WO2020107474A1 - 上方障碍物检测方法及装置、系统、车辆、存储介质 - Google Patents

上方障碍物检测方法及装置、系统、车辆、存储介质 Download PDF

Info

Publication number
WO2020107474A1
WO2020107474A1 PCT/CN2018/118770 CN2018118770W WO2020107474A1 WO 2020107474 A1 WO2020107474 A1 WO 2020107474A1 CN 2018118770 W CN2018118770 W CN 2018118770W WO 2020107474 A1 WO2020107474 A1 WO 2020107474A1
Authority
WO
WIPO (PCT)
Prior art keywords
target
frame
distance
detected
trend
Prior art date
Application number
PCT/CN2018/118770
Other languages
English (en)
French (fr)
Inventor
李怡强
陆新飞
王凯
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 CN201880040372.3A priority Critical patent/CN110785676A/zh
Priority to PCT/CN2018/118770 priority patent/WO2020107474A1/zh
Publication of WO2020107474A1 publication Critical patent/WO2020107474A1/zh

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
    • 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

Definitions

  • the embodiments of the present invention relate to obstacle detection technology, in particular to an upper obstacle detection method and device, system, vehicle, and storage medium, which belong to the technical field of assisted driving.
  • ADAS Advanced Driver Assistant
  • AD Autonomous Driving
  • millimeter wave radar is generally used to check obstacles in front of the vehicle, and the detection accuracy of obstacles above the road where the vehicle is located is poor.
  • the obstacles above represented by gantry and street signs are easily scattered by millimeter-wave radar as stationary vehicles due to strong scattering, which may cause emergency braking of autonomous vehicles, resulting in poor vehicle stability .
  • a radar that increases the pitch to the receiving channel is generally used to detect obstacles above; however, this kind of radar will cause an increase in the amount of calculation, and a chip with more processing power needs to be selected to perform data processing.
  • the invention provides an upper obstacle detection method and device, system, vehicle, and storage medium, which are used to realize the detection of the upper obstacle without increasing the system hardware overhead, reduce the probability of false alarm of the front obstacle, and improve the vehicle Driving stability.
  • the present invention provides an upper obstacle detection method, including:
  • the present invention provides an upper obstacle detection device, including:
  • the computer program is stored in the memory and is configured to be executed by the processor to implement the method according to the first aspect.
  • the present invention provides an upper obstacle detection system, including:
  • the upper obstacle detection device according to the second aspect
  • Radar is used to send out detection radar signals and receive radar signals reflected by the target to be detected.
  • the present invention provides a vehicle, including the upper obstacle detection system as described in the third aspect.
  • the present invention provides a computer-readable storage medium having a computer program stored thereon, the computer program being executed by a processor to implement the method according to the first aspect.
  • the upper obstacle detection method and device, system, vehicle, and storage medium provided by the present invention considering that the radar has a fixed pitch antenna pattern, the closer it is to the target to be detected, the greater the elevation angle, and thus, reflected by the target to be detected
  • the embodiment of the present invention can achieve accurate identification of the target to be detected through the change trend between the relative position relationship between the vehicle and the target to be detected and the signal energy of the radar signal.
  • the detection of obstacles above is implemented through software, which reduces the probability of false alarms in front of obstacles and improves vehicle stability.
  • FIG. 1 is an oblique view of a road in a driving scene of a vehicle provided by an embodiment of the present invention
  • FIG. 2 is a top view of a road in the driving scenario of the vehicle shown in FIG. 1 in an embodiment of the present invention
  • FIG. 3 is a right side view of the road in the driving scenario of the vehicle shown in FIG. 1 in an embodiment of the present invention
  • FIG. 4 is a schematic flowchart of a method for detecting an upper obstacle provided by an embodiment of the present invention.
  • FIG. 5 is a schematic flowchart of another method for detecting an upper obstacle provided by an embodiment of the present invention.
  • FIG. 6 is a schematic flowchart of another method for detecting an upper obstacle provided by an embodiment of the present invention.
  • FIG. 7 is a schematic diagram of the physical structure of an upper obstacle detection device provided by an embodiment of the present invention.
  • FIG. 8 is a schematic structural diagram of an upper obstacle detection system according to an embodiment of the present invention.
  • FIG. 9 is a schematic structural diagram of a vehicle according to an embodiment of the present invention.
  • the specific application scenario of the present invention is: a detection scenario for an obstacle above in front of the vehicle.
  • FIGS. 1 and 2 wherein FIG. 1 shows a perspective view of a road in a vehicle driving scene, and FIG. 2 shows a top view of the road in a vehicle driving scene shown in FIG. 1.
  • the coordinate systems shown in FIG. 1 and FIG. 2 are radar coordinate systems, where the X-axis direction points to the road edge, the Y-axis direction points to the front of the road, and the Z-axis direction is the vertical upward direction.
  • the method for detecting an upper obstacle aims to solve the above technical problems of the prior art, and proposes the following solution: using the relative positional relationship between the vehicle and the target to be detected and the radar signal reflected by the target to be detected The change trend between signal energies determines whether the target to be detected is an obstacle above.
  • An embodiment of the present invention provides a method for detecting obstacles above.
  • the inventive idea of the method for detecting an upper obstacle provided by an embodiment of the present invention will be briefly described.
  • FIG. 3 shows a right side view of the road in the vehicle driving scenario shown in FIG. 1, where the right side view of the road shows a schematic diagram of the driving between the vehicle and the obstacle above the right side of the road.
  • R represents the straight-line distance between the scattering center U2 of the obstacle on the right side of the road and the vehicle. It is simply called the elevation angle of the obstacle on the right side of the road and the vehicle.
  • the target to be detected is an obstacle above based on the change trend between the relative position relationship between the vehicle and the target to be detected and the signal energy of the radar signal reflected by the target to be detected.
  • the upper obstacle detection method provided by the embodiment of the present invention includes the following steps:
  • the radar can emit a detection radar signal to the outside.
  • the detection radar signal will be reflected by the obstacle to the radar.
  • the radar signal involved in the embodiments of the present invention refers to: a signal sent by the radar and received by the radar after being reflected by the target to be detected.
  • the signal emitted by the radar is referred to as a detection radar signal
  • the signal received by the radar after being reflected by an obstacle is referred to as a radar signal.
  • the start frame of the target period may be the transmission time of the aforementioned detection radar signal or the reception time of the aforementioned radar signal
  • the end frame may be the current frame
  • the end frame of the target period is the current frame
  • the start frame of the target period is a frame where the radar initially receives the reflected radar signal.
  • the end frame of the target period is the current frame
  • the start frame of the target period is a frame after the radar initially sends out a detection radar signal and starts tracking the reflected radar signal.
  • the frame from which the radar sends out a detection radar signal (referred to as the transmission frame) may be different from the frame from which the radar starts tracking the radar signal (referred to as the tracking frame).
  • the radar starts tracking the radar signal at a certain frame after the detection radar signal is sent
  • the start frame is a frame after the detection radar signal is sent and starts tracking the radar signal.
  • the radar may not record the The frame interval between the transmission frame and the tracking frame, and the frame interval is generally fixed, and can be preset in the present obstacle detection method execution device (hereinafter, referred to as the upper obstacle detection device) or radar or other In the storage location that is read, therefore, in this implementation scenario, after acquiring the transmission frame recorded by the radar, the preset frame interval can be obtained, and the tracking frame can be obtained by adding.
  • the transmission frame is the same as the tracking frame.
  • the start frame of the target period may also directly send a frame for detecting radar signals from the radar. No longer.
  • the aforementioned target time period may be a time period formed by one, or more, radar signals being transmitted, reflected, and received.
  • the start frame of the target time period is the start frame of the first radar signal among the multiple radar signals (the aforementioned at least three methods will not be repeated) .
  • the multiple radar signals may be radar signals reflected for the target to be detected.
  • the signal parameters involved in the embodiments of the present invention may include, but are not limited to: the transmission time of the detection radar signal (which may be represented by frames), the reception time of the radar signal (which may also be represented by frames), and the signal energy of the radar signals.
  • the signal energy can be expressed by P i , whose unit is decibel (dB), where i represents the frame number, the starting frame of the frame number is a frame where the radar emits the detection radar signal and starts tracking the radar signal, and its end A frame is a frame where the radar receives the radar signal.
  • the signal parameters of the aforementioned radar signals are recorded during the process of radar detecting obstacles. Therefore, this step can be achieved by acquiring data from the radar processor.
  • the specific implementation of acquiring the signal parameters of the radar signal is related to the relationship between the obstacle detection device above and the radar.
  • the upper obstacle detection device may be provided inside the radar, which may be used as one or more processors (or processing modules) in the radar independent of the main processor, or may also be used as the main processor One or more processing modules.
  • the upper obstacle detection device can interact with the radar's main processor to request the main processor to obtain the aforementioned signal parameters.
  • the upper obstacle detection device can be set independently of the radar.
  • the upper obstacle detection device and the processor of the radar can implement data interaction through wired or wireless communication.
  • the wireless communication method may include but is not limited to: wireless fidelity communication (Wireless-Fidelity, WiFi), Bluetooth communication, near field communication (Near Field Communication, NFC).
  • the upper obstacle detection device can send a request to the radar processor in a wired or wireless manner, and the radar processor feeds back data to the upper obstacle detection device according to the request to achieve the acquisition of signal parameters; Or, you can set automatic transmission rules in the radar processor, for example, periodic transmission, real-time transmission, etc., as the upper obstacle detection device, you only need to receive the signal sent by the radar processor through wired or wireless means Parameters.
  • S404 Acquire the relative position relationship between the target to be detected and the vehicle according to the signal parameters.
  • the relative position relationship is used to characterize the distance relationship between the target to be detected and the vehicle.
  • the relative position relationship involved in the embodiment of the present invention may include: a first distance between the vehicle and the target to be detected. That is, the distance R shown in FIG. 3.
  • this step can be implemented by detecting the transmission time of the radar signal and the reception time of the radar signal in the signal parameters.
  • the transmission time of the detection radar signal is t1
  • the reception time of the radar signal is t2
  • the signal propagation speed is v
  • the transmission time of the radar signal between the radar and the target to be detected is (t2-t1). Therefore, the product of the transfer time and the signal propagation speed is divided by 2 to obtain the first distance, which can be specifically expressed as: (t2-t1)*v/2.
  • S406 Determine whether the target to be detected is an obstacle above the vehicle according to the relative position relationship and the change trend of the signal energy in the signal parameter within the target period.
  • An embodiment of the present invention proposes a trend parameter, and uses the trend parameter to characterize the changing trend between the first distance and the signal energy.
  • the trend parameter may be determined according to the change in the first distance and the change in signal energy.
  • the embodiments of the present invention provide two implementation methods for obtaining trend parameters:
  • the first one is to obtain the trend parameters in consecutive multiple frames.
  • the first one is to obtain the trend parameters in consecutive multiple frames.
  • the first change parameter is the sum of the product of the distance deviation value and the energy deviation value of each frame in the continuous multiple frames in the target period
  • the second change parameter is the target The sum of squares of the distance deviation values of each frame in consecutive multiple frames within the period
  • S represents the trend parameter corresponding to continuous multi-frames
  • R i represents the first distance between the target to be detected and the vehicle at the i-th frame
  • R * represents the first distance between the target to be detected and the vehicle within the continuous multi-frame
  • P i represents the signal energy between the target to be detected and the vehicle at the i-th frame
  • P * represents the average value of the signal energy between the target to be detected and the vehicle within continuous multiple frames
  • i 0 represents the continuous multiple frames
  • the starting frame of i, e e represents the end frame of consecutive multiple frames.
  • the continuous multiple frames may be specifically the target period, in which case i 0 represents the start frame of the target period and i e represents the end frame of the target period.
  • the continuous multi-frames in the target period refer to at least two consecutive frames in the target period.
  • the ratio between the signal energy deviation value and the distance deviation value is obtained as the trend parameter corresponding to the frame.
  • S i represents the trend parameter corresponding to frame i
  • R i represents the first distance between the target to be detected and the vehicle at frame i
  • R j represents the relationship between the target to be detected and the vehicle corresponding to the start frame of the target period
  • P i represents the signal energy between the target to be detected and the vehicle at the i-th frame
  • P j represents the signal energy between the target to be detected and the vehicle corresponding to the start frame
  • i represents the division in the target period Any frame other than the start frame.
  • the foregoing second implementation manner can also have other forms of deformation.
  • the signal energy and The distance is replaced by: the signal energy and distance corresponding to the previous frame of the frame (or a specified number of frames, where the specified bibliography is an integer greater than 1), to obtain the signal energy deviation value and the distance deviation value, and then obtain the signal The ratio between the energy deviation value and the distance deviation value is used as the trend parameter corresponding to the frame.
  • the embodiment of the present invention does not specifically limit the order of acquiring the distance deviation value and the energy deviation value, and the two steps may be performed simultaneously, or, Execute in sequence.
  • S4064 Determine whether the target to be detected is an obstacle above the vehicle according to the trend parameter and the preset trend threshold.
  • the trend parameters corresponding to the continuous multiple frames can be compared with the preset trend threshold. If the trend parameters corresponding to the continuous multiple frames are less than the trend threshold, it is determined to be detected The target is an obstacle above the vehicle. Conversely, if the trend parameter corresponding to multiple consecutive frames is greater than or equal to the trend threshold, it is determined that the target to be detected is not an obstacle above the vehicle.
  • the detection can be realized by direct comparison, which has higher accuracy and is beneficial to improve the detection accuracy.
  • Method one in any frame except the start frame in the target period, compare the trend parameter corresponding to the frame with the trend threshold, if the trend parameter corresponding to the frame is less than the trend threshold, determine that the target to be detected is an obstacle above the vehicle . Conversely, if the trend parameter corresponding to the frame is greater than or equal to the trend threshold, it is determined that the target to be detected is not an obstacle above the vehicle.
  • This implementation has a small amount of data processing, which is helpful to improve the detection efficiency.
  • Method 2 In any frame other than the start frame in the target period, if the trend parameter corresponding to the frame is less than the trend threshold, the number of consecutive frames with the trend parameter less than the trend parameter threshold is obtained. Therefore, if the number of consecutive frames is greater than or equal to the preset Determines the target to be detected as an obstacle above the vehicle, where the frame threshold is at least two frames.
  • this implementation is equivalent to adding a secondary inspection process, which can further avoid accidents and further improve the detection accuracy.
  • Manner 3 In the target period, the average value of the trend parameters corresponding to the frames other than the start frame is obtained, so that if the average value of the trend parameters is less than the trend threshold, it is determined that the target to be detected is an obstacle above the vehicle.
  • the average value of the trend parameters in the entire target period can better characterize the relative position relationship and the change trend of the signal energy in the target period, which is more conducive to improving the detection accuracy.
  • trend threshold in each of the foregoing implementations can be set as needed, and the trend threshold in each implementation can be set to the same value, or can be set to different thresholds in combination with different detection needs.
  • the aforementioned trend threshold may be set to the same value, for example, to 0.05.
  • FIGS. 1 and 2 please refer to FIGS. 1 and 2 to know that the obstacles above the road are generally closer to the road boundary, that is, the horizontal distance in the X-axis direction is generally within a certain distance threshold, so This feature is judged as an auxiliary feature in the aforementioned detection step.
  • the relative position relationship of the embodiment of the present invention may also include a second distance, where the second distance is the distance between the target to be detected and the radar pointing line.
  • the second distance of the upper left obstacle shown in FIG. 1 is the distance between the upper left obstacle and the radar pointing line; the second distance of the upper right obstacle shown in FIG. 1 is the The distance between the upper right obstacle and the radar pointing line.
  • this method can be implemented with reference to the method shown in FIG. 6. As shown in FIG. 6, before executing S406, the method further includes the following steps:
  • the first distance is the straight-line distance between the target to be detected and the vehicle, and will not be described in detail.
  • S4054 According to the first distance and the second distance, determine whether the target to be detected is an obstacle above to be determined.
  • execute S406 that is, perform the foregoing step of determining whether the target to be detected is an obstacle above the vehicle based on the relative position relationship and the change trend of the signal energy in the target period, which will not be described in detail.
  • the judgment process may be: if the first distance is greater than the first distance threshold and the second distance is less than the preset second distance threshold, it is determined that the target to be detected is an obstacle to be determined above. Conversely, if the first distance is less than or equal to the first distance threshold, and/or the second distance is greater than or equal to the preset second distance threshold, it is determined that the target to be detected is not an obstacle to be determined above.
  • the implementation shown in FIG. 6 is a possible design, and the embodiment of the present invention does not specifically limit the execution order of the lateral feature detection and the foregoing trend parameter detection through the second distance. That is, if the aforementioned lateral feature detection is used as an auxiliary detection step for trend parameter detection, only if the detection results of both are YES, can the target to be detected be finally determined as an obstacle above to be determined; otherwise, if there is at least one detection step If the detection result is no, it is determined that the target to be detected is not an obstacle above to be determined.
  • the detection of the aforementioned trend parameters may also be performed first. If the detection result is yes, the lateral feature detection shown in FIG. 6 is performed. At this time, if the lateral feature detection result is yes , You can determine the target to be detected as the obstacle above the pending
  • an embodiment of the present invention further provides a possible detection method: the elevation angle a shown in FIG. 3 is used to detect the target to be detected.
  • the detection method can be used as an auxiliary solution to any of the aforementioned achievable solutions. Therefore, on the premise that the inspection results of the foregoing solutions are YES, if the elevation angle detection result is also YES, the target to be detected can be determined to be pending Obstacle above. Conversely, if the detection result of any of the detection steps is no, it is determined that the target to be detected is not an obstacle above to be determined.
  • the elevation angle is used as a basis for the detection of the obstacle above
  • a similar way to the first distance can be used to obtain the change trend between the elevation angle and the signal energy, and it can be used to characterize the change trend.
  • the comparison between the second trend parameter and the second trend threshold value enables the detection of the target to be detected.
  • the implementation method is the same as above and will not be repeated here.
  • the radar can also detect obstacles in front of the vehicle, the detection method is divided by the existing method.
  • similar methods of the detection method provided in the embodiments of the present invention may also be used.
  • the signal energy of the radar signal received by the ground obstacle will be higher and higher. Therefore, it can be similar to FIG. In this way, according to the relative position relationship and the change trend of the signal energy of the radar signal in the target period, if the signal energy of the radar signal increases with the shortening of the first distance, it can be determined as the ground obstacle of the vehicle.
  • the radar involved in the foregoing implementation steps may be a millimeter wave radar.
  • an embodiment of the present invention further provides a device embodiment that implements the steps and methods in the above method embodiment.
  • An embodiment of the present invention provides an upper obstacle detection device. Please refer to FIG. 7.
  • the upper obstacle detection device 700 includes:
  • the computer program is stored in the memory 710 and is configured to be executed by the processor 720 to implement the method described in the above embodiment.
  • the upper obstacle detection device 700 is further provided with a transceiver 730 for data transmission or communication with other devices, which will not be repeated here.
  • the memory 710, the processor 720, and the transceiver 730 are connected and communicate through a bus.
  • the number of processors 720 in the upper obstacle detection device 700 may be one or more, and the processor 720 may also be called a processing unit, which may implement a certain control function.
  • the processor 720 may be a general-purpose processor or a dedicated processor.
  • the processor 720 may also store instructions, and the instructions may be executed by the processor, so that the upper obstacle detection device 700 executes the method described in the above method embodiments.
  • the upper obstacle detection device 700 may include a circuit that can implement the function of sending or receiving or communicating in the foregoing method embodiments.
  • the number of the memory 710 in the upper obstacle detection device 700 may be one or more.
  • the memory 710 has instructions or intermediate data stored thereon, and the instructions may be executed on the processor so that The upper obstacle detection device 700 executes the method described in the above method embodiments.
  • the memory 710 may also store other related data.
  • the processor 720 may also store instructions and/or data. The processor 720 and the memory 710 may be set separately, or may be integrated together.
  • the processor 720 may be referred to as a processing unit.
  • the transceiver 730 may be referred to as a transceiver unit, a transceiver, a transceiver circuit, or a transceiver, etc., for implementing the transceiver function of the obstacle detection device 700 above.
  • the transceiver 730 is used to obtain The signal parameter of the radar signal reflected by the target to be detected.
  • the transceiver 730 can further complete other corresponding communication functions.
  • the processor 720 is used to complete a corresponding determination or control operation, and optionally, a corresponding instruction may also be stored in the memory 710.
  • a corresponding instruction may also be stored in the memory 710.
  • the processor 720 and the transceiver 730 described in the embodiments of the present invention can be implemented in an integrated circuit (IC), analog IC, radio frequency integrated circuit RFIC, mixed signal IC, application specific integrated circuit (ASIC), Printed circuit (PCB), electronic equipment, etc.
  • the processor and transceiver can also be manufactured using various 1C process technologies, such as complementary metal oxide semiconductor (CMOS), N-type metal oxide semiconductor (nMetal-oxide-semiconductor, NMOS), P-type Metal oxide semiconductor (positive channel metal oxide semiconductor (PMOS), bipolar junction transistor (Bipolar Junction Transistor, BJT), bipolar CMOS (BiCMOS), silicon germanium (SiGe), gallium arsenide (GaAs), etc.
  • CMOS complementary metal oxide semiconductor
  • N-type metal oxide semiconductor nMetal-oxide-semiconductor
  • PMOS positive channel metal oxide semiconductor
  • BJT bipolar junction transistor
  • BiCMOS bipolar CMOS
  • SiGe
  • the upper obstacle detection apparatus 700 may be an independent device or may be a part of a larger device.
  • an embodiment of the present invention provides a readable storage medium on which a computer program is stored, which is executed by a processor to implement the method described in the foregoing embodiments.
  • an embodiment of the present invention also provides a computer program product, which is used to execute the method described in the foregoing embodiment when the computer program is executed by a computer.
  • the program in the eighth aspect may be stored in whole or in part on a storage medium packaged with the processor, or in part or in whole on a memory that is not packaged with the processor.
  • the upper obstacle detection system 800 includes:
  • the radar 810 is used to send out detection radar signals and receive radar signals reflected by the target to be detected.
  • the radar is a millimeter wave radar.
  • the vehicle 900 includes an upper obstacle detection system 800.
  • the vehicle 900 may be a general vehicle including an obstacle detection system 800 above, or a vehicle equipped with an ADAS system, or an autonomous driving vehicle.
  • the radar 810 in the vehicle 900 may be disposed at the front of the vehicle 900 or the front part of the vehicle to obtain environmental information in front of the vehicle; and the upper obstacle detection device 700 may be disposed inside the vehicle, for example The location close to the vehicle control device is not limited here.
  • the communication between the radar 810 in the vehicle 900 and the obstacle detection device 700 above may be via CAN bus, Ethernet link, wireless communication, near field communication, etc., and is not limited here.

Abstract

本发明提供一种上方障碍物检测方法及装置、系统、车辆、存储介质，该方法包括：在车辆行驶过程中的目标时段内，获取待检测目标反射的雷达信号的信号参数，然后，根据所述信号参数，获取所述待检测目标与所述车辆之间的相对位置关系，进而，根据所述相对位置关系与所述信号参数中的信号能量在所述目标时段内的变化趋势，确定所述待检测目标是否为所述车辆的上方障碍物。因此，本发明实施例提供的技术方案能够在不增加系统硬件开销的前提下实现对上方障碍物的检测，降低了前方障碍物虚警概率，提高了车辆行驶稳定性。

Description

上方障碍物检测方法及装置、系统、车辆、存储介质 技术领域
本发明实施例涉及障碍物检测技术，尤其涉及一种上方障碍物检测方法及装置、系统、车辆、存储介质，属于辅助驾驶技术领域。
背景技术
随着高级辅助驾驶系统(Advanced Driver Assistant System，ADAS)和自动驾驶(Autonomous Driving，AD)技术的不断发展，毫米波雷达作为重要传感器也随之快速发展。
但是，毫米波雷达一般用于车辆前方障碍物的检查，对于车辆所在道路的上方障碍物的检测精度较差。具体而言，以龙门架、路牌为代表的上方障碍物由于散射强烈，很容易被毫米波雷达识别为静止车辆，这可能会引起自动驾驶车辆的紧急制动，造成车辆行驶的稳定性较差。为了解决这个问题，现有技术中一般采用增加俯仰向接收通道的雷达来实现对上方障碍物的检测；然而，这种雷达会导致计算量的增加，还需要选用处理能力更强的芯片来进行数据处理。
现有技术中通过毫米波雷达结合俯仰向接收通道、高处理能力芯片的方案会导致检测成本大幅提高。因此，如何在不增加系统硬件开销的前提下，通过传统的低成本毫米波雷达实现上方障碍物的检测成为本领域亟待解决的技术问题。
发明内容
本发明提供了一种上方障碍物检测方法及装置、系统、车辆、存储介质，用以在不增加系统硬件开销的前提下实现对上方障碍物的检测，降低前方障碍物虚警概率，提高车辆行驶稳定性。
第一方面，本发明提供一种上方障碍物检测方法，包括：
在车辆行驶过程中的目标时段内，获取待检测目标反射的雷达信号的信号参数；
根据所述信号参数，获取所述待检测目标与所述车辆之间的相对位置关系；
根据所述相对位置关系与所述信号参数中的信号能量在所述目标时段内的变化趋势，确定所述待检测目标是否为所述车辆的上方障碍物。
第二方面，本发明提供一种上方障碍物检测装置，包括：
存储器；
处理器；以及
计算机程序；
其中，所述计算机程序存储在所述存储器中，并被配置为由所述处理器执行以实现如第一方面所述的方法。
第三方面，本发明提供一种上方障碍物检测系统，包括：
如第二方面所述的上方障碍物检测装置；
雷达，用于发出探测雷达信号，并接收经待检测目标反射的雷达信号。
第四方面，本发明提供一种车辆，包括：如第三方面所述的上方障碍物检测系统。
第五方面，本发明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如第一方面所述的方法。
本发明提供的上方障碍物检测方法及装置、系统、车辆、存储介质，考虑到雷达具备固定的俯仰向天线方向图，其距离待检测目标越近，仰角越大，从而，经待检测目标反射的雷达信号的信号能量越低，因此，本发明实施例通过车辆和待检测目标之间的相对位置关系与雷达信号的信号能量之间的变化趋势，可以实现对待检测目标的准确识别，该方案无需对现有检测系统的硬件进行增加，避免硬件成本的开销，而是通过软件方式实现对上方障碍物的检测，降低了前方障碍物的虚警概率，提高了车辆行驶稳定性。
附图说明
此处的附图被并入说明书中并构成本说明书的一部分，示出了符合本公开的实施例，并与说明书一起用于解释本公开的原理。
图1为本发明实施例所提供的一种车辆行驶场景中的道路斜视图；
图2为本发明实施例中图1所示车辆行驶场景中的道路俯视图；
图3为本发明实施例中图1所示车辆行驶场景中的道路右视图；
图4为本发明实施例所提供的一种上方障碍物检测方法的流程示意图；
图5为本发明实施例所提供的另一种上方障碍物检测方法的流程示意图；
图6为本发明实施例所提供的另一种上方障碍物检测方法的流程示意图；
图7为本发明实施例所提供的一种上方障碍物检测装置的实体结构示意图；
图8为本发明实施例所提供的一种上方障碍物检测系统的架构示意图；
图9为本发明实施例所提供的一种车辆的架构示意图。
通过上述附图，已示出本公开明确的实施例，后文中将有更详细的描述。这些附图和文字描述并不是为了通过任何方式限制本公开构思的范围，而是通过参考特定实施例为本领域技术人员说明本公开的概念。
具体实施方式
这里将详细地对示例性实施例进行说明，其示例表示在附图中。下面的描述涉及附图时，除非另有表示，不同附图中的相同数字表示相同或相似的要素。以下示例性实施例中所描述的实施方式并不代表与本公开相一致的所有实施方式。相反，它们仅是与如所附权利要求书中所详述的、本公开的一些方面相一致的装置和方法的例子。
本发明具体的应用场景为：针对车辆前方的上方障碍物的检测场景。
具体而言，请参考图1与图2，其中，图1示出了一种车辆行驶场景中的道路斜视图，图2示出了图1所示车辆行驶场景中的道路俯视图。其中，图1与图2中所示坐标系为雷达坐标系，其中，X轴方向指向道路边沿，Y轴方向指向道路正前方，Z轴方向为垂直向上的方向。
如图1与图2所示，在该车辆行驶场景中，道路两侧设置有上方障碍物，其中，U1所示位置为道路左侧上方障碍物的散射中心，U2所示位置为道路右侧上方障碍物的散射中心，由于散射强烈，容易导致雷达将其识别为静止车辆，进而，可能会造成车辆紧急制动，影响车辆行驶的稳定性。
本发明提供的上方障碍物的检测方法，旨在解决现有技术的如上技术问题，并提出如下解决思路：利用车辆与待检测目标之间的相对位置关系与经待检测目标反射的雷达信号的信号能量之间的变化趋势，确定待检测目标是 否为上方障碍物。
下面以具体地实施例对本发明的技术方案以及本发明实施例的技术方案如何解决上述技术问题进行详细说明。下面这几个具体的实施例可以相互结合，对于相同或相似的概念或过程可能在某些实施例中不再赘述。下面将结合附图，对本发明的实施例进行描述。
实施例一
本发明实施例提供了一种上方障碍物检测方法。以下，对本发明实施例所提供的上方障碍物检测方法的发明思路进行简单说明。
具体而言，可以参考图3，图3示出了图1所示车辆行驶场景中的道路右视图，该道路右视图中示出了车辆与道路右侧上方障碍物之间的行驶示意图。
如图3所示，R表示道路右侧上方障碍物的散射中心U2与车辆之间的直线距离，该直线距离与前述雷达坐标系中的Y轴方向之间的侧面夹角记为a，可简称之为该道路右侧上方障碍物与车辆的仰角。
由图3所示示意图可知，随着车辆沿着Y轴方向向前行驶，其道路右侧上方障碍物距离车辆越来越近，仰角a越来越大，而在雷达所具备的固定的俯仰向天线方向图中，仰角越大，经该道路右侧上方障碍物反射的雷达信号的信号能量越弱。而与之相反的，针对与车辆同处于一个平面上的地面障碍物而言，车辆距离地面障碍物越近，经地面障碍物反射的雷达信号的能量越强。
由此，可基于车辆与待检测目标之间的相对位置关系与经待检测目标反射的雷达信号的信号能量之间的变化趋势，确定待检测目标是否为上方障碍物。
基于此，请参考图4，本发明实施例所提供的上方障碍物检测方法包括如下步骤：
S402，在车辆行驶过程中的目标时段内，获取待检测目标反射的雷达信号的信号参数。
可知，雷达可对外发射探测雷达信号，在遇到障碍物时，该探测雷达信号会经障碍物的阻挡而反射给雷达，如此，若雷达接收到反射的雷达信号，则可以确定前方有障碍物。由此，本发明实施例所涉及到的雷达信号是指： 由雷达发出，并经待检测目标反射后由雷达接收的信号。
以下，为了便于说明，将雷达发出的信号称之为探测雷达信号，将经将障碍物(本发明实施例所涉及到的为待检测目标)反射并由雷达接收到的信号称之为雷达信号。
而在具体实现过程中，目标时段的起始帧可以为前述探测雷达信号的发送时刻或者前述雷达信号的接收时刻，结束帧可以为当前帧。
在一个可能的场景中，目标时段的结束帧为当前帧，目标时段的起始帧为雷达初始接收到反射的雷达信号的一帧。
在另一可能的场景中，目标时段的结束帧为当前帧，目标时段的起始帧为雷达初始发出探测雷达信号后开始跟踪反射的雷达信号的一帧。
需要注意的是，雷达发出探测雷达信号的一帧(简称为发射帧)与雷达开始跟踪雷达信号的一帧(简称为跟踪帧)可能不同。
具体的，若雷达在发出探测雷达信号后的某一帧开始跟踪雷达信号，则该起始帧为该探测雷达信号发出后、开始跟踪雷达信号的一帧，此时，雷达可能不会记录该发射帧与跟踪帧之间的帧间隔，而该帧间隔一般是固定的，可预先设置在该本上方障碍物的检测方法的执行装置(以下，简称上方障碍物检测装置)或雷达或其他可被读取到的存储位置中，因此，在这种实现场景中，可在获取到雷达记录的发射帧后，获取该预设的帧间隔，相加即可得到跟踪帧。
或者，若雷达在发出探测雷达信号的同一帧开始跟踪雷达信号，则该发射帧与跟踪帧相同。
而在另一可能的场景中，目标时段的起始帧也可直接为雷达发出探测雷达信号的一帧。不再赘述。
此外需要说明的是，前述目标时段可以是一个或多个雷达信号经发射、反射、接收构成的时段。举例说明，若目标时段中包含多个雷达信号的传递，则目标时段的起始帧即为多个雷达信号中的第一个雷达信号的起始帧(前述至少三种方式，不再赘述)。此外，考虑到雷达在正常工作时会持续对外发出雷达信号，而本发明实施例为针对待检测目标的检测，因此，该多个雷达信号可以为针对待检测目标反射的雷达信号。
本发明实施例所涉及到的信号参数可以包括但不限于：探测雷达信号的 发射时刻(可通过帧来表示)、雷达信号的接收时刻(亦可通过帧表示)、雷达信号的信号能量。其中，信号能量可通过P i表示，其单位为分贝(dB)，其中i表示帧号，该帧号的起始帧为雷达发射出探测雷达信号并开始跟踪雷达信号的一帧，而其结束帧即为雷达接收到雷达信号的一帧。
前述雷达信号的信号参数均在雷达检测障碍物过程中被记录下来，因此，该步骤可通过向雷达处理器获取数据的方式实现。
此时，获取雷达信号的信号参数的具体实现方式，与本上方障碍物的检测装置与雷达之间的关系有关。
一种可能的设计中，该上方障碍物检测装置可设置于雷达内部，其可作为雷达内部独立于主处理器的一个或多个处理器(或处理模块)，或者，也可作为主处理器中的一个或多个处理模块。这种实现场景中，该上方障碍物检测装置可与雷达的主处理器进行信息交互，向主处理器请求以获取前述信号参数。
在另一可能的设计中，该上方障碍物检测装置可独立于雷达设置，此时，上方障碍物检测装置与雷达的处理器之间可通过有线或无线通信的方式实现数据交互。其中，无线通信方式可以包括但不限于：无线保真通信(Wireless-Fidelity，WiFi)、蓝牙通信、近场通信(Near Field Communication，NFC)。在具体实现场景中，可由上方障碍物检测装置通过有线或无线方式向雷达的处理器发送请求，而雷达的处理器根据该请求向该上方障碍物检测装置反馈数据，以实现信号参数的获取；或者，也可以在雷达的处理器中设置自动发送规则，例如，周期性发送、实时发送等方式，而作为上方障碍物检测装置，则仅需接收雷达的处理器通过有线或无线方式发送的信号参数即可。
S404，根据信号参数，获取待检测目标与车辆之间的相对位置关系。
基于前述发明思路，该相对位置关系用以表征待检测目标与车辆之间的距离关系。具体而言，本发明实施例所涉及到的相对位置关系可以包括：车辆与待检测目标之间的第一距离。也就是，图3所示的距离R。
具体而言，该步骤可通过信号参数中的探测雷达信号的发射时刻与雷达信号的接收时刻来实现。
举例说明，若探测雷达信号的发射时刻为t1，而雷达信号的接收时刻为 t2，信号传播速度为v，则雷达信号在雷达与待检测目标之间的传递时长为(t2-t1)，由此，获取该传递时长与信号传播速度之积并除以2，即可得到第一距离，其可具体表示为：(t2-t1)*v/2。
S406，根据相对位置关系与信号参数中的信号能量在目标时段内的变化趋势，确定待检测目标是否为车辆的上方障碍物。
基于如图3所示的发明构思，在具体实现该方案中S406的步骤时，可参考图5所示方式实现：
S4062，在目标时段内，获取第一距离与信号能量之间的趋势参数。
本发明实施例提出一种趋势参数，并通过趋势参数来表征第一距离与信号能量之间的变化趋势。具体而言，该趋势参数可根据第一距离的变化量与信号能量的变化量来确定。
具体而言，本发明实施例提供两种可供实现的获取趋势参数的实现方式：
第一种，可获取连续多帧内的趋势参数。具体可参考如下方式实现：
1.1)获取目标时段内的每一帧对应的距离偏差值，距离偏差值为该帧对应的第一距离与目标时段内的连续多帧中的第一距离平均值之差；
1.2)获取目标时段内的每一帧对应的信号能量偏差值，信号能量偏差值为该帧对应的信号能量与目标时段内的连续多帧中的信号能量平均值之差；
1.3)获取第一变化参数与第二变化参数，其中，第一变化参数为目标时段内的连续多帧中，各帧的距离偏差值与能量偏差值之积的总和；第二变化参数为目标时段内的连续多帧中，各帧的距离偏差值的平方和；
1.4)获取第一变化参数与第二变化参数之间的比值，以作为连续多帧对应的趋势参数。
具体的，可通过如下公式(记为公式一)实现：
Figure PCTCN2018118770-appb-000001
其中，
Figure PCTCN2018118770-appb-000002
Figure PCTCN2018118770-appb-000003
其中，S表示连续多帧对应的趋势参数，R i表示第i帧时的待检测目标与车辆之间的第一距离，R *表示连续多帧内待检测目标与车辆之间的第一距离的平均值，P i表示第i帧时的待检测目标与车辆之间的信号能量，P *表示连续多帧内待检测目标与车辆之间的信号能量的平均值，i 0表示连续多帧的起始帧，i e表示连续多帧的结束帧。
在一种可能的设计中，该连续多帧可具体为目标时段，此时，i 0表示目标时段的起始帧，i e表示目标时段的结束帧。
此外，前述目标时段内的连续多帧是指目标时段内连续的至少两帧。
第二种，可获取单一帧内的趋势参数。具体可参考如下方式实现：
2.1)获取目标时段内除起始帧外的每一帧对应的距离偏差值，距离偏差值为该帧对应的第一距离与起始帧对应的第一距离之差；
2.2)获取目标时段内除起始帧外的每一帧对应的信号能量偏差值，信号能量偏差值为该帧对应的信号能量与起始帧对应的信号能量之差；
2.3)在目标时段内除起始帧外的每一帧，获取信号能量偏差值与距离偏差值之间的比值，以作为该帧对应的趋势参数。
具体的，可通过如下公式(记为公式二)实现：
Figure PCTCN2018118770-appb-000004
其中，S i表示第i帧对应的趋势参数，R i表示第i帧时的待检测目标与车辆之间的第一距离，R j表示目标时段的起始帧对应的待检测目标与车辆之间的第一距离，P i表示第i帧时的待检测目标与车辆之间的信号能量，P j表示起始帧对应的待检测目标与车辆之间的信号能量，i表示目标时段中除起始帧之外的任意帧。
除此之外，前述第二种实现方式还可以有其他形式的变形。例如，在一种可能的设计中，针对除起始帧之外的任意帧，可在获取该帧对应的信号能量偏差值与距离偏差值时，还可将前述起始帧对应的信号能量和距离，更换为：该帧的前一帧(或指定数目帧，其中指定书目为大于1的整数)对应的信号能量和距离，以此来得到信号能量偏差值与距离偏差值之后，再获取信号能量偏差值与距离偏差值之间的比值，以作为该帧对应的趋势参数。
需要说明的是，通过前述公式一或公式二实现趋势参数的获取时，本发 明实施例对于距离偏差值与能量偏差值之间的获取顺序无特别限定，这两个步骤可同时执行，或者，先后次序执行。
S4064，根据趋势参数与预设的趋势阈值，确定待检测目标是否为车辆的上方障碍物。
具体而言，前述步骤中，能够获取到不同的趋势参数，基于如图3所示的发明思路，可以通过将趋势参数与预设的趋势阈值进行比较的方法，实现对待检测目标是否为车辆的上方障碍物的判断。
具体而言，若通过S4062中的公式一实现该检测，则可以将连续多帧对应的趋势参数与预设的趋势阈值进行比较，若连续多帧对应的趋势参数小于趋势阈值，则确定待检测目标为车辆的上方障碍物。反之，若连续多帧对应的趋势参数大于或者等于趋势阈值，则确定待检测目标不是车辆的上方障碍物。
由于公式一所示方式为连续多帧内的趋势参数，因此，可通过直接比较的方式实现检测，具备较高的精确度，有利于提高检测准确率。
若通过S4062中的公式二实现该检测，由于公式二是得到单帧内的趋势参数，因此，为了适应于不同的检测需求，本发明实施例给出如下三种可能的实现方式：
方式一，在目标时段内除起始帧外的任意帧，将该帧对应的趋势参数与趋势阈值进行比较，若该帧对应的趋势参数小于趋势阈值，确定待检测目标为车辆的上方障碍物。反之，若该帧对应的趋势参数大于或者等于趋势阈值，确定待检测目标不是车辆的上方障碍物。
这种实现方式的数据处理量较少，有利于提高检测效率。
方式二，在目标时段内除起始帧外的任意帧，若该帧对应的趋势参数小于趋势阈值，获取趋势参数小于趋势参数阈值的连续帧数目，从而，若连续帧数目大于或者等于预设的帧阈值，确定待检测目标为车辆的上方障碍物，其中，帧阈值至少为两帧。
可知，前述连续帧的数目小于预设的帧阈值，则可确定待检测目标不是车辆的上方障碍物。
也就是，若在单帧的判断结果为是的前提下，为了进一步保证该判断结果不是偶然情况，因此，在至少两帧均判断为是的情况下，才会将待检测目 标确定为车辆的上方障碍物。这种实现方式相较于前述方式一，相当于增加了一个二次检验过程，由此，能够进一步避免偶然情况的发生，进一步提高检测准确率。
方式三，在目标时段内，获取除起始帧外的各帧对应的趋势参数的平均值，从而，若趋势参数的平均值小于趋势阈值，确定待检测目标为车辆的上方障碍物。
这种实现方式中，整个目标时段的趋势参数的平均值更能够表征相对位置关系与信号能量在目标时段内的变化趋势，更有利于提高检测精确度。
通过如上方案，可实现对待检测目标的检测。
此外，需要说明的是，前述各实现方式中的趋势阈值可根据需要设置，各不同实现方式中的趋势阈值可设置为相同数值，或者，可结合不同检测需求设置为不同阈值。
例如，在一个可能的设计中，可将前述趋势阈值设置为同一数值，如，设置为0.05。
除此之外，请参考图1和图2可知，道路上方的上方障碍物一般距离道路边界线较近，也就是，X轴方向的横向距离一般在一定的距离阈值范围内，因此，可将该特征作为前述检测步骤中的辅助特征进行判断。
此时，本发明实施例的相对位置关系，除第一距离之外，还可以包括第二距离，其中，第二距离为待检测目标与雷达指向线之间的距离。例如，图1所示的左侧上方障碍物的第二距离就是，该左侧上方障碍物与雷达指向线之间的距离；图1所示的右侧上方障碍物的第二距离就是，该右侧上方障碍物与雷达指向线之间的距离。
具体而言，该方法可参考图6所示方法实现。如图6所示，在执行S406之前，该方法还包括如下步骤：
S4052，在目标时段内的每一帧，分别获取第一距离与第二距离。
其中，第一距离为待检测目标与车辆之间的直线距离，不再赘述。
S4054，根据第一距离与第二距离，判断待检测目标是否为待定上方障碍物。
若是，执行S406，也就是，执行前述根据相对位置关系与信号能量在目标时段内的变化趋势，确定待检测目标是否为车辆的上方障碍物的步骤，不 再赘述。
若否，执行S408，确定该待检测目标不是车辆的上方障碍物。
具体而言，其判断过程可以为：若第一距离大于第一距离阈值且第二距离小于预设的第二距离阈值时，确定待检测目标为待定上方障碍物。反之，若第一距离小于或者等于第一距离阈值，和/或，第二距离大于或者等于预设的第二距离阈值，则确定待检测目标不是待定上方障碍物。
此外，需要说明的是，如图6所示的实现方式为一种可能的设计，本发明实施例对于通过第二距离实现横向特征检测与前述趋势参数检测的执行次序无特别限定。也就是，若将前述横向特征检测作为趋势参数检测的辅助检测步骤时，只有二者的检测结果均为是，才能最终确定待检测目标为待定上方障碍物；反之，若存在至少一个检测步骤的检测结果为否，都确定待检测目标不是待定上方障碍物。
因此，在其他可能的设计中，也可先执行前述趋势参数的检测，若其检测结果为是，则在执行如图6所示的横向特征检测，此时，若横向特征检测的结果为是，即可确定待检测目标为待定上方障碍物
除前述流程之外，如图3所示，本发明实施例还进一步给出一种可能的检测方式：利用图3所示的仰角a实现对待检测目标的检测。此时，该检测方式可作为前述任一可实现方案的辅助方案，从而，在前述方案的检查结果均为是的前提下，若该仰角检测结果也为是，则可确定待检测目标为待定上方障碍物。反之，若任一检测步骤的检测结果为否，则确定待检测目标不是待定上方障碍物。
具体的，若以仰角作为上方障碍物的一个检测依据时，可采用如第一距离的实现方式类似的方式，获取仰角与信号能量之间的变化趋势，并将能够用以表征变化趋势的第二趋势参数与第二趋势阈值的比较，来实现对待检测目标的检测。实现方式同上，不再赘述。
此外，考虑到传统雷达可能不具备针对仰角的测量工具，因此，若以仰角作为上方障碍物的一个检测依据时，还需要设置仰角测量工具，这会在一定程度上增加硬件设备成本。
除基于前述方案对待检测目标进行检测，以确定该待检测目标是否为车辆的上方障碍物之外，可知，雷达还可实现对车辆行驶前方障碍物的检测， 检测方式除以现有的方式之外，也可采用本发明实施例所提供检测方法的类似手段实现。
具体而言，如图3所示的实现场景中已述，随着车辆向前方行驶，接收到地面障碍物反射的雷达信号的信号能量会越来越高，由此，可通过与图1类似方式，根据相对位置关系与雷达信号的信号能量在目标时段内的变化趋势，若雷达信号的信号能量随着第一距离的缩短而增强，则可将其确定为车辆的地面障碍物。
此外，只需要能够实现雷达信号的发射和接收的雷达均可实现本方案，因此，本发明实施例对于雷达类型无特殊限定。
在一种可能的实现场景中，如背景技术的自动驾驶或辅助驾驶场景中，前述各实现步骤中所涉及到的雷达可以为毫米波雷达。
可以理解的是，上述实施例中的部分或全部步骤或操作仅是示例，本发明实施例还可以执行其它操作或者各种操作的变形。此外，各个步骤可以按照上述实施例呈现的不同的顺序来执行，并且有可能并非要执行上述实施例中的全部操作。
基于上述实施例一所提供的上方障碍物检测方法，本发明实施例进一步给出实现上述方法实施例中各步骤及方法的装置实施例。
本发明实施例提供了一种上方障碍物检测装置，请参考图7，该上方障碍物检测装置700，包括：
存储器710；
处理器720；以及
计算机程序；
其中，计算机程序存储在存储器710中，并被配置为由处理器720执行以实现如上述实施例所述的方法。
此外，如图7所示，在该上方障碍物检测装置700中还设置有收发器730，用于与其他设备进行数据传输或通信，在此不再赘述。
如图7所示，存储器710、处理器720与收发器730之间通过总线连接并通信。
其中，所述上方障碍物检测装置700中处理器720的数目可以为一个或多个，处理器720也可以称为处理单元，可以实现一定的控制功能。所述处 理器720可以是通用处理器或者专用处理器等。
在一种可选地设计中，处理器720也可以存有指令，所述指令可以被所述处理器运行，使得所述上方障碍物检测装置700执行上述方法实施例中描述的方法。
在又一种可能的设计中，上方障碍物检测装置700可以包括电路，所述电路可以实现前述方法实施例中发送或接收或者通信的功能。
可选地，所述上方障碍物检测装置700中存储器710的数目可以为一个或多个，存储器710，其上存有指令或者中间数据，所述指令可在所述处理器上被运行，使得所述上方障碍物检测装置700执行上述方法实施例中描述的方法。可选地，所述存储器710中还可以存储有其他相关数据。可选地处理器720中也可以存储指令和/或数据。所述处理器720和存储器710可以单独设置，也可以集成在一起。
此外，所述处理器720可以称为处理单元。所述收发器730可以称为收发单元、收发机、收发电路、或者收发器等，用于实现上方障碍物检测装置700的收发功能。
具体而言，在一个可能的实现场景中，若该上方障碍物检测装置700用于实现对应于图4所示实施例中的上方障碍物检测方法的操作时，所述收发器730用于获取待检测目标反射的雷达信号的信号参数。
此外，收发器730还可以进一步完成其他相应的通信功能。而处理器720用于完成相应的确定或者控制操作，可选的，还可以在存储器710中存储相应的指令。各个部件的具体的处理方式可以参考前述实施例的相关描述。
本发明实施例中描述的处理器720和收发器730可实现在集成电路(integrated circuit，IC)、模拟IC、射频集成电路RFIC、混合信号IC、专用集成电路(application specific integrated circuit，ASIC)、印刷电路板(printed circuit board，PCB)、电子设备等上。该处理器和收发器也可以用各种1C工艺技术来制造，例如互补金属氧化物半导体(complementary metal oxide semiconductor,CMOS)、N型金属氧化物半导体(nMetal-oxide-semiconductor，NMOS)、P型金属氧化物半导体(positive channel metal oxide semiconductor,PMOS)、双极结型晶体管(Bipolar Junction Transistor，BJT)、双极CMOS(BiCMOS)、硅锗(SiGe)、砷化镓(GaAs)等。
可选的，上方障碍物检测装置700可以是独立的设备或者可以是较大设备的一部分。
此外，本发明实施例提供了一种可读存储介质，其上存储有计算机程序，该计算机程序被处理器执行以实现前述实施例所述的方法。
此外，本发明实施例还提供了一种计算机程序产品，当所述计算机程序被计算机执行时，用于执行前述实施例所述的方法。
在一种可能的设计中，第八方面中的程序可以全部或者部分存储在与处理器封装在一起的存储介质上，也可以部分或者全部存储在不与处理器封装在一起的存储器上。
以及，本发明实施例提供了一种上方障碍物检测系统，请参考图8，该上方障碍物检测系统800包括：
上方障碍物检测装置700；
雷达810，用于发出探测雷达信号，并接收经待检测目标反射的雷达信号。
其中，一种可能的设计中，雷达为毫米波雷达。
此外，本发明实施例还提供了一种车辆，请参考图9，该车辆900包括：上方障碍物检测系统800。该车辆900可以是包括有上方障碍物检测系统800的普通车辆，或配备有ADAS系统的车辆，或自动驾驶车辆。在一种可能的实施方式中，车辆900中的雷达810可以设置在车辆900的车头或车辆偏前方部分，从而获取车辆前方的环境信息；而上方障碍物检测装置700可以设置在车辆内部，例如接近车辆控制装置的位置，此处并不作限制。车辆900中的雷达810和上方障碍物检测装置700之间的通信可以通过CAN总线、以太网链路、无线通信、近场通信等方式，此处并不作限制。
本领域普通技术人员可以理解：实现上述方法实施例的全部或部分步骤可以通过程序指令相关的硬件来完成，前述的程序可以存储于一计算机可读取存储介质中，该程序在执行时，执行包括上述方法实施例的步骤；而前述的存储介质包括：ROM、RAM、磁碟或者光盘等各种可以存储程序代码的介质。
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 (22)

  1. 一种上方障碍物检测方法，其特征在于，包括：
    在车辆行驶过程中的目标时段内，获取待检测目标反射的雷达信号的信号参数；
    根据所述信号参数，获取所述待检测目标与所述车辆之间的相对位置关系；
    根据所述相对位置关系与所述信号参数中的信号能量在所述目标时段内的变化趋势，确定所述待检测目标是否为所述车辆的上方障碍物。
  2. 根据权利要求1所述的方法，其特征在于，所述相对位置关系包括：所述车辆与所述待检测目标之间的第一距离。
  3. 根据权利要求2所述的方法，其特征在于，所述根据所述相对位置关系与所述信号能量在所述目标时段内的变化趋势，确定所述待检测目标是否为所述车辆的上方障碍物，包括：
    在所述目标时段内，获取所述第一距离与所述信号能量之间的趋势参数；
    根据所述趋势参数与预设的趋势阈值，确定所述待检测目标是否为所述车辆的上方障碍物。
  4. 根据权利要求3所述的方法，其特征在于，所述在所述目标时段内，获取所述第一距离与所述信号能量之间的趋势参数，包括：
    获取所述目标时段内的每一帧对应的距离偏差值，所述距离偏差值为该帧对应的第一距离与所述目标时段内的连续多帧中的第一距离平均值之差；
    获取所述目标时段内的每一帧对应的信号能量偏差值，所述信号能量偏差值为该帧对应的信号能量与所述连续多帧中的信号能量平均值之差；
    获取第一变化参数与第二变化参数，其中，所述第一变化参数为所述连续多帧中，各帧的所述距离偏差值与所述能量偏差值之积的总和；所述第二变化参数为所述连续多帧中，各帧的所述距离偏差值的平方和；
    获取所述第一变化参数与所述第二变化参数之间的比值，以作为所述连续多帧对应的趋势参数。
  5. 根据权利要求4所述的方法，其特征在于，所述根据所述趋势参数与预设的趋势阈值，确定所述待检测目标是否为所述车辆的上方障碍物，包括：
    若所述连续多帧对应的趋势参数小于所述趋势阈值，确定所述待检测目 标为所述车辆的上方障碍物。
  6. 根据权利要求3所述的方法，其特征在于，所述在所述目标时段内，获取所述第一距离与所述信号能量之间的趋势参数，包括：
    获取所述目标时段内除起始帧外的每一帧对应的距离偏差值，所述距离偏差值为该帧对应的第一距离与所述起始帧对应的第一距离之差；
    获取所述目标时段内除起始帧外的每一帧对应的信号能量偏差值，所述信号能量偏差值为该帧对应的信号能量与所述起始帧对应的信号能量之差；
    在所述目标时段内除起始帧外的每一帧，获取所述信号能量偏差值与所述距离偏差值之间的比值，以作为该帧对应的趋势参数。
  7. 根据权利要求6所述的方法，其特征在于，所述根据所述趋势参数与预设的趋势阈值，确定所述待检测目标是否为所述车辆的上方障碍物，包括：
    在所述目标时段内除起始帧外的任意帧，若该帧对应的所述趋势参数小于所述趋势阈值，确定所述待检测目标为所述车辆的上方障碍物。
  8. 根据权利要求6所述的方法，其特征在于，所述根据所述趋势参数与预设的趋势阈值，确定所述待检测目标是否为所述车辆的上方障碍物，包括：
    在所述目标时段内除起始帧外的任意帧，若该帧对应的所述趋势参数小于所述趋势阈值，获取所述趋势参数小于所述趋势参数阈值的连续帧数目；
    若所述连续帧数目大于或者等于预设的帧阈值，确定所述待检测目标为所述车辆的上方障碍物，其中，所述帧阈值至少为两帧。
  9. 根据权利要求6所述的方法，其特征在于，所述根据所述趋势参数与预设的趋势阈值，确定所述待检测目标是否为所述车辆的上方障碍物，包括：
    在所述目标时段内，获取除起始帧外的各帧对应的所述趋势参数的平均值；
    若所述趋势参数的平均值小于所述趋势阈值，确定所述待检测目标为所述车辆的上方障碍物。
  10. 根据权利要求1-9任一项所述的方法，其特征在于，所述相对位置关系还包括第二距离，所述第二距离为所述待检测目标与所述雷达的指向线之间的距离。
  11. 根据权利要求10所述的方法，其特征在于，所述根据所述相对位置关系与所述信号能量在所述目标时段内的变化趋势，确定所述待检测目标是 否为所述车辆的上方障碍物之前，所述方法还包括：
    在所述目标时段内的每一帧，分别获取第一距离与所述第二距离，所述第一距离为所述待检测目标与所述车辆之间的直线距离；
    根据所述第一距离与所述第二距离，判断所述待检测目标是否为待定上方障碍物；
    若是，根据所述相对位置关系与所述信号能量在所述目标时段内的变化趋势，确定所述待检测目标是否为所述车辆的上方障碍物。
  12. 根据权利要求11所述的方法，其特征在于，所述根据所述第一距离与所述第二距离，判断所述待检测目标是否为候选障碍物，包括：
    若所述第一距离大于第一距离阈值且第二距离小于预设的第二距离阈值时，确定所述待检测目标为所述待定上方障碍物。
  13. 根据权利要求1-9任一项所述的方法，其特征在于，所述雷达信号由雷达发出，并经所述待检测目标反射后由所述雷达接收的信号。
  14. 根据权利要求13所述的方法，其特征在于，所述目标时段的结束帧为当前帧，所述目标时段的起始帧为所述雷达初始接收到反射的所述雷达信号的一帧。
  15. 根据权利要求13所述的方法，其特征在于，所述目标时段的结束帧为当前帧，所述目标时段的起始帧为所述雷达初始发出所述雷达信号后开始跟踪反射的所述雷达信号的一帧。
  16. 根据权利要求13所述方法，其特征在于，所述雷达为毫米波雷达。
  17. 一种上方障碍物检测装置，其特征在于，包括：
    存储器；
    处理器；以及
    计算机程序；
    其中，所述计算机程序存储在所述存储器中，并被配置为由所述处理器执行以实现如权利要求1-16任一项所述的方法。
  18. 根据权利要求17所述的装置，其特征在于，还包括：
    收发器，所述收发器用于获取雷达信号的信号参数。
  19. 一种上方障碍物检测系统，其特征在于，包括：
    如权利要求17或18所述的上方障碍物检测装置；
    雷达，用于发出探测雷达信号，并接收经待检测目标反射的雷达信号。
  20. 根据权利要求19所述的系统，其特征在于，所述雷达为毫米波雷达。
  21. 一种车俩，其特征在于，包括：如权利要求19或20所述的上方障碍物检测系统。
  22. 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1-16任一项所述的方法。
PCT/CN2018/118770 2018-11-30 2018-11-30 上方障碍物检测方法及装置、系统、车辆、存储介质 WO2020107474A1 (zh)

Priority Applications (2)

Application Number Priority Date Filing Date Title
CN201880040372.3A CN110785676A (zh) 2018-11-30 2018-11-30 上方障碍物检测方法及装置、系统、车辆、存储介质
PCT/CN2018/118770 WO2020107474A1 (zh) 2018-11-30 2018-11-30 上方障碍物检测方法及装置、系统、车辆、存储介质

Applications Claiming Priority (1)

Application Number Priority Date Filing Date Title
PCT/CN2018/118770 WO2020107474A1 (zh) 2018-11-30 2018-11-30 上方障碍物检测方法及装置、系统、车辆、存储介质

Publications (1)

Publication Number Publication Date
WO2020107474A1 true WO2020107474A1 (zh) 2020-06-04

Family

ID=69383078

Family Applications (1)

Application Number Title Priority Date Filing Date
PCT/CN2018/118770 WO2020107474A1 (zh) 2018-11-30 2018-11-30 上方障碍物检测方法及装置、系统、车辆、存储介质

Country Status (2)

Country Link
CN (1) CN110785676A (zh)
WO (1) WO2020107474A1 (zh)

Families Citing this family (3)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN114190821A (zh) * 2020-09-16 2022-03-18 尚科宁家(中国)科技有限公司 一种行走顺畅的清洁机器人
CN113341417B (zh) * 2021-06-09 2024-04-19 深圳市九洲电器有限公司 基于探测雷达的路面障碍检测方法、车辆及存储介质
CN113640811A (zh) * 2021-08-13 2021-11-12 浙江吉利控股集团有限公司 数据处理方法、装置、电子设备及存储介质

Citations (4)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US20080231496A1 (en) * 2007-03-20 2008-09-25 Denso Corporation Method for determining noise floor level and radar using the same
CN103513234A (zh) * 2012-06-19 2014-01-15 中国科学院电子学研究所 一种基于矩阵恢复的运动目标快速检测方法及系统
CN106383339A (zh) * 2016-08-30 2017-02-08 电子科技大学 一种多站点雷达信号级联合检测的镜像目标抑制方法
CN108205136A (zh) * 2016-12-20 2018-06-26 北京行易道科技有限公司 雷达及探测装置

Family Cites Families (3)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
AUPR301401A0 (en) * 2001-02-09 2001-03-08 Commonwealth Scientific And Industrial Research Organisation Lidar system and method
CN101216561A (zh) * 2008-01-02 2008-07-09 凌子龙 自动倒车泊车雷达
CN103033808A (zh) * 2012-12-24 2013-04-10 西安电子工程研究所 基于雷达回波特征的铁路路障探测与告警方法及装置

Patent Citations (4)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US20080231496A1 (en) * 2007-03-20 2008-09-25 Denso Corporation Method for determining noise floor level and radar using the same
CN103513234A (zh) * 2012-06-19 2014-01-15 中国科学院电子学研究所 一种基于矩阵恢复的运动目标快速检测方法及系统
CN106383339A (zh) * 2016-08-30 2017-02-08 电子科技大学 一种多站点雷达信号级联合检测的镜像目标抑制方法
CN108205136A (zh) * 2016-12-20 2018-06-26 北京行易道科技有限公司 雷达及探测装置

Also Published As

Publication number Publication date
CN110785676A (zh) 2020-02-11

Similar Documents

Publication Publication Date Title
US20210124013A1 (en) Signal processing apparatus, signal processing method, and program
US11092696B2 (en) Grouping for efficient cooperative positioning calculations
WO2020107474A1 (zh) 上方障碍物检测方法及装置、系统、车辆、存储介质
US11635766B2 (en) Method for docking and automatically charging robot, charging station and robot
US11175668B2 (en) Navigation method and apparatus, and terminal device
CN109490825B (zh) 定位导航方法、装置、设备、系统及存储介质
US20130261948A1 (en) Periphery vehicle determination apparatus
CN110782465B (zh) 一种基于激光雷达的地面分割方法、装置及存储介质
US9810766B2 (en) Method and apparatus for modeling time relationships between clocks
US10754003B2 (en) Method for determining the position of mobile node and related communication system, road side unit, and vehicle thereof
US10782395B2 (en) True velocity vector estimation using V2X
JP2014169922A (ja) 物標認識装置
US20190377087A1 (en) Vehicle location determination using synthetic aperture radar
US20210356556A1 (en) Radio Signal Sending Method and Apparatus
CN111699404B (zh) 行驶辅助目标获取方法与装置、雷达、行驶系统与车辆
US20190375422A1 (en) Dual-measurement data structure for autonomous vehicles
WO2014073558A1 (ja) 車載レーダ装置、及び、この装置における坂道判定方法
US11520019B2 (en) Light signal detection device, range finding device, and detection method
US10444343B2 (en) Mobile navigation method and system
US20220116162A1 (en) Communication method and apparatus
CN110941003B (zh) 车辆识别方法，装置，存储介质及电子设备
KR102637515B1 (ko) 차량 및 차량의 제어방법
JP2019070567A (ja) 移動体認識レーダ装置
KR20150098439A (ko) 레이더 기반 종방향 차량 검지 장치 및 방법
JP2017116445A (ja) 物体検出装置

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: 18941356

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: 18941356

Country of ref document: EP

Kind code of ref document: A1