CN110648542A - High-precision vehicle flow detection system based on azimuth recognition narrow-wave radar - Google Patents
High-precision vehicle flow detection system based on azimuth recognition narrow-wave radar Download PDFInfo
- Publication number
- CN110648542A CN110648542A CN201911086945.9A CN201911086945A CN110648542A CN 110648542 A CN110648542 A CN 110648542A CN 201911086945 A CN201911086945 A CN 201911086945A CN 110648542 A CN110648542 A CN 110648542A
- Authority
- CN
- China
- Prior art keywords
- vehicle
- radar
- target
- lane
- 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.)
- Granted
Links
Images
Classifications
-
- G—PHYSICS
- G08—SIGNALLING
- G08G—TRAFFIC CONTROL SYSTEMS
- G08G1/00—Traffic control systems for road vehicles
- G08G1/01—Detecting movement of traffic to be counted or controlled
- G08G1/017—Detecting movement of traffic to be counted or controlled identifying vehicles
-
- G—PHYSICS
- G08—SIGNALLING
- G08G—TRAFFIC CONTROL SYSTEMS
- G08G1/00—Traffic control systems for road vehicles
- G08G1/01—Detecting movement of traffic to be counted or controlled
- G08G1/052—Detecting movement of traffic to be counted or controlled with provision for determining speed or overspeed
-
- G—PHYSICS
- G08—SIGNALLING
- G08G—TRAFFIC CONTROL SYSTEMS
- G08G1/00—Traffic control systems for road vehicles
- G08G1/065—Traffic control systems for road vehicles by counting the vehicles in a section of the road or in a parking area, i.e. comparing incoming count with outgoing count
Landscapes
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Radar Systems Or Details Thereof (AREA)
Abstract
The invention provides a high-precision traffic flow detection system based on an azimuth recognition narrow-wave radar, which comprises: the azimuth recognition narrow-wave radar is used for transmitting a horizontal 3dB main lobe beam width of an antenna to be not more than 6 degrees, multi-channel receiving is used for azimuth judgment, and a rapid continuous wave frequency modulation system is adopted to realize accurate judgment of the distance, the speed and the vehicle type of a target vehicle; and the duplication-elimination decision information processor is used for judging and integrating vehicles running on the pressed line according to the real-time positions of the vehicles output by the radars of the first lane and the second lane, the information such as vehicle type identification, motion trail of a detection target, motion equation, vehicle type, speed and the like when the vehicles run on the pressed line, so that repeated statistics of the traffic flow is avoided. The invention adopts a narrow-wave radar based on novel direction recognition and a deduplication decision processing mechanism to realize high-precision traffic flow statistics of various road scenes, and the accuracy rate is more than 99.5%.
Description
Technical Field
The invention relates to the technical field of traffic flow detection, in particular to a high-precision traffic flow detection system based on an azimuth recognition narrow-wave radar.
Background
The high-precision traffic flow detection system (hereinafter referred to as the high-precision traffic flow detection system) based on the millimeter wave radar technology can be widely applied to the requirements of accurate speed measurement and accurate traffic flow statistics of high-speed and urban roads.
In the prior art, most of traffic flow statistical systems adopt video detection, coil detection and flow radar detection technologies. Visual detection is susceptible to light environment and rain and fog. The coil detection is not high in long-term working reliability under the scene that the traffic rate of the heavy truck is high. The traditional vehicle flow detection radar has the defects that no matter the radar is provided with multiple lanes in the front or the side, the accuracy is difficult to reach 99.5 percent due to the fact that a large vehicle is blocked in the lane and the classification of the vehicle type is inaccurate.
Disclosure of Invention
The invention provides a high-precision traffic flow detection system based on an azimuth identification narrow-wave radar, which aims to solve at least one technical problem.
To solve the above problems, as an aspect of the present invention, there is provided a high-precision traffic flow detection system based on an azimuth recognition narrow-wave radar, including: the azimuth recognition narrow-wave radar is used for transmitting a horizontal 3dB main lobe beam width of an antenna to be not more than 6 degrees, multi-channel receiving is used for azimuth judgment, and a rapid continuous wave frequency modulation system is adopted to realize accurate judgment of the distance, the speed and the vehicle type of a target vehicle; and the duplication-elimination decision information processor is used for judging and integrating vehicles running on the pressed line according to the real-time positions of the vehicles output by the radars of the first lane and the second lane, the information such as vehicle type identification, motion trail of a detection target, motion equation, vehicle type, speed and the like when the vehicles run on the pressed line, so that repeated statistics of the traffic flow is avoided.
Preferably, in order to realize good discrimination and detection of multiple targets, the accurate discrimination of the distance, the speed and the vehicle type of the target vehicle by using the fast continuous wave frequency modulation system comprises: adopting a two-dimensional FFT processing technology to distinguish the targets in a two-dimensional mode from a distance dimension and a velocity dimension; the detection probability of the radar is improved by adopting a constant false alarm detection technology on the premise of keeping a lower false alarm rate; the method has the advantages that higher angle resolution is obtained in the angle dimension through a DBF technology and a phase comparison angle measurement principle, so that the positioning accuracy and the distinguishing capability of multiple targets are improved; performing target similarity correlation on position, speed and acceleration by adopting a fuzzy mathematic method; a Kalman filter is adopted to realize the estimation of the value of a random signal of observation data with noise, the estimation is used for processing radar data, and position information can be extracted from a detected target to form trace data.
Preferably, the method for distinguishing the vehicle type is based on radar scattering points of a target vehicle, and vehicle contour information including vehicle height, length and width is reconstructed by inversion.
Preferably, the inversely reconstructing vehicle profile information based on the radar scattering points of the target vehicle comprises: extracting distance, speed and angular speed information of the characteristic points by integrating and processing radar echo data; establishing a characteristic point motion equation based on the three groups of data, combining a tracking filtering algorithm to perform adaptive adjustment, and simultaneously applying the three groups of data to fuzzy recognition of a vehicle scattering model and performing dynamic adjustment; and finally, combining the two methods to dynamically match the vehicle type scattering information with the characteristic points, and outputting the length, width and height of the vehicle.
Preferably, the data processing flow of the deduplication resolution information processing machine is as follows: when a vehicle runs on a pressed line and the first radar and the second radar stably track at the same time, defining a vehicle detected by the first radar in a first lane as a first target and a vehicle detected by the second radar in a second lane as a second target; according to the vehicle information that orientation discernment narrow wave radar gathered carries out information fusion, include: sequentially comparing the transverse distance and the longitudinal distance of the two targets, further comparing the vehicle length and the vehicle height when the difference value of the two targets is smaller than a set value, judging to be repeated statistics if the parameters are smaller than the set value, and judging to be independent statistics if any one of the parameters is larger than the set value; and after repeated statistics is judged, respectively calculating Euclidean distances of the target vehicle relative to the centers of the first lane and the second lane, and judging the lane to which the target vehicle belongs.
The high-precision traffic flow detection system based on the novel direction recognition narrow-wave millimeter wave radar realizes high-precision traffic flow statistics of various road scenes by adopting the novel direction recognition narrow-wave radar and a deduplication resolution processing mechanism, and the accuracy is more than 99.5%.
Drawings
Fig. 1 schematically shows a vehicle contour information extraction flowchart;
FIG. 2 schematically illustrates a vehicle lane line travel;
fig. 3 schematically shows a data processing flow diagram of a deduplication resolution information handler.
Detailed Description
The embodiments of the invention will be described in detail below with reference to the drawings, but the invention can be implemented in many different ways as defined and covered by the claims.
Taking a typical two-lane application scene as an example, the invention mainly comprises two novel direction recognition narrow-wave radars and a repeat-resolution information processor.
Narrow-wave radar capable of recognizing type and direction
The horizontal 3dB main lobe beam width of the novel azimuth identification narrow-wave radar transmitting antenna is not more than 6 degrees, and multi-channel receiving is used for azimuth judgment. And a rapid continuous wave frequency modulation system is adopted to realize accurate judgment of the distance, the speed and the vehicle type of the target vehicle.
The method for realizing the distance and the speed of the target vehicle by using the rapid continuous wave frequency modulation system is a common processing mode in the prior art. The radar has three main tasks, namely distance estimation, phase velocity estimation and direction estimation, in order to realize good distinguishing and detection of multiple targets, a two-dimensional FFT processing technology is adopted, targets are distinguished from a distance dimension, a velocity dimension and a two-dimensional dimension, a constant false alarm detection technology is adopted, and the detection probability of the radar is improved on the premise of keeping a low false alarm rate. And a higher angle resolution is obtained in the angle dimension through a DBF technology and a phase comparison angle measurement principle, so that the positioning precision and the distinguishing capability of multiple targets are improved. And performing target similarity correlation on position, speed and acceleration by adopting a fuzzy mathematical method. A Kalman filter is adopted to realize the estimation of the value of a random signal of observation data with noise, the estimation is used for processing radar data, and position information can be extracted from a detected target to form trace data.
The method for judging the vehicle type is based on the radar echo scattering point of a target vehicle, vehicle contour information including the height, the length and the width of the vehicle is inverted and reconstructed, and the specific method is as follows:
and extracting the distance, speed and angular speed information of the characteristic points by integrating and processing the radar echo data. Establishing a characteristic point motion equation based on the three groups of data, and then combining a tracking filtering algorithm to carry out adaptability adjustment; and simultaneously, applying the three groups of data to fuzzy recognition of a vehicle scattering model and carrying out dynamic adjustment. And finally, combining the two methods to dynamically match the vehicle type scattering information with the characteristic points, and outputting the length, width and height of the vehicle.
Second, duplicate removal decision information processor
And the de-duplication decision information processor is used for outputting the real-time position of the vehicle and identifying the vehicle type to the de-duplication decision processor respectively by the radars of the first lane and the second lane when the vehicle is pressed to run. The duplication elimination decision processor judges and integrates the vehicles running through pressing lines according to the information of the motion tracks, the motion equation, the vehicle types, the speed and the like of the two radar detection targets, and avoids repeated statistics of the traffic flow.
When a vehicle runs on the line, and the first radar and the second radar stably track at the same time, the vehicle detected by the first radar in the first lane is defined as a first target, and the vehicle detected by the second radar in the second lane is defined as a second target. According to the method, vehicle information collected by a direction identification narrow-wave radar is subjected to information fusion, the transverse distance and the longitudinal distance of two targets are sequentially compared, when the difference value of the two is smaller than a set value, the vehicle length and the vehicle height are further compared, if the parameters are smaller than the set value, repeated statistics can be judged, and if any one of the parameters is larger than the set value, independent statistics can be judged. After being judged as a repeated statistic, according toAnd respectively calculating Euclidean distances of the target vehicle relative to the centers of the first lane and the second lane, and judging the lane to which the target vehicle belongs.
The high-precision traffic flow detection system based on the novel direction recognition narrow-wave millimeter wave radar realizes high-precision traffic flow statistics of various road scenes by adopting the novel direction recognition narrow-wave radar and a deduplication resolution processing mechanism, and the accuracy is more than 99.5%.
The above description is only a preferred embodiment of the present invention and is not intended to limit the present invention, and various modifications and changes may be made by those skilled in the art. Any modification, equivalent replacement, or improvement made within the spirit and principle of the present invention should be included in the protection scope of the present invention.
Claims (5)
1. A high accuracy vehicle flow detecting system based on orientation discernment narrow wave radar, its characterized in that includes:
the method comprises the following steps that a square recognition narrow-wave radar is used for enabling the horizontal 3dB main lobe beam width of a transmitting antenna to be not more than 6 degrees, multi-channel receiving is used for direction judgment, and a fast continuous wave frequency modulation system is adopted to accurately judge the distance, the speed and the vehicle type of a target vehicle;
and the repeated interruption removing information processor is used for judging and integrating vehicles running on the pressed line according to the real-time positions of the vehicles output by the radars of the first lane and the second lane, the information such as vehicle type identification, motion trail of a detection target, motion equation, vehicle type, speed and the like when the vehicles run on the pressed line, so that repeated statistics of the traffic flow is avoided.
2. The system of claim 1, wherein in order to achieve good discrimination and detection of multiple targets, the accurate discrimination of the distance, speed and vehicle type of the target vehicle by using the fast continuous wave frequency modulation system comprises:
adopting a two-dimensional FFT processing technology to distinguish the targets in a two-dimensional mode from a distance dimension and a velocity dimension;
the detection probability of the radar is improved by adopting a constant false alarm detection technology on the premise of keeping a lower false alarm rate;
the method has the advantages that higher angle resolution is obtained in the angle dimension through a DBF technology and a phase comparison angle measurement principle, so that the positioning accuracy and the distinguishing capability of multiple targets are improved;
performing target similarity correlation on position, speed and acceleration by adopting a fuzzy mathematic method;
a Kalman filter is adopted to realize the estimation of the value of a random signal of observation data with noise, the estimation is used for processing radar data, and position information can be extracted from a detected target to form trace data.
3. The system of claim 1, wherein the method for identifying the vehicle type is based on radar scattering points of a target vehicle, and vehicle contour information including vehicle height, length and width is inversely reconstructed.
4. The system of claim 3, wherein the inversely reconstructing vehicle profile information based on target vehicle radar echo scattering points comprises:
extracting distance, speed and angular speed information of the characteristic points by integrating and processing radar echo data;
establishing a characteristic point motion equation based on the three groups of data, combining a tracking filtering algorithm to perform adaptive adjustment, and simultaneously applying the three groups of data to fuzzy recognition of a vehicle scattering model and performing dynamic adjustment;
and finally, combining the two methods to dynamically match the vehicle type scattering information with the characteristic points, and outputting the length, width and height of the vehicle.
5. The system of claim 1, wherein the data processing flow of the deduplication resolution information processor is as follows:
when a vehicle runs on a pressed line and the first radar and the second radar stably track at the same time, defining a vehicle detected by the first radar in a first lane as a first target and a vehicle detected by the second radar in a second lane as a second target;
according to the vehicle information that orientation discernment narrow wave radar gathered carries out information fusion, include: sequentially comparing the transverse distance and the longitudinal distance of the two targets, further comparing the vehicle length and the vehicle height when the difference value of the two targets is smaller than a set value, judging to be repeated statistics if the parameters are smaller than the set value, and judging to be independent statistics if any one of the parameters is larger than the set value;
and after repeated statistics is judged, respectively calculating Euclidean distances of the target vehicle relative to the centers of the first lane and the second lane, and judging the lane to which the target vehicle belongs.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201911086945.9A CN110648542B (en) | 2019-11-08 | 2019-11-08 | High-precision vehicle flow detection system based on azimuth recognition narrow-wave radar |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201911086945.9A CN110648542B (en) | 2019-11-08 | 2019-11-08 | High-precision vehicle flow detection system based on azimuth recognition narrow-wave radar |
Publications (2)
Publication Number | Publication Date |
---|---|
CN110648542A true CN110648542A (en) | 2020-01-03 |
CN110648542B CN110648542B (en) | 2021-09-21 |
Family
ID=69014297
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN201911086945.9A Active CN110648542B (en) | 2019-11-08 | 2019-11-08 | High-precision vehicle flow detection system based on azimuth recognition narrow-wave radar |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN110648542B (en) |
Cited By (2)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN112991774A (en) * | 2021-02-02 | 2021-06-18 | 深圳市天鼎微波科技有限公司 | Traffic flow detection method and device based on millimeter waves |
CN114495520A (en) * | 2021-12-30 | 2022-05-13 | 北京万集科技股份有限公司 | Vehicle counting method, device, terminal and storage medium |
Citations (8)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
GB871641A (en) * | 1958-10-29 | 1961-06-28 | Gen Motors Corp | Improved motor road vehicle control system |
CN102402861A (en) * | 2011-11-25 | 2012-04-04 | 金庆江 | Vehicle distinguishing and controlling system |
CN102810250A (en) * | 2012-07-31 | 2012-12-05 | 长安大学 | Video based multi-vehicle traffic information detection method |
CN105987263A (en) * | 2015-01-28 | 2016-10-05 | 邹谋炎 | Inclined horizontal irradiation method and support design for road monitoring radar |
CN108492586A (en) * | 2018-05-22 | 2018-09-04 | 南京城建隧桥经营管理有限责任公司 | One kind is based on distributed road interval monitoring system and its speed-measuring method |
CN109410578A (en) * | 2018-11-09 | 2019-03-01 | 浙江浩腾电子科技股份有限公司 | A kind of traffic intersection section traffic flow detecting method based on computer vision |
CN109557530A (en) * | 2017-09-25 | 2019-04-02 | 北京华同微波科技有限公司 | A kind of narrow beam, long covering fmcw radar |
CN110084906A (en) * | 2018-01-25 | 2019-08-02 | 深圳市以捷智慧交通科技有限公司 | A kind of urban road pavement branch sections charging system and method based on traffic congestion degree |
-
2019
- 2019-11-08 CN CN201911086945.9A patent/CN110648542B/en active Active
Patent Citations (8)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
GB871641A (en) * | 1958-10-29 | 1961-06-28 | Gen Motors Corp | Improved motor road vehicle control system |
CN102402861A (en) * | 2011-11-25 | 2012-04-04 | 金庆江 | Vehicle distinguishing and controlling system |
CN102810250A (en) * | 2012-07-31 | 2012-12-05 | 长安大学 | Video based multi-vehicle traffic information detection method |
CN105987263A (en) * | 2015-01-28 | 2016-10-05 | 邹谋炎 | Inclined horizontal irradiation method and support design for road monitoring radar |
CN109557530A (en) * | 2017-09-25 | 2019-04-02 | 北京华同微波科技有限公司 | A kind of narrow beam, long covering fmcw radar |
CN110084906A (en) * | 2018-01-25 | 2019-08-02 | 深圳市以捷智慧交通科技有限公司 | A kind of urban road pavement branch sections charging system and method based on traffic congestion degree |
CN108492586A (en) * | 2018-05-22 | 2018-09-04 | 南京城建隧桥经营管理有限责任公司 | One kind is based on distributed road interval monitoring system and its speed-measuring method |
CN109410578A (en) * | 2018-11-09 | 2019-03-01 | 浙江浩腾电子科技股份有限公司 | A kind of traffic intersection section traffic flow detecting method based on computer vision |
Non-Patent Citations (2)
Title |
---|
YIGUANG XUAN 等: "A High-Range-Resolution Microwave Radar System for Traffic Flow Rate Measurement", 《IEEE CONFERENCE ON INTELLIGENT TRANSPORTATION SYSTEMS》 * |
任军利 等: "采用深度卷积神经网络技术的汽车群体属性分析研究", 《湘潭大学自然科学学报》 * |
Cited By (3)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN112991774A (en) * | 2021-02-02 | 2021-06-18 | 深圳市天鼎微波科技有限公司 | Traffic flow detection method and device based on millimeter waves |
CN114495520A (en) * | 2021-12-30 | 2022-05-13 | 北京万集科技股份有限公司 | Vehicle counting method, device, terminal and storage medium |
CN114495520B (en) * | 2021-12-30 | 2023-10-03 | 北京万集科技股份有限公司 | Counting method and device for vehicles, terminal and storage medium |
Also Published As
Publication number | Publication date |
---|---|
CN110648542B (en) | 2021-09-21 |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
US10605896B2 (en) | Radar-installation-angle calculating device, radar apparatus, and radar-installation-angle calculating method | |
CN106991389B (en) | Device and method for determining road edge | |
CN103064086B (en) | Vehicle tracking method based on depth information | |
CN111045008B (en) | Vehicle millimeter wave radar target identification method based on widening calculation | |
CN113419244A (en) | Vehicle track splicing method based on millimeter wave radar data | |
CN104183127A (en) | Traffic surveillance video detection method and device | |
CN107942329B (en) | Method for detecting sea surface ship target by maneuvering platform single-channel SAR | |
CN112085950B (en) | Method and system for estimating traffic state discrimination index, storage medium and application | |
CN110648542B (en) | High-precision vehicle flow detection system based on azimuth recognition narrow-wave radar | |
CN103425764A (en) | Vehicle matching method based on videos | |
CN109541601A (en) | Differentiating obstacle and its detection method based on millimeter wave | |
CN112731296A (en) | Automobile millimeter wave radar point trace condensation method and system | |
WO2019091448A1 (en) | Method and device for tracking movable target | |
CN114814823A (en) | Rail vehicle detection system and method based on integration of millimeter wave radar and camera | |
CN114415171A (en) | Automobile travelable area detection method based on 4D millimeter wave radar | |
CN115236603A (en) | Method for processing abnormal track measured by millimeter wave radar based on space-time relation in tunnel | |
CN113740874A (en) | Road edge detection method, electronic equipment and vehicle | |
CN108693517B (en) | Vehicle positioning method and device and radar | |
CN113537417A (en) | Target identification method and device based on radar, electronic equipment and storage medium | |
CN115079121B (en) | Multipath target identification method and device for vehicle-mounted radar and storage medium | |
Wittmann et al. | Improving lidar data evaluation for object detection and tracking using a priori knowledge and sensorfusion | |
CN115932831A (en) | Target segment tracking method, device, equipment and storage medium based on radar | |
CN114495483A (en) | Millimeter wave radar-based vehicle abnormal driving behavior identification method | |
CN115629385A (en) | Vehicle queuing length real-time detection method based on correlation of millimeter wave radar and camera | |
Spraul et al. | Persistent multiple hypothesis tracking for wide area motion imagery |
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 | ||
CP03 | Change of name, title or address | ||
CP03 | Change of name, title or address |
Address after: Room 704, building F, qihangkechuang R & D Industrial Park, 1008 Songbai Road, sunshine community, Xili street, Shenzhen, Guangdong 518000 Patentee after: Habo intelligent (Shenzhen) Co.,Ltd. Address before: 518000 803-a8111, building 10, Shenzhen Bay science and technology ecological park, No. 10, Gaoxin South ninth Road, high tech Zone community, Yuehai street, Nanshan District, Shenzhen, Guangdong Patentee before: SHENZHEN HITSYS INFORMATION TECHNOLOGY Co.,Ltd. |