CN117115407B - Slope detection method, device, computer equipment and storage medium - Google Patents
Slope detection method, device, computer equipment and storage medium Download PDFInfo
- Publication number
- CN117115407B CN117115407B CN202311349715.3A CN202311349715A CN117115407B CN 117115407 B CN117115407 B CN 117115407B CN 202311349715 A CN202311349715 A CN 202311349715A CN 117115407 B CN117115407 B CN 117115407B
- Authority
- CN
- China
- Prior art keywords
- plane
- grid
- determining
- current
- area
- 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
- 238000001514 detection method Methods 0.000 title claims abstract description 53
- 238000000034 method Methods 0.000 claims abstract description 35
- 239000013598 vector Substances 0.000 claims description 94
- 238000004590 computer program Methods 0.000 claims description 24
- 238000012545 processing Methods 0.000 claims description 18
- 230000008569 process Effects 0.000 claims description 6
- 230000008859 change Effects 0.000 description 8
- 238000004891 communication Methods 0.000 description 8
- 238000010586 diagram Methods 0.000 description 5
- 230000001174 ascending effect Effects 0.000 description 4
- 230000003287 optical effect Effects 0.000 description 3
- 230000009471 action Effects 0.000 description 2
- 238000005516 engineering process Methods 0.000 description 2
- 230000006870 function Effects 0.000 description 2
- 230000006872 improvement Effects 0.000 description 2
- 238000005259 measurement Methods 0.000 description 2
- 230000003068 static effect Effects 0.000 description 2
- 230000000007 visual effect Effects 0.000 description 2
- OKTJSMMVPCPJKN-UHFFFAOYSA-N Carbon Chemical compound [C] OKTJSMMVPCPJKN-UHFFFAOYSA-N 0.000 description 1
- 238000004458 analytical method Methods 0.000 description 1
- 230000001413 cellular effect Effects 0.000 description 1
- 238000004140 cleaning Methods 0.000 description 1
- 238000011161 development Methods 0.000 description 1
- 229910021389 graphene Inorganic materials 0.000 description 1
- 238000003384 imaging method Methods 0.000 description 1
- 239000004973 liquid crystal related substance Substances 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 238000000513 principal component analysis Methods 0.000 description 1
- 238000012847 principal component analysis method Methods 0.000 description 1
- 238000005507 spraying Methods 0.000 description 1
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V10/00—Arrangements for image or video recognition or understanding
- G06V10/10—Image acquisition
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01V—GEOPHYSICS; GRAVITATIONAL MEASUREMENTS; DETECTING MASSES OR OBJECTS; TAGS
- G01V8/00—Prospecting or detecting by optical means
- G01V8/10—Detecting, e.g. by using light barriers
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V10/00—Arrangements for image or video recognition or understanding
- G06V10/20—Image preprocessing
- G06V10/22—Image preprocessing by selection of a specific region containing or referencing a pattern; Locating or processing of specific regions to guide the detection or recognition
Landscapes
- Engineering & Computer Science (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Multimedia (AREA)
- Theoretical Computer Science (AREA)
- Life Sciences & Earth Sciences (AREA)
- General Life Sciences & Earth Sciences (AREA)
- Geophysics (AREA)
- Image Analysis (AREA)
Abstract
The application relates to a slope detection method, a slope detection device, computer equipment and a storage medium. The method is applied to a robot, the robot comprises an image acquisition device, and the method comprises the following steps: acquiring a depth image acquired by image acquisition equipment, and determining at least two plane areas based on the depth image; determining a current plane area of the robot and an adjacent plane area corresponding to the current plane area in the at least two plane areas; determining a plane included angle and a plane height difference between the current plane area and the adjacent plane area; and determining a slope detection result corresponding to the adjacent plane area according to the plane included angle and the plane height difference. By adopting the method, the robot can timely and accurately identify the slope in the scene, and the risk that the robot cannot work normally due to the fact that the robot cannot identify the slope and changes the moving route is avoided.
Description
Technical Field
The present disclosure relates to the field of robotics, and in particular, to a method and apparatus for detecting a slope, a computer device, and a storage medium.
Background
With the rapid development of robot technology and the continuous improvement of life quality requirements of people, robots with autonomous navigation function gradually enter the daily life of people.
Due to the diversity of environments, the robot can not encounter a scene with a slope in the moving process of autonomous navigation, and if the robot can not identify the slope in the scene and can erroneously identify the slope as an obstacle or an unvented area, the robot can change the moving route of autonomous navigation, and the normal work of the robot can be affected. Obviously, having the ability to recognize the slope is one of the important functions to ensure that the robot maintains normal operation.
Disclosure of Invention
In view of the foregoing, it is desirable to provide a detection method, apparatus, computer device, computer-readable storage medium, and computer program product that can timely and accurately identify a slope in a scene.
In a first aspect, the present application provides a slope detection method applied to a robot, where the robot includes an image acquisition device. The method comprises the following steps:
acquiring a depth image acquired by image acquisition equipment, and determining at least two plane areas based on the depth image;
Determining a current plane area of the robot and an adjacent plane area corresponding to the current plane area in the at least two plane areas;
determining a plane included angle and a plane height difference between the current plane area and the adjacent plane area;
and determining a slope detection result corresponding to the adjacent plane area according to the plane included angle and the plane height difference.
In a second aspect, the present application further provides a slope detection device, which is applied to a robot, and the robot includes an image acquisition device. The device comprises:
the first determining module is used for acquiring the depth image acquired by the image acquisition equipment and determining at least two plane areas based on the depth image;
the second determining module is used for determining the current plane area of the robot and the adjacent plane areas corresponding to the current plane area in the at least two plane areas;
the third determining module is used for determining a plane included angle and a plane height difference between the current plane area and the adjacent plane area;
and the fourth determining module is used for determining a slope detection result corresponding to the adjacent plane area according to the plane included angle and the plane height difference.
In a third aspect, the present application also provides a computer device. The computer device comprises a memory storing a computer program and a processor which when executing the computer program performs the steps of:
Acquiring a depth image acquired by image acquisition equipment, and determining at least two plane areas based on the depth image;
determining a current plane area of the robot and an adjacent plane area corresponding to the current plane area in the at least two plane areas;
determining a plane included angle and a plane height difference between the current plane area and the adjacent plane area;
and determining a slope detection result corresponding to the adjacent plane area according to the plane included angle and the plane height difference.
In a fourth aspect, the present application also provides a computer-readable storage medium. The computer readable storage medium having stored thereon a computer program which when executed by a processor performs the steps of:
acquiring a depth image acquired by image acquisition equipment, and determining at least two plane areas based on the depth image;
determining a current plane area of the robot and an adjacent plane area corresponding to the current plane area in the at least two plane areas;
determining a plane included angle and a plane height difference between the current plane area and the adjacent plane area;
and determining a slope detection result corresponding to the adjacent plane area according to the plane included angle and the plane height difference.
In a fifth aspect, the present application also provides a computer program product. The computer program product comprises a computer program which, when executed by a processor, implements the steps of:
acquiring a depth image acquired by image acquisition equipment, and determining at least two plane areas based on the depth image;
determining a current plane area of the robot and an adjacent plane area corresponding to the current plane area in the at least two plane areas;
determining a plane included angle and a plane height difference between the current plane area and the adjacent plane area;
and determining a slope detection result corresponding to the adjacent plane area according to the plane included angle and the plane height difference.
The slope detection method, the slope detection device, the computer equipment, the storage medium and the computer program product acquire depth images acquired by the image acquisition equipment and determine at least two plane areas based on the depth images; determining a current plane area of the robot and an adjacent plane area corresponding to the current plane area in the at least two plane areas; determining a plane included angle and a plane height difference between the current plane area and the adjacent plane area; and determining a slope detection result corresponding to the adjacent plane area according to the plane included angle and the plane height difference. According to the method, the depth image acquired by the image acquisition equipment is used for determining at least two plane areas in the depth image, and the slope detection result is determined in the at least two plane areas, so that the robot can timely and accurately identify the slope in the scene, and the risk that the robot cannot work normally due to the fact that the robot cannot identify the slope and change the moving route is avoided.
Drawings
FIG. 1 is a diagram of an application environment of a ramp detection method in one embodiment;
FIG. 2 is a flow chart of a ramp detection method in one embodiment;
FIG. 3 is a schematic diagram of a determination result of at least two planar areas in one embodiment;
FIG. 4 is a block diagram of a ramp detection device in one embodiment;
FIG. 5 is an internal block diagram of a computer device in one embodiment;
fig. 6 is an internal structural view of a computer device in another embodiment.
Detailed Description
In order to make the objects, technical solutions and advantages of the present application more apparent, the present application will be further described in detail with reference to the accompanying drawings and examples. It should be understood that the specific embodiments described herein are for purposes of illustration only and are not intended to limit the present application.
It should be noted that in the following description, the terms "first, second, and third" are used only to distinguish similar objects and do not represent a specific ordering of the objects. It is understood that "first, second and third" may be interchanged with one another in the specific order or sequence in which the embodiments of the present application are described in other than the illustrated or described order where appropriate.
The slope detection method provided by the embodiment of the application may be applied to an application environment as shown in fig. 1, where the robot 102 performs a task on a working surface (or a working area). Wherein the robot 102 includes an image capturing device 1022, the robot 102 captures a depth image obtained by the image capturing device 1022, and determines at least two planar areas based on the depth image; the robot 102 determines a current plane area of the robot and an adjacent plane area corresponding to the current plane area in at least two plane areas; the robot 102 determines a plane angle and a plane height difference between the current plane area and the adjacent plane area; the robot 102 determines a slope detection result corresponding to the adjacent plane area according to the plane included angle and the plane height difference. The robot 102 may be, but is not limited to, various industrial robots (e.g., handling robots, palletizing robots, spraying robots, etc.), service robots (e.g., cleaning robots, distribution robots, mowing robots, etc.), or special robots (fire robots, underwater robots, security robots, etc.), which require autonomous movement.
In one embodiment, as shown in fig. 2, a slope detection method is provided, which is illustrated by way of example by the robot in fig. 1, which includes an image acquisition device, including steps S202 to S208 as follows:
S202, acquiring a depth image acquired by an image acquisition device, and determining at least two plane areas based on the depth image.
Among them, the image capturing device refers to a device capable of capturing and obtaining depth information, for example, various commonly used active depth cameras (structured light camera, toF camera, light field camera, etc.) and passive depth cameras (binocular camera, etc.).
Specifically, the image capturing device may be disposed at a top position in a front end direction of the robot, with the lens facing downward, and the front end direction of the robot corresponds to a moving direction when the robot moves, so that the depth image captured by the image capturing device of the robot includes a working surface image in the front end direction of the robot.
The depth image may comprise one or more frames of images. When the depth image includes a plurality of frames of images, the plurality of frames of images may be acquired by the image acquisition apparatus within a preset time, and for example, the plurality of frames of images may be acquired by the image acquisition apparatus within 1 second.
A falling area with the falling height being greater than or equal to a preset falling height does not exist in the plane area; planar areas, which may include floors, slopes, walls, or other areas.
Illustratively, as shown in (a) of fig. 3, a depth image including a planar area 1 as a work surface and a planar area 2 as a slope is shown, and as shown in (b) of fig. 3, the planar area 1 and the planar area 2 determined based on the depth image is shown.
In one embodiment, determining at least two planar areas based on the depth image includes: performing image enhancement processing on the depth image to obtain an enhanced depth image; at least two planar regions are determined based on the enhanced depth image.
In one embodiment, acquiring a depth image acquired by an image acquisition device and determining at least two planar areas based on the depth image comprises: acquiring current map data corresponding to a current position and a depth image acquired by image acquisition equipment; when the current map data includes a slope identification, at least two planar areas are determined based on the depth image.
S204, determining the current plane area of the robot and the adjacent plane areas corresponding to the current plane area in the at least two plane areas.
The current plane area is one plane area corresponding to an image position with a minimum distance value between the image positions corresponding to the depth image and the robot.
In one embodiment, determining a current planar area of a robot includes: determining a distance value between each image position corresponding to the depth image and the robot; determining a target image position according to the distance value between each image position and the robot, wherein the target image position is one image position with the minimum distance value between each image position and the robot; and determining the plane area corresponding to the target image position as the current plane area of the robot.
Adjacent planar areas corresponding to the current planar area refer to planar areas having a common point or a common side with the current planar area except the current planar area in at least two planar areas.
Illustratively, as shown in (b) of fig. 3, the distance value between the planar area 1 and the robot is smaller relative to the planar area 2, and thus the planar area 1 is the current planar area of the robot, that is, the current planar area of the robot is a plane; and there is a common edge between the planar area 2 and the planar area 1, so that the planar area 2 is an adjacent planar area corresponding to the current planar area, that is, the adjacent planar area corresponding to the current planar area is a slope.
S206, determining the plane included angle and the plane height difference between the current plane area and the adjacent plane area.
Specifically, taking the current plane area as a reference plane and the anticlockwise rotation direction as an example, the range of the plane included angle can be [0 degrees, 360 degrees ]); further, the range of the plane included angle between the adjacent plane region and the current plane region determined based on the depth image may be [0, 180 °) ] U (270 °,360 °.
Specifically, with the current planar area as a reference plane, the planar height difference may be an absolute value between the current planar area and the adjacent planar area.
S208, determining a slope detection result corresponding to the adjacent plane area according to the plane included angle and the plane height difference.
The slope detection result comprises that the adjacent plane area is a slope and the adjacent plane area is not a slope.
Specifically, when the plane included angle is 0, the adjacent plane area is coplanar with the current plane area; when the plane included angle is 90 degrees, the adjacent plane area is perpendicular to the current plane area, namely the adjacent plane area is a wall surface relative to the current plane area; when the plane height difference is greater than or equal to the preset height difference, the adjacent plane area is a plane area which can not be directly reached by the robot, such as a step. Thus, in one embodiment, determining a slope detection result corresponding to an adjacent planar area according to the planar included angle and the planar height difference includes: when the plane included angles are special included angles of 0 degrees, 90 degrees, 180 degrees, 270 degrees and the like, determining that the slope detection result corresponding to the adjacent plane area is non-slope of the adjacent plane area; when the plane included angle is a non-special included angle and the plane height difference is larger than or equal to the preset height difference, determining that the slope detection result corresponding to the adjacent plane area is a non-slope of the adjacent plane area, otherwise, determining that the slope detection result corresponding to the adjacent plane area is a slope when the plane included angle is a non-special included angle and the plane height difference is smaller than the preset height difference.
In one embodiment, when the ramp detection result is that the adjacent planar area is a ramp, after determining the ramp detection result corresponding to the adjacent planar area, the method further includes: the robot determines a target adjacent plane area, a target plane included angle between the current plane area and the target adjacent plane area and a moving speed corresponding to the robot, wherein the target plane area is an adjacent plane area with a minimum distance value with the robot; determining the slope type corresponding to the adjacent plane area according to the plane included angle or the slope detection result, wherein the slope type comprises an ascending slope and a descending slope; according to the type of the slope, a speed change signal is generated, the speed change signal is a speed gain signal or a speed attenuation signal, and the magnitude of the speed change signal and the magnitude of the included angle of the target plane are in positive correlation. Specifically, when the slope type is an ascending slope, generating a speed gain signal, wherein the magnitude of the speed gain signal and the magnitude of the included angle of the target plane are in positive correlation; and when the slope type is a downhill slope, generating a speed attenuation signal, wherein the magnitude of the speed attenuation signal and the magnitude of the included angle of the target plane are in positive correlation. Therefore, when the robot ascends a slope, the larger the included angle of the slope, namely the steeper the slope surface of the ascending slope, the larger speed gain signal is generated by the robot, so that the robot can complete the ascending slope action at a larger moving speed; when the robot descends, the larger the included angle of the slope, namely the steeper the slope surface of the descending slope, the robot generates a larger speed attenuation signal, so that the robot finishes the descending action at a smaller moving speed, and the falling accident or the collision accident of the robot caused by the overlarge speed of the robot when the robot descends is avoided.
In the slope detection method, a depth image acquired by image acquisition equipment is acquired, and at least two plane areas are determined based on the depth image; determining a current plane area of the robot and an adjacent plane area corresponding to the current plane area in the at least two plane areas; determining a plane included angle and a plane height difference between the current plane area and the adjacent plane area; and determining a slope detection result corresponding to the adjacent plane area according to the plane included angle and the plane height difference. According to the method, the depth image acquired by the image acquisition equipment is used for determining at least two plane areas in the depth image, and the slope detection result is determined in the at least two plane areas, so that the robot can timely and accurately identify the slope in the scene, and the risk that the robot cannot work normally due to the fact that the robot cannot identify the slope and change the moving route is avoided.
In one embodiment, the determining at least two planar areas based on the depth image includes:
performing point cloud rasterization processing on the depth image to obtain a plurality of grids;
determining the polar coordinates of each grid according to the equipment parameters corresponding to the image acquisition equipment;
Performing plane fitting processing on each grid based on the polar coordinates of each grid to obtain a plane normal vector and a three-dimensional coordinate of each grid;
establishing a normal vector histogram according to the plane normal vector of each grid, and determining a seed grid in the normal vector histogram;
and carrying out region growth based on the seed grids, the plane normal vector and the three-dimensional coordinates of each grid so as to obtain at least two plane regions.
The number of the grids obtained by performing point cloud rasterization processing on the depth image is determined according to the acquisition precision corresponding to the image acquisition equipment and the image size of the depth image.
In one embodiment, performing a point cloud rasterization process on a depth image to obtain a plurality of grids, including: acquiring acquisition precision and image size of a depth image corresponding to the image acquisition equipment; determining the grid size according to the acquisition precision; performing point cloud rasterization on the depth image based on the grid size to obtain a plurality of grids; the number of the plurality of grids is a ratio between the size of the depth image and the grid size. Further, the acquisition accuracy and the grid size are in a negative correlation.
For example, assuming that the image size of the depth image acquired by the image acquisition device is 160×120 pixels, the grid size determined according to the corresponding acquisition precision of the image acquisition device is 8×8 pixels, and therefore, the point cloud rasterization processing is performed on the depth image, and the number of the obtained multiple grids is (160/8) ×120/8) =20×15 grids.
Specifically, the device parameters corresponding to the image acquisition device include: a lateral offset Cx of the image capturing device optical axis in a lateral direction (i.e., in the X-axis direction) of the depth image coordinate system, a longitudinal offset Cy of the image capturing device optical axis in a longitudinal direction (i.e., in the Y-axis direction) of the depth image coordinate system, a lateral focal length Fx of the image capturing device in the lateral direction (i.e., in the X-axis direction) of the depth image coordinate system, a longitudinal focal length Fy of the image capturing device in the longitudinal direction (i.e., in the Y-axis direction) of the depth image coordinate system, and a depth d of each pixel in the depth image; the coordinates of each pixel in the depth image coordinate system are represented as (x, y), and the polar coordinates of each grid in the depth image in the image acquisition device polar coordinate system are represented as Pc (px, py, pz); the polar coordinates Pc (px, py, pz) of each grid are determined by the following formula:
specifically, the plane fitting processing of each grid based on the polar coordinates of each grid may be implemented by a principal component analysis method (Principal Component Analysis, PCA), so that the obtained planar normal vector of each grid is a feature vector corresponding to the minimum mean square error, and the obtained three-dimensional coordinates are the three-dimensional coordinate average values of the point clouds in the corresponding grids.
In this embodiment, a plurality of grids are obtained by performing point cloud rasterization on a depth image, and polar coordinates of each grid are determined according to equipment parameters corresponding to an image acquisition device, and then plane fitting processing is performed on each grid based on the polar coordinates of each grid to obtain plane normal vectors and three-dimensional coordinates of each grid, a normal vector histogram is built according to the plane normal vectors of each grid, and a seed grid is determined in the normal vector histogram, so that at least two plane areas are obtained by performing area growth based on the seed grid and the plane normal vectors and the three-dimensional coordinates of each grid. The obtained at least two plane areas are ensured to have accuracy and reliability, so that the slope detection result determined in the at least two plane areas is more accurate and reliable.
In one embodiment, determining a seed grid in the normal vector histogram includes:
determining the number of grids corresponding to each straight square grid included in the normal vector histogram, and determining the straight square grid with the number of grids meeting the first preset number condition as a target straight square grid;
and determining the mean square error corresponding to each grid included in the target straight square, and determining the grid with the mean square error meeting the preset average error condition as a seed grid.
Wherein the number of grids satisfies a first preset number condition, which may mean that the number of grids is greater than or equal to the preset number. Since the number of grids is greater than or equal to the preset number, the straight square lattice is more likely to be a large-area, namely more likely to be a plane area, so that at least two plane areas with large areas are more likely to be obtained during subsequent area growth.
The mean square error (Mean Squared Error, MSE) of the grid represents the degree of matching between the measured predicted value and the true value of the three-dimensional coordinates corresponding to the grid; the mean square error satisfies a preset mean square error condition, which may mean that the mean square error is minimum, so that the closest grid between the predicted value and the true value of the three-dimensional coordinate measurement is determined as the target grid.
Illustratively, the seed grid is a grid corresponding to a minimum mean square error among the number of straight squares greater than or equal to the preset number.
In the embodiment, the number of the straight square grids with the grid number larger than or equal to the preset number is determined as the target straight square grid, and determining a grid corresponding to the minimum mean square error in the target straight square lattice as a seed grid, therefore, the area growth is carried out on the seed grid with the most accurate measurement predicted value based on the three-dimensional coordinates in the straight square grid which is more likely to be a large area, at least two plane areas obtained through the area growth can have accuracy and reliability, and further the slope detection result obtained later also has accuracy and reliability.
In one embodiment, the growing of the area based on the seed grid and the planar normal vector and the three-dimensional coordinates of each grid to obtain at least two planar areas includes:
taking the seed grid as a current grid, and acquiring a neighborhood grid of the current grid;
determining a normal vector included angle between the current grid and the neighborhood grid according to the plane normal vector of the current grid and the plane normal vector of the neighborhood grid;
determining the plane drop between the current grid and the neighborhood grid according to the three-dimensional coordinates of the current grid and the three-dimensional coordinates of the neighborhood grid;
determining a grid to be grown in the neighborhood grid according to the normal vector included angle and the plane fall;
and taking the grid to be grown as a new current grid, acquiring a neighborhood grid of the new current grid, and performing region growth again until all grids in the target straight square grid where all the sub-grids are positioned are grown, so as to obtain at least two plane regions, wherein the number of the grids included in each plane region meets a second preset number condition.
The neighborhood grids of the current grid are part or all of the four neighborhood grids of the current grid, and are the neighborhood grids contained in the depth image in the four neighborhood grids of the current grid. Illustratively, when the current grid is a top corner grid in the depth image, then there are only two neighbor grids of the current grid; when the current grid is an edge non-vertex angle grid in the depth image, three neighbor grids of the current grid are arranged; and when the current grid is a non-edge non-vertex angle grid in the depth image, four neighbor grids of the current grid are provided.
Specifically, in the neighborhood grid, if the included angle of the target normal vector between the target grid and the current grid is smaller than the preset included angle and the plane drop between the target grid and the current grid is smaller than the preset plane drop, determining that the target grid and the current grid are grids on the same plane, namely determining that the target grid is a grid to be grown.
Illustratively, taking the seed grid as a current grid, and acquiring neighbor grids of the current grid as an A grid, a B grid, a C grid and a D grid respectively; determining normal vector included angles between the current grid and the A grid, the B grid, the C grid and the D grid respectively according to plane normal vectors of the current grid, the A grid, the B grid, the C grid and the D grid; determining the plane drop between the current grid and the A grid, the B grid, the C grid and the D grid respectively according to the three-dimensional coordinates of the current grid, the A grid, the B grid, the C grid and the D grid; the normal vector included angle between the current grid and the A grid is smaller than a preset included angle, and the plane drop between the current grid and the A grid is smaller than a preset plane drop, so that the current grid and the A grid are determined to be grids on the same plane, and the A grid is determined to be a grid to be grown; therefore, the grid A is determined to be a new current grid, the neighborhood grid of the grid A is obtained to perform region growing again, and the region growing mode of the grid A is consistent with the region growing mode of the seed grid in principle, so that details are not repeated until all grids in the depth image are grown, and a passable region in the depth image is obtained.
The second preset number of conditions may be the same as the first preset number of conditions; the number of grids satisfying the second preset number condition may mean that the number of grids is greater than or equal to the preset number.
In this embodiment, when the area growth is performed based on the current grid, the grid to be grown is determined in the neighborhood grid according to the normal vector included angle and the plane drop between the current grid and the neighborhood grid, so that the grid to be grown, which is determined in the neighborhood grid of each grid, is continuously used as a new current grid, and the area growth is performed again until each grid in the target straight square where each sub-grid is located is grown, and at least two plane areas are obtained. Further, at least two planar regions obtained after the region growth have accuracy and reliability.
In one embodiment, the building a normal vector histogram according to the planar normal vector of each grid includes:
determining the polar angle and the azimuth angle of each grid according to the plane normal vector of each grid;
discretizing the plane normal vector of each grid by an area equipartition spherical method according to the polar angle and the azimuth angle of each grid to obtain a discretization result;
and establishing a normal vector histogram according to the discretization result.
The plane normal vector of each grid is discretized, so that the number of grids at different positions can be intuitively presented, and the establishment efficiency of a normal vector histogram is improved.
The polar angle of the grid is denoted as θ, the azimuth angle of the grid is denoted as Φ, and the polar angle and azimuth angle of each grid are determined by the following formula:
specifically, according to the polar angle and the azimuth angle of each grid, the plane normal vector of each grid is discretized through an area equipartition spherical method, in order to treat the polar angle theta as the spherical latitude and the azimuth angle phi as the spherical longitude according to the longitude and latitude of the spherical surface, the polar angle theta and the azimuth angle phi of each grid are equipartition processed, the areas of the equipartition small blocks obtained by the equipartition processing of the azimuth angle phi are equal, the areas of the equipartition small blocks obtained by the equipartition processing of the polar angle theta are unequal, the discretization of the plane normal vector of each grid is realized, and therefore, the normal vector histogram established according to the discretization result can intuitively present the grid number in different straight squares.
In this embodiment, according to the plane normal vector of each grid, the polar angle and the azimuth angle of each grid are determined, and according to the polar angle and the azimuth angle of each grid, the plane normal vector of each grid is discretized by an area equipartition spherical method to obtain a discretization result, so that a normal vector histogram is built according to the discretization result, the building efficiency of the normal vector histogram is improved, the obtained normal vector histogram is more visual, the seed grid determined in the normal vector histogram in the follow-up process is more accurate and reliable, and the accuracy and reliability of at least two obtained plane areas are ensured.
In one embodiment, the determining the plane height difference between the current plane area and the adjacent plane area includes:
determining a target grid pair with a distance meeting a preset distance condition from a current plane area in an adjacent plane area;
a grid height difference between two grids included in the target grid pair is determined as a plane height difference between the current plane area and the adjacent plane area.
The distance between the adjacent plane area and the current plane area meets the preset distance condition, and the minimum distance value between the adjacent plane area and the current plane area can be obtained.
In one embodiment, determining a target grid pair in an adjacent planar region whose distance from the current planar region satisfies a preset distance condition includes: determining a first target grid with a minimum distance value from the current plane area in the adjacent plane area; determining a second target grid with a minimum distance value from the distance between the second target grid and the current plane area in the adjacent grids corresponding to the first target grid; the first target grid and the second target grid are determined as a target grid pair.
Specifically, the distance between the grid and the current plane area is determined by three-dimensional coordinates corresponding to the grid and a plane equation corresponding to the current plane area.
Specifically, determining the grid height difference between the two grids included in the target grid pair may be performed by three-dimensional coordinates corresponding to each of the two grids.
In the present embodiment, a target grid pair whose distance from the current planar area satisfies a preset distance condition is determined in the adjacent planar area, and a grid height difference between two grids included in the target grid pair is determined as a planar height difference between the current planar area and the adjacent planar area. By the grid height difference between the two grids included in the target grid pair, the plane height difference between the current plane area and the adjacent plane area can be determined more accurately, so that the robot can recognize the slope in the scene timely and accurately.
In one embodiment, determining the slope detection result corresponding to the adjacent plane area according to the plane included angle and the plane height difference includes:
when the plane included angle meets the preset included angle condition and the plane height difference meets the preset height difference condition, determining that the adjacent plane area is a slope.
Wherein, the plane contained angle satisfies the condition of preset contained angle, and the plane difference in height satisfies the condition of preset difference in height, means that the plane contained angle is greater than or equal to the preset contained angle, and the plane difference in height is less than the preset difference in height. Therefore, when the plane included angle is larger than or equal to the preset included angle and the plane height difference is smaller than the preset height difference, the adjacent plane area is determined to be a slope.
In this embodiment, when the plane included angle between the current plane area and the adjacent plane area is greater than or equal to the preset included angle, it indicates that the adjacent plane area is an inclined plane area with respect to the current plane area, and when the plane height difference between the current plane area and the adjacent plane area is smaller than the preset height difference, it indicates that the adjacent plane area is reachable with respect to the current plane area, that is, there is no step or drop area between the adjacent plane area and the current plane area, so that the adjacent plane area meeting the specific preset condition in this embodiment is determined as an inclined plane, so that the robot can timely and accurately identify the inclined plane in the scene, and meanwhile, the robot is prevented from being unable to identify the step or drop area and being unable to act according to the moving route.
The application process of the slope detection method is elaborated by taking a robot with an image acquisition device as an RGB-D camera as an execution main body, and the application process is specifically as follows:
(1) Determining at least two planar areas
The robot acquires a depth image acquired by an RGB-D camera, and performs point cloud rasterization on the depth image according to the acquisition precision and the image size of the depth image corresponding to the RGB-D camera to acquire a plurality of grids with corresponding numbers;
Determining the polar coordinates of each grid according to the equipment parameters corresponding to the RGB-D camera; performing plane fitting processing on each grid based on the polar coordinates of each grid to obtain a plane normal vector and a three-dimensional coordinate of each grid; determining the polar angle and the azimuth angle of each grid according to the plane normal vector of each grid;
discretizing the plane normal vector of each grid by an area equipartition spherical method according to the polar angle and the azimuth angle of each grid to obtain a discretization result; establishing a normal vector histogram according to the discretization result;
determining the grid number corresponding to each straight square lattice included in the normal vector histogram, and determining the straight square lattice with the largest grid number as a target straight square lattice;
determining a mean square error corresponding to each grid included in the target straight square, and determining a grid with the minimum mean square error as a seed grid; taking the seed grid as a current grid, and acquiring a neighborhood grid of the current grid;
determining a normal vector included angle between the current grid and the neighborhood grid according to the plane normal vector of the current grid and the plane normal vector of the neighborhood grid;
determining the plane drop between the current grid and the neighborhood grid according to the three-dimensional coordinates of the current grid and the three-dimensional coordinates of the neighborhood grid; determining a grid to be grown in the neighborhood grid according to the normal vector included angle and the plane fall;
Taking the grid to be grown as a new current grid, acquiring a neighborhood grid of the new current grid, and performing region growth again until all grids included in the target straight grid are grown to obtain a plane region, removing the target straight grid in the normal vector histogram, and determining whether the straight grid with the number larger than or equal to the preset number exists in the normal vector histogram; if so, namely, straight squares with the number of grids larger than or equal to the preset number still exist in the normal vector histogram, determining the straight square with the largest number as a new target straight square in the rest straight squares, determining seed grids in the new target straight square, and carrying out region growth again to obtain another plane region; if not, determining that the normal vector histogram does not have straight squares with the number of the grids being greater than or equal to the preset number, determining that all the straight squares included in the normal vector histogram are grown, and reserving the plane areas with the number of the grids being greater than or equal to the preset number, so as to obtain at least two plane areas.
(2) Determining a current plane area and adjacent plane areas corresponding to the current plane area
Searching a plane area corresponding to an image position with a minimum distance value between the image positions corresponding to the depth image and the robot, and determining the plane area as a current plane area;
And searching a plane area with a common edge or a common point between the current plane area and the plane area, and determining the plane area as an adjacent plane area corresponding to the adjacent of the current plane.
(3) Determining a plane angle and a plane height difference between a current plane area and an adjacent plane area
The robot respectively determines a plane normal vector of the current plane area and a plane normal vector of the adjacent plane area so as to determine a plane included angle between the current plane area and the adjacent plane area;
determining that a distance from a current planar region in the adjacent planar region satisfies a target grid pair having a minimum distance value; a grid height difference between two grids included in the target grid pair is determined as a plane height difference between the current plane area and the adjacent plane area.
(4) Determining slope detection results corresponding to adjacent plane areas
When the plane included angle is larger than the preset included angle and the plane height difference is smaller than the preset height difference, the robot determines that the adjacent plane area is a slope.
In this embodiment, at least two planar areas are determined in a depth image obtained by an RGB-D camera in an area growth manner, a planar area with a minimum distance value image position between the planar areas and the robot is determined as a current planar area of the robot, an adjacent planar area corresponding to the current planar area is determined, and then a slope detection result corresponding to the adjacent planar area is determined by determining a planar included angle and a planar height difference between the current planar area and the adjacent planar area, so that the robot can timely and accurately identify a slope in a scene.
It should be understood that, although the steps in the flowcharts related to the embodiments described above are sequentially shown as indicated by arrows, these steps are not necessarily sequentially performed in the order indicated by the arrows. The steps are not strictly limited to the order of execution unless explicitly recited herein, and the steps may be executed in other orders. Moreover, at least some of the steps in the flowcharts described in the above embodiments may include a plurality of steps or a plurality of stages, which are not necessarily performed at the same time, but may be performed at different times, and the order of the steps or stages is not necessarily performed sequentially, but may be performed alternately or alternately with at least some of the other steps or stages.
Based on the same inventive concept, embodiments of the present application also provide a slope detection apparatus for implementing the slope detection method referred to above. The implementation of the solution provided by the device is similar to that described in the above method, so the specific limitation of one or more embodiments of the slope detection device provided below may be referred to above for limitation of the slope detection method, and will not be repeated here.
In one embodiment, as shown in fig. 4, there is provided a slope detection apparatus, applied to a robot including an image acquisition device, the apparatus including: a first determination module 1002, a second determination module 1004, a third determination module 1006, and a fourth determination module 1008, wherein:
a first determining module 1002, configured to acquire a depth image acquired by an image acquisition device, and determine at least two planar areas based on the depth image.
The second determining module 1004 is configured to determine, in at least two planar areas, a current planar area of the robot and an adjacent planar area corresponding to the current planar area.
A third determining module 1006 is configured to determine a plane angle and a plane height difference between the current plane area and the adjacent plane area.
And a fourth determining module 1008, configured to determine a slope detection result corresponding to the adjacent planar area according to the plane included angle and the plane height difference.
In one embodiment, in determining at least two planar areas based on the depth image, the first determining module 1002 is further configured to:
performing point cloud rasterization processing on the depth image to obtain a plurality of grids;
determining the polar coordinates of each grid according to the equipment parameters corresponding to the image acquisition equipment;
Performing plane fitting processing on each grid based on the polar coordinates of each grid to obtain a plane normal vector and a three-dimensional coordinate of each grid;
establishing a normal vector histogram according to the plane normal vector of each grid, and determining a seed grid in the normal vector histogram;
and carrying out region growth based on the seed grids, the plane normal vector and the three-dimensional coordinates of each grid so as to obtain at least two plane regions.
In one embodiment, in determining the seed grid in the normal vector histogram, the first determination module 1002 described above is further configured to:
determining the number of grids corresponding to each straight square grid included in the normal vector histogram, and determining the straight square grid with the number of grids meeting the first preset number condition as a target straight square grid;
and determining the mean square error corresponding to each grid included in the target straight square, and determining the grid with the mean square error meeting the preset average error condition as a seed grid.
In one embodiment, the first determining module 1002 is further configured to, in terms of performing region growing based on the seed grid and the planar normal vector and the three-dimensional coordinates of each grid to obtain at least two planar regions:
taking the seed grid as a current grid, and acquiring a neighborhood grid of the current grid;
Determining a normal vector included angle between the current grid and the neighborhood grid according to the plane normal vector of the current grid and the plane normal vector of the neighborhood grid;
determining the plane drop between the current grid and the neighborhood grid according to the three-dimensional coordinates of the current grid and the three-dimensional coordinates of the neighborhood grid;
determining a grid to be grown in the neighborhood grid according to the normal vector included angle and the plane fall;
and taking the grid to be grown as a new current grid, acquiring a neighborhood grid of the new current grid, and performing region growth again until all grids in the target straight square grid where all the sub-grids are positioned are grown, so as to obtain at least two plane regions, wherein the number of the grids included in each plane region meets a second preset number condition.
In one embodiment, in terms of building a normal vector histogram from the planar normal vectors of each grid, the first determining module 1002 is further configured to:
determining the polar angle and the azimuth angle of each grid according to the plane normal vector of each grid;
discretizing the plane normal vector of each grid by an area equipartition spherical method according to the polar angle and the azimuth angle of each grid to obtain a discretization result;
and establishing a normal vector histogram according to the discretization result.
In one embodiment, in determining the plane height difference between the current plane area and the adjacent plane area, the third determining module 1006 is further configured to:
determining a target grid pair with a distance meeting a preset distance condition from a current plane area in an adjacent plane area;
a grid height difference between two grids included in the target grid pair is determined as a plane height difference between the current plane area and the adjacent plane area.
In one embodiment, in determining the slope detection result corresponding to the adjacent planar area according to the planar included angle and the planar height difference, the fourth determining module 1008 is further configured to:
when the plane included angle meets the preset included angle condition and the plane height difference meets the preset height difference condition, determining that the adjacent plane area is a slope.
The various modules in the ramp detection means described above may be implemented in whole or in part by software, hardware, and combinations thereof. The above modules may be embedded in hardware or may be independent of a processor in the computer device, or may be stored in software in a memory in the computer device, so that the processor may call and execute operations corresponding to the above modules.
In one embodiment, a computer device is provided, which may be a server, the internal structure of which may be as shown in fig. 5. The computer device includes a processor, a memory, an Input/Output interface (I/O) and a communication interface. The processor, the memory and the input/output interface are connected through a system bus, and the communication interface is connected to the system bus through the input/output interface. Wherein the processor of the computer device is configured to provide computing and control capabilities. The memory of the computer device includes a non-volatile storage medium and an internal memory. The non-volatile storage medium stores an operating system, computer programs, and a database. The internal memory provides an environment for the operation of the operating system and computer programs in the non-volatile storage media. The database of the computer device is for storing image data. The input/output interface of the computer device is used to exchange information between the processor and the external device. The communication interface of the computer device is used for communicating with an external terminal through a network connection. The computer program is executed by a processor to implement a ramp detection method.
In one embodiment, a computer device is provided, which may be a terminal, and the internal structure of which may be as shown in fig. 6. The computer device includes a processor, a memory, an input/output interface, a communication interface, a display unit, and an input means. The processor, the memory and the input/output interface are connected through a system bus, and the communication interface, the display unit and the input device are connected to the system bus through the input/output interface. Wherein the processor of the computer device is configured to provide computing and control capabilities. The memory of the computer device includes a non-volatile storage medium and an internal memory. The non-volatile storage medium stores an operating system and a computer program. The internal memory provides an environment for the operation of the operating system and computer programs in the non-volatile storage media. The input/output interface of the computer device is used to exchange information between the processor and the external device. The communication interface of the computer device is used for carrying out wired or wireless communication with an external terminal, and the wireless mode can be realized through WIFI, a mobile cellular network, NFC (near field communication) or other technologies. The computer program is executed by a processor to implement a ramp detection method. The display unit of the computer equipment is used for forming a visual picture, and can be a display screen, a projection device or a virtual reality imaging device, wherein the display screen can be a liquid crystal display screen or an electronic ink display screen, the input device of the computer equipment can be a touch layer covered on the display screen, can also be a key, a track ball or a touch pad arranged on a shell of the computer equipment, and can also be an external keyboard, a touch pad or a mouse and the like.
It will be appreciated by those skilled in the art that the structure shown in fig. 6 is merely a block diagram of some of the structures associated with the present application and is not limiting of the computer device to which the present application may be applied, and that a particular computer device may include more or fewer components than shown, or may combine certain components, or have a different arrangement of components.
In an embodiment, there is also provided a computer device comprising a memory and a processor, the memory having stored therein a computer program, the processor implementing the steps of the method embodiments described above when the computer program is executed.
In one embodiment, a computer-readable storage medium is provided, on which a computer program is stored which, when executed by a processor, carries out the steps of the method embodiments described above.
In an embodiment, a computer program product is provided, comprising a computer program which, when executed by a processor, implements the steps of the method embodiments described above.
It should be noted that, the data (including, but not limited to, data for analysis, stored data, displayed data, etc.) referred to in the present application are all information and data authorized by the user or sufficiently authorized by each party, and the collection, use and processing of the related data are required to comply with the related laws and regulations and standards of the related countries and regions.
Those skilled in the art will appreciate that implementing all or part of the above described methods may be accomplished by way of a computer program stored on a non-transitory computer readable storage medium, which when executed, may comprise the steps of the embodiments of the methods described above. Any reference to memory, database, or other medium used in the various embodiments provided herein may include at least one of non-volatile and volatile memory. The nonvolatile Memory may include Read-Only Memory (ROM), magnetic tape, floppy disk, flash Memory, optical Memory, high density embedded nonvolatile Memory, resistive random access Memory (ReRAM), magnetic random access Memory (Magnetoresistive Random Access Memory, MRAM), ferroelectric Memory (Ferroelectric Random Access Memory, FRAM), phase change Memory (Phase Change Memory, PCM), graphene Memory, and the like. Volatile memory can include random access memory (Random Access Memory, RAM) or external cache memory, and the like. By way of illustration, and not limitation, RAM can be in the form of a variety of forms, such as Static Random access memory (Static Random access memory AccessMemory, SRAM) or dynamic Random access memory (Dynamic Random Access Memory, DRAM), and the like. The databases referred to in the various embodiments provided herein may include at least one of relational databases and non-relational databases. The non-relational database may include, but is not limited to, a blockchain-based distributed database, and the like. The processors referred to in the embodiments provided herein may be general purpose processors, central processing units, graphics processors, digital signal processors, programmable logic units, quantum computing-based data processing logic units, etc., without being limited thereto.
The technical features of the above embodiments may be arbitrarily combined, and all possible combinations of the technical features in the above embodiments are not described for brevity of description, however, as long as there is no contradiction between the combinations of the technical features, they should be considered as the scope of the description.
The above examples only represent a few embodiments of the present application, which are described in more detail and are not to be construed as limiting the scope of the present application. It should be noted that it would be apparent to those skilled in the art that various modifications and improvements could be made without departing from the spirit of the present application, which would be within the scope of the present application. Accordingly, the scope of protection of the present application shall be subject to the appended claims.
Claims (10)
1. A slope detection method, characterized by being applied to a robot, the robot including an image acquisition device, the method comprising:
acquiring a depth image acquired by the image acquisition equipment, and determining at least two plane areas based on the depth image;
determining a current plane area of the robot and an adjacent plane area corresponding to the current plane area in at least two plane areas; a common point or a common edge exists between the adjacent plane area and the current plane area;
Determining a plane included angle and a plane height difference between the current plane area and the adjacent plane area;
when the plane included angle meets a preset included angle condition and the plane height difference meets a preset height difference condition, determining that the adjacent plane area is a slope;
wherein the determining the plane included angle and the plane height difference between the current plane area and the adjacent plane area includes:
respectively determining a plane normal vector of the current plane area and a plane normal vector of the adjacent plane area to determine a plane included angle between the current plane area and the adjacent plane area;
determining a target grid pair with the distance between the target grid pair and the current plane area meeting a preset distance condition in the adjacent plane area; a grid height difference between two grids included in the target grid pair is determined as a plane height difference between the current plane region and the adjacent plane region.
2. The method of claim 1, wherein the determining at least two planar areas based on the depth image comprises:
performing point cloud rasterization processing on the depth image to obtain a plurality of grids;
Determining the polar coordinates of each grid according to the equipment parameters corresponding to the image acquisition equipment;
performing plane fitting processing on each grid based on the polar coordinates of each grid to obtain a plane normal vector and a three-dimensional coordinate of each grid;
establishing a normal vector histogram according to the plane normal vector of each grid, and determining a seed grid in the normal vector histogram;
and carrying out region growth based on the seed grids, the plane normal vector and the three-dimensional coordinates of each grid so as to obtain at least two plane regions.
3. The method of claim 2, wherein the determining a seed grid in the normal vector histogram comprises:
determining the grid number corresponding to each straight square lattice included in the normal vector histogram, and determining the straight square lattice with the grid number meeting a first preset number condition as a target straight square lattice;
and determining the mean square error corresponding to each grid included in the target straight square, and determining the grid with the mean square error meeting the preset average error condition as the seed grid.
4. A method according to claim 3, wherein said performing region growing based on said seed grid and planar normal vectors and three-dimensional coordinates of each of said grids to obtain at least two of said planar regions comprises:
Taking the seed grid as a current grid, and acquiring a neighborhood grid of the current grid;
determining a normal vector included angle between the current grid and the neighborhood grid according to the plane normal vector of the current grid and the plane normal vector of the neighborhood grid;
determining the plane drop between the current grid and the neighborhood grid according to the three-dimensional coordinates of the current grid and the three-dimensional coordinates of the neighborhood grid;
determining a grid to be grown in the neighborhood grid according to the normal vector included angle and the plane drop;
and taking the grid to be grown as a new current grid, acquiring a neighborhood grid of the new current grid, and performing region growth again until each grid in the target straight square grid where each seed grid is positioned is grown, and obtaining at least two plane regions, wherein the number of grids included in each plane region meets a second preset number condition.
5. The method of claim 2, wherein said creating a normal vector histogram from planar normal vectors of each of said grids comprises:
determining the polar angle and the azimuth angle of each grid according to the plane normal vector of each grid;
Discretizing the plane normal vector of each grid by an area equipartition spherical method according to the polar angle and the azimuth angle of each grid to obtain a discretization result;
and establishing the normal vector histogram according to the discretization result.
6. The method according to any one of claims 1 to 5, wherein the image pickup device is disposed at a top position in a front end direction of the robot, and a lens is directed downward, the front end direction of the robot corresponding to a moving direction when the robot moves.
7. The method according to any one of claims 1-5, wherein the performing a point cloud rasterization process on the depth image to obtain a plurality of grids includes:
acquiring acquisition precision and image size of a depth image corresponding to the image acquisition equipment;
determining the grid size according to the acquisition precision;
performing point cloud rasterization processing on the depth image based on the grid size to obtain a plurality of grids; the number of the plurality of grids is a ratio between the size of the depth image and the grid size.
8. A slope detection apparatus for use in a robot, the robot including an image acquisition device, the apparatus comprising:
The first determining module is used for acquiring a depth image acquired by the image acquisition equipment and determining at least two plane areas based on the depth image;
the second determining module is used for determining a current plane area of the robot and an adjacent plane area corresponding to the current plane area in at least two plane areas; a common point or a common edge exists between the adjacent plane area and the current plane area;
a third determining module, configured to determine a plane angle and a plane height difference between the current plane area and the adjacent plane area;
a fourth determining module, configured to determine that the adjacent planar area is a slope when the plane included angle meets a preset included angle condition and the plane height difference meets a preset height difference condition;
wherein the determining the plane included angle and the plane height difference between the current plane area and the adjacent plane area includes:
respectively determining a plane normal vector of the current plane area and a plane normal vector of the adjacent plane area to determine a plane included angle between the current plane area and the adjacent plane area;
determining a target grid pair with the distance between the target grid pair and the current plane area meeting a preset distance condition in the adjacent plane area; a grid height difference between two grids included in the target grid pair is determined as a plane height difference between the current plane region and the adjacent plane region.
9. A computer device comprising a memory and a processor, the memory storing a computer program, characterized in that the processor implements the steps of the method of any of claims 1-7 when the computer program is executed.
10. A computer readable storage medium, on which a computer program is stored, characterized in that the computer program, when being executed by a processor, implements the steps of the method of any of claims 1-7.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202311349715.3A CN117115407B (en) | 2023-10-18 | 2023-10-18 | Slope detection method, device, computer equipment and storage medium |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202311349715.3A CN117115407B (en) | 2023-10-18 | 2023-10-18 | Slope detection method, device, computer equipment and storage medium |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN117115407A CN117115407A (en) | 2023-11-24 |
| CN117115407B true CN117115407B (en) | 2024-02-20 |
Family
ID=88805772
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202311349715.3A Active CN117115407B (en) | 2023-10-18 | 2023-10-18 | Slope detection method, device, computer equipment and storage medium |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN117115407B (en) |
Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN113112491A (en) * | 2021-04-27 | 2021-07-13 | 深圳市优必选科技股份有限公司 | Cliff detection method and device, robot and storage medium |
| CN114495043A (en) * | 2022-04-06 | 2022-05-13 | 北京中科慧眼科技有限公司 | Method and system for detecting up-and-down slope road conditions based on binocular vision system and intelligent terminal |
| CN114911235A (en) * | 2022-05-11 | 2022-08-16 | 深圳优地科技有限公司 | Robot anti-falling method, robot and storage medium |
| WO2023000337A1 (en) * | 2021-07-23 | 2023-01-26 | 华为技术有限公司 | Road gradient determination method and apparatus, lane line projection method and apparatus, and lane line display method and apparatus |
| WO2023056720A1 (en) * | 2021-10-09 | 2023-04-13 | 邦鼓思电子科技（上海）有限公司 | Visual boundary detection-based robot control system and method |
| CN116533240A (en) * | 2023-05-19 | 2023-08-04 | 上海擎朗智能科技有限公司 | Anti-drop method and device for robot, robot and storage medium |
-
2023
- 2023-10-18 CN CN202311349715.3A patent/CN117115407B/en active Active
Patent Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN113112491A (en) * | 2021-04-27 | 2021-07-13 | 深圳市优必选科技股份有限公司 | Cliff detection method and device, robot and storage medium |
| WO2023000337A1 (en) * | 2021-07-23 | 2023-01-26 | 华为技术有限公司 | Road gradient determination method and apparatus, lane line projection method and apparatus, and lane line display method and apparatus |
| WO2023056720A1 (en) * | 2021-10-09 | 2023-04-13 | 邦鼓思电子科技（上海）有限公司 | Visual boundary detection-based robot control system and method |
| CN114495043A (en) * | 2022-04-06 | 2022-05-13 | 北京中科慧眼科技有限公司 | Method and system for detecting up-and-down slope road conditions based on binocular vision system and intelligent terminal |
| CN114911235A (en) * | 2022-05-11 | 2022-08-16 | 深圳优地科技有限公司 | Robot anti-falling method, robot and storage medium |
| CN116533240A (en) * | 2023-05-19 | 2023-08-04 | 上海擎朗智能科技有限公司 | Anti-drop method and device for robot, robot and storage medium |
Also Published As
| Publication number | Publication date |
|---|---|
| CN117115407A (en) | 2023-11-24 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| US20220036574A1 (en) | System and method for obstacle avoidance | |
| US8199977B2 (en) | System and method for extraction of features from a 3-D point cloud | |
| US10636168B2 (en) | Image processing apparatus, method, and program | |
| Javanmardi et al. | Factors to evaluate capability of map for vehicle localization | |
| US10451403B2 (en) | Structure-based camera pose estimation system | |
| KR20160003776A (en) | Posture estimation method and robot | |
| US8369578B2 (en) | Method and system for position determination using image deformation | |
| US9858669B2 (en) | Optimized camera pose estimation system | |
| CN108491818B (en) | Detection method, device and the electronic equipment of target object | |
| CN113052907B (en) | Positioning method of mobile robot in dynamic environment | |
| US10902610B2 (en) | Moving object controller, landmark, and moving object control method | |
| CN108444452B (en) | Method and device for detecting longitude and latitude of target and three-dimensional space attitude of shooting device | |
| Dani et al. | Image moments for higher-level feature based navigation | |
| CN112102375B (en) | Point cloud registration reliability detection method and device and mobile intelligent equipment | |
| CN115371673A (en) | Binocular camera target positioning method based on Bundle Adjustment in unknown environment | |
| US20170091945A1 (en) | Point and sensor estimation from images | |
| CN117115407B (en) | Slope detection method, device, computer equipment and storage medium | |
| Sahdev et al. | Indoor localization in dynamic human environments using visual odometry and global pose refinement | |
| KR101783585B1 (en) | Method for managing plant facilities | |
| US20220276046A1 (en) | System and method for providing improved geocoded reference data to a 3d map representation | |
| CN117095342B (en) | Drop zone detection method, drop zone detection device, computer equipment and storage medium | |
| Emaduddin et al. | Accurate floor detection and segmentation for indoor navigation using RGB+ D and stereo cameras | |
| CN114943809A (en) | Map model generation method and device and storage medium | |
| Saeedi et al. | 3D localization and tracking in unknown environments | |
| CN114459467A (en) | Target positioning method based on VI-SLAM in unknown rescue environment |
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 |