CN114415171A - Automobile travelable area detection method based on 4D millimeter wave radar - Google Patents
Automobile travelable area detection method based on 4D millimeter wave radar Download PDFInfo
- Publication number
- CN114415171A CN114415171A CN202111573817.4A CN202111573817A CN114415171A CN 114415171 A CN114415171 A CN 114415171A CN 202111573817 A CN202111573817 A CN 202111573817A CN 114415171 A CN114415171 A CN 114415171A
- Authority
- CN
- China
- Prior art keywords
- road
- target
- point cloud
- travelable
- target obstacle
- 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.)
- Pending
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
- G01S13/86—Combinations of radar systems with non-radar systems, e.g. sonar, direction finder
- G01S13/867—Combination of radar systems with cameras
-
- 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
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 belongs to the technical field of automobile auxiliary driving, and particularly relates to an automobile travelable area detection method based on a 4D millimeter wave radar, which comprises the following steps of effective target point cloud screening: screening effective target point clouds by utilizing point cloud data of the 4D millimeter wave radar after data preprocessing and point cloud feature identification; road edge obstacle identification: identifying continuous protruding obstacles on two sides of a drivable road based on the effective target point cloud; extracting a drivable road: extracting characteristics of a travelable road and a travelable road according to the identified continuous protruding obstacles; target obstacle recognition: identifying a target obstacle in a travelable road area by using a target tracking method; drivable region extraction: and calculating the relative safe distance between the vehicle and the target obstacle according to the position and speed information of the target obstacle, thereby extracting the travelable area of the vehicle. The invention provides a method for detecting a travelable area of an automobile based on a 4D millimeter wave radar, which can effectively improve the detection efficiency and accuracy.
Description
Technical Field
The invention belongs to the technical field of automobile auxiliary driving, and particularly relates to an automobile travelable area detection method based on a 4D millimeter wave radar.
Background
At present, the mainstream scheme for identifying the drivable area is to detect the drivable area of a road based on camera visual detection images and/or laser radar measurement point cloud perception fusion; the camera visual detection image is often suitable for extracting road surface characteristics such as lane lines and steering arrows by combining a machine learning algorithm; the laser radar three-dimensional measurement point cloud is suitable for extracting raised obstacles on road edges and road surfaces. However, sensors such as a camera and a laser radar are easily affected by the environment, and the accuracy of the sensing result of the drivable road area is affected by the illumination condition and the extreme weather; in a traffic jam road section, the accuracy of the perception effect of a drivable area of the road is also influenced by shielding caused by surrounding vehicles; and the laser radar is expensive at present and is not the standard configuration of all mass-produced vehicle types. Based on the limitations, the current driving area identification scheme is poor in instantaneity, limited in applicable scene and environment and difficult to achieve the effect of mass production and use.
Disclosure of Invention
In order to solve the defects of the prior art, the invention provides a method for detecting the automobile travelable area based on a 4D millimeter wave radar, the 4D millimeter wave radar is used for detecting the travelable area of the automobile, the 4D millimeter wave radar is a radar sensor which has four-dimensional environment sensing capabilities including distance, horizontal, vertical positioning and speed and meets the sensing requirements of full targets, full coverage and multiple working conditions, the method not only can effectively analyze the outline and the type of a target object and is slightly influenced by the external weather conditions and the surrounding environment, but also has small data processing burden and low cost compared with a visual detection image and a laser radar, and can be widely applied to scenes such as high-speed cruising, safe obstacle avoidance, urban cruising, non-visual distance preceding automobile detection, environment carving, 360-degree omnibearing detection, low-speed parking and the like, therefore, the method for detecting the automobile travelable area based on the 4D millimeter wave radar of the invention, the method is not only limited by external weather conditions and little influenced by surrounding environment, but also can effectively improve the accuracy of detection, effectively improve the diversity of application scenes and applicable environments, has little data processing burden and can effectively improve the detection efficiency; in addition, compared with the expensive laser radar, the cost of the equipment can be effectively reduced.
The technical effect to be achieved by the invention is realized by the following technical scheme:
the method for detecting the automobile travelable area based on the 4D millimeter wave radar comprises the following steps of screening effective target point clouds: screening effective target point clouds by utilizing point cloud data of the 4D millimeter wave radar after data preprocessing and point cloud feature identification; road edge obstacle identification: identifying continuous protruding obstacles on two sides of a drivable road based on the effective target point cloud; extracting a drivable road: extracting characteristics of a travelable road and a travelable road according to the identified continuous protruding obstacles; target obstacle recognition: identifying a target obstacle in a travelable road area by using a target tracking method; drivable region extraction: and calculating the relative safe distance between the vehicle and the target obstacle according to the position and speed information of the target obstacle, thereby extracting the travelable area of the vehicle.
Further, in the effective target point cloud screening step, the data preprocessing is as follows: compensating the cloud historical data to relative coordinates of the current point cloud data at the detection moment of the point cloud data from the detection moment of the point cloud data through the vehicle running track, and screening the point cloud data in an effective range; clustering the point cloud data by a density clustering method, judging whether the point cloud data is a noise point or not by the number of clustering points, and filtering the noise point; the point cloud features are identified as: and counting the clustering point number characteristics, the distribution of the calculated points, the length and width characteristics of the class and the average signal-to-noise ratio characteristics of the calculated class of the clustered point cloud.
Further, if the number of clustering points is larger than 3, the current class is considered as the effective class, otherwise, the current class is considered as the noise point, and the noise point is filtered.
Further, in the step of identifying the road edge barrier, screening point cloud data which are static to the ground, fitting the points to form a curve which is approximate to the road edge or the railing by a minimum two fitting method, and judging whether the current road has a real road edge or the railing or not by fitting the shape and the effect; and when the ground speed is less than 0.5m/s, the data is regarded as point cloud data which is static to the ground.
Further, in the travelable road extraction step, the width and shape of the road on which the vehicle is traveling are estimated by the identification of the left and right road edges or the balustrade, and the shape of the road ahead is predicted based on the shape of the balustrade.
Further, in the step of identifying the target obstacle, point cloud data on the inner side of a road are screened, the motion track of the same target is tracked through track establishment and multi-frame point association matching of a target initial point, track information of the target is obtained, and the motion state of the target is estimated by utilizing the track information; the motion state of the target is estimated by using the track information, wherein the motion state comprises the vehicle speed, the course angle and the target size.
Further, in the travelable region extraction step, an initial travelable region of the host vehicle is extracted according to the stationary target obstacle, and then a final travelable region of the host vehicle is extracted according to the moving target obstacle.
Further, in the travelable region extraction step, the relative safe distance of the vehicle from the stationary target obstacle is calculated by the time ttc1 of collision with the stationary target obstacle according to the position of the stationary target obstacle, thereby extracting the initial travelable region of the vehicle; the calculation formula of the time ttc1 for collision with the stationary target obstacle is: ttc1 is dis1/v, dis1 indicates the relative distance between the host vehicle and the stationary target obstacle, and v indicates the movement speed of the host vehicle.
Further, in the travelable region extraction step, the real-time relative safety distance of the vehicle from the moving target obstacle is calculated through the time ttc2 of collision with the moving target obstacle according to the position and the speed of the moving target obstacle, so that the final travelable region of the vehicle is extracted; the calculation formula of the collision time ttc2 with the moving target obstacle is as follows: ttc2 is dis2/dv, dis2 indicates the real-time relative safe distance between the host vehicle and the moving target obstacle, and dv indicates the real-time relative speed between the host vehicle and the moving target obstacle.
Further, when ttc1 is greater than 3s, the vehicle and the static target obstacle are considered to be within a relatively safe distance; when ttc2 is greater than 3s, the vehicle and the moving target obstacle are considered to be within a real-time relative safety distance.
In summary, the method for detecting the automobile driving area based on the 4D millimeter wave radar of the present invention has at least the following advantages:
1. compared with the mode of detecting by adopting a camera and a laser radar in the prior art, the method for detecting the automobile travelable area based on the 4D millimeter wave radar detects the travelable area of the automobile by adopting the 4D millimeter wave radar, the 4D millimeter wave radar is not easily influenced by the external weather conditions and the surrounding environment, has good robustness, can effectively improve the accuracy of detection of the travelable area, and provides the travelable area for low-speed parking or automatic driving path planning.
2. Compared with the mode of adopting a camera to visually detect images and adopting a laser radar to measure in the prior art, the method for detecting the automobile travelable area based on the 4D millimeter wave radar has the advantages of high data processing efficiency, long detection distance, capability of reserving more processing time for an automatic driving system and small data processing burden.
3. The method for detecting the automobile drivable area based on the 4D millimeter wave radar can effectively expand the application range of the 4D millimeter wave radar and enhance the functionality of the 4D millimeter wave radar and can provide technical feasibility verification for subsequently realizing the SLAM function of the 4D millimeter wave radar in view of the fact that the 4D millimeter wave radar can be widely applied to scenes such as high-speed cruising, safe obstacle avoidance, urban cruising, non-line-of-sight front automobile detection, environment portrayal, 360-degree all-directional detection, low-speed parking and the like.
4. According to the method for detecting the automobile travelable area based on the 4D millimeter wave radar, the 4D millimeter wave radar can effectively reduce the equipment cost compared with a laser radar with high price.
5. According to the method for detecting the automobile travelable area based on the 4D millimeter wave radar, the 4D millimeter wave radar can be fused with visual detection, and the defect of image identification is overcome.
Drawings
FIG. 1 is a block flow diagram of a method for detecting a drivable area of an automobile based on a 4D millimeter-wave radar in accordance with an embodiment of the present invention;
fig. 2 is a schematic view of a vehicle travelable region based on a 4D millimeter wave radar in the embodiment of the present invention.
Detailed Description
In order to make the objects, technical solutions and advantages of the embodiments of the present invention more apparent, the technical solutions of the embodiments of the present invention will be described in detail and completely with reference to the accompanying drawings. The described embodiments are a few embodiments of the invention, rather than all embodiments.
Thus, the following detailed description of the embodiments of the present invention, presented in the figures, is not intended to limit the scope of the invention, as claimed, but is merely representative of selected embodiments of the invention. All other embodiments, which can be obtained by a person skilled in the art without any inventive step based on the embodiments of the present invention, are within the scope of the present invention.
Example 1:
the method for detecting the automobile travelable region based on the 4D millimeter wave radar in the embodiment comprises the following steps,
screening effective target point clouds: screening effective target point clouds by utilizing point cloud data of the 4D millimeter wave radar after data preprocessing and point cloud feature identification;
road edge obstacle identification: identifying continuous protruding obstacles on two sides of a drivable road based on the effective target point cloud;
extracting a drivable road: extracting characteristics of a travelable road and a travelable road according to the identified continuous protruding obstacles;
target obstacle recognition: identifying a target obstacle in a travelable road area by using a target tracking method;
drivable region extraction: and calculating the relative safe distance between the vehicle and the target obstacle according to the position and speed information of the target obstacle, thereby extracting the travelable area of the vehicle.
Compared with the camera visual detection image and the laser radar measurement in the prior art, the method for detecting the automobile travelable area based on the 4D millimeter wave radar in the embodiment has the advantages that the method is limited by external weather conditions and is slightly influenced by the surrounding environment, the detection accuracy can be effectively improved, the diversity of application scenes and applicable environments can be effectively improved, the data processing burden is small, and the detection efficiency can be effectively improved; in addition, compared with the expensive laser radar, the cost of the equipment can be effectively reduced. In the method for detecting the automobile travelable area based on the 4D millimeter wave radar in the embodiment, the detection of the automobile travelable area is realized in a mode of combining effective target point cloud screening, obstacle classification and identification and extraction, the detection mode is simple, the data processing burden is small, and the detection efficiency of the travelable area can be further effectively improved.
Example 2:
the method for detecting the automobile travelable region based on the 4D millimeter wave radar in the embodiment comprises the following steps,
screening effective target point clouds: screening effective target point clouds by utilizing point cloud data of the 4D millimeter wave radar after data preprocessing and point cloud feature identification;
road edge obstacle identification: identifying continuous protruding obstacles on two sides of a drivable road based on the effective target point cloud;
extracting a drivable road: extracting characteristics of a travelable road and a travelable road according to the identified continuous protruding obstacles;
target obstacle recognition: identifying a target obstacle in a travelable road area by using a target tracking method;
drivable region extraction: and calculating the relative safe distance between the vehicle and the target obstacle according to the position and speed information of the target obstacle, thereby extracting the travelable area of the vehicle.
In the effective target point cloud screening step, the data preprocessing comprises the following specific steps: the method comprises the steps that cloud historical data are compensated from the moment point cloud data are detected to the relative coordinates of the current point cloud data at the moment the point cloud data are detected through a vehicle running track, and point cloud data in an effective range are screened, wherein the straight line distance is 100 m; clustering the point cloud data by a density clustering method, judging whether the point cloud data is a noise point or not by the number of clustering points, and filtering the noise point; preferably, if the number of clustering points is greater than 3, the current class is considered as a valid class, otherwise, the current class is considered as a noise point, and the noise point is filtered. The specific steps of point cloud feature identification are as follows: and counting the clustering point number characteristics, the distribution of the calculated points, the length and width characteristics of the class and the average signal-to-noise ratio characteristics of the calculated class of the clustered point cloud.
Example 3:
the method for detecting the automobile travelable region based on the 4D millimeter wave radar in the embodiment comprises the following steps,
screening effective target point clouds: screening effective target point clouds by utilizing point cloud data of the 4D millimeter wave radar after data preprocessing and point cloud feature identification;
road edge obstacle identification: identifying continuous protruding obstacles on two sides of a drivable road based on the effective target point cloud;
extracting a drivable road: extracting characteristics of a travelable road and a travelable road according to the identified continuous protruding obstacles;
target obstacle recognition: identifying a target obstacle in a travelable road area by using a target tracking method;
drivable region extraction: and calculating the relative safe distance between the vehicle and the target obstacle according to the position and speed information of the target obstacle, thereby extracting the travelable area of the vehicle.
In the step of identifying the road edge barrier, screening point cloud data which are static to the ground, fitting the points to form a curve which is approximate to the road edge or the railing by a minimum two fitting method, and judging whether the current road has a real road edge or the railing or not by fitting the shape and the effect; and when the ground speed is less than 0.5m/s, the data is regarded as point cloud data which is static to the ground.
In the travelable road extraction step, the width and shape of the road on which the vehicle is traveling are estimated by the identification of the left and right road edges or the balustrade, and the shape of the road ahead, such as a straight road or a curved road, is predicted based on the shape of the balustrade.
Example 4:
the method for detecting the automobile travelable region based on the 4D millimeter wave radar in the embodiment comprises the following steps,
screening effective target point clouds: screening effective target point clouds by utilizing point cloud data of the 4D millimeter wave radar after data preprocessing and point cloud feature identification;
road edge obstacle identification: identifying continuous protruding obstacles on two sides of a drivable road based on the effective target point cloud;
extracting a drivable road: extracting characteristics of a travelable road and a travelable road according to the identified continuous protruding obstacles;
target obstacle recognition: identifying a target obstacle in a travelable road area by using a target tracking method;
drivable region extraction: and calculating the relative safe distance between the vehicle and the target obstacle according to the position and speed information of the target obstacle, thereby extracting the travelable area of the vehicle.
In the step of identifying the target obstacle, point cloud data on the inner side of a road are screened, the motion trail of the same target is tracked through track establishment and multi-frame point association matching of a target initial point to obtain track information of the target, and the motion state of the target is estimated by utilizing the track information; the motion state of the target is estimated by using the track information, wherein the motion state comprises the vehicle speed, the course angle and the target size.
In the travelable region extraction step, an initial travelable region of the vehicle is extracted according to the stationary target obstacle, and then a final travelable region of the vehicle is extracted according to the moving target obstacle.
Example 5:
the method for detecting the automobile travelable region based on the 4D millimeter wave radar in the embodiment comprises the following steps,
screening effective target point clouds: screening effective target point clouds by utilizing point cloud data of the 4D millimeter wave radar after data preprocessing and point cloud feature identification;
road edge obstacle identification: identifying continuous protruding obstacles on two sides of a drivable road based on the effective target point cloud;
extracting a drivable road: extracting characteristics of a travelable road and a travelable road according to the identified continuous protruding obstacles;
target obstacle recognition: identifying a target obstacle in a travelable road area by using a target tracking method;
drivable region extraction: and calculating the relative safe distance between the vehicle and the target obstacle according to the position and speed information of the target obstacle, thereby extracting the travelable area of the vehicle.
In the travelable area extraction step, the relative safe distance between the vehicle and the static target obstacle is calculated according to the position of the static target obstacle (such as a static vehicle) and the collision time ttc1 of the vehicle and the static target obstacle, so that the initial travelable area of the vehicle is extracted; the calculation formula of the time ttc1 for collision with the stationary target obstacle is:
ttc1＝dis1/v，
dis1 indicates the relative distance between the host vehicle and the stationary target obstacle, and v indicates the movement speed of the host vehicle.
According to the position and the speed of a moving target obstacle (such as a pedestrian or a running vehicle), calculating the real-time relative safe distance between the vehicle and the moving target obstacle through the collision time ttc2 of the vehicle and the moving target obstacle, and extracting the final travelable area of the vehicle, namely the area represented by two curves in the figure 2; the calculation formula of the collision time ttc2 with the moving target obstacle is as follows:
ttc2＝dis2/dv，
dis2 indicates a real-time relative safe distance between the host vehicle and the moving target obstacle, and dv indicates a real-time relative speed between the host vehicle and the moving target obstacle.
When ttc1 is greater than 3s, the vehicle and the static target obstacle are considered to be within a relative safe distance; when ttc2 is greater than 3s, the vehicle and the moving target obstacle are considered to be within a real-time relative safety distance.
According to the technical scheme of the embodiment, the method for detecting the automobile travelable area based on the 4D millimeter wave radar is not only limited by external weather conditions and is slightly influenced by the surrounding environment, but also can effectively improve the accuracy of detection, effectively improve the diversity of application scenes and applicable environments, has small data processing burden and can effectively improve the detection efficiency; in addition, compared with the expensive laser radar, the cost of the equipment can be effectively reduced.
While the invention has been described in conjunction with the specific embodiments set forth above, it is evident that many alternatives, modifications, and variations will be apparent to those skilled in the art in light of the foregoing description. Accordingly, it is intended to embrace all such alternatives, modifications, and variations that fall within the spirit and scope of the appended claims.
Claims (10)
1. A method for detecting the automobile driving area based on a 4D millimeter wave radar is characterized by comprising the following steps,
screening effective target point clouds: screening effective target point clouds by utilizing point cloud data of the 4D millimeter wave radar after data preprocessing and point cloud feature identification;
road edge obstacle identification: identifying continuous protruding obstacles on two sides of a drivable road based on the effective target point cloud;
extracting a drivable road: extracting characteristics of a travelable road and a travelable road according to the identified continuous protruding obstacles;
target obstacle recognition: identifying a target obstacle in a travelable road area by using a target tracking method;
drivable region extraction: and calculating the relative safe distance between the vehicle and the target obstacle according to the position and speed information of the target obstacle, thereby extracting the travelable area of the vehicle.
2. The method for detecting a drivable area of a vehicle as claimed in claim 1, wherein, in the step of screening the valid target point clouds, the data preprocessing is: compensating the cloud historical data to relative coordinates of the current point cloud data at the detection moment of the point cloud data from the detection moment of the point cloud data through the vehicle running track, and screening the point cloud data in an effective range; clustering the point cloud data by a density clustering method, judging whether the point cloud data is a noise point or not by the number of clustering points, and filtering the noise point;
the point cloud features are identified as: and counting the clustering point number characteristics, the distribution of the calculated points, the length and width characteristics of the class and the average signal-to-noise ratio characteristics of the calculated class of the clustered point cloud.
3. The method according to claim 2, wherein if the number of clustering points is greater than 3, the current class is considered as a valid class, and otherwise, the current class is considered as a noise point, and the noise point is filtered.
4. The method for detecting the drivable area of the vehicle as claimed in claim 1, wherein in the step of identifying the obstacle along the road, point cloud data of geostationary points are screened, a curve approximating to the road edge or the balustrade is fitted to the points by a least squares fitting method, and whether a real road edge or a balustrade exists on the current road is judged by fitting shape and effect;
and when the ground speed is less than 0.5m/s, the data is regarded as point cloud data which is static to the ground.
5. The method for detecting a travelable area of an automobile according to claim 1, wherein in the travelable road extraction step, the width and shape of the road on which the automobile is traveling are estimated by identifying the left and right road edges or the balustrade, and the shape of the road ahead is predicted based on the shape of the balustrade.
6. The method for detecting the drivable area of the vehicle as claimed in claim 1, wherein in the step of identifying the target obstacle, the point cloud data of the inner side of the road are screened, the track of the initial point of the target is established and the multiple frames of points are matched in an associated manner, the movement track of the same target is tracked to obtain the track information of the target, and the movement state of the target is estimated by using the track information;
the motion state of the target is estimated by using the track information, wherein the motion state comprises the vehicle speed, the course angle and the target size.
7. The method according to claim 1, wherein in the travelable region extraction step, an initial travelable region of the host vehicle is extracted on the basis of the stationary target obstacle, and then a final travelable region of the host vehicle is extracted on the basis of the moving target obstacle.
8. The method according to claim 7, wherein in the travelable region extraction step, the initial travelable region of the host vehicle is extracted by calculating a relative safe distance of the host vehicle from the stationary target obstacle by a time ttc1 of collision with the stationary target obstacle, based on the position of the stationary target obstacle; the calculation formula of the time ttc1 for collision with the stationary target obstacle is:
ttc1 is dis1/v, dis1 indicates the relative distance between the host vehicle and the stationary target obstacle, and v indicates the movement speed of the host vehicle.
9. The method according to claim 7, wherein in the travelable region extraction step, the real-time relative safe distance of the host vehicle from the moving target obstacle is calculated by the time ttc2 of collision with the moving target obstacle according to the position and speed of the moving target obstacle, thereby extracting the final travelable region of the host vehicle; the calculation formula of the collision time ttc2 with the moving target obstacle is as follows:
ttc2 is dis2/dv, dis2 indicates the real-time relative safe distance between the host vehicle and the moving target obstacle, and dv indicates the real-time relative speed between the host vehicle and the moving target obstacle.
10. The automobile drivable area detection method as claimed in claim 8 or 9, characterized in that, when ttc1 > 3s, the own vehicle is considered to be within a relatively safe distance from a stationary target obstacle; when ttc2 is greater than 3s, the vehicle and the moving target obstacle are considered to be within a real-time relative safety distance.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202111573817.4A CN114415171A (en) | 2021-12-21 | 2021-12-21 | Automobile travelable area detection method based on 4D millimeter wave radar |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202111573817.4A CN114415171A (en) | 2021-12-21 | 2021-12-21 | Automobile travelable area detection method based on 4D millimeter wave radar |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN114415171A true CN114415171A (en) | 2022-04-29 |
Family
ID=81268462
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202111573817.4A Pending CN114415171A (en) | 2021-12-21 | 2021-12-21 | Automobile travelable area detection method based on 4D millimeter wave radar |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN114415171A (en) |
Cited By (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN115236674A (en) * | 2022-06-15 | 2022-10-25 | 北京踏歌智行科技有限公司 | Mining area environment sensing method based on 4D millimeter wave radar |
| CN116299300A (en) * | 2023-05-15 | 2023-06-23 | 北京集度科技有限公司 | Determination method and device for drivable area, computer equipment and storage medium |
| CN116500621A (en) * | 2023-06-27 | 2023-07-28 | 长沙莫之比智能科技有限公司 | Radar blind area early warning method based on double-subframe obstacle recognition |
| CN116533998A (en) * | 2023-07-04 | 2023-08-04 | 深圳海星智驾科技有限公司 | Automatic driving method, device, equipment, storage medium and vehicle of vehicle |
-
2021
- 2021-12-21 CN CN202111573817.4A patent/CN114415171A/en active Pending
Cited By (8)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN115236674A (en) * | 2022-06-15 | 2022-10-25 | 北京踏歌智行科技有限公司 | Mining area environment sensing method based on 4D millimeter wave radar |
| CN115236674B (en) * | 2022-06-15 | 2024-06-04 | 北京踏歌智行科技有限公司 | Mining area environment sensing method based on 4D millimeter wave radar |
| CN116299300A (en) * | 2023-05-15 | 2023-06-23 | 北京集度科技有限公司 | Determination method and device for drivable area, computer equipment and storage medium |
| CN116299300B (en) * | 2023-05-15 | 2023-08-08 | 北京集度科技有限公司 | Determination method and device for drivable area, computer equipment and storage medium |
| CN116500621A (en) * | 2023-06-27 | 2023-07-28 | 长沙莫之比智能科技有限公司 | Radar blind area early warning method based on double-subframe obstacle recognition |
| CN116500621B (en) * | 2023-06-27 | 2023-08-29 | 长沙莫之比智能科技有限公司 | Radar blind area early warning method based on double-subframe obstacle recognition |
| CN116533998A (en) * | 2023-07-04 | 2023-08-04 | 深圳海星智驾科技有限公司 | Automatic driving method, device, equipment, storage medium and vehicle of vehicle |
| CN116533998B (en) * | 2023-07-04 | 2023-09-29 | 深圳海星智驾科技有限公司 | Automatic driving method, device, equipment, storage medium and vehicle of vehicle |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| Narote et al. | A review of recent advances in lane detection and departure warning system | |
| WO2021259344A1 (en) | Vehicle detection method and device, vehicle, and storage medium | |
| CN114415171A (en) | Automobile travelable area detection method based on 4D millimeter wave radar | |
| Wijesoma et al. | Road-boundary detection and tracking using ladar sensing | |
| CN111369541B (en) | Vehicle detection method for intelligent automobile under severe weather condition | |
| CN106991389B (en) | Device and method for determining road edge | |
| JP3463858B2 (en) | Perimeter monitoring device and method | |
| US7046822B1 (en) | Method of detecting objects within a wide range of a road vehicle | |
| CN101608924B (en) | Method for detecting lane lines based on grayscale estimation and cascade Hough transform | |
| CN110077399A (en) | A kind of vehicle collision avoidance method merged based on roadmarking, wheel detection | |
| EP1361543B1 (en) | Determining object motion from optical flow analysis | |
| CN108398672B (en) | Forward-tilting 2D laser radar mobile scanning-based pavement and obstacle detection method | |
| Perrollaz et al. | Long range obstacle detection using laser scanner and stereovision | |
| CN111461088B (en) | Rail transit obstacle avoidance system based on image processing and target recognition | |
| CN110065494A (en) | A kind of vehicle collision avoidance method based on wheel detection | |
| WO2003001473A1 (en) | Vision-based collision threat detection system_ | |
| WO2015141247A1 (en) | In-vehicle image processing device and vehicle system using same | |
| CN107274678B (en) | A kind of night vehicle flowrate and model recognizing method based on Kinect | |
| CN110659552B (en) | Tramcar obstacle detection and alarm method | |
| CN113850102B (en) | Vehicle-mounted vision detection method and system based on millimeter wave radar assistance | |
| CN113568002A (en) | Rail transit active obstacle detection device based on laser and image data fusion | |
| KR20110001427A (en) | High speed road lane detection method based on extraction of roi-lb | |
| Knoeppel et al. | Robust vehicle detection at large distance using low resolution cameras | |
| Yang et al. | On-road collision warning based on multiple FOE segmentation using a dashboard camera | |
| Wang et al. | An improved hough transform method for detecting forward vehicle and lane in road |
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 |