CN114418858A - Remote sensing image embedding method, device, equipment and storage medium - Google Patents
Remote sensing image embedding method, device, equipment and storage medium Download PDFInfo
- Publication number
- CN114418858A CN114418858A CN202210096367.2A CN202210096367A CN114418858A CN 114418858 A CN114418858 A CN 114418858A CN 202210096367 A CN202210096367 A CN 202210096367A CN 114418858 A CN114418858 A CN 114418858A
- Authority
- CN
- China
- Prior art keywords
- mosaic
- image
- screening
- image data
- mode
- 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 58
- 238000003860 storage Methods 0.000 title claims abstract description 10
- 238000012216 screening Methods 0.000 claims abstract description 126
- 238000012545 processing Methods 0.000 claims abstract description 47
- 238000010276 construction Methods 0.000 claims abstract description 30
- 238000003384 imaging method Methods 0.000 claims description 42
- 238000007781 pre-processing Methods 0.000 claims description 10
- 230000008569 process Effects 0.000 claims description 8
- 230000000877 morphologic effect Effects 0.000 claims description 7
- 238000004590 computer program Methods 0.000 claims description 5
- 238000010586 diagram Methods 0.000 description 20
- 239000013598 vector Substances 0.000 description 16
- 238000013507 mapping Methods 0.000 description 12
- 230000011218 segmentation Effects 0.000 description 11
- 238000000605 extraction Methods 0.000 description 9
- XLYOFNOQVPJJNP-UHFFFAOYSA-N water Substances O XLYOFNOQVPJJNP-UHFFFAOYSA-N 0.000 description 8
- 230000005855 radiation Effects 0.000 description 6
- 239000000047 product Substances 0.000 description 5
- 238000012937 correction Methods 0.000 description 4
- 238000012544 monitoring process Methods 0.000 description 4
- 238000012360 testing method Methods 0.000 description 4
- 238000005516 engineering process Methods 0.000 description 3
- 230000006870 function Effects 0.000 description 3
- 238000004519 manufacturing process Methods 0.000 description 3
- 230000008439 repair process Effects 0.000 description 3
- 238000004458 analytical method Methods 0.000 description 2
- 238000013459 approach Methods 0.000 description 2
- 230000000903 blocking effect Effects 0.000 description 2
- 238000013135 deep learning Methods 0.000 description 2
- 238000011161 development Methods 0.000 description 2
- 230000018109 developmental process Effects 0.000 description 2
- 238000003709 image segmentation Methods 0.000 description 2
- 239000000203 mixture Substances 0.000 description 2
- 238000005457 optimization Methods 0.000 description 2
- 230000009467 reduction Effects 0.000 description 2
- 238000010845 search algorithm Methods 0.000 description 2
- 238000000638 solvent extraction Methods 0.000 description 2
- 239000013589 supplement Substances 0.000 description 2
- 230000000007 visual effect Effects 0.000 description 2
- 230000002776 aggregation Effects 0.000 description 1
- 238000004220 aggregation Methods 0.000 description 1
- 230000032683 aging Effects 0.000 description 1
- 230000008859 change Effects 0.000 description 1
- 238000007621 cluster analysis Methods 0.000 description 1
- 238000013499 data model Methods 0.000 description 1
- 230000007123 defense Effects 0.000 description 1
- 238000013461 design Methods 0.000 description 1
- 238000009826 distribution Methods 0.000 description 1
- 238000001914 filtration Methods 0.000 description 1
- 230000006872 improvement Effects 0.000 description 1
- 238000007689 inspection Methods 0.000 description 1
- 238000011835 investigation Methods 0.000 description 1
- 238000005259 measurement Methods 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 238000010606 normalization Methods 0.000 description 1
- 230000002093 peripheral effect Effects 0.000 description 1
- 238000003672 processing method Methods 0.000 description 1
- 238000011160 research Methods 0.000 description 1
- 230000004044 response Effects 0.000 description 1
- 238000010187 selection method Methods 0.000 description 1
- 239000002689 soil Substances 0.000 description 1
- 230000003595 spectral effect Effects 0.000 description 1
- 230000002123 temporal effect Effects 0.000 description 1
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T3/00—Geometric image transformations in the plane of the image
- G06T3/40—Scaling of whole images or parts thereof, e.g. expanding or contracting
- G06T3/4038—Image mosaicing, e.g. composing plane images from plane sub-images
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T2200/00—Indexing scheme for image data processing or generation, in general
- G06T2200/32—Indexing scheme for image data processing or generation, in general involving image mosaicing
Landscapes
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Engineering & Computer Science (AREA)
- Theoretical Computer Science (AREA)
- Image Processing (AREA)
Abstract
The present disclosure provides a remote sensing image embedding method, apparatus, device and storage medium, the method includes: determining a corresponding image mosaic mode based on the application scene of the current mosaic task; under the determined image mosaic mode, acquiring an image data source, screening the image data source, and screening image data for image mosaic from the image data source; constructing mosaic lines by using the associated mosaic line construction strategy in the image mosaic mode based on the image data; according to the constructed mosaic lines, the image data are subjected to mosaic processing, so that the automatic operation of remote sensing image mosaic can be realized for different scenes.
Description
Technical Field
The present disclosure relates to the field of computer technologies, and in particular, to a method, an apparatus, a device, and a storage medium for embedding a remote sensing image.
Background
With the rapid development of sensor technology and remote sensing data processing methods, remote sensing image data gradually presents the characteristics of three-more (multi-platform, multi-sensor and multi-temporal), "four-high (high spectral resolution, high spatial resolution, high temporal resolution, high radiation resolution) and global coverage, and the remote sensing image data is widely applied to the fields of emergency, surveying and mapping, homeland, forestry, national defense and other industries due to the characteristics of wide coverage range, rich information content and the like of the remote sensing image data. The most prominent application of remote sensing images is to provide high-precision regional orthoimage mosaic base maps for various industries. At present, China already realizes the following purposes: 50000 basic geographic data and 2 m orthophoto data, and the image resolution of local area can reach 0.5 m or even higher. Because the limited data of the data acquisition means (provided geographic spatial information reflects the current latest state as much as possible) cannot meet the requirements of national economic construction, the dynamic update mode of geographic data represented by high-resolution remote sensing images is an important method for image mosaic meeting the requirements of practical application.
With the rapid development of the earth observation technology, the remote sensing data acquisition means is greatly improved in variety, quantity and capacity. However, imaging conditions of various satellite/aviation platforms are complex, and requirements of different application scenes on accuracy, timeliness and the like of the mosaic products are different, so that processing modes of mosaic tasks are different, and the difference exists in the production process of image mosaic, and automatic operation cannot be realized.
Disclosure of Invention
In view of this, the present disclosure provides a remote sensing image mosaic method, apparatus, device and storage medium, which can implement automatic operation of remote sensing image mosaic.
According to an aspect of the present disclosure, there is provided a remote sensing image mosaic method, including:
determining a corresponding image mosaic mode based on the application scene of the current mosaic task;
under the determined image mosaic mode, acquiring an image data source, screening the image data source, and screening image data for image mosaic from the image data source;
constructing mosaic lines by using the associated mosaic line construction strategy in the image mosaic mode based on the image data;
and carrying out mosaic processing on the image data according to the constructed mosaic line.
In one possible implementation, the image mosaic mode includes: at least one of a regional high-precision mosaic, a regional emergency mosaic, a high-precision update mosaic, and an emergency update mosaic.
In a possible implementation manner, when the image data source is screened, different screening manners are correspondingly set in different image mosaic modes;
the screening mode comprises at least one screening mode selected from screening based on screening conditions and screening based on a screening model;
when data screening is carried out based on the screening conditions, the screening conditions comprise: at least one of imaging conditions, image conditions, and task constraints;
when data screening is carried out based on the screening model, the screening model comprises at least one of a new region task screening model and a similar task screening model;
and the new region screening model is constructed according to the screening conditions.
In one possible implementation, constructing a mosaic line using the associated mosaic line construction strategy in the image mosaic mode includes:
under the condition that the image mosaic mode is regional high-precision mosaic or high-precision update mosaic or emergency update mosaic, a mosaic line is constructed by using a mosaic line construction strategy based on a morphological method;
and constructing the mosaic lines by using a mosaic line construction strategy based on the same name points when the image mosaic mode is regional emergency mosaic.
In one possible implementation manner, after the image data for image mosaic is screened from the image data source, the method further includes: preprocessing the screened image data;
and the different image mosaic modes are correspondingly matched with corresponding data preprocessing modes.
In a possible implementation manner, after performing mosaic processing on the image data according to the constructed mosaic line, the method further includes: and performing color processing on the image data subjected to the mosaic processing.
In one possible implementation, the color processing on the mosaic processed image data includes:
performing color consistency processing under the condition of no base map under the condition that the image mosaic mode is regional high-precision mosaic or regional emergency mosaic;
and performing color consistency processing based on the base map under the condition that the image mosaic mode is high-precision update mosaic or emergency update mosaic.
According to a second aspect of the present disclosure, there is provided a mosaic device for remote sensing images, comprising:
the mosaic mode acquisition module is used for determining a corresponding image mosaic mode based on the application scene of the current mosaic task;
the data screening model is used for acquiring an image data source under the determined image mosaic mode, screening the image data source and screening image data used for image mosaic from the image data source;
a mosaic line construction module for constructing a mosaic line based on the image data using the associated mosaic line construction strategy in the image mosaic mode;
and the mosaic module is used for carrying out mosaic processing on the image data according to the constructed mosaic line.
According to a third aspect of the present disclosure, there is provided a mosaic device of remote sensing images, comprising: a processor; a memory for storing processor-executable instructions; wherein the processor is configured to execute the executable instructions to perform the above method.
According to a fourth aspect of the present disclosure, there is provided a non-transitory computer readable storage medium having stored thereon computer program instructions, wherein the computer program instructions, when executed by a processor, implement the above-described method.
In the present disclosure, a corresponding image mosaic mode is determined based on an application scene of a current mosaic task; and screening the image data and constructing a mosaic line under the determined image mosaic mode so as to finish mosaic processing of the image data. Because the image mosaic method is the same under the same image mosaic mode, the automatic operation of remote sensing image mosaic can be realized under the condition of determining the image mosaic mode.
Other features and aspects of the present disclosure will become apparent from the following detailed description of exemplary embodiments, which proceeds with reference to the accompanying drawings.
Drawings
FIG. 1 shows a schematic flow diagram of a method of mosaicing remote-sensed images according to an embodiment of the present disclosure;
FIG. 2 shows a schematic flow diagram of a damascene line construction method in accordance with an embodiment of the present disclosure;
FIG. 3 illustrates a schematic diagram of acquiring an overlap region of an active area according to an embodiment of the present disclosure;
FIG. 4 shows a schematic diagram of an initial damascene reference line according to an embodiment of the present disclosure;
FIG. 5 shows a schematic diagram of an overlap region segmentation result according to an embodiment of the present disclosure;
FIG. 6 shows a schematic diagram of a damascene line extraction result according to an embodiment of the present disclosure;
FIG. 7 shows a schematic view of a complete inlaid strand according to an embodiment of the present disclosure;
FIG. 8 shows a schematic flow diagram of a damascene line construction method in accordance with yet another embodiment of the present disclosure;
FIG. 9 illustrates a schematic diagram of an overlap region active area range according to an embodiment of the present disclosure;
FIG. 10 shows a schematic diagram of efficient overlap region geo-entity element information extraction according to an embodiment of the present disclosure;
FIG. 11 is a diagram illustrating an image update edge determination result according to an embodiment of the present disclosure;
FIG. 12 illustrates a region of interest block diagram according to an embodiment of the present disclosure;
FIG. 13 shows an updated tessellation segment generation diagram, in accordance with an embodiment of the present disclosure;
FIG. 14 is a schematic diagram illustrating a mosaic line search algorithm structure based on improved GraphCut according to an embodiment of the present disclosure;
FIG. 15 shows an updated tessellation segment generation diagram, in accordance with yet another embodiment of the present disclosure;
FIG. 16 shows a schematic block diagram of a mosaic device of remote sensing images according to an embodiment of the present disclosure;
FIG. 17 shows a schematic block diagram of a mosaic device of remotely sensed images according to an embodiment of the present disclosure.
Detailed Description
Various exemplary embodiments, features and aspects of the present disclosure will be described in detail below with reference to the accompanying drawings. In the drawings, like reference numbers can indicate functionally identical or similar elements. While the various aspects of the embodiments are presented in drawings, the drawings are not necessarily drawn to scale unless specifically indicated.
The word "exemplary" is used exclusively herein to mean "serving as an example, embodiment, or illustration. Any embodiment described herein as "exemplary" is not necessarily to be construed as preferred or advantageous over other embodiments.
Furthermore, in the following detailed description, numerous specific details are set forth in order to provide a better understanding of the present disclosure. It will be understood by those skilled in the art that the present disclosure may be practiced without some of these specific details. In some instances, methods, means, elements and circuits that are well known to those skilled in the art have not been described in detail so as not to obscure the present disclosure.
< method examples >
Fig. 1 shows a schematic flow chart of a remote sensing image mosaicing method according to an embodiment of the present disclosure. As shown in FIG. 1, the mosaic method of remote sensing images comprises steps S110-S140.
And S110, determining a corresponding image mosaic mode based on the application scene of the current mosaic task.
The mosaic task is a task of combining two or more remote sensing images together to form an integral mosaic image. The application scene is a scene of a mosaic image obtained by using a mosaic task. The application scenario may include: surveying and mapping, national economic construction, national soil resource investigation, ecological environment monitoring, regional application rescue, large-scale disaster monitoring, updating of a basic surveying and mapping base map, local military operation, emergency rescue and other application scenes.
The requirements for mosaic images vary from application scenario to application scenario. For example, for application scenarios such as mapping, national economic construction, national resource survey, ecological environment monitoring, etc., an embedded image with a large coverage area needs to be obtained through an embedding task, and the obtained embedded image meets the following requirements: the precision is higher, and the timeliness is general, and the time phase requires as required, and product quality is higher. For another example, for application scenes such as regional application rescue and large-scale disaster monitoring, an embedded image with a large coverage area needs to be obtained through an embedding task, and the obtained embedded image meets the following requirements: the precision is general, and the ageing is the highest, and the time phase requires higher, and the product quality is general. For another example, for application scenes such as updating of a basic mapping base map and local military operations, a remote sensing image of a local area needs to be updated through an embedding task to obtain a locally updated embedded image, and the obtained embedded image meets the following requirements: the precision is higher, and the timeliness is higher, and the time phase requires the highest, and the product quality is higher. For another example, for an application scene such as emergency rescue, the remote sensing image of the local area needs to be updated through an embedding task to obtain a locally updated embedded image, and the obtained embedded image meets the following requirements: the precision is higher, and the timeliness is higher, and the time phase requirement is general, and product quality is higher.
In order to meet the requirements of different application scenes on mosaic images, an image mosaic mode corresponding to the application scene needs to be selected for image mosaic.
In one possible implementation, the image mosaic mode includes: at least one of a regional high-precision mosaic, a regional emergency mosaic, a high-precision update mosaic, and an emergency update mosaic.
In one possible implementation, the mapping relationship between the application scene and the image mosaic mode can be as shown in table 1. Under the condition of acquiring the application scene of the mosaic task, the corresponding image mosaic mode can be determined by inquiring the mapping relation table.
TABLE 1
And S120, acquiring an image data source under the determined image mosaic mode, screening the image data source, and screening image data for image mosaic from the image data source.
The image data source is selected differently in different image mosaic modes. In embodiments where the image mosaic modes include regional high-precision mosaics, regional emergency mosaics, high-precision update mosaics, and emergency update mosaics, the mapping between different image mosaic modes and selected image data sources may be as shown in table 1.
In the regional high-precision mosaic mode, historical remote sensing image data may be selected as an image data source, or latest remote sensing image data acquired in real time may be selected as an image data source, which is not specifically limited herein.
In the regional emergency mosaic mode, when the historical remote sensing image data meet the application scene requirements, selecting the historical remote sensing image data as an image data source to perform rapid image mosaic; and when the historical remote sensing image data does not meet the application scene requirements, selecting the latest remote sensing image data acquired in real time as an image data source.
Under the high-precision updating mosaic mode, the digital orthographic image is used as a mosaic base map, and an image data source for local updating is selected. When an image data source for local updating is selected, if the real-time remote sensing image data meet the application scene requirements, selecting the number of the real-time remote sensing images as the image data source for local updating; and when the real-time remote sensing image data do not meet the application scene requirements, selecting the historical remote sensing image data with the latest time as an image data source for local updating.
In the emergency updating mosaic mode, the digital orthographic image is used as a mosaic base map, and an image data source for local updating is selected. When an image data source for local updating is selected, the time constraint condition is used as a priority reference, and the orthoimage to be updated is quickly generated according to the latest shot remote sensing image which can be obtained under emergency rescue and other sudden time conditions, and the accuracy is inferior.
In a possible implementation manner, when the image data source is screened, different screening manners are correspondingly set in different image mosaic modes. The screening mode comprises at least one screening mode selected from screening based on screening conditions and screening based on a screening model.
When data screening is performed based on screening conditions, the screening conditions include: at least one of imaging conditions, image conditions, and task constraints.
The imaging conditions may specifically include: data imaging mode, imaging season and time, imaging angle and resolution, and terrain.
Data imaging mode: the data imaging mode can comprise a region imaging mode, a different rail strip mode, a different rail single scene mode and the like, and the consistency of the geometric relationship between the remote sensing image data acquired in different data imaging modes is different, so that a certain degree of influence is generated on a processing algorithm and even processing precision, and therefore, the data imaging mode is considered when an image data source is screened.
Imaging season and time: the data can be screened according to four seasons or specific time ranges of spring, summer, autumn and winter, and can also be screened in a mode of shielding a certain season or a certain time range. Different mosaic tasks have different time requirements on image data sources, for example, for mapping emergency repair and measurement tasks, theoretically, the imaging time is as new as possible, but if the time point is close to winter, the ground object is covered by heavy snow, and winter data or a time period in which the heavy snow falls may need to be avoided; for the emergency task, a target region of interest is mainly used as a guarantee object, and as long as the target region and the acquisition time meet requirements, even if the snow coverage area of the region is large, whether the region is winter imaging data does not need to be restricted.
Imaging angle and resolution: for regional high-precision mosaic tasks, data acquired based on surveying and mapping satellite/aviation platform observation is constrained by the design of the load, generally vertical photography is adopted, and the angle is within 5 degrees; for the regional emergency mosaic task, the large-pitch and large-side-sway imaging is a normal state for the purpose of acquiring a target, and the constraint on the data acquisition angle is properly relaxed. Based on the requirements of the task on data precision and a mapping scale, the requirements on the resolution of the data are different, for example: 1: the image resolution required by the 5000-10000 mapping scale is better than 1 meter; 1: the image resolution required by the 25000 imaging scale is better than 2.5 meters; 1: the resolution of the image required by the 50000 imaging scale is better than 5 meters; when local fast update (repair test, supplement test) is needed, the requirement for resolution can be relaxed appropriately, for example, 2.5 m resolution image local repair test, supplement test 1: 10000, modified with 10 meter resolution 1: 50000.
landform: different topographical conditions bring different requirements for screening data, preprocessing and tessellation processing. For example, uniform field objects are prone to color shift after being processed, some loads are serious in color shift, data of the loads need to be avoided from being selected, meanwhile, due to the fact that the uniform field objects lack significant objects when mosaic lines are selected, processing cannot be carried out based on a morphological algorithm, and a mosaic line generation method based on the same name points needs to be used instead. Meanwhile, the influence of factors such as different solar altitude angles and mountain terrain fluctuation on radiation characteristics can be comprehensively considered. Therefore, the data screening needs to consider the condition of the landform, wherein the landform comprises a uniform field, a sea, a desert, a mountain, a plain and the like.
The image condition may specifically include: at least one of radiation quality, geometric internal and external accuracy, registration accuracy, cloud cover, and sharpness. During the operation of the sensor, on one hand, factors such as load device faults, performance attenuation, change of space environment and the like can bring about data quality reduction, for example, gyroscope abnormity, camera output abnormity, camera defocusing causes definition reduction, stripes under a certain gear are obvious, and radiation quality and geometric quality are influenced; on the other hand, the influence of the data with different precisions on the precision of the preprocessing and the mosaic processing is different. Meanwhile, the cloud cover size is one of the most important factors influencing data use, and data with the cloud cover less than 10% can be selected in general screening conditions; but for mountains or areas with high cloud coverage due to climate reasons all year round, the conditions can be properly relaxed.
The task constraints may specifically include: at least one of adjacent image overlap, intra-region resolution difference, and adjacent angular difference and range.
In the regional high-precision mosaic mode, the screening conditions may include image conditions, imaging angles in the imaging conditions, adjacent image overlap in task constraints, and adjacent angle differences and ranges. The imaging angle can be less than or equal to 15 degrees, the adjacent image overlapping degree can be greater than or equal to 15 percent, and the adjacent angle difference and the overlapping degree between the strips in the range can be greater than or equal to 5 percent. The cloud amount in the image condition may be 10% or less. The consistency of the radiation in the image conditions is directly screened by visual interpretation of a multi-spectral browsing map; the geometric registration precision takes the panchromatic image as a reference, and the distortion error within a threshold value of 10 pixels meets the requirement of the image.
In the regional emergency mosaic mode, the screening condition is the same as that in the regional high-precision mosaic mode, but the timeliness requirement in the regional emergency mosaic mode is extremely high, so that the constraints of an imaging angle, the adjacent image overlapping degree, the strip overlapping degree and the cloud amount in the image condition can be relaxed relative to the regional high-precision mosaic mode. For example, the imaging angle may be relaxed to 30% or less, the adjacent image overlap may be relaxed to 10% or more, the overlap between bands in the adjacent angle difference and range may be relaxed to 10% or more, and the cloud amount in the image condition may be relaxed to 15% or less.
In the high-precision updating mosaic mode, when the remote sensing image data is screened, the screening condition can comprise an image condition and an adjacent image overlapping degree in task constraint. The imaging angles are all within 5 degrees, the overlapping degree of the adjacent images can be more than or equal to 15%, and under the condition that the overlapping area is small, if the positioning accuracy and the imaging quality of the images are good, the overlapping degree can be widened to be more than or equal to 8%. The cloud amount in the image condition may be 10% or less. The consistency of the radiation in the image conditions is directly screened by visual interpretation of a multi-spectral browsing map; the geometric registration precision takes the panchromatic image as a reference, and the distortion error within a threshold value of 10 pixels meets the requirement of the image.
In the emergency update mosaic mode, when remote sensing image data is screened, the screening condition is the same as that in the high-precision update mosaic mode, but the requirement on the effectiveness in the emergency update mosaic mode is high, so that the cloud amount in the image condition can be widened to be less than or equal to 10%.
In different image mosaic modes, other filtering conditions may be further included to meet the requirements of different application scenarios, which are not specifically limited herein.
And when data screening is carried out based on the screening model, the screening model comprises at least one of a new region task screening model and a similar task screening model.
The new area task is a mosaic task executed on an area where the image mosaic task has not been performed. For example, if the image mosaic task is not performed on the Qinghai-West autonomous state, the mosaic task for producing mosaic images with a resolution of 1 meter in the entire State in 2020 summer of the Qinghai-West autonomous state is a new region task.
For a new area task, after image data source screening is performed based on screening conditions, the obtained initial image data set meeting the screening conditions also has redundant data in some areas and imaging time, and the method mainly comprises the following aspects: firstly, the imaging time of the multi-scene remote sensing image data is close, but the resolution ratio is different; secondly, the resolution of the remote sensing image data at the same point is the same, but the imaging time is different; thirdly, the cloud cover and the coverage rate of different remote sensing image data in the same area are good and bad, for example, the cloud cover of the data A is low, the coverage rate of the area is low, the cloud cover of the data B is high, and the coverage rate of the area is high.
In order to further screen the optimal image data set in the initial data set, after screening based on the screening condition, further data screening is carried out based on the new region task screening model, so that the retrieval efficiency of the image data source can be improved, and the process of manual participation in screening is reduced.
The new area task screening model is constructed according to screening conditions. The new region task screening model can be specifically shown as follows: gamma-gamma1*α1+γ2*α2+γ3*α3+……γn*αn. Wherein alpha is1To alphanNormalized data values for n screening conditions, γ1To gammanThe weight value coefficient is preset for n screening conditions, and γ is a weight value corresponding to the image data.
And correspondingly setting different new area task screening models in different mosaic modes. For example, in the area high-precision mosaic mode, the new area task screening model may include: 4 screening conditions of image conditions, imaging angles in the imaging conditions, adjacent image overlapping degrees in task constraint, adjacent angle differences and ranges; in the regional high-precision mosaic mode, the new region task screening model can include: time phase, imaging angle, adjacent image overlapping degree, inter-strip overlapping degree and cloud amount in image condition are 5 screening conditions; in the high-precision updating mode, the new region task screening model may include: 4 screening conditions of image conditions, imaging angles in the imaging conditions, adjacent image overlapping degrees in task constraint, adjacent angle differences and ranges; in the emergency update mode, the new area task screening model may include: time phase, imaging angle, adjacent image overlap, inter-strip overlap and cloud cover in image condition 5 screening conditions. The weight coefficient of each screening condition can be set according to the application scene requirements. The weight coefficient value is in the range of [0,1], and the weight proportion is lower as the weight coefficient value approaches 0, and the weight proportion is higher as the weight coefficient value approaches 1.
The step of screening the image data source based on the new region task screening model comprises the following steps:
and normalizing the numerical values of the image data corresponding to the screening conditions. For example, imaging time: the imaging time is updated and the normalization value is increased, the reciprocal (6.34 x 10-9,1) of the difference between the current set time and the imaging time (set value range: 1s, 5 years (157680000s)) is taken and normalized to the range of (0, 100), and the value is alpha1(ii) a Cloud amount: the percentage value (0.01, 100) is alpha within the normalized interval range (0, 100)2(ii) a Resolution ratio: taking reciprocal (0.001, 100) of (0.01m, 1000m), normalizing to the range of (0, 100), and taking value as alpha3。
And inputting the normalized data values of the screening conditions into the new area task screening model to obtain the weight values corresponding to the images.
And repeating the second step and the third step until the weight value of each initial image data is obtained, and screening out the image data with the weight value meeting the set requirement.
And performing deduplication processing on the result output in the third step, eliminating repeated data, and finally outputting an optimal data set to complete the screening response process.
The similar task is a similar mosaic task existing in the history task of the whole process, and can be determined as the similar task when at least one of the task area, the video resolution, the imaging time and the precision of the mosaic task are basically consistent. For example, the 0.5 m mosaic image production of the whole autumn city of the Beijing area 2021 and the 0.5 m mosaic image production of the whole autumn city of the Beijing area 2017 found in the historical task library are basically consistent in task area, time phase and precision and can be considered as similar tasks.
Under the condition of acquiring the mosaic task, the similar task screening model can screen the similar task according to at least one requirement of a task area, an image resolution, imaging time and precision requirement of the mosaic task. Under the condition that similar tasks exist in historical data, a task screening model used by the similar tasks can be used for obtaining an image data source with a weight value meeting the set requirement; and under the condition that no mosaic task exists in the historical data, judging that the current mosaic task is a new area task, and screening the image data source by adopting the screening mode of the image data source of the new area task.
In one possible implementation, after the image data for image mosaic is screened from the image data source, the method further includes: and carrying out preprocessing operation on the screened image data. Wherein, the different image mosaic modes are correspondingly matched with corresponding data preprocessing modes. For example, in the area high-precision mosaic mode, the block adjustment and the ortho-correction process may be performed on the screened video data, or the ortho-correction process may be performed on the screened video data. For another example, in the local emergency mosaic mode, the system geometry correction processing may be performed on the screened image data, or the secondary correction processing may be performed on the screened image data. For another example, under the high-precision updating mosaic model, the adjustment and the orthorectification of the local area network can be performed on a plurality of pieces of image data which are screened out, and the orthorectification can be directly performed on single-scene data which are screened out. For another example, in the emergency update mosaic mode, the screened image data may be subjected to an orthorectification process.
S130, based on the image data, the mosaic line is constructed by using the related mosaic line construction strategy in the image mosaic mode.
In one possible implementation, constructing a mosaic line using an associated mosaic line construction strategy in image mosaic mode includes: and under the condition that the image mosaic mode is regional high-precision mosaic or high-precision updating mosaic or emergency updating mosaic, constructing the mosaic line by using a mosaic line construction strategy based on a morphological method. And constructing the mosaic lines by using a mosaic line construction strategy based on the same-name points under the condition that the image mosaic mode is regional emergency mosaic.
In one possible implementation, the mosaic wire is constructed based on a mosaic wire construction strategy of a morphological method, including the following steps as shown in fig. 2.
Step 1, obtaining an effective overlapping area of an image to be embedded. The effective overlapping area is the overlapping area of the effective area of the image to be embedded. Fig. 3 shows a schematic diagram of obtaining an overlapping area of an effective area, where an effective area of an image to be embedded is obtained first, and then an overlapping area between adjacent images is obtained as an effective overlapping area.
And 2, generating an initial mosaic reference line. And (3) according to the overlapping area between the adjacent images acquired in the step (1), generating an initial mosaic reference line by adopting a mosaic line automatic extraction method based on pixel difference feathering, wherein the initial mosaic reference line is shown in figure 4, and the initial mosaic reference line is represented in the overlapping area by adopting a coordinate sequence.
And 3, segmenting the overlapped area based on the primary feature library, and specifically comprising the following steps:
1) and selecting and grading the feature library.
And (3) carrying out regional object feature classification on the overlapping region in the acquired satellite image, and establishing a primary feature library and a secondary feature library, wherein the primary feature library is used for determining the segmentation limit, and the secondary feature library is used for determining the selection of the mosaic line. Selecting a primary characteristic library and a secondary characteristic library from the characteristic library data, wherein: the primary feature library comprises dense boundary vector data and sparse boundary vector data; the secondary feature library comprises road vector data, water system vector data, scarp data and the like. The feature library is mainly used for carrying out cluster analysis on the ground feature features in the image overlapping area.
The overlap region is segmented. Judging the types of sparse, dense and mixed ground objects, and partitioning the ground objects at one time. And according to the ground feature type and the feature library data established by various remote sensing geographic information resources, dividing the overlapped area into a dense section, a sparse section and a mixed section according to dense boundary vector data and sparse boundary vector data in the primary feature library.
The segment boundary is judged to contain road vector points (here north and south are relative to the block). Such as an intra-block start point, an intra-block end point, etc.
The segmentation result of the overlapped region obtained through the above steps is shown in fig. 5.
And 4, extracting mosaic lines of the segmented overlapping area based on a secondary feature library. For the segmented image, there are three cases, namely, a dense segment, a sparse segment and a mixed segment.
1) For dense segments. Firstly, judging whether dense boundary vector data exist in an overlapping area, if so, segmenting according to roads and water areas, and acquiring an inlaid line by adopting an inlaid line automatic selection method based on a water system vector and a road vector; if no boundary vector data exists, the initial mosaic reference line in the step 2 is directly selected without segmentation.
2) For sparse segments. Firstly, judging whether sparse boundary vector data exist in the overlapping region, if the sparse boundary vector data exist, constructing a minimum circumscribed rectangle, and obtaining a lower boundary intersection point through intersection of the boundary of the overlapping region and the boundary of a known sparse section to obtain an inlaid line; if no sparse boundary vector data exists, the initial mosaic reference line in the step 2 is directly selected without segmentation, and other segments except the dense segment and the sparse segment are collectively called as a mixed segment.
3) Aiming at the generation of mosaic lines in the mixed sections except for the dense sections and the sparse sections, the intersection points of the initial mosaic reference lines and the sparse sections in the step 2 and the intersection points of the initial mosaic reference lines or the boundary lines of the dense sections are respectively selected as the starting points and the end points of the mosaic line sections, and the initial mosaic lines in the step 2 are taken as the mosaic lines.
Fig. 6 shows a schematic diagram of the damascene line extraction result obtained through the above steps.
And 5, connecting the sections by embedding wires.
The hybrid section uses the initial mosaic reference line; dense segment using step, obtaining optimal mosaic lines A2A5 and A5A3 of the feature vectors obtained in step 4; the sparse segment uses the optimal mosaic lines AA4, A4a1 obtained in step 4. Finally, the endpoints of the segment and the inter-segment mosaic lines on the segment boundary lines of the mixed segment, the sparse segment and the dense segment are combined into a complete optimal mosaic line vector in the overlapping region, namely, the complete mosaic line in the embodiment is AA4A1A2A5A3B as shown in FIG. 7.
Step 6, after generating a complete mosaic line, storing the mosaic line into a feature library, and taking the mosaic line as the mosaic line of the next region mosaic under the condition of small variation difference of the ground features; under the condition of large variation difference of the ground features, the obtained complete mosaic line is used as a mosaic reference line, and the mosaic line optimization algorithm from step 1 to step 5 in the embodiment is continuously carried out, so that the mosaic line generation efficiency in the area mosaic is improved.
In a possible implementation, constructing a mosaic line based on the mosaic line construction strategy of the morphological method may further include the following steps as shown in fig. 8.
Step 1, quickly searching the effective area range of the overlapping area based on the image characteristics. The range of the effective area of the overlap region is specifically shown in fig. 9.
The method for rapidly searching the effective area range of the overlapping area is researched by combining the characteristic of dynamic intelligent updating and inlaying of geographic elements of image raster data, particularly the method for rapidly searching the effective range of the overlapping area of a single-scene image based on a base map, the effective range of a remote sensing image capable of generating inlaid lines is obtained on the basis, and useless information in the process of generating the inlaid lines is removed.
And 2, extracting and researching geographic entity element information for image mosaic.
Aiming at the characteristics of typical geographic elements (mainly roads, buildings, water systems, vegetation and the like), developing geographic entity element extraction rules and geographic element analysis research; on the basis, the deep learning method is researched, the ground object segmentation method in mosaic line efficient and rapid generation and extraction is aimed at, the geographic entity element unit is constructed, and technical support is provided for subsequent mosaic line extraction. The effective overlap area geographic entity element information extraction is shown in fig. 10.
And 3, acquiring boundary information of the ground object target elements.
Based on the boundary information of the geographic elements, the boundary of the segmentation image is subjected to image boundary acquisition, updated edge determination, region-of-interest partitioning and segmentation mosaic line generation according to the characteristics of intelligent updating mosaic, and boundary information of the ground object is provided for mosaic line generation.
The edge determination is updated.
Because the remote sensing image has a large data volume, in order to reduce the disk IO and improve the efficiency, the embodiment obtains the image update edge determination result shown in fig. 11 by extending the overlapping range of the monoscopic remote sensing image and the base map image by 10% of pixels. By X1，X2，…，XnTo represent a plurality of monoscopic images to be updated, and to represent the mosaic base map by R, wherein X is equal to R. Determining the effective overlap region facilitates reducing the update mosaic line generation time while defining the region of interest.
(2) Region of interest segmentation
For the determined image update edge, the image to be embedded is divided into four blocks, and four sub-images with the same size and determined update edge after color equalization are shown in fig. 12. In this embodiment, the monoscopic image is set as S, and the sub-image set is set as { S }1，S2，S3，S4Where S ═ S1+S2+S3+S4. The blocking strategy considers the ground feature elements and mainly comprises the following steps: an updated mosaic line segment generated based on the blocking policy along a water system, a road, and a building by-pass is shown in fig. 13.
(3) Segmented damascene line generation
The segmented mosaic lines for each sub-picture SiThe improved GraphCut method in the embodiment is adopted to realize the generation of the segmented mosaic line, the mosaic line search algorithm structure based on the improved GraphCut is shown in fig. 14, and the steps include: firstly, a Gaussian mixture model is adopted to replace a histogram to describe the probability distribution of color information, so that the image segmentation range is popularized from a gray image to a color image; secondly, the iterative mode is adopted to replace the once estimation of the Gaussian mixture model parameters, and the score is improvedCutting precision; thirdly, after introducing the color data model of the GMM, the energy function V can be rewritten as:
E(α，k，θ，z)＝U(α，k，θ，z)+V(α，z)
wherein k is (k)1，…，kn…，kN)，knE {1, 2, …, K } serves as the GMM label for each pixel. Its data items may be defined as:
fourthly, initializing according to an energy function; fifthly, image and background segmentation is carried out according to pixels in the image, and the steps from one step to three steps are repeated until the conditions are met, so that the result of considering the sectional mosaic lines of the water system and the road building is shown in fig. 15.
And 4, generating a mosaic line considering the geographic entity.
And based on the geographic element boundary information, carrying out updating edge determination based on the integrity of the target element, searching through a deep learning algorithm to generate an optimal mosaic line, and acquiring the optimized ground object mosaic boundary.
And the data is extracted, aggregated, divided and the like, so that the geographic entity element unit is simplified. When an extraction rule is formulated, the graph and the attribute characteristics of elements such as a boundary, a road, a water system, a residential area and the like are mainly analyzed, the range and the boundary information of geographic entity elements are focused, the analysis and the utilization of element information such as a road center line, a road sideline, a water system skeleton line, a house residential area sideline, a planting land sideline and the like are respectively carried out, the geographic characteristics of a map are combined, and the optimal entity sideline is selected as the boundary of a geographic entity element unit. Extracting entity boundaries follows the following rules:
1) and (3) selecting linear geographic element objects (such as roads and rivers) to construct a mosaic area skeleton, and dividing the whole area into small-range geographic entity element units with relatively regular shapes.
2) The construction of geographic entity element cell boundaries across overhead geographic element objects (such as overpasses, elevated roads, pipelines, etc.) is avoided. When avoidance cannot be achieved, secondary editing processing can be carried out on the inlaid results, and continuity and no deformation of the geographic element images are guaranteed.
3) For large-area or short-distance geographic element objects (such as forest lands, roads, rivers and the like), segmentation processing can be carried out by utilizing obvious linear ground objects (such as vegetation, artificial structures and the like) on the boundaries or images, and the geographic entity element unit structure can be refined.
4) For the broken or over-small area geographic element objects (such as houses, single artificial buildings and the like), the overlapping area range of the peripheral single-chip images is referred, and on the basis of ensuring the integrity of the geographic element objects, the aggregation processing of geographic entity element units is carried out, so that the processing efficiency of image mosaic is improved.
Through the constraint of the rules, a reasonable and effective geographic information topological pattern spot unit can be produced, and a foundation is laid for subsequent image segmentation and efficient processing based on orthoimage mosaic.
The mosaic line segments are generated by using an improved GrabCT-based optimization model, the partitioned images are segmented, the mosaic line segments intelligently bypass ground objects such as buildings through topology inspection, and the generated four mosaic line segments are combined to generate a complete mosaic line, so that the updated mosaic based on the existing regional base map is realized.
And S140, carrying out mosaic processing on the image data according to the constructed mosaic line. Namely, a mosaic image is obtained according to the constructed mosaic line.
In one possible implementation manner, after performing mosaic processing on the image data according to the constructed mosaic line, the method further includes: and performing color processing on the image data subjected to the mosaic processing.
In one possible implementation, the color processing on the mosaic processed image data includes: performing color consistency processing under the condition of no base map under the condition that the image mosaic mode is regional high-precision mosaic or regional emergency mosaic; and performing color consistency processing based on the base map when the image mosaic mode is the high-precision update mosaic or the emergency update mosaic.
In the present disclosure, a corresponding image mosaic mode is determined based on an application scene of a current mosaic task; and screening the image data and constructing a mosaic line under the determined image mosaic mode so as to finish mosaic processing of the image data. Because the image mosaic method is the same under the same image mosaic mode, the automatic operation of remote sensing image mosaic can be realized under the condition of determining the image mosaic mode.
< apparatus embodiment >
Fig. 16 shows a schematic block diagram of a mosaic device of remote sensing images according to an embodiment of the present disclosure. As shown in fig. 16, the mosaic device 100 for remote sensing images includes:
a mosaic mode obtaining module 110, configured to determine a corresponding image mosaic mode based on an application scene of a current mosaic task;
a data screening module 120, configured to obtain an image data source in the determined image mosaic mode, screen the image data source, and screen image data for image mosaic from the image data source;
a mosaic line construction module 130 for constructing a mosaic line using a mosaic line construction strategy associated in an image mosaic mode based on image data;
the mosaic module 140 is configured to perform mosaic processing on the image data according to the constructed mosaic line.
In one possible implementation, the image mosaic mode includes: at least one of a regional high-precision mosaic, a regional emergency mosaic, a high-precision update mosaic, and an emergency update mosaic.
In one possible implementation manner, when the image data source is screened, different screening manners are correspondingly set in different image mosaic modes; the screening mode comprises at least one screening mode selected from screening based on screening conditions and screening based on a screening model; when data screening is performed based on screening conditions, the screening conditions include: at least one of imaging conditions, image conditions, and task constraints; when data screening is carried out based on the screening model, the screening model comprises at least one of a new region task screening model and a similar task screening model; and the new region screening model is constructed according to screening conditions, and the similar task screening model is constructed according to the mosaic task.
In one possible implementation, constructing a mosaic line using an associated mosaic line construction strategy in image mosaic mode includes:
under the condition that the image mosaic mode is regional high-precision mosaic or high-precision update mosaic or emergency update mosaic, a mosaic line is constructed by using a mosaic line construction strategy based on a morphological method;
and constructing the mosaic lines by using a mosaic line construction strategy based on the same-name points under the condition that the image mosaic mode is regional emergency mosaic.
In one possible implementation, after the image data for image mosaic is screened from the image data source, the method further includes: preprocessing the screened image data;
wherein, the different image mosaic modes are correspondingly matched with corresponding data preprocessing modes.
In one possible implementation manner, after performing mosaic processing on the image data according to the constructed mosaic line, the method further includes: and performing color processing on the image data subjected to the mosaic processing.
In one possible implementation, the color processing on the mosaic processed image data includes:
performing color consistency processing under the condition of no base map under the condition that the image mosaic mode is regional high-precision mosaic or regional emergency mosaic;
and performing color consistency processing based on the base map when the image mosaic mode is the high-precision update mosaic or the emergency update mosaic.
< apparatus embodiment >
FIG. 17 shows a schematic block diagram of a mosaic device of remotely sensed images according to an embodiment of the present disclosure. As shown in fig. 17, the remote sensing image tessellation apparatus 200 includes a processor 210 and a memory 220 for storing instructions executable by processor 210. Wherein the processor 210 is configured to execute the executable instructions to implement a mosaic method of the remotely sensed image of any of the above.
Here, it should be noted that the number of the processors 210 may be one or more. Meanwhile, in the remote sensing image mosaic apparatus 200 according to the embodiment of the present disclosure, an input device 230 and an output device 240 may be further included. The processor 210, the memory 220, the input device 230, and the output device 240 may be connected via a bus, or may be connected via other methods, which is not limited in detail herein.
The memory 220, which is a computer-readable storage medium, may be used to store software programs, computer-executable programs, and various modules, such as: the remote sensing image mosaic method disclosed by the embodiment of the disclosure corresponds to a program or a module. The processor 210 executes various functional applications and data processing of the mosaic device 200 of the remote sensing image by running software programs or modules stored in the memory 220.
The input device 230 may be used to receive an input number or signal. Wherein the signal may be a key signal generated in connection with user settings and function control of the device/terminal/server. The output device 240 may include a display device such as a display screen.
< computer-readable storage Medium embodiment >
According to another aspect of the present disclosure, there is also provided a non-transitory computer readable storage medium having stored thereon computer program instructions which, when executed by the processor 210, implement the method of tessellation of remotely sensed images of any of the foregoing.
Having described embodiments of the present disclosure, the foregoing description is intended to be exemplary, not exhaustive, and not limited to the disclosed embodiments. Many modifications and variations will be apparent to those of ordinary skill in the art without departing from the scope and spirit of the described embodiments. The terms used herein were chosen in order to best explain the principles of the embodiments, the practical application, or technical improvements to the techniques in the marketplace, or to enable others of ordinary skill in the art to understand the embodiments disclosed herein.
Claims (10)
1. A remote sensing image mosaic method is characterized by comprising the following steps:
determining a corresponding image mosaic mode based on the application scene of the current mosaic task;
under the determined image mosaic mode, acquiring an image data source, screening the image data source, and screening image data for image mosaic from the image data source;
constructing mosaic lines by using the associated mosaic line construction strategy in the image mosaic mode based on the image data;
and carrying out mosaic processing on the image data according to the constructed mosaic line.
2. The method of claim 1, wherein the image mosaic mode comprises: at least one of a regional high-precision mosaic, a regional emergency mosaic, a high-precision update mosaic, and an emergency update mosaic.
3. The method according to claim 2, wherein different screening modes are set in different image mosaic modes when the image data sources are screened;
the screening mode comprises at least one screening mode selected from screening based on screening conditions and screening based on a screening model;
when data screening is carried out based on the screening conditions, the screening conditions comprise: at least one of imaging conditions, image conditions, and task constraints;
when data screening is carried out based on the screening model, the screening model comprises at least one of a new region task screening model and a similar task screening model;
and the new region screening model is constructed according to the screening conditions.
4. The method of claim 2, wherein constructing a mosaic line using the associated mosaic line construction strategy in the image mosaic mode comprises:
under the condition that the image mosaic mode is regional high-precision mosaic or high-precision update mosaic or emergency update mosaic, a mosaic line is constructed by using a mosaic line construction strategy based on a morphological method;
and constructing the mosaic lines by using a mosaic line construction strategy based on the same name points when the image mosaic mode is regional emergency mosaic.
5. The method of claim 2, further comprising, after screening image data for image mosaicing from the image data source: preprocessing the screened image data;
and the different image mosaic modes are correspondingly matched with corresponding data preprocessing modes.
6. The method of claim 2, further comprising, after performing a mosaic process on the image data according to the constructed mosaic lines: and performing color processing on the image data subjected to the mosaic processing.
7. The method of claim 6, wherein the color processing of the mosaic-processed image data comprises:
performing color consistency processing under the condition of no base map under the condition that the image mosaic mode is regional high-precision mosaic or regional emergency mosaic;
and performing color consistency processing based on the base map under the condition that the image mosaic mode is high-precision update mosaic or emergency update mosaic.
8. An inlaying device for remote sensing images, comprising:
the mosaic mode acquisition module is used for determining a corresponding image mosaic mode based on the application scene of the current mosaic task;
the data screening model is used for acquiring an image data source under the determined image mosaic mode, screening the image data source and screening image data used for image mosaic from the image data source;
a mosaic line construction module for constructing a mosaic line based on the image data using the associated mosaic line construction strategy in the image mosaic mode;
and the mosaic module is used for carrying out mosaic processing on the image data according to the constructed mosaic line.
9. An inlaying device for remote sensing images, comprising:
a processor;
a memory for storing processor-executable instructions;
wherein the processor is configured to carry out the executable instructions when implementing the method of any one of claims 1 to 7.
10. A non-transitory computer readable storage medium having computer program instructions stored thereon, wherein the computer program instructions, when executed by a processor, implement the method of any of claims 1 to 7.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202210096367.2A CN114418858A (en) | 2022-01-26 | 2022-01-26 | Remote sensing image embedding method, device, equipment and storage medium |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202210096367.2A CN114418858A (en) | 2022-01-26 | 2022-01-26 | Remote sensing image embedding method, device, equipment and storage medium |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN114418858A true CN114418858A (en) | 2022-04-29 |
Family
ID=81277236
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202210096367.2A Pending CN114418858A (en) | 2022-01-26 | 2022-01-26 | Remote sensing image embedding method, device, equipment and storage medium |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN114418858A (en) |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN115858840A (en) * | 2023-02-28 | 2023-03-28 | 北京数慧时空信息技术有限公司 | Scene-based remote sensing image mosaic method |
-
2022
- 2022-01-26 CN CN202210096367.2A patent/CN114418858A/en active Pending
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN115858840A (en) * | 2023-02-28 | 2023-03-28 | 北京数慧时空信息技术有限公司 | Scene-based remote sensing image mosaic method |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN112085845B (en) | Outdoor scene rapid three-dimensional reconstruction device based on unmanned aerial vehicle image | |
| CN112085844B (en) | Unmanned aerial vehicle image rapid three-dimensional reconstruction method for field unknown environment | |
| US7310606B2 (en) | Method and system for generating an image-textured digital surface model (DSM) for a geographical area of interest | |
| CN107527328B (en) | Unmanned aerial vehicle image geometric processing method considering precision and speed | |
| KR101165523B1 (en) | Geospatial modeling system and related method using multiple sources of geographic information | |
| CN109242862B (en) | Real-time digital surface model generation method | |
| CN113192193A (en) | High-voltage transmission line corridor three-dimensional reconstruction method based on Cesium three-dimensional earth frame | |
| US7778808B2 (en) | Geospatial modeling system providing data thinning of geospatial data points and related methods | |
| CN115375868B (en) | Map display method, remote sensing map display method, computing device and storage medium | |
| CN116468869A (en) | Live-action three-dimensional modeling method, equipment and medium based on remote sensing satellite image | |
| CN117237780B (en) | Multidimensional data feature graph construction method, multidimensional data feature graph construction system, intelligent terminal and medium | |
| CN114418858A (en) | Remote sensing image embedding method, device, equipment and storage medium | |
| Javadnejad et al. | An assessment of UAS-based photogrammetry for civil integrated management (CIM) modeling of pipes | |
| KR20190004086A (en) | Method for generating three-dimensional object model | |
| CN113282695B (en) | Vector geographic information acquisition method and device based on remote sensing image | |
| CN116188587A (en) | Positioning method and device and vehicle | |
| CN114758087A (en) | Method and device for constructing city information model | |
| Du et al. | High-precision DEM extraction by region segmentation-based progressive triangulation encryption filtering | |
| CN111127474A (en) | Airborne LiDAR point cloud assisted orthophoto mosaic line automatic selection method and system | |
| Lalak et al. | The analysis of the accuracy of digital terrain model (Dtm) obtained from high resolution geoeye-1 satellite imagery | |
| Gruen et al. | High accuracy 3D processing of stereo satellite images in mountainous areas | |
| Wang et al. | Location Discovery of Vector Data Update Driven by Map Image Tiles for National Geo-Information Service Platform | |
| Wenger | Evaluation of SfM against tradional stereophotogrammetry and LiDAR techniques for DSM creation in various land cover areas | |
| Ali et al. | UAV 3d photogrammetric mapping & GIS development case study: Khartoum railway station | |
| Nandakishore et al. | Advanced Application of Unmanned Aerial Vehicle (UAV) for Rapid Surveying and Mapping: A Case Study from Maharashtra, India |
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 |