CN113903179B - Using method of multi-beam laser radar background filtering device based on point cloud density superposition distribution - Google Patents
Using method of multi-beam laser radar background filtering device based on point cloud density superposition distribution Download PDFInfo
- Publication number
- CN113903179B CN113903179B CN202111162738.4A CN202111162738A CN113903179B CN 113903179 B CN113903179 B CN 113903179B CN 202111162738 A CN202111162738 A CN 202111162738A CN 113903179 B CN113903179 B CN 113903179B
- Authority
- CN
- China
- Prior art keywords
- background
- cubes
- laser radar
- cube
- matrix
- 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
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
- G08G1/04—Detecting movement of traffic to be counted or controlled using optical or ultrasonic detectors
-
- 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
- G01S17/00—Systems using the reflection or reradiation of electromagnetic waves other than radio waves, e.g. lidar systems
- G01S17/88—Lidar systems specially adapted for specific applications
- G01S17/89—Lidar systems specially adapted for specific applications for mapping or imaging
-
- 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
- G08G1/0104—Measuring and analyzing of parameters relative to traffic conditions
- G08G1/0125—Traffic data processing
-
- 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
Abstract
The invention relates to a using method of a multi-beam laser radar background filtering device based on point cloud density overlapping distribution, and belongs to the technical field of road traffic monitoring. Firstly, aggregating a period of data frames based on a laser radar point coordinate, then establishing a three-dimensional matrix to represent the whole space, wherein the matrix elements are cubes, recording the density of aggregation points in the cubes, determining a point density threshold value of the cubes, the cubes higher than the threshold value are background cubes, the cubes lower than the threshold value are non-background cubes, after the background cubes with the determined threshold values are identified, the background cubes are stored in the three-dimensional matrix, the three-dimensional matrix is used as the background matrix, the background matrix is combined with real-time data, points collected in the real-time data can be found in the background matrix and are eliminated, the points cannot be found in the background matrix and are reserved, and background filtering is achieved.
Description
Technical Field
The invention relates to a using method of a multi-beam laser radar background filtering device based on point cloud density overlapping distribution, and belongs to the technical field of road traffic monitoring.
Background
The car networking technology can connect all road users, sharing real-time position, speed and direction, thereby helping to avoid accidents, save time and cost, and reduce fuel consumption and pollutant emissions. However, road users installing car networking devices are limited, and users who are not networked and users who are networked exist for a long time. Under the mixed traffic condition that non-networked users and networked users coexist, the vehicle networking technology can only obtain part of vehicle motion information, and a new method is needed to collect high-resolution micro-flow data for filling up data vacancy caused by mixed traffic flow.
In recent years, advanced autonomous cars have begun to employ lidar sensors to detect road boundaries and lane markings. The vehicle-mounted system acquires the necessary data through the point cloud output of the lidar sensor to determine the potential obstacles present in the environment and the relationship of the vehicle to those potential obstacles. The laser radar is used as an important sensor of the car networking technology, can perform 360-degree high-precision scanning on surrounding target objects, simultaneously tracks and reports the accurate position and speed of each target object in the scanning range of the laser radar, and can provide an effective solution for filling data vacancy caused by mixed traffic flow by being installed on the road side.
In order to obtain high-resolution microscopic flow data of all road users, background filtering is a preprocessing step and is also a basis for improving data accuracy and calculation efficiency. Background filtering refers to the elimination of all objects except for road objects. The so-called background includes static objects such as trees, buildings and traffic facilities, and also dynamic objects such as swaying branches and noise points. In past research, background filtering for different data types has developed many approaches. For example, an algorithm that extracts a background image from a traffic video stream using pixel information for each frame analyzes the color value of each pixel in a series of frames and then uses the pattern of the sequence as the correct color value for the background image. In addition, there is a method of calculating a difference between a background and a non-background using a median value of each color channel. The results show that these methods are well suited for freeways under free-flow to medium congestion conditions. However, these vision-based data processing algorithms cannot be used directly for lidar data because roadside lidar data is a series of points, rather than raster pixel information. Therefore, currently existing background filtering methods cannot directly extract data from roadside lidar.
Disclosure of Invention
Aiming at the defects of the prior art, the invention provides a using method of a multi-beam laser radar background filtering device based on point cloud density overlapping distribution, which is applied to different driving environments such as roads, bridges and tunnels, and high-resolution micro flow data is obtained by processing the scanned laser radar through a background filtering method.
Interpretation of terms:
polymerization: the aggregation of the invention refers to analyzing and integrating collected point cloud data frames, and forming a plurality of data frames into a single data frame for transmission, thereby increasing transmission content and improving efficiency for subsequent background recognition.
The technical scheme of the invention is as follows:
the utility model provides a multi-thread bundle laser radar background filtering device's application method based on point cloud density stack distribution, the device includes laser radar and control terminal, and laser radar is connected to control terminal, carries out data acquisition through laser radar scanning, handles the data that laser radar gathered through control terminal, and the use step is as follows:
(1) when the device is applied to the middle section of a road and a bridge, a supporting rod is erected firstly, and a laser radar is arranged on the supporting rod and connected with a control terminal;
(2) scanning by a laser radar at 360 degrees to acquire point cloud data, and collecting original data in a period of time as initial input;
(3) aggregating a period of time data frames based on the laser radar point coordinates; the greater the number of frames, the higher the accuracy, increasing the time cost and having higher requirements on the computer.
(4) Cutting the three-dimensional space into continuous cubes:
establishing a three-dimensional matrix to represent the whole space (the whole space refers to a data space obtained after aggregation of data acquired by a laser radar), wherein the matrix element is a cube, and recording the number of aggregation points (the aggregation points are focused 3D points and comprise background points and non-background points) in the cube;
(5) determining a point density threshold of each cube according to the density of the aggregation points in each cube to distinguish a background cube from a non-background cube, wherein the density is the ratio of the number of the aggregation points in each cube to the volume of the cube, the cube higher than the threshold is the background cube, and the cube lower than the threshold is the non-background cube; the density of points scanned by the lidar on the same object varies with the distance from the lidar, generally, if the distance between the target and the lidar sensor increases, the number of points decreases, wherein, as the distance between the vehicle and the lidar sensor increases, the range and the number of points follow a power function relationship, so when the distance between the background object and the lidar sensor is different, the background point density is also different, which means that the threshold value should be different in different detection ranges, and generally, the density of the background space is higher than the spatial density of the moving vehicle or pedestrian;
(6) after the background cube with the determined threshold value is identified, the background cube is stored in a three-dimensional matrix, the three-dimensional matrix is used as the background matrix, the background matrix is combined with real-time data, points acquired from the real-time data can be eliminated if the points can be found in the background matrix, the points can be reserved if the points cannot be found in the background matrix, and background filtering is achieved.
Preferably, moving vehicles and pedestrians create a low density cube. In the background frame, the number of cubes of different densities is uniform, while the low-density cube number variations of pedestrians and vehicles are uniform. Therefore, the point density threshold of the cube is determined by the following equation
N i The number of the aggregation points of the ith cube is increased, and the numbering sequence of the cubes is increased from a point number which is less to a point number which is more;
F i is N i Frequency, frequency refers to the number of cubes with the same number of points;
slope is the Slope between the collection point and the collection point;
when slope is 0 or positive, the frequency F of the point number of each cube in the formula is used as a threshold value; the slope is meaningless when being a negative value, and a threshold value is selected from the slope which becomes 0 or a positive value;
cubes above the threshold are background cubes and those below the threshold are non-background cubes.
Preferably, in the step (1), the height of the supporting rod is 4-6m, the requirement of a scanning range is met, artificial touch is avoided, the electric box is arranged at a position, 0.5m away from the top end, of the supporting rod, the electric box is connected to the supporting rod through a screw nut and a hoop support, a control terminal is arranged in the electric box, the control terminal is protected from weather damage through the electric box, and the electric box is provided with a switch door and facilitates installation, disassembly and maintenance of built-in equipment.
Preferably, in the step (1), when signal lamps exist on the middle section of the road and the bridge, the signal lamp post is used as the support rod.
Preferably, in step (1), when being applied to in the tunnel, install the dead lever in vault department, dead lever one side sets up lidar, and the electrical cabinet is fixed to be set up at same cross section tunnel lateral wall, is provided with control terminal in the electrical cabinet, lidar connection control terminal.
Preferably, in the step (3), the aggregation frame number of the 16-beam lidar is 1500-3000, and the aggregation frame number of the 32-beam or 64-beam lidar can be reduced according to specific situations to ensure real-time processing efficiency, and the aggregation frame number is set to 2000 in a peak period to ensure real-time data analysis.
Preferably, in step (4), the cube has a side length of 0.1 m. The key parameter for cube partitioning is the side length of the cube, which affects the number of rows and columns of the three-dimensional matrix. A shorter side length increases the time cost and when the dynamic background point movement distance is large, the divided cube is crossed, so that the dynamic point cannot be captured well, and a longer side length may reduce the precision.
The invention has the beneficial effects that:
1. the laser radar recognition device used by the invention realizes the comprehensive coverage of the bidirectional traffic flow of the route.
2. The installation position of the invention is the road center line, which does not influence the running of the motor vehicle and ensures the traffic safety.
3. The algorithm used by the invention can improve the recognition precision of the vehicle and the pedestrian and obviously reduce the time cost of data processing.
4. The algorithm used by the invention can automatically learn the density threshold of the cube point. Only two parameters, the number of frames aggregated and the side length of the multi-dimensional dataset, are needed to give the recommended values.
5. The algorithm used by the invention has small calculation amount and can be used for real-time data processing such as vehicle monitoring, pedestrian tracking and the like.
Drawings
FIG. 1 is a schematic view of the structure of the present invention on a road section without street lamps and a bridge in a road center line;
FIG. 2 is a schematic view of the structure of the present invention on a road segment with street lamps in the road;
FIG. 3 is a schematic diagram of the structure of the road with signal lights on the road;
FIG. 4 is a schematic diagram of the structure of the present invention in a tunnel;
FIG. 5 is a schematic view of the working state of the present invention;
FIG. 6 is a schematic flow chart of the present invention;
wherein: 1. a laser radar; 2. a support bar; 3. an electric box; 4. a data connection line; 5. a control terminal; 6. a light pole; 7. a street lamp; 8. a signal light pole; 9. a signal lamp; 10. a signal lamp bracket; 11. a dome; 12. fixing the rod; 13. laser; 14. a road surface.
Detailed Description
The present invention will be further described by way of examples, but not limited thereto, with reference to the accompanying drawings.
Example 1
As shown in fig. 1, this embodiment provides a method for using a multi-line beam laser radar background filtering device based on point cloud density overlapping distribution, and the device includes a laser radar 1 and a control terminal 5, the laser radar is connected to the control terminal, and data acquisition is performed through laser radar scanning, and a vehicle within a 100m range can be effectively detected, and the data acquired by the laser radar is processed through the control terminal, and the using steps are as follows:
(1) when the device is applied to the middle section of a road and a bridge, a supporting rod 2 is erected firstly, a laser radar 1 is arranged on the supporting rod 2, and the laser radar 1 is connected with a control terminal 5;
(2) scanning by a laser radar at 360 degrees to acquire point cloud data, and collecting original data in a period of time as initial input;
(3) aggregating a period of time data frames based on the laser radar point coordinates; the greater the number of frames, the higher the accuracy, increasing the time cost and having higher requirements on the computer.
(4) Cutting the three-dimensional space into successive cubes:
establishing a three-dimensional matrix to represent the whole space (the whole space refers to a data space obtained by aggregating data acquired by a laser radar), wherein the matrix element is a cube, and recording the number of aggregation points (the aggregation points are focused 3D points and comprise background points and non-background points) in the cube;
(5) determining a point density threshold of each cube according to the density of the aggregation points in each cube to distinguish a background cube from a non-background cube, wherein the density is the ratio of the number of the aggregation points in each cube to the volume of the cube, the cubes higher than the threshold are background cubes, and the cubes lower than the threshold are non-background cubes; the density of points scanned by the lidar over the same object varies with the distance from the lidar, and in general, if the distance between the target and the lidar sensor increases, the number of points decreases, wherein as the distance between the vehicle and the lidar sensor increases, the value range and the number of points follow a power function relationship, so when the distance between the background object and the lidar sensor is different, the background point density is different, which means that the threshold value should be different in different detection ranges, and in general, the density of the background space is higher than the spatial density of moving vehicles or pedestrians.
Moving vehicles and pedestrians create a low density cube. In the background frame, the number of cubes of different densities is uniform, while the low-density cube number variations of pedestrians and vehicles are uniform. Therefore, the point density threshold of the cube is determined by the following equation
N i The number of the aggregation points of the ith cube is increased, and the numbering sequence of the cubes is increased from a point number which is less to a point number which is more;
F i is N i Frequency, frequency refers to the number of cubes with the same number of points;
slope is the Slope between the collection point and the collection point;
when slope is 0 or positive, the frequency F of the point number of each cube in the formula is used as a threshold value; the slope is meaningless when being a negative value, and a threshold value is selected from the slope which becomes 0 or a positive value;
cubes above the threshold are background cubes, and those below the threshold are non-background cubes;
after the background cube with the determined threshold value is identified, the background cube is stored in a three-dimensional matrix, the three-dimensional matrix is used as the background matrix, the background matrix is combined with real-time data, points acquired from the real-time data can be eliminated if the points can be found in the background matrix, the points can be reserved if the points cannot be found in the background matrix, and background filtering is achieved.
In the step (1), the height of the supporting rod 2 is 4-6m, the requirement of a scanning range is met, manual touch is avoided, the electric box 3 is arranged at a position, 0.5m away from the top end, close to the upper position of the supporting rod, and is connected to the supporting rod in a screw nut and hoop support mode, a control terminal 5 is arranged in the electric box 3, the control terminal is protected from weather damage through the electric box, and the electric box is provided with a switch door, so that the installation, the disassembly and the maintenance of built-in equipment are facilitated.
In the step (1), when the signal lamp 9 exists on the road middle section and the bridge, the signal lamp post 8 is used as a support rod, and the signal lamp 9 is supported on the signal lamp post 8 through the signal lamp support 10, as shown in fig. 3. When the street lamp 7 is arranged on the middle section of the road and the bridge, the street lamp post 6 is used as a support rod, as shown in figure 2.
In the step (3), the aggregation frame number of the 16-beam laser radar is 2000, and the aggregation frame number of the 32-beam laser radar or 64-beam laser radar can be reduced according to specific conditions, so that the real-time processing efficiency is ensured.
In the step (4), the side length of the cube is 0.1 m. The key parameter for cube partitioning is the side length of the cube, which affects the number of rows and columns of the three-dimensional matrix. A shorter side length increases the time cost and the moving distance of the dynamic background point is large, the divided cube is crossed, so that the dynamic point cannot be captured well, and a longer side length may reduce the precision.
Example 2:
the using method of the multi-beam laser radar background filtering device based on point cloud density superposition distribution comprises the steps of embodiment 1, and is characterized in that in the step (1), when the device is applied to a tunnel, a fixing rod 12 is installed at the position of an arch top 11, a laser radar 1 is arranged on one side of the fixing rod 12, an electric box 3 is fixedly arranged on the side wall of the tunnel with the same cross section, a control terminal is arranged in the electric box 3, and the laser radar 1 is connected with the control terminal 5, as shown in fig. 4.
Example 3:
the application method of the multi-beam lidar background filtering device based on point cloud density superposition distribution comprises the steps of embodiment 1, and is characterized in that in the step (3), the laser radar aggregation frame number of 16 beams is 1500.
Example 4:
the use method of the multi-beam laser radar background filtering device based on the point cloud density superposition distribution comprises the steps of embodiment 1, and is characterized in that in the step (3), the number of laser radar aggregation frames of 16 beams is 3000.
Claims (6)
1. The utility model provides a multi-thread bundle laser radar background filtering device's application method based on point cloud density stack distributes, the device includes laser radar and control terminal, and laser radar is connected to control terminal, carries out data acquisition through the laser radar scanning, handles the data that laser radar gathered through control terminal, its characterized in that, uses the step as follows:
(1) when the device is applied to the middle section of a road and a bridge, firstly, erecting a support rod, arranging a laser radar on the support rod, and connecting the laser radar with a control terminal;
(2) the method comprises the steps that the laser radar scans for 360 degrees to collect point cloud data, and original data in a period of time are collected to serve as initial input;
(3) aggregating a period of time data frames based on the laser radar point coordinates;
(4) cutting the three-dimensional space into successive cubes:
establishing a three-dimensional matrix to represent the whole space, wherein the matrix element is a cube, and recording the number of aggregation points in the cube;
(5) determining a point density threshold of each cube according to the density of the aggregation points in each cube to distinguish a background cube from a non-background cube, wherein the density is the ratio of the number of the aggregation points in each cube to the volume of the cube, the cubes higher than the threshold are background cubes, and the cubes lower than the threshold are non-background cubes;
(6) after a background cube with a determined threshold value is identified, the background cube is stored in a three-dimensional matrix, the three-dimensional matrix is used as a background matrix, the background matrix is combined with real-time data, points acquired from the real-time data can be found in the background matrix and then eliminated, points cannot be found in the background matrix and then reserved, and background filtering is achieved;
in the step (5), the point density threshold of the cube is determined by the following formula
N i The number of the aggregation points of the ith cube is increased, and the numbering sequence of the cubes is increased from a point number which is less to a point number which is more;
F i is N i Frequency, frequency refers to the number of cubes with the same number of points;
slope is the Slope between the aggregation point and the aggregation point;
when slope is 0 or positive, the frequency F of the point number of each cube in the formula is used as a threshold value; when slope is a negative value, the slope is meaningless, and a threshold value is selected from the slope which becomes 0 or a positive value;
cubes above the threshold are background cubes and below the threshold are non-background cubes.
2. The use method of the multi-line beam laser radar background filtering device based on the point cloud density superposition distribution as recited in claim 1, wherein in the step (1), the height of the supporting rod is 4-6m, an electric box is arranged at the position, close to the upper position, of the supporting rod, and the distance between the supporting rod and the top end is 0.5m, and a control terminal is arranged in the electric box.
3. The use method of the multi-beam lidar background filtering apparatus based on point cloud density overlay distribution of claim 1, wherein in the step (1), when signal lamps exist on the road middle section and the bridge, signal lamp posts are used as supporting rods.
4. The method for using the multi-line-beam laser radar background filtering device based on the point cloud density superposition distribution as claimed in claim 1, wherein in the step (1), when the device is applied to a tunnel, a fixing rod is installed at the arch crown, a laser radar is arranged on one side of the fixing rod, an electric box is fixedly arranged on the side wall of the tunnel with the same cross section, a control terminal is arranged in the electric box, and the laser radar is connected with the control terminal.
5. The method as claimed in claim 1, wherein in step (3), the aggregation frame number is 1500-.
6. The use method of the multi-beam lidar background filtering apparatus based on point cloud density overlay distribution of claim 1, wherein in the step (4), the cube has a side length of 0.1 m.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202111162738.4A CN113903179B (en) | 2021-09-30 | 2021-09-30 | Using method of multi-beam laser radar background filtering device based on point cloud density superposition distribution |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202111162738.4A CN113903179B (en) | 2021-09-30 | 2021-09-30 | Using method of multi-beam laser radar background filtering device based on point cloud density superposition distribution |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN113903179A CN113903179A (en) | 2022-01-07 |
| CN113903179B true CN113903179B (en) | 2022-07-26 |
Family
ID=79189998
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202111162738.4A Active CN113903179B (en) | 2021-09-30 | 2021-09-30 | Using method of multi-beam laser radar background filtering device based on point cloud density superposition distribution |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN113903179B (en) |
Families Citing this family (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN114638853B (en) * | 2022-05-18 | 2022-09-02 | 广东工业大学 | Method and system for filtering background based on roadside solid-state laser radar |
Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20140111618A1 (en) * | 2012-10-19 | 2014-04-24 | Kabushiki Kaisha Topcon | Three-Dimensional Measuring Device and Three-Dimensional Measuring System |
| CN109934120A (en) * | 2019-02-20 | 2019-06-25 | 东华理工大学 | A kind of substep point cloud noise remove method based on space density and cluster |
| WO2019198011A1 (en) * | 2018-04-13 | 2019-10-17 | Sony Corporation | Method & apparatus for point cloud color processing |
| CN111540201A (en) * | 2020-04-23 | 2020-08-14 | 山东大学 | Vehicle queuing length real-time estimation method and system based on roadside laser radar |
| CN113176546A (en) * | 2020-10-20 | 2021-07-27 | 苏州思卡信息系统有限公司 | Method for filtering background of road side radar in real time based on NURBS modeling |
Family Cites Families (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN110264567B (en) * | 2019-06-19 | 2022-10-14 | 南京邮电大学 | Real-time three-dimensional modeling method based on mark points |
-
2021
- 2021-09-30 CN CN202111162738.4A patent/CN113903179B/en active Active
Patent Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20140111618A1 (en) * | 2012-10-19 | 2014-04-24 | Kabushiki Kaisha Topcon | Three-Dimensional Measuring Device and Three-Dimensional Measuring System |
| WO2019198011A1 (en) * | 2018-04-13 | 2019-10-17 | Sony Corporation | Method & apparatus for point cloud color processing |
| CN109934120A (en) * | 2019-02-20 | 2019-06-25 | 东华理工大学 | A kind of substep point cloud noise remove method based on space density and cluster |
| CN111540201A (en) * | 2020-04-23 | 2020-08-14 | 山东大学 | Vehicle queuing length real-time estimation method and system based on roadside laser radar |
| CN113176546A (en) * | 2020-10-20 | 2021-07-27 | 苏州思卡信息系统有限公司 | Method for filtering background of road side radar in real time based on NURBS modeling |
Non-Patent Citations (2)
| Title |
|---|
| A data mapping method for roadside LiDAR sensors;yuan tian et.al;《2019 IEEE Intelligent Transportation Systems Conference (ITSC)》;20191130;全文 * |
| 激光扫描点云图像背景交互式滤除;李永强 等;《测绘科学》;20080131;全文 * |
Also Published As
| Publication number | Publication date |
|---|---|
| CN113903179A (en) | 2022-01-07 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN103714363B (en) | A kind of motor vehicle exhaust smoke video identification system | |
| US7689347B2 (en) | Traffic signal light control system and method | |
| CN110097762B (en) | Road video image low visibility scale estimation method and system | |
| CN108717540B (en) | Method and device for distinguishing pedestrians and vehicles based on 2D laser radar | |
| CN113496491B (en) | Road surface segmentation method and device based on multi-line laser radar | |
| CN111833598B (en) | Automatic traffic incident monitoring method and system for unmanned aerial vehicle on highway | |
| CN102867414A (en) | Vehicle queue length measurement method based on PTZ (Pan/Tilt/Zoom) camera fast calibration | |
| CN102930735A (en) | City real-time traffic and road condition information issuing method based on traffic video | |
| CN113345237A (en) | Lane-changing identification and prediction method, system, equipment and storage medium for extracting vehicle track by using roadside laser radar data | |
| CN114333330B (en) | Intersection event detection system based on road side edge holographic sensing | |
| CN114898296A (en) | Bus lane occupation detection method based on millimeter wave radar and vision fusion | |
| CN107221175B (en) | Pedestrian intention detection method and system | |
| CN113903179B (en) | Using method of multi-beam laser radar background filtering device based on point cloud density superposition distribution | |
| CN105262983A (en) | Road monitoring system and method based on internet of lamps | |
| Cai et al. | Measurement of vehicle queue length based on video processing in intelligent traffic signal control system | |
| CN106529404A (en) | Imaging principle-based recognition method for pilotless automobile to recognize road marker line | |
| CN101425128A (en) | People stream detecting method based on laser sensor depth image | |
| CN114155720B (en) | Vehicle detection and track prediction method for roadside laser radar | |
| CN114003849A (en) | Multi-lane non-contact type axle number automatic calculation method and system | |
| Wu et al. | A variable dimension-based method for roadside LiDAR background filtering | |
| Cheng et al. | Semantic segmentation of road profiles for efficient sensing in autonomous driving | |
| CN114638853A (en) | Method and system for filtering background based on roadside solid-state laser radar | |
| CN113176546B (en) | Method for filtering background of road side radar in real time based on NURBS modeling | |
| CN109801503B (en) | Vehicle speed measuring method and system based on laser | |
| Liu et al. | Background filtering and object detection with roadside LiDAR data |
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 |