CN111427059A - Method and system for detecting terrain in front of vehicle - Google Patents
Method and system for detecting terrain in front of vehicle Download PDFInfo
- Publication number
- CN111427059A CN111427059A CN202010201002.2A CN202010201002A CN111427059A CN 111427059 A CN111427059 A CN 111427059A CN 202010201002 A CN202010201002 A CN 202010201002A CN 111427059 A CN111427059 A CN 111427059A
- Authority
- CN
- China
- Prior art keywords
- point cloud
- cloud data
- point
- distance
- data
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Granted
Links
Images
Classifications
-
- G—PHYSICS
- 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
- 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
- G01S7/48—Details of systems according to groups G01S13/00, G01S15/00, G01S17/00 of systems according to group G01S17/00
- G01S7/4802—Details of systems according to groups G01S13/00, G01S15/00, G01S17/00 of systems according to group G01S17/00 using analysis of echo signal for target characterisation; Target signature; Target cross-section
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V20/00—Scenes; Scene-specific elements
- G06V20/50—Context or environment of the image
- G06V20/56—Context or environment of the image exterior to a vehicle by using sensors mounted on the vehicle
- G06V20/58—Recognition of moving objects or obstacles, e.g. vehicles or pedestrians; Recognition of traffic objects, e.g. traffic signs, traffic lights or roads
Landscapes
- Engineering & Computer Science (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Computer Networks & Wireless Communication (AREA)
- Radar, Positioning & Navigation (AREA)
- Remote Sensing (AREA)
- Multimedia (AREA)
- Theoretical Computer Science (AREA)
- Electromagnetism (AREA)
- Traffic Control Systems (AREA)
Abstract
The invention discloses a method and a system for detecting terrain in front of a vehicle, wherein the method comprises the following steps: acquiring a point cloud data set of a laser radar; cutting and filtering the point cloud data set to obtain a preprocessed data set; the preprocessed data set is spatially divided into a plurality of groups of data sets according to the advancing direction of the vehicle head by a third set distance, and the heights of a plurality of point cloud data in each group of data sets are sorted; selecting point cloud data of which the height is smaller than a plane distance threshold value in each group of data sets as a seed point set; determining a plane model according to the seed point set; determining each point cloud data in each group of data set as a ground point or a non-ground point according to the plane model; the ground points comprise ramp points that can pass through a ramp; the non-ground points are impenetrable obstacle points. According to the invention, the passable slope point cloud is fully considered, so that the accuracy of the detection of the terrain in front of the vehicle is improved.
Description
Technical Field
The invention relates to the technical field of vehicle front terrain scanning, in particular to a vehicle front terrain detection method and system.
Background
With the rapid development of automatic driving and assisted driving, environmental awareness is crucial. For the rapid measurement of the terrain in front of an emergency rescue vehicle (including an unmanned vehicle), the fact that the inclined plane can be detected as a passable ground point is of great significance.
At present, the main content of detecting the terrain in front of the vehicle is to detect the information of the road surface obstacle in front of the vehicle, but the non-ground points can provide useful information for detecting the information of the road surface obstacle in front of the vehicle, so the first step of detecting the information of the road surface obstacle in front of the vehicle is to remove the ground points and leave the non-ground points. The existing method for detecting the front terrain comprises the steps of researching on the terrain without a slope and judging the terrain with a passable slope, so that the problem that the detection of the front terrain is inaccurate is solved.
Disclosure of Invention
Based on the above, the invention aims to provide a method and a system for detecting the terrain in front of the vehicle, which fully consider the passable slope point cloud so as to improve the accuracy of detection of the terrain in front of the vehicle.
In order to achieve the above object, the present invention provides a method for detecting a terrain ahead of a vehicle, the method comprising:
step S1: acquiring a point cloud data set of a laser radar;
step S2: cutting and filtering the point cloud data set to obtain a preprocessed data set;
step S3: the preprocessed data set is spatially divided into a plurality of groups of data sets according to the advancing direction of the vehicle head by a third set distance, and the heights of a plurality of point cloud data in each group of data sets are sorted;
step S4: selecting point cloud data of which the height is smaller than a plane distance threshold value in each group of data sets as a seed point set;
step S5: determining a plane model according to the seed point set;
step S6: determining each point cloud data in each group of data set as a ground point or a non-ground point according to the plane model; the ground points comprise ramp points that can pass through a ramp; the non-ground points are impenetrable obstacle points.
Optionally, the point cloud data set is clipped and filtered to obtain a preprocessed data set, and the specific steps include:
step S21: cutting the point cloud data at a position larger than a first set distance in the point cloud data set to obtain a cutting data set; the first set distance is a distance from the laser radar;
step S22: filtering point cloud data at a position smaller than a second set distance in the cutting data set to obtain a preprocessed data set; the second set distance is a distance from the laser radar.
Optionally, the determining, according to the plane model, that each point cloud data in each group of data sets is a ground point or a non-ground point includes:
step S61: judging whether the distance from each point cloud data in each group of data set to the orthogonal projection of the plane model is smaller than a plane distance threshold value or not; if the point cloud data is smaller than the plane distance threshold value, the point cloud data is a ground point, and the step S62 is executed; if the point cloud data is larger than or equal to the plane distance threshold value, the point cloud data is a non-ground point, and the step S62 is executed;
step S62: judging whether the iteration times are larger than a set threshold value or not; if the iteration times are larger than or equal to a set threshold value, outputting ground points and non-ground points; and if the iteration number is smaller than the set threshold, adding one to the iteration number, adding the point cloud data into the seed point set, and returning to the step S5.
Optionally, a formula of a distance between each point cloud data in each group of data sets and an orthogonal projection of the plane model is as follows:
h＝|(x,y,z)*n|；
wherein h is the distance between each point cloud data and the orthogonal projection of the plane model, (x, y, z) is the three-dimensional coordinate of each point cloud data, and n is the normal vector of the plane.
Optionally, the determining the plane distance threshold includes:
step S71: calculating a height average value according to the heights of the point cloud data in the seed point set;
step S72: acquiring a seed height threshold;
step S73: and determining a plane distance threshold according to the height average value and the height threshold.
The invention also discloses a system for detecting the terrain in front of the vehicle, which comprises:
the acquisition module is used for acquiring a point cloud data set of the laser radar;
the preprocessing module is used for cutting and filtering the point cloud data set to obtain a preprocessed data set;
the segmentation module is used for spatially segmenting the preprocessed data set into a plurality of groups of data sets according to the advancing direction of the vehicle head by a third set distance and sequencing the heights of a plurality of point cloud data in each group of data sets;
the seed point set determining module is used for selecting point cloud data of which the height is less than a plane distance threshold value in each group of data sets as a seed point set;
the plane model determining module is used for determining a plane model according to the seed point set;
the ground point and non-ground point determining module is used for determining that each point cloud data in each group of data set is a ground point or a non-ground point according to the plane model; the ground points comprise ramp points that can pass through a ramp; the non-ground points are impenetrable obstacle points.
Optionally, the preprocessing module specifically includes:
the cutting unit is used for cutting the point cloud data at a position larger than a first set distance in the point cloud data set to obtain a cutting data set; the first set distance is a distance from the laser radar;
the filtering unit is used for filtering point cloud data at a position smaller than a second set distance in the cutting data set to obtain a preprocessing data set; the second set distance is a distance from the laser radar.
Optionally, the ground point and non-ground point determining module specifically includes:
the first judgment unit is used for judging whether the distance from each point cloud data in each group of data set to the orthogonal projection of the plane model is smaller than a plane distance threshold value or not; if the point cloud data is smaller than the plane distance threshold, the point cloud data is a ground point, and a second judgment unit is executed; if the point cloud data is larger than or equal to the plane distance threshold, the point cloud data is a non-ground point, and a second judgment unit is executed;
the second judgment unit is used for judging whether the iteration times are larger than a set threshold value or not; if the iteration times are larger than or equal to a set threshold value, outputting ground points and non-ground points; and if the iteration times are less than the set threshold, adding one to the iteration times, adding the point cloud data into the seed point set, and returning to the plane model determining module.
Optionally, a formula of a distance between each point cloud data in each group of data sets and an orthogonal projection of the plane model is as follows:
h＝|(x,y,z)*n|；
wherein h is the distance between each point cloud data and the orthogonal projection of the plane model, (x, y, z) is the three-dimensional coordinate of each point cloud data, and n is the normal vector of the plane.
Optionally, the system further includes: and the plane distance threshold value determining module is used for determining a plane distance threshold value.
According to the specific embodiment provided by the invention, the invention discloses the following technical effects:
the invention discloses a method and a system for detecting terrain in front of a vehicle, wherein the method comprises the following steps: acquiring a point cloud data set of a laser radar; cutting and filtering the point cloud data set to obtain a preprocessed data set; the preprocessed data set is spatially divided into a plurality of groups of data sets according to the advancing direction of the vehicle head by a third set distance, and the heights of a plurality of point cloud data in each group of data sets are sorted; selecting point cloud data of which the height is smaller than a plane distance threshold value in each group of data sets as a seed point set; determining a plane model according to the seed point set; determining each point cloud data in each group of data set as a ground point or a non-ground point according to the plane model; the ground points comprise ramp points that can pass through a ramp; the non-ground points are impenetrable obstacle points. According to the invention, the passable slope point cloud is fully considered, so that the accuracy of the detection of the terrain in front of the vehicle is improved.
Drawings
In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the drawings needed to be used in the embodiments will be briefly described below, and it is obvious that the drawings in the following description are only some embodiments of the present invention, and it is obvious for those skilled in the art to obtain other drawings without inventive exercise.
FIG. 1 is a flow chart of a method for detecting terrain ahead of a vehicle according to an embodiment of the present invention;
FIG. 2 is a schematic diagram of spatial segmentation according to an embodiment of the present invention;
FIG. 3 is a schematic top view of a spatial partition according to an embodiment of the present invention;
FIG. 4 is a schematic diagram illustrating a point cloud classification determination according to an embodiment of the present invention
Fig. 5 is a structural diagram of a vehicle front terrain detection system according to an embodiment of the present invention.
Detailed Description
The technical solutions in the embodiments of the present invention will be clearly and completely described below with reference to the drawings in the embodiments of the present invention, and it is obvious that the described embodiments are only a part of the embodiments of the present invention, and not all of the embodiments. All other embodiments, which can be derived by a person skilled in the art from the embodiments given herein without making any creative effort, shall fall within the protection scope of the present invention.
The invention aims to provide a method and a system for detecting the terrain in front of a vehicle, which fully consider the passable slope point cloud so as to improve the accuracy of detecting the terrain in front of the vehicle.
In order to make the aforementioned objects, features and advantages of the present invention comprehensible, embodiments accompanied with figures are described in further detail below.
The radar is arranged in the center of the vehicle head, so that the terrain in front of the vehicle can be better scanned. In the embodiment of the invention, the bicycle is placed in the center of a bicycle head, and the height is 2 meters. The user can place the radar according to own demand.
Fig. 1 is a flowchart of a method for detecting a terrain in front of a vehicle according to an embodiment of the present invention, and as shown in fig. 1, the present invention provides a method for detecting a terrain in front of a vehicle, the method including:
step S1: acquiring a point cloud data set of a laser radar; the point cloud data set includes a plurality of point cloud data.
Step S2: and cutting and filtering the point cloud data set to obtain a preprocessed data set.
Step S3: and spatially dividing the preprocessed data set into a plurality of groups of data sets according to the advancing direction of the vehicle head by a third set distance, and sequencing the heights of a plurality of point cloud data in each group of data sets.
Step S4: and selecting the point cloud data of which the height is less than the plane distance threshold value in each group of data sets as a seed point set.
Step S5: and determining a plane model according to the seed point set.
Step S6: determining each point cloud data in each group of data set as a ground point or a non-ground point according to the plane model; the ground points comprise ramp points that can pass through a ramp; the non-ground points are impenetrable obstacle points.
The individual steps are discussed in detail below:
step S2: the point cloud data set is cut and filtered to obtain a preprocessed data set, and the specific steps include:
step S21: cutting the point cloud data at a position larger than a first set distance in the point cloud data set to obtain a cutting data set; the first set distance is a distance from the laser radar.
Step S22: filtering point cloud data at a position smaller than a second set distance in the cutting data set to obtain a preprocessed data set; the second set distance is a distance from the laser radar.
The user may crop and filter the point cloud data set according to the height at which the radar is placed and the size of the vehicle and the area of interest, so the first set distance and the second set distance are not fixed values, the first set distance is set to 5 meters, and the second set distance is set to 1 meter.
Step S3: and spatially dividing the preprocessed data set into a plurality of groups of data sets according to the advancing direction of the vehicle head by a third set distance, and sequencing the heights of a plurality of point cloud data in each group of data sets.
Referring to fig. 2 and 3, in the embodiment of the present invention, the vehicle head is divided according to the division distance of 4 meters. The user may set the distance of the spatial division according to the size of the vehicle passing through the slope. After the segmentation is finished, sequencing each group of point cloud data according to the z direction, namely the height.
Step S5: determining a plane model according to the seed point set; the planar model is represented as:
ax+by+cz+d＝0；
wherein, the covariance matrix C describes the walking condition of the seed point set, and the covariance matrix is
Wherein the content of the first and second substances,
average of all point cloud data, s ∈ R3x3For the seed point set, a, b, and c are three Singular vectors, which can be obtained by Singular Value Decomposition (SVD), and these three Singular vectors describe the spread of the point cloud data in three main directions. Since it is a plane model, the normal vector n perpendicular to the plane represents the direction with the smallest variance, and can be found by calculating the singular vector with the smallest singular value, i.e., n ═ a, b, c]T. d can be determined by substituting the average of the seed point set
To be determined.
Step S6: determining that each point cloud data in each group of data set is a ground point or a non-ground point according to the plane model, wherein the specific steps comprise:
step S61: judging whether the distance from each point cloud data in each group of data set to the orthogonal projection of the plane model is smaller than a plane distance threshold value or not; if the point cloud data is smaller than the plane distance threshold value, the point cloud data is a ground point, and the step S62 is executed; if the point cloud data is greater than or equal to the plane distance threshold, the point cloud data is a non-ground point, and step S62 is executed, as shown in detail in fig. 4.
The distance between each point cloud data in each group of data sets and the orthogonal projection of the plane model is represented by the following formula: h | (x, y, z) × n |; wherein h is a distance of an orthogonal projection of each point cloud data to the plane model, and (x, y, z) are three-dimensional coordinates of each point cloud data, and n is [ a, b, c ]]TAnd a, b and c are three singular vectors of the plane model.
Step S62: judging whether the iteration times are larger than a set threshold value or not; if the iteration times are larger than or equal to a set threshold value, outputting ground points and non-ground points; if the iteration times are smaller than the set threshold, adding one to the iteration times, adding the point cloud data to the seed point set, and returning to the step S5; the ground points comprise a slope point cloud that can pass through a slope; the non-ground points are impenetrable obstacle points.
Fig. 5 is a structural diagram of a vehicle front terrain detecting system according to an embodiment of the present invention, and as shown in fig. 5, the present invention further discloses a vehicle front terrain detecting system, which includes:
the acquisition module 1 is used for acquiring a point cloud data set of the laser radar;
the preprocessing module 2 is used for cutting and filtering the point cloud data set to obtain a preprocessed data set;
the segmentation module 3 is used for spatially segmenting the preprocessed data set into a plurality of groups of data sets according to the advancing direction of the vehicle head by a third set distance and sequencing the heights of a plurality of point cloud data in each group of data sets;
the seed point set determining module 4 is used for selecting point cloud data of which the height is less than a plane distance threshold value in each group of data sets as a seed point set;
a plane model determining module 5, configured to determine a plane model according to the seed point set;
the ground point and non-ground point determining module 6 is used for determining that cloud data of each point in each group of data set are ground points or non-ground points according to the plane model; the ground points comprise ramp points that can pass through a ramp; the non-ground points are impenetrable obstacle points.
As an embodiment, the preprocessing module 2 of the present invention specifically includes:
the cutting unit is used for cutting the point cloud data at a position larger than a first set distance in the point cloud data set to obtain a cutting data set; the first set distance is a distance from the laser radar.
The filtering unit is used for filtering point cloud data at a position smaller than a second set distance in the cutting data set to obtain a preprocessing data set; the second set distance is a distance from the laser radar.
As an implementation manner, the ground point and non-ground point determining module 6 of the present invention specifically includes:
the first judgment unit is used for judging whether the distance from each point cloud data in each group of data set to the orthogonal projection of the plane model is smaller than a plane distance threshold value or not; if the point cloud data is smaller than the plane distance threshold, the point cloud data is a ground point, and a second judgment unit is executed; and if the point cloud data is larger than or equal to the plane distance threshold, the point cloud data is a non-ground point, and a second judgment unit is executed.
The second judgment unit is used for judging whether the iteration times are larger than a set threshold value or not; if the iteration times are larger than or equal to a set threshold value, outputting ground points and non-ground points; and if the iteration times are less than the set threshold, adding one to the iteration times, adding the point cloud data into the seed point set, and returning to the plane model determining module.
As an embodiment, a formula of a distance between each point cloud data in each group of data sets and an orthogonal projection of the plane model in the invention is as follows:
h＝|(x,y,z)*n|；
wherein h is the distance between each point cloud data and the orthogonal projection of the plane model, (x, y, z) is the three-dimensional coordinate of each point cloud data, and n is the normal vector of the plane.
As an embodiment, the system of the present invention further includes: and the plane distance threshold value determining module is used for determining a plane distance threshold value.
The plane distance threshold determination module specifically includes:
and the height average value calculating unit is used for calculating the height average value according to the heights of the point cloud data in the seed point set.
An obtaining unit, configured to obtain a seed height threshold.
And the plane distance threshold value determining unit is used for determining a plane distance threshold value according to the height average value and the height threshold value.
The embodiments in the present description are described in a progressive manner, each embodiment focuses on differences from other embodiments, and the same and similar parts among the embodiments are referred to each other.
The principles and embodiments of the present invention have been described herein using specific examples, which are provided only to help understand the method and the core concept of the present invention; meanwhile, for a person skilled in the art, according to the idea of the present invention, the specific embodiments and the application range may be changed. In view of the above, the present disclosure should not be construed as limiting the invention.
Claims (10)
1. A method of detecting an anterior terrain, the method comprising:
step S1: acquiring a point cloud data set of a laser radar;
step S2: cutting and filtering the point cloud data set to obtain a preprocessed data set;
step S3: the preprocessed data set is spatially divided into a plurality of groups of data sets according to the advancing direction of the vehicle head by a third set distance, and the heights of a plurality of point cloud data in each group of data sets are sorted;
step S4: selecting point cloud data of which the height is smaller than a plane distance threshold value in each group of data sets as a seed point set;
step S5: determining a plane model according to the seed point set;
step S6: determining each point cloud data in each group of data set as a ground point or a non-ground point according to the plane model; the ground points comprise ramp points that can pass through a ramp; the non-ground points are impenetrable obstacle points.
2. The method for detecting the terrain of the vehicle front according to claim 1, characterized in that the point cloud data set is cropped and filtered to obtain a preprocessed data set, and the specific steps include:
step S21: cutting the point cloud data at a position larger than a first set distance in the point cloud data set to obtain a cutting data set; the first set distance is a distance from the laser radar;
step S22: filtering point cloud data at a position smaller than a second set distance in the cutting data set to obtain a preprocessed data set; the second set distance is a distance from the laser radar.
3. The method according to claim 1, wherein the step of determining, based on the plane model, whether each cloud data in each set of data sets is a ground point or a non-ground point comprises:
step S61: judging whether the distance from each point cloud data in each group of data set to the orthogonal projection of the plane model is smaller than a plane distance threshold value or not; if the point cloud data is smaller than the plane distance threshold value, the point cloud data is a ground point, and the step S62 is executed; if the point cloud data is larger than or equal to the plane distance threshold value, the point cloud data is a non-ground point, and the step S62 is executed;
step S62: judging whether the iteration times are larger than a set threshold value or not; if the iteration times are larger than or equal to a set threshold value, outputting ground points and non-ground points; and if the iteration number is smaller than the set threshold, adding one to the iteration number, adding the point cloud data into the seed point set, and returning to the step S5.
4. The method according to claim 3, wherein the distance from each point cloud data in each group of data sets to the orthogonal projection of the plane model is represented by the formula:
h＝|(x,y,z)*n|；
wherein h is the distance between each point cloud data and the orthogonal projection of the plane model, (x, y, z) is the three-dimensional coordinate of each point cloud data, and n is the normal vector of the plane.
5. The method of detecting the terrain of a vehicle according to claim 4, characterized in that the determination of the plane distance threshold comprises the specific steps of:
step S71: calculating a height average value according to the heights of the point cloud data in the seed point set;
step S72: acquiring a seed height threshold;
step S73: and determining a plane distance threshold according to the height average value and the height threshold.
6. An anterior terrain sensing system, characterized in that the system comprises:
the acquisition module is used for acquiring a point cloud data set of the laser radar;
the preprocessing module is used for cutting and filtering the point cloud data set to obtain a preprocessed data set;
the segmentation module is used for spatially segmenting the preprocessed data set into a plurality of groups of data sets according to the advancing direction of the vehicle head by a third set distance and sequencing the heights of a plurality of point cloud data in each group of data sets;
the seed point set determining module is used for selecting point cloud data of which the height is less than a plane distance threshold value in each group of data sets as a seed point set;
the plane model determining module is used for determining a plane model according to the seed point set;
the ground point and non-ground point determining module is used for determining that each point cloud data in each group of data set is a ground point or a non-ground point according to the plane model; the ground points comprise ramp points that can pass through a ramp; the non-ground points are impenetrable obstacle points.
7. The system of claim 6, wherein the preprocessing module specifically includes:
the cutting unit is used for cutting the point cloud data at a position larger than a first set distance in the point cloud data set to obtain a cutting data set; the first set distance is a distance from the laser radar;
the filtering unit is used for filtering point cloud data at a position smaller than a second set distance in the cutting data set to obtain a preprocessing data set; the second set distance is a distance from the laser radar.
8. The system of claim 6, wherein the ground point and non-ground point determination module includes:
the first judgment unit is used for judging whether the distance from each point cloud data in each group of data set to the orthogonal projection of the plane model is smaller than a plane distance threshold value or not; if the point cloud data is smaller than the plane distance threshold, the point cloud data is a ground point, and a second judgment unit is executed; if the point cloud data is larger than or equal to the plane distance threshold, the point cloud data is a non-ground point, and a second judgment unit is executed;
the second judgment unit is used for judging whether the iteration times are larger than a set threshold value or not; if the iteration times are larger than or equal to a set threshold value, outputting ground points and non-ground points; and if the iteration times are less than the set threshold, adding one to the iteration times, adding the point cloud data into the seed point set, and returning to the plane model determining module.
9. The system of claim 8, wherein the distance of each point cloud data in each set of data sets to the orthogonal projection of the planar model is formulated as:
h＝|(x,y,z)*n|；
wherein h is the distance between each point cloud data and the orthogonal projection of the plane model, (x, y, z) is the three-dimensional coordinate of each point cloud data, and n is the normal vector of the plane.
10. The vehicle anterior terrain detection system of claim 8, wherein the system further comprises: and the plane distance threshold value determining module is used for determining a plane distance threshold value.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202010201002.2A CN111427059B (en) | 2020-03-20 | 2020-03-20 | Method and system for detecting terrain in front of vehicle |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202010201002.2A CN111427059B (en) | 2020-03-20 | 2020-03-20 | Method and system for detecting terrain in front of vehicle |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN111427059A true CN111427059A (en) | 2020-07-17 |
| CN111427059B CN111427059B (en) | 2022-02-11 |
Family
ID=71548367
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202010201002.2A Active CN111427059B (en) | 2020-03-20 | 2020-03-20 | Method and system for detecting terrain in front of vehicle |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN111427059B (en) |
Cited By (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN112508970A (en) * | 2020-12-16 | 2021-03-16 | 北京超星未来科技有限公司 | Point cloud data segmentation method and device |
| CN113239726A (en) * | 2021-04-06 | 2021-08-10 | 北京航空航天大学杭州创新研究院 | Target detection method and device based on coloring point cloud and electronic equipment |
Citations (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN105488770A (en) * | 2015-12-11 | 2016-04-13 | 中国测绘科学研究院 | Object-oriented airborne laser radar point cloud filtering method |
| CN108189637A (en) * | 2017-12-29 | 2018-06-22 | 燕山大学 | A kind of data fusion method of emergency management and rescue vehicle Active Suspensions actuator controlled quentity controlled variable |
| CN108873013A (en) * | 2018-06-27 | 2018-11-23 | 江苏大学 | A kind of road using multi-line laser radar can traffic areas acquisition methods |
| WO2019162327A2 (en) * | 2018-02-23 | 2019-08-29 | Audi Ag | Method for determining a distance between a motor vehicle and an object |
| CN110335352A (en) * | 2019-07-04 | 2019-10-15 | 山东科技大学 | A kind of biradical first multiresolution level filtering method of airborne laser radar point cloud |
| CN110782472A (en) * | 2019-09-05 | 2020-02-11 | 腾讯科技（深圳）有限公司 | Point cloud ground point identification method and device |
| CN110865394A (en) * | 2019-09-24 | 2020-03-06 | 中国船舶重工集团公司第七0七研究所 | Target classification system based on laser radar data and data processing method thereof |
-
2020
- 2020-03-20 CN CN202010201002.2A patent/CN111427059B/en active Active
Patent Citations (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN105488770A (en) * | 2015-12-11 | 2016-04-13 | 中国测绘科学研究院 | Object-oriented airborne laser radar point cloud filtering method |
| CN108189637A (en) * | 2017-12-29 | 2018-06-22 | 燕山大学 | A kind of data fusion method of emergency management and rescue vehicle Active Suspensions actuator controlled quentity controlled variable |
| WO2019162327A2 (en) * | 2018-02-23 | 2019-08-29 | Audi Ag | Method for determining a distance between a motor vehicle and an object |
| CN108873013A (en) * | 2018-06-27 | 2018-11-23 | 江苏大学 | A kind of road using multi-line laser radar can traffic areas acquisition methods |
| CN110335352A (en) * | 2019-07-04 | 2019-10-15 | 山东科技大学 | A kind of biradical first multiresolution level filtering method of airborne laser radar point cloud |
| CN110782472A (en) * | 2019-09-05 | 2020-02-11 | 腾讯科技（深圳）有限公司 | Point cloud ground point identification method and device |
| CN110865394A (en) * | 2019-09-24 | 2020-03-06 | 中国船舶重工集团公司第七0七研究所 | Target classification system based on laser radar data and data processing method thereof |
Cited By (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN112508970A (en) * | 2020-12-16 | 2021-03-16 | 北京超星未来科技有限公司 | Point cloud data segmentation method and device |
| CN112508970B (en) * | 2020-12-16 | 2023-08-25 | 北京超星未来科技有限公司 | Point cloud data segmentation method and device |
| CN113239726A (en) * | 2021-04-06 | 2021-08-10 | 北京航空航天大学杭州创新研究院 | Target detection method and device based on coloring point cloud and electronic equipment |
| CN113239726B (en) * | 2021-04-06 | 2022-11-08 | 北京航空航天大学杭州创新研究院 | Target detection method and device based on coloring point cloud and electronic equipment |
Also Published As
| Publication number | Publication date |
|---|---|
| CN111427059B (en) | 2022-02-11 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN107272021B (en) | Object detection using radar and visually defined image detection areas | |
| CN110992683B (en) | Dynamic image perception-based intersection blind area early warning method and system | |
| CN109100741B (en) | Target detection method based on 3D laser radar and image data | |
| CN110988912B (en) | Road target and distance detection method, system and device for automatic driving vehicle | |
| CN107341453B (en) | Lane line extraction method and device | |
| Oniga et al. | Processing dense stereo data using elevation maps: Road surface, traffic isle, and obstacle detection | |
| CN110531376B (en) | Obstacle detection and tracking method for port unmanned vehicle | |
| CN101975951B (en) | Field environment barrier detection method fusing distance and image information | |
| JP5157067B2 (en) | Automatic travel map creation device and automatic travel device. | |
| US9373043B2 (en) | Method and apparatus for detecting road partition | |
| CN111179300A (en) | Method, apparatus, system, device and storage medium for obstacle detection | |
| CN111427059B (en) | Method and system for detecting terrain in front of vehicle | |
| EP2637126B1 (en) | Method and apparatus for detecting vehicle | |
| CN113176585A (en) | Three-dimensional laser radar-based road surface anomaly detection method | |
| CN101408978B (en) | Method and apparatus for detecting barrier based on monocular vision | |
| KR101822373B1 (en) | Apparatus and method for detecting object | |
| CN104541302A (en) | Range-cued object segmentation system and method | |
| CN111553252A (en) | Road pedestrian automatic identification and positioning method based on deep learning and U-V parallax algorithm | |
| CN108108667B (en) | A kind of front vehicles fast ranging method based on narrow baseline binocular vision | |
| CN101629820A (en) | Road-edge detection | |
| CN110197173B (en) | Road edge detection method based on binocular vision | |
| CN110674705A (en) | Small-sized obstacle detection method and device based on multi-line laser radar | |
| CN115032651A (en) | Target detection method based on fusion of laser radar and machine vision | |
| Kellner et al. | Road curb detection based on different elevation mapping techniques | |
| DE102011078615A1 (en) | Object detector for detecting pedestrian in surrounding area of vehicle, has pedestrian identification portion for identifying whether window image is image depicting object, and identification model selected to identify object |
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 |