CN114910050A - Unmanned aerial vehicle visual positioning method based on grid map - Google Patents
Unmanned aerial vehicle visual positioning method based on grid map Download PDFInfo
- Publication number
- CN114910050A CN114910050A CN202210723563.8A CN202210723563A CN114910050A CN 114910050 A CN114910050 A CN 114910050A CN 202210723563 A CN202210723563 A CN 202210723563A CN 114910050 A CN114910050 A CN 114910050A
- Authority
- CN
- China
- Prior art keywords
- aerial vehicle
- unmanned aerial
- grid map
- grid
- matching
- 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
- 238000000034 method Methods 0.000 title claims abstract description 29
- 230000000007 visual effect Effects 0.000 title claims abstract description 18
- 238000006243 chemical reaction Methods 0.000 claims abstract description 4
- 230000009466 transformation Effects 0.000 claims description 8
- 238000009434 installation Methods 0.000 description 3
- 238000012986 modification Methods 0.000 description 3
- 230000004048 modification Effects 0.000 description 3
- 230000009286 beneficial effect Effects 0.000 description 2
- 238000004590 computer program Methods 0.000 description 2
- 238000010276 construction Methods 0.000 description 1
- 230000007547 defect Effects 0.000 description 1
Images
Classifications
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01C—MEASURING DISTANCES, LEVELS OR BEARINGS; SURVEYING; NAVIGATION; GYROSCOPIC INSTRUMENTS; PHOTOGRAMMETRY OR VIDEOGRAMMETRY
- G01C11/00—Photogrammetry or videogrammetry, e.g. stereogrammetry; Photographic surveying
Landscapes
- Engineering & Computer Science (AREA)
- Multimedia (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Radar, Positioning & Navigation (AREA)
- Remote Sensing (AREA)
- Navigation (AREA)
Abstract
The invention discloses an unmanned aerial vehicle visual positioning method based on a grid map, which belongs to the field of unmanned aerial vehicle vision and comprises the following steps: the method comprises the steps of converting a grid map and a real-time grid surface constructed by the unmanned aerial vehicle into three-dimensional point clouds, obtaining the two three-dimensional point clouds through matching conversion, converting the problem of matching the two three-dimensional grid surfaces into the problem of matching the two three-dimensional point clouds, and calculating the absolute position of the unmanned aerial vehicle at the observation time by using the three-dimensional point cloud matching and the position information of the grid map. The invention can realize positioning under low-altitude complex environment only by the monocular camera, and the mounting mode of the airborne camera of the unmanned aerial vehicle is not limited.
Description
Technical Field
The invention relates to the field of unmanned aerial vehicle vision, in particular to an unmanned aerial vehicle vision positioning method based on a grid map.
Background
At present, the positioning of the unmanned aerial vehicle mainly depends on navigation satellite systems such as GNSS (global navigation satellite system) or ground differential stations. In a war scene, signals of a navigation satellite system are easily interfered, so that an unmanned aerial vehicle is crashed or captured by a place, and a ground differential station needs to deploy a base station on the ground in advance, which is unrealistic in the war scene. Visual positioning is a type of method in which an unmanned aerial vehicle performs autonomous positioning through the observation condition of an onboard camera. Most unmanned aerial vehicle visual positioning methods are completed through matching of aerial images and satellite maps, and the satellite maps are formed by splicing images shot by satellites at high altitude. In order to ensure that the aerial images and the satellite-shot visual angles are as consistent as possible, the airborne camera needs to be installed in the direction pointing to the geocentric direction, and under a low-altitude scene, the difference between the observation visual angle and the satellite-shot visual angle is too large, so that the matching with a satellite map is often failed. At this time, matching and positioning with a pre-constructed three-dimensional map is a feasible positioning method. The three-dimensional grid map is a three-dimensional map representation method which connects sparse three-dimensional space points into a plurality of three-dimensional triangular planes and uses the three-dimensional triangular planes spliced together to describe the scene geometric structure. The map representation method occupies small storage space, is beneficial to the terrain construction of an ultra-large scene, but is difficult to be applied to a positioning task because three-dimensional space points used for constructing the grid map are different in each time.
Disclosure of Invention
The invention aims to overcome the defects of the prior art, and provides a visual positioning method of an unmanned aerial vehicle based on a grid map, which can realize positioning in a low-altitude complex environment only by a monocular camera, and the mounting mode of an airborne camera of the unmanned aerial vehicle is not limited.
The purpose of the invention is realized by the following scheme:
an unmanned aerial vehicle visual positioning method based on a grid map comprises the following steps:
the method comprises the steps of converting a grid map and a real-time grid surface constructed by the unmanned aerial vehicle into three-dimensional point clouds, obtaining the two three-dimensional point clouds through matching conversion, converting the problem of matching the two three-dimensional grid surfaces into the problem of matching the two three-dimensional point clouds, and calculating the absolute position of the unmanned aerial vehicle at the observation time by using the three-dimensional point cloud matching and the position information of the grid map.
Further, comprising the sub-steps of:
s1, extracting the area to be matched of the grid map near the initial position, and then respectively voxelizing the grid map to be matched and the real-time grid surface;
s2, marking all the voxels which are penetrated by the grid as occupied, marking the rest of the voxels which are not penetrated as empty, and forming a three-dimensional point cloud by all the voxel blocks marked as occupied;
s3, matching the two three-dimensional point clouds to obtain a relative transformation relation between the two groups of point clouds;
and S4, calculating the absolute position of the unmanned aerial vehicle at the observation time according to the relative transformation relation between the two groups of point clouds and the position information of the grid map.
Further, in step S3, an ICP point cloud matching algorithm is used to match the two three-dimensional point clouds.
Further, in step S4, the position information of the grid map is the longitude and latitude coordinates of the grid map.
Further, in step S1, the voxelization is specifically configured by dividing the three-dimensional mesh surface space into a plurality of cubes, and the cubes are called voxels.
Further, the onboard camera can be mounted in any direction that allows the ground to be observed.
The beneficial effects of the invention include:
the invention provides an unmanned aerial vehicle positioning method based on a three-dimensional grid map, after the constructed three-dimensional grid map is possessed, the unmanned aerial vehicle can realize positioning under a low-altitude complex environment only through a monocular camera, the installation mode of an airborne camera of the unmanned aerial vehicle is not limited, and compared with the installation in the center direction in the prior art, the unmanned aerial vehicle has a wider observation visual field.
Drawings
In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the drawings used in the description of the embodiments or the prior art will be briefly described below, and it is obvious that the drawings in the following description are only some embodiments of the present invention, and for those skilled in the art, other drawings can be obtained according to these drawings without creative efforts.
FIG. 1 is a grid map positioning flow chart;
FIG. 2 is a schematic view of a terrain mesh surface map;
fig. 3 is a schematic view of grid surface voxelization.
Detailed Description
All features disclosed in all embodiments in this specification, or all methods or process steps implicitly disclosed, may be combined and/or expanded, or substituted, in any way, except for mutually exclusive features and/or steps.
The embodiment of the invention uses the matching of the grid surface constructed in real time by using the image shot by the unmanned aerial vehicle and the established grid map for positioning.
Firstly, extracting a to-be-matched area of a grid map near an initial position, and then respectively carrying out voxelization on the to-be-matched grid map and a real-time grid surface (voxelization is to assume that a three-dimensional space is composed of an infinite cube with a certain side length, and the cube is called a voxel). All voxels traversed by the grid are then labeled as "occupied" and the remaining non-traversed voxels are labeled as "empty". As shown in fig. 3, gray voxel blocks are crossed by the grid surface, the white representation is not crossed, and all voxel blocks marked as "occupied" may constitute a three-dimensional point cloud. Through grid surface voxelization, the problem of matching two three-dimensional grid surfaces is converted into the problem of matching two three-dimensional point clouds. Then, matching the two three-dimensional point clouds by using a classical ICP point cloud matching algorithm to obtain a relative transformation relation between the two groups of point clouds. And calculating the absolute position of the unmanned aerial vehicle at the observation moment according to the relative transformation relation between the point clouds and the position information of the grid map.
This embodiment is under the condition that possess the grid map that has established, and unmanned aerial vehicle can fix a position through single camera under the low latitude complex environment, and the airborne camera can be installed to arbitrary direction that can observe ground, compares the installation of geocentric direction, can make unmanned aerial vehicle have wider observation field of vision.
Example 1
An unmanned aerial vehicle visual positioning method based on a grid map comprises the following steps:
the method comprises the steps of converting a grid map and a real-time grid surface constructed by the unmanned aerial vehicle into three-dimensional point clouds, obtaining the two three-dimensional point clouds through matching conversion, converting the problem of matching the two three-dimensional grid surfaces into the problem of matching the two three-dimensional point clouds, and calculating the absolute position of the unmanned aerial vehicle at the observation time by using the three-dimensional point cloud matching and the position information of the grid map.
Example 2
On the basis of the embodiment 1, the method comprises the following substeps:
s1, extracting a to-be-matched area of the grid map near the initial position, and then respectively carrying out voxelization on the to-be-matched grid map and the real-time grid surface;
s2, marking all the voxels which are penetrated by the grid as occupied, marking the rest of the voxels which are not penetrated as empty, and forming a three-dimensional point cloud by all the voxel blocks marked as occupied;
s3, matching the two three-dimensional point clouds to obtain a relative transformation relation between the two groups of point clouds;
and S4, calculating the absolute position of the unmanned aerial vehicle at the observation time according to the relative transformation relation between the two groups of point clouds and the position information of the grid map.
Example 3
On the basis of embodiment 2, in step S3, an ICP point cloud matching algorithm is used to match two three-dimensional point clouds.
Example 4
In addition to embodiment 2, in step S4, the position information of the grid map is the longitude and latitude coordinates of the grid map.
Example 5
On the basis of embodiment 2, in step S1, the voxelization is specifically configured by dividing a three-dimensional mesh surface space into a plurality of cubes, which are called voxels.
Example 6
On the basis of embodiment 2, the onboard camera can be installed in any direction that can observe the ground.
The units described in the embodiments of the present invention may be implemented by software, or may be implemented by hardware, and the described units may also be disposed in a processor. Wherein the names of the elements do not in some way constitute a limitation on the elements themselves.
According to an aspect of the application, a computer program product or computer program is provided, comprising computer instructions, the computer instructions being stored in a computer readable storage medium. The processor of the computer device reads the computer instructions from the computer-readable storage medium, and the processor executes the computer instructions to cause the computer device to perform the method provided in the various alternative implementations described above.
As another aspect, the present application also provides a computer-readable medium, which may be contained in the electronic device described in the above embodiment; or may exist separately without being assembled into the electronic device. The computer readable medium carries one or more programs which, when executed by an electronic device, cause the electronic device to implement the method described in the above embodiments.
The parts not involved in the present invention are the same as or can be implemented using the prior art.
The above-described embodiment is only one embodiment of the present invention, and it will be apparent to those skilled in the art that various modifications and variations can be easily made based on the application and principle of the present invention disclosed in the present application, and the present invention is not limited to the method described in the above-described embodiment of the present invention, so that the above-described embodiment is only preferred, and not restrictive.
In addition to the foregoing examples, those skilled in the art, having the benefit of this disclosure, may derive other embodiments from the teachings of the foregoing disclosure or from modifications and variations utilizing knowledge or skill of the related art, which may be interchanged or substituted for features of various embodiments, and such modifications and variations may be made by those skilled in the art without departing from the spirit and scope of the present invention as set forth in the following claims.
Claims (6)
1. An unmanned aerial vehicle visual positioning method based on a grid map is characterized by comprising the following steps:
the method comprises the steps of converting a grid map and a real-time grid surface constructed by the unmanned aerial vehicle into three-dimensional point clouds, obtaining the two three-dimensional point clouds through matching conversion, converting the problem of matching the two three-dimensional grid surfaces into the problem of matching the two three-dimensional point clouds, and calculating the absolute position of the unmanned aerial vehicle at the observation time by using the three-dimensional point cloud matching and the position information of the grid map.
2. The grid map based visual positioning method of unmanned aerial vehicle according to claim 1, comprising the sub-steps of:
s1, extracting a to-be-matched area of the grid map near the initial position, and then respectively carrying out voxelization on the to-be-matched grid map and the real-time grid surface;
s2, marking all the voxels which are penetrated by the grid as occupied, marking the rest of the voxels which are not penetrated as empty, and forming a three-dimensional point cloud by all the voxel blocks marked as occupied;
s3, matching the two three-dimensional point clouds to obtain a relative transformation relation between the two groups of point clouds;
and S4, calculating the absolute position of the unmanned aerial vehicle at the observation time according to the relative transformation relation between the two groups of point clouds and the position information of the grid map.
3. The mesh map-based visual positioning method for unmanned aerial vehicle as claimed in claim 2, wherein in step S3, an ICP point cloud matching algorithm is used to match two three-dimensional point clouds.
4. The visual positioning method for unmanned aerial vehicle based on grid map as claimed in claim 2, wherein in step S4, the position information of grid map is longitude and latitude coordinates of grid map.
5. The mesh map-based visual positioning method for unmanned aerial vehicle as claimed in claim 2, wherein in step S1, the voxelization is embodied by dividing a three-dimensional mesh surface space into a plurality of cubes, and the cubes are called voxels.
6. The visual positioning method of unmanned aerial vehicle based on grid map as claimed in claim 2, wherein the onboard camera can be installed in any direction to observe the ground.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202210723563.8A CN114910050A (en) | 2022-06-24 | 2022-06-24 | Unmanned aerial vehicle visual positioning method based on grid map |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202210723563.8A CN114910050A (en) | 2022-06-24 | 2022-06-24 | Unmanned aerial vehicle visual positioning method based on grid map |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN114910050A true CN114910050A (en) | 2022-08-16 |
Family
ID=82772114
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202210723563.8A Pending CN114910050A (en) | 2022-06-24 | 2022-06-24 | Unmanned aerial vehicle visual positioning method based on grid map |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN114910050A (en) |
Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN110673632A (en) * | 2019-09-27 | 2020-01-10 | 中国船舶重工集团公司第七0九研究所 | Unmanned aerial vehicle autonomous obstacle avoidance method and device based on visual SLAM |
| CN113359810A (en) * | 2021-07-29 | 2021-09-07 | 东北大学 | Unmanned aerial vehicle landing area identification method based on multiple sensors |
| CN113506374A (en) * | 2021-07-16 | 2021-10-15 | 西安电子科技大学 | Point cloud registration method based on GPS information assistance and space grid division |
| US20210358206A1 (en) * | 2020-05-14 | 2021-11-18 | Star Institute Of Intelligent Systems | Unmanned aerial vehicle navigation map construction system and method based on three-dimensional image reconstruction technology |
| KR20220021158A (en) * | 2020-08-13 | 2022-02-22 | 한국전력공사 | Apparatus for generating flight path of unmanned aerial vehicle and method thereof |
| CN114120095A (en) * | 2020-08-31 | 2022-03-01 | 中国科学院宁波材料技术与工程研究所 | Mobile robot autonomous positioning system and method based on aerial three-dimensional model |
-
2022
- 2022-06-24 CN CN202210723563.8A patent/CN114910050A/en active Pending
Patent Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN110673632A (en) * | 2019-09-27 | 2020-01-10 | 中国船舶重工集团公司第七0九研究所 | Unmanned aerial vehicle autonomous obstacle avoidance method and device based on visual SLAM |
| US20210358206A1 (en) * | 2020-05-14 | 2021-11-18 | Star Institute Of Intelligent Systems | Unmanned aerial vehicle navigation map construction system and method based on three-dimensional image reconstruction technology |
| KR20220021158A (en) * | 2020-08-13 | 2022-02-22 | 한국전력공사 | Apparatus for generating flight path of unmanned aerial vehicle and method thereof |
| CN114120095A (en) * | 2020-08-31 | 2022-03-01 | 中国科学院宁波材料技术与工程研究所 | Mobile robot autonomous positioning system and method based on aerial three-dimensional model |
| CN113506374A (en) * | 2021-07-16 | 2021-10-15 | 西安电子科技大学 | Point cloud registration method based on GPS information assistance and space grid division |
| CN113359810A (en) * | 2021-07-29 | 2021-09-07 | 东北大学 | Unmanned aerial vehicle landing area identification method based on multiple sensors |
Non-Patent Citations (1)
| Title |
|---|
| 向怀坤;陈淑仪;: "超低空无人机交通事故现场三维建模勘测系统设计", 深圳职业技术学院学报, no. 01, 20 January 2020 (2020-01-20) * |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN112085845B (en) | Outdoor scene rapid three-dimensional reconstruction device based on unmanned aerial vehicle image | |
| JP7345533B2 (en) | System and method for generating improved environmental representations for mobile objects | |
| US20220292711A1 (en) | Pose estimation method and device, related equipment and storage medium | |
| CN109934868A (en) | One kind is based on three-dimensional point cloud and the matched vehicle positioning method of satellite mapping | |
| CN114387341A (en) | Method for calculating six-degree-of-freedom pose of aircraft through single aerial observation image | |
| Lacroix et al. | Digital elevation map building from low altitude stereo imagery | |
| KR102525519B1 (en) | Drone used 3d mapping method | |
| CN114612559A (en) | Unmanned aerial vehicle pose calculation method, electronic equipment and storage medium | |
| Gbopa et al. | Unmanned Aerial Vehicles for Three‑dimensional Mapping and Change Detection Analysis | |
| Kim et al. | Assessment of Unmanned Aerial Vehicle for Management of Disaster Information | |
| CN111089580B (en) | Unmanned war chariot simultaneous positioning and map construction method based on covariance intersection | |
| CN114910050A (en) | Unmanned aerial vehicle visual positioning method based on grid map | |
| CN115016545A (en) | Landing point autonomous selection method, device and medium for unmanned aerial vehicle landing | |
| Türk et al. | Accuracy assessment of UAV-post-processing kinematic (PPK) and UAV-traditional (with ground control points) georeferencing methods | |
| CN113129422A (en) | Three-dimensional model construction method and device, storage medium and computer equipment | |
| KR102488553B1 (en) | Drone used 3d mapping method | |
| CN114418858A (en) | Remote sensing image embedding method, device, equipment and storage medium | |
| DE102021121363A1 (en) | Navigation device and positioning method | |
| CN113610952A (en) | Three-dimensional scene reconstruction method and device, electronic equipment and storage medium | |
| CN113009533A (en) | Vehicle positioning method and device based on visual SLAM and cloud server | |
| Guo et al. | Research on 3D geometric modeling of urban buildings based on airborne lidar point cloud and image | |
| KR102557775B1 (en) | Drone used 3d mapping method | |
| Riadi et al. | Vertical Accuracy Assessment of DSM from TerraSAR-X and DTM from Aerial Photogrammetry on Paddy Fields–Karawang, Indonesia | |
| Lalak et al. | The analysis of the accuracy of digital terrain model (Dtm) obtained from high resolution geoeye-1 satellite imagery | |
| KR102466007B1 (en) | Multidimensional spatial information generation system and method |
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 |