CN115794975A - High-precision map original data storage optimization method and system - Google Patents
High-precision map original data storage optimization method and system Download PDFInfo
- Publication number
- CN115794975A CN115794975A CN202211436946.3A CN202211436946A CN115794975A CN 115794975 A CN115794975 A CN 115794975A CN 202211436946 A CN202211436946 A CN 202211436946A CN 115794975 A CN115794975 A CN 115794975A
- Authority
- CN
- China
- Prior art keywords
- data
- point cloud
- point
- deleting
- track
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Pending
Links
Images
Landscapes
- Instructional Devices (AREA)
- Processing Or Creating Images (AREA)
Abstract
The invention discloses a high-precision map original data storage optimization method and system, which relate track data, point cloud data and picture data based on timestamp information; setting a track point distance threshold, and deleting the next track point data of which the distance from the previous track point is less than the track point distance threshold; deleting point cloud data corresponding to the deleted track point time, setting an intensity threshold and a point cloud density threshold, and deleting road surface point cloud data with the intensity lower than the intensity threshold and road outer side point cloud data with the point cloud density lower than the point cloud density threshold; deleting the picture data corresponding to the deleted track point time, setting a gray average value threshold value, and deleting the picture data of which the gray average value is smaller than the gray average value threshold value; therefore, the consumption of data storage hardware is reduced, the data storage cost and the network bandwidth pressure in the data scheduling and transmission process are reduced, and the data processing and browsing efficiency and the interactive operation response speed in the high-precision map making process are improved.
Description
Technical Field
The invention relates to a high-precision map making technology, in particular to a high-precision map original data storage optimization method and system.
Background
High-precision map making generally adopts a vehicle-mounted mobile measurement system to acquire three-dimensional data of a road network, including point clouds, images, tracks and the like. The obtained sensor raw data is huge, and a large amount of storage resources are consumed. Particularly, in the high-precision map making process, process data of a plurality of production links need to be stored, so that the high-precision map making needs PB-level storage system support. Therefore, reducing data storage cost is an important optimization item in high-precision mapping engineering.
Disclosure of Invention
The invention aims to overcome the technical defects, provides a high-precision map original data storage optimization method and system, and solves the problems that the existing high-precision map original data is huge and needs to consume a large amount of storage resources.
In order to achieve the above technical object, a first aspect of the technical solution of the present invention provides a method for optimizing storage of original data of a high-precision map, which includes the following steps:
acquiring three-dimensional live-action data, and associating track data, point cloud data and picture data based on timestamp information;
setting a track point distance threshold, and deleting the next track point data of which the distance from the previous track point is less than the track point distance threshold;
deleting point cloud data corresponding to the deleted track point time, setting an intensity threshold and a point cloud density threshold, and deleting road surface point cloud data with the intensity lower than the intensity threshold and road outer side point cloud data with the point cloud density lower than the point cloud density threshold;
and deleting the picture data corresponding to the deleted track point time, setting a gray average value threshold value, and deleting the picture data of which the gray average value is smaller than the gray average value threshold value.
The invention provides a high-precision map original data storage optimization system, which comprises the following functional modules:
the data association module is used for acquiring three-dimensional live-action data and associating the track data, the point cloud data and the picture data based on the timestamp information;
the track point deleting module is used for setting a track point distance threshold value and deleting the next track point data of which the distance from the previous track point is less than the track point distance threshold value;
the point cloud deleting module is used for deleting the point cloud data corresponding to the deleted track point time, setting an intensity threshold and a point cloud density threshold, and deleting the road surface point cloud data with the intensity lower than the intensity threshold and the road outer side point cloud data with the point cloud density lower than the point cloud density threshold;
and the picture deleting module is used for deleting the picture data corresponding to the deleted track point time, setting a gray average value threshold value and deleting the picture data of which the gray average value is smaller than the gray average value threshold value.
A third aspect of the present invention provides a server, including a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor implements the above-mentioned method for optimizing the storage of raw data of a high-precision map when executing the computer program.
A fourth aspect of the present invention provides a computer-readable storage medium, which stores a computer program, and when the computer program is executed by a processor, the computer program implements the above-mentioned method for optimizing storage of raw data of a high-precision map.
Compared with the prior art, the high-precision map original data storage optimization method and system are used for associating track data, point cloud data and picture data based on timestamp information; setting a track point distance threshold, and deleting the next track point data of which the distance from the previous track point is less than the track point distance threshold; deleting point cloud data corresponding to the deleted track point time, setting an intensity threshold value and a point cloud density threshold value, and deleting road surface point cloud data with the intensity lower than the intensity threshold value and road outer side point cloud data with the point cloud density lower than the point cloud density threshold value; deleting the picture data corresponding to the deleted track point time, setting a gray average value threshold value, and deleting the picture data of which the gray average value is smaller than the gray average value threshold value; therefore, the total amount of track data, point cloud data and image data in the high-precision map data is reduced, the consumption of data storage hardware is reduced, the data storage cost in the high-precision map data manufacturing process and the network bandwidth pressure in the data scheduling and transmitting process are reduced, and the data processing efficiency, the data browsing efficiency and the interactive operation response speed in the high-precision map manufacturing process are improved.
Drawings
Fig. 1 is a flow chart of a method for optimizing storage of raw data of a high-precision map according to an embodiment of the present invention;
fig. 2 is a block diagram of a high-precision map raw data storage optimization system according to an embodiment of the present invention.
Detailed Description
In order to make the objects, technical solutions and advantages of the present invention more apparent, the present invention is described in further detail below with reference to the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are merely illustrative of the invention and are not intended to limit the invention.
As shown in fig. 1, an embodiment of the present invention provides a high-precision map raw data storage optimization method, which includes the following steps:
s1, three-dimensional live-action data are obtained, and track data, point cloud data and picture data are associated based on timestamp information.
The track data, the point cloud data and the picture data can be associated based on the timestamp information, and specifically, the track data, the point cloud data and the picture data at the same time point are associated and set.
S2, setting a track point distance threshold, and deleting the next track point data of which the distance from the previous track point is smaller than the track point distance threshold.
Set up track point interval threshold value promptly to first track point is the benchmark, and the interval between first track point and the second track point is calculated to second track point on the same orbit in order, if the interval between second track point and the first track point is less than track point interval threshold value, then judge this second track point and be invalid track point, otherwise for effective track point, delete invalid track point.
Specifically, the track coordinates are converted into a WGS84 coordinate system, space distance analysis is carried out based on the three-dimensional coordinates of the track points, and the space distance D of two adjacent track points (Pn and Pn + 1) is calculated. When D is smaller than a set threshold value L, marking Pn +1 as an invalid track point, and deleting the invalid track point; recalculating the distance D of the track points (Pn, pn + 2), and judging whether the track points (Pn + 2) are invalid track points or not again until the distance D between the track points (Pn, pn + i) is greater than a set threshold value L, and judging that the points (Pn + i) are valid track points and keeping the points.
And S3, deleting the point cloud data corresponding to the deleted track point time, setting an intensity threshold and a point cloud density threshold, and deleting the road surface point cloud data with the intensity lower than the intensity threshold and the road outer side point cloud data with the point cloud density lower than the point cloud density threshold.
Namely, based on the time information marked as the invalid track point, the associated point cloud frame data is inquired, and the associated discrete points in the point cloud frame are marked as invalid data and deleted, so that the total amount of the discrete data is reduced.
And identifying road surface point cloud data by adopting a seed growing method based on the deleted point cloud data. Specifically, the deleted point cloud data is used as seeds to grow towards two sides, the growing direction of the point cloud data is the vertical direction based on the front track point and the rear track point, and the growing conditions are set as follows: the Z value difference in the plane formed by the produced points is not more than 5cm, and the growth range of each time is not more than 0.5m; and identifying road surface point cloud data according to the growth condition.
Because the road surface data has the characteristic that the strength of the printed matter is higher than that of other artificial objects, based on the characteristic, the watershed method is adopted to segment the foreground and the background of the road surface point cloud data based on the strength threshold value, the road surface printed matter is segmented from the road surface background, and the point cloud data of the road surface background is deleted. However, the actual scene is complex, the problem that the printed matter is abraded and shielded possibly, the strength is low, and the printed matter is incomplete in separation, so that the point cloud of the pavement printed matter is used as a seed to grow to the periphery, and if the difference value of the intensity of the point cloud of the previous growth and the intensity of the point cloud of the next growth is smaller than the threshold span range, the iteration is continued for 3 times, so that the completeness of the printed matter is ensured under the condition that the data is filtered as much as possible. Preferably, the threshold span range is 5% of the maximum intensity span of the current point cloud data.
The main objects for making the high-precision map data are roads and artificial facilities on two sides of the roads, trees and vegetations on two sides of the roads can be classified into invalid data, and trees and vegetations on two sides of the roads basically occupy a large proportion of the whole data. The point cloud of trees and vegetation has the characteristics of dispersion, no plane and positions on two sides of a road, the areas on two sides of the road surface are identified based on point cloud analysis, plane identification extraction and discrete point filtration are carried out on the point cloud in the areas, vegetation data are reduced, and the total amount of the point cloud data is reduced.
Namely, after the road surface point cloud data is processed, the road outside point cloud data with the point cloud density smaller than the point cloud density threshold is further deleted, and the method comprises the following steps: and widening a preset distance range to two sides of the road to obtain an effective area outside the road, identifying the effective area outside the road based on point cloud analysis, and performing plane identification extraction and discrete point filtration on point clouds in the effective area outside the road. The method specifically comprises the following steps:
finding out a polygonal outer wrapping frame of the road surface based on the road surface point cloud data obtained by identification, and fitting two side lines in the driving direction;
extrapolating a preset distance from the road line to the two sides to form a road outer area, and collecting point clouds in the road outer area into a point cloud data set of the road outer area;
analyzing the field point cloud density of each discrete point in the point cloud data set of the road outer side area based on a neighboring point algorithm, deleting the point cloud data set of which the point cloud density is lower than a first preset density threshold value, and filtering isolated points;
projecting the rest point clouds to an xoy plane, performing field density analysis on the xoy plane, deleting the point cloud data set with the point cloud density lower than a second preset density threshold value, and filtering isolated points;
and for the remaining points, marking the points as non-planar data based on a plane recognition method provided by a PCL library, and growing downwards to avoid filtering the point cloud of the rod piece by taking the points on the upper edge and the lower edge of the board as seed points in consideration of the fact that the rod below the route guide signboard needs to be manufactured because the road side planar data is basically the route guide signboard.
The point cloud data has the characteristic that the closer the scanning distance, the higher the data density, especially on the road surface right below the mobile measurement system, the scanning distance is less than 3 meters, the distance between adjacent points is less than 1cm, and the density is far greater than the precision requirement of high-precision map making. Therefore, after deleting the point cloud data with the road surface intensity lower than the intensity threshold and the point cloud data with the point cloud density lower than the point cloud density threshold, setting a point cloud spacing threshold, and deleting one point cloud data in the adjacent point clouds with the spacing distance smaller than the point cloud spacing threshold.
Specifically, a distance threshold L of adjacent points can be set, the adjacent points are traversed towards the left side and the right side respectively by taking the point cloud right below the laser scanner as a reference, the distance d1 of the adjacent point cloud (Pt, pt + 1) is calculated, when d is less than L, pt +1 is marked as an invalid point cloud, one point is deleted, the distance d2 of the point cloud (Pt, pt + 2) is calculated, the calculation is stopped until the distance of the point cloud (Pt, pt + i) is greater than L, and Pt + i is marked as an valid point cloud and is reserved. And removing meaningless discrete points made for subsequent data according to the invalid marks of the point cloud, and reducing the total amount of the point cloud data.
And S4, deleting the picture data corresponding to the deleted track point time, setting a gray average value threshold value, and deleting the picture data of which the gray average value is smaller than the gray average value threshold value.
And inquiring related image data based on the time information marked as the invalid track points, marking the image data as invalid data and deleting the image data.
Because the mobile measurement system passes through a tunnel, a sunlight shielding area below an overpass and the like in the acquisition process, the acquisition direction is opposite to the sunlight irradiation direction, and thus, the image data acquired by image sensing is over-exposed or over-dark; therefore, the acquired GRB image is converted into a gray level image, the gray level average value and the average value deviation are calculated, whether the image is over-exposed or over-dark is judged according to the set gray level average value threshold, and the over-exposed or over-dark image is deleted from the image data.
After deleting the picture data with the gray average value smaller than the gray average value threshold, in the effective area outside the road, identifying whether the vegetation is sky and road test vegetation or not by using the deep learning model, and modifying the pixels in the range of the sky and the vegetation into black. Namely, on the basis of the road surface identified by the point cloud, two sides of the road, for example, 10 meters, are set as effective areas, the effective areas are projected to image data, and pixels in the effective area range are marked as effective pixels. And for the unmarked pixel set, identifying whether the pixel set is sky and road test vegetation by using the deep learning model, modifying the pixels in the sky and vegetation range into black, and compressing invalid data by using the characteristics of a jpeg format so as to reduce the total amount of image data.
And storing the track data, the point cloud data and the image data which are invalid in filtering into a directory of specified rules according to the use requirements of subsequent high-precision map making.
The method comprises the steps of associating track data, point cloud data and picture data based on timestamp information; setting a track point distance threshold, and deleting the next track point data of which the distance from the previous track point is less than the track point distance threshold; deleting point cloud data corresponding to the deleted track point time, setting an intensity threshold and a point cloud density threshold, and deleting road surface point cloud data with the intensity lower than the intensity threshold and road outer side point cloud data with the point cloud density lower than the point cloud density threshold; deleting the picture data corresponding to the deleted track point time, setting a gray average value threshold value, and deleting the picture data of which the gray average value is smaller than the gray average value threshold value; therefore, the total amount of track data, point cloud data and image data in the high-precision map data is reduced, the consumption of data storage hardware is reduced, the data storage cost in the high-precision map data manufacturing process and the network bandwidth pressure in the data scheduling and transmitting process are reduced, and the data processing efficiency, the data browsing efficiency and the interactive operation response speed in the high-precision map manufacturing process are improved.
As shown in fig. 2, the embodiment of the present invention further discloses a high-precision map raw data storage optimization system, which includes the following functional modules:
the data association module 10 is used for acquiring three-dimensional live-action data and associating the track data, the point cloud data and the picture data based on the timestamp information;
the track point deleting module 20 is configured to set a track point interval threshold, and delete a subsequent track point data whose interval distance from a previous track point is smaller than the track point interval threshold;
the point cloud deleting module 30 is used for deleting the point cloud data corresponding to the deleted track point time, setting an intensity threshold value and a point cloud density threshold value, and deleting the point cloud data of which the road surface intensity is lower than the intensity threshold value and the point cloud data of which the point cloud density is lower than the point cloud density threshold value;
and the picture deleting module 40 is used for deleting the picture data corresponding to the deleted track point time, setting a gray average value threshold value and deleting the picture data of which the gray average value is smaller than the gray average value threshold value.
The execution mode of the high-precision map raw data storage optimization system of this embodiment is basically the same as that of the above-mentioned high-precision map raw data storage optimization method, and therefore will not be described in detail.
The server in this embodiment is a device providing computing services, and generally refers to a computer with high computing power and provided for multiple consumers to use through a network. The server of this embodiment includes: a memory including an executable program stored thereon, a processor, and a system bus, it will be understood by those skilled in the art that the terminal device structure of the present embodiment does not constitute a limitation of the terminal device, and may include more or fewer components than shown, or some of the components may be combined, or a different arrangement of components.
The memory may be used to store software programs and modules, and the processor may execute various functional applications of the terminal and data processing by operating the software programs and modules stored in the memory. The memory may mainly include a storage program area and a storage data area, wherein the storage program area may store an operating system, an application program required by at least one function (such as a sound playing function, an image playing function, etc.), and the like; the storage data area may store data (such as audio data, a phonebook, etc.) created according to the use of the terminal, etc. Further, the memory may include high speed random access memory, and may also include non-volatile memory, such as at least one magnetic disk storage device, flash memory device, or other volatile solid state storage device.
The executable program of the storage optimization method for the raw data of the high-precision map is contained in a memory, the executable program can be divided into one or more modules/units, the one or more modules/units are stored in the memory and executed by a processor to complete the acquisition of the information and the implementation process, and the one or more modules/units can be a series of instruction sections of a computer program capable of completing specific functions, and the instruction sections are used for describing the execution process of the computer program in the server. For example, the computer program may be divided into a data association module 10, a track point pruning module 20, a point cloud pruning module 30, and a picture pruning module 40.
The processor is a control center of the server, connects various parts of the whole terminal device by various interfaces and lines, and performs various functions of the terminal and processes data by running or executing software programs and/or modules stored in the memory and calling data stored in the memory, thereby integrally monitoring the terminal. Alternatively, the processor may include one or more processing units; preferably, the processor may integrate an application processor, which mainly handles operating systems, application programs, etc., and a modem processor, which mainly handles wireless communications. It will be appreciated that the modem processor described above may not be integrated into the processor.
The system bus is used to connect functional units in the computer, and can transmit data information, address information and control information, and the types of the functional units can be PCI bus, ISA bus, VESA bus, etc. The system bus is responsible for data and instruction interaction between the processor and the memory. Of course, the system bus may also access other devices such as network interfaces, display devices, etc.
The server at least includes a CPU, a chipset, a memory, a disk system, and the like, and other components are not described herein again.
In the embodiment of the present invention, the executable program executed by the processor included in the terminal specifically includes: a high-precision map original data storage optimization method comprises the following steps:
acquiring three-dimensional live-action data, and associating track data, point cloud data and picture data based on timestamp information;
setting a track point distance threshold, and deleting the next track point data of which the distance from the previous track point is less than the track point distance threshold;
deleting point cloud data corresponding to the deleted track point time, setting an intensity threshold and a point cloud density threshold, and deleting road surface point cloud data with the intensity lower than the intensity threshold and road outer side point cloud data with the point cloud density lower than the point cloud density threshold;
and deleting the picture data corresponding to the deleted track point time, setting a gray average value threshold value, and deleting the picture data of which the gray average value is smaller than the gray average value threshold value.
It is clear to those skilled in the art that, for convenience and brevity of description, the specific working processes of the above-described systems, apparatuses and units may refer to the corresponding processes in the foregoing method embodiments, and are not described herein again.
In the above embodiments, the description of each embodiment has its own emphasis, and reference may be made to the related description of other embodiments for parts that are not described or recited in any embodiment.
Those of ordinary skill in the art would appreciate that the modules, elements, and/or method steps of the various embodiments described in connection with the embodiments disclosed herein may be implemented as electronic hardware, or combinations of computer software and electronic hardware. Whether such functionality is implemented as hardware or software depends upon the particular application and design constraints imposed on the technical solution. Skilled artisans may implement the described functionality in varying ways for each particular application, but such implementation decisions should not be interpreted as causing a departure from the scope of the present invention.
The above embodiments are only used to illustrate the technical solution of the present invention, and not to limit the same; although the present invention has been described in detail with reference to the foregoing embodiments, it should be understood by those of ordinary skill in the art that: the technical solutions described in the foregoing embodiments may still be modified, or some technical features may be equivalently replaced; and such modifications or substitutions do not depart from the spirit and scope of the corresponding technical solutions of the embodiments of the present invention.
Claims (10)
1. A high-precision map original data storage optimization method is characterized by comprising the following steps:
acquiring three-dimensional live-action data, and associating the track data, the point cloud data and the picture data based on the timestamp information;
setting a track point distance threshold, and deleting the next track point data of which the distance from the previous track point is less than the track point distance threshold;
deleting point cloud data corresponding to the deleted track point time, setting an intensity threshold and a point cloud density threshold, and deleting road surface point cloud data with the intensity lower than the intensity threshold and road outer side point cloud data with the point cloud density lower than the point cloud density threshold;
and deleting the picture data corresponding to the deleted track point time, setting a gray average value threshold value, and deleting the picture data of which the gray average value is smaller than the gray average value threshold value.
2. The original data storage optimization method for the high-precision map as claimed in claim 1, wherein the track point distance threshold is set, and the subsequent track point data with the distance from the previous track point smaller than the track point distance threshold is deleted; the method comprises the following steps:
and setting a track point interval threshold value, using the first track point as a reference point, calculating the interval between the first track point and the second track point by using the second track point on the same track in sequence, if the interval between the second track point and the first track point is smaller than the track point interval threshold value, judging that the second track point is an invalid track point, otherwise, deleting the invalid track point for the valid track point.
3. The method for storing and optimizing the original data of the high-precision map according to claim 1, wherein the deleting the point cloud data with the road surface intensity lower than the intensity threshold comprises:
identifying road surface point cloud data by adopting a seed growing method based on the deleted point cloud data;
based on the intensity threshold value, the pavement printed matter is segmented from the pavement background through a watershed method, and the point cloud data of the pavement background is deleted.
4. The method for storing and optimizing original data of a high-precision map as claimed in claim 3, wherein after the road print is segmented from the road background by the watershed method, the segmented road print point cloud is used as a seed to grow to the periphery, and if the difference value of the point cloud intensity between the previous growth and the next growth is smaller than the threshold span range, the outward iteration is continued for 3 times.
5. The method for optimizing the storage of the raw data of the high-precision map according to claim 1, wherein the deleting of the point cloud data outside the road with the point cloud density smaller than the point cloud density threshold comprises: widening a preset distance range to two sides of a road to obtain an effective area outside the road, identifying the effective area outside the road based on point cloud analysis, performing plane identification and extraction on point clouds in the effective area outside the road, and filtering discrete points based on a point cloud density threshold value.
6. The method for storing and optimizing the original data of the high-precision map as claimed in claim 1, wherein after deleting the road surface point cloud data with the intensity lower than the intensity threshold and the road outside point cloud data with the point cloud density smaller than the point cloud density threshold, the point cloud spacing threshold is set, and one of the adjacent point clouds with the spacing distance smaller than the point cloud spacing threshold is deleted.
7. The method for optimizing the storage of the original data of the high-precision map according to claim 5, wherein the deleting the picture data with the average value of gray scale smaller than the threshold value of the average value of gray scale further comprises: in the effective area outside the road, the deep learning model is used for identifying whether the vegetation is the sky and the road measurement vegetation, and the pixels in the range of the sky and the vegetation are modified into black.
8. The high-precision map raw data storage optimization system is characterized by comprising the following functional modules:
the data association module is used for acquiring three-dimensional live-action data and associating the track data, the point cloud data and the picture data based on the timestamp information;
the track point deleting module is used for setting a track point distance threshold value and deleting the next track point data of which the distance from the previous track point is less than the track point distance threshold value;
the point cloud deleting module is used for deleting the point cloud data corresponding to the deleted track point time, setting an intensity threshold and a point cloud density threshold, and deleting the road surface point cloud data with the intensity lower than the intensity threshold and the road outer side point cloud data with the point cloud density lower than the point cloud density threshold;
and the picture deleting module is used for deleting the picture data corresponding to the deleted track point time, setting a gray average value threshold value and deleting the picture data of which the gray average value is smaller than the gray average value threshold value.
9. A server comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor implements the high accuracy map raw data storage optimization method according to any one of claims 1 to 7 when executing the computer program.
10. A computer-readable storage medium storing a computer program, wherein the computer program, when executed by a processor, implements the method for optimizing raw data storage of high-precision maps according to any one of claims 1 to 7.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202211436946.3A CN115794975A (en) | 2022-11-16 | 2022-11-16 | High-precision map original data storage optimization method and system |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202211436946.3A CN115794975A (en) | 2022-11-16 | 2022-11-16 | High-precision map original data storage optimization method and system |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN115794975A true CN115794975A (en) | 2023-03-14 |
Family
ID=85438319
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202211436946.3A Pending CN115794975A (en) | 2022-11-16 | 2022-11-16 | High-precision map original data storage optimization method and system |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN115794975A (en) |
-
2022
- 2022-11-16 CN CN202211436946.3A patent/CN115794975A/en active Pending
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN105893972B (en) | Automatic monitoring method for illegal building based on image and implementation system thereof | |
| CN109241846B (en) | Method and device for estimating space-time change of remote sensing image and storage medium | |
| CN113252053B (en) | High-precision map generation method and device and electronic equipment | |
| CN113593017A (en) | Method, device and equipment for constructing surface three-dimensional model of strip mine and storage medium | |
| CN111949817A (en) | Crop information display system, method, equipment and medium based on remote sensing image | |
| CN114089786A (en) | Autonomous inspection system based on unmanned aerial vehicle vision and along mountain highway | |
| CN114648709A (en) | Method and equipment for determining image difference information | |
| CN114722944A (en) | Point cloud precision determination method, electronic device and computer storage medium | |
| CN114241326A (en) | Progressive intelligent production method and system for ground feature elements of remote sensing images | |
| CN114937081A (en) | Internet vehicle position estimation method and device based on independent non-uniform incremental sampling | |
| CN114882316A (en) | Target detection model training method, target detection method and device | |
| CN114660568A (en) | Laser radar obstacle detection method and device | |
| CN116597270A (en) | Road damage target detection method based on attention mechanism integrated learning network | |
| CN115797775A (en) | Intelligent illegal building identification method and system based on near-earth video image | |
| CN115439753A (en) | Steep river bank identification method and system based on DEM | |
| CN115586536A (en) | Forest resource investigation monitoring system and method based on laser point cloud | |
| CN117451012B (en) | Unmanned aerial vehicle aerial photography measurement method and system | |
| CN113033386B (en) | High-resolution remote sensing image-based transmission line channel hidden danger identification method and system | |
| CN112668448B (en) | Ecological process change analysis method, device, medium and terminal equipment | |
| CN114092651A (en) | Intelligent modeling system and method for emergency management | |
| CN116563774B (en) | Automatic identification method and system for illegal mining of cultivated land in China | |
| CN115794975A (en) | High-precision map original data storage optimization method and system | |
| WO2022048193A1 (en) | Map drawing method and apparatus | |
| CN115423975A (en) | Ground elevation extraction method based on visible light image and deep learning algorithm | |
| CN111382645B (en) | Method and system for identifying overdue building in electronic map |
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 |