CN113204026B - Method for improving detection performance of rear millimeter wave radar blind area - Google Patents
Method for improving detection performance of rear millimeter wave radar blind area Download PDFInfo
- Publication number
- CN113204026B CN113204026B CN202110495543.5A CN202110495543A CN113204026B CN 113204026 B CN113204026 B CN 113204026B CN 202110495543 A CN202110495543 A CN 202110495543A CN 113204026 B CN113204026 B CN 113204026B
- Authority
- CN
- China
- Prior art keywords
- information
- boundary
- lane line
- obstacle
- vehicle
- 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
- 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
-
- 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
- G01S7/00—Details of systems according to groups G01S13/00, G01S15/00, G01S17/00
- G01S7/02—Details of systems according to groups G01S13/00, G01S15/00, G01S17/00 of systems according to group G01S13/00
- G01S7/40—Means for monitoring or calibrating
-
- 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
- G01S2013/9315—Monitoring blind spots
Landscapes
- Engineering & Computer Science (AREA)
- Radar, Positioning & Navigation (AREA)
- Remote Sensing (AREA)
- Physics & Mathematics (AREA)
- Computer Networks & Wireless Communication (AREA)
- General Physics & Mathematics (AREA)
- Electromagnetism (AREA)
- Traffic Control Systems (AREA)
- Radar Systems Or Details Thereof (AREA)
Abstract
The invention discloses a method for improving blind area detection performance of a rear millimeter wave radar, which is characterized in that a vehicle foresight device is used for acquiring road conditions in front of a vehicle and calculating to obtain travelable area information, a vehicle foresight device is used for acquiring lane line conditions in front of the vehicle and calculating to obtain lane line information, a front millimeter wave radar is used for acquiring road boundary obstacles in front of the vehicle and outputting road boundary obstacle information, the travelable area information, the lane line information and the road boundary obstacle information are subjected to data processing to obtain fusion boundary information, blind area obstacle information is acquired through a rear millimeter wave radar, blind area obstacles positioned outside the travelable area or outside the lane line or outside the road boundary obstacles are filtered, and the filtered blind area obstacle information is output. The method can improve the detection accuracy of the blind area target, reduce false alarm and improve the detection stability and reliability.
Description
Technical Field
The invention relates to the field of intelligent vehicles, in particular to a method for improving detection performance of a rear millimeter wave radar blind area.
Background
With the continuous development of the vehicle driving assistance function, the blind area warning function is realized through the rear millimeter wave radar, and the method for providing safe driving assistance for the driver becomes a common and effective way more and more. At present, the quality of the blind area alarm function mainly depends on the stability and reliability of a target output by a rear millimeter wave angle radar. However, for road boundary obstacles, that is, obstacles on both sides of a road for distinguishing the boundaries of both sides of the road, such as metal railings, green belts, etc., a false alarm problem often occurs, and the use of the blind zone alarm function is seriously affected.
The existing solution is to improve the performance of blind area target detection by optimizing signal processing and data processing algorithms under the condition of determining hardware resources of the rear millimeter wave radar. However, due to the limitation of hardware resources and algorithm performance of the rear millimeter wave radar, there is a certain limitation in solving the problem only by the millimeter wave radar sensor itself. Often, blind area targets such as static metal railings, green belts and the like cannot be detected accurately and effectively. If the target identification precision is improved by increasing the size of the millimeter wave radar antenna and the performance of the processing chip, the size, power consumption and cost of the front millimeter wave radar can be increased, and actual installation and wide use are not satisfied.
Disclosure of Invention
Aiming at the defects in the prior art, the invention aims to provide a method for improving the detection performance of the blind area of the rear millimeter wave radar, which can improve the detection accuracy of the target in the blind area, reduce false alarm and improve the detection stability and reliability.
In order to achieve the purpose, the invention provides the following technical scheme: a method for improving the detection performance of a blind area of a rear millimeter wave radar provides a vehicle forward-looking device, a forward millimeter wave radar and a backward millimeter wave radar, and is characterized in that: the method for improving the detection performance of the rear millimeter wave radar blind area comprises a data processing step, a fusion processing step and a logic judgment step;
the data processing step comprises a travelable region processing sub-step, a lane line processing sub-step and a road boundary obstacle processing sub-step;
the travelable region processing sub-step comprises the steps of constructing a coordinate system, acquiring the road condition in front of the vehicle through the vehicle front-view device, calculating to obtain travelable region information, wherein the travelable region information comprises the position of a boundary line of a travelable region relative to the vehicle, and constructing a travelable region on the coordinate system according to the travelable region information;
the lane line processing substep comprises the steps of obtaining the lane line condition in front of the vehicle through the vehicle forward-looking device and calculating to obtain lane line information, wherein the lane line information comprises the position of the lane line relative to the vehicle, the lane line type and the lane line length, the lane line type comprises a left lane line, a right lane line, a solid line and a dotted line, and the lane line is constructed on the coordinate system according to the lane line information;
the regional obstacle processing sub-step comprises the steps of obtaining road boundary obstacles in front of a vehicle through the forward millimeter wave radar and outputting road boundary obstacle information, wherein the road boundary obstacle information comprises the positions of the road boundary obstacles relative to the vehicle, and road boundary obstacles are constructed on the coordinate system according to the road boundary obstacle information;
the fusion processing step comprises the steps of carrying out data processing on the obtained travelable area information, lane line information and road boundary obstacle information on a coordinate system to obtain fusion boundary information, wherein the fusion boundary information comprises the position of a fusion boundary obtained by carrying out data processing on a boundary line of a travelable area, a lane line or a road boundary obstacle relative to the vehicle, and constructing the fusion boundary on the coordinate system according to the fusion boundary information;
the logic judgment step includes acquiring blind area obstacle information including a position of a blind area obstacle relative to the vehicle through the backward millimeter wave radar, constructing a blind area obstacle on the coordinate system, filtering the blind area obstacle located outside a travelable area, outside a lane line or outside a road boundary obstacle according to whether the acquired fusion boundary information refers to the travelable area information, the lane line information or the road boundary obstacle information, and outputting the filtered blind area obstacle information.
As a further improvement of the present invention, the travelable region processing sub-step is specifically to construct a coordinate system, obtain boundary available points of a travelable region in front of the vehicle by the vehicle forward-looking device, perform straight-line fitting on the boundary available points to obtain boundary lines of the travelable region when the number of the boundary available points is greater than a preset threshold value of the minimum number of the boundary available points, calculate the position of the boundary lines of the travelable region relative to the vehicle, and construct the travelable region on the coordinate system according to the travelable region information.
As a further improvement of the present invention, the lane line processing substep specifically includes acquiring lane line data by the vehicle forward-looking device, performing mean filtering on the lane line data, determining the availability of the lane line after the mean filtering, acquiring lane line information when an available lane line exists, and constructing a lane line on the coordinate system according to the lane line information.
As a further improvement of the present invention, when the availability of the lane line after the mean value filtering is determined, if no available lane line is available, the lane line data is obtained again by the vehicle forward-looking device.
As a further improvement of the present invention, the step of processing the road boundary barrier specifically includes obtaining road boundary barrier data points by extracting the point cloud data through the forward millimeter wave radar, performing data processing on the barrier data points to obtain the road boundary barrier when the number of the road boundary barrier data points is greater than a preset threshold value of the minimum number of the road boundary barrier data points, calculating the position of the road boundary barrier relative to the vehicle, and constructing the road boundary barrier on the coordinate system according to the information of the road boundary barrier.
As a further improvement of the invention, the obstacle data points are subjected to data processing by a histogram method to obtain the road boundary obstacle.
As a further improvement of the present invention, the fusion processing step is embodied to, when only one of the travelable region information, the lane line information, and the road boundary obstacle information is obtained, take the obtained travelable region information, the lane line information, or the road boundary obstacle information as fusion boundary information;
when only two of the travelable area information, the lane line information and the road boundary obstacle information are obtained, averaging the obtained data of the two on the coordinate system to obtain fused boundary information;
when the travelable region information, the lane line information, and the road boundary obstacle information are obtained at the same time; the method comprises the steps of firstly averaging the lane line information and the road boundary barrier information on the coordinate system to obtain preliminary fusion boundary information, then averaging the preliminary fusion boundary information and the travelable area information on the coordinate system to obtain fusion boundary information, and constructing a fusion boundary on the coordinate system according to the fusion boundary information.
As a further improvement of the present invention, the logic determining step specifically includes acquiring blind area obstacle information by the backward millimeter wave radar, constructing a blind area obstacle on the coordinate system, acquiring a current vehicle speed of the vehicle when the fusion boundary information is obtained by referring to the lane line information or the road boundary obstacle information, filtering the blind area obstacle located outside the lane line or outside the road boundary obstacle when the vehicle speed is greater than a preset vehicle speed threshold, and outputting the filtered blind area obstacle information; when the vehicle speed is not greater than a preset vehicle speed threshold value, the fusion boundary information is obtained again;
when the fusion boundary information is obtained by referring to the travelable area information, acquiring the current speed of the vehicle, when the speed is less than a preset speed threshold value, filtering blind area obstacles positioned outside the travelable area, and outputting the filtered blind area obstacle information; and when the vehicle speed is not less than the preset vehicle speed threshold value, the fusion boundary information is acquired again.
As a further improvement of the invention, the value range of the vehicle speed threshold is 40km/h-60 km/h.
As a further improvement of the present invention, the vehicle forward view device is a vehicle forward view camera.
The invention has the beneficial effects that: through the arrangement of the data processing step, a travelable area, a lane line and a road boundary barrier are firstly constructed on a coordinate system by utilizing data acquired by a vehicle forward-looking device of the vehicle and a forward millimeter wave radar, then the travelable area, the lane line and the road boundary barrier are processed to obtain a fusion boundary, finally a blind area barrier acquired by a backward millimeter wave radar is constructed on the coordinate system, the blind area barrier positioned outside the travelable area or outside the lane line or outside the road boundary barrier is filtered, and the filtered blind area barrier information is output. By the arrangement, the vehicle only runs in the travelable area, the lane line and the road boundary barriers, and the filtered blind area barriers have no influence on the running of the vehicle, so that the barriers do not need to be prompted, and the information of the filtered blind area barriers is the barriers to be avoided by the vehicle and needs to be prompted. And because the road boundary barrier is constructed in the coordinate system by the front-looking millimeter wave radar, the defect that the rear millimeter wave radar cannot accurately identify the road boundary barrier is overcome. Therefore, the method can avoid the prompting of the road boundary barrier and the blind area barrier which has no influence on the running of the vehicle, and only prompts the filtered barrier which has the influence on the running of the vehicle and needs to be avoided by the vehicle, thereby improving the detection accuracy of the target in the blind area, reducing the false alarm and improving the detection stability and reliability.
Drawings
FIG. 1 is a schematic flow diagram of the present invention;
FIG. 2 is a flow diagram illustrating a travelable region processing sub-step;
FIG. 3 is a schematic flow diagram of a lane line processing substep;
FIG. 4 is a schematic flow chart of a road boundary obstacle processing sub-step;
FIG. 5 is a flow chart illustrating the steps of the fusion process;
FIG. 6 is a flowchart illustrating the logic determining step.
Detailed Description
The present invention will be described in further detail with reference to the accompanying drawings and examples. In which like parts are designated by like reference numerals.
Referring to fig. 1, the method for improving the detection performance of the blind area of the rear millimeter wave radar in the embodiment provides a vehicle forward-looking device, a forward millimeter wave radar and a backward millimeter wave radar, and the vehicle forward-looking device in the embodiment is a vehicle forward-looking camera. The method for improving the detection performance of the rear millimeter wave radar blind area comprises a data processing step, a fusion processing step and a logic judgment step, wherein the data processing step comprises a travelable area processing sub-step, a lane line processing sub-step and a road boundary obstacle processing sub-step.
Referring to fig. 2, the travelable region processing sub-step includes constructing a coordinate system using the host vehicle as an origin, and acquiring a boundary available point of a travelable region in front of the vehicle, which is a region where the host vehicle can travel after avoiding a traveling obstacle such as a preceding vehicle, from the point cloud data by the vehicle forward-looking device. And when the number of the boundary available points is greater than a preset threshold value of the minimum number of the boundary available points, performing linear fitting on the boundary available points to obtain a boundary line of a travelable area, calculating to obtain travelable area information, wherein the travelable area information comprises the position of the boundary line of the travelable area relative to the vehicle, and constructing the travelable area on a coordinate system according to the travelable area information. And when the number of the boundary available points is not more than the preset threshold value of the minimum number of the boundary available points, the boundary available points of the drivable area in front of the vehicle are acquired again.
Referring to fig. 3, the lane marking sub-step includes acquiring lane marking data by a vehicle forward-looking device, and performing mean filtering on the lane marking data, where the mean filtering is to obtain a relatively smooth lane marking to avoid abrupt change of the lane marking. And judging the availability of the lane line after the mean filtering, wherein the availability of the lane line represents whether the lane line is suitable for subsequent data processing or whether the obtained lane line accords with the actual road condition, for example, when the lane line is incomplete or has sudden change after the mean filtering, the lane line is determined to be unavailable. And if no available lane line exists, acquiring lane line data again through the vehicle forward-looking device. When available lane lines exist, lane line information is obtained, the lane line information comprises the positions of the lane lines relative to the vehicle, the types of the lane lines and the lengths of the lane lines, the types of the lane lines comprise left lane lines, right lane lines, solid lines, dotted lines, lane lines at the edges of the road and lane lines in the middle of the road, and the lane lines are constructed on a coordinate system according to the lane line information.
Referring to fig. 4, the sub-step of processing the road boundary obstacles includes obtaining road boundary obstacles in front of the vehicle according to the point cloud data by the forward millimeter wave radar and extracting road boundary obstacle data points, where the road boundary obstacles are obstacles on both sides of the road, such as metal railings and green belts, for distinguishing the boundaries on both sides of the road. When the number of the road boundary obstacle data points is larger than a preset threshold value of the minimum number of the road boundary obstacle data points, performing data processing on the obstacle data points through a histogram method to obtain road boundary obstacles, calculating and obtaining road boundary obstacle information, wherein the road boundary obstacle information comprises the positions of the road boundary obstacles relative to the vehicle, and constructing the road boundary obstacles on a coordinate system according to the road boundary obstacle information.
Referring to fig. 5, the fusion processing step includes, when only one of the travelable region information, the lane line information, and the road boundary obstacle information is obtained, taking the obtained travelable region information, lane line information, or road boundary obstacle information as fusion boundary information, and constructing a fusion boundary on the coordinate system based on the fusion boundary information.
When only two of the travelable area information, the lane line information and the road boundary obstacle information are obtained, the obtained data of the travelable area information, the lane line information and the road boundary obstacle information are averaged on a coordinate system to obtain the fusion boundary information, and the averaging mode can be that the data are weighted and assigned and then averaged. The fusion boundary information includes a position of a fusion boundary relative to the host vehicle, the fusion boundary being obtained by data processing two of a boundary line of a travelable region, a lane line, or a road boundary obstacle. And constructing a fusion boundary on the coordinate system according to the fusion boundary information.
When the travelable area information, the lane line information and the road boundary obstacle information are simultaneously obtained; firstly, averaging the lane line information and the road boundary obstacle information on a coordinate system to obtain preliminary fusion boundary information, wherein the preliminary fusion boundary information is obtained by processing the lane line information and the road boundary obstacle information. The preliminary fusion boundary information includes a position of a preliminary fusion boundary relative to the own vehicle, which is obtained by data processing of the lane line and the road boundary obstacle. And averaging the preliminary fusion boundary information and the travelable area information on a coordinate system to obtain fusion boundary information, wherein the averaging mode can be that the data is weighted and assigned and then averaged. The fusion boundary information includes the position of the fusion boundary relative to the vehicle, which is obtained by data processing of the boundary line of the travelable region and the preliminary fusion boundary, and the fusion boundary is constructed on the coordinate system according to the fusion boundary information.
Referring to fig. 6, the logic determining step includes obtaining blind area obstacle information by the backward millimeter wave radar, where the blind area obstacle information includes a position of a blind area obstacle relative to the vehicle, and constructing a blind area obstacle on a coordinate system, obtaining a current vehicle speed of the vehicle when the fusion boundary information is obtained by referring to lane line information or road boundary obstacle information, filtering the blind area obstacle located outside a lane line or outside a road boundary obstacle when the vehicle speed is greater than a preset vehicle speed threshold, and outputting the filtered blind area obstacle information; and when the vehicle speed is not greater than the preset vehicle speed threshold value, acquiring the fusion boundary information again. The value range of the vehicle speed threshold is 40km/h-60km/h, and the value of the vehicle speed threshold in the embodiment is 50 km/h.
When the fusion boundary information is obtained by referring to the travelable area information, the current speed of the vehicle is obtained, when the speed is less than a preset speed threshold value, blind area obstacles positioned outside the travelable area are filtered, and the filtered blind area obstacle information is output; and when the vehicle speed is not less than the preset vehicle speed threshold value, acquiring the fusion boundary information again.
The above is only a preferred embodiment of the present invention, and the protection scope of the present invention is not limited to the above-mentioned embodiments, and all technical solutions belonging to the idea of the present invention belong to the protection scope of the present invention. It should be noted that modifications and embellishments within the scope of the invention may occur to those skilled in the art without departing from the principle of the invention, and are considered to be within the scope of the invention.
Claims (9)
1. A method for improving the detection performance of a blind area of a rear millimeter wave radar provides a vehicle forward-looking device, a forward millimeter wave radar and a backward millimeter wave radar, and is characterized in that: the method for improving the detection performance of the rear millimeter wave radar blind area comprises a data processing step, a fusion processing step and a logic judgment step;
the data processing step comprises a travelable region processing sub-step, a lane line processing sub-step and a road boundary obstacle processing sub-step;
the travelable region processing sub-step comprises the steps of constructing a coordinate system, acquiring the road condition in front of the vehicle through the vehicle front-view device, calculating to obtain travelable region information, wherein the travelable region information comprises the position of a boundary line of a travelable region relative to the vehicle, and constructing a travelable region on the coordinate system according to the travelable region information;
the lane line processing substep comprises the steps of obtaining the lane line condition in front of the vehicle through the vehicle forward-looking device and calculating to obtain lane line information, wherein the lane line information comprises the position of the lane line relative to the vehicle, the lane line type and the lane line length, the lane line type comprises a left lane line, a right lane line, a solid line and a dotted line, and the lane line is constructed on the coordinate system according to the lane line information;
the road boundary obstacle processing sub-step comprises the steps of obtaining road boundary obstacles in front of a vehicle through the forward millimeter wave radar and outputting road boundary obstacle information, wherein the road boundary obstacle information comprises the position of the road boundary obstacles relative to the vehicle, and constructing the road boundary obstacles on the coordinate system according to the road boundary obstacle information;
the fusion processing step includes performing data processing on at least one of the obtained travelable region information, the lane line information, and the road boundary obstacle information on a coordinate system to obtain fusion boundary information, where the fusion boundary information includes a position of a fusion boundary obtained by performing data processing on a boundary line of a travelable region, a lane line, or a road boundary obstacle with respect to the host vehicle, and constructing a fusion boundary on the coordinate system according to the fusion boundary information;
the logic judgment step comprises the steps of obtaining blind area obstacle information through the backward millimeter wave radar, wherein the blind area obstacle information comprises the position of a blind area obstacle relative to the vehicle, constructing a blind area obstacle on the coordinate system, filtering the blind area obstacle positioned outside a travelable area, or outside a lane line, or outside a road boundary obstacle according to whether the obtained fusion boundary information refers to the travelable area information, the lane line information or the road boundary obstacle information, and outputting the filtered blind area obstacle information;
the logic judgment step is specifically to acquire blind area obstacle information through the backward millimeter wave radar, construct a blind area obstacle on the coordinate system, acquire the current speed of the vehicle when the fusion boundary information is obtained by referring to the lane line information or the road boundary obstacle information, filter the blind area obstacle positioned outside the lane line or outside the road boundary obstacle when the speed is greater than a preset speed threshold value, and output the filtered blind area obstacle information; when the vehicle speed is not greater than a preset vehicle speed threshold value, the fusion boundary information is obtained again;
when the fusion boundary information is obtained by referring to the travelable area information, acquiring the current speed of the vehicle, when the speed is less than a preset speed threshold value, filtering blind area obstacles positioned outside the travelable area, and outputting the filtered blind area obstacle information; and when the vehicle speed is not less than the preset vehicle speed threshold value, the fusion boundary information is acquired again.
2. The method for improving the detection performance of the blind area of the rear millimeter wave radar according to claim 1, wherein the method comprises the following steps: the travelable region processing sub-step is specifically to construct a coordinate system, obtain boundary available points of a travelable region in front of the vehicle through the vehicle front-view device, perform straight line fitting on the boundary available points to obtain a boundary line of the travelable region when the number of the boundary available points is greater than a preset threshold value of the minimum number of the boundary available points, calculate the position of the boundary line of the travelable region relative to the vehicle, and construct the travelable region on the coordinate system according to the travelable region information.
3. The method for improving the detection performance of the blind area of the rear millimeter wave radar according to claim 1, wherein the method comprises the following steps: the lane line processing sub-step specifically includes acquiring lane line data through the vehicle forward-looking device, performing mean filtering on the lane line data, judging the availability of the lane line after the mean filtering, acquiring lane line information when an available lane line exists, and constructing a lane line on the coordinate system according to the lane line information.
4. The method according to claim 3, wherein the method for improving the blind area detection performance of the rear millimeter wave radar comprises the following steps: and when the availability of the lane line after the average value filtering is judged, if the available lane line does not exist, acquiring lane line data again through the vehicle forward-looking device.
5. The method for improving the detection performance of the blind area of the rear millimeter wave radar according to claim 1, wherein the method comprises the following steps: the road boundary obstacle processing substep specifically includes obtaining road boundary obstacle data points according to point cloud data extraction through the forward millimeter wave radar, performing data processing on the obstacle data points to obtain road boundary obstacles when the number of the road boundary obstacle data points is larger than a preset road boundary obstacle data point minimum number threshold value, calculating the position of the road boundary obstacles relative to the vehicle, and constructing road boundary obstacles on the coordinate system according to the road boundary obstacle information.
6. The method for improving the detection performance of the blind area of the rear millimeter wave radar according to claim 5, wherein the method comprises the following steps: and carrying out data processing on the obstacle data points through a histogram method to obtain the road boundary obstacles.
7. The method for improving detection performance of the blind area of the rear millimeter wave radar according to claim 1, characterized in that: the fusion processing step is specifically configured to, when only one of the travelable region information, the lane line information, and the road boundary obstacle information is obtained, take the obtained travelable region information, the lane line information, or the road boundary obstacle information as fusion boundary information;
when only two of the travelable area information, the lane line information and the road boundary obstacle information are obtained, averaging the obtained data of the two on the coordinate system to obtain fused boundary information;
when the travelable region information, the lane line information, and the road boundary obstacle information are obtained at the same time; the method comprises the steps of firstly averaging the lane line information and the road boundary barrier information on the coordinate system to obtain preliminary fusion boundary information, then averaging the preliminary fusion boundary information and the travelable area information on the coordinate system to obtain fusion boundary information, and constructing a fusion boundary on the coordinate system according to the fusion boundary information.
8. The method for improving the detection performance of the blind area of the rear millimeter wave radar according to claim 1, wherein the method comprises the following steps: the value range of the vehicle speed threshold is 40km/h-60 km/h.
9. The method for improving detection performance of the blind area of the rear millimeter wave radar according to claim 1, characterized in that: the vehicle front view device is a vehicle front view camera.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202110495543.5A CN113204026B (en) | 2021-05-07 | 2021-05-07 | Method for improving detection performance of rear millimeter wave radar blind area |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202110495543.5A CN113204026B (en) | 2021-05-07 | 2021-05-07 | Method for improving detection performance of rear millimeter wave radar blind area |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN113204026A CN113204026A (en) | 2021-08-03 |
| CN113204026B true CN113204026B (en) | 2022-05-24 |
Family
ID=77029611
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202110495543.5A Active CN113204026B (en) | 2021-05-07 | 2021-05-07 | Method for improving detection performance of rear millimeter wave radar blind area |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN113204026B (en) |
Families Citing this family (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN113689718B (en) * | 2021-08-13 | 2022-09-13 | 吉林大学 | Intelligent signal lamp and lane matching system and method |
Family Cites Families (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| JP5299688B2 (en) * | 2009-06-03 | 2013-09-25 | アイシン精機株式会社 | Vehicle periphery monitoring method and vehicle periphery monitoring device |
| CN106019283B (en) * | 2016-05-24 | 2019-05-24 | 深圳市雷博泰克科技有限公司 | A kind of vehicle blind zone detection method, apparatus and system |
| CN106485233B (en) * | 2016-10-21 | 2020-01-17 | 深圳地平线机器人科技有限公司 | Method and device for detecting travelable area and electronic equipment |
| CN110386065B (en) * | 2018-04-20 | 2021-09-21 | 比亚迪股份有限公司 | Vehicle blind area monitoring method and device, computer equipment and storage medium |
| CN111923857B (en) * | 2020-09-24 | 2021-02-09 | 深圳佑驾创新科技有限公司 | Vehicle blind area detection processing method and device, vehicle-mounted terminal and storage medium |
-
2021
- 2021-05-07 CN CN202110495543.5A patent/CN113204026B/en active Active
Also Published As
| Publication number | Publication date |
|---|---|
| CN113204026A (en) | 2021-08-03 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN109634282B (en) | Autonomous vehicle, method and apparatus | |
| CN109254289B (en) | Detection method and detection equipment for road guardrail | |
| CN106991389B (en) | Device and method for determining road edge | |
| US8199046B2 (en) | Radar system to determine whether an object is subject of detection based on intensity of a radio wave emission of the object | |
| CN110386065B (en) | Vehicle blind area monitoring method and device, computer equipment and storage medium | |
| CN110809792B (en) | Collision estimation device and collision estimation method | |
| CN112009462B (en) | Forward automatic parking method and device | |
| CN111278694A (en) | Method and device for recognizing lane state | |
| CN109696676B (en) | Effective obstacle target determination method and device and vehicle | |
| US11046321B2 (en) | Adaptive control of automated lane change in vehicle | |
| JP2008117073A (en) | Interruption vehicle detection device | |
| CN112101316B (en) | Target detection method and system | |
| CN114415171A (en) | Automobile travelable area detection method based on 4D millimeter wave radar | |
| CN113204026B (en) | Method for improving detection performance of rear millimeter wave radar blind area | |
| CN111824143A (en) | Vehicle transverse control method and device, computer equipment and storage medium | |
| CN111959515B (en) | Forward target selection method, device and system based on visual detection | |
| CN114084129A (en) | Fusion-based vehicle automatic driving control method and system | |
| JP2002160598A (en) | Outside car control device | |
| US10300913B2 (en) | Vehicle identification device and vehicle identification method | |
| CN111874003B (en) | Vehicle driving deviation early warning method and system | |
| CN103847736A (en) | System by detection of lane marking | |
| CN111414857A (en) | Front vehicle detection method based on vision multi-feature fusion | |
| CN113879312B (en) | Forward target selection method and device based on multi-sensor fusion and storage medium | |
| JP3930309B2 (en) | Vehicle driving support device | |
| CN115402349A (en) | High-speed assistant driving control method and system combined with weather state |
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 |