WO2022242204A1 - 一种对象检测方法、装置、电子设备及存储介质 - Google Patents

一种对象检测方法、装置、电子设备及存储介质 Download PDF

Info

Publication number
WO2022242204A1
WO2022242204A1 PCT/CN2022/071649 CN2022071649W WO2022242204A1 WO 2022242204 A1 WO2022242204 A1 WO 2022242204A1 CN 2022071649 W CN2022071649 W CN 2022071649W WO 2022242204 A1 WO2022242204 A1 WO 2022242204A1
Authority
WO
WIPO (PCT)
Prior art keywords
data
detection
difference
detected
signal
Prior art date
Application number
PCT/CN2022/071649
Other languages
English (en)
French (fr)
Inventor
许荣雪
陈高
马雅奇
陈彦宇
Original Assignee
珠海格力电器股份有限公司
珠海联云科技有限公司
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 珠海格力电器股份有限公司, 珠海联云科技有限公司 filed Critical 珠海格力电器股份有限公司
Publication of WO2022242204A1 publication Critical patent/WO2022242204A1/zh

Links

Images

Classifications

    • G—PHYSICS
    • G01—MEASURING; TESTING
    • G01B—MEASURING LENGTH, THICKNESS OR SIMILAR LINEAR DIMENSIONS; MEASURING ANGLES; MEASURING AREAS; MEASURING IRREGULARITIES OF SURFACES OR CONTOURS
    • G01B15/00—Measuring arrangements characterised by the use of electromagnetic waves or particle radiation, e.g. by the use of microwaves, X-rays, gamma rays or electrons
    • G01B15/04—Measuring arrangements characterised by the use of electromagnetic waves or particle radiation, e.g. by the use of microwaves, X-rays, gamma rays or electrons for measuring contours or curvatures
    • G—PHYSICS
    • G01—MEASURING; TESTING
    • G01B—MEASURING LENGTH, THICKNESS OR SIMILAR LINEAR DIMENSIONS; MEASURING ANGLES; MEASURING AREAS; MEASURING IRREGULARITIES OF SURFACES OR CONTOURS
    • G01B15/00—Measuring arrangements characterised by the use of electromagnetic waves or particle radiation, e.g. by the use of microwaves, X-rays, gamma rays or electrons
    • G01B15/06—Measuring arrangements characterised by the use of electromagnetic waves or particle radiation, e.g. by the use of microwaves, X-rays, gamma rays or electrons for measuring the deformation in a solid
    • 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

Definitions

  • the present disclosure relates to the technical field of automation, and in particular to an object detection method, device, electronic equipment and storage medium.
  • Machine fault detection means that after the lower computer establishes a connection with the system, the system periodically sends a detection signal to the lower computer, and judges whether the system has a fault through the received response data frame; The reason is to determine the type of system failure, diagnose the specific failure location and cause of the system failure, and take different measures according to the cause of the failure to recover the system failure.
  • the present disclosure provides an object detection method, device, electronic equipment, and storage medium.
  • an object detection method including:
  • the reference data is calculated based on the second detection signal output by the millimeter-wave radar scanning the reference object, and the shape of the reference object is not produce defects;
  • the first difference data is greater than a preset first threshold, it is determined that a defect occurs in the shape of the object to be detected.
  • the calculating the detection data corresponding to the object to be detected based on the first detection signal includes:
  • the calculating the detection data corresponding to the object to be detected based on the electromagnetic wave signal and the first detection signal includes:
  • the phase is determined as the detection data corresponding to the object to be detected.
  • the calculating the detection data corresponding to the object to be detected based on the electromagnetic wave signal and the first detection signal includes:
  • the frequency is determined as the detection data corresponding to the object to be detected.
  • calculating the first difference data between the detection data and the preset reference data includes:
  • the difference value is determined as the first difference data.
  • the method also includes:
  • the second difference data is greater than the preset second threshold, it is determined that a defect occurs in the shape of the object to be detected after verification.
  • calculating the second difference data between the first point cloud data and the second point cloud data includes:
  • an object detection device including:
  • An acquisition module configured to acquire the first detection signal output by the millimeter-wave radar used to scan the object to be detected
  • a first calculation module configured to calculate detection data corresponding to the object to be detected based on the first detection signal
  • the second calculation module is configured to calculate the first difference data between the detection data and preset reference data, the reference data is calculated based on the second detection signal output by the millimeter-wave radar scanning the reference object , the shape of the reference object does not produce defects;
  • the determination module is configured to determine that a defect occurs in the shape of the object to be detected if the first difference data is greater than a preset first threshold.
  • the present disclosure provides an electronic device, including a processor, a communication interface, a memory, and a communication bus, wherein, the processor, the communication interface, and the memory complete mutual communication through the communication bus;
  • a memory configured to store a computer program
  • the processor is configured to implement the object detection method described in any one of the first aspect when executing the program stored in the memory.
  • the present disclosure provides a computer-readable storage medium, where a program of an object detection method is stored on the computer-readable storage medium, and when the program of the object detection method is executed by a processor, any one of the first aspects is implemented. The steps of the object detection method.
  • the first detection signal output by the millimeter-wave radar used to scan the object to be detected is obtained first, and then the detection data corresponding to the object to be detected is calculated based on the first detection signal, and then the detection data is calculated.
  • the first difference data between the data and the preset reference data, the reference data is calculated based on the second detection signal output by the millimeter-wave radar scanning the reference object, the shape of the reference object does not produce defects, if If the first difference data is greater than a preset first threshold, it can be determined that a defect occurs in the shape of the object to be detected.
  • the embodiment of the present disclosure calculates the first difference data between the detection data obtained by detecting the object to be detected and the reference data obtained by detecting the reference object, that is, calculates the reference object whose shape relative to the object to be detected does not produce defects
  • the first difference data is greater than the preset first threshold value, it can be determined that the shape of the object to be detected is defective, and the wear condition of the object can be detected automatically, and the detection result is more accurate and efficient.
  • FIG. 1 is a flowchart of an object detection method provided by an embodiment of the present disclosure
  • FIG. 2 is a schematic diagram of a detection process of a normal component provided by an embodiment of the present disclosure
  • FIG. 3 is a schematic diagram of a detection process of a wear element provided by an embodiment of the present disclosure
  • FIG. 4 is a frequency domain diagram after FFT of a normal and worn element provided by an embodiment of the present disclosure
  • FIG. 5 is a structural diagram of an object detection device provided by an embodiment of the present disclosure.
  • FIG. 6 is a structural diagram of an electronic device provided by an embodiment of the present disclosure.
  • embodiments of the present disclosure provide an object detection method, an apparatus, an electronic device, and a storage medium, and the object detection method may be applied to electronic devices and the like.
  • an object detection method can include the following steps:
  • Step S101 acquiring a first detection signal output by a millimeter-wave radar configured to scan an object to be detected;
  • the object to be detected may refer to the component to be detected, etc.
  • the millimeter wave radar may be installed inside or outside the electronic device, and the CPU in the electronic device may communicate with the millimeter wave radar.
  • the CPU can send control instructions to the millimeter-wave radar.
  • the millimeter-wave radar sends electromagnetic wave signals to the object to be detected through the electromagnetic wave transmitter according to the control instructions.
  • the object to be detected reflects electromagnetic wave signals to many directions. A part of the electromagnetic wave signal (such as: millimeter wave) is reflected back to the antenna of the receiving end of the millimeter wave radar by the object to be detected and is received by the radar.
  • the millimeter wave radar outputs the first detection signal, and then the CPU of the electronic device can obtain the first detection signal.
  • the millimeter-wave radar can be set on the side of the object to be detected. There is no obstacle between the millimeter-wave radar and the object to be detected. The distance between the objects to be detected is within the effective radiation range of the millimeter-wave radar, and the millimeter-wave radar is kept powered on and normal signal transmission and reception.
  • Step S102 calculating detection data corresponding to the object to be detected based on the first detection signal
  • the corresponding first detection signal detected by the millimeter-wave radar should also be regular and Periodic, as shown in Figure 2, when the object is worn, the surface of the object is not smooth, and the first detection signal reflected from the electromagnetic wave signal emitted by the millimeter-wave radar to the worn part will appear abnormal. Therefore, it is necessary to calculate the change of the first detection signal relative to the original emitted electromagnetic wave signal, so in this step, the detection data corresponding to the object to be detected can be calculated based on the first detection signal.
  • Step S103 calculating first difference data between the detected data and preset reference data
  • the reference data is calculated based on the second detection signal output by the millimeter-wave radar scanning the reference object, and the shape of the reference object has no defects, and is used as a reference standard to measure the external shape of the object to be detected The amount of change that occurs.
  • the reference object can refer to an unworn element.
  • the reference object can refer to an object to be detected that has not been put into use.
  • the reference object can also refer to the same batch of objects as the object to be detected, that is, the external shape of the reference object is exactly the same as that of the object to be detected;
  • the reference data of the reference object can be pre-determined.
  • the CPU can send control instructions to the millimeter-wave radar.
  • the millimeter-wave radar sends electromagnetic wave signals to the reference object through the electromagnetic wave transmitter according to the control instructions.
  • the reference object reflects the electromagnetic wave signal to many directions, and part of the electromagnetic wave signal (such as: millimeter wave) is reflected by the reference object back to the receiving end antenna of the millimeter wave radar to be received by the radar, and the millimeter wave radar outputs the second detection signal, based on the second
  • the detected signal calculates reference data corresponding to the reference object.
  • the difference between the detection data and the reference data can be directly obtained to obtain a difference, and the difference is determined as the first difference data.
  • Step S104 if the first difference data is greater than a preset first threshold, it is determined that a defect occurs in the shape of the object to be detected.
  • the first difference data can be compared with the preset first threshold value, if the first difference data is greater than the preset first threshold value, it can be determined that the shape of the object to be detected has a defect, that is, wear; if the first difference data If it is less than or equal to the preset first threshold, it can be determined that the shape of the object to be detected has no defect, that is, no wear.
  • the embodiment of the present disclosure calculates the first difference data between the detection data obtained by detecting the object to be detected and the reference data obtained by detecting the reference object, that is, calculates the reference object whose shape relative to the object to be detected does not produce defects
  • the first difference data is greater than the preset first threshold value, it can be determined that the shape of the object to be detected is defective, and the wear condition of the object can be detected automatically, and the detection result is more accurate and efficient.
  • the calculating the detection data corresponding to the object to be detected based on the first detection signal includes:
  • Step 201 acquiring the electromagnetic wave signal emitted by the millimeter wave radar to the object to be detected;
  • Step 202 calculating detection data corresponding to the object to be detected based on the electromagnetic wave signal and the first detection signal.
  • the embodiments of the present disclosure can calculate the detection data based on the electromagnetic wave signal and the first detection signal, so as to facilitate knowing the amount of change of the first detection signal relative to the electromagnetic wave signal.
  • the electromagnetic wave signal is transmitted, returns after encountering an obstacle, and the receiving antenna receives the signal. Because there is a certain distance between the obstacle and the radar, there is a receiving time difference. It can be seen from Figure 2 and Figure 3 that the small circle is the radar, and the large regular heptagon is the component with detection. The component in Figure 2 is normal, and the component in Figure 3 is worn out. In this way, the reflected echo received by the radar will be extended, and the time t is longer than the wavelength received by the normal component, and the received signal is the same as the transmitted signal. The difference is only a time difference. On the one hand, the time difference can be It is reflected in the phase difference, so the phase difference can be used to determine whether the component is worn or not.
  • the calculating the detection data corresponding to the object to be detected based on the electromagnetic wave signal and the first detection signal includes:
  • Step 301 making a difference between the electromagnetic wave signal and the first detection signal to obtain a difference frequency signal
  • Step 302 converting the difference frequency signal from the time domain to the frequency domain, and determining the phase of the difference frequency signal
  • the difference frequency signal can be converted to the frequency domain by fast Fourier transform (FFT), and analyzed in the frequency domain to obtain
  • FFT fast Fourier transform
  • ⁇ is the circumference ratio, which is a definite value
  • ⁇ d is the size of the wear
  • ⁇ is the wavelength of the millimeter wave, which is uniquely determined by the parameters of the millimeter wave radar.
  • this parameter is the only constant. value. It can be seen from the formula that the phase is only related to ⁇ d, and the phase is positively correlated with ⁇ d.
  • Step 303 determining the phase as the detection data corresponding to the object to be detected.
  • the signal received by the millimeter wave and reflected back by the detected element is transformed by FFT to obtain a frequency domain map, and the phase of the peak value in the frequency domain is the phase of the difference frequency signal.
  • the phase of the reference element at the peak in the frequency domain is ⁇ 0
  • the difference between the phase of the normal element and ⁇ 0 at the energy peak will be small, and the difference between the phase of the worn element and ⁇ 0 at the energy peak will be large, so by Comparing the two phases can determine whether the component is worn or not.
  • the phase difference threshold determines whether the phase difference between the phase of the difference frequency signal of the object to be detected and the phase of the difference frequency signal of the reference object (which can be calculated and obtained in a similar manner as in this embodiment) is greater than the phase difference threshold.
  • the embodiment of the present disclosure can automatically determine the phase of the beat frequency signal as the detection data, so as to facilitate subsequent determination of whether the object to be detected is worn or not based on the detection data.
  • the electromagnetic wave signal is transmitted, returns after encountering an obstacle, and the receiving antenna receives the signal. Because there is a certain distance between the obstacle and the radar, there is a receiving time difference. It can be seen from Figure 2 and Figure 3 that the small circle is the radar, and the large regular heptagon is the component with detection. The component in Figure 2 is normal, and the component in Figure 3 is worn out, so that the reflected echo received by the radar will be extended, and the time t is longer than the wavelength received by the normal component, and the received signal is the same as the transmitted signal. The difference is only a time difference. On the other hand, the time difference It can be reflected in the frequency difference, so the frequency difference can be used to determine whether the component is worn or not.
  • the calculating the detection data corresponding to the object to be detected based on the electromagnetic wave signal and the first detection signal includes:
  • Step 401 making a difference between the electromagnetic wave signal and the first detection signal to obtain a difference frequency signal
  • Step 402 converting the difference frequency signal from the time domain to the frequency domain, and determining the frequency of the difference frequency signal
  • the difference frequency signal can be converted to the frequency domain by fast Fourier transform (FFT), and analyzed in the frequency domain to obtain The frequency of the beat signal.
  • FFT fast Fourier transform
  • the frequency can be calculated by the following formula:
  • ⁇ is the frequency modulation slope of the millimeter-wave signal, which is uniquely determined by the parameters of the millimeter-wave radar.
  • this parameter is the only fixed value;
  • ⁇ d is the size of the wear;
  • c is the light in the atmosphere The propagation velocity in is also a definite value. It can be seen from the formula that the frequency is only related to ⁇ d, and the frequency is positively correlated with ⁇ d.
  • Step 403 determining the frequency as the detection data corresponding to the object to be detected
  • the signal received by the millimeter wave and reflected by the detected element is transformed by FFT to obtain a frequency domain diagram, and the frequency where the peak is located is the frequency of the difference frequency signal.
  • the frequency difference between the beat frequency signal obtained by the normal component and the reference component is small, while the frequency difference between the beat frequency signal obtained by the worn component and the reference component is relatively large. Whether the component is worn or not can be judged by comparing the frequency difference between the tested component and the reference component.
  • the minimum frequency difference that millimeter wave radar can detect is Among them, Fs is the sampling rate used by the system, and N is the number of points for FFT transformation of the difference frequency signal. Combined with the formula of the difference frequency signal frequency, it can be concluded that the minimum wear size that can be detected by the frequency difference method is
  • the frequency modulation slope of the millimeter-wave radar is 30M/ ⁇ s (frequency modulation slope unit, megamicrosecond)
  • the sampling rate is 10M
  • the number of sampling points is 300 points.
  • the number of FFT points used for FFT transformation is 512 points
  • the estimated value of c is 299792458 meters. /sec
  • the minimum size that can be detected is
  • ⁇ d 0.0976 meters, that is, when the wear distance is greater than 9.76 cm, the frequency difference method is selected for detection, and when the wear size is less than 9.76 cm, the phase difference method is used for detection. At this time, the minimum wear that can be detected by the frequency difference method is 9.76 cm.
  • the frequency difference threshold is
  • the preset first threshold may use the frequency difference threshold in the embodiment of the present disclosure, when the first difference data is the frequency of the frequency difference signal of the object to be detected and the frequency of the frequency difference signal of the reference object (which can be used in accordance with this embodiment
  • the frequency difference between calculated and obtained in a similar manner in the example
  • the frequency difference threshold it is determined that the part is worn.
  • the automatic frequency may be determined as the detection data, which is convenient for subsequently determining whether the object to be detected is worn or not based on the detection data.
  • the phase method or the frequency method can be selected to detect whether the component is worn.
  • the phase method is used to judge whether it is worn.
  • the frequency method is used for detection. Therefore, first use the frequency method to detect, if the detected frequency difference is greater than the threshold, it is judged that there is wear; threshold, it is judged that there is no wear and components are normal.
  • the method further includes:
  • Step 501 converting the first detection signal into first point cloud data
  • the first detection signal can be processed into the first point cloud data by signal processing methods such as distance FFT, velocity FFT, channel accumulation amplitude energy matrix or Cfar.
  • Step 502 acquiring second point cloud data converted from the second detection signal
  • the second detection signal can be processed into the second point cloud data by means of signal processing methods such as distance FFT, velocity FFT, channel accumulation amplitude energy matrix, or Cfar.
  • Step 503 calculating second difference data between the first point cloud data and the second point cloud data
  • the difference between the first point cloud data and the second point cloud can be compared to obtain second difference data.
  • step 504 if the second difference data is greater than a preset second threshold, it is determined that a defect occurs in the shape of the object to be detected after verification.
  • the embodiment of the present disclosure can convert the first detection signal and the second detection signal into the first point cloud data and the second point cloud data respectively, calculate the difference between the two, and then compare with the preset second threshold, Further verification of the judgment result of whether the object is worn or not in the foregoing embodiments is realized, and the accuracy of parts wear detection is improved.
  • calculating the second difference data between the first point cloud data and the second point cloud data includes:
  • Step 601 extracting a first distance value and a first angle value between the millimeter wave radar and the object to be detected from the first point cloud data;
  • Step 602 extracting a second distance value and a second angle value between the millimeter-wave radar and the reference object from the second point cloud data;
  • Step 603 constructing a first matrix based on the first distance value and the first angle value, and constructing a second matrix based on the second distance value and the second angle value;
  • Step 604 calculate the similarity between the first matrix and the second matrix, and determine the obtained similarity data as the second difference data.
  • the distance and angle values are obtained after processing.
  • the similarity of the matrix we will find that the similarity between the worn element and the normal element is low, and the similarity formula between matrix A and matrix B is as follows:
  • A represents the data matrix of normal components
  • B represents the data matrix of worn components
  • Tr represents the trace (rank) of the matrix
  • A' represents the transpose matrix of A
  • B represents the transpose matrix of B'
  • s represents the dimension of the matrix number.
  • the embodiment of the present disclosure can automatically calculate the similarity between the matrices, and then obtain the second difference data between the first point cloud data and the second point cloud data, that is, obtain the difference between the first detection signal and the second detection signal.
  • the differences are convenient for further verification of the results obtained in the foregoing embodiments on object wear discrimination.
  • an object detection device including:
  • the acquisition module 11 is configured to acquire the first detection signal output by the millimeter-wave radar for scanning the object to be detected;
  • the first calculation module 12 is configured to calculate detection data corresponding to the object to be detected based on the first detection signal
  • the second calculation module 13 is configured to calculate the first difference data between the detection data and preset reference data, the reference data is calculated based on the second detection signal output by the millimeter-wave radar scanning the reference object , the shape of the reference object does not produce defects;
  • the determination module 14 is configured to determine that a defect occurs in the shape of the object to be detected if the first difference data is greater than a preset first threshold.
  • an electronic device including a processor, a communication interface, a memory, and a communication bus, wherein the processor, the communication interface, and the memory complete mutual communication through the communication bus;
  • a memory configured to store a computer program
  • the processor When the processor is configured to execute the program stored in the memory, it implements the object detection method described in any one of the foregoing method embodiments.
  • the processor executes the program stored in the memory to first obtain the first detection signal output by the millimeter-wave radar set to scan the object to be detected, and then based on the first detection Calculate the detection data corresponding to the object to be detected, and then calculate the first difference data between the detection data and the preset reference data, the reference data is based on the first output of the millimeter-wave radar scanning reference object Based on the calculated two detection signals, the shape of the reference object has no defect, and if the first difference data is greater than a preset first threshold, it can be determined that the shape of the object to be inspected has a defect.
  • the embodiment of the present disclosure calculates the first difference data between the detection data obtained by detecting the object to be detected and the reference data obtained by detecting the reference object, that is, calculates the reference object whose shape relative to the object to be detected does not produce defects
  • the first difference data is greater than the preset first threshold value, it can be determined that the shape of the object to be detected is defective, and the wear condition of the object can be detected automatically, and the detection result is more accurate and efficient.
  • the communication bus 1140 mentioned in the above electronic device may be a Peripheral Component Interconnect (PCI for short) bus or an Extended Industry Standard Architecture (EISA for short) bus or the like.
  • PCI Peripheral Component Interconnect
  • EISA Extended Industry Standard Architecture
  • the communication bus 1140 can be divided into address bus, data bus, control bus and so on. For ease of representation, only one thick line is used in FIG. 6 , but it does not mean that there is only one bus or one type of bus.
  • the communication interface 1120 is provided for communication between the above-mentioned electronic device and other devices.
  • the memory 1130 may include a random access memory (Random Access Memory, RAM for short), and may also include a non-volatile memory (non-volatile memory), such as at least one disk memory. In some implementations, the memory may also be at least one storage device located far away from the aforementioned processor.
  • RAM Random Access Memory
  • non-volatile memory such as at least one disk memory.
  • the memory may also be at least one storage device located far away from the aforementioned processor.
  • the above-mentioned processor 1110 can be a general-purpose processor, including a central processing unit (Central Processing Unit, referred to as CPU), a network processor (Network Processor, referred to as NP), etc.; it can also be a digital signal processor (Digital Signal Processing, referred to as DSP), an application-specific integrated circuit (Application Specific Integrated Circuit, referred to as ASIC), Field-Programmable Gate Array (Field-Programmable Gate Array, referred to as FPGA) or other programmable logic devices, discrete gate or transistor logic devices, discrete hardware components.
  • CPU Central Processing Unit
  • NP Network Processor
  • DSP Digital Signal Processing
  • ASIC Application Specific Integrated Circuit
  • FPGA Field-Programmable Gate Array
  • FPGA Field-Programmable Gate Array
  • a computer-readable storage medium is also provided, the program of the object detection method is stored on the computer-readable storage medium, and when the program of the object detection method is executed by a processor, the aforementioned The steps of the object detection method described in any method embodiment.

Landscapes

  • Physics & Mathematics (AREA)
  • Electromagnetism (AREA)
  • General Physics & Mathematics (AREA)
  • Engineering & Computer Science (AREA)
  • Radar, Positioning & Navigation (AREA)
  • Remote Sensing (AREA)
  • Computer Networks & Wireless Communication (AREA)
  • Radar Systems Or Details Thereof (AREA)

Abstract

一种对象检测方法、装置、电子设备及存储介质，其中，对象检测方法包括：获取被设置为对待检测对象进行扫描的毫米波雷达输出的第一检测信号（S101）；基于第一检测信号计算与待检测对象对应的检测数据（S102）；计算检测数据与预设的参考数据之间的第一差异数据（S103），参考数据是基于毫米波雷达扫描参考对象输出的第二检测信号计算得到的，参考对象的形状未产生缺陷；若第一差异数据大于预设第一阈值，确定待检测对象的形状产生缺陷（S104）。通过基于对待检测对象检测得到的检测数据与对参考对象检测得到的参考数据，得到待检测对象相对于的形状未产生缺陷的参考对象之间发生的形变量，通过和预设第一阈值比较，可以确定待检测对象的形状产生缺陷，实现自动检测对象的磨损情况，检测结果更加准确且效率更高。

Description

一种对象检测方法、装置、电子设备及存储介质
本公开要求于2021年05月17日提交中国专利局、申请号为202110534302.7、发明名称为“一种对象检测方法、装置、电子设备及存储介质”的中国专利申请的优先权，其全部内容通过引用结合在本公开中。
技术领域
本公开涉及自动化技术领域，尤其涉及一种对象检测方法、装置、电子设备及存储介质。
背景技术
机器故障检测是指下位机与系统建立连接后，系统周期性地向下位机发送检测信号，通过接收的响应数据帧，判断系统是否产生故障；故障类型判断就是系统在检测出故障之后，通过分析原因，判断出系统故障的类型，诊断出系统具体故障部位和故障原因，根据故障原因，采取不同的措施，对系统故障进行恢复。
对于现实生活中用于流水线生产的设备，通常在生产过程中就会出现设备磕碰和机器长期使用引发的机器元件磨损故障问题，常规的故障诊断仪器都较大型复杂，并且需要人工检查，通过人工对每个元件都检查耗费人力和时间，并且由于人的疲劳或者没注意，可能存在部分元件漏检的现象，这样精度和准确率低，效率低，没有及时发现的磨损元件将其安装到机器上，会造成生产安全问题。轻则产品不合格，返场重修，重则会有零件掉落，机器停滞等问题，影响工作还会导致使用机器的人员受伤。
发明内容
为了解决上述人工检查机器元件磨损准确率低且效率低的技术问题，本公开提供了一种对象检测方法、装置、电子设备及存储介质。
第一方面，本公开提供了一种对象检测方法，包括：
获取被设置为对待检测对象进行扫描的毫米波雷达输出的第一检测信号；
基于所述第一检测信号计算与所述待检测对象对应的检测数据；
计算所述检测数据与预设的参考数据之间的第一差异数据，所述参考数据是基于所述毫米波雷达扫描参考对象输出的第二检测信号计算得到的，所述参考对象的形状未产生缺陷；
若所述第一差异数据大于预设第一阈值，确定所述待检测对象的形状产生缺陷。
在一些实施方式中，所述基于所述第一检测信号计算与所述待检测对象对应的检测数据，包括：
获取所述毫米波雷达向待检测对象发射的电磁波信号；
基于所述电磁波信号和所述第一检测信号计算与所述待检测对象对应的检测数据。
在一些实施方式中，所述基于所述电磁波信号和所述第一检测信号计算与所述待检测对象对应的检测数据，包括：
将所述电磁波信号和所述第一检测信号做差，得到差频信号；
将所述差频信号从时域转化至频域，确定所述差频信号的相位；
将所述相位确定为与所述待检测对象对应的所述检测数据。
在一些实施方式中，所述基于所述电磁波信号和所述第一检测信号计算与所述待检测对象对应的检测数据，包括：
将所述电磁波信号和所述第一检测信号做差，得到差频信号；
将所述差频信号从时域转化至频域，确定所述差频信号的频率；
将所述频率确定为与所述待检测对象对应的所述检测数据。
在一些实施方式中，计算所述检测数据与预设的参考数据之间的第一差异数据，包括：
将所述检测数据与所述参考数据做差，得到差值；
将所述差值确定为所述第一差异数据。
在一些实施方式中，所述方法还包括：
将所述第一检测信号转化为第一点云数据；
获取所述第二检测信号转化成的第二点云数据；
计算所述第一点云数据和第二点云数据之间的第二差异数据；
若所述第二差异数据大于预设第二阈值，确定经过验证所述待检测对象的形状产生缺陷。
在一些实施方式中，计算所述第一点云数据和第二点云数据之间的第二差异数据，包括：
在所述第一点云数据中提取所述毫米波雷达与所述待检测对象之间的第一距离值和第一角度值；
在所述第二点云数据中提取所述毫米波雷达与所述参考对象之间的第二距离值和第二角度值；
基于所述第一距离值和第一角度值构建第一矩阵，基于所述第二距离值和第二角度值构建第二矩阵；
计算所述第一矩阵和所述第二矩阵之间的相似度，将得到的相似度数据确定为所述第二差异数据。
第二方面，本公开提供了一种对象检测装置，包括：
获取模块，被设置为获取用于对待检测对象进行扫描的毫米波雷达输出的第一检测信号；
第一计算模块，被设置为基于所述第一检测信号计算与所述待检测对象对应的检测数据；
第二计算模块，被设置为计算所述检测数据与预设的参考数据之间的第一差异数据，所述参考数据是基于所述毫米波雷达扫描参考对象输出的第二检测信号计算得到的，所述参考对象的形状未产生缺陷；
确定模块，被设置为若所述第一差异数据大于预设第一阈值，确定所 述待检测对象的形状产生缺陷。
第三方面，本公开提供了一种电子设备，包括处理器、通信接口、存储器和通信总线，其中，处理器，通信接口，存储器通过通信总线完成相互间的通信；
存储器，被设置为存放计算机程序；
处理器，被设置为执行存储器上所存放的程序时，实现第一方面任一所述的对象检测方法。
第四方面，本公开提供了一种计算机可读存储介质，所述计算机可读存储介质上存储有对象检测方法的程序，所述对象检测方法的程序被处理器执行时实现第一方面任一所述的对象检测方法的步骤。
本公开实施例提供的上述技术方案与相关技术相比具有如下优点：
本公开实施例通过首先获取用于对待检测对象进行扫描的毫米波雷达输出的第一检测信号，然后基于所述第一检测信号计算与所述待检测对象对应的检测数据，再计算所述检测数据与预设的参考数据之间的第一差异数据，所述参考数据是基于所述毫米波雷达扫描参考对象输出的第二检测信号计算得到的，所述参考对象的形状未产生缺陷，若所述第一差异数据大于预设第一阈值，可以确定所述待检测对象的形状产生缺陷。
本公开实施例通过基于对待检测对象检测得到的检测数据与对参考对象检测得到的参考数据，计算二者之间的第一差异数据，即计算待检测对象相对于的形状未产生缺陷的参考对象之间发生的形变量，在第一差异数据大于预设第一阈值时，可以确定待检测对象的形状产生缺陷，实现自动检测对象的磨损情况，检测结果更加准确且效率更高。
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。
为了更清楚地说明本公开实施例或相关技术中的技术方案，下面将对 实施例或相关技术描述中所需要使用的附图作简单地介绍，显而易见地，对于本领域普通技术人员而言，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为本公开实施例提供的一种对象检测方法的流程图；
图2为本公开实施例提供的一种正常元件的检测过程示意图；
图3为本公开实施例提供的一种磨损元件的检测过程示意图；
图4为本公开实施例提供的一种正常与磨损元件FFT后频域图；
图5为本公开实施例提供的一种对象检测装置的结构图；
图6为本公开实施例提供的一种电子设备的结构图。
具体实施方式
为使本公开实施例的目的、技术方案和优点更加清楚，下面将结合本公开实施例中的附图，对本公开实施例中的技术方案进行清楚、完整地描述，显然，所描述的实施例是本公开的一部分实施例，而不是全部的实施例。基于本公开中的实施例，本领域普通技术人员在没有做出创造性劳动的前提下所获得的所有其他实施例，都属于本公开保护的范围。
由于相关技术中，对于现实生活中用于流水线生产的设备，通常在生产过程中就会出现设备磕碰和机器长期使用引发的机器元件磨损故障问题，常规的故障诊断仪器都较大型复杂，并且需要人工检查，通过人工对每个元件都检查耗费人力和时间，并且由于人的疲劳或者没注意，可能存在部分元件漏检的现象，这样精度和准确率低，效率低，没有及时发现的磨损元件将其安装到机器上，会造成生产安全问题。轻则产品不合格，返场重修，重则会有零件掉落，机器停滞等问题，影响工作还会导致使用机器的人员受伤。为此，本公开实施例提供了一种对象检测方法、装置、电子设备及存储介质，所述对象检测方法可以应用于电子设备中等。
如图1所示，对象检测方法可以包括以下步骤：
步骤S101，获取被设置为对待检测对象进行扫描的毫米波雷达输出的第一检测信号；
本公开实施例中，待检测对象可以指待检测的元件等，毫米波雷达可以设置于电子设备内部，也可以设置于电子设备外部，电子设备内的CPU可以与毫米波雷达通信连接，当需要检测待检测对象是否磨损时，CPU可以向毫米波雷达发送控制指令，毫米波雷达根据控制指令，通过电磁波发送端向待检测对象发送电磁波信号，待检测对象将电磁波信号反射到很多方向上，其中一部分电磁波信号(如：毫米波)经待检测对象反射回毫米波雷达的接收端天线被雷达接收，毫米波雷达输出第一检测信号，进而，电子设备的CPU可以获取到第一检测信号。
在实际应用中，为保证能够收到更加准确的第一检测信号，毫米波雷达可以设置于待检测对象待检测的一面，毫米波雷达与待检测对象之间无障碍物遮挡，毫米波雷达与待检测对象之间的距离位于毫米波雷达的有效辐射范围内，并且保持毫米波雷达通电及正常的信号发射与接收。
为了提高后续判别工作的准确率，可以对毫米波雷达接收到的第一检测信号进行杂波过滤处理，得到过滤后纯净的信号，这样可以减少杂波干扰。
步骤S102，基于所述第一检测信号计算与所述待检测对象对应的检测数据；
由于正常未磨损的对象，在使用过程中，由于毫米波雷达发射的电磁波信号是具有预设波形的电磁波信号，所以，相应的毫米波雷达探测到的第一检测信号也应当是有规律性有周期的，而如图2所示，对象被磨损时，对象表面不平整，毫米波雷达发射电磁波信号到磨损处反射回来的第一检测信号会出现异常。所以，需要计算出第一检测信号相对于原始发射的电磁波信号的的变化，所以在该步骤中，可以基于第一检测信号计算与所述待检测对象对应的检测数据。
步骤S103，计算所述检测数据与预设的参考数据之间的第一差异数据；
在本公开实施例中，参考数据是基于所述毫米波雷达扫描参考对象输出的第二检测信号计算得到的，所述参考对象的形状未产生缺陷，用以作为参考标准衡量待检测对象外部形态发生的变化量，示例性的，参考对象 可以指未磨损的元件，在本公开的一种实施方式中，该参考对象可以指未被投入使用的待检测对象，在本公开的另一种实施方式中，该参考对象还可以指与待检测对象同一批次的对象，即参考对象与待检测对象的外部形态完全相同；
在实际应用中，可以预先确定参考对象的参考数据，具体的，CPU可以向毫米波雷达发送控制指令，如图3所示，毫米波雷达根据控制指令，通过电磁波发送端向参考对象发送电磁波信号，参考对象将电磁波信号反射到很多方向上，其中一部分电磁波信号(如：毫米波)经参考对象反射回毫米波雷达的接收端天线被雷达接收，毫米波雷达输出第二检测信号，基于第二检测信号计算与参考对象对应的参考数据。
在该步骤中，可以直接将检测数据与参考数据做差，得到差值，将该差值确定为第一差异数据。
步骤S104，若所述第一差异数据大于预设第一阈值，确定所述待检测对象的形状产生缺陷。
在该步骤中，可以将第一差异数据与预设第一阈值比较，若第一差异数据大于预设第一阈值，则可以确定待检测对象的形状产生缺陷，即磨损；若第一差异数据小于或者等于预设第一阈值，则可以确定待检测对象的形状未产生缺陷，即未磨损。
本公开实施例通过首先获取被设置为对待检测对象进行扫描的毫米波雷达输出的第一检测信号，然后基于所述第一检测信号计算与所述待检测对象对应的检测数据，再计算所述检测数据与预设的参考数据之间的第一差异数据，所述参考数据是基于所述毫米波雷达扫描参考对象输出的第二检测信号计算得到的，所述参考对象的形状未产生缺陷，若所述第一差异数据大于预设第一阈值，可以确定所述待检测对象的形状产生缺陷。
本公开实施例通过基于对待检测对象检测得到的检测数据与对参考对象检测得到的参考数据，计算二者之间的第一差异数据，即计算待检测对象相对于的形状未产生缺陷的参考对象之间发生的形变量，在第一差异数据大于预设第一阈值时，可以确定待检测对象的形状产生缺陷，实现自动 检测对象的磨损情况，检测结果更加准确且效率更高。
在本公开的又一实施例中，所述基于所述第一检测信号计算与所述待检测对象对应的检测数据，包括：
步骤201，获取所述毫米波雷达向待检测对象发射的电磁波信号；
步骤202，基于所述电磁波信号和所述第一检测信号计算与所述待检测对象对应的检测数据。
本公开实施例能够基于电磁波信号和第一检测信号计算检测数据，便于了解第一检测信号相对于电磁波信号的变化量。
电磁波信号发射，遇到障碍物后返回，接收天线接收信号，因为障碍物与雷达之间有一定距离就产生了接收时间差。由图2和图3可知，小圆是雷达，大的正七边形是带检测的元件。图2中元件正常，图3元件磨损一块，这样雷达收到的反射回波会延长，时间t比接收正常元件回波长，而接收信号和发射信号相同，区别只是有时间差，该时间差一方面可以体现为相位差，所以，可以通过相位差判定元件是否有磨损。在本公开的又一实施例中，所述基于所述电磁波信号和所述第一检测信号计算与所述待检测对象对应的检测数据，包括：
步骤301，将所述电磁波信号和所述第一检测信号做差，得到差频信号；
通过该步骤，可以计算得到第一检测信号相对于电磁波信号的变化。
步骤302，将所述差频信号从时域转化至频域，确定所述差频信号的相位；
为了便于分析第一检测信号相对于电磁波信号在时间和能量上的变化，在该步骤中，可以将差频信号通过快速傅里叶变换(FFT)转化至频域，在频域进行分析，得到差频信号的相位，相位可以通过如下公式计算：
ΔΦ＝4πΔd/λ
其中，π是圆周率，是确定的值；Δd是磨损的尺寸；λ是毫米波的波长，由毫米波雷达参数唯一确定，当确定毫米波雷达使用的发射信号的时候，该参数是唯一的定值。从公式可以看出，相位只和Δd有关，并且相位和Δd 成正相关。
步骤303，将所述相位确定为与所述待检测对象对应的所述检测数据。
毫米波接收到的由被探测元件反射回的信号经过FFT变换后，得到频域图，频域中峰值的相位就是差频信号的相位。假设参考元件在频域峰值的相位是Φ 0，则正常元件在能量峰值处的相位与Φ 0的差会小，而磨损的元件在能量峰值处的相位与Φ 0的差会大，因此通过对比两个相位就可以判断元件磨损与否。根据公式，假设参考元件Δd＝0，则相位Φ 0＝0，被测元件磨损了Δd＝0.5mm(毫米)，所用的毫米波雷达波长是λ＝5mm(毫米)，则相位是ΔΦ＝0.4π。相应的，预设第一阈值在本公开实施例中可以使用相位差阈值，相位差阈值可以根据元件磨损阈值来确定。假设元件可以接受的磨损最大为d 0，则相位差阈值可以取ΔΦ＝4πd 0/λ。当第一差异数据即待检测对象的差频信号的相位与参考对象的差频信号的相位(可以利用与本实施例中类似方式计算获得)之间的相位差大于这个相位差阈值时，确定零件有磨损。
本公开实施例可以自动将差频信号的相位确定为检测数据，便于后续基于检测数据判别待检测对象是否磨损。
电磁波信号发射，遇到障碍物后返回，接收天线接收信号，因为障碍物与雷达之间有一定距离就产生了接收时间差。由图2和图3可知，小圆是雷达，大的正七边形是带检测的元件。图2中元件正常，图3元件磨损一块，这样雷达收到的反射回波会延长，时间t比接收正常元件回波长，而接收信号和发射信号相同，区别只是有时间差，该时间差另一方面可以体现为频率差，所以，可以通过频率差判定元件是否有磨损。在本公开的又一实施例中，所述基于所述电磁波信号和所述第一检测信号计算与所述待检测对象对应的检测数据，包括：
步骤401，将所述电磁波信号和所述第一检测信号做差，得到差频信号；
通过该步骤，可以计算得到第一检测信号相对于电磁波信号的变化。
步骤402，将所述差频信号从时域转化至频域，确定所述差频信号的频率；
为了便于分析第一检测信号相对于电磁波信号在时间和能量上的变 化，在该步骤中，可以将差频信号通过快速傅里叶变换(FFT)转化至频域，在频域进行分析，得到差频信号的频率。
频率可以通过如下公式计算：
Δf＝2μΔd/c
其中，μ是毫米波信号的调频斜率，由毫米波雷达参数唯一确定，当确定毫米波雷达使用的发射波形的时候，该参数是唯一的定值；Δd是磨损的尺寸；c是光在大气中的传播速度，也是确定的值。从公式可以看出，频率只和Δd有关，并且频率和Δd成正相关。
步骤403，将所述频率确定为与所述待检测对象对应的所述检测数据；
如图4所示，毫米波接收到的由被探测元件反射回的信号经过FFT变换后，得到频域图，峰值所在的频率就是差频信号的频率。正常元件得到的差频信号的频率与参考元件差频信号的频率差小，而磨损元件得到的差频信号的频率与参考元件的差频信号的的频率差较大。根据对比被测元件和参考元件的频率差就可以判断元件磨损与否。
毫米波雷达能够检测出的频率差最小为
Figure PCTCN2022071649-appb-000001
其中，Fs是系统使用的采样率，N是差频信号进行FFT变换的点数。结合差频信号频率的公式可以得出，能够使用频率差方法检测出的最小磨损尺寸为
Figure PCTCN2022071649-appb-000002
假设毫米波雷达调频斜率是30M/μs(调频斜率单位，兆每微妙)，采样率是10M，采样点数300点，进行FFT变换的时候使用的FFT点数是512点，光速c取估计值299792458米/秒，则能检测出的最小尺寸是
Δd＝0.0976米，即磨损距离大于9.76厘米的时候选择频率差方法检测，当磨损尺寸小于9.76厘米的时候使用相位差方法检测。此时频率差方法能够检测到的最小磨损是9.76厘米。频率差阈值是
Figure PCTCN2022071649-appb-000003
相应的，预设第一阈值在本公开实施例中可以使用频率差阈值，当第一差异数据即待检测对象的差频信号的频率与参考对象的差频信号的频率(可以利用与本实施例中类似方式计算获得)之间的频率差大于这个频率 差阈值时，确定零件有磨损。
本公开实施例可以自动频率确定为检测数据，便于后续基于检测数据判别待检测对象是否磨损。
检测元件是否磨损可以选择相位法或者频率法，当磨损较小时，使用相位法判断是否磨损，当磨损较大时使用频率法检测。因此，首先使用频率法检测，如果检测到频率差大于阈值，则判断有磨损；如果频率差小于阈值，再使用相位法做精确检测，如果相位差大于阈值，则判断有磨损，如果相位差小于阈值，则判断没有磨损，元件正常。
在本公开的又一实施例中，所述方法还包括：
步骤501，将所述第一检测信号转化为第一点云数据；
由于磨损的不达标的元件反射回信号不同于正常元件，可以通过距离FFT、速度FFT、通道累加幅值能量矩阵或者Cfar等信号处理手段，将第一检测信号处理成第一点云数据。
步骤502，获取所述第二检测信号转化成的第二点云数据；
同理，可以通过距离FFT、速度FFT、通道累加幅值能量矩阵或者Cfar等信号处理手段，将第二检测信号处理成第二点云数据。
步骤503，计算所述第一点云数据和第二点云数据之间的第二差异数据；
在该步骤中，可以比较第一点云数据和第二点云之间的差异，得到第二差异数据。
步骤504，若所述第二差异数据大于预设第二阈值，确定经过验证所述待检测对象的形状产生缺陷。
本公开实施例能够通过将第一检测信号和第二检测信号分别转化为第一点云数据和第二点云数据，计算二者之间的差异，再通过与预设第二阈值的比较，实现对前述实施例中关于对象是否磨损的判别结果进行进一步验证，提高了零件磨损检测的准确率。
在本公开的又一实施例中，计算所述第一点云数据和第二点云数据之 间的第二差异数据，包括：
步骤601，在所述第一点云数据中提取所述毫米波雷达与所述待检测对象之间的第一距离值和第一角度值；
步骤602，在所述第二点云数据中提取所述毫米波雷达与所述参考对象之间的第二距离值和第二角度值；
步骤603，基于所述第一距离值和第一角度值构建第一矩阵，基于所述第二距离值和第二角度值构建第二矩阵；
步骤604，计算所述第一矩阵和所述第二矩阵之间的相似度，将得到的相似度数据确定为所述第二差异数据。
处理后得到距离和角度值。我们将正常元件返回的数据与磨损元件产生的数据分别做成矩阵并进行标记，对新的到的数据，通过计算矩阵相似度。根据矩阵相似度我们会发现磨损元件与正常元件相似度低，其中矩阵A与矩阵B的相似度公式如下：
Figure PCTCN2022071649-appb-000004
其中，A表示正常元件数据矩阵，B表示磨损元件的数据矩阵，Tr表示求矩阵的迹(秩)，A’表示A的转置矩阵，B表示B’的转置矩阵，s表示矩阵的维度数。
对新采集到的数据进行一个与正常设备的相似度匹配，如果大于给定的阈值，则我们将其判断为正常元件，否则为磨损元件。
本公开实施例能够自动计算矩阵之间的相似度，进而得到第一点云数据和第二点云数据之间的第二差异数据，也即得到第一检测信号和第二检测信号之间的差异，便于进一步对前述实施例得到的关于对象磨损判别的结果进行验证。
在本公开的又一实施例中，如图5所示，还提供一种对象检测装置，包括：
获取模块11，被设置为获取用于对待检测对象进行扫描的毫米波雷达 输出的第一检测信号；
第一计算模块12，被设置为基于所述第一检测信号计算与所述待检测对象对应的检测数据；
第二计算模块13，被设置为计算所述检测数据与预设的参考数据之间的第一差异数据，所述参考数据是基于所述毫米波雷达扫描参考对象输出的第二检测信号计算得到的，所述参考对象的形状未产生缺陷；
确定模块14，被设置为若所述第一差异数据大于预设第一阈值，确定所述待检测对象的形状产生缺陷。
在本公开的又一实施例中，还提供一种电子设备，包括处理器、通信接口、存储器和通信总线，其中，处理器，通信接口，存储器通过通信总线完成相互间的通信；
存储器，被设置为存放计算机程序；
处理器，被设置为执行存储器上所存放的程序时，实现前述任一方法实施例所述的对象检测方法。
本公开实施例提供的电子设备，处理器通过执行存储器上所存放的程序实现了通过首先获取被设置为对待检测对象进行扫描的毫米波雷达输出的第一检测信号，然后基于所述第一检测信号计算与所述待检测对象对应的检测数据，再计算所述检测数据与预设的参考数据之间的第一差异数据，所述参考数据是基于所述毫米波雷达扫描参考对象输出的第二检测信号计算得到的，所述参考对象的形状未产生缺陷，若所述第一差异数据大于预设第一阈值，可以确定所述待检测对象的形状产生缺陷。
本公开实施例通过基于对待检测对象检测得到的检测数据与对参考对象检测得到的参考数据，计算二者之间的第一差异数据，即计算待检测对象相对于的形状未产生缺陷的参考对象之间发生的形变量，在第一差异数据大于预设第一阈值时，可以确定待检测对象的形状产生缺陷，实现自动检测对象的磨损情况，检测结果更加准确且效率更高。
上述电子设备提到的通信总线1140可以是外设部件互连标准(PeripheralComponentInterconnect，简称PCI)总线或扩展工业标准结构 (ExtendedIndustryStandardArchitecture，简称EISA)总线等。该通信总线1140可以分为地址总线、数据总线、控制总线等。为便于表示，图6中仅用一条粗线表示，但并不表示仅有一根总线或一种类型的总线。
通信接口1120被设置为上述电子设备与其他设备之间的通信。
存储器1130可以包括随机存取存储器(RandomAccessMemory，简称RAM)，也可以包括非易失性存储器(non-volatilememory)，例如至少一个磁盘存储器。在一些实施方式中，存储器还可以是至少一个位于远离前述处理器的存储装置。
上述的处理器1110可以是通用处理器，包括中央处理器(CentralProcessingUnit，简称CPU)、网络处理器(NetworkProcessor，简称NP)等；还可以是数字信号处理器(DigitalSignalProcessing，简称DSP)、专用集成电路(ApplicationSpecificIntegratedCircuit，简称ASIC)、现场可编程门阵列(Field-ProgrammableGateArray，简称FPGA)或者其他可编程逻辑器件、分立门或者晶体管逻辑器件、分立硬件组件。
在本公开的又一实施例中，还提供一种计算机可读存储介质，所述计算机可读存储介质上存储有对象检测方法的程序，所述对象检测方法的程序被处理器执行时实现前述任一方法实施例所述的对象检测方法的步骤。
需要说明的是，在本文中，诸如“第一”和“第二”等之类的关系术语仅仅用来将一个实体或者操作与另一个实体或操作区分开来，而不一定要求或者暗示这些实体或操作之间存在任何这种实际的关系或者顺序。而且，术语“包括”、“包含”或者其任何其他变体意在涵盖非排他性的包含，从而使得包括一系列要素的过程、方法、物品或者设备不仅包括那些要素，而且还包括没有明确列出的其他要素，或者是还包括为这种过程、方法、物品或者设备所固有的要素。在没有更多限制的情况下，由语句“包括一个……”限定的要素，并不排除在包括所述要素的过程、方法、物品或者设备中还存在另外的相同要素。
以上所述仅是本公开的具体实施方式，使本领域技术人员能够理解或实现本公开。对这些实施例的多种修改对本领域的技术人员来说将是显而 易见的，本文中所定义的一般原理可以在不脱离本公开的精神或范围的情况下，在其它实施例中实现。因此，本公开将不会被限制于本文所示的这些实施例，而是要符合与本文所申请的原理和新颖特点相一致的最宽的范围。

Claims (10)

  1. 一种对象检测方法，包括：
    获取被设置为对待检测对象进行扫描的毫米波雷达输出的第一检测信号；
    基于所述第一检测信号计算与所述待检测对象对应的检测数据；
    计算所述检测数据与预设的参考数据之间的第一差异数据，所述参考数据是基于所述毫米波雷达扫描参考对象输出的第二检测信号计算得到的，所述参考对象的形状未产生缺陷；
    若所述第一差异数据大于预设第一阈值，确定所述待检测对象的形状产生缺陷。
  2. 根据权利要求1所述的对象检测方法，其中，所述基于所述第一检测信号计算与所述待检测对象对应的检测数据，包括：
    获取所述毫米波雷达向待检测对象发射的电磁波信号；
    基于所述电磁波信号和所述第一检测信号计算与所述待检测对象对应的检测数据。
  3. 根据权利要求2所述的对象检测方法，其中，所述基于所述电磁波信号和所述第一检测信号计算与所述待检测对象对应的检测数据，包括：
    将所述电磁波信号和所述第一检测信号做差，得到差频信号；
    将所述差频信号从时域转化至频域，确定所述差频信号的相位；
    将所述相位确定为与所述待检测对象对应的所述检测数据。
  4. 根据权利要求2所述的对象检测方法，其中，所述基于所述电磁波信号和所述第一检测信号计算与所述待检测对象对应的检测数据，包括：
    将所述电磁波信号和所述第一检测信号做差，得到差频信号；
    将所述差频信号从时域转化至频域，确定所述差频信号的频率；
    将所述频率确定为与所述待检测对象对应的所述检测数据。
  5. 根据权利要求1所述的对象检测方法，其中，计算所述检测数据与预设的参考数据之间的第一差异数据，包括：
    将所述检测数据与所述参考数据做差，得到差值；
    将所述差值确定为所述第一差异数据。
  6. 根据权利要求1所述的对象检测方法，其中，所述方法还包括：
    将所述第一检测信号转化为第一点云数据；
    获取所述第二检测信号转化成的第二点云数据；
    计算所述第一点云数据和第二点云数据之间的第二差异数据；
    若所述第二差异数据大于预设第二阈值，确定经过验证所述待检测对象的形状产生缺陷。
  7. 根据权利要求6所述的对象检测方法，其中，计算所述第一点云数据和第二点云数据之间的第二差异数据，包括：
    在所述第一点云数据中提取所述毫米波雷达与所述待检测对象之间的第一距离值和第一角度值；
    在所述第二点云数据中提取所述毫米波雷达与所述参考对象之间的第二距离值和第二角度值；
    基于所述第一距离值和第一角度值构建第一矩阵，基于所述第二距离值和第二角度值构建第二矩阵；
    计算所述第一矩阵和所述第二矩阵之间的相似度，将得到的相似度数据确定为所述第二差异数据。
  8. 一种对象检测装置，包括：
    获取模块，被设置为获取用于对待检测对象进行扫描的毫米波雷达输出的第一检测信号；
    第一计算模块，被设置为基于所述第一检测信号计算与所述待检测对象对应的检测数据；
    第二计算模块，被设置为计算所述检测数据与预设的参考数据之间的 第一差异数据，所述参考数据是基于所述毫米波雷达扫描参考对象输出的第二检测信号计算得到的，所述参考对象的形状未产生缺陷；
    确定模块，被设置为若所述第一差异数据大于预设第一阈值，确定所述待检测对象的形状产生缺陷。
  9. 一种电子设备，包括处理器、通信接口、存储器和通信总线，其中，处理器，通信接口，存储器通过通信总线完成相互间的通信；
    存储器，被设置为存放计算机程序；
    处理器，被设置为执行存储器上所存放的程序时，实现权利要求1～7任一所述的对象检测方法。
  10. 一种计算机可读存储介质，所述计算机可读存储介质上存储有对象检测方法的程序，所述对象检测方法的程序被处理器执行时实现权利要求1-7任一所述的对象检测方法的步骤。
PCT/CN2022/071649 2021-05-17 2022-01-12 一种对象检测方法、装置、电子设备及存储介质 WO2022242204A1 (zh)

Applications Claiming Priority (2)

Application Number Priority Date Filing Date Title
CN202110534302.7A CN113390370B (zh) 2021-05-17 2021-05-17 一种对象检测方法、装置、电子设备及存储介质
CN202110534302.7 2021-05-17

Publications (1)

Publication Number Publication Date
WO2022242204A1 true WO2022242204A1 (zh) 2022-11-24

Family

ID=77617080

Family Applications (1)

Application Number Title Priority Date Filing Date
PCT/CN2022/071649 WO2022242204A1 (zh) 2021-05-17 2022-01-12 一种对象检测方法、装置、电子设备及存储介质

Country Status (2)

Country Link
CN (1) CN113390370B (zh)
WO (1) WO2022242204A1 (zh)

Families Citing this family (1)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN113390370B (zh) * 2021-05-17 2023-01-13 珠海格力电器股份有限公司 一种对象检测方法、装置、电子设备及存储介质

Citations (7)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US20100106432A1 (en) * 2008-10-29 2010-04-29 Hitachi, Ltd. Ultrasonic flaw detector and ultrasonic flaw detection method
CN102012403A (zh) * 2010-11-01 2011-04-13 北京市市政工程研究院 超声法检测混凝土构筑物节点内部不密实性缺陷的判定方法
CN103257182A (zh) * 2013-06-07 2013-08-21 电子科技大学 一种脉冲涡流缺陷定量检测方法及检测系统
CN107052086A (zh) * 2017-06-01 2017-08-18 扬州苏星机器人科技有限公司 基于三维视觉的冲压件表面缺陷检测装置及检测方法
CN110044934A (zh) * 2019-04-01 2019-07-23 黑凤梨供应链管理（上海）有限公司 一种表面破损或者表面状态变化的检测装置及其检测方法
CN111337924A (zh) * 2020-04-16 2020-06-26 湖南科技大学 一种桥梁健康监测的裂缝识别与检测方法
CN113390370A (zh) * 2021-05-17 2021-09-14 珠海格力电器股份有限公司 一种对象检测方法、装置、电子设备及存储介质

Family Cites Families (5)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US4564295A (en) * 1983-03-07 1986-01-14 New York Institute Of Technology Apparatus and method for projection moire topography
CN103093196B (zh) * 2013-01-14 2014-08-27 大连理工大学 一种基于手势的汉字交互输入与识别方法
CN106570311B (zh) * 2016-10-12 2023-05-23 武汉数字工程研究所（中国船舶重工集团公司第七0九研究所） 复杂条件下航迹连续性评估方法及系统
DE102016119728A1 (de) * 2016-10-17 2018-04-19 Inoex Gmbh Lnnovationen Und Ausrüstungen Für Die Extrusionstechnik Terahertz-Messgerät
CN109614459B (zh) * 2019-03-06 2019-05-28 上海思岚科技有限公司 应用于二维激光的地图构建回环检测方法及设备

Patent Citations (7)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US20100106432A1 (en) * 2008-10-29 2010-04-29 Hitachi, Ltd. Ultrasonic flaw detector and ultrasonic flaw detection method
CN102012403A (zh) * 2010-11-01 2011-04-13 北京市市政工程研究院 超声法检测混凝土构筑物节点内部不密实性缺陷的判定方法
CN103257182A (zh) * 2013-06-07 2013-08-21 电子科技大学 一种脉冲涡流缺陷定量检测方法及检测系统
CN107052086A (zh) * 2017-06-01 2017-08-18 扬州苏星机器人科技有限公司 基于三维视觉的冲压件表面缺陷检测装置及检测方法
CN110044934A (zh) * 2019-04-01 2019-07-23 黑凤梨供应链管理（上海）有限公司 一种表面破损或者表面状态变化的检测装置及其检测方法
CN111337924A (zh) * 2020-04-16 2020-06-26 湖南科技大学 一种桥梁健康监测的裂缝识别与检测方法
CN113390370A (zh) * 2021-05-17 2021-09-14 珠海格力电器股份有限公司 一种对象检测方法、装置、电子设备及存储介质

Also Published As

Publication number Publication date
CN113390370A (zh) 2021-09-14
CN113390370B (zh) 2023-01-13

Similar Documents

Publication Publication Date Title
US9097805B2 (en) Systems and methods for calibrating dual polarization radar systems
WO2022242204A1 (zh) 一种对象检测方法、装置、电子设备及存储介质
US9261585B2 (en) Radar apparatus using image change detector and method of operating the same
CN1666109A (zh) 时－频域反射仪的装置及方法
CN110554049B (zh) 基于太赫兹波的复合绝缘子缺陷检测装置、方法及介质
WO2023004628A1 (zh) 反射率校正方法、装置、计算机可读存储介质及终端设备
JP2023047319A (ja) 気象レーダーのためのノイズ除去装置および方法
CN117192502B (zh) 基于目标雷达的锚泊船只走锚监测系统
CN111371436A (zh) 雷达天线扫描周期测量方法、装置、设备及存储介质
CN114488107B (zh) 一种海杂波时空分布及影响分级产品制作的方法及装置
CN111090133B (zh) 一种雨量雷达数据质量控制方法
JP2001159678A (ja) レーダによる目標判定方法及びレーダ装置
CN111648206B (zh) 一种沥青路面实时摊铺辅助监测系统
Atwater et al. Temporal error analysis for compact cross-loop direction-finding HF radar
TWI474028B (zh) Frequency Leveling of Continuous Wave Radar and Its Measuring Method
US10480932B2 (en) Automated computation of a dimension of a moving platform
CN111596286A (zh) 测距方法和装置
CN111751794A (zh) 一种雷达威力监控方法
KR20150097950A (ko) 타겟 탐지 방법 및 장치
CN117392515B (zh) 一种基于视觉传感的桥梁结构计量检测系统
KR102011962B1 (ko) 탐지성능 분석장치 및 방법
CN117268296B (zh) 一种基于4d毫米波的水轮发电机转子吊装气隙监测装置
JP5586217B2 (ja) レーダ装置
Jiang et al. An Adaptive Denoising Method for Industrial Big Data with Multi-indicator Fusion
CN117872296A (zh) 基于水上无线信号检测处理器的雷达监测方法

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: 22803542

Country of ref document: EP

Kind code of ref document: A1

NENP Non-entry into the national phase

Ref country code: DE