WO2024044870A1 - Underground parking lot passage moving vehicle real-time detection system and method - Google Patents

Underground parking lot passage moving vehicle real-time detection system and method Download PDF

Info

Publication number
WO2024044870A1
WO2024044870A1 PCT/CN2022/115393 CN2022115393W WO2024044870A1 WO 2024044870 A1 WO2024044870 A1 WO 2024044870A1 CN 2022115393 W CN2022115393 W CN 2022115393W WO 2024044870 A1 WO2024044870 A1 WO 2024044870A1
Authority
WO
WIPO (PCT)
Prior art keywords
real
time
parking lot
wave
vehicles
Prior art date
Application number
PCT/CN2022/115393
Other languages
French (fr)
Chinese (zh)
Inventor
应坚国
王金栋
凌海超
蒋盛川
Original Assignee
上海金桥(集团)有限公司
同济大学
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 上海金桥(集团)有限公司, 同济大学 filed Critical 上海金桥(集团)有限公司
Priority to PCT/CN2022/115393 priority Critical patent/WO2024044870A1/en
Publication of WO2024044870A1 publication Critical patent/WO2024044870A1/en

Links

Images

Classifications

    • BPERFORMING OPERATIONS; TRANSPORTING
    • B61RAILWAYS
    • B61LGUIDING RAILWAY TRAFFIC; ENSURING THE SAFETY OF RAILWAY TRAFFIC
    • B61L25/00Recording or indicating positions or identities of vehicles or trains or setting of track apparatus
    • B61L25/02Indicating or recording positions or identities of vehicles or trains
    • GPHYSICS
    • G01MEASURING; TESTING
    • G01SRADIO 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
    • G01S13/00Systems 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
    • G01S13/66Radar-tracking systems; Analogous systems
    • GPHYSICS
    • G01MEASURING; TESTING
    • G01SRADIO DIRECTION-FINDING; RADIO NAVIGATION; DETERMINING DISTANCE OR VELOCITY BY USE OF RADIO WAVES; LOCATING OR PRESENCE-DETECTING BY USE OF THE REFLECTION OR RERADIATION OF RADIO WAVES; ANALOGOUS ARRANGEMENTS USING OTHER WAVES
    • G01S7/00Details of systems according to groups G01S13/00, G01S15/00, G01S17/00
    • G01S7/02Details of systems according to groups G01S13/00, G01S15/00, G01S17/00 of systems according to group G01S13/00
    • G01S7/41Details of systems according to groups G01S13/00, G01S15/00, G01S17/00 of systems according to group G01S13/00 using analysis of echo signal for target characterisation; Target signature; Target cross-section

Definitions

  • the invention belongs to the field of passage vehicle detection, and in particular relates to a real-time detection system and method for vehicles operating in passages of underground parking lots.
  • the existing vehicle detection technology inside the parking lot focuses on the detection of vehicles in parking spaces and the detection of vehicles entering and exiting the parking lot, and lacks real-time detection methods and equipment for vehicles operating in the internal passages of the parking lot.
  • the patent CN106297373B realizes the detection of vehicles in parking spaces based on cross-correlation and geomagnetic sensors.
  • the geomagnetic sensor nodes collect the geomagnetic disturbance signals of passing vehicles, and perform cross-correlation calculations on the collected real-time monitoring data and reference signals.
  • This method can only detect vehicles in a single parking space, and requires one geomagnet to be installed in each parking space, which is costly.
  • Patent CN216202070U discloses a parking lot vehicle detector, which includes a fixed box. The inside of the fixed box is symmetrically fixed and connected to a limit rod. The outside of the limit rod is slidingly connected to a lifting seat. The top of the lifting seat is connected to a bottom plate. The bottom of the bottom plate Hooks are fixedly connected at equal distances, and the top of the lifting base is provided with a slot used in conjunction with the hooks.
  • This kind of equipment can only detect the passage of vehicles at the entrance and exit, but cannot detect the running trajectory of the vehicle. The detection range is narrow and cannot be installed in areas other than the entrance and exit, which has great limitations.
  • the purpose of the present invention is to provide a real-time detection system and method for vehicles operating in underground parking lot passages to solve the problems existing in the above-mentioned existing technologies.
  • the present invention provides a real-time detection system for vehicles operating in underground parking lots, including a millimeter wave radar, a metal identification tape, a data analysis unit, a data storage unit, a communication unit and a main control computer;
  • the millimeter wave radar is used to generate and emit electromagnetic waves
  • the metal identification tape is used to reflect the electromagnetic wave and obtain the reflected wave
  • the data analysis unit is used to obtain a detection area according to the reflected wave, process the reflected wave, and obtain real-time information of vehicle movement;
  • the data storage unit is used to store the real-time information
  • the communication unit is used to transmit the real-time information to the main control computer;
  • the main control computer is used to distinguish the running trajectory information of different vehicles and the same vehicle according to the real-time information.
  • the millimeter wave radar is also used to receive the reflected wave of the metal identification tape;
  • the millimeter wave radar includes an oscillator, a transmitter, and an antenna; the oscillator is used to generate a linear frequency modulated continuous wave or a triangular wave; the transmitter is used to transmit the linear frequency modulated continuous wave or a triangular wave; and the antenna is used to The linear frequency modulated continuous wave or triangular wave carries out directional radiation;
  • the linear frequency modulated continuous wave or triangular wave propagates in space in the form of electromagnetic waves. When it encounters a target, it is reflected back to obtain a reflected wave.
  • the data analysis unit identifies the internal passage of the parking lot by analyzing the two-dimensional time-frequency characteristics of the reflected wave and identifying the position of the reflected wave of the metal sign band based on two-dimensional spectrum analysis.
  • the data analysis unit intercepts the reflected wave in a single column, performs time-frequency analysis based on the short-time Fourier transform method, and performs energy normalization after superposition;
  • time-frequency diagrams of different targets are obtained and a gray-level co-occurrence matrix diagram is generated, differentiated Doppler correlation information is obtained based on the gray-level co-occurrence matrix diagram, and eigenvalues are formed;
  • the feature values are synthesized into vectors, and the vectors are used as inputs for training based on the neural network model, and the real-time target coordinate position, speed, and motion direction information results of the vehicle are output. .
  • the communication unit transmits the real-time information of the vehicle within a unit time to the main control computer at a fixed call response frequency.
  • the main control computer collects real-time information transmitted from various locations in the parking lot, conducts secondary analysis on the real-time information, distinguishes the running trajectory information of different vehicles and the same vehicle, and calculates the coordinates of vehicles running on the internal roads of the parking lot. Position, running direction, and running trajectory are detected.
  • the present invention provides a real-time detection method of vehicles operating in underground parking passages, which includes the following steps:
  • the coordinate position, running direction, and running trajectory of the vehicle running on the road inside the parking lot are detected.
  • the process of reflecting the electromagnetic waves includes:
  • a metal identification tape is provided on the center line of the parking lot passage, and the electromagnetic wave is reflected based on the metal identification tape.
  • the process of detecting the coordinate position, running direction, and running trajectory of vehicles running on the road inside the parking lot based on the reflected waves includes:
  • the real-time information includes coordinate position, speed, and movement direction information
  • the process of first analyzing the reflected wave includes:
  • the reflected waves are intercepted in a single column, time-frequency analysis is performed based on the short-time Fourier transform method, and energy normalization is performed after superposition;
  • time-frequency diagrams of different targets are obtained and a gray-level co-occurrence matrix diagram is generated, differentiated Doppler correlation information is obtained based on the gray-level co-occurrence matrix diagram, and eigenvalues are formed;
  • the feature values are synthesized into vectors, and the vectors are used as inputs for training based on the neural network model, and the real-time target coordinate position, speed, and motion direction information results of the vehicle are output.
  • the identification area is accurate and controllable.
  • the metal identification tape effectively solves the data deficiencies of millimeter wave radar.
  • the layout area can be manually controlled and accurately identified with millimeter wave radar;
  • the data dimension is high and can detect vehicle target coordinate position, speed, movement direction, and movement trajectory information
  • the communication unit transmits data at a fixed call response frequency
  • this system has a small number of millimeter wave radar deployments, mature technology and low cost, and the overall system cost is low.
  • Figure 1 is a structural diagram of a vehicle real-time detection system in an embodiment of the present invention
  • Figure 2 is a practical application structure diagram of the detection system in the embodiment of the present invention.
  • Figure 3 is a schematic diagram of the installation position of the metal identification tape in the embodiment of the present invention; wherein: 1-main control computer, 2-data analysis unit, 3-data storage unit, 4-communication unit, 5-millimeter wave radar, 6-metal Logo tape.
  • this embodiment provides a method based on millimeter-wave radar to solve the problems in the prior art that only vehicles in parking spaces and vehicles entering and exiting the parking lot can be detected, and vehicles in the passage cannot be detected.
  • the cost of detection equipment is high and the layout area is limited.
  • the system consists of a millimeter-wave radar hoisted by a parking lot bridge, a metal identification tape nailed to the channel floor, a data analysis unit, a data storage unit, a communication unit and a main control computer, including:
  • the hoisted millimeter-wave radar generates linear frequency modulation continuous waves or triangular waves through an oscillator, which are emitted by the transmitter and then directionally radiated by the antenna. They propagate in the form of electromagnetic waves in space and are reflected back when encountering a target. Since the reflection data of millimeter wave radar can only provide distance and angle information and cannot provide height information like lidar, the lack of height information in the interior scene of the parking lot will lead to abnormal or missing vehicle and channel identification.
  • the micro-Doppler characteristics of the metal sign strip are selected as the time-frequency characteristic map of the internal road in the parking lot, and the two-dimensional time-frequency characteristic texture map of the radar echo is analyzed to determine the road location.
  • a copper alloy, iron alloy or aluminum alloy metal identification tape is installed on the center line of the parking lot passage to mark the detection area.
  • the data analysis unit performs signal processing and data processing on the reflected signals, analyzes the two-dimensional time-frequency characteristics of the reflected millimeter waves, and identifies the reflection of the metal marking tape based on two-dimensional spectrum analysis. Wave position, thereby realizing the identification of internal passages in the parking lot.
  • the vehicle blocks the metal sign strip located on the center line of the channel, and its metal shell directly reflects millimeter waves to obtain a reflected wave.
  • the two-dimensional time-frequency characteristic texture map of the reflected wave is reflected as the Doppler main frequency of the car shell.
  • the micro-movement components generated by other components are centered around the main Doppler frequency of the car.
  • Micro-Doppler information requires the joint use of multiple frames of data to collect, so a large number of time-frequency analysis techniques are used to extract target features in order to distinguish their differences.
  • Time-frequency analysis techniques include sparse Fourier transform (SFT) and fast Fourier transform (FFT).
  • the data analysis unit intercepts single columns of different detected targets, performs time-frequency analysis, and performs energy normalization after superposition.
  • the time-frequency processing here uses short-time Fourier transform (STFT).
  • STFT short-time Fourier transform
  • the gray-level co-occurrence matrix diagram will be generated using the time-frequency diagrams of different targets, providing differentiated Doppler correlation information and forming eigenvalues.
  • the extracted feature values are synthesized into vectors, and multi-frame vectors are used as input, and neural network model training is used to output the vehicle's real-time target coordinate position, speed, and motion direction information results.
  • Available training models include: Recurrent Neural Network (RNN) and Long Short-Term Memory Network (LSTM).
  • the data calculated by the data analysis unit is stored in the storage unit, and the communication unit transmits the real-time vehicle information stored in the unit time to the main control computer at a fixed call response frequency (20s, 30s, 40s, 60s, etc.).
  • the main control computer collects the timing information transmitted by the equipment in each location in the parking lot, it performs secondary analysis on the data to distinguish the running trajectory information of different vehicle units and the same vehicle unit, and realize the coordinate position and running direction of the vehicles running on the road inside the parking lot. , Detection of running trajectories.
  • this embodiment provides an application example of a real-time detection system for vehicles operating in underground parking lots:
  • the system consists of a main control computer 1, a data analysis unit 2, a data storage unit 3, a communication unit 4, a millimeter wave radar 5, and a metal identification tape 6.
  • the data analysis unit 2, data storage unit 3, communication unit 4, millimeter Wave radar 5 together form a millimeter wave sensor.
  • the millimeter wave radar 5 emits electromagnetic waves to the metal identification tape 6 in the area and receives the reflected waves. If there is a moving vehicle in the process, it will receive different electromagnetic waveforms. Then, the data analysis unit 2 in the millimeter wave sensor will The data storage unit 3 and the communication unit 4 analyze, store and transmit real-time data in sequence.
  • the millimeter wave radar in this embodiment adopts the ARS-408 radar of the millimeter wave radar company Continental.
  • This radar emits millimeter waves in the 77GHz frequency band.
  • the frequency of the radar in this frequency band is higher and the bandwidth is wider.
  • the detection range is long and the detection range is long.
  • the angle is small, the detection accuracy is high, and it is suitable for long-distance detection; the radar circuit board area is small, and the whole machine is small in size, so it is most suitable for underground parking lots.
  • the data processing unit uses a built-in decoder of the radar.
  • the data storage unit uses a 10G capacity memory card or magnetic disk hard drive.
  • the communication unit supports wired communication such as cables and optical cables or wireless communication such as Bluetooth, radio frequency, infrared, and WIFI.
  • the main control computer in this embodiment can be a cloud server, or it can be equipped with an industrial computer in the supporting computer room of the parking lot.
  • the schematic diagram of the metal identification tape installed on the center line of the internal channel is shown in Figure 3.
  • a metal tape made of copper alloy, iron alloy or aluminum alloy can be used. Its width does not exceed 5cm and its thickness is less than 2mm. The length can be extended according to the needs of the channel.
  • This embodiment provides a method for real-time detection of vehicles operating in underground parking lot passages, which specifically includes the following steps:
  • Step 1 Generate and emit electromagnetic waves through millimeter wave radar.
  • Step 2 Set a metal identification tape of copper alloy, iron alloy or aluminum alloy on the center line of the parking lot passage, and reflect the electromagnetic wave through the metal identification tape to obtain the reflected wave.
  • Step 3 Identify the position of the reflected wave of the metal marking strip based on the two-dimensional time-frequency characteristic analysis of the reflected wave.
  • Step 4 Intercept the reflected waves in a single column, conduct time-frequency analysis based on the short-time Fourier transform method, and perform energy normalization after superposition;
  • time-frequency diagrams of different targets are obtained and a gray-level co-occurrence matrix diagram is generated, differentiated Doppler correlation information is obtained based on the gray-level co-occurrence matrix diagram, and eigenvalues are formed;
  • the feature values are synthesized into vectors, and the vectors are used as inputs for training based on the neural network model to output the vehicle's real-time target coordinate position, speed, and motion direction information results; and the real-time information obtained through the first analysis is stored and transmitted.
  • Step 5 Conduct a secondary analysis of the real-time information to distinguish the running trajectory information of different vehicle units and the same vehicle unit, and realize the detection of the coordinate position, running direction and running trajectory of the vehicles running on the road inside the parking lot.

Landscapes

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

Abstract

Disclosed are an underground parking lot passage moving vehicle real-time detection system and method. The detection system comprises a millimeter-wave radar used to generate electromagnetic waves, a metal marking strip installed on a center line of a parking lot passage, a data analysis unit used to analyze reflected waves which are reflected back, a data storage unit, a communication unit used for data transmission, and a host computer. The steps of the detection method are: generating and emitting electromagnetic waves on the basis of the millimeter-wave radar; reflecting the electromagnetic waves, to acquire reflected waves; detecting a coordinate position, a direction of motion and a motion trajectory of a moving vehicle in the parking lot passage on the basis of the reflected waves. In the present invention, a detection area is accurate and controllable, and the target coordinate position, speed, direction of motion and motion trajectory information of a vehicle can be detected; the technology is mature, and the cost is low.

Description

一种地下停车场通道运行车辆实时检测系统与方法A real-time detection system and method for vehicles operating in underground parking lot passages 技术领域Technical field
本发明属于通道车辆检测领域,特别是涉及一种地下停车场通道运行车辆实时检测系统与方法。The invention belongs to the field of passage vehicle detection, and in particular relates to a real-time detection system and method for vehicles operating in passages of underground parking lots.
背景技术Background technique
大型停车场的内部通道交织错杂,导致车辆在停车场内部的实时运行位置信息变化速度快、规律性低。为精细化、智能化管理停车场内部交通,亟需一种车辆检测方法,对通道运行中的车辆实现实时检测。The internal passages of large parking lots are intertwined and complex, causing the real-time operating position information of vehicles inside the parking lot to change quickly and with low regularity. In order to manage the internal traffic of the parking lot in a refined and intelligent manner, a vehicle detection method is urgently needed to achieve real-time detection of vehicles running in the channel.
然而,现有的停车场内部车辆检测技术集中关注于车位车辆检测、停车场进出车辆检测,缺乏对停车场内部通道运行车辆的实时检测方法及设备。如专利CN106297373B基于互相关和地磁传感器实现对车位车辆的检测,通过地磁传感器节点采集所经过车辆对地磁的扰动信号,将采集的实时监测数据与参考信号进行互相关计算,最后根据相关性,做出车辆检测的相应判断。这种方法仅能实现对单个车位上的车辆检测,且需一个车位安装一个地磁,成本高昂。专利CN216202070U公开了一种停车场车辆检测器,包括固定箱,固定箱的内部对称固定连接有限位杆,限位杆的外侧滑动连接有升降座,升降座的顶部卡接有底板,底板的底部等距固定连接有卡钩,升降座的顶部设有与卡钩配合使用的卡槽。这种设备仅能检测出入口出车辆通行与否,无法检测车辆运行轨迹,检测范围窄,无法在除出入口以外的区域安装,局限性大。However, the existing vehicle detection technology inside the parking lot focuses on the detection of vehicles in parking spaces and the detection of vehicles entering and exiting the parking lot, and lacks real-time detection methods and equipment for vehicles operating in the internal passages of the parking lot. For example, the patent CN106297373B realizes the detection of vehicles in parking spaces based on cross-correlation and geomagnetic sensors. The geomagnetic sensor nodes collect the geomagnetic disturbance signals of passing vehicles, and perform cross-correlation calculations on the collected real-time monitoring data and reference signals. Finally, based on the correlation, do Make corresponding judgments for vehicle detection. This method can only detect vehicles in a single parking space, and requires one geomagnet to be installed in each parking space, which is costly. Patent CN216202070U discloses a parking lot vehicle detector, which includes a fixed box. The inside of the fixed box is symmetrically fixed and connected to a limit rod. The outside of the limit rod is slidingly connected to a lifting seat. The top of the lifting seat is connected to a bottom plate. The bottom of the bottom plate Hooks are fixedly connected at equal distances, and the top of the lifting base is provided with a slot used in conjunction with the hooks. This kind of equipment can only detect the passage of vehicles at the entrance and exit, but cannot detect the running trajectory of the vehicle. The detection range is narrow and cannot be installed in areas other than the entrance and exit, which has great limitations.
发明内容Contents of the invention
本发明的目的是提供一种地下停车场通道运行车辆实时检测系统与方 法,以解决上述现有技术存在的问题。The purpose of the present invention is to provide a real-time detection system and method for vehicles operating in underground parking lot passages to solve the problems existing in the above-mentioned existing technologies.
一方面为实现上述目的,本发明提供了一种地下停车场通道运行车辆实时检测系统,包括毫米波雷达、金属标识带、数据分析单元、数据储存单元、通讯单元和主控计算机;On the one hand, to achieve the above objectives, the present invention provides a real-time detection system for vehicles operating in underground parking lots, including a millimeter wave radar, a metal identification tape, a data analysis unit, a data storage unit, a communication unit and a main control computer;
所述毫米波雷达用于产生并发射电磁波;The millimeter wave radar is used to generate and emit electromagnetic waves;
所述金属标识带用于对所述电磁波进行反射,获取反射波;The metal identification tape is used to reflect the electromagnetic wave and obtain the reflected wave;
所述数据分析单元用于根据所述反射波获取检测区域,并对所述反射波进行处理,获取车辆运动的实时信息;The data analysis unit is used to obtain a detection area according to the reflected wave, process the reflected wave, and obtain real-time information of vehicle movement;
所述数据储存单元用于对所述实时信息进行存储;The data storage unit is used to store the real-time information;
所述通讯单元用于向所述主控计算机传输所述实时信息;The communication unit is used to transmit the real-time information to the main control computer;
所述主控计算机用于根据所述实时信息区分不同车辆以及同一车辆的运行轨迹信息。The main control computer is used to distinguish the running trajectory information of different vehicles and the same vehicle according to the real-time information.
可选地,所述毫米波雷达还用于接收所述金属标识带的反射波;Optionally, the millimeter wave radar is also used to receive the reflected wave of the metal identification tape;
所述毫米波雷达包括振荡器、发射机、天线;所述振荡器用于产生线性调频连续波或三角波,所述发射机用于发射所述线性调频连续波或三角波,所述天线用于对所述线性调频连续波或三角波进行定向辐射;The millimeter wave radar includes an oscillator, a transmitter, and an antenna; the oscillator is used to generate a linear frequency modulated continuous wave or a triangular wave; the transmitter is used to transmit the linear frequency modulated continuous wave or a triangular wave; and the antenna is used to The linear frequency modulated continuous wave or triangular wave carries out directional radiation;
所述线性调频连续波或三角波在空间以电磁波形式传播,当遇到目标时反射回来,得到反射波。The linear frequency modulated continuous wave or triangular wave propagates in space in the form of electromagnetic waves. When it encounters a target, it is reflected back to obtain a reflected wave.
可选地,所述数据分析单元通过分析所述反射波的二维时频特征,基于二维频谱分析识别金属标识带反射波的位置,对停车场的内部通道进行标识。Optionally, the data analysis unit identifies the internal passage of the parking lot by analyzing the two-dimensional time-frequency characteristics of the reflected wave and identifying the position of the reflected wave of the metal sign band based on two-dimensional spectrum analysis.
可选地,当车辆经过所述检测区域时,所述数据分析单元对所述反射 波进行单列截取,基于短时傅里叶变换法进行时频分析,并叠加后进行能量归一化处理;Optionally, when the vehicle passes through the detection area, the data analysis unit intercepts the reflected wave in a single column, performs time-frequency analysis based on the short-time Fourier transform method, and performs energy normalization after superposition;
基于时频分析的结果获取不同目标的时频图并生成灰度共生矩阵图,基于所述灰度共生矩阵图获取差异化的多普勒相关性信息,并形成特征值;Based on the results of time-frequency analysis, time-frequency diagrams of different targets are obtained and a gray-level co-occurrence matrix diagram is generated, differentiated Doppler correlation information is obtained based on the gray-level co-occurrence matrix diagram, and eigenvalues are formed;
将所述特征值合成矢量,将所述矢量作为输入,基于神经网络模型进行训练,输出车辆的实时目标坐标位置、速度、运动方向信息结果。。The feature values are synthesized into vectors, and the vectors are used as inputs for training based on the neural network model, and the real-time target coordinate position, speed, and motion direction information results of the vehicle are output. .
可选地,所述通讯单元以固定呼叫应答频率向所述主控计算机传输单位时间内车辆的实时信息。Optionally, the communication unit transmits the real-time information of the vehicle within a unit time to the main control computer at a fixed call response frequency.
可选地,所述主控计算机通过收集停车场各位置传输的实时信息,对所述实时信息进行二次分析,区分不同车辆以及同一车辆的运行轨迹信息,对停车场内部道路运行车辆的坐标位置、运行方向、运行轨迹进行检测。Optionally, the main control computer collects real-time information transmitted from various locations in the parking lot, conducts secondary analysis on the real-time information, distinguishes the running trajectory information of different vehicles and the same vehicle, and calculates the coordinates of vehicles running on the internal roads of the parking lot. Position, running direction, and running trajectory are detected.
另一方面为实现上述目的,本发明提供了一种地下停车场通道运行车辆实时检测方法,包括以下步骤:On the other hand, in order to achieve the above object, the present invention provides a real-time detection method of vehicles operating in underground parking passages, which includes the following steps:
基于毫米波雷达产生并发射电磁波;Generate and emit electromagnetic waves based on millimeter wave radar;
对所述电磁波进行反射,获取反射波;Reflect the electromagnetic wave to obtain the reflected wave;
基于所述反射波对停车场内部道路运行车辆的坐标位置、运行方向、运行轨迹进行检测。Based on the reflected wave, the coordinate position, running direction, and running trajectory of the vehicle running on the road inside the parking lot are detected.
可选地,对所述电磁波进行反射的过程包括:Optionally, the process of reflecting the electromagnetic waves includes:
在停车场通道的中心线设置金属标识带,基于所述金属标识带对所述电磁波进行反射。A metal identification tape is provided on the center line of the parking lot passage, and the electromagnetic wave is reflected based on the metal identification tape.
可选地,基于所述反射波对停车场内部道路运行车辆的坐标位置、运行方向、运行轨迹进行检测的过程包括:Optionally, the process of detecting the coordinate position, running direction, and running trajectory of vehicles running on the road inside the parking lot based on the reflected waves includes:
基于所述反射波的二维时频特征识别金属标识带反射波的位置;Identify the position of the reflected wave of the metal marking band based on the two-dimensional time-frequency characteristics of the reflected wave;
对所述反射波进行首次分析,获取运行车辆的实时信息;实时信息包括坐标位置、速度、运动方向信息;Conduct the first analysis of the reflected wave to obtain real-time information of the operating vehicle; the real-time information includes coordinate position, speed, and movement direction information;
对所述实时信息进行存储并传输;Store and transmit the real-time information;
对所述实时信息进行二次分析,区分不同车辆以及同一车辆的运行轨迹信息。Conduct a secondary analysis on the real-time information to distinguish the running trajectory information of different vehicles and the same vehicle.
可选地,对所述反射波进行首次分析的过程包括:Optionally, the process of first analyzing the reflected wave includes:
对所述反射波进行单列截取,基于短时傅里叶变换法进行时频分析,并叠加后进行能量归一化处理;The reflected waves are intercepted in a single column, time-frequency analysis is performed based on the short-time Fourier transform method, and energy normalization is performed after superposition;
基于时频分析的结果获取不同目标的时频图并生成灰度共生矩阵图,基于所述灰度共生矩阵图获取差异化的多普勒相关性信息,并形成特征值;Based on the results of time-frequency analysis, time-frequency diagrams of different targets are obtained and a gray-level co-occurrence matrix diagram is generated, differentiated Doppler correlation information is obtained based on the gray-level co-occurrence matrix diagram, and eigenvalues are formed;
将所述特征值合成矢量,将所述矢量作为输入,基于神经网络模型进行训练,输出车辆的实时目标坐标位置、速度、运动方向信息结果。The feature values are synthesized into vectors, and the vectors are used as inputs for training based on the neural network model, and the real-time target coordinate position, speed, and motion direction information results of the vehicle are output.
本发明的技术效果为:The technical effects of the present invention are:
本发明的一种地下停车场通道运行车辆实时检测系统的优点在于:The advantages of the real-time detection system for vehicles operating in underground parking lot passages of the present invention are:
(1)识别区域精准可控,通过金属标识带有效解决了毫米波雷达数据缺陷,可人为控制布设区域并结合毫米波雷达精确识别;(1) The identification area is accurate and controllable. The metal identification tape effectively solves the data deficiencies of millimeter wave radar. The layout area can be manually controlled and accurately identified with millimeter wave radar;
(2)数据维度高,可检测车辆目标坐标位置、速度、运动方向、运动轨迹信息;(2) The data dimension is high and can detect vehicle target coordinate position, speed, movement direction, and movement trajectory information;
(3)数据传输实时,延误低稳定性强,通讯单元以固定呼叫应答频率传输数据;(3) Data transmission is real-time, with low delay and strong stability. The communication unit transmits data at a fixed call response frequency;
(4)相对于地磁、激光雷达等现有技术,该系统毫米波雷达布设数量 少、技术成熟且成本低廉,系统总体成本低。(4) Compared with existing technologies such as geomagnetic and laser radar, this system has a small number of millimeter wave radar deployments, mature technology and low cost, and the overall system cost is low.
附图说明Description of drawings
构成本申请的一部分的附图用来提供对本申请的进一步理解,本申请的示意性实施例及其说明用于解释本申请,并不构成对本申请的不当限定。在附图中:The drawings that form a part of this application are used to provide a further understanding of this application. The illustrative embodiments and descriptions of this application are used to explain this application and do not constitute an improper limitation of this application. In the attached picture:
图1为本发明实施例中的车辆实时检测系统结构图;Figure 1 is a structural diagram of a vehicle real-time detection system in an embodiment of the present invention;
图2为本发明实施例中的检测系统实际应用结构图;Figure 2 is a practical application structure diagram of the detection system in the embodiment of the present invention;
图3为本发明实施例中的金属标识带安装位置示意图;其中:1-主控计算机、2-数据分析单元、3-数据储存单元、4-通讯单元、5-毫米波雷达、6-金属标识带。Figure 3 is a schematic diagram of the installation position of the metal identification tape in the embodiment of the present invention; wherein: 1-main control computer, 2-data analysis unit, 3-data storage unit, 4-communication unit, 5-millimeter wave radar, 6-metal Logo tape.
具体实施方式Detailed ways
需要说明的是,在不冲突的情况下,本申请中的实施例及实施例中的特征可以相互组合。下面将参考附图并结合实施例来详细说明本申请。It should be noted that, as long as there is no conflict, the embodiments and features in the embodiments of this application can be combined with each other. The present application will be described in detail below with reference to the accompanying drawings and embodiments.
实施例一 Embodiment 1
如图1所示,本实施例针对现有技术中仅检测停车场车位车辆、出入车辆,不能检测通道内部车辆,检测设备成本高,布设区域受限的问题,提供了一种基于毫米波雷达及金属标识带的地下停车场通道运行车辆实时检测系统,以实现停车场通道运动车辆检测的目的:As shown in Figure 1, this embodiment provides a method based on millimeter-wave radar to solve the problems in the prior art that only vehicles in parking spaces and vehicles entering and exiting the parking lot can be detected, and vehicles in the passage cannot be detected. The cost of detection equipment is high and the layout area is limited. and a real-time vehicle detection system operating in the underground parking lot passage with metal sign tape to achieve the purpose of detecting moving vehicles in the parking lot passage:
该系统包括由停车场桥架吊装的毫米波雷达、通道地面钉装的金属标识带、数据分析单元、数据储存单元、通讯单元和主控计算机组成,其中:The system consists of a millimeter-wave radar hoisted by a parking lot bridge, a metal identification tape nailed to the channel floor, a data analysis unit, a data storage unit, a communication unit and a main control computer, including:
吊装的毫米波雷达通过振荡器产生线性调频连续波或三角波,经由发射机发射,再由天线定向辐射出去,在空间以电磁波形式传播,当遇到目 标时反射回来。由于毫米波雷达的反射数据只能提供距离和角度信息,不能像激光雷达那样提供高度信息,在停车场内部场景下没有高度信息将导致车辆与通道识别异常、缺失等情况。同时由于金属的回波反应远比水泥强烈,因此选取金属标识带的微多普勒特征作为停车场内部道路的时频特征图,分析雷达回波二维时频特征纹理图实现道路位置的确定,利用毫米波对金属材质物品反射率高敏感度高的特点,在停车场通道中心线上安装铜合金、铁合金或铝合金的金属标识带,用作对检测区域的标识。The hoisted millimeter-wave radar generates linear frequency modulation continuous waves or triangular waves through an oscillator, which are emitted by the transmitter and then directionally radiated by the antenna. They propagate in the form of electromagnetic waves in space and are reflected back when encountering a target. Since the reflection data of millimeter wave radar can only provide distance and angle information and cannot provide height information like lidar, the lack of height information in the interior scene of the parking lot will lead to abnormal or missing vehicle and channel identification. At the same time, because the echo response of metal is much stronger than that of cement, the micro-Doppler characteristics of the metal sign strip are selected as the time-frequency characteristic map of the internal road in the parking lot, and the two-dimensional time-frequency characteristic texture map of the radar echo is analyzed to determine the road location. , taking advantage of the high sensitivity and high reflectivity of millimeter waves to metal objects, a copper alloy, iron alloy or aluminum alloy metal identification tape is installed on the center line of the parking lot passage to mark the detection area.
布设好所述设备后,需针对场景特点进行设备标定,由数据分析单元对反射信号进行信号处理、数据处理,分析反射毫米波的二维时频特征,基于二维频谱分析识别金属标识带反射波位置,进而实现对停车场内部通道的标识。After the equipment is deployed, the equipment needs to be calibrated according to the scene characteristics. The data analysis unit performs signal processing and data processing on the reflected signals, analyzes the two-dimensional time-frequency characteristics of the reflected millimeter waves, and identifies the reflection of the metal marking tape based on two-dimensional spectrum analysis. Wave position, thereby realizing the identification of internal passages in the parking lot.
当有车辆经过时,车辆遮挡位于通道中心线的金属标识带,其金属外壳直接反射毫米波,得到反射波,反射波的二维时频特征纹理图反映为汽车外壳的多普勒主频,以及其他部件产生的围绕着汽车主多普勒频率为中心的微动分量。When a vehicle passes by, the vehicle blocks the metal sign strip located on the center line of the channel, and its metal shell directly reflects millimeter waves to obtain a reflected wave. The two-dimensional time-frequency characteristic texture map of the reflected wave is reflected as the Doppler main frequency of the car shell. And the micro-movement components generated by other components are centered around the main Doppler frequency of the car.
当车辆目标运动时,除了车辆躯干有着主要多普勒信息,车辆的其他部件也将会有着除了主速度外的微动速度,因此这部分的多普勒属性也称为微多普勒,由于微多普勒信息需要多帧数据的联合使用才能收集,因此使用大量的时频分析技术进行目标的特征提取,以便区分其差别。时频分析技术包括稀疏傅里叶变换(SFT)、快速傅里叶变换(FFT)。When the vehicle target moves, in addition to the main Doppler information of the vehicle trunk, other parts of the vehicle will also have micro-movement speeds in addition to the main speed. Therefore, the Doppler properties of this part are also called micro-Doppler. Micro-Doppler information requires the joint use of multiple frames of data to collect, so a large number of time-frequency analysis techniques are used to extract target features in order to distinguish their differences. Time-frequency analysis techniques include sparse Fourier transform (SFT) and fast Fourier transform (FFT).
数据分析单元对于检测到的不同目标分别进行单列截取,做时频分析,并叠加后进行能量归一化处理,这里的时频处理采用短时傅里叶变换 (STFT)。在时频处理后,将会以不同目标的时频图来生成灰度共生矩阵图,提供差异化的多普勒相关性信息,并形成特征值。将所提取的特征值合成矢量,以多帧矢量作为输入,以神经网络模型训练来输出车辆的实时目标坐标位置、速度、运动方向信息结果。可使用的训练模型包括:循环神经网络(RNN)、长短时记忆网络(LSTM)。The data analysis unit intercepts single columns of different detected targets, performs time-frequency analysis, and performs energy normalization after superposition. The time-frequency processing here uses short-time Fourier transform (STFT). After time-frequency processing, the gray-level co-occurrence matrix diagram will be generated using the time-frequency diagrams of different targets, providing differentiated Doppler correlation information and forming eigenvalues. The extracted feature values are synthesized into vectors, and multi-frame vectors are used as input, and neural network model training is used to output the vehicle's real-time target coordinate position, speed, and motion direction information results. Available training models include: Recurrent Neural Network (RNN) and Long Short-Term Memory Network (LSTM).
数据分析单元计算得到的数据由储存单元储存,由通讯单元以固定呼叫应答频率(20s、30s、40s、60s等)向主控计算机传输单位时间内储存的车辆实时信息。The data calculated by the data analysis unit is stored in the storage unit, and the communication unit transmits the real-time vehicle information stored in the unit time to the main control computer at a fixed call response frequency (20s, 30s, 40s, 60s, etc.).
主控计算机收集停车场内各位置设备传输的时序信息后,对数据进行二次分析,区分不同车辆单位以及同一车辆单位的运行轨迹信息,实现对停车场内部道路运行车辆的坐标位置、运行方向、运行轨迹的检测。After the main control computer collects the timing information transmitted by the equipment in each location in the parking lot, it performs secondary analysis on the data to distinguish the running trajectory information of different vehicle units and the same vehicle unit, and realize the coordinate position and running direction of the vehicles running on the road inside the parking lot. , Detection of running trajectories.
实施例二 Embodiment 2
如图2-3所示,本实施例中提供地下停车场通道运行车辆实时检测系统的应用实例:As shown in Figure 2-3, this embodiment provides an application example of a real-time detection system for vehicles operating in underground parking lots:
该系统由主控计算机1、数据分析单元2、数据储存单元3、通讯单元4、毫米波雷达5、和金属标识带6组成,其中数据分析单元2、数据储存单元3、通讯单元4、毫米波雷达5共同组成毫米波传感器。如图2,毫米波雷达5向区域内的金属标识带6发射电磁波并接收反射波,若该过程中有运动车辆则接收到不同的电磁波形,接着由毫米波传感器内的数据分析单元2、数据储存单元3、通讯单元4依次分析、储存和传输实时数据。具体的,本实施例中的毫米波雷达采用毫米波雷达公司Continental的ARS-408型雷达,该雷达发射77GHz频段毫米波,该频段内雷达的频率较 高,带宽较宽;探测距离长,探测角度小,探测精度较高,适用于长距离探测;且雷达线路板面积小,整机体积小,最为适用于地下停车场场景。数据处理单元采用雷达内置的解码器,数据储存单元采用10G容量内存卡或磁盘硬盘,通讯单元支持电缆、光缆等有线通讯或蓝牙,射频、红外、WIFI等无线通讯,本实例采用停车场内搭建的工业级无线AP网络传输。最后预处理数据将传输到主控计算机,进行进一步的解波数据处理工作以及运动车辆的重识别与轨迹匹配工作。本实施例中的主控计算机可采用云端服务器,也可在停车场配套机房中搭载工控机。安装在内部通道中心线上的金属标识带示意图如图3所示,本实例中可采用铜合金、铁合金或铝合金材质的金属带,其宽度不超过5cm,厚度小于2mm,长度按照需求延通道方向布设。The system consists of a main control computer 1, a data analysis unit 2, a data storage unit 3, a communication unit 4, a millimeter wave radar 5, and a metal identification tape 6. Among them, the data analysis unit 2, data storage unit 3, communication unit 4, millimeter Wave radar 5 together form a millimeter wave sensor. As shown in Figure 2, the millimeter wave radar 5 emits electromagnetic waves to the metal identification tape 6 in the area and receives the reflected waves. If there is a moving vehicle in the process, it will receive different electromagnetic waveforms. Then, the data analysis unit 2 in the millimeter wave sensor will The data storage unit 3 and the communication unit 4 analyze, store and transmit real-time data in sequence. Specifically, the millimeter wave radar in this embodiment adopts the ARS-408 radar of the millimeter wave radar company Continental. This radar emits millimeter waves in the 77GHz frequency band. The frequency of the radar in this frequency band is higher and the bandwidth is wider. The detection range is long and the detection range is long. The angle is small, the detection accuracy is high, and it is suitable for long-distance detection; the radar circuit board area is small, and the whole machine is small in size, so it is most suitable for underground parking lots. The data processing unit uses a built-in decoder of the radar. The data storage unit uses a 10G capacity memory card or magnetic disk hard drive. The communication unit supports wired communication such as cables and optical cables or wireless communication such as Bluetooth, radio frequency, infrared, and WIFI. This example is built in a parking lot. Industrial-grade wireless AP network transmission. Finally, the preprocessed data will be transmitted to the main control computer for further processing of dewavelength data and re-identification and trajectory matching of moving vehicles. The main control computer in this embodiment can be a cloud server, or it can be equipped with an industrial computer in the supporting computer room of the parking lot. The schematic diagram of the metal identification tape installed on the center line of the internal channel is shown in Figure 3. In this example, a metal tape made of copper alloy, iron alloy or aluminum alloy can be used. Its width does not exceed 5cm and its thickness is less than 2mm. The length can be extended according to the needs of the channel. Direction layout.
实施例三 Embodiment 3
本实施例中提供一种地下停车场通道运行车辆实时检测方法,具体包括以下步骤:This embodiment provides a method for real-time detection of vehicles operating in underground parking lot passages, which specifically includes the following steps:
步骤一:通过毫米波雷达产生并发射电磁波。Step 1: Generate and emit electromagnetic waves through millimeter wave radar.
步骤二:在停车场通道的中心线设置铜合金、铁合金或铝合金的金属标识带,通过所述金属标识带对所述电磁波进行反射,获取反射波。Step 2: Set a metal identification tape of copper alloy, iron alloy or aluminum alloy on the center line of the parking lot passage, and reflect the electromagnetic wave through the metal identification tape to obtain the reflected wave.
步骤三:基于反射波的二维时频特征分析识别所述金属标识带反射波的位置。Step 3: Identify the position of the reflected wave of the metal marking strip based on the two-dimensional time-frequency characteristic analysis of the reflected wave.
步骤四:对所述反射波进行单列截取,基于短时傅里叶变换法进行时频分析,并叠加后进行能量归一化处理;Step 4: Intercept the reflected waves in a single column, conduct time-frequency analysis based on the short-time Fourier transform method, and perform energy normalization after superposition;
基于时频分析的结果获取不同目标的时频图并生成灰度共生矩阵图, 基于所述灰度共生矩阵图获取差异化的多普勒相关性信息,并形成特征值;Based on the results of time-frequency analysis, time-frequency diagrams of different targets are obtained and a gray-level co-occurrence matrix diagram is generated, differentiated Doppler correlation information is obtained based on the gray-level co-occurrence matrix diagram, and eigenvalues are formed;
将所述特征值合成矢量,将所述矢量作为输入,基于神经网络模型进行训练,输出车辆的实时目标坐标位置、速度、运动方向信息结果;并对首次分析获取的实时信息进行存储并传输。The feature values are synthesized into vectors, and the vectors are used as inputs for training based on the neural network model to output the vehicle's real-time target coordinate position, speed, and motion direction information results; and the real-time information obtained through the first analysis is stored and transmitted.
步骤五:对所述实时信息进行二次分析,区分不同车辆单位以及同一车辆单位的运行轨迹信息,实现对停车场内部道路运行车辆的坐标位置、运行方向、运行轨迹的检测。Step 5: Conduct a secondary analysis of the real-time information to distinguish the running trajectory information of different vehicle units and the same vehicle unit, and realize the detection of the coordinate position, running direction and running trajectory of the vehicles running on the road inside the parking lot.
以上所述,仅为本申请较佳的具体实施方式,但本申请的保护范围并不局限于此,任何熟悉本技术领域的技术人员在本申请揭露的技术范围内,可轻易想到的变化或替换,都应涵盖在本申请的保护范围之内。因此,本申请的保护范围应该以权利要求的保护范围为准。The above are only preferred specific implementations of the present application, but the protection scope of the present application is not limited thereto. Any person familiar with the technical field can easily think of changes or modifications within the technical scope disclosed in the present application. Replacements shall be covered by the protection scope of this application. Therefore, the protection scope of this application should be subject to the protection scope of the claims.

Claims (10)

  1. 一种地下停车场通道运行车辆实时检测系统,其特征在于,包括毫米波雷达、金属标识带、数据分析单元、数据储存单元、通讯单元和主控计算机;A real-time detection system for vehicles operating in an underground parking lot passage, which is characterized by including a millimeter wave radar, a metal identification tape, a data analysis unit, a data storage unit, a communication unit and a main control computer;
    所述毫米波雷达用于产生并发射电磁波;The millimeter wave radar is used to generate and emit electromagnetic waves;
    所述金属标识带用于对所述电磁波进行反射,获取反射波;The metal identification tape is used to reflect the electromagnetic wave and obtain the reflected wave;
    所述数据分析单元用于根据所述反射波获取检测区域,并对所述反射波进行处理,获取车辆运动的实时信息;The data analysis unit is used to obtain a detection area according to the reflected wave, process the reflected wave, and obtain real-time information about vehicle movement;
    所述数据储存单元用于对所述实时信息进行存储;The data storage unit is used to store the real-time information;
    所述通讯单元用于向所述主控计算机传输所述实时信息;The communication unit is used to transmit the real-time information to the main control computer;
    所述主控计算机用于根据所述实时信息区分不同车辆以及同一车辆的运行轨迹信息。The main control computer is used to distinguish the running trajectory information of different vehicles and the same vehicle according to the real-time information.
  2. 根据权利要求1所述的地下停车场通道运行车辆实时检测系统,其特征在于,所述毫米波雷达还用于接收所述金属标识带的反射波;The real-time detection system for vehicles operating in underground parking passages according to claim 1, wherein the millimeter wave radar is also used to receive the reflected wave of the metal identification tape;
    所述毫米波雷达包括振荡器、发射机、天线;所述振荡器用于产生线性调频连续波或三角波,所述发射机用于发射所述线性调频连续波或三角波,所述天线用于对所述线性调频连续波或三角波进行定向辐射;The millimeter wave radar includes an oscillator, a transmitter, and an antenna; the oscillator is used to generate a linear frequency modulated continuous wave or a triangular wave; the transmitter is used to transmit the linear frequency modulated continuous wave or a triangular wave; and the antenna is used to The linear frequency modulated continuous wave or triangular wave carries out directional radiation;
    所述线性调频连续波或三角波在空间以电磁波形式传播,当遇到目标时反射回来,得到反射波。The linear frequency modulated continuous wave or triangular wave propagates in space in the form of electromagnetic waves. When it encounters a target, it is reflected back to obtain a reflected wave.
  3. 根据权利要求1所述的地下停车场通道运行车辆实时检测系统,其特征在于,所述数据分析单元通过分析所述反射波的二维时频特征,基于二维频谱分析识别金属标识带反射波的位置,对停车场的内部通道进行标识。The real-time detection system for vehicles running in underground parking passages according to claim 1, characterized in that the data analysis unit identifies the reflected wave of the metal marking band based on two-dimensional spectrum analysis by analyzing the two-dimensional time-frequency characteristics of the reflected wave. location to mark the internal passages of the parking lot.
  4. 根据权利要求1所述的地下停车场通道运行车辆实时检测系统,其特征在于,当车辆经过所述检测区域时,所述数据分析单元对所述反射波进行单列截取,基于短时傅里叶变换法进行时频分析,并叠加后进行能量归一化处理;The real-time detection system for vehicles running in underground parking lots according to claim 1, characterized in that when the vehicle passes through the detection area, the data analysis unit intercepts the reflected waves in a single column and analyzes the reflected waves based on short-time Fourier transform. The transformation method is used for time-frequency analysis, and energy normalization is performed after superposition;
    基于时频分析的结果获取不同目标的时频图并生成灰度共生矩阵图,基于所述灰度共生矩阵图获取差异化的多普勒相关性信息,并形成特征值;Based on the results of time-frequency analysis, time-frequency diagrams of different targets are obtained and a gray-level co-occurrence matrix diagram is generated, differentiated Doppler correlation information is obtained based on the gray-level co-occurrence matrix diagram, and eigenvalues are formed;
    将所述特征值合成矢量,将所述矢量作为输入,基于神经网络模型进行训练,输出车辆的实时目标坐标位置、速度、运动方向信息结果。The feature values are synthesized into vectors, and the vectors are used as inputs for training based on the neural network model, and the real-time target coordinate position, speed, and motion direction information results of the vehicle are output.
  5. 根据权利要求1所述的地下停车场通道运行车辆实时检测系统,其特征在于,所述通讯单元以固定呼叫应答频率向所述主控计算机传输单位时间内车辆的实时信息。The real-time detection system for vehicles operating in underground parking lot passages according to claim 1, wherein the communication unit transmits real-time information about vehicles within a unit time to the main control computer at a fixed call response frequency.
  6. 根据权利要求1所述的地下停车场通道运行车辆实时检测系统,其特征在于,所述主控计算机通过收集停车场各位置传输的实时信息,对所述实时信息进行二次分析,区分不同车辆以及同一车辆的运行轨迹信息,对停车场内部道路运行车辆的坐标位置、运行方向、运行轨迹进行检测。The real-time detection system for vehicles operating in the underground parking lot passage according to claim 1, characterized in that the main control computer collects real-time information transmitted from various locations in the parking lot, performs secondary analysis on the real-time information, and distinguishes different vehicles. As well as the running trajectory information of the same vehicle, the coordinate position, running direction and running trajectory of the vehicle running on the road inside the parking lot are detected.
  7. 一种地下停车场通道运行车辆实时检测方法,其特征在于,包括以下步骤:A method for real-time detection of vehicles operating in underground parking passages, which is characterized by including the following steps:
    基于毫米波雷达产生并发射电磁波;Generate and emit electromagnetic waves based on millimeter wave radar;
    对所述电磁波进行反射,获取反射波;Reflect the electromagnetic wave to obtain the reflected wave;
    基于所述反射波对停车场内部道路运行车辆的坐标位置、运行方向、运行轨迹进行检测。Based on the reflected wave, the coordinate position, running direction, and running trajectory of the vehicle running on the road inside the parking lot are detected.
  8. 根据权利要求7所述的地下停车场通道运行车辆实时检测方法,其 特征在于,对所述电磁波进行反射的过程包括:The real-time detection method of vehicles running in underground parking lots according to claim 7, wherein the process of reflecting the electromagnetic waves includes:
    在停车场通道的中心线设置金属标识带,基于所述金属标识带对所述电磁波进行反射。A metal identification tape is provided on the center line of the parking lot passage, and the electromagnetic wave is reflected based on the metal identification tape.
  9. 根据权利要求7所述的地下停车场通道运行车辆实时检测方法,其特征在于,基于所述反射波对停车场内部道路运行车辆的坐标位置、运行方向、运行轨迹进行检测的过程包括:The method for real-time detection of vehicles running in underground parking passages according to claim 7, characterized in that the process of detecting the coordinate position, running direction and running trajectory of vehicles running on roads inside the parking lot based on the reflected waves includes:
    基于所述反射波的二维时频特征分析识别金属标识带反射波的位置;Identify the position of the reflected wave of the metal marking band based on the two-dimensional time-frequency characteristic analysis of the reflected wave;
    对所述反射波进行首次分析,获取运行车辆的实时信息;实时信息包括坐标位置、速度、运动方向信息;Conduct the first analysis of the reflected wave to obtain real-time information of the operating vehicle; the real-time information includes coordinate position, speed, and movement direction information;
    对所述实时信息进行存储并传输;Store and transmit the real-time information;
    对所述实时信息进行二次分析,区分不同车辆以及同一车辆的运行轨迹信息。Conduct a secondary analysis on the real-time information to distinguish the running trajectory information of different vehicles and the same vehicle.
  10. 根据权利要求9所述的地下停车场通道运行车辆实时检测方法,其特征在于,对所述反射波进行首次分析的过程包括:The method for real-time detection of vehicles operating in underground parking passages according to claim 9, characterized in that the process of first analyzing the reflected waves includes:
    对所述反射波进行单列截取,基于短时傅里叶变换法进行时频分析,并叠加后进行能量归一化处理;The reflected waves are intercepted in a single column, time-frequency analysis is performed based on the short-time Fourier transform method, and energy normalization is performed after superposition;
    基于时频分析的结果获取不同目标的时频图并生成灰度共生矩阵图,基于所述灰度共生矩阵图获取差异化的多普勒相关性信息,并形成特征值;Based on the results of time-frequency analysis, time-frequency diagrams of different targets are obtained and a gray-level co-occurrence matrix diagram is generated, differentiated Doppler correlation information is obtained based on the gray-level co-occurrence matrix diagram, and eigenvalues are formed;
    将所述特征值合成矢量,将所述矢量作为输入,基于神经网络模型进行训练,输出车辆的实时目标坐标位置、速度、运动方向信息结果。The feature values are synthesized into vectors, and the vectors are used as inputs for training based on the neural network model, and the real-time target coordinate position, speed, and motion direction information results of the vehicle are output.
PCT/CN2022/115393 2022-08-29 2022-08-29 Underground parking lot passage moving vehicle real-time detection system and method WO2024044870A1 (en)

Priority Applications (1)

Application Number Priority Date Filing Date Title
PCT/CN2022/115393 WO2024044870A1 (en) 2022-08-29 2022-08-29 Underground parking lot passage moving vehicle real-time detection system and method

Applications Claiming Priority (1)

Application Number Priority Date Filing Date Title
PCT/CN2022/115393 WO2024044870A1 (en) 2022-08-29 2022-08-29 Underground parking lot passage moving vehicle real-time detection system and method

Publications (1)

Publication Number Publication Date
WO2024044870A1 true WO2024044870A1 (en) 2024-03-07

Family

ID=90100076

Family Applications (1)

Application Number Title Priority Date Filing Date
PCT/CN2022/115393 WO2024044870A1 (en) 2022-08-29 2022-08-29 Underground parking lot passage moving vehicle real-time detection system and method

Country Status (1)

Country Link
WO (1) WO2024044870A1 (en)

Citations (5)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN110736982A (en) * 2019-10-28 2020-01-31 江苏集萃智能传感技术研究所有限公司 Underground parking lot vehicle tracking method and device based on radar monitoring
CN110865365A (en) * 2019-11-27 2020-03-06 江苏集萃智能传感技术研究所有限公司 Parking lot noise elimination method based on millimeter wave radar
CN112389505A (en) * 2019-08-16 2021-02-23 比亚迪股份有限公司 Train positioning system and train positioning method
CN113419244A (en) * 2021-05-28 2021-09-21 同济大学 Vehicle track splicing method based on millimeter wave radar data
CN113447905A (en) * 2021-06-29 2021-09-28 西安电子科技大学 Double-millimeter-wave radar human body falling detection device and detection method

Patent Citations (5)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN112389505A (en) * 2019-08-16 2021-02-23 比亚迪股份有限公司 Train positioning system and train positioning method
CN110736982A (en) * 2019-10-28 2020-01-31 江苏集萃智能传感技术研究所有限公司 Underground parking lot vehicle tracking method and device based on radar monitoring
CN110865365A (en) * 2019-11-27 2020-03-06 江苏集萃智能传感技术研究所有限公司 Parking lot noise elimination method based on millimeter wave radar
CN113419244A (en) * 2021-05-28 2021-09-21 同济大学 Vehicle track splicing method based on millimeter wave radar data
CN113447905A (en) * 2021-06-29 2021-09-28 西安电子科技大学 Double-millimeter-wave radar human body falling detection device and detection method

Similar Documents

Publication Publication Date Title
US11340332B2 (en) Method and apparatus for processing radar data
CN105261215B (en) Intelligent transportation behavior cognitive method and system based on microwave
Urazghildiiev et al. Vehicle classification based on the radar measurement of height profiles
US11506776B2 (en) Method and device with improved radar resolution
Fang et al. A low-cost vehicle detection and classification system based on unmodulated continuous-wave radar
CN112162283B (en) Multi-target detection system of full-road-section networking traffic radar
CN103048656B (en) Tunnel surrounding rock deformation measurement early warning system and method based on continuous wave radar
US20200333453A1 (en) Method and device for determining at least one parameter of an object
US11448744B2 (en) Sequential doppler focusing
Cui et al. 3D detection and tracking for on-road vehicles with a monovision camera and dual low-cost 4D mmWave radars
CN105575132B (en) Detection method and system be present in the crossing based on microwave
CN103176183A (en) Short-range high-resolution detection imaging method and device for implementing same
Baczyk et al. Traffic density monitoring using passive radars
Zhu et al. Measurement and ray-tracing simulation for millimeter-wave automotive radar
WO2024044870A1 (en) Underground parking lot passage moving vehicle real-time detection system and method
Sadovskis et al. Modern methods for UAV detection, classification, and tracking
CN103745601A (en) Speeding vehicle lane detection method
JP6745489B2 (en) Detector
Czyżewski et al. Comparative study on the effectiveness of various types of road traffic intensity detectors
Tan et al. Bidirectional multi-lane vehicle counting approach based on trajectory features using MIMO radar
Shafew et al. A Study on mm Wave Sensor Technology and its Applications
Sun et al. High-Precision Railway Fastener Detecting via Deep Learning Radar for Intelligent Train Positioning
Raimondi et al. mmDetect: YOLO-based Processing of mm-Wave Radar Data for Detecting Moving People
Ren et al. Research and Implementation of 77GHz Automotive Radar Target Detection Technology
CN103163517A (en) Measured target real-time speed estimation method based on back wave phase detection

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: 22956706

Country of ref document: EP

Kind code of ref document: A1