的聚类点与所述历史时刻的连续障碍物航迹的匹配度，包括：若所述当前时刻的所述聚类的质量大于预设质量门限，则计算所述当前时刻的所述聚类中的聚类点与所述历史时刻的连续障碍物航迹的匹配度。
例如，在对雷达当前时刻探测到的静止目标点进行聚类处理，得到如图13所示的虚线框130中的聚类后，进一步该聚类中的聚类点个数、该聚类的长度、该聚类与车辆的车辆信息的匹配度中的至少一个，对该聚类进行打分，如果打分后的分值大于预设分值，则该聚类的质量大于预设质量门限，进一步，计算该聚类与历史时刻的连续障碍物航迹的匹配度。
作为一种可能的实现方式，所述计算所述当前时刻的所述聚类中的聚类点与所述历史时刻的连续障碍物航迹的匹配度，包括：根据所述当前时刻的所述聚类中的聚类点相对于所述雷达的距离和所述历史时刻的连续障碍物航迹中的历史航迹点相对于所述雷达的距离，计算所述当前时刻的所述聚类中的聚类点与所述历史时刻的连续障碍物航迹的匹配度；和/或根据所述当前时刻的所述聚类中的聚类点相对于所述雷达的速度和所述历史时刻的连续障碍物航迹中的历史航迹点相对于所述雷达的速度，计算所述当前时刻的所述聚类中的聚类点与所述历史时刻的连续障碍物航迹的匹配度。
例如，根据虚线框130中的各个聚类点相对于雷达的距离，计算该各个聚类点相对于雷达的平均距离。根据历史时刻的连续障碍物航迹例如虚线110中的各个历史航迹点相对于雷达的距离，计算该各个历史航迹点相 对于雷达的平均距离。进一步比较虚线框130中的各个聚类点相对于雷达的平均距离和该各个历史航迹点相对于雷达的平均距离，如果两者的差值小于预设值，则确定虚线框130中的聚类点与历史时刻的连续障碍物航迹的匹配度大于预设匹配度。
或者，还可以选取历史时刻的连续障碍物航迹例如虚线110中靠近虚线框130的多个历史航迹点，该多个历史航迹具体如图14所示的白色部分的点，通过虚线框130中的各个聚类点相对于雷达的距离，以及各个白色部分的点相对于雷达的距离，计算虚线框130中的聚类点与历史时刻的连续障碍物航迹的匹配度。可以理解，计算虚线框130中的聚类点与历史时刻的连续障碍物航迹的匹配度的方法不限于此，还可以采用其他方法计算虚线框130中的聚类点与历史时刻的连续障碍物航迹的匹配度。
例如，还可以根据虚线框130中的各个聚类点相对于雷达的速度和历史时刻的连续障碍物航迹例如虚线110中的各个历史航迹点相对于雷达的速度，计算虚线框130中的聚类点与历史时刻的连续障碍物航迹的匹配度。具体的，不限于通过比较虚线框130中的各个聚类点相对于雷达的平均速度和历史时刻的连续障碍物航迹例如虚线110中的各个历史航迹点相对于雷达的平均速度，计算虚线框130中的聚类点与历史时刻的连续障碍物航迹的匹配度。
作为另一种可能的实现方式，所述计算所述当前时刻的所述聚类中的聚类点与所述历史时刻的连续障碍物航迹的匹配度，包括：对所述当前时刻的所述聚类进行参数拟合，得到所述当前时刻的所述聚类对应的新航迹的参数信息；根据所述当前时刻的所述聚类对应的新航迹的参数信息和所述历史时刻的连续障碍物航迹的参数信息，计算所述当前时刻的所述聚类中的聚类点与所述历史时刻的连续障碍物航迹的匹配度。
如图13所示，在对雷达当前时刻探测到的静止目标点进行聚类处理，得到如图13所示的虚线框130中的聚类，并确定该聚类的质量大于预设质量门限后，还可以进一步，对虚线框130中的聚类进行参数拟合，得到虚线框130中的聚类对应的新航迹的参数信息，该新航迹具体如图15所示的曲线150。可选的，所述对所述当前时刻的所述聚类进行参数拟合，包括如下至少一种：采用多项式拟合方法对所述当前时刻的所述聚类进行 参数拟合；采用半径圆弧拟合方法对所述当前时刻的所述聚类进行参数拟合。对虚线框130中的聚类进行参数拟合的过程与拟合得到虚线110的过程一致，此处不再赘述。
例如，以二阶拟合为例，采用二阶拟合方法对虚线框130中的聚类进行参数拟合后，可得到曲线150对应的参数信息。进一步，根据曲线150对应的参数信息和历史时刻的连续障碍物航迹例如虚线110的参数信息，计算虚线框130中的聚类点与该历史时刻的连续障碍物航迹的匹配度。例如，曲线150对应的参数信息包括0阶系数、一阶系数、二阶系数、最近距离信息和最远距离信息，该历史时刻的连续障碍物航迹的参数信息也包括0阶系数、一阶系数、二阶系数、最近距离信息和最远距离信息，依次计算曲线150对应的0阶系数和该历史时刻的连续障碍物航迹对应的0阶系数的差值，曲线150对应的一阶系数和该历史时刻的连续障碍物航迹对应的一阶系数的差值，曲线150对应的二阶系数和该历史时刻的连续障碍物航迹对应的二阶系数的差值，曲线150对应的最近距离信息和该历史时刻的连续障碍物航迹对应的最近距离信息的差值，曲线150对应的最远距离信息和该历史时刻的连续障碍物航迹对应的最远距离信息的差值，如果前述差值均在预设范围内，则确定虚线框130中的聚类点与该历史时刻的连续障碍物航迹的匹配度大于预设匹配度。
步骤S1203、如果所述当前时刻的所述聚类中的聚类点和所述历史时刻的连续障碍物航迹的匹配度大于预设匹配度，则将所述当前时刻的所述聚类中的聚类点和所述历史时刻的连续障碍物航迹进行关联，得到所述当前时刻的连续障碍物航迹。
例如，虚线框130中的聚类点与该历史时刻的连续障碍物航迹的匹配度大于预设匹配度，则将虚线框130中的聚类点与该历史时刻的连续障碍物航迹例如虚线110进行关联，得到当前时刻的连续障碍物航迹。
作为一种可能的实现方式，所述将所述当前时刻的所述聚类中的聚类点和所述历史时刻的连续障碍物航迹进行关联，得到所述当前时刻的连续障碍物航迹，包括：根据所述当前时刻的所述聚类中的聚类点，得到所述当前时刻的所述聚类对应的新航迹；将所述当前时刻的所述聚类对应的新航迹和所述历史时刻的连续障碍物航迹进行关联，得到所述当前时刻的连 续障碍物航迹，所述当前时刻的连续障碍物航迹包括所述新航迹和所述历史时刻的连续障碍物航迹。
例如，通过对虚线框130中的聚类点进行参数拟合，得到曲线150的参数信息，曲线150为根据虚线框130中的聚类点得到的新航迹，将该新航迹与历史时刻的连续障碍物航迹例如虚线110进行关联，得到当前时刻的连续障碍物航迹，如图15所示，当前时刻的连续障碍物航迹包括该新航迹即曲线150和历史时刻的连续障碍物航迹例如虚线110。
可选的，所述新航迹和所述历史时刻的连续障碍物航迹相连接。例如，从历史时刻到当前时刻，连续障碍物没有发生中断，或者连续障碍物没有被遮挡，在这种情况下，该新航迹即曲线150和历史时刻的连续障碍物航迹例如虚线110是直接相连接的，如图15所示。
在另外一些实施例中，所述新航迹和所述历史时刻的连续障碍物航迹不相连。例如，从历史时刻到当前时刻，连续障碍物发生了中断，或者，该连续障碍物被其他物体所遮挡，则根据当前时刻的聚类得到的新航迹可能无法与历史时刻的连续障碍物航迹直接相连接，如图16所示，但是在这种情况下，新航迹和历史时刻的连续障碍物航迹也是相关联的，只是连续障碍物航迹出现了断裂，该新航迹即曲线150和历史时刻的连续障碍物航迹例如虚线110共同构成当前时刻的连续障碍物航迹。
作为另一种可能的实现方式，所述将所述当前时刻的所述聚类中的聚类点和所述历史时刻的连续障碍物航迹进行关联，得到所述当前时刻的连续障碍物航迹，包括：将所述当前时刻的所述聚类中的聚类点和所述历史时刻的连续障碍物航迹中的历史航迹点进行关联，得到所述当前时刻的连续障碍物航迹的航迹点；根据所述当前时刻的连续障碍物航迹的航迹点，确定所述当前时刻的连续障碍物航迹。
如图17所示，白色部分的点表示历史时刻的连续障碍物航迹例如虚线110中的各个历史航迹点，在对虚线框130中的聚类点与该历史时刻的连续障碍物航迹进行关联进行关联时，具体的，可以将虚线框130中的聚类点和历史时刻的连续障碍物航迹例如虚线110中的各个历史航迹点构成一个大的集合，并采用上述所述的拟合方法对该集合中的点进行参数拟合，得到一条新的航迹的参数信息，该条新的航迹即为如图15所示的由曲线 150和虚线110构成的航迹，该条航迹即可作为当前时刻的连续障碍物航迹。
另外，在一些实施例中，对雷达当前时刻探测到的静止目标点进行聚类处理后得到的聚类可能与历史时刻的连续障碍物航迹不匹配，且该聚类的质量大于预设质量门限，如图18所示，虚线框180中的聚类是对雷达当前时刻探测到的静止目标点进行聚类处理后得到的聚类，虚线110表示历史时刻的连续障碍物航迹，通过计算虚线框180中的聚类点与历史时刻的连续障碍物航迹的匹配度，确定该匹配度小于预设匹配度，则虚线框180中的聚类点与历史时刻的连续障碍物航迹无法关联，此时，可以根据虚线框180中的聚类点生成一个新的航迹，例如，虚线110是右侧的栅栏，该新的航迹为左侧的栅栏。当在下一时刻确定出一个新的聚类后，需要计算该聚类与历史时刻的连续障碍物航迹的匹配度，以及该聚类与虚线框180中的聚类点对应的新的航迹的匹配度，以确定将该聚类与该历史时刻的连续障碍物航迹或该新的航迹进行关联。
在另一些实施例中，若历史时刻的所述连续障碍物航迹无法与所述历史时刻之后的多个时刻中每个时刻的聚类对应的新航迹关联，则所述历史时刻的所述连续障碍物航迹中超出所述雷达探测范围的部分将逐渐消失。
如图18所示，虚线110表示历史时刻的连续障碍物航迹，当前时刻确定的虚线框180中的聚类点对应的新航迹与历史时刻的连续障碍物航迹无法关联，若当前时刻之后，该历史时刻的连续障碍物航迹例如虚线110多次没有与新航迹关联，则随着车辆不断的向前行驶，虚线110将逐渐消失。例如，α表示雷达的探测范围，随着车辆不断向前行驶，虚线110中的点将逐渐的超出该雷达的探测范围，若该虚线110多次没有与新航迹关联，则该虚线110将逐渐消失。同理，如果虚线框180中的聚类点对应的新航迹在当前时刻之后的将来时刻多次没有与新航迹关联，则虚线框180中的聚类点对应的新航迹也会随着车辆不断向前行驶而逐渐消失。
本实施例通过对所述雷达在所述当前时刻探测到的所述静止目标点进行聚类处理，得到所述当前时刻的聚类，计算所述当前时刻的所述聚类中的聚类点与所述历史时刻的连续障碍物航迹的匹配度，如果所述当前时刻的所述聚类中的聚类点和所述历史时刻的连续障碍物航迹的匹配度大 于预设匹配度，则将所述当前时刻的所述聚类中的聚类点和所述历史时刻的连续障碍物航迹进行关联，得到所述当前时刻的连续障碍物航迹，使得连续障碍物航迹可以在车辆行驶的过程中不断的被更新。
本发明实施例提供一种连续障碍物检测系统。图19为本发明实施例提供的连续障碍物检测系统的结构图，如图19所示，连续障碍物检测系统190包括：存储器191、处理器192和雷达193；其中，雷达193设置在车辆上。在一种可能的情况下，该连续障碍物检测系统190具体是雷达系统，此时，处理器192具体可以是雷达193中的信号处理单元。在另一种可能的情况下，该连续障碍物检测系统190具体是安装有雷达的车辆，此时，该处理器192可以是车载处理器。在又一种可能的情况下，该连续障碍物检测系统190具体是由安装有雷达的车辆和如图1所示的服务器12构成的系统，此时，该处理器192具体可以是如图1所示的服务器12的处理器。
具体的，雷达193至少包括天线，所述天线用于接收回波信号；存储器191用于存储程序代码；处理器192，调用所述程序代码，当程序代码被执行时，用于执行以下操作：获取当前时刻的所述回波信号，并根据所述回波信号生成所述当前时刻的探测数据；根据所述当前时刻的所述探测数据和所述当前时刻所述车辆的车辆信息，确定所述雷达在所述当前时刻探测到的静止目标点；根据所述雷达在所述当前时刻探测到的所述静止目标点，确定所述当前时刻的连续障碍物航迹。
可选的，处理器192根据所述雷达在所述当前时刻探测到的所述静止目标点，确定所述当前时刻的连续障碍物航迹之后，还用于：根据所述当前时刻的连续障碍物航迹，确定所述当前时刻所述车辆所在车道的边界。
可选的，所述探测数据包括如下至少一种：所述雷达探测到的目标点的能量、所述目标点相对于所述雷达的距离、速度、角度。
可选的，所述车辆的车辆信息包括如下至少一种：所述车辆的速度、转向、横摆角速度。
可选的，处理器192根据所述当前时刻的所述探测数据和所述当前时刻所述车辆的车辆信息，确定所述雷达在所述当前时刻探测到的静止目标 点时，具体用于：根据所述当前时刻所述车辆的速度、所述雷达在所述当前时刻探测到的目标点相对于所述雷达的距离和速度，确定所述雷达在所述当前时刻探测到的静止目标点。
可选的，处理器192根据所述当前时刻所述车辆的速度、所述雷达在所述当前时刻探测到的目标点相对于所述雷达的距离和速度，确定所述雷达在所述当前时刻探测到的静止目标点时，具体用于：若所述雷达在所述当前时刻探测到的目标点相对于所述雷达的距离大于预设距离，则比较所述目标点相对于所述雷达的速度和所述当前时刻所述车辆的速度；若所述目标点相对于所述雷达的速度和所述当前时刻所述车辆的速度的差值小于第一预设差值，则将所述目标点确定为所述雷达在所述当前时刻探测到的静止目标点。
可选的，处理器192根据所述当前时刻所述车辆的速度、所述雷达在所述当前时刻探测到的目标点相对于所述雷达的距离和速度，确定所述雷达在所述当前时刻探测到的静止目标点时，具体用于：若所述雷达在所述当前时刻探测到的目标点相对于所述雷达的距离小于或等于预设距离，则根据所述目标点相对于所述雷达的角度，确定所述目标点的等效地速；比较所述目标点的等效地速和所述当前时刻所述车辆的速度；若所述目标点的等效地速和所述当前时刻所述车辆的速度的差值小于第二预设差值，则将所述目标点确定为所述雷达在所述当前时刻探测到的静止目标点。
可选的，所述目标点的等效地速是所述目标点相对于所述雷达的径向速度。
可选的，处理器192根据所述雷达在所述当前时刻探测到的所述静止目标点，确定所述当前时刻的连续障碍物航迹时，具体用于：根据所述雷达在所述当前时刻探测到的所述静止目标点，生成所述当前时刻的连续障碍物航迹。
可选的，处理器192根据所述雷达在所述当前时刻探测到的所述静止目标点，生成所述当前时刻的连续障碍物航迹时，具体用于：对所述雷达在所述当前时刻探测到的所述静止目标点进行聚类处理，得到所述当前时刻的聚类；若所述当前时刻的所述聚类的质量大于预设质量门限，则根据所述当前时刻的所述聚类生成所述当前时刻的连续障碍物航迹。
可选的，处理器192根据所述当前时刻的所述聚类生成所述当前时刻的连续障碍物航迹之前，还用于：根据所述当前时刻的所述聚类中聚类点的个数、所述聚类的长度、所述聚类与所述车辆的车辆信息的匹配度中的至少一个，确定所述当前时刻的所述聚类的质量。
可选的，处理器192根据所述雷达在所述当前时刻探测到的所述静止目标点，确定所述当前时刻的连续障碍物航迹时，具体用于：根据所述雷达在所述当前时刻探测到的所述静止目标点，对历史时刻的连续障碍物航迹进行更新，得到所述当前时刻的连续障碍物航迹。
可选的，处理器192根据所述雷达在所述当前时刻探测到的所述静止目标点，对历史时刻的连续障碍物航迹进行更新，得到所述当前时刻的连续障碍物航迹时，具体用于：对所述雷达在所述当前时刻探测到的所述静止目标点进行聚类处理，得到所述当前时刻的聚类；计算所述当前时刻的所述聚类中的聚类点与所述历史时刻的连续障碍物航迹的匹配度；如果所述当前时刻的所述聚类中的聚类点和所述历史时刻的连续障碍物航迹的匹配度大于预设匹配度，则将所述当前时刻的所述聚类中的聚类点和所述历史时刻的连续障碍物航迹进行关联，得到所述当前时刻的连续障碍物航迹。
可选的，处理器192计算所述当前时刻的所述聚类中的聚类点与所述历史时刻的连续障碍物航迹的匹配度之前，还用于：根据所述当前时刻的所述聚类中聚类点的个数、所述聚类的长度、所述聚类与所述车辆的车辆信息的匹配度中的至少一个，确定所述当前时刻的所述聚类的质量；处理器192计算所述当前时刻的所述聚类中的聚类点与所述历史时刻的连续障碍物航迹的匹配度时，具体用于：若所述当前时刻的所述聚类的质量大于预设质量门限，则计算所述当前时刻的所述聚类中的聚类点与所述历史时刻的连续障碍物航迹的匹配度。
可选的，处理器192计算所述当前时刻的所述聚类中的聚类点与所述历史时刻的连续障碍物航迹的匹配度时，具体用于：根据所述当前时刻的所述聚类中的聚类点相对于所述雷达的距离和所述历史时刻的连续障碍物航迹中的历史航迹点相对于所述雷达的距离，计算所述当前时刻的所述聚类中的聚类点与所述历史时刻的连续障碍物航迹的匹配度；和/或根据 所述当前时刻的所述聚类中的聚类点相对于所述雷达的速度和所述历史时刻的连续障碍物航迹中的历史航迹点相对于所述雷达的速度，计算所述当前时刻的所述聚类中的聚类点与所述历史时刻的连续障碍物航迹的匹配度。
可选的，处理器192计算所述当前时刻的所述聚类中的聚类点与所述历史时刻的连续障碍物航迹的匹配度时，具体用于：对所述当前时刻的所述聚类进行参数拟合，得到所述当前时刻的所述聚类对应的新航迹的参数信息；根据所述当前时刻的所述聚类对应的新航迹的参数信息和所述历史时刻的连续障碍物航迹的参数信息，计算所述当前时刻的所述聚类中的聚类点与所述历史时刻的连续障碍物航迹的匹配度。
可选的，处理器192对所述当前时刻的所述聚类进行参数拟合时，具体用于如下至少一种：采用多项式拟合方法对所述当前时刻的所述聚类进行参数拟合；采用半径圆弧拟合方法对所述当前时刻的所述聚类进行参数拟合。
可选的，处理器192将所述当前时刻的所述聚类中的聚类点和所述历史时刻的连续障碍物航迹进行关联，得到所述当前时刻的连续障碍物航迹时，具体用于：根据所述当前时刻的所述聚类中的聚类点，得到所述当前时刻的所述聚类对应的新航迹；将所述当前时刻的所述聚类对应的新航迹和所述历史时刻的连续障碍物航迹进行关联，得到所述当前时刻的连续障碍物航迹，所述当前时刻的连续障碍物航迹包括所述新航迹和所述历史时刻的连续障碍物航迹。
可选的，所述新航迹和所述历史时刻的连续障碍物航迹相连接。
可选的，所述新航迹和所述历史时刻的连续障碍物航迹不相连。
可选的，处理器192将所述当前时刻的所述聚类中的聚类点和所述历史时刻的连续障碍物航迹进行关联，得到所述当前时刻的连续障碍物航迹时，具体用于：将所述当前时刻的所述聚类中的聚类点和所述历史时刻的连续障碍物航迹中的历史航迹点进行关联，得到所述当前时刻的连续障碍物航迹的航迹点；根据所述当前时刻的连续障碍物航迹的航迹点，确定所述当前时刻的连续障碍物航迹。
可选的，若历史时刻的所述连续障碍物航迹无法与所述历史时刻之后 的多个时刻中每个时刻的聚类对应的新航迹关联，则所述历史时刻的所述连续障碍物航迹中超出所述雷达探测范围的部分将逐渐消失。
可选的，所述雷达为毫米波雷达。
本发明实施例提供的连续障碍物检测系统的具体原理和实现方式均与上述实施例类似，此处不再赘述。
本实施例通过获取当前时刻的所述回波信号，并根据所述回波信号生成所述当前时刻的探测数据，根据所述当前时刻的所述探测数据和所述当前时刻所述车辆的车辆信息，确定所述雷达在所述当前时刻探测到的静止目标点，根据所述雷达在所述当前时刻探测到的所述静止目标点，确定所述当前时刻的连续障碍物航迹，从而实现了对车辆周围连续障碍物的检测。
本发明实施例提供一种车辆。该车辆包括：车身、动力系统和上述实施例所述的连续障碍物检测系统。其中，动力系统安装在所述车身，用于提供动力。该连续障碍物检测系统的实现方式和具体原理与上述实施例均一致，此处不再赘述。
另外，本实施例还提供一种计算机可读存储介质，其上存储有计算机程序，所述计算机程序被处理器执行以实现上述实施例所述的连续障碍物检测方法。
在本发明所提供的几个实施例中，应该理解到，所揭露的装置和方法，可以通过其它的方式实现。例如，以上所描述的装置实施例仅仅是示意性的，例如，所述单元的划分，仅仅为一种逻辑功能划分，实际实现时可以有另外的划分方式，例如多个单元或组件可以结合或者可以集成到另一个系统，或一些特征可以忽略，或不执行。另一点，所显示或讨论的相互之间的耦合或直接耦合或通信连接可以是通过一些接口，装置或单元的间接耦合或通信连接，可以是电性，机械或其它的形式。
所述作为分离部件说明的单元可以是或者也可以不是物理上分开的，作为单元显示的部件可以是或者也可以不是物理单元，即可以位于一个地方，或者也可以分布到多个网络单元上。可以根据实际的需要选择其中的部分或者全部单元来实现本实施例方案的目的。
另外，在本发明各个实施例中的各功能单元可以集成在一个处理单元中，也可以是各个单元单独物理存在，也可以两个或两个以上单元集成在一个单元中。上述集成的单元既可以采用硬件的形式实现，也可以采用硬件加软件功能单元的形式实现。
上述以软件功能单元的形式实现的集成的单元，可以存储在一个计算机可读取存储介质中。上述软件功能单元存储在一个存储介质中，包括若干指令用以使得一台计算机设备(可以是个人计算机，服务器，或者网络设备等)或处理器(processor)执行本发明各个实施例所述方法的部分步骤。而前述的存储介质包括：U盘、移动硬盘、只读存储器(Read-Only Memory，ROM)、随机存取存储器(Random Access Memory，RAM)、磁碟或者光盘等各种可以存储程序代码的介质。
本领域技术人员可以清楚地了解到，为描述的方便和简洁，仅以上述各功能模块的划分进行举例说明，实际应用中，可以根据需要而将上述功能分配由不同的功能模块完成，即将装置的内部结构划分成不同的功能模块，以完成以上描述的全部或者部分功能。上述描述的装置的具体工作过程，可以参考前述方法实施例中的对应过程，在此不再赘述。
最后应说明的是：以上各实施例仅用以说明本发明的技术方案，而非对其限制；尽管参照前述各实施例对本发明进行了详细的说明，本领域的普通技术人员应当理解：其依然可以对前述各实施例所记载的技术方案进行修改，或者对其中部分或者全部技术特征进行等同替换；而这些修改或者替换，并不使相应技术方案的本质脱离本发明各实施例技术方案的范围。

Claims (48)

  1. 一种连续障碍物检测方法，应用于车辆，所述车辆设置有雷达，所述雷达至少包括天线，所述天线用于接收回波信号，其特征在于，所述方法包括：
    获取当前时刻的所述回波信号，并根据所述回波信号生成所述当前时刻的探测数据；
    根据所述当前时刻的所述探测数据和所述当前时刻所述车辆的车辆信息，确定所述雷达在所述当前时刻探测到的静止目标点；
    根据所述雷达在所述当前时刻探测到的所述静止目标点，确定所述当前时刻的连续障碍物航迹。
  2. 根据权利要求1所述的方法，其特征在于，所述根据所述雷达在所述当前时刻探测到的所述静止目标点，确定所述当前时刻的连续障碍物航迹之后，所述方法还包括：
    根据所述当前时刻的连续障碍物航迹，确定所述当前时刻所述车辆所在车道的边界。
  3. 根据权利要求1或2所述的方法，其特征在于，所述探测数据包括如下至少一种：
    所述雷达探测到的目标点的能量、所述目标点相对于所述雷达的距离、速度、角度。
  4. 根据权利要求1-3任一项所述的方法，其特征在于，所述车辆的车辆信息包括如下至少一种：
    所述车辆的速度、转向、横摆角速度。
  5. 根据权利要求1-4任一项所述的方法，其特征在于，所述根据所述当前时刻的所述探测数据和所述当前时刻所述车辆的车辆信息，确定所述雷达在所述当前时刻探测到的静止目标点，包括：
    根据所述当前时刻所述车辆的速度、所述雷达在所述当前时刻探测到的目标点相对于所述雷达的距离和速度，确定所述雷达在所述当前时刻探测到的静止目标点。
  6. 根据权利要求5所述的方法，其特征在于，所述根据所述当前时刻所述车辆的速度、所述雷达在所述当前时刻探测到的目标点相对于所述 雷达的距离和速度，确定所述雷达在所述当前时刻探测到的静止目标点，包括：
    若所述雷达在所述当前时刻探测到的目标点相对于所述雷达的距离大于预设距离，则比较所述目标点相对于所述雷达的速度和所述当前时刻所述车辆的速度；
    若所述目标点相对于所述雷达的速度和所述当前时刻所述车辆的速度的差值小于第一预设差值，则将所述目标点确定为所述雷达在所述当前时刻探测到的静止目标点。
  7. 根据权利要求5所述的方法，其特征在于，所述根据所述当前时刻所述车辆的速度、所述雷达在所述当前时刻探测到的目标点相对于所述雷达的距离和速度，确定所述雷达在所述当前时刻探测到的静止目标点，包括：
    若所述雷达在所述当前时刻探测到的目标点相对于所述雷达的距离小于或等于预设距离，则根据所述目标点相对于所述雷达的角度，确定所述目标点的等效地速；
    比较所述目标点的等效地速和所述当前时刻所述车辆的速度；
    若所述目标点的等效地速和所述当前时刻所述车辆的速度的差值小于第二预设差值，则将所述目标点确定为所述雷达在所述当前时刻探测到的静止目标点。
  8. 根据权利要求7所述的方法，其特征在于，所述目标点的等效地速是所述目标点相对于所述雷达的径向速度。
  9. 根据权利要求1-8任一项所述的方法，其特征在于，所述根据所述雷达在所述当前时刻探测到的所述静止目标点，确定所述当前时刻的连续障碍物航迹，包括：
    根据所述雷达在所述当前时刻探测到的所述静止目标点，生成所述当前时刻的连续障碍物航迹。
  10. 根据权利要求9所述的方法，其特征在于，所述根据所述雷达在所述当前时刻探测到的所述静止目标点，生成所述当前时刻的连续障碍物航迹，包括：
    对所述雷达在所述当前时刻探测到的所述静止目标点进行聚类处理， 得到所述当前时刻的聚类；
    若所述当前时刻的所述聚类的质量大于预设质量门限，则根据所述当前时刻的所述聚类生成所述当前时刻的连续障碍物航迹。
  11. 根据权利要求10所述的方法，其特征在于，所述若所述当前时刻的所述聚类的质量大于预设质量门限，则根据所述当前时刻的所述聚类生成所述当前时刻的连续障碍物航迹之前，所述方法还包括：
    根据所述当前时刻的所述聚类中聚类点的个数、所述聚类的长度、所述聚类与所述车辆的车辆信息的匹配度中的至少一个，确定所述当前时刻的所述聚类的质量。
  12. 根据权利要求1-8任一项所述的方法，其特征在于，所述根据所述雷达在所述当前时刻探测到的所述静止目标点，确定所述当前时刻的连续障碍物航迹，包括：
    根据所述雷达在所述当前时刻探测到的所述静止目标点，对历史时刻的连续障碍物航迹进行更新，得到所述当前时刻的连续障碍物航迹。
  13. 根据权利要求12所述的方法，其特征在于，所述根据所述雷达在所述当前时刻探测到的所述静止目标点，对历史时刻的连续障碍物航迹进行更新，得到所述当前时刻的连续障碍物航迹，包括：
    对所述雷达在所述当前时刻探测到的所述静止目标点进行聚类处理，得到所述当前时刻的聚类；
    计算所述当前时刻的所述聚类中的聚类点与所述历史时刻的连续障碍物航迹的匹配度；
    如果所述当前时刻的所述聚类中的聚类点和所述历史时刻的连续障碍物航迹的匹配度大于预设匹配度，则将所述当前时刻的所述聚类中的聚类点和所述历史时刻的连续障碍物航迹进行关联，得到所述当前时刻的连续障碍物航迹。
  14. 根据权利要求13所述的方法，其特征在于，所述计算所述当前时刻的所述聚类中的聚类点与所述历史时刻的连续障碍物航迹的匹配度之前，所述方法还包括：
    根据所述当前时刻的所述聚类中聚类点的个数、所述聚类的长度、所述聚类与所述车辆的车辆信息的匹配度中的至少一个，确定所述当前时刻 的所述聚类的质量；
    所述计算所述当前时刻的所述聚类中的聚类点与所述历史时刻的连续障碍物航迹的匹配度，包括：
    若所述当前时刻的所述聚类的质量大于预设质量门限，则计算所述当前时刻的所述聚类中的聚类点与所述历史时刻的连续障碍物航迹的匹配度。
  15. 根据权利要求13或14所述的方法，其特征在于，所述计算所述当前时刻的所述聚类中的聚类点与所述历史时刻的连续障碍物航迹的匹配度，包括：
    根据所述当前时刻的所述聚类中的聚类点相对于所述雷达的距离和所述历史时刻的连续障碍物航迹中的历史航迹点相对于所述雷达的距离，计算所述当前时刻的所述聚类中的聚类点与所述历史时刻的连续障碍物航迹的匹配度；和/或
    根据所述当前时刻的所述聚类中的聚类点相对于所述雷达的速度和所述历史时刻的连续障碍物航迹中的历史航迹点相对于所述雷达的速度，计算所述当前时刻的所述聚类中的聚类点与所述历史时刻的连续障碍物航迹的匹配度。
  16. 根据权利要求13或14所述的方法，其特征在于，所述计算所述当前时刻的所述聚类中的聚类点与所述历史时刻的连续障碍物航迹的匹配度，包括：
    对所述当前时刻的所述聚类进行参数拟合，得到所述当前时刻的所述聚类对应的新航迹的参数信息；
    根据所述当前时刻的所述聚类对应的新航迹的参数信息和所述历史时刻的连续障碍物航迹的参数信息，计算所述当前时刻的所述聚类中的聚类点与所述历史时刻的连续障碍物航迹的匹配度。
  17. 根据权利要求16所述的方法，其特征在于，所述对所述当前时刻的所述聚类进行参数拟合，包括如下至少一种：
    采用多项式拟合方法对所述当前时刻的所述聚类进行参数拟合；
    采用半径圆弧拟合方法对所述当前时刻的所述聚类进行参数拟合。
  18. 根据权利要求13-17任一项所述的方法，其特征在于，所述将所 述当前时刻的所述聚类中的聚类点和所述历史时刻的连续障碍物航迹进行关联，得到所述当前时刻的连续障碍物航迹，包括：
    根据所述当前时刻的所述聚类中的聚类点，得到所述当前时刻的所述聚类对应的新航迹；
    将所述当前时刻的所述聚类对应的新航迹和所述历史时刻的连续障碍物航迹进行关联，得到所述当前时刻的连续障碍物航迹，所述当前时刻的连续障碍物航迹包括所述新航迹和所述历史时刻的连续障碍物航迹。
  19. 根据权利要求18所述的方法，其特征在于，所述新航迹和所述历史时刻的连续障碍物航迹相连接。
  20. 根据权利要求18所述的方法，其特征在于，所述新航迹和所述历史时刻的连续障碍物航迹不相连。
  21. 根据权利要求13-17任一项所述的方法，其特征在于，所述将所述当前时刻的所述聚类中的聚类点和所述历史时刻的连续障碍物航迹进行关联，得到所述当前时刻的连续障碍物航迹，包括：
    将所述当前时刻的所述聚类中的聚类点和所述历史时刻的连续障碍物航迹中的历史航迹点进行关联，得到所述当前时刻的连续障碍物航迹的航迹点；
    根据所述当前时刻的连续障碍物航迹的航迹点，确定所述当前时刻的连续障碍物航迹。
  22. 根据权利要求9-21任一项所述的方法，其特征在于，若历史时刻的所述连续障碍物航迹无法与所述历史时刻之后的多个时刻中每个时刻的聚类对应的新航迹关联，则所述历史时刻的所述连续障碍物航迹中超出所述雷达探测范围的部分将逐渐消失。
  23. 根据权利要求1-22任一项所述的方法，其特征在于，所述雷达为毫米波雷达。
  24. 一种连续障碍物检测系统，其特征在于，包括：存储器、处理器和雷达；所述雷达设置在车辆上，所述雷达至少包括天线，所述天线用于接收回波信号；
    所述存储器用于存储程序代码；
    所述处理器，调用所述程序代码，当程序代码被执行时，用于执行以 下操作：
    获取当前时刻的所述回波信号，并根据所述回波信号生成所述当前时刻的探测数据；
    根据所述当前时刻的所述探测数据和所述当前时刻所述车辆的车辆信息，确定所述雷达在所述当前时刻探测到的静止目标点；
    根据所述雷达在所述当前时刻探测到的所述静止目标点，确定所述当前时刻的连续障碍物航迹。
  25. 根据权利要求24所述的系统，其特征在于，所述处理器根据所述雷达在所述当前时刻探测到的所述静止目标点，确定所述当前时刻的连续障碍物航迹之后，还用于：
    根据所述当前时刻的连续障碍物航迹，确定所述当前时刻所述车辆所在车道的边界。
  26. 根据权利要求24或25所述的系统，其特征在于，所述探测数据包括如下至少一种：
    所述雷达探测到的目标点的能量、所述目标点相对于所述雷达的距离、速度、角度。
  27. 根据权利要求24-26任一项所述的系统，其特征在于，所述车辆的车辆信息包括如下至少一种：
    所述车辆的速度、转向、横摆角速度。
  28. 根据权利要求24-27任一项所述的系统，其特征在于，所述处理器根据所述当前时刻的所述探测数据和所述当前时刻所述车辆的车辆信息，确定所述雷达在所述当前时刻探测到的静止目标点时，具体用于：
    根据所述当前时刻所述车辆的速度、所述雷达在所述当前时刻探测到的目标点相对于所述雷达的距离和速度，确定所述雷达在所述当前时刻探测到的静止目标点。
  29. 根据权利要求28所述的系统，其特征在于，所述处理器根据所述当前时刻所述车辆的速度、所述雷达在所述当前时刻探测到的目标点相对于所述雷达的距离和速度，确定所述雷达在所述当前时刻探测到的静止目标点时，具体用于：
    若所述雷达在所述当前时刻探测到的目标点相对于所述雷达的距离 大于预设距离，则比较所述目标点相对于所述雷达的速度和所述当前时刻所述车辆的速度；
    若所述目标点相对于所述雷达的速度和所述当前时刻所述车辆的速度的差值小于第一预设差值，则将所述目标点确定为所述雷达在所述当前时刻探测到的静止目标点。
  30. 根据权利要求根据权利要求28所述的系统，其特征在于，所述处理器根据所述当前时刻所述车辆的速度、所述雷达在所述当前时刻探测到的目标点相对于所述雷达的距离和速度，确定所述雷达在所述当前时刻探测到的静止目标点时，具体用于：
    若所述雷达在所述当前时刻探测到的目标点相对于所述雷达的距离小于或等于预设距离，则根据所述目标点相对于所述雷达的角度，确定所述目标点的等效地速；
    比较所述目标点的等效地速和所述当前时刻所述车辆的速度；
    若所述目标点的等效地速和所述当前时刻所述车辆的速度的差值小于第二预设差值，则将所述目标点确定为所述雷达在所述当前时刻探测到的静止目标点。
  31. 根据权利要求30所述的系统，其特征在于，所述目标点的等效地速是所述目标点相对于所述雷达的径向速度。
  32. 根据权利要求24-31任一项所述的系统，其特征在于，所述处理器根据所述雷达在所述当前时刻探测到的所述静止目标点，确定所述当前时刻的连续障碍物航迹时，具体用于：
    根据所述雷达在所述当前时刻探测到的所述静止目标点，生成所述当前时刻的连续障碍物航迹。
  33. 根据权利要求32所述的系统，其特征在于，所述处理器根据所述雷达在所述当前时刻探测到的所述静止目标点，生成所述当前时刻的连续障碍物航迹时，具体用于：
    对所述雷达在所述当前时刻探测到的所述静止目标点进行聚类处理，得到所述当前时刻的聚类；
    若所述当前时刻的所述聚类的质量大于预设质量门限，则根据所述当前时刻的所述聚类生成所述当前时刻的连续障碍物航迹。
  34. 根据权利要求33所述的系统，其特征在于，所述处理器根据所述当前时刻的所述聚类生成所述当前时刻的连续障碍物航迹之前，还用于：
    根据所述当前时刻的所述聚类中聚类点的个数、所述聚类的长度、所述聚类与所述车辆的车辆信息的匹配度中的至少一个，确定所述当前时刻的所述聚类的质量。
  35. 根据权利要求24-31任一项所述的系统，其特征在于，所述处理器根据所述雷达在所述当前时刻探测到的所述静止目标点，确定所述当前时刻的连续障碍物航迹时，具体用于：
    根据所述雷达在所述当前时刻探测到的所述静止目标点，对历史时刻的连续障碍物航迹进行更新，得到所述当前时刻的连续障碍物航迹。
  36. 根据权利要求35所述的系统，其特征在于，所述处理器根据所述雷达在所述当前时刻探测到的所述静止目标点，对历史时刻的连续障碍物航迹进行更新，得到所述当前时刻的连续障碍物航迹时，具体用于：
    对所述雷达在所述当前时刻探测到的所述静止目标点进行聚类处理，得到所述当前时刻的聚类；
    计算所述当前时刻的所述聚类中的聚类点与所述历史时刻的连续障碍物航迹的匹配度；
    如果所述当前时刻的所述聚类中的聚类点和所述历史时刻的连续障碍物航迹的匹配度大于预设匹配度，则将所述当前时刻的所述聚类中的聚类点和所述历史时刻的连续障碍物航迹进行关联，得到所述当前时刻的连续障碍物航迹。
  37. 根据权利要求36所述的系统，其特征在于，所述处理器计算所述当前时刻的所述聚类中的聚类点与所述历史时刻的连续障碍物航迹的匹配度之前，还用于：
    根据所述当前时刻的所述聚类中聚类点的个数、所述聚类的长度、所述聚类与所述车辆的车辆信息的匹配度中的至少一个，确定所述当前时刻的所述聚类的质量；
    所述处理器计算所述当前时刻的所述聚类中的聚类点与所述历史时刻的连续障碍物航迹的匹配度时，具体用于：
    若所述当前时刻的所述聚类的质量大于预设质量门限，则计算所述当 前时刻的所述聚类中的聚类点与所述历史时刻的连续障碍物航迹的匹配度。
  38. 根据权利要求36或37所述的系统，其特征在于，所述处理器计算所述当前时刻的所述聚类中的聚类点与所述历史时刻的连续障碍物航迹的匹配度时，具体用于：
    根据所述当前时刻的所述聚类中的聚类点相对于所述雷达的距离和所述历史时刻的连续障碍物航迹中的历史航迹点相对于所述雷达的距离，计算所述当前时刻的所述聚类中的聚类点与所述历史时刻的连续障碍物航迹的匹配度；和/或
    根据所述当前时刻的所述聚类中的聚类点相对于所述雷达的速度和所述历史时刻的连续障碍物航迹中的历史航迹点相对于所述雷达的速度，计算所述当前时刻的所述聚类中的聚类点与所述历史时刻的连续障碍物航迹的匹配度。
  39. 根据权利要求36或37所述的系统，其特征在于，所述处理器计算所述当前时刻的所述聚类中的聚类点与所述历史时刻的连续障碍物航迹的匹配度时，具体用于：
    对所述当前时刻的所述聚类进行参数拟合，得到所述当前时刻的所述聚类对应的新航迹的参数信息；
    根据所述当前时刻的所述聚类对应的新航迹的参数信息和所述历史时刻的连续障碍物航迹的参数信息，计算所述当前时刻的所述聚类中的聚类点与所述历史时刻的连续障碍物航迹的匹配度。
  40. 根据权利要求39所述的系统，其特征在于，所述处理器对所述当前时刻的所述聚类进行参数拟合时，具体用于如下至少一种：
    采用多项式拟合方法对所述当前时刻的所述聚类进行参数拟合；
    采用半径圆弧拟合方法对所述当前时刻的所述聚类进行参数拟合。
  41. 根据权利要求36-40任一项所述的系统，其特征在于，所述处理器将所述当前时刻的所述聚类中的聚类点和所述历史时刻的连续障碍物航迹进行关联，得到所述当前时刻的连续障碍物航迹时，具体用于：
    根据所述当前时刻的所述聚类中的聚类点，得到所述当前时刻的所述聚类对应的新航迹；
    将所述当前时刻的所述聚类对应的新航迹和所述历史时刻的连续障碍物航迹进行关联，得到所述当前时刻的连续障碍物航迹，所述当前时刻的连续障碍物航迹包括所述新航迹和所述历史时刻的连续障碍物航迹。
  42. 根据权利要求41所述的系统，其特征在于，所述新航迹和所述历史时刻的连续障碍物航迹相连接。
  43. 根据权利要求41所述的系统，其特征在于，所述新航迹和所述历史时刻的连续障碍物航迹不相连。
  44. 根据权利要求36-40任一项所述的系统，其特征在于，所述处理器将所述当前时刻的所述聚类中的聚类点和所述历史时刻的连续障碍物航迹进行关联，得到所述当前时刻的连续障碍物航迹时，具体用于：
    将所述当前时刻的所述聚类中的聚类点和所述历史时刻的连续障碍物航迹中的历史航迹点进行关联，得到所述当前时刻的连续障碍物航迹的航迹点；
    根据所述当前时刻的连续障碍物航迹的航迹点，确定所述当前时刻的连续障碍物航迹。
  45. 根据权利要求32-44任一项所述的系统，其特征在于，若历史时刻的所述连续障碍物航迹无法与所述历史时刻之后的多个时刻中每个时刻的聚类对应的新航迹关联，则所述历史时刻的所述连续障碍物航迹中超出所述雷达探测范围的部分将逐渐消失。
  46. 根据权利要求24-45任一项所述的系统，其特征在于，所述雷达为毫米波雷达。
  47. 一种车辆，其特征在于，包括：
    车身；
    动力系统，安装在所述车身，用于提供动力；
    以及如权利要求24-46任一项所述的连续障碍物检测系统。
  48. 一种计算机可读存储介质，其特征在于，其上存储有计算机程序，所述计算机程序被处理器执行以实现如权利要求1-23任一项所述的方法。
PCT/CN2018/124887 2018-12-28 2018-12-28 连续障碍物检测方法、设备、系统及存储介质 WO2020133217A1 (zh)

Priority Applications (3)

Application Number Priority Date Filing Date Title
CN201880069474.8A CN111316128A (zh) 2018-12-28 2018-12-28 连续障碍物检测方法、设备、系统及存储介质
PCT/CN2018/124887 WO2020133217A1 (zh) 2018-12-28 2018-12-28 连续障碍物检测方法、设备、系统及存储介质
US17/202,322 US20210261154A1 (en) 2018-12-28 2021-03-15 Continuous obstacle detection method, device, and system, and storage medium

Applications Claiming Priority (1)

Application Number Priority Date Filing Date Title
PCT/CN2018/124887 WO2020133217A1 (zh) 2018-12-28 2018-12-28 连续障碍物检测方法、设备、系统及存储介质

Related Child Applications (1)

Application Number Title Priority Date Filing Date
US17/202,322 Continuation US20210261154A1 (en) 2018-12-28 2021-03-15 Continuous obstacle detection method, device, and system, and storage medium

Publications (1)

Publication Number Publication Date
WO2020133217A1 true WO2020133217A1 (zh) 2020-07-02

Family

ID=71126722

Family Applications (1)

Application Number Title Priority Date Filing Date
PCT/CN2018/124887 WO2020133217A1 (zh) 2018-12-28 2018-12-28 连续障碍物检测方法、设备、系统及存储介质

Country Status (3)

Country Link
US (1) US20210261154A1 (zh)
CN (1) CN111316128A (zh)
WO (1) WO2020133217A1 (zh)

Cited By (2)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN113721234A (zh) * 2021-08-30 2021-11-30 南京慧尔视智能科技有限公司 一种车载毫米波雷达点云数据动静分离过滤方法和装置
CN115236627A (zh) * 2022-09-21 2022-10-25 深圳安智杰科技有限公司 一种基于多帧多普勒速度扩维的毫米波雷达数据聚类方法

Families Citing this family (12)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN111832665B (zh) * 2020-09-10 2021-01-05 福瑞泰克智能系统有限公司 栅栏检测方法、装置、计算机设备和存储介质
CN112198503A (zh) * 2020-10-16 2021-01-08 无锡威孚高科技集团股份有限公司 一种目标航迹预测优化方法、装置及雷达系统
CN112526503B (zh) * 2020-11-20 2024-06-07 广州极飞科技股份有限公司 探测物体距离的方法及相关装置
CN112462368B (zh) * 2020-11-25 2022-07-12 中国第一汽车股份有限公司 一种障碍物检测方法、装置、车辆及存储介质
CN112764034B (zh) * 2020-12-25 2022-11-04 南京市德赛西威汽车电子有限公司 一种车载bsd毫米波雷达低速下障碍物识别方法
CN112949489B (zh) * 2021-03-01 2023-05-12 成都安智杰科技有限公司 一种道路边界识别方法、装置、电子设备和存储介质
CN113740836A (zh) * 2021-07-31 2021-12-03 南京市德赛西威汽车电子有限公司 一种基于毫米波雷达的静止目标跟踪优化方法
CN113791409A (zh) * 2021-08-04 2021-12-14 南京市德赛西威汽车电子有限公司 一种基于毫米波雷达的静止目标提取方法及系统
CN114170751A (zh) * 2021-11-17 2022-03-11 青岛海信日立空调系统有限公司 一种入侵检测方法及装置
CN113866734B (zh) * 2021-12-03 2022-03-04 中国电子科技集团公司信息科学研究院 一种分布式雷达系统航迹误差校正方法及装置
CN114488065A (zh) * 2022-01-27 2022-05-13 中国第一汽车股份有限公司 一种航迹数据处理方法、装置、车辆和介质
CN116299474B (zh) * 2023-05-23 2023-09-12 禾多科技（北京）有限公司 一体化雷达装置和车辆避障方法

Citations (4)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN106681318A (zh) * 2016-12-09 2017-05-17 重庆长安汽车股份有限公司 自动驾驶中车道线检测短暂丢失的车辆安全控制系统及方法
US20170345311A1 (en) * 2016-05-24 2017-11-30 Kabushiki Kaisha Toshiba Information processing apparatus and information processing method
US20170369054A1 (en) * 2016-06-24 2017-12-28 Toyota Jidosha Kabushiki Kaisha Collision avoidance apparatus
CN108573272A (zh) * 2017-12-15 2018-09-25 蔚来汽车有限公司 车道拟合方法

Family Cites Families (4)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN101761083B (zh) * 2008-12-24 2011-08-24 上海市基础工程有限公司 穿越超厚障碍物的地下连续墙清障施工方法
US9297892B2 (en) * 2013-04-02 2016-03-29 Delphi Technologies, Inc. Method of operating a radar system to reduce nuisance alerts caused by false stationary targets
US9335766B1 (en) * 2013-12-06 2016-05-10 Google Inc. Static obstacle detection
CN108828527B (zh) * 2018-06-19 2021-04-16 驭势（上海）汽车科技有限公司 一种多传感器数据融合方法、装置、车载设备及存储介质

Patent Citations (4)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US20170345311A1 (en) * 2016-05-24 2017-11-30 Kabushiki Kaisha Toshiba Information processing apparatus and information processing method
US20170369054A1 (en) * 2016-06-24 2017-12-28 Toyota Jidosha Kabushiki Kaisha Collision avoidance apparatus
CN106681318A (zh) * 2016-12-09 2017-05-17 重庆长安汽车股份有限公司 自动驾驶中车道线检测短暂丢失的车辆安全控制系统及方法
CN108573272A (zh) * 2017-12-15 2018-09-25 蔚来汽车有限公司 车道拟合方法

Cited By (4)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN113721234A (zh) * 2021-08-30 2021-11-30 南京慧尔视智能科技有限公司 一种车载毫米波雷达点云数据动静分离过滤方法和装置
CN113721234B (zh) * 2021-08-30 2023-09-01 南京慧尔视智能科技有限公司 一种车载毫米波雷达点云数据动静分离过滤方法和装置
CN115236627A (zh) * 2022-09-21 2022-10-25 深圳安智杰科技有限公司 一种基于多帧多普勒速度扩维的毫米波雷达数据聚类方法
CN115236627B (zh) * 2022-09-21 2022-12-16 深圳安智杰科技有限公司 一种基于多帧多普勒速度扩维的毫米波雷达数据聚类方法

Also Published As

Publication number Publication date
US20210261154A1 (en) 2021-08-26
CN111316128A (zh) 2020-06-19

Similar Documents

Publication Publication Date Title
WO2020133217A1 (zh) 连续障碍物检测方法、设备、系统及存储介质
CN108226951B (zh) 一种基于激光传感器的快速运动障碍物实时跟踪方法
US11475678B2 (en) Lane marker detection and lane instance recognition
WO2018177026A1 (zh) 确定道路边沿的装置和方法
CN108226924B (zh) 基于毫米波雷达的汽车行驶环境探测方法、装置及其应用
US11508122B2 (en) Bounding box estimation and object detection
US11195028B2 (en) Real-time simultaneous detection of lane marker and raised pavement marker for optimal estimation of multiple lane boundaries
US9255988B2 (en) Object fusion system of multiple radar imaging sensors
EP3792660B1 (en) Method, apparatus and system for measuring distance
US11544940B2 (en) Hybrid lane estimation using both deep learning and computer vision
CN112051575B (zh) 一种毫米波雷达与激光雷达的调整方法及相关装置
JP2016053563A (ja) 軸ずれ検出装置
KR101468963B1 (ko) 차량 장착용 다중 레이더 장착 각도 보정 장치 및 방법
CN113743171A (zh) 目标检测方法及装置
US20220215197A1 (en) Data processing method and apparatus, chip system, and medium
CN116022163A (zh) 基于超局部子图的自动驾驶车辆扫描匹配和雷达姿态估计器
CN116772831A (zh) 基于多传感器融合的移动机器人导航定位系统及方法
JP6480504B2 (ja) 物標認識システム、物標認識方法、およびプログラム
CN115082562A (zh) 一种外参标定方法、装置、设备、服务器及车载计算设备
US11914028B2 (en) Object detection device for vehicle
CN116125488A (zh) 目标追踪方法、信号融合方法、装置、终端和存储介质
CN115792891A (zh) 基于多毫米波雷达与激光雷达融合的目标航迹跟踪方法
JP2019148593A (ja) 物標認識システム、物標認識方法、およびプログラム
WO2021132227A1 (ja) 情報処理装置、センシング装置、移動体及び情報処理方法
CN117690109A (zh) 识别车道边沿的方法和电子设备

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: 18944567

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: 18944567

Country of ref document: EP

Kind code of ref document: A1