CN110058239B - Vehicle-mounted millimeter wave radar device and target detection method - Google Patents
Vehicle-mounted millimeter wave radar device and target detection method Download PDFInfo
- Publication number
- CN110058239B CN110058239B CN201910355156.4A CN201910355156A CN110058239B CN 110058239 B CN110058239 B CN 110058239B CN 201910355156 A CN201910355156 A CN 201910355156A CN 110058239 B CN110058239 B CN 110058239B
- Authority
- CN
- China
- Prior art keywords
- target
- track
- fences
- fence
- information
- Prior art date
- Legal status (The legal status 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 status listed.)
- Active
Links
Classifications
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01S—RADIO DIRECTION-FINDING; RADIO NAVIGATION; DETERMINING DISTANCE OR VELOCITY BY USE OF RADIO WAVES; LOCATING OR PRESENCE-DETECTING BY USE OF THE REFLECTION OR RERADIATION OF RADIO WAVES; ANALOGOUS ARRANGEMENTS USING OTHER WAVES
- G01S13/00—Systems using the reflection or reradiation of radio waves, e.g. radar systems; Analogous systems using reflection or reradiation of waves whose nature or wavelength is irrelevant or unspecified
- G01S13/88—Radar or analogous systems specially adapted for specific applications
- G01S13/93—Radar or analogous systems specially adapted for specific applications for anti-collision purposes
- G01S13/931—Radar or analogous systems specially adapted for specific applications for anti-collision purposes of land vehicles
Landscapes
- Engineering & Computer Science (AREA)
- Radar, Positioning & Navigation (AREA)
- Remote Sensing (AREA)
- Physics & Mathematics (AREA)
- Electromagnetism (AREA)
- Computer Networks & Wireless Communication (AREA)
- General Physics & Mathematics (AREA)
- Radar Systems Or Details Thereof (AREA)
Abstract
The invention relates to a vehicle-mounted millimeter wave radar device and a target detection method, comprising a radio frequency front end module, a power supply module and a signal processing module, wherein the power supply module supplies power for the radio frequency front end module and the signal processing module, the radio frequency front end module is used for transmitting millimeter wave signals, receiving echo signals of targets and preprocessing the echo signals of the targets, and the signal processing module comprises: a distance and speed acquisition unit for acquiring speed information and distance information of the target according to the preprocessed signals; a position acquisition unit for acquiring position information of the target according to the preprocessed signal; the target detection unit is used for filtering the fences at the two sides of the track according to the obtained speed information, distance information and position information of the target, and extracting the target in the fences as an effective target. The invention can effectively filter the fences on two sides of the rail transit, and is convenient for users to make decisions.
Description
Technical Field
The invention relates to the technical field of millimeter wave radar detection, in particular to a vehicle-mounted millimeter wave radar device and a target detection method.
Background
Radar is a method of finding a target and detecting a spatial position of the target using radio. Radar can be classified into pulse radar, continuous wave radar, pulse compression radar, and frequency agile radar according to signal form. And the Frequency Modulation Continuous Wave (FMCW) radar is applied in the field of automotive radar due to the characteristics of simple structure, easy modulation, low cost, simple signal processing and the like. The frequency modulation continuous radar obtains the information of the target through the frequency difference between the echo signal frequency and the transmitting signal at any time. The millimeter wave radar is a detection radar of a radar tool in a millimeter wave band, the wavelength of the millimeter wave is between centimetre waves and microwaves, and the wavelength is 1-10 mm.
With the development of intelligent traffic and unmanned, the development of active detection sensors is promoted. The millimeter wave radar is an important part of an active detector of an automobile, has the characteristics of small antenna caliber, large bandwidth, strong anti-interference capability, no influence of light and all-weather work, and is highly valued by units such as government departments, research institutions, universities, enterprises and the like of various countries. However, today millimeter wave radar technology is not mature enough, mostly stays in the functions of ranging, speed measuring and angle measuring, and the precision is not high enough, and the applications of adaptive cruise control (Adaptive Cruise Control, ACC), front car collision avoidance warning system (Forward Collision Warning System, FCWS) and advanced driving assistance system (Advanced Driver Assistance Systems, ADAS) cannot be satisfied yet.
In recent years, millimeter wave radars find certain application in the fields of tramcars, trains, cloud tracks and the like. However, because of the specificity of the vehicle running track, the millimeter wave radar can cause erroneous judgment of the decision terminal when detecting fence targets on both sides of the track.
Disclosure of Invention
The invention aims to solve the technical problem of providing a vehicle-mounted millimeter wave radar device and a target detection method, which can effectively filter fences on two sides of rail traffic, and are convenient for users to make decisions.
The technical scheme adopted for solving the technical problems is as follows: the utility model provides a vehicle-mounted millimeter wave radar device, includes radio frequency front end module, power module and signal processing module, power module supplies power for radio frequency front end module and signal processing module, radio frequency front end module for the transmission millimeter wave signal, the echo signal of receiving target, and carry out preliminary treatment to the echo signal of target, signal processing module includes: a distance and speed acquisition unit for acquiring speed information and distance information of the target according to the preprocessed signals; a position acquisition unit for acquiring position information of the target according to the preprocessed signal; the target detection unit is used for determining whether the target is a curve or a straight road according to the obtained speed information, distance information and position information of the target, filtering fences on two sides of the track, and extracting the target in the fences as an effective target.
The position acquisition unit is provided with a data association unit at the back, and the data association unit solves the problem of speed ambiguity by the principle that the target distance cannot be suddenly changed.
The target detection unit compares the speed information of the detected target with the speed information of the whole vehicle, judges whether the detected target is a static target, if so, determines whether the current track is a straight track or a curve track through a RANSAC algorithm, and determines the fence position.
If the target is not a static target, judging whether the abscissa value of the target is smaller than a fixed value between 1/2 fences, if so, the target is an effective target, and if not, the target is an ineffective target.
After the current track is determined, the fence position is determined according to the fixed value between fences of which the abscissa value of the position information of the target is equal to 1/2, and if the abscissa value of the target is smaller than the fixed value between fences of which the ratio is 1/2, the target is an effective target.
The RANSAC algorithm processing flow is as follows: any two points are found out to construct a linear equation, all stationary targets are traversed, a threshold value is set, if the number of stationary targets on the found straight line is larger than the threshold value, the track at the moment is determined to be a straight line track, otherwise, the track is a curve track, and a straight line covering the most stationary targets is taken as a fence.
According to the obtained fence, if the target display is positioned in the fence, the target is an effective target, and if the target display is positioned outside the fence, the target is regarded as an ineffective target.
The technical scheme adopted for solving the technical problems is as follows: the object detection method of the vehicle-mounted millimeter wave radar device comprises the following steps:
(1) The radar transmits electromagnetic signals, receives echo signals of the target, and preprocesses the echo signals of the target;
(2) Acquiring speed information, distance information and position information of a target according to the preprocessed signals;
(3) And determining whether the road is a curve or a straight road according to the obtained speed information, distance information and position information of the target, filtering fences on two sides of the track, and extracting the target in the fences as an effective target.
The specific steps of target detection are as follows:
(3.1) comparing the speed information of the detected target in the step (3) with the speed information of the whole vehicle, and judging whether the detected target is a static target or not;
(3.2) if the target is a stationary target, determining whether the current track is a straight track or a curved track through a RANSAC algorithm, and determining a fence position;
after the current track is determined, determining the position of the fence according to a fixed value between fences with the abscissa value equal to 1/2 of the target position information, and if the abscissa value of the target is smaller than the fixed value between the fences with the ratio of 1/2, determining the target as an effective target;
(3.2.1) the RANSAC algorithm processing flow is as follows: any two points are found out to construct a linear equation, all stationary targets are traversed, a threshold value is set, if the number of the stationary targets on the found straight line is larger than the threshold value, the track at the moment is determined to be a straight line track, otherwise, the track is a curve track, and a straight line covering the most stationary targets is taken as a fence;
and (3.3) if the target is not a static target, judging whether the abscissa value of the target is smaller than a fixed value between 1/2 fences, if so, judging that the target is a valid non-static target, and otherwise, judging that the target is an invalid target.
Advantageous effects
Due to the adoption of the technical scheme, compared with the prior art, the invention has the following advantages and positive effects: the invention not only has the functions of speed measurement, distance measurement and angle measurement, but also has the functions of target tracking, target classification and data post-processing.
Drawings
FIG. 1 is a system block diagram of an embodiment of the present invention;
FIG. 2 is a signal processing flow diagram in an embodiment of the invention;
FIG. 3 is a schematic diagram of a display module according to an embodiment of the invention;
FIG. 4 is a schematic diagram of a data management module in an embodiment of the invention;
FIG. 5 is a schematic diagram of an alarm module in an embodiment of the invention;
FIG. 6 is a flow chart of linear track data processing in an embodiment of the invention;
fig. 7 is a flowchart of the object detection process in the embodiment of the present invention.
Detailed Description
The invention will be further illustrated with reference to specific examples. It is to be understood that these examples are illustrative of the present invention and are not intended to limit the scope of the present invention. Further, it is understood that various changes and modifications may be made by those skilled in the art after reading the teachings of the present invention, and such equivalents are intended to fall within the scope of the claims appended hereto.
The embodiment of the invention relates to a vehicle millimeter wave radar device, which comprises a power supply module, a radio frequency front end, a signal processing module, a communication module, a data management module, a fault alarm module and a display module as shown in fig. 1. The power module mainly provides corresponding working power for the signal processing module, the radio frequency front end, the display module, the communication module, the data management module and the like; the radio frequency front end mainly emits electromagnetic waves with certain frequency, echo signals are generated when the electromagnetic waves are contacted with the surface of a target, the receiving antenna receives the echo signals and converts the echo signals into intermediate frequency signals through the signal conditioning circuit, and the intermediate frequency signals enter the analog-to-digital converter ADC through the low-pass filter circuit (filtering target intermediate frequency signals beyond the maximum detection distance of the radar); the maximum ranging threshold is related to the frequency of the intermediate frequency signal, and in order to avoid the occurrence of the distance blurring phenomenon, the device carries out the processing of a low-pass filter on the intermediate frequency signal so that the frequency of the output signal is within half of the sampling frequency of the ADC. The signal processing module is mainly used for sequentially carrying out Fast Fourier Transform (FFT), constant false alarm detection (CFAR), digital Beam Forming (DBF), target tracking, target detection (RANSAC) and target classification (classification) on data acquired by the ADC. The display module comprises target distance display, target speed display, target angle display, target category display, target state display and display setting options; the fault alarm module comprises an audible alarm, a lamplight alarm, a silencing button and a reset button; data management includes data storage, data printing, data analysis, and data purging.
The signal processing module is shown in fig. 2, and the FFT unit in the module mainly processes ADC data, and the FFT unit realizes conversion from time domain to frequency domain, obtains distance information of the target through one-dimensional fast fourier transform, and obtains speed information of the target through two-dimensional fast fourier transform. In order to prevent spectrum leakage, windowing operations are also needed, and methods such as hamming windows, chebyshev windows, blackman windows and the like are adopted for windowing. The present embodiment employs chebyshev windows.
The speed information and the distance information of the target obtained by the FFT unit contain certain false alarm and clutter information, CFAR processing is needed to be carried out on the result of the FFT unit, and the result obtained by the CFAR processing is information of a real target; in this embodiment, in order to reduce the shadowing effect, the distance information is processed by an OS-CFAR algorithm (ordered statistics type constant false alarm detection); in order to reduce the operation amount, the speed information is processed by using a CA-CFAR algorithm (unit average method constant false alarm detection).
When the speeds and distances of two or more targets are the same, an angular measurement of the targets is required in order to accurately obtain the specific position of the targets. The DBF is mainly used for calculating and obtaining the relative radar angular position of a target, so as to distinguish a plurality of targets and determine the specific positions of the targets.
Because the road condition of the vehicle running is complex, a data association unit is added after the DBF, so as to further solve the speed ambiguityThe problem is that the data association unit can calculate the accurate target speed according to a formula of speed and distance according to the principle that the distance of the target cannot be suddenly changed under the condition that whether the target speed returned by the radar is in a speed fuzzy phenomenon or not is not determined. Let t be R t The position at time t-1 is R t-1 ，V t For the speed of radar return at time t, V t-1 The speed of radar return at time t-1, Δt is the time difference. The formula of the speed and the distance is R t ＝R t-1 +V t-1 * Δt, it can be seen that For the true speed of the target at time t-1 calculated from the target position, since the radar refresh rate is in the order of milliseconds, Δt is small enough, the speed of the target at time t-1 and the speed of the target at time t-1 can be considered to be substantially the same, in which case the comparison ∈>And radar return V t If the difference in speed is large, the difference in speed can be very large. If the target value V t And V is equal to t-1 If the difference is large, the target is considered to be false alarm or speed ambiguity is generated, and the target needs to be removed.
The main purpose of the target detection unit of the device is to filter the fences on two sides of the track, extract the targets in the fences and output the targets to the user, and the detection process is as follows: the target detection of the rail transit comprises the steps of determining whether a rail is a straight line or a curve, judging whether a target is in the rail or not by adopting different methods according to the difference of the straight line rail and the curve, and outputting an effective target.
The target detection method of the vehicle-mounted millimeter wave radar device of the embodiment comprises the following steps: (1) The radar transmits millimeter wave signals, receives echo signals of the targets, and preprocesses the echo signals of the targets; (2) Acquiring speed information, distance information and position information of a target according to the preprocessed signals; (3) And filtering the fences at two sides of the track according to the obtained speed information, distance information and position information of the targets, and extracting the targets in the fences as effective targets. The method comprises the following steps:
determining whether the target is in the rail fence, the radar detecting target information including distance, speed and angle, the distance, speed and angle information being usable (R x 、R y ,V x 、V y ,A x 、A y ) And (3) representing. The CAN interface of the radar is communicated with the whole vehicle, the speed of the whole vehicle is introduced, and the speed of a target detected by the radar is compared with the speed of the whole vehicle, so that whether the target detected by the radar is a static target or not CAN be judged. When the radar detected target speed is equal to the whole vehicle speed and the direction is opposite, the target is judged to be a stationary target (relatively largely stationary). When the vehicle runs along the track, the fence spacing at two sides of the track is a fixed value R, and the target position is R x (distance in the x-axis direction after the target position vector is decomposed). In detection, firstly, judging whether the target is relatively static or not, if not, judging whether the target is R x And r/2, if yes, outputting a target for effective target, and if not, outputting no target for ineffective target. If the target is a static target, the target is processed by a RANSAC algorithm (random sampling consensus algorithm), and the processing flow is as follows: first, two points (R x1 、R y1 )、(R x2 、R y2 ) Two points construct a linear equation of y=ax+b; secondly, traversing all the static targets, and finding out a straight line covering the most static targets as a fence. Traversing only the speed 0 object here can reduce the traversing time, the purpose of which is to determine whether the object is currently running on a straight track or on a curved track, and whether the stationary object is a fence. At this time, a RANSAC threshold value α is set, if the target number β on the straight line is greater than α, the track at this time is determined to be a straight line track, at this time, the straight line y=ax+b may be obtained and determined to be a fence, and filtering is performed to remove the fence from display. When the detected static target is in the fence, outputting the target to a user, and if the static target is out of the fence, filtering and not displaying. As shown in fig. 7, in a straight line of the vehicleThe determination criteria of the effective target during running are that the target speeds v=0, R x =r/2, then the target is a fence on a straight line that accords with the RANSAC algorithm detection, and is not output; if R is x And if the target is in the fence, the target is an effective target, and the target is output. If the target number β on this straight line is smaller than α, it is determined that the curve track is entered at this time, and the effective target determination criteria are that the target speeds v=0, R x =r/2, then the target is a fence on a straight line that accords with the RANSAC algorithm detection, and is not output; if R is x And if the target is in the fence, the target is an effective target, and the target is output.
As shown in FIG. 6, only the stationary object can be judged first, all the stationary objects are traversed according to RANSAC to obtain a linear fence which covers the stationary object most, and R of the moving object is not required after the track is determined to be a linear track x And (3) judging the ratio < r/2, displaying a moving or static target in the fence according to the linear fence, taking the moving or static target as an effective target, not displaying a moving or static target outside the fence, taking the moving or static target as an ineffective target, filtering the fence, and preventing false alarm. When the target is detected, whether the target is a static target or a moving target, if the target is not in the fence, the target is not output to a user, namely is not output on the display screen; and if the target is in the fence, outputting the target. At this time, R by comparison of targets is not required x And r/2 to determine whether the moving object or the stationary object is a valid object.
According to the invention, the iteration mode is adopted to estimate the parameters of the mathematical model from a group of observed data containing discrete data, and the target stationary relative to the vehicle speed is traversed, so that the iteration times are reduced, and the calculation speed is further improved. When a target that is stationary relative to the radar and in the same direction is detected, the target may be processed using the RANSAC algorithm, which may then filter the fence to the user to prevent false alarms. Since the guardrails/fences on both sides of the rail transit field are generally made of metal, the radar is prone to erroneous judgment (false alarm) after detecting the fences/guardrails. The inventor finds that the spacing between the fences at two sides of the track is a fixed value, so that the distance between the fences can be judged firstly, then whether the target is in the fences is judged to determine whether the target is effective or not, namely, the distance between the targets is helped to judge whether the target is in the fences or not, and if the target is in the fences or the fences, the target is judged to be the effective target and is output to the whole vehicle. If the object is not in the fence/guardrail, the object is judged to be an invalid object and is not output to the whole vehicle.
In order to detect the specific position of the target in real time, the target needs to be tracked. The tracking algorithm of the device comprises, but is not limited to, an extended Kalman filtering algorithm (Extended Kalman Filter, EKF), and the algorithm estimates, tracks and predicts the distance, speed and angle of the target, so that the running condition of the target can be tracked in real time.
The device also comprises a target classifying unit, and can distinguish targets such as pedestrians, bicycles, motorcycles, cars, trucks and the like according to the size of Radar Cross-Section (RCS) of the detected targets, so that the targets are displayed on a display module for the whole vehicle to make decisions. The device is not only limited to realizing the classification of the targets by the RCS, but also can construct a library of targets such as pedestrians, bicycles, motorcycles, cars, trucks and the like, and when the targets are detected, the targets can be accurately identified by a table look-up method; the target recognition method can also adopt complex algorithms such as deep learning, machine learning, neural network and the like to recognize targets such as pedestrians, bicycles, motorcycles, cars, trucks and the like.
The display module is shown in fig. 3, and displays the speed, distance, angle, category and status of the target, respectively. The state of the target comprises a static state, a far-away state and a near-close state; the display setting options are information such as setting the number of display targets, setting the distance range in which the display detects the targets, setting the angle range of the display targets, setting the status display of the display targets, setting the categories of the display targets, and the like.
The data management module is shown in fig. 4, and the data storage in the module is data for storing ADC data and FFT (fourier transform), CFAR (constant false alarm detection), tracking (tracking target), and classification (target classification) in signal processing; the data printing is mainly to print the data of FFT, CFAR, tracking, clustering in the data storage module respectively; the data clearing is to clear the data in the storage module so as to store more data; the data analysis is to analyze ADC data and FFT, CFAR, tracking, RANSAC, clustering data.
The alarm module is shown in fig. 5, and can alarm faults of each module and inform a user to check through sound alarm and different-color lamplight alarm. According to different fault characteristics, fault codes can be output on the display screen for users to refer to and locate fault positions. The device also comprises a silencing button and a reset button, and when the silencing button is pressed down, the sound alarm is eliminated; when the reset button is pressed, the system is restarted. The module is not only limited to fault alarming, but also can alarm a target close to the radar so as to prompt a user to judge whether to slow down/stop.
The communication module in the device is connected with the whole vehicle control module through a communication interface and transmits detected target data to the whole vehicle control module in real time. The whole vehicle control module can also communicate with the radar device through the communication interface. The communication method may be a controller area network (Controller Area Network, CAN) communication method, a network communication method, or the like.
It should be noted that the device has a monitoring function, and self-monitoring, i.e. an automatic fail-safe detection design. The fault can be automatically detected, the fault code is automatically output, and further fault information is obtained. The device is not limited to be used in the tram field, but can also be applied to the rail transit fields such as railways, subways and the like. The working frequency of the device is not limited to 77GHz, and the device can be applied to millimeter wave radars with 24GHz and other frequency bands. The power module of the device supplies power to the display module, the alarm module, the data processing module, the signal processing module and the communication module respectively. The power module can be communicated with the central processing unit, and the output of the power module is further controlled according to the working state of each module, so that the power consumption of the device is reduced. The waveform used by the device is not limited to sawtooth wave, but triangular wave, frequency Shift Keying (FSK), phase Shift Keying (PSK) or a combination of various waveforms can be used.
Claims (6)
1. The utility model provides a vehicle-mounted millimeter wave radar device, includes radio frequency front end module, power module and signal processing module, power module supplies power for radio frequency front end module and signal processing module, a serial communication port, the radio frequency front end module for the transmission millimeter wave signal, the echo signal of receiving target, and carry out preliminary treatment to the echo signal of target, signal processing module includes: a distance and speed acquisition unit for acquiring speed information and distance information of the target according to the preprocessed signals; a position acquisition unit for acquiring position information of the target according to the preprocessed signal; the target detection unit is used for determining whether the target is a curve or a straight road according to the obtained speed information, distance information and position information of the target, filtering fences on two sides of the track, and extracting the target in the fences as an effective target; the target detection unit compares the speed information of the detected target with the speed information of the whole vehicle, judges whether the detected target is a static target, if so, determines whether the current track is a straight track or a curve track through a RANSAC algorithm, and determines the fence position; the RANSAC algorithm processing flow is as follows: any two points are found out to construct a linear equation, all stationary targets are traversed, a threshold value is set, if the number of stationary targets on the found straight line is larger than the threshold value, the track at the moment is determined to be a straight line track, otherwise, the track is a curve track, and a straight line covering the most stationary targets is taken as a fence.
2. The vehicle-mounted millimeter wave radar device according to claim 1, wherein the position acquisition unit is provided with a data correlation unit at the rear, and the data correlation unit solves the problem of speed ambiguity by the principle that the target distance cannot be suddenly changed.
3. The vehicle-mounted millimeter wave radar device according to claim 1, wherein if it is not a stationary target, it is determined whether or not the abscissa value of the target is smaller than a fixed value between 1/2 of the barriers, and if it is, it is an effective target, and otherwise it is an ineffective target.
4. The vehicle-mounted millimeter wave radar device according to claim 1, wherein after determining the current track, the fence position is determined based on a fixed value between fences where the abscissa value of the position information of the target is equal to 1/2, and if the abscissa value of the target is smaller than the fixed value between fences of 1/2, the target is a valid target.
5. The vehicle-mounted millimeter wave radar device according to claim 1, wherein according to the obtained fence, if the target display is located inside the fence, the target is a valid target, and if the target display is located outside the fence, the target is regarded as an invalid target.
6. The object detection method of the vehicle-mounted millimeter wave radar device is characterized by comprising the following steps of:
(1) The radar transmits electromagnetic signals, receives echo signals of the target, and preprocesses the echo signals of the target;
(2) Acquiring speed information, distance information and position information of a target according to the preprocessed signals;
(3) Determining whether the road is a curve or a straight road according to the obtained speed information, distance information and position information of the target, filtering fences on two sides of the track, and extracting the target in the fences as an effective target;
the specific steps of target detection are as follows:
(3.1) comparing the speed information of the detected target in the step (3) with the speed information of the whole vehicle, and judging whether the detected target is a static target or not;
(3.2) if the target is a stationary target, determining whether the current track is a straight track or a curved track through a RANSAC algorithm, and determining a fence position;
after the current track is determined, determining the position of the fence according to a fixed value between fences with the abscissa value equal to 1/2 of the target position information, and if the abscissa value of the target is smaller than the fixed value between the fences with the ratio of 1/2, determining the target as an effective target;
(3.2.1) the RANSAC algorithm processing flow is as follows: any two points are found out to construct a linear equation, all stationary targets are traversed, a threshold value is set, if the number of the stationary targets on the found straight line is larger than the threshold value, the track at the moment is determined to be a straight line track, otherwise, the track is a curve track, and a straight line covering the most stationary targets is taken as a fence;
and (3.3) if the target is not a static target, judging whether the abscissa value of the target is smaller than a fixed value between 1/2 fences, if so, judging that the target is a valid non-static target, and otherwise, judging that the target is an invalid target.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201910355156.4A CN110058239B (en) | 2019-04-29 | 2019-04-29 | Vehicle-mounted millimeter wave radar device and target detection method |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201910355156.4A CN110058239B (en) | 2019-04-29 | 2019-04-29 | Vehicle-mounted millimeter wave radar device and target detection method |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN110058239A CN110058239A (en) | 2019-07-26 |
| CN110058239B true CN110058239B (en) | 2023-08-01 |
Family
ID=67321551
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201910355156.4A Active CN110058239B (en) | 2019-04-29 | 2019-04-29 | Vehicle-mounted millimeter wave radar device and target detection method |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN110058239B (en) |
Families Citing this family (10)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN110988881B (en) * | 2019-10-31 | 2021-12-31 | 惠州市德赛西威智能交通技术研究院有限公司 | Target detection method of vehicle-mounted millimeter wave radar and vehicle-mounted radar system thereof |
| CN112313539B (en) * | 2019-11-26 | 2024-03-15 | 深圳市大疆创新科技有限公司 | Guardrail detection method and equipment, storage medium and movable platform |
| CN111323757B (en) * | 2019-12-30 | 2022-04-05 | 北京海兰信数据科技股份有限公司 | Target detection method and device for marine radar |
| CN111198370B (en) * | 2020-01-02 | 2022-07-08 | 北京百度网讯科技有限公司 | Millimeter wave radar background detection method and device, electronic equipment and storage medium |
| CN111289980B (en) * | 2020-03-06 | 2022-03-08 | 成都纳雷科技有限公司 | Roadside stationary object detection method and system based on vehicle-mounted millimeter wave radar |
| CN112130136B (en) * | 2020-09-11 | 2024-04-12 | 中国重汽集团济南动力有限公司 | Comprehensive perception system and method for traffic targets |
| CN112233416A (en) * | 2020-09-17 | 2021-01-15 | 北京聚利科技有限公司 | Traffic flow detection method and device |
| CN112198503A (en) * | 2020-10-16 | 2021-01-08 | 无锡威孚高科技集团股份有限公司 | Target track prediction optimization method and device and radar system |
| CN112799044A (en) * | 2020-12-30 | 2021-05-14 | 南京市德赛西威汽车电子有限公司 | BSD radar-based simple and efficient railing identification method |
| WO2022183369A1 (en) * | 2021-03-02 | 2022-09-09 | 华为技术有限公司 | Target detection method and apparatus |
Citations (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| JPH07309238A (en) * | 1994-05-17 | 1995-11-28 | Ishikawajima Harima Heavy Ind Co Ltd | Rolling stock having safety confirmation function |
| CN1152958A (en) * | 1994-07-18 | 1997-06-25 | 西门子公司 | Arrangement for detecting objects in a region to be monitored |
| CN103235310A (en) * | 2013-03-26 | 2013-08-07 | 北京理工雷科电子信息技术有限公司 | Vehicular millimeter-wave train collision avoidance radar system |
| CN106458237A (en) * | 2014-05-20 | 2017-02-22 | 株式会社日立国际电气 | Wireless communication system, wireless communication device, wireless communication method, movable fence control system, communication device, and movable fence device |
| CN107064952A (en) * | 2017-04-21 | 2017-08-18 | 中国科学院半导体研究所 | Railway track barrier monitors the device of identification automatically |
| CN109164443A (en) * | 2018-08-27 | 2019-01-08 | 南京微达电子科技有限公司 | Rail track foreign matter detecting method and system based on radar and image analysis |
| CN109684921A (en) * | 2018-11-20 | 2019-04-26 | 吉林大学 | A kind of road edge identification and tracking based on three-dimensional laser radar |
-
2019
- 2019-04-29 CN CN201910355156.4A patent/CN110058239B/en active Active
Patent Citations (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| JPH07309238A (en) * | 1994-05-17 | 1995-11-28 | Ishikawajima Harima Heavy Ind Co Ltd | Rolling stock having safety confirmation function |
| CN1152958A (en) * | 1994-07-18 | 1997-06-25 | 西门子公司 | Arrangement for detecting objects in a region to be monitored |
| CN103235310A (en) * | 2013-03-26 | 2013-08-07 | 北京理工雷科电子信息技术有限公司 | Vehicular millimeter-wave train collision avoidance radar system |
| CN106458237A (en) * | 2014-05-20 | 2017-02-22 | 株式会社日立国际电气 | Wireless communication system, wireless communication device, wireless communication method, movable fence control system, communication device, and movable fence device |
| CN107064952A (en) * | 2017-04-21 | 2017-08-18 | 中国科学院半导体研究所 | Railway track barrier monitors the device of identification automatically |
| CN109164443A (en) * | 2018-08-27 | 2019-01-08 | 南京微达电子科技有限公司 | Rail track foreign matter detecting method and system based on radar and image analysis |
| CN109684921A (en) * | 2018-11-20 | 2019-04-26 | 吉林大学 | A kind of road edge identification and tracking based on three-dimensional laser radar |
Non-Patent Citations (5)
| Title |
|---|
| FUNDAMENTAL EXPERIMENT FOR UTILIZING LIDAR SENSOR FOR RAILWAY;NORIYUKI SHINODA 等;《Environmental Science》;20181115;319-329 * |
| 城轨列车非接触式障碍物检测系统的研究;曲越;《中国优秀硕士学位论文全文数据库 工程科技Ⅱ辑》;20170615;C033-184 * |
| 基于毫米波雷达与机器视觉信息融合的有轨电车障碍物检测;翟光耀;《中国优秀硕士学位论文全文数据库 工程科技Ⅱ辑》;20190115;第2.1、2.2、5.1、5.2节 * |
| 基于深度数据的车辆目标检测与跟踪方法;陆德彪 等;《交通运输系统工程与信息》;20180630;第18卷(第3期);55-62 * |
| 机载 LiDAR铁路测绘关键技术及应用;武永斌 等;《测绘通报》;20150930;第三节 * |
Also Published As
| Publication number | Publication date |
|---|---|
| CN110058239A (en) | 2019-07-26 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN110058239B (en) | Vehicle-mounted millimeter wave radar device and target detection method | |
| EP1681583B1 (en) | Vehicle radar process | |
| CN110531336A (en) | A kind of object detection recognition methods and system | |
| US10585188B2 (en) | Broadside detection system and techniques for use in a vehicular radar | |
| CN109814080B (en) | Millimeter wave radar target tracking and confidence coefficient algorithm and device thereof | |
| CN115575922B (en) | Moving target detection method and device based on vehicle-mounted FMCW millimeter wave radar | |
| US9812008B2 (en) | Vehicle detection and tracking based on wheels using radar and vision | |
| CN112526521B (en) | Multi-target tracking method for automobile millimeter wave anti-collision radar | |
| CN110832340A (en) | System for detecting moving objects | |
| CN111615641B (en) | Method and apparatus for detecting critical lateral movement | |
| CN111798700B (en) | Blind area monitoring alarm method and device | |
| Sun et al. | Automatic radar-based gesture detection and classification via a region-based deep convolutional neural network | |
| CN110161505A (en) | One kind being based on millimetre-wave radar rear anti-crash method for early warning | |
| EP4343369A2 (en) | Interference signal detection method and apparatus, and integrated circuit, radio device and terminal | |
| CN104977566B (en) | Signal processing method and device for a frequency modulated continuous wave radar sensing system | |
| JP2787014B2 (en) | Vehicle obstacle identification system | |
| CN116660847A (en) | Interference signal detection method and device | |
| CN112098969B (en) | Target detection and early warning optimization method for millimeter wave large vehicle blind area radar | |
| Kruse et al. | Target classification based on near-distance radar sensors | |
| CN110691985B (en) | System for enhanced object tracking | |
| CN114814778B (en) | Carrier speed calculation method based on millimeter wave radar | |
| US20240235590A9 (en) | Signal processing method, storage medium, integrated circuit, device and terminal | |
| US20240137055A1 (en) | Signal processing method, storage medium, integrated circuit, device and terminal | |
| CN115148018B (en) | Traffic event detection device and method | |
| JP7115402B2 (en) | radar equipment |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |