CN113077551A - Occupation grid map construction method and device, electronic equipment and storage medium - Google Patents
Occupation grid map construction method and device, electronic equipment and storage medium Download PDFInfo
- Publication number
- CN113077551A CN113077551A CN202110338394.1A CN202110338394A CN113077551A CN 113077551 A CN113077551 A CN 113077551A CN 202110338394 A CN202110338394 A CN 202110338394A CN 113077551 A CN113077551 A CN 113077551A
- Authority
- CN
- China
- Prior art keywords
- grid
- grid map
- occupied
- occupation
- occupancy
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Pending
Links
- 238000010276 construction Methods 0.000 title claims abstract description 24
- 238000000034 method Methods 0.000 claims abstract description 24
- 230000000295 complement effect Effects 0.000 claims description 7
- 238000013507 mapping Methods 0.000 claims description 3
- 238000004891 communication Methods 0.000 description 7
- 230000009466 transformation Effects 0.000 description 5
- 238000010586 diagram Methods 0.000 description 4
- 239000011159 matrix material Substances 0.000 description 4
- 238000013519 translation Methods 0.000 description 4
- 230000009471 action Effects 0.000 description 3
- 238000004590 computer program Methods 0.000 description 3
- 230000008878 coupling Effects 0.000 description 3
- 238000010168 coupling process Methods 0.000 description 3
- 238000005859 coupling reaction Methods 0.000 description 3
- 230000002093 peripheral effect Effects 0.000 description 3
- 238000012545 processing Methods 0.000 description 3
- 238000011161 development Methods 0.000 description 2
- 230000004048 modification Effects 0.000 description 2
- 238000012986 modification Methods 0.000 description 2
- 238000003491 array Methods 0.000 description 1
- 238000013473 artificial intelligence Methods 0.000 description 1
- 238000006243 chemical reaction Methods 0.000 description 1
- 230000000694 effects Effects 0.000 description 1
- 230000006870 function Effects 0.000 description 1
- 230000006872 improvement Effects 0.000 description 1
- 230000003287 optical effect Effects 0.000 description 1
- 230000008569 process Effects 0.000 description 1
- 230000000717 retained effect Effects 0.000 description 1
- 230000011664 signaling Effects 0.000 description 1
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T17/00—Three dimensional [3D] modelling, e.g. data description of 3D objects
- G06T17/05—Geographic models
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T17/00—Three dimensional [3D] modelling, e.g. data description of 3D objects
- G06T17/20—Finite element generation, e.g. wire-frame surface description, tesselation
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T7/00—Image analysis
- G06T7/70—Determining position or orientation of objects or cameras
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T7/00—Image analysis
- G06T7/80—Analysis of captured images to determine intrinsic or extrinsic camera parameters, i.e. camera calibration
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T2207/00—Indexing scheme for image analysis or image enhancement
- G06T2207/10—Image acquisition modality
- G06T2207/10028—Range image; Depth image; 3D point clouds
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T2207/00—Indexing scheme for image analysis or image enhancement
- G06T2207/30—Subject of image; Context of image processing
- G06T2207/30244—Camera pose
Landscapes
- Engineering & Computer Science (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Theoretical Computer Science (AREA)
- Geometry (AREA)
- Software Systems (AREA)
- Computer Graphics (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Remote Sensing (AREA)
- Traffic Control Systems (AREA)
Abstract
The application provides an occupation grid map construction method, an occupation grid map construction device, electronic equipment and a storage medium, wherein the method comprises the following steps: acquiring the position and observation image of the unmanned aerial vehicle at the current moment; reserving occupied grids in an area corresponding to the grid map occupied at the previous moment and an area overlapping area corresponding to the position of the current moment, and constructing occupied grids of a newly increased area in the area corresponding to the position of the current moment compared with the area corresponding to the occupied grid map at the previous moment to obtain the occupied grid map at the current moment of the area corresponding to the position of the current moment, wherein the occupied grid map at the previous moment is the occupied grid map constructed at the previous moment, and the occupied grid map at the current moment is consistent with the occupied grid map at the previous moment in size; according to the observation image, the occupation probability of the occupied grid in the grid map at the current moment is updated, so that the problem that a large amount of storage space is occupied by the stored occupied grid map is solved.
Description
Technical Field
The present application relates to the field of artificial intelligence, and in particular, to a method and an apparatus for constructing an occupancy grid map, an electronic device, and a computer storage medium.
Background
Along with the continuous development of unmanned aerial vehicles, in order to ensure the autonomous safe flight of unmanned aerial vehicles, the unmanned aerial vehicle path needs to be planned. The occupation grid map is an important basis for unmanned plane path planning. However, when the existing drone performs grid map construction, all occupied grid maps (i.e., global grid maps) during the flight of the drone are stored. However, because the storage resources of the unmanned aerial vehicle are limited, a large amount of storage space can be occupied by storing the global grid map, and the performance of the unmanned aerial vehicle is further influenced.
Disclosure of Invention
In view of the above, an object of the present application is to provide an occupied grid map construction method, an occupied grid map construction device, an electronic device, and a computer storage medium, so as to solve the problem that storing a global grid map occupies a large storage space.
In a first aspect, the present invention provides an occupancy grid map construction method, including: acquiring the position and observation image of the unmanned aerial vehicle at the current moment; reserving an occupied grid in an area corresponding to a grid map occupied at the previous moment and an area overlapping area corresponding to the position of the current moment, constructing an occupied grid of a newly increased area in the area corresponding to the position of the current moment compared with the area corresponding to the occupied grid map at the previous moment, and obtaining the occupied grid map at the current moment of the area corresponding to the position of the current moment, wherein the occupied grid map at the previous moment is the occupied grid map constructed at the previous moment, and the occupied grid map at the current moment is consistent with the occupied grid map at the previous moment in size; and updating the occupation probability of the occupation grid in the current-time occupation grid map according to the observation image.
The embodiment of the application only reserves the occupied grid map of the periphery of the area where the unmanned aerial vehicle is located and establishes the occupied grid which is compared with the newly-added area at the last moment, and the occupied grid map which exceeds the preset area is not reserved, so that the size of the occupied grid map which is constructed at each moment is kept unchanged, the occupied probability of the occupied grid is updated according to the observation image, and the construction of the occupied grid map at the current moment is completed. By the aid of the construction method, the occupied grid maps of the peripheral areas of the unmanned aerial vehicle are only reserved, the occupied grid maps of other areas are deleted, the occupied grid maps constructed at each moment are guaranteed to be consistent in size, and the problem that the occupied grid maps occupy a large amount of storage space and further influence the performance of the unmanned aerial vehicle is solved.
In an optional embodiment, the updating, according to the observation image, the occupation probability of the occupation grid in the grid map at the current time includes: determining an observation region according to the observation image; and updating the occupation probability of the occupation grid in the observation area in the current-time occupation grid map according to the observation image.
In an alternative embodiment, the determining an observation region from the observation image includes: projecting an occupation grid in the occupation grid map at the current moment onto a plane where the observation image is located; determining a region of the observation image that occupies the grid and whose projection is located within the region of the observation image as the observation region.
In an optional embodiment, the updating, according to the observation image, an occupancy probability of an occupancy grid in the observation area in the current-time occupancy grid map includes: converting the observation image into a depth map; determining a three-dimensional point cloud coordinate of an obstacle in the observation image according to the depth map; and updating the occupation probability of the occupation grids in the observation area according to the three-dimensional point cloud coordinates. The occupation probability of the occupied grids in the observation area at the current moment is updated, so that the constructed occupied grid map can be updated in real time, the probability that the unmanned aerial vehicle collides with suddenly-appearing obstacles in the flight is reduced, and the flight safety of the unmanned aerial vehicle is improved.
In an alternative embodiment, the updating the occupancy probability of the occupancy grid in the observation region according to the three-dimensional point cloud coordinates includes: increasing the occupation probability of an occupation grid corresponding to the three-dimensional point cloud coordinate in the observation area by a first preset value; and reducing the occupation probability of an occupation grid which is complementary to the occupation grid corresponding to the three-dimensional point cloud coordinate and is positioned in the observation area by a second preset value. Through modifying the occupation probability of the occupation grid, the area with high occupation probability is avoided during path planning, and the flight safety of the unmanned aerial vehicle is ensured.
In a second aspect, the present invention provides an occupancy grid mapping apparatus, the apparatus comprising: the acquisition module is used for acquiring the current position and observation image of the unmanned aerial vehicle; the construction module is used for reserving an occupied grid in an area corresponding to a grid map occupied at the previous moment and an area overlapping area corresponding to the position of the current moment, constructing an occupied grid of a newly increased area in the area corresponding to the position of the current moment compared with the area corresponding to the occupied grid map at the previous moment, and obtaining the occupied grid map at the current moment of the area corresponding to the position of the current moment, wherein the occupied grid map at the previous moment is the occupied grid map constructed at the previous moment, and the occupied grid map at the current moment is consistent with the occupied grid map at the previous moment in size; and the updating module is used for updating the occupation probability of the occupation grid in the current-time occupation grid map according to the observation image.
In an optional embodiment, the updating module is configured to determine an observation region according to the observation image; updating the occupation probability of the occupation grid in the observation area in the current-time occupation grid map according to the observation image.
In an optional embodiment, the updating module is configured to project an occupation grid in the current-time occupation grid map onto a plane where the observation image is located; determining a region of the observation image that occupies the grid and has the projection located within the region as an observation region.
In an optional embodiment, the updating module is configured to convert the observation image into a depth map; determining a three-dimensional point cloud coordinate of an obstacle in the observation image according to the depth map; and updating the occupation probability of the occupation grids in the observation area according to the three-dimensional point cloud coordinates.
In an optional embodiment, the updating module is configured to increase an occupation probability of an occupation grid corresponding to the three-dimensional point cloud coordinate in the observation area by a first preset value; and reducing the occupation probability of an occupation grid which is complementary to the occupation grid corresponding to the three-dimensional point cloud coordinate and is positioned in the observation area by a second preset value.
In a third aspect, the present invention provides an electronic device comprising: a processor, a memory, and a bus; the processor and the memory are communicated with each other through the bus; the memory stores program instructions executable by the processor, the processor being capable of executing the method of any one of the preceding embodiments when invoked by the processor.
In a fourth aspect, the present invention provides a computer storage medium provided with computer instructions which, when executed by a computer, cause the computer to perform a method according to any one of the preceding embodiments.
Drawings
In order to more clearly illustrate the technical solutions of the embodiments of the present application, the drawings that are required to be used in the embodiments of the present application will be briefly described below, it should be understood that the following drawings only illustrate some embodiments of the present application and therefore should not be considered as limiting the scope, and that those skilled in the art can also obtain other related drawings based on the drawings without inventive efforts.
Fig. 1 is a flowchart of an occupancy grid map construction method according to an embodiment of the present application;
fig. 2 is a block diagram illustrating an occupancy grid map building apparatus according to an embodiment of the present disclosure;
fig. 3 is a block diagram of an electronic device according to an embodiment of the present disclosure.
Icon: 200-an occupancy grid map building means; 201-an acquisition module; 202-a building block; 203-an update module; 300-an electronic device; 301-a processor; 302-a communication interface; 303-a memory; 304-bus.
Detailed Description
The technical solutions in the embodiments of the present application will be described below with reference to the drawings in the embodiments of the present application.
Along with the continuous development of unmanned aerial vehicles, in order to ensure the autonomous safe flight of unmanned aerial vehicles, the unmanned aerial vehicle path needs to be planned. The occupation grid map is an important basis for unmanned plane path planning. However, when the existing drone performs grid map construction, all occupied grid maps (i.e., global grid maps) during the flight of the drone are stored. However, because the storage resources of the unmanned aerial vehicle are limited, a large amount of storage space can be occupied by storing the global grid map, and the performance of the unmanned aerial vehicle is further influenced.
Based on this, embodiments of the present application provide an occupancy grid map construction method, apparatus, electronic device, and computer storage medium, so as to solve the above problems.
The following describes embodiments of the present application in detail.
Referring to fig. 1, fig. 1 is a flowchart of an occupancy grid map building method according to an embodiment of the present application, where the occupancy grid map building method may include the following steps:
step S101: and acquiring the position and the observation image of the unmanned aerial vehicle at the current moment.
Step S102: and reserving the occupied grids in the area corresponding to the grid map occupied at the previous moment and the area overlapping area corresponding to the position of the current moment, and constructing the occupied grids of the newly added area in the area corresponding to the position of the current moment compared with the area corresponding to the grid map occupied at the previous moment to obtain the grid map occupied at the current moment of the area corresponding to the position of the current moment.
Step S103: and updating the occupation probability of the occupation grid in the occupation grid map at the current moment according to the observation image.
The above-described flow will be described in detail below.
Step S101: and acquiring the position and the observation image of the unmanned aerial vehicle at the current moment.
In the embodiment of the application, the unmanned aerial vehicle is provided with a binocular camera, and observation images of the unmanned aerial vehicle at the current moment can be acquired through the binocular camera. In addition, still be provided with the orientation module on the unmanned aerial vehicle for confirm the current positional information of unmanned aerial vehicle.
As an alternative embodiment, the binocular camera may be a forward-looking camera of the drone, for capturing an image in the forward direction of the drone as the observation image.
Step S102: and reserving the occupied grids in the area corresponding to the grid map occupied at the previous moment and the area overlapping area corresponding to the position of the current moment, and constructing the occupied grids of the newly added area in the area corresponding to the position of the current moment compared with the area corresponding to the grid map occupied at the previous moment to obtain the grid map occupied at the current moment of the area corresponding to the position of the current moment.
In the embodiment of the application, in order to reduce the storage overhead of the unmanned aerial vehicle storage occupying grid map, when the occupying grid map is constructed, only the occupying grid map around the position where the unmanned aerial vehicle is located is constructed, and the size of the constructed occupying grid map is fixed.
Specifically, the present embodiment is described by taking the number of occupied cells of the occupied cell map as 64 × 64 as an example. According to the position of the unmanned aerial vehicle, a 64 × 64 occupancy grid map is constructed by taking the position of the unmanned aerial vehicle as the center, each occupancy grid is a cubic grid with the side length of 0.3m, and the area covered by the occupancy grid map can be understood as an area covered by a cube consisting of 64 × 64 occupancy grids. With the movement of the unmanned aerial vehicle, the occupied grids in the area corresponding to the grid map occupied at the previous moment and the area overlapping area corresponding to the position at the current moment are reserved, and the occupied grids of the newly added area in the area corresponding to the position at the current moment and the area corresponding to the grid map occupied at the previous moment are built.
For ease of understanding, the following is explained as an example. Assuming that at a certain time, the drone has moved 0.3m to the right relative to the previous time, when the occupancy grid map is constructed at this time, the occupancy grids in the region where the previous time coincides with this time are reserved, that is, the occupancy grids except for the leftmost 1 × 64 occupancy grids in the occupancy grid map at the previous time are reserved, and 63 × 64 occupancy grids are reserved. Then, at the position of the shift direction, 1 × 64 new occupied grids are constructed, so that the occupied grid map at the current moment is still composed of 64 × 64 occupied grids. Since the unmanned aerial vehicle has moved 0.3m to the right with respect to the previous time, it can be understood that the occupied grid map at the current time has moved 0.3m to the right as a whole compared to the occupied grid map at the previous time.
Step S103: and updating the occupation probability of the occupation grid in the occupation grid map at the current moment according to the observation image.
In the embodiment of the present application, after the occupancy grid of the occupancy grid map is constructed, the occupancy probability of the occupancy grid in the occupancy grid map at the current time needs to be updated.
As an embodiment, step S103 may include the following steps:
firstly, determining an observation area according to an observation image;
and secondly, updating the occupation probability of the occupation grid in the observation area in the grid map at the current moment according to the observation image.
The embodiment of the application constructs the occupation grid map according to the binocular camera on the unmanned aerial vehicle. For a certain moment, the binocular camera acquires an observation image at the moment. From the observation image, the occupation probability of the occupation grid in the occupation grid map is updated. An observation image does not cover all the occupied grids of the occupied grid map, and therefore, the observation range of the drone at the current time is determined to determine which occupied grids can be observed in the current occupied grid map (i.e., which occupied grids are located in the observation image at the current time).
Specifically, determining the observation region according to the observation image may include the steps of:
projecting an occupying grid in the occupying grid map at the current moment onto a plane where an observation image is located;
the region of the projection occupying the grid within the region of the observation image is determined as the observation region.
In the embodiment of the present application, the coordinate system occupying the grid map is a coordinate system established with the unmanned aerial vehicle as an origin. When the observation area is determined, the coordinate system occupying the grid map needs to be converted into a navigation coordinate system (North East Down, NED coordinate system) for processing. Therefore, the transformation of the coordinate system needs to be performed by the following formula:
Pned＝(Plocal+offset)*cellsize
wherein, PnedCoordinates in the NED coordinate system for each of the occupancy grids; plocalCoordinates for each of the occupancy grids in an occupancy grid map coordinate system; the offset is the offset from the grid map coordinate system to the NED coordinate system; cellsize is the size of the occupied grid.
After the coordinates of each occupied grid under the NED coordinate system are determined, each occupied grid is projected onto a plane where an observation image is located according to the current position and posture of the unmanned aerial vehicle and camera parameters of a binocular camera, and the process of projection can be represented as:
Puv＝Kc*Tc_b*Tb_w*Pned
wherein, PuvCoordinates on the observation image for each of the occupancy grids; kcIs an internal reference of the binocular camera; t isc_bA transformation matrix (including rotation and translation) of the IMU coordinate system to the camera coordinate system for the drone; t isb_wIs the transformation matrix (including rotation and translation) of the NED coordinate system to the IMU coordinate system.
In the embodiment of the application, the upper left corner of the observation image is used as the origin of coordinates, the direction extending to the right side is the positive direction of the U axis, and the direction extending to the lower side is the positive direction of the V axis. Therefore, if the occupancy grid can be projected onto the observation image, the coordinates P of the occupancy grid on the observation imageuvMust be greater than 0 and less than the maximum value on the U-axis of the observed image in the coordinate system, and the V-axis component occupying the grid must also be greater than 0 and less than the maximum value on the V-axis of the observed image in the coordinate system. The occupancy grid that does not satisfy the above condition is not projected onto the observation image. Namely:
Puv>0 and Puv＜image_size,observable
else,Unobservable
The occupation grid projected in the region of the observation image is determined through the method, and the region corresponding to the occupation grid projected on the observation image is the observation region corresponding to the observation image.
And after the observation area is determined, updating the occupation probability of the occupation grids in the observation area in the current occupation grid map according to the observation image.
As an alternative embodiment, updating the occupation probability of the occupation grid in the observation area in the occupation grid map at the current time according to the observation image may include the following steps:
firstly, converting an observation image into a depth map;
secondly, determining a three-dimensional point cloud coordinate of the obstacle in the observation image according to the depth map;
and thirdly, updating the occupation probability of the occupation grids in the observation area according to the three-dimensional point cloud coordinates.
In the embodiment of the present application, the occupation probability of the occupation grid is updated according to the observation image, and it is first necessary to determine whether an obstacle exists in a region corresponding to the occupation grid.
Specifically, the observation image is first converted into a depth map. The observation image is converted into the depth map by using a Block Matching algorithm (BM algorithm). It should be noted that the above-mentioned conversion of the observation image into the depth map by using the BM algorithm is only one mode provided in the embodiment of the present application, and in addition, an SGBM algorithm, a GC algorithm, and the like may also be used, which is not limited in the present application.
After the depth map is determined, the depth map is further processed to obtain a three-dimensional point cloud coordinate, and the three-dimensional point cloud coordinate is matched with a coordinate corresponding to the occupied grid, so that the occupied grid can be determined to have the obstacles. Wherein, the three-dimensional point cloud coordinate determined from the depth map can be determined by the following method:
wherein, Pdepth_imageTwo-dimensional coordinates on the depth map; d is the depth value on the depth map;
is the inverse of the internal reference of the binocular camera; t isb_cA transformation matrix (including rotation and translation) for the camera coordinate system to the IMU coordinate system of the drone; t isw_bA transformation matrix (including rotation and translation) of the IMU coordinate system to NED coordinate system for the drone; pned3dIs the coordinates of the three-dimensional point cloud in the NED coordinate system as determined by the depth map.
And in the observation image, the position of the obstacle exists, and the three-dimensional point cloud coordinate can be recovered. Therefore, after the three-dimensional point cloud coordinate is determined from the depth map, the determined three-dimensional point cloud coordinate is matched with the coordinate corresponding to the occupied grid, if the coordinate corresponding to a certain occupied grid is matched with the coordinate of a certain three-dimensional point cloud, it is indicated that an obstacle exists in the area corresponding to the occupied grid, and the occupied probability of the occupied grid is increased, so that the occupied probability of the occupied grid is improved; if the coordinate corresponding to a certain occupying grid cannot be matched with any three-dimensional point cloud coordinate, the occupying grid is determined to have no obstacle, and the occupying probability of the occupying grid is reduced so as to reduce the occupying probability of the occupying grid. According to the principle of the occupancy grid map, the higher the occupancy probability of the occupancy grid, the higher the probability of indicating that an obstacle exists in the occupancy grid, and the lower the occupancy probability of the occupancy grid, the lower the probability of indicating that an obstacle exists in the occupancy grid.
As an alternative embodiment, updating the occupation probability of the occupation grid in the observation area according to the three-dimensional point cloud coordinates may include the following steps:
increasing the occupation probability of an occupation grid corresponding to the three-dimensional point cloud coordinate in the observation area by a first preset value;
and reducing the occupation probability of an occupation grid which is complementary to the occupation grid corresponding to the three-dimensional point cloud coordinate and is positioned in the observation area by a second preset value.
Specifically, the occupation probability of an occupation grid corresponding to the three-dimensional point cloud coordinate in the observation area is increased by a first preset value, wherein the first preset value may be 0.85. And when the three-dimensional point cloud coordinates in the observation area determine that the area corresponding to the occupied grid has the obstacle, increasing the occupied probability of the occupied grid by 0.85.
And reducing the occupation probability of an occupation grid which is complementary to the occupation grid corresponding to the three-dimensional point cloud coordinate and is positioned in the observation area by a second preset value, wherein the second preset value can be 0.2. The area without the obstacle does not have the three-dimensional point cloud coordinates, and therefore, the area corresponding to the occupancy grid complementary to the occupancy grid corresponding to the three-dimensional point cloud coordinates in the observation area (i.e., the area in the observation area without the occupancy grid corresponding to the three-dimensional point cloud) does not have the obstacle, and thus the occupancy probability of these occupancy grids is reduced by 0.2.
According to the principle of the occupancy grid map, the higher the occupancy probability of the occupancy grid, the higher the probability that an obstacle exists in the occupancy grid. Therefore, when the corresponding area of the occupied grid has the obstacle, the occupied probability of the occupied grid is increased, so that the unmanned aerial vehicle can avoid the corresponding area of the occupied grid during path planning, and the flight safety of the unmanned aerial vehicle is ensured. Accordingly, the lower the occupation probability of the occupation grid, the lower the probability that the occupation grid has an obstacle is. Therefore, for the occupation grid without the obstacle, the occupation probability of the occupation grid is reduced, so that the area can pass, and an important basis is provided for the unmanned aerial vehicle to plan the flight route.
It should be noted that the first preset value and the second preset value are only one implementation manner provided in the embodiment of the present application, and the first preset value may also be: 0.8, 0.9, 1.0, etc., the second preset value may also be: 0.15, 0.25, 0.3, etc., which the present application does not specifically limit.
The method for constructing the occupied grid map is the occupied grid map generated in real time, and the occupied grid map can be continuously generated according to the observation image shot by the binocular camera at each moment. The aforementioned method of updating the occupancy probability of the occupancy grid is for the occupancy grid within the observation area covered by the observation image. The occupied grid map constructed by the method is centered at the position of the unmanned aerial vehicle, and the constructed map range covers all the peripheral areas of the unmanned aerial vehicle. However, since the area shot by the binocular camera at each time cannot cover all areas around the unmanned aerial vehicle, the observation image does not cover each occupied grid of the occupied grid map generated at the current time. In other words, the occupancy grid in the occupancy grid map at each time may be divided into: an occupancy grid located in the observation region and an occupancy grid not located in the observation region.
For the occupancy grid located in the observation area, the aforementioned method can be used to update the occupancy probability. For an occupancy grid that is not located in the observation area, the following method may be employed for updating.
As an alternative embodiment, for an occupancy grid that is not in the observation area at the current time, if it is in the observation area of the occupancy grid map constructed at the previous time, the occupancy probability that the occupancy grid map constructed at the previous time is the occupancy grid is retained.
For an occupancy grid that is not in the observation region at the current time and that is never in the observation region of the occupancy grid map constructed at any previous time, the occupancy probability of the occupancy grid map is set to the highest probability. For an occupation grid which never appears in an observation image, whether an obstacle exists in a corresponding area is unclear, and in order to ensure the operation safety of the unmanned aerial vehicle, the occupation probability of the occupation grid is set to be the highest probability, so that the unmanned aerial vehicle is ensured to avoid the area corresponding to the occupation grid during path planning.
In addition, as an optional implementation manner, the method adopts a loop register to store the occupied grid map information, the storage space of the loop register is fixed, and the local occupied grid map is continuously updated iteratively by adopting the fixed storage space, so that the use of resources can be effectively reduced. When the occupied grid map is searched, the search can be completed only by shifting the pointer of the register, and the search speed is high.
The embodiment of the application provides a method for constructing an occupied grid map, wherein when the occupied grid map is constructed, occupied grids in an area corresponding to the occupied grid map at the previous moment and an area overlapping area corresponding to the position of the current moment are constructed, occupied grids of a newly increased area in the area corresponding to the position of the current moment and the area corresponding to the occupied grid map at the previous moment are constructed, in other words, only occupied grid maps around the area where an unmanned aerial vehicle is located are reserved, occupied grids of the newly increased area are constructed, the occupied grid map exceeding the preset area is not reserved, the size of the occupied grid map constructed at each moment is kept unchanged, then the occupied probability of the occupied grids is updated according to an observed image, and the construction of the occupied grid map at the current moment is completed. By the aid of the construction method, the occupied grid maps of the peripheral areas of the unmanned aerial vehicle are only reserved, the occupied grid maps of other areas are deleted, the occupied grid maps constructed at each moment are guaranteed to be consistent in size, and the problem that the occupied grid maps occupy a large amount of storage space and further influence the performance of the unmanned aerial vehicle is solved.
Based on the same inventive concept, the embodiment of the application also provides an occupying grid map constructing device. Referring to fig. 2, fig. 2 is a block diagram illustrating an occupancy grid map building apparatus 200 according to an embodiment of the present application, including:
an obtaining module 201, configured to obtain a current position and an observation image of the unmanned aerial vehicle;
a building module 202, configured to reserve an occupied grid in an area corresponding to a grid map occupied at a previous time and an area overlapping area corresponding to a position of the current time, and build an occupied grid of a newly added area in the area corresponding to the position of the current time, where the occupied grid map is an occupied grid map built at the previous time, and the occupied grid map at the current time is identical to the occupied grid map at the previous time in size;
and the updating module 203 is configured to update the occupation probability of the occupation grid in the current-time occupation grid map according to the observation image.
In an alternative embodiment, the updating module 203 is configured to determine an observation region according to the observation image; updating the occupation probability of the occupation grid in the observation area in the current-time occupation grid map according to the observation image.
In an optional embodiment, the updating module 203 is configured to project an occupation grid in the current-time occupation grid map onto a plane where the observation image is located; determining a region of the observation image that occupies the grid and has the projection located within the region as an observation region.
In an alternative embodiment, the updating module 203 is configured to convert the observation image into a depth map; determining a three-dimensional point cloud coordinate of an obstacle in the observation image according to the depth map; and updating the occupation probability of the occupation grids in the observation area according to the three-dimensional point cloud coordinates.
In an optional embodiment, the updating module 203 is configured to increase an occupation probability of an occupation grid corresponding to the three-dimensional point cloud coordinate in the observation area by a first preset value; and reducing the occupation probability of an occupation grid which is complementary to the occupation grid corresponding to the three-dimensional point cloud coordinate and is positioned in the observation area by a second preset value.
The occupying grid map constructing apparatus 200 provided in the embodiment of the present application has the same implementation principle and the same technical effect as those of the foregoing method embodiments, and for the sake of brief description, reference may be made to the corresponding content in the foregoing method embodiments where no mention is made in part of the apparatus embodiments.
Referring to fig. 3, fig. 3 is a schematic structural diagram of an electronic device 300 according to an embodiment of the present application, where the electronic device 300 includes: at least one processor 301, at least one communication interface 302, at least one memory 303, and at least one bus 304. Wherein the bus 304 is used for realizing direct connection communication of these components, the communication interface 302 is used for communicating signaling or data with other node devices, and the memory 303 stores machine readable instructions executable by the processor 301. When the electronic device 300 is in operation, the processor 301 communicates with the memory 303 via the bus 304, and the machine-readable instructions, when invoked by the processor 301, perform the occupancy grid mapping method described above.
The processor 301 may be an integrated circuit chip having signal processing capabilities. The Processor 301 may be a general-purpose Processor, including a Central Processing Unit (CPU), a Network Processor (NP), and the like; but also Digital Signal Processors (DSPs), Application Specific Integrated Circuits (ASICs), Field-Programmable Gate arrays (FPGAs) or other Programmable logic devices, discrete Gate or transistor logic devices, discrete hardware components. Which may implement or perform the various methods, steps, and logic blocks disclosed in the embodiments of the present application. A general purpose processor may be a microprocessor or the processor may be any conventional processor or the like.
The Memory 303 may include, but is not limited to, a Random Access Memory (RAM), a Read Only Memory (ROM), a Programmable Read Only Memory (PROM), an Erasable Read Only Memory (EPROM), an electrically Erasable Read Only Memory (EEPROM), and the like.
It will be appreciated that the configuration shown in fig. 3 is merely illustrative and that electronic device 300 may include more or fewer components than shown in fig. 3 or have a different configuration than shown in fig. 3. The components shown in fig. 3 may be implemented in hardware, software, or a combination thereof. In the embodiment of the present application, the electronic device 300 may be, but is not limited to, an entity device such as a desktop, a notebook computer, a smart phone, an intelligent wearable device, and a vehicle-mounted device, and may also be a virtual device such as a virtual machine. In addition, the electronic device 300 is not necessarily a single device, but may also be a combination of multiple devices, such as a server cluster, and the like.
In addition, the present application further provides a computer storage medium, which stores a computer program, and when the computer program is executed by a computer, the computer program executes the steps of the occupancy grid map construction method in the above embodiment.
In the embodiments provided in the present application, it should be understood that the disclosed apparatus and method may be implemented in other ways. The above-described embodiments of the apparatus are merely illustrative, and for example, the division of the units is only one logical division, and there may be other divisions when actually implemented, and for example, a plurality of units or components may be combined or integrated into another system, or some features may be omitted, or not executed. In addition, the shown or discussed mutual coupling or direct coupling or communication connection may be an indirect coupling or communication connection of devices or units through some communication interfaces, and may be in an electrical, mechanical or other form.
In addition, units described as separate parts may or may not be physically separate, and parts displayed as units may or may not be physical units, may be located in one place, or may be distributed on a plurality of network units. Some or all of the units can be selected according to actual needs to achieve the purpose of the solution of the embodiment.
Furthermore, the functional modules in the embodiments of the present application may be integrated together to form an independent part, or each module may exist separately, or two or more modules may be integrated to form an independent part.
It should be noted that the functions, if implemented in the form of software functional modules and sold or used as independent products, may be stored in a computer readable storage medium. Based on such understanding, the technical solution of the present application or portions thereof that substantially contribute to the prior art may be embodied in the form of a software product stored in a storage medium and including instructions for causing a computer device (which may be a personal computer, a server, or a network device) to execute all or part of the steps of the method according to the embodiments of the present application. And the aforementioned storage medium includes: various media capable of storing program codes, such as a usb disk, a removable hard disk, a Read-Only Memory (ROM), a Random Access Memory (RAM), a magnetic disk, or an optical disk.
In this document, relational terms such as first and second, and the like may be used solely to distinguish one entity or action from another entity or action without necessarily requiring or implying any actual such relationship or order between such entities or actions.
The above description is only an example of the present application and is not intended to limit the scope of the present application, and various modifications and changes may be made by those skilled in the art. Any modification, equivalent replacement, improvement and the like made within the spirit and principle of the present application shall be included in the protection scope of the present application.
Claims (10)
1. An occupancy grid map construction method, comprising:
acquiring the position and observation image of the unmanned aerial vehicle at the current moment;
reserving an occupied grid in an area corresponding to a grid map occupied at the previous moment and an area overlapping area corresponding to the position of the current moment, constructing an occupied grid of a newly increased area in the area corresponding to the position of the current moment compared with the area corresponding to the occupied grid map at the previous moment, and obtaining the occupied grid map at the current moment of the area corresponding to the position of the current moment, wherein the occupied grid map at the previous moment is the occupied grid map constructed at the previous moment, and the occupied grid map at the current moment is consistent with the occupied grid map at the previous moment in size;
and updating the occupation probability of the occupation grid in the current-time occupation grid map according to the observation image.
2. The occupancy grid map construction method according to claim 1, wherein the updating, from the observation image, the occupancy probability of the occupancy grid in the occupancy grid map at the current time includes:
determining an observation region according to the observation image;
and updating the occupation probability of the occupation grid in the observation area in the current-time occupation grid map according to the observation image.
3. The occupancy grid map construction method of claim 2, wherein the determining an observation region from the observation image comprises:
projecting an occupation grid in the occupation grid map at the current moment onto a plane where the observation image is located;
determining a region of the observation image that occupies the grid and whose projection is located within the region of the observation image as the observation region.
4. The occupancy grid map construction method according to claim 2, wherein the updating, from the observed image, the occupancy probability of the occupancy grid in the observed area in the current-time occupancy grid map includes:
converting the observation image into a depth map;
determining a three-dimensional point cloud coordinate of an obstacle in the observation image according to the depth map;
and updating the occupation probability of the occupation grids in the observation area according to the three-dimensional point cloud coordinates.
5. The occupancy grid map construction method of claim 4, wherein the updating the occupancy probability of the occupancy grid in the observation area from the three-dimensional point cloud coordinates comprises:
increasing the occupation probability of an occupation grid corresponding to the three-dimensional point cloud coordinate in the observation area by a first preset value;
and reducing the occupation probability of an occupation grid which is complementary to the occupation grid corresponding to the three-dimensional point cloud coordinate and is positioned in the observation area by a second preset value.
6. An occupancy grid mapping apparatus, the apparatus comprising:
the acquisition module is used for acquiring the current position and observation image of the unmanned aerial vehicle;
the construction module is used for reserving an occupied grid in an area corresponding to a grid map occupied at the previous moment and an area overlapping area corresponding to the position of the current moment, constructing an occupied grid of a newly increased area in the area corresponding to the position of the current moment compared with the area corresponding to the occupied grid map at the previous moment, and obtaining the occupied grid map at the current moment of the area corresponding to the position of the current moment, wherein the occupied grid map at the previous moment is the occupied grid map constructed at the previous moment, and the occupied grid map at the current moment is consistent with the occupied grid map at the previous moment in size;
and the updating module is used for updating the occupation probability of the occupation grid in the current-time occupation grid map according to the observation image.
7. The occupancy grid map construction device of claim 6, wherein the update module is configured to determine an observation region from the observation image; updating the occupation probability of the occupation grid in the observation area in the current-time occupation grid map according to the observation image.
8. The occupancy grid map building apparatus of claim 7, wherein the updating module is configured to project the occupancy grid in the current-time occupancy grid map onto a plane on which the observation image is located; determining a region of the observation image that occupies the grid and has the projection located within the region as an observation region.
9. An electronic device, comprising: a processor, a memory, and a bus;
the processor and the memory are communicated with each other through the bus;
the memory stores program instructions executable by the processor, the processor invoking the program instructions to perform the method of any one of claims 1-5.
10. A computer storage medium, characterized in that it is provided with computer instructions which, when executed by a computer, the computer performs the method according to any one of claims 1-5.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202110338394.1A CN113077551A (en) | 2021-03-30 | 2021-03-30 | Occupation grid map construction method and device, electronic equipment and storage medium |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202110338394.1A CN113077551A (en) | 2021-03-30 | 2021-03-30 | Occupation grid map construction method and device, electronic equipment and storage medium |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN113077551A true CN113077551A (en) | 2021-07-06 |
Family
ID=76611468
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202110338394.1A Pending CN113077551A (en) | 2021-03-30 | 2021-03-30 | Occupation grid map construction method and device, electronic equipment and storage medium |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN113077551A (en) |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN116088489B (en) * | 2021-11-05 | 2024-02-27 | 北京三快在线科技有限公司 | Grid map updating method and device |
Citations (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| WO2019080924A1 (en) * | 2017-10-26 | 2019-05-02 | 广州极飞科技有限公司 | Method for configuring navigation chart, obstacle avoidance method and device, terminal, unmanned aerial vehicle |
| CN111381585A (en) * | 2018-12-11 | 2020-07-07 | 北京图森智途科技有限公司 | Method and device for constructing occupation grid map and related equipment |
-
2021
- 2021-03-30 CN CN202110338394.1A patent/CN113077551A/en active Pending
Patent Citations (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| WO2019080924A1 (en) * | 2017-10-26 | 2019-05-02 | 广州极飞科技有限公司 | Method for configuring navigation chart, obstacle avoidance method and device, terminal, unmanned aerial vehicle |
| CN111381585A (en) * | 2018-12-11 | 2020-07-07 | 北京图森智途科技有限公司 | Method and device for constructing occupation grid map and related equipment |
Non-Patent Citations (1)
| Title |
|---|
| 秦玉鑫;张高峰;王裕清;: "针对复杂环境的模块化栅格地图构建算法", 控制工程, no. 10 * |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN116088489B (en) * | 2021-11-05 | 2024-02-27 | 北京三快在线科技有限公司 | Grid map updating method and device |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| EP3505866B1 (en) | Method and apparatus for creating map and positioning moving entity | |
| CN107223244B (en) | Localization method and device | |
| CN111210429B (en) | Point cloud data partitioning method and device and obstacle detection method and device | |
| CN110207716B (en) | Reference driving line rapid generation method, system, terminal and storage medium | |
| EP2385496A1 (en) | Extraction of 2D surfaces from a 3D point cloud | |
| CN111582054A (en) | Point cloud data processing method and device and obstacle detection method and device | |
| EP3620820A1 (en) | Simulation data augmentation method, device and terminal | |
| CN114565863A (en) | Real-time generation method, device, medium and equipment for orthophoto of unmanned aerial vehicle image | |
| CN112598673A (en) | Panorama segmentation method, device, electronic equipment and computer readable medium | |
| CN113077551A (en) | Occupation grid map construction method and device, electronic equipment and storage medium | |
| CN112036274A (en) | Driving region detection method and device, electronic equipment and storage medium | |
| US11734799B2 (en) | Point cloud feature enhancement and apparatus, computer device and storage medium | |
| CN115014328A (en) | Dynamic loading method, device, equipment and medium for grid map | |
| CN112150550B (en) | Fusion positioning method and device | |
| CN114743395B (en) | Signal lamp detection method, device, equipment and medium | |
| CN115661313A (en) | Point cloud map generation method, point cloud map generation device and storage medium | |
| CN115761119A (en) | Neighborhood voxel storage method and device, computer equipment and storage medium | |
| CN112669196B (en) | Method and equipment for optimizing data by factor graph in hardware acceleration engine | |
| CN115761425A (en) | Target detection method, device, terminal equipment and computer readable storage medium | |
| CN113077475B (en) | Visual positioning method, device, system, mobile robot and storage medium | |
| CN113808196A (en) | Plane fusion positioning method and device, electronic equipment and storage medium | |
| JP2023122614A (en) | Vehicle attitude estimating method, apparatus, electronic device, storage medium, and program | |
| CN117011481A (en) | Method and device for constructing three-dimensional map, electronic equipment and storage medium | |
| EP3621040A1 (en) | Data augmentation method, device and terminal | |
| CN113763468A (en) | Positioning method, device, system and storage medium |
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 | ||
| AD01 | Patent right deemed abandoned |
Effective date of abandoning: 20240621 |
|
| AD01 | Patent right deemed abandoned |