CN115861838A - Image segmentation method and computer equipment - Google Patents
Image segmentation method and computer equipment Download PDFInfo
- Publication number
- CN115861838A CN115861838A CN202211542883.XA CN202211542883A CN115861838A CN 115861838 A CN115861838 A CN 115861838A CN 202211542883 A CN202211542883 A CN 202211542883A CN 115861838 A CN115861838 A CN 115861838A
- Authority
- CN
- China
- Prior art keywords
- image
- reflectivity
- segmented
- grouping
- block
- 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
- Image Processing (AREA)
Abstract
The invention provides an image segmentation method and computer equipment, wherein the image segmentation method comprises the following steps: obtaining a remote sensing image to be segmented of a region to be analyzed; determining the size of a block image, and blocking the remote sensing image to be segmented according to the size of the block image to obtain a plurality of block images; respectively determining the reflectivity grouping modes of a plurality of wave bands according to the surface feature reflectivity of the block grids in each block image; determining a dividing line of the block image according to the reflectivity grouping mode of a plurality of wave bands; and merging the segmentation lines of the multiple segmented images to obtain a segmentation image of the remote sensing image to be segmented. The scheme of the invention can fully utilize the natural difference rule of multispectral image ground object information and realize accurate and efficient image segmentation.
Description
Technical Field
The present invention relates to the field of image processing, and in particular, to a method for segmenting an image and a computer device.
Background
In the process of supervising the environmental water conservation work in the construction period of the power transmission line, the areas of disturbance, covering and other environmental water conservation information need to be acquired in time. Along with the emission of remote sensing satellites such as 'high-score' series in China, more and more multispectral data provide a solid data base for timely acquisition of environmental water protection information.
In the field of image information extraction, object-oriented remote sensing information extraction is a common technical method. Image segmentation is the basis of the object-oriented remote sensing information extraction technology, and the accuracy and the processing efficiency of segmentation are the key points of technical practicability.
The existing image segmentation technology, such as a multi-scale segmentation algorithm, has poor effect due to the fact that the natural law of spectral reflectivity difference between multiband image ground objects cannot be fully reflected, and is not widely used. Therefore, the existing image segmentation technology cannot meet the requirement of accurately analyzing the environmental water conservation information.
Disclosure of Invention
An object of the present invention is to provide an accurate image segmentation method and computer apparatus.
Particularly, the present invention provides a method for segmenting an image, comprising:
obtaining a remote sensing image to be segmented of a region to be analyzed;
determining the size of a block image, and blocking the remote sensing image to be segmented according to the size of the block image to obtain a plurality of block images;
respectively determining the reflectivity grouping modes of a plurality of wave bands according to the surface feature reflectivity of the block grids in each block image;
determining a dividing line of the block image according to the reflectivity grouping mode of a plurality of wave bands; and
and merging the segmentation lines of the multiple segmented images to obtain a segmentation image of the remote sensing image to be segmented.
Optionally, the step of obtaining a to-be-segmented remote sensing image of the to-be-analyzed region includes:
acquiring position information of an area to be analyzed;
acquiring an original image corresponding to the position information;
preprocessing an original image;
and cutting the preprocessed image by using the polygon with the set vector to obtain the remote sensing image with the required shape.
Optionally, the step of determining the size of the block image comprises:
identifying and extracting the size of the target category in the remote sensing image to be segmented;
and expanding the size of the extracted target category in the remote sensing image to be segmented to set the number of pixels to obtain the size of the segmented image.
Optionally, after the step of blocking the remote sensing image to be segmented according to the size of the blocked image, the method further includes:
and merging the parts of the remote sensing image to be segmented which are not divided into adjacent segmented images.
Optionally, the step of determining the reflectivity grouping modes of the multiple bands according to the feature reflectivity of the block grid in each block image includes:
obtaining the multiband ground object reflectivity of each block grid in each block image;
sequencing the surface feature reflectivity of each block grid of each wave band to obtain a single-wave-band reflectivity sequence;
naturally grouping the single-waveband reflectivity sequence to obtain a plurality of alternative grouping modes;
selecting one of the multiple alternative grouping modes with the minimum intra-group deviation as a reflectivity grouping mode of the current band;
and counting the reflectivity grouping modes of a plurality of wave bands.
Optionally, the step of selecting one of the multiple candidate grouping manners with the smallest intra-group deviation includes:
calculating the square deviation sum of squares of the category means of a plurality of candidate grouping modes;
and determining the alternative grouping mode with the minimum square deviation sum of the category mean values.
Optionally, before the step of naturally grouping the single-band reflectivity sequences, the method further includes:
estimating the number of natural land types contained in the remote sensing image to be segmented;
and setting the estimated natural land type quantity as the grouping quantity of the natural grouping.
Optionally, the step of determining the partition lines of the segmented image according to the reflectivity grouping manner of the plurality of bands comprises:
respectively calculating the difference value of the reflectivity at two sides of the grouping interval in the reflectivity grouping mode of a plurality of wave bands;
sorting the difference values of the reflectivity from large to small;
determining a blocking grid corresponding to the difference value of the reflectivity of the set number which is ranked in front;
taking the partitioning grid as a breakpoint position;
and connecting the positions of the breakpoints to obtain the dividing lines of the block images.
According to another aspect of the present invention, there is also provided a computer device comprising a memory, a processor and a machine executable program stored on the memory and running on the processor, and the processor when executing the machine executable program implements the method of segmenting an image according to any of the above.
The image segmentation method comprises the steps of segmenting remote sensing images to be segmented in an area to be analyzed into a set number of segmented images according to the size of the segmented images; respectively determining the grid breakpoint positions of respective wave bands according to the surface feature reflectivity of the respective wave bands of each block image; determining a partition line of the blocked image according to the positions of the grid breakpoints of the plurality of wave bands; and merging the segmentation lines of the multiple segmented images to obtain a segmentation image of the remote sensing image to be segmented. The number and the size of the block images are determined according to the segmentation requirements, and on the basis of determining the size of the block images and the division of the block images, the ground object reflectivity of a plurality of wave bands is used for determining the segmentation lines, so that the segmentation is more accurate and efficient.
Furthermore, the image segmentation method of the invention naturally groups the feature reflectivity of each block grid of the block image, selects a group with the minimum deviation in the group as the reflectivity group of the corresponding wave band, and adopts the method of the square deviation square sum of the class mean value to calculate the deviation, so as to fully mine the natural difference rule of the feature spectral reflectivity, and the data classification effect is good and the calculation efficiency is high. The ground object reflectivity of a plurality of wave bands is comprehensively considered, and the segmentation accuracy is further improved.
The above and other objects, advantages and features of the present invention will become more apparent to those skilled in the art from the following detailed description of specific embodiments thereof taken in conjunction with the accompanying drawings.
Drawings
Some specific embodiments of the invention will be described in detail hereinafter, by way of illustration and not limitation, with reference to the accompanying drawings. The same reference numbers in the drawings identify the same or similar elements or components. Those skilled in the art will appreciate that the drawings are not necessarily drawn to scale. In the drawings:
FIG. 1 is a schematic flow chart of a segmentation method for an image according to an embodiment of the present invention;
FIG. 2 is a diagram illustrating a segmented image for determining a breakpoint of a band grid according to an embodiment of the present invention;
FIG. 3 is a diagram illustrating a method for determining a partition line of a block image according to an embodiment of the present invention; and
FIG. 4 is a schematic diagram of a computer device according to one embodiment of the invention.
Detailed Description
It should be understood by those skilled in the art that the embodiments described below are only a part of the embodiments of the present invention, not all of the embodiments of the present invention, and the part of the embodiments are intended to explain the technical principle of the present invention and not to limit the scope of the present invention. All other embodiments, which can be derived by a person skilled in the art from the embodiments given herein without inventive step, shall fall within the scope of protection of the present invention.
It should be noted that the logic and/or steps shown in the flowcharts or otherwise described herein, such as an ordered listing of executable instructions that can be considered to implement logical functions, can be embodied in any computer-readable medium for use by or in connection with an instruction execution system, apparatus, or device, such as a computer-based system, processor-containing system, or other system that can fetch the instructions from the instruction execution system, apparatus, or device and execute the instructions.
Fig. 1 is a schematic flow chart of a segmentation method of an image according to an embodiment of the present invention. The image segmentation method of this embodiment generally includes the following steps:
and S102, acquiring a remote sensing image to be segmented of the area to be analyzed. The remote sensing image to be segmented can be obtained by an original image shot by a remote sensing satellite. The original image may be a satellite image reflecting the reflectivity of the ground object. The reflectivity of the ground object is the percentage of the reflection energy of the ground object to the total incident energy. The features have different reflectivities at different wavelengths, and at the same wavelength, different features also have different reflectivities. The land feature reflectivity mainly depends on the geographical position, the illumination condition, the nature of the land feature (such as the degree of dryness and wetness, the surface condition) and the environmental influence factor, so that the analysis of the land feature reflectivity can determine the type of the land feature (such as the environmental water conservation land feature information) required.
A specific acquiring process in step S102 may be: acquiring position information of an area to be analyzed; acquiring an original image corresponding to the position information; preprocessing an original image; and cutting the preprocessed image by using the polygon with the set vector to obtain the remote sensing image with the required shape. For example, when the method of this embodiment is applied to an extra-high voltage power transmission and transformation project, a remote sensing original image is obtained according to the project location information, for example, a buffer area within a certain range (1 km) around the project location is used for clipping. The shape of the specific cutting and the size of the buffer area can be determined according to the terrain of the processing region required.
Preprocessing the raw image may include: radiation correction, atmospheric correction, geometric correction and clipping. The accuracy of subsequent image processing can be improved by preprocessing the original image. The calibration techniques for radiation calibration, atmospheric calibration, and geometric calibration are known in the art and will not be described herein. The reflectivity of the ground objects in a plurality of wave bands at each position in the image can be determined through the remote sensing image to be segmented.
And step S104, determining the size of the block image, and blocking the remote sensing image to be segmented according to the size of the block image to obtain a plurality of block images. The size of the segmented image in this embodiment is required to include the type of feature to be analyzed.
The process of determining the size of the block image in step S104 may include: identifying and extracting the size of the target category in the remote sensing image to be segmented; and expanding the size of the extracted target class in the remote sensing image to be segmented by setting the number of pixels to obtain the size of the segmented image. The target category can be obtained through preliminary analysis of the image, and can also be manually demarcated or selected. For example, a certain number (e.g., 100) of pixels may be expanded outside the region in the remote sensing image to be segmented according to the extraction category, so as to set the size a × b of the segmented image (where a and b are the row number and column number of the segmented image, and the reference size may be 800 × 800, taking underground cable cover segmentation as an example). According to the situation of the remote sensing image to be segmented, the number of the natural land types contained in the remote sensing image to be segmented under the size can be estimated and recorded as e.
Step S104 further includes, after the step of blocking the remote sensing image to be segmented according to the size of the blocked image: and merging the parts of the remote sensing image to be segmented which are not divided into adjacent segmented images. That is, the remote sensing image to be segmented can be segmented into n rows and n columns of segmented images according to the size of the segmented images, and m × n segmented images are obtained. The image areas (images at corner positions having a size smaller than the size of the block image) remaining for the division are merged into the respective adjacent block images. The person skilled in the art can adjust the division mode and the division number of the remote sensing image according to the requirement of image division.
And step S106, respectively determining the reflectivity grouping modes of a plurality of wave bands according to the feature reflectivity of the block grids in each block image. The process of specifically determining the grouping manner may include: obtaining the multiband ground object reflectivity of each block grid in each block image; sequencing the surface feature reflectivity of each block grid of each wave band to obtain a single-wave-band reflectivity sequence; naturally grouping the single-waveband reflectivity sequence to obtain a plurality of alternative grouping modes; selecting one of the multiple alternative grouping modes with the minimum intra-group deviation as a reflectivity grouping mode of the current band; and counting the reflectivity grouping modes of a plurality of wave bands. The blocking grid may be a pixel in the image or a set of multiple neighboring pixels.
For example, a block image has i rows and j columns of block grids and has S wave band feature reflectivities, the feature reflectivities of the first wave band of the block grids of i rows and j columns are firstly sorted, and the reflectivity grouping mode of the first wave band is obtained by naturally grouping and performing deviation calculation on the reflectivity sequence of the first wave band. And performing the S wave bands one by one to obtain S reflectivity grouping modes.
The calculation method for selecting the reflectivity grouping method from the plurality of candidate grouping methods through deviation may be: calculating the square deviation sum of squares of class means of a plurality of candidate grouping modes; and determining the alternative grouping mode with the minimum square deviation sum of the category mean values.
The number of groups for natural grouping may be set according to the number of natural types of land included in the remote sensing image to be segmented or a number set manually. For example, before the step of naturally grouping the feature reflectivity of the segmented image, the method may further include: estimating the number of natural land types contained in the remote sensing image to be segmented; and setting the estimated natural land type quantity as the grouping quantity of the natural grouping.
Step S108, determining the dividing lines of the block images according to the reflectivity grouping mode of a plurality of wave bands. One way to determine the split line may be: respectively calculating the difference value of the reflectivity at two sides of the grouping interval in the reflectivity grouping mode of a plurality of wave bands; sorting the difference values of the reflectivity from large to small; determining a blocking grid corresponding to the difference value of the set number of reflectivity which is ranked in front; taking the blocking grid as a breakpoint position; and connecting the positions of the breakpoints to obtain the dividing lines of the block images. The difference of the reflectivities at the two sides of the grouping interval in the reflectivity grouping mode refers to the difference of the last reflectivity of the first group and the first reflectivity of the second group, the difference of the last reflectivity of the second group and the first reflectivity of the third group, … … and the difference of the last reflectivity of the last but-one group and the first reflectivity of the last but-one group.
And step S110, merging the dividing lines of the plurality of block images to obtain a dividing map of the remote sensing image to be divided.
The image segmentation method fully excavates the natural difference rule of the spectral reflectivity of the ground object, and is good in data classification effect and high in calculation efficiency. The ground object reflectivity of a plurality of wave bands is comprehensively considered, and the segmentation accuracy is further improved.
FIG. 2 is a diagram illustrating a reflectivity grouping method for determining a band for a block image in an image segmentation method according to an embodiment of the present invention. As shown in fig. 2, the process of determining the reflectivity grouping manner of a band may include:
step S202, the reflectivity of the wave band of each block grid in the block image is sequenced from small to large to obtain a wave band reflectivity sequence rho ij Where i represents a row of the block image and j represents a column of the block image.
In step S204, the number of packets is determined, and for example, the number of natural classes e may be selected as the number of packets f.
And step S206, naturally grouping the waveband reflectivity sequences to obtain a plurality of alternative grouping modes. That is, natural grouping results in a variety of grouping methods, for example, the number of packets is denoted as d.
Step S208, calculating the square deviation sum of squares of the category mean values of the alternative grouping modes. The calculation algorithm may include:
calculating the mean value of the reflectivity in the group according to the formula (1)
x represents the total number of raster rows of the tile image within the group and y represents the total number of raster columns of the tile image within the group, i.e., the group includes x y rasters.
The square deviation of the mean of the classes within each group of the group, SDAM, is calculated according to equation (2):
calculating the square deviation sum of squares of the class means of the candidate grouping mode SDCM _ ALL according to formula (3):
in formula (3), i is the group number of the subgroup, and f is the total number of subgroups.
Step S210, finding out the minimum value SDCM _ ALL from SDCM _ ALL of a plurality of candidate grouping modes min 。
Step S212, sending SDCM _ ALL min The corresponding reflectivity grouping mode is the wave band. That is, finding SDCM _ ALL from d packet modes min A corresponding one.
The wave band is set according to the wave band data of the remote sensing image. The different wave bands have different reflectivity due to the difference of the feature characteristics, and the data accuracy can be improved by processing the data of each wave band. The method of this embodiment determines the reflectivity grouping manner for a plurality of bands one by one to obtain the reflectivity grouping manner for the plurality of bands.
Fig. 3 is a schematic diagram illustrating the determination of the segmentation lines of the segmented image in the image segmentation method according to an embodiment of the present invention. As shown in fig. 3, the step of determining the partition lines of the segmented image according to the reflectivity grouping manner of the plurality of bands may include:
step S302, respectively calculating the difference of the reflectances at two sides of the packet interval in the reflectivity grouping mode of the multiple bands, that is, counting the SDCM _ ALL of each band min In the corresponding grouping manner, the difference between the reflectivity of the last grid of the previous grouping and the reflectivity of the first grid of the next grouping. I.e. the difference in reflectivity of the grid between the groups of a plurality of set bands is counted. E.g. counting the first band, SDCM _ ALL min The difference between the first maximum value and the second minimum value in the f determined groups (taking 5 as an example, the specific values can be flexibly adjusted) is represented as Z11, the second maximum value and the third minimum value are represented as Z12, the third maximum value and the fourth minimum value are represented as Z13, and the fourth maximum value and the fifth minimum value are represented as Z14. The corresponding values of the second band are Z21, Z22, Z23, Z24, respectively, the corresponding values of the S-th band are ZS1, ZS2, ZS3, ZS4, respectively. Where S is the total number of bands. As described aboveEach band is naturally grouped into 4 subgroups, by way of example only, and one skilled in the art can set the number of subgroups as desired.
Step S304, the reflectivity difference values are sequenced to obtain a difference value sequence. For example, Z11, Z12, Z13, Z14, Z21, Z22, Z23, Z24, ZS1, ZS2, ZS3, ZS4 are ordered from large to small.
Step S306, the block grids corresponding to the differences with the quantity ranked at the top in the difference sequence are used as breakpoint positions. That is, the largest f-1 value is selected as the positions of f-1 breakpoints of the block image, that is, the positions of the f types of segmentation finally, and further combined to obtain the segmentation lines of the block image.
The image segmentation method in the above embodiment performs image segmentation according to the size of the feature of the environmental protection information to be extracted (it should be understood by those skilled in the art that the method is also applicable to image segmentation of other feature types besides the image segmentation for the environmental protection information). And acquiring a partitioning line of the partitioned multiband image based on the partitioning scheme of the partitioned image single-waveband image. The method can fully utilize the natural difference rule of multispectral image ground object information and realize accurate and efficient image segmentation.
FIG. 4 is a schematic diagram of a computer device according to one embodiment of the invention. The computer device 400 may include a memory 420, a processor 410, and a machine-executable program 421 stored in the memory 420 and running on the processor 410, and the processor 410 executes the machine-executable program 421 to implement the image segmentation method of any of the above embodiments.
The computer device 400 may be, for example, a server, a desktop computer, a notebook computer, a tablet computer, or a smartphone. In some examples, computer device 400 may be a cloud computing node. Computer device 400 may be described in the general context of computer system-executable instructions, such as program modules, being executed by a computer system. Generally, program modules may include routines, programs, objects, components, logic, data structures, etc. that perform particular tasks or implement particular abstract data types. Computer device 400 may be practiced in distributed cloud computing environments where tasks are performed by remote processing devices that are linked through a communications network. In a distributed cloud computing environment, program modules may be located in both local and remote computer system storage media including memory storage devices.
Processor 410 may be a single core processor, a multi-core processor, a computing cluster, or any number of other configurations. The memory 421 may include Random Access Memory (RAM), read only memory, flash memory, or any other suitable storage system.
Thus, it should be appreciated by those skilled in the art that while a number of exemplary embodiments of the invention have been illustrated and described in detail herein, many other variations or modifications consistent with the principles of the invention may be directly determined or derived from the disclosure of the present invention without departing from the spirit and scope of the invention. Accordingly, the scope of the invention should be understood and interpreted to cover all such other variations or modifications.
Claims (9)
1. A method for segmenting an image comprises the following steps:
obtaining a remote sensing image to be segmented of a region to be analyzed;
determining the size of a block image, and blocking the remote sensing image to be segmented according to the size of the block image to obtain a plurality of block images;
determining the reflectivity grouping modes of a plurality of wave bands according to the surface feature reflectivity of the block grids in each block image;
determining the dividing lines of the block images according to the reflectivity grouping modes of the plurality of wave bands; and
and merging the segmentation lines of the plurality of segmented images to obtain a segmentation image of the remote sensing image to be segmented.
2. The image segmentation method according to claim 1, wherein the step of obtaining the remote sensing image to be segmented of the region to be analyzed comprises:
acquiring the position information of the area to be analyzed;
acquiring an original image corresponding to the position information;
preprocessing the original image;
and cutting the preprocessed image by using the polygon with the set vector to obtain the remote sensing image with the required shape.
3. The method for segmenting an image according to claim 1, wherein said step of determining the size of the segmented image comprises:
identifying and extracting the size of the target category in the remote sensing image to be segmented;
and expanding the size of the extracted target category in the remote sensing image to be segmented by setting the number of pixels to obtain the size of the segmented image.
4. The image segmentation method according to claim 1, wherein the step of segmenting the remote sensing image to be segmented according to the size of the segmented image further comprises:
and merging the parts of the remote sensing image to be segmented which are not divided into adjacent segmented images.
5. The method for segmenting an image according to claim 1, wherein the step of determining the reflectivity grouping manner of a plurality of wavelength bands according to the feature reflectivity of the block grid in each of the block images comprises:
obtaining the multi-band ground object reflectivity of each block grid in each block image;
sequencing the surface feature reflectivity of each blocking grid of each wave band to obtain a single-wave-band reflectivity sequence;
naturally grouping the single-waveband reflectivity sequence to obtain a plurality of alternative grouping modes;
selecting one of the multiple alternative grouping modes with the minimum deviation in the group as a reflectivity grouping mode of the current band;
and counting the reflectivity grouping modes of a plurality of wave bands.
6. The method for segmenting an image according to claim 5, wherein the step of selecting one of the plurality of candidate grouping methods having the smallest intra-group variation includes:
calculating the square deviation and the sum of squares of the mean values of the categories of the plurality of candidate grouping modes;
and determining the alternative grouping mode with the minimum square deviation sum of the squared deviations of the class means.
7. The image segmentation method according to claim 5, wherein the step of naturally grouping the single-band reflectivity sequences further comprises:
estimating the number of natural land types contained in the remote sensing image to be segmented;
and setting the estimated natural land type quantity as the grouping quantity of the natural grouping.
8. The method for segmenting an image according to claim 5, wherein the step of determining the segmentation lines of the segmented image according to the reflectivity grouping manner of the plurality of wavelength bands comprises:
calculating the difference of the reflectances at two sides of the grouping interval in the reflectivity grouping modes of the multiple bands respectively;
sorting the differences in reflectivity from large to small;
determining a blocking grid corresponding to the difference value of the reflectivity of a set number which is ranked in front;
taking the block grid as a breakpoint position;
and connecting the breakpoint positions to obtain the dividing lines of the block images.
9. A computer device comprising a memory, a processor and a machine-executable program stored on the memory and running on the processor, wherein the processor executes the machine-executable program to implement the image segmentation method according to any one of claims 1 to 8.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202211542883.XA CN115861838A (en) | 2022-12-02 | 2022-12-02 | Image segmentation method and computer equipment |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202211542883.XA CN115861838A (en) | 2022-12-02 | 2022-12-02 | Image segmentation method and computer equipment |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN115861838A true CN115861838A (en) | 2023-03-28 |
Family
ID=85669562
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202211542883.XA Pending CN115861838A (en) | 2022-12-02 | 2022-12-02 | Image segmentation method and computer equipment |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN115861838A (en) |
-
2022
- 2022-12-02 CN CN202211542883.XA patent/CN115861838A/en active Pending
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| US11615615B2 (en) | Method and apparatus for extracting mountain landscape buildings based on high-resolution remote sensing images | |
| CN106384081B (en) | Slope farmland extraction method and system based on high-resolution remote sensing image | |
| CN110472661B (en) | Automatic change detection method and system based on historical background and current remote sensing image | |
| US9384399B2 (en) | Method and system for processing image data obtained from scanning a network infrastructure | |
| US9064150B2 (en) | Aerial image segmentation for refineries | |
| US10768303B2 (en) | Method for identifying individual trees in airborne lidar data and corresponding computer program product | |
| CN112381013B (en) | Urban vegetation inversion method and system based on high-resolution remote sensing image | |
| CN111222539B (en) | Method for optimizing and expanding supervision classification samples based on multi-source multi-temporal remote sensing image | |
| US11804025B2 (en) | Methods and systems for identifying topographic features | |
| US20080270031A1 (en) | Geospatial modeling system providing data thinning of geospatial data points and related methods | |
| CN106096497A (en) | A kind of house vectorization method for polynary remotely-sensed data | |
| CN109031235B (en) | Method for rapidly acquiring three-dimensional contour line data of radar basic reflectivity | |
| CN114898118A (en) | Automatic statistical method and system for power transmission line house removal amount based on multi-source point cloud | |
| CN109241369B (en) | Rainfall isopleth construction method based on grid stretching method | |
| CN115861838A (en) | Image segmentation method and computer equipment | |
| CN113343819B (en) | Efficient unmanned airborne SAR image target segmentation method | |
| CN116245400A (en) | Mining area landscape pattern evolution analysis method based on high-resolution remote sensing | |
| Amri et al. | Stadium detection from Alsat-2 and Google-Earth multispectral images using YOLOv5 and Mask R-CNN | |
| Belarmino et al. | Implementation of image processing and machine learning in high resolution aerial image datasets for lake resource usage, aquaculture, and coastal community | |
| McLaughlin et al. | Change detection over the state of Queensland using high resolution Planet satellite mosaics | |
| Hamraz et al. | Remote sensing of forests using discrete return airborne LiDAR | |
| CN113160262A (en) | Oyster row extraction method, system and medium based on high-resolution satellite remote sensing image | |
| Zhai et al. | Identifying wind turbines from multiresolution and multibackground remote sensing imagery | |
| CN114511724A (en) | Large-scale remote sensing image soil change pseudo label manufacturing and change detection method | |
| Rhee et al. | Comparing Stereo Image Matching Performance by Multidimensional Search Windows |
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 |