CN116309057A - Remote sensing image splicing method, device, computer equipment and storage medium - Google Patents
Remote sensing image splicing method, device, computer equipment and storage medium Download PDFInfo
- Publication number
- CN116309057A CN116309057A CN202310240878.1A CN202310240878A CN116309057A CN 116309057 A CN116309057 A CN 116309057A CN 202310240878 A CN202310240878 A CN 202310240878A CN 116309057 A CN116309057 A CN 116309057A
- Authority
- CN
- China
- Prior art keywords
- remote sensing
- sensing image
- pixel value
- current
- effective pixel
- 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 46
- 239000011159 matrix material Substances 0.000 claims description 62
- 238000004590 computer program Methods 0.000 claims description 28
- 238000012545 processing Methods 0.000 claims description 6
- 238000010586 diagram Methods 0.000 description 9
- 238000003491 array Methods 0.000 description 4
- 238000005516 engineering process Methods 0.000 description 3
- 238000012217 deletion Methods 0.000 description 2
- 230000037430 deletion Effects 0.000 description 2
- 230000001360 synchronised effect Effects 0.000 description 2
- 230000005540 biological transmission Effects 0.000 description 1
- 125000004122 cyclic group Chemical group 0.000 description 1
- 238000011835 investigation Methods 0.000 description 1
- 239000010410 layer Substances 0.000 description 1
- 239000004973 liquid crystal related substance Substances 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
- 238000012544 monitoring process Methods 0.000 description 1
- 238000012216 screening Methods 0.000 description 1
- 230000003068 static effect Effects 0.000 description 1
- 239000002344 surface layer Substances 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
- G06T2207/00—Indexing scheme for image analysis or image enhancement
- G06T2207/10—Image acquisition modality
- G06T2207/10032—Satellite or aerial image; Remote sensing
Landscapes
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Engineering & Computer Science (AREA)
- Theoretical Computer Science (AREA)
- Image Processing (AREA)
Abstract
The application relates to a remote sensing image splicing method, a remote sensing image splicing device, computer equipment and a storage medium. The method comprises the following steps: the method comprises the steps of obtaining a current effective pixel value corresponding to a current boundary point of a first remote sensing image, determining a corresponding forward boundary point and a corresponding backward boundary point according to the current boundary point, obtaining a corresponding forward effective pixel value corresponding to the forward boundary point and a corresponding backward effective pixel value corresponding to the backward boundary point, determining an integrity result corresponding to the first remote sensing image according to the current effective pixel value, the forward effective pixel value and the backward effective pixel value, obtaining a second remote sensing image corresponding to the first remote sensing image when the integrity result indicates that the first remote sensing image is an incomplete image, and splicing the first remote sensing image and the second remote sensing image to obtain a target remote sensing image. The method can improve the image quality of the remote sensing image.
Description
Technical Field
The present disclosure relates to the field of computer technologies, and in particular, to a remote sensing image stitching method, a device, a computer device, and a storage medium.
Background
The remote sensing technology is a modern comprehensive technology for receiving electromagnetic wave information from various ground objects on the surface layer of the earth from the high altitude or outer space, and carrying out remote measurement and control and identification on various ground objects and phenomena on the surface by scanning, photographing, transmitting and processing the information, and the remote sensing image greatly widens the space scale of earth observation and is widely applied to the fields of cadastral investigation, land utilization monitoring, urban planning, rescue and relief work and the like.
The satellite remote sensing image has the characteristics of wide acquisition range, strong timeliness and the like, and becomes one of the most important spatial data sources in practical application. In order to enable the remote sensing image service to be accessed smoothly in the application, the image data behind the service is usually required to be converted into image tiles organized in a pyramid structure, and the updating and slicing of the data behind the image service are more frequent along with the increasing requirement of industry application on the timeliness of the image.
In the operation process of the remote sensing image tiles, the tiles are often acquired in batches, and in this case, the tiles at the edges of the image range acquired each time are often incomplete, so that the quality of the remote sensing image is poor.
Disclosure of Invention
In view of the foregoing, it is desirable to provide a remote sensing image stitching method, apparatus, computer device, and storage medium that can improve the image quality of remote sensing images.
A remote sensing image stitching method, the method comprising:
acquiring a current effective pixel value corresponding to a current boundary point of the first remote sensing image, wherein the current boundary point is any boundary point;
determining corresponding forward boundary points and backward boundary points according to the current boundary points;
acquiring a forward effective pixel value corresponding to a forward boundary point and a backward effective pixel value corresponding to a backward boundary point;
determining an integrity result corresponding to the first remote sensing image according to the current effective pixel value, the forward effective pixel value and the backward effective pixel value;
when the integrity result shows that the first remote sensing image is an incomplete image, acquiring a second remote sensing image corresponding to the first remote sensing image;
and splicing the first remote sensing image and the second remote sensing image to obtain the target remote sensing image.
In one embodiment, determining the forward boundary point and the backward boundary point from the current boundary point includes: two boundary points in the first direction are determined to be forward boundary points based on the current boundary point as a starting point, and two boundary points in the second direction are determined to be backward boundary points based on the current boundary point as a starting point.
In one embodiment, determining the integrity result corresponding to the first remote sensing image according to the current effective pixel value, the forward effective pixel value and the backward effective pixel value includes: judging whether the current effective pixel value, the forward effective pixel value and the backward effective pixel value are continuous black pixel values, when the continuous black pixel value is judged, determining that the integrity result corresponding to the first remote sensing image is an incomplete image, and when the discontinuous black pixel value is judged, determining that the integrity result corresponding to the first remote sensing image is an complete image.
In one embodiment, when the discontinuous black pixel value is determined, determining that the integrity result corresponding to the first remote sensing image is a complete image includes: when the discontinuous black pixel value is determined, acquiring a next boundary point of the current boundary point in the first remote sensing image; and determining the next boundary point as a current boundary point, and returning to the step of acquiring the current effective pixel value corresponding to the current boundary point of the first remote sensing image until all the boundary points of the first remote sensing image are traversed, and determining the integrity result corresponding to the first remote sensing image as a complete image.
In one embodiment, acquiring a second remote sensing image corresponding to the first remote sensing image includes: and acquiring the remote sensing image row and column numbers associated with the first remote sensing image, and acquiring a second remote sensing image with the same remote sensing image row and column number from the incomplete remote sensing image library according to the remote sensing image row and column numbers.
In one embodiment, the method for determining the integrity result corresponding to the first remote sensing image according to the current effective pixel value, the forward effective pixel value and the backward effective pixel value comprises the steps of generating a corresponding current sparse matrix according to the current effective pixel value, generating a corresponding forward sparse matrix according to the forward effective pixel value, generating a corresponding backward sparse matrix according to the backward effective pixel value, judging whether the current sparse matrix, the forward sparse matrix and the backward sparse matrix are continuous all-zero element matrixes or not, determining that the integrity result corresponding to the first remote sensing image is a complete image when the non-continuous all-zero element matrixes are determined, and determining that the integrity result corresponding to the first remote sensing image is a non-complete image when the continuous all-zero element matrixes are determined.
In one embodiment, the method further comprises: and determining the target remote sensing image as a first remote sensing image, and returning to the step of acquiring the current effective pixel value corresponding to the current boundary point of the first remote sensing image until the integrity result corresponding to the target remote sensing image is a complete image.
A remote sensing image stitching device, the device comprising:
the first acquisition module is used for acquiring a current effective pixel value corresponding to a current boundary point of the first remote sensing image, wherein the current boundary point is any boundary point;
The processing module is used for determining corresponding forward boundary points and backward boundary points according to the current boundary points;
the second acquisition module is used for acquiring a forward effective pixel value corresponding to the forward boundary point and a backward effective pixel value corresponding to the backward boundary point;
the judging module is used for determining an integrity result corresponding to the first remote sensing image according to the current effective pixel value, the forward effective pixel value and the backward effective pixel value;
the third acquisition module is used for acquiring a second remote sensing image corresponding to the first remote sensing image when the integrity result indicates that the first remote sensing image is an incomplete image;
and the splicing module is used for splicing the first remote sensing image and the second remote sensing image to obtain a target remote sensing image.
A computer device comprising a memory, a processor and a computer program stored on the memory and executable on the processor, the processor implementing the steps of:
acquiring a current effective pixel value corresponding to a current boundary point of the first remote sensing image, wherein the current boundary point is any boundary point;
determining corresponding forward boundary points and backward boundary points according to the current boundary points;
acquiring a forward effective pixel value corresponding to a forward boundary point and a backward effective pixel value corresponding to a backward boundary point;
Determining an integrity result corresponding to the first remote sensing image according to the current effective pixel value, the forward effective pixel value and the backward effective pixel value;
when the integrity result shows that the first remote sensing image is an incomplete image, acquiring a second remote sensing image corresponding to the first remote sensing image;
and splicing the first remote sensing image and the second remote sensing image to obtain the target remote sensing image.
A computer readable storage medium having stored thereon a computer program which when executed by a processor performs the steps of:
acquiring a current effective pixel value corresponding to a current boundary point of the first remote sensing image, wherein the current boundary point is any boundary point;
determining corresponding forward boundary points and backward boundary points according to the current boundary points;
acquiring a forward effective pixel value corresponding to a forward boundary point and a backward effective pixel value corresponding to a backward boundary point;
determining an integrity result corresponding to the first remote sensing image according to the current effective pixel value, the forward effective pixel value and the backward effective pixel value;
when the integrity result shows that the first remote sensing image is an incomplete image, acquiring a second remote sensing image corresponding to the first remote sensing image;
and splicing the first remote sensing image and the second remote sensing image to obtain the target remote sensing image.
According to the remote sensing image stitching method, the device, the computer equipment and the storage medium, whether the first remote sensing image is a complete remote sensing image is judged through the effective pixel values corresponding to the current boundary point, the forward boundary point and the backward boundary point of the first remote sensing image, when the first remote sensing image is judged to be an incomplete remote sensing image, the problem of image quality of the first remote sensing image is explained, therefore, a second remote sensing image corresponding to the first remote sensing image is obtained, the first remote sensing image and the second remote sensing image are the same remote sensing image, but the image quality problem exists in the first remote sensing image and the second remote sensing image, but the possible positions are different, and finally the first remote sensing image and the second remote sensing image are stitched in a lossless manner, so that a stitched target remote sensing image is obtained. The image quality of the spliced target remote sensing image is higher than that of the first remote sensing image, and the incomplete remote sensing image can be spliced and updated in the splicing mode to obtain the target remote sensing image with higher image quality.
Drawings
FIG. 1 is a diagram of an application environment of a remote sensing image stitching method according to an embodiment;
FIG. 2 is a flowchart of a remote sensing image stitching method according to an embodiment;
FIG. 2A is a schematic diagram of a first remote sensing image according to an embodiment;
FIG. 2B is a schematic diagram of a second remote sensing image according to one embodiment;
FIG. 2C is a schematic diagram of a target remote sensing image according to one embodiment;
FIG. 3 is a flow chart of a boundary point determination step in one embodiment;
FIG. 4 is a flow chart of an integrity result determination step in one embodiment;
FIG. 5 is a flowchart illustrating a complete image determination step according to one embodiment;
FIG. 6 is a flowchart illustrating a second remote sensing image acquisition step according to an embodiment;
FIG. 7 is a flow chart of an integrity result determination step in one embodiment;
FIG. 8 is a flowchart of a remote sensing image stitching method according to an embodiment;
FIG. 9 is a block diagram illustrating a remote sensing image stitching device according to an embodiment;
FIG. 10 is an internal block diagram of a computer device in one embodiment;
FIG. 11 is an internal block diagram of a computer device in one embodiment.
Detailed Description
In order to make the objects, technical solutions and advantages of the present application more apparent, the present application will be further described in detail with reference to the accompanying drawings and examples. It should be understood that the specific embodiments described herein are for purposes of illustration only and are not intended to limit the present application.
The remote sensing image stitching method provided by the application can be applied to an application environment shown in fig. 1. Wherein the terminal 102 communicates with the server 104 via a network. The terminal 102 may be, but not limited to, various personal computers, notebook computers, smartphones, tablet computers, and portable wearable devices, and the server 104 may be implemented by a stand-alone server or a server cluster composed of a plurality of servers.
Specifically, the terminal 102 acquires a first remote sensing image, sends the first remote sensing image to the server 104, the server 104 acquires a current effective pixel value corresponding to a current boundary point of the first remote sensing image, the current boundary point is any boundary point, corresponding forward boundary point and backward boundary point are determined according to the current boundary point, a forward effective pixel value corresponding to the forward boundary point and a backward effective pixel value corresponding to the backward boundary point are acquired, an integrity result corresponding to the first remote sensing image is determined according to the current effective pixel value, the forward effective pixel value and the backward effective pixel value, when the integrity result indicates that the first remote sensing image is an incomplete image, a second remote sensing image corresponding to the first remote sensing image is acquired, and the first remote sensing image and the second remote sensing image are spliced to obtain the target remote sensing image. Finally, the server 104 returns the target remote sensing image to the terminal 102.
In another embodiment, the terminal 102 obtains a current effective pixel value corresponding to a current boundary point of the first remote sensing image, the current boundary point is any boundary point, a corresponding forward boundary point and a corresponding backward boundary point are determined according to the current boundary point, a corresponding forward effective pixel value corresponding to the forward boundary point and a corresponding backward effective pixel value corresponding to the backward boundary point are obtained, an integrity result corresponding to the first remote sensing image is determined according to the current effective pixel value, the forward effective pixel value and the backward effective pixel value, when the integrity result indicates that the first remote sensing image is an incomplete image, a second remote sensing image corresponding to the first remote sensing image is obtained, and the first remote sensing image and the second remote sensing image are spliced to obtain the target remote sensing image.
In one embodiment, as shown in fig. 2, a remote sensing image stitching method is provided, and the method is applied to the terminal or the server in fig. 1 for illustration, and includes the following steps:
The remote sensing image is a film or a photo for recording electromagnetic wave sizes of various ground objects, and is mainly divided into an aerial photo and a satellite photo, and the remote sensing image has a plurality of boundaries, for example, four boundaries. The boundary is composed of a plurality of boundary points, and each boundary point has a corresponding effective pixel value.
Specifically, the first remote sensing image is acquired, or the first remote sensing image is acquired from the stored images, any boundary point of any boundary of the first remote sensing image is acquired as a current boundary point, and an effective pixel value corresponding to the current boundary point, that is, a current effective pixel value, is a value given by a computer when the first remote sensing image is digitized, and represents average brightness information of a certain small square in the first remote sensing image, or average reflection (transmission) density information of the small square.
And 204, determining corresponding forward boundary points and backward boundary points according to the current boundary points.
The forward boundary point is a boundary point in a first direction corresponding to a current boundary point in the first remote sensing image, for example, a boundary point on the left side of the current boundary point in the first remote sensing image is a forward boundary point, and the backward boundary point is a boundary point in a second direction corresponding to the current boundary point in the first remote sensing image, for example, a boundary point on the right side of the current boundary point in the first remote sensing image is a backward boundary point. Wherein the second direction may be the opposite direction of the first direction. Specifically, in the first remote sensing image, a current boundary point is taken as a starting point, a preset number of boundary points are obtained according to a first direction to be taken as forward boundary points, a same preset number of boundary points are obtained according to a second direction to be taken as backward boundary points, and the preset number can be obtained according to actual service requirements or actual product requirements or actual application scenes.
The method comprises the steps of determining a forward boundary point and a backward boundary point, wherein the boundary point of any boundary in a first remote sensing image corresponds to an effective pixel value, and then acquiring the forward effective pixel value corresponding to the forward boundary point and the backward effective pixel value corresponding to the backward boundary point after determining the forward boundary point and the backward boundary point.
The integrity result represents the integrity of the first remote sensing image, that is, whether the first remote sensing image is damaged, specifically, after the current effective pixel value, the forward effective pixel value and the backward effective pixel value are obtained, whether the current effective pixel value, the forward effective pixel value and the backward effective pixel value are continuous black pixels or continuous non-zero element matrixes can be judged, and a judgment standard can be set according to actual service requirements, actual product requirements or actual application scenes.
In one embodiment, it is determined whether the current effective pixel value, the forward effective pixel value, and the backward effective pixel value are consecutive black pixels, and when it is determined that consecutive black pixels are consecutive black pixels, it is indicated that the first remote sensing image is damaged or missing, so that it may be determined that the integrity result corresponding to the first remote sensing image is represented as an incomplete image. On the contrary, when the discontinuous black pixels are determined, the first remote sensing image is not damaged or missing, so that the integrity result corresponding to the first remote sensing image can be determined to be expressed as a complete image.
In another embodiment, the current effective pixel value, the forward effective pixel value and the backward effective pixel value can be converted into corresponding sparse matrixes, whether the sparse matrixes corresponding to the current effective pixel value, the forward effective pixel value and the backward effective pixel value are continuous non-zero element matrixes or not is judged according to elements in the sparse matrixes, when the continuous non-zero element matrixes are judged, the problem that the first remote sensing image is not damaged or lost is described, and therefore the integrity result corresponding to the first remote sensing image can be determined to be expressed as a complete image. On the contrary, when the discontinuous non-zero element matrix is determined, the problem that the first remote sensing image is damaged or missing is described, so that the integrity result corresponding to the first remote sensing image can be determined to be represented as an incomplete image.
In step 210, when the integrity result indicates that the first remote sensing image is an incomplete image, a second remote sensing image corresponding to the first remote sensing image is obtained.
Specifically, when the integrity result indicates that the first remote sensing image is an incomplete image, it is indicated that the first remote sensing image has a problem of damage or lack of damage, etc., and may affect the image quality of the first remote sensing image, so that a second remote sensing image corresponding to the first remote sensing image may be acquired, specifically, may be acquired through a remote sensing image identifier, for example, acquiring a second remote sensing image identical to the remote sensing image identifier of the first remote sensing image, or may be acquired through a remote sensing image rank number associated with the first remote sensing image, for example, acquiring a second remote sensing image identical to the remote sensing image rank number associated with the first remote sensing image.
For example, as shown in fig. 2A, fig. 2A shows a schematic view of a first remote sensing image in one embodiment, and fig. 2B shows a schematic view of a second remote sensing image in one embodiment, where the first remote sensing image and the second remote sensing image may be remote sensing images with the same remote sensing image identifier or the same remote sensing image row number, but the first remote sensing image and the second remote sensing image may have the same position loss or deletion, or may have the different position loss or deletion, or the like.
In step 212, the first remote sensing image and the second remote sensing image are spliced to obtain the target remote sensing image.
Specifically, after the first remote sensing image and the second remote sensing image are obtained, the first remote sensing image and the second remote sensing image are spliced to obtain the target remote sensing image. At this time, the target remote sensing image may be a complete remote sensing image, and the first remote sensing image and the second remote sensing image may be accurately spliced and quickly spliced, and for the incomplete first remote sensing image, the complete remote sensing image may be obtained by splicing. For example, as shown in fig. 2C, fig. 2C is a schematic diagram of a target remote sensing image in an embodiment, and fig. 2C may be a result of stitching the first remote sensing image shown in fig. 2A and the second remote sensing image shown in fig. 2B.
In the above method for stitching the remote sensing images, whether the first remote sensing image is a complete remote sensing image is judged by the effective pixel values corresponding to the current boundary point, the forward boundary point and the backward boundary point of the first remote sensing image, when the first remote sensing image is judged to be an incomplete remote sensing image, the image quality problem of the first remote sensing image is described, so that the second remote sensing image corresponding to the first remote sensing image is obtained, the first remote sensing image and the second remote sensing image are the same remote sensing image, but the image quality problem exists in both the first remote sensing image and the second remote sensing image, but the possible positions are different, and therefore, the first remote sensing image and the second remote sensing image are subjected to lossless stitching to obtain the stitched target remote sensing image. The image quality of the spliced target remote sensing image is higher than that of the first remote sensing image, and the incomplete remote sensing image can be spliced and updated in the splicing mode to obtain the target remote sensing image with higher image quality.
In one embodiment, as shown in fig. 3, determining the forward boundary point and the backward boundary point from the current boundary point includes:
The first remote sensing image comprises a plurality of boundaries, each boundary comprises a plurality of boundary points, a current boundary point is determined from any boundary point of any boundary, and a forward boundary point and a backward boundary point can be acquired according to a specified direction by taking the current boundary point as a starting point. Specifically, in the first remote sensing image, the current boundary point is taken as a starting point, a preset number of boundary points are obtained according to a first direction as forward boundary points, the preset number can be two, and the first direction can be the left side of the current boundary point, so that the current boundary point is taken as a starting point, and the two boundary points on the left side are obtained as forward boundary points.
Further, in the first remote sensing image, the current boundary point is taken as a starting point, a preset number of boundary points are obtained according to a second direction as backward boundary points, the preset number can be two, and the second direction can be the right side of the current boundary point, so that the current boundary point is taken as a starting point, and the two boundary points on the right side are obtained as backward boundary points.
In one embodiment, as shown in fig. 4, determining the integrity result corresponding to the first remote sensing image according to the current effective pixel value, the forward effective pixel value and the backward effective pixel value includes:
In step 404, when it is determined that the continuous black pixel values are determined, the integrity result corresponding to the first remote sensing image is determined to be an incomplete image.
In step 406, when it is determined that the black pixel value is discontinuous, the integrity result corresponding to the first remote sensing image is determined to be a complete image.
After the current effective pixel value, the forward effective pixel value and the backward effective pixel value are obtained, whether the first remote sensing image has quality problems such as damage, missing and the like can be judged through the current effective pixel value, the forward effective pixel value and the backward effective pixel value. Specifically, it is determined whether the current effective pixel value, the forward effective pixel value, and the backward effective pixel value are consecutive black pixel values, and the black pixel value is a value corresponding to the black pixel, for example, the black pixel value is (0, 0). Wherein the current effective pixel value, the forward effective pixel value and the backward effective pixel value are continuous and are black pixel values one by one.
Further, after the current effective pixel value, the forward effective pixel value and the backward effective pixel value are determined to be continuous black pixel values, the quality problems such as damage and missing of the first remote sensing image are described, so that the integrity result corresponding to the first remote sensing image can be determined to be an incomplete image. On the contrary, after the current effective pixel value, the forward effective pixel value and the backward effective pixel value are determined to be continuous black pixel values, the quality problems such as damage, missing and the like of the first remote sensing image are not caused, so that the integrity result corresponding to the first remote sensing image can be determined to be a complete image.
In one embodiment, as shown in fig. 5, when determining that the black pixel values are discontinuous, determining that the integrity result corresponding to the first remote sensing image is a complete image includes:
in step 502, when it is determined that the black pixel value is discontinuous, a next boundary point of the current boundary point in the first remote sensing image is obtained.
And step 504, determining the next boundary point as the current boundary point, and returning to the step of acquiring the current effective pixel value corresponding to the current boundary point of the first remote sensing image.
When the current effective pixel value, the forward effective pixel value and the backward effective pixel value are determined to be continuous black pixel values, only the current boundary point can be described as having no quality problem, therefore, all boundary points of all boundaries of the first remote sensing image need to be traversed, and when all boundary points of all boundaries are discontinuous black pixel values, the quality problems of damage, missing and the like of the first remote sensing image can be described, and the integrity result corresponding to the first remote sensing image is determined as a complete image.
Specifically, when the current effective pixel value, the forward effective pixel value and the backward effective pixel value are determined to be continuous black pixel values, acquiring the next boundary point of the current boundary point of the first remote sensing image in the appointed direction, determining the next boundary point as the current boundary point, and returning to the step of acquiring the current effective pixel value corresponding to the current boundary point of the first remote sensing image until all boundary points of all boundaries of the first remote sensing image are traversed, wherein when all boundary points of all boundaries of the first remote sensing image are determined to be discontinuous black pixel values, the integrity result corresponding to the first remote sensing image can be determined to be a complete image.
In one embodiment, as shown in fig. 6, acquiring a second remote sensing image corresponding to the first remote sensing image includes:
Each remote sensing image corresponds to a remote sensing image line and column number, the remote sensing image line and column number is equivalent to the image identification of the first remote sensing image, and different remote sensing images correspond to different remote sensing image line and column numbers, so that the remote sensing image line and column numbers associated with the first remote sensing image are obtained, and the second remote sensing image with the same remote sensing image line and column number is searched from the incomplete remote sensing image library through the remote sensing image line and column numbers. The incomplete remote sensing image library is pre-stored with a plurality of incomplete remote sensing images, each incomplete remote sensing image is associated with a corresponding remote sensing image row number, and the remote sensing images with the integrity result being the incomplete images can be stored in the incomplete remote sensing image library. That is, a second remote sensing image matched with the first remote sensing image is searched from the incomplete remote sensing image library, and the second remote sensing image is an incomplete remote sensing image, and may have different damage, missing or other flaw parts with the first remote sensing image, but belongs to the same remote sensing image.
In one embodiment, as shown in fig. 7, determining the integrity result corresponding to the first remote sensing image according to the current effective pixel value, the forward effective pixel value and the backward effective pixel value includes:
and step 702, generating a corresponding current sparse matrix according to the current effective pixel value.
In step 710, when it is determined that the non-continuous matrix is the zero element matrix, the integrity result corresponding to the first remote sensing image is determined to be the complete image.
In step 712, when it is determined that the continuous matrix is all zero, it is determined that the integrity result corresponding to the first remote sensing image is an incomplete image.
Specifically, converting the current effective pixel value, the forward effective pixel value and the backward effective pixel value into corresponding sparse matrixes to obtain the current sparse matrix corresponding to the current effective pixel value, and obtaining the forward sparse matrix corresponding to the forward effective pixel value and the backward sparse matrix corresponding to the backward effective pixel value.
Further, whether the current sparse matrix, the forward sparse matrix and the backward sparse matrix are continuous all-zero element matrixes is judged, if all elements in the continuous sparse matrix are zero, the quality problems such as damage and missing of the corresponding remote sensing image are indicated, otherwise, if all elements in the continuous sparse matrix are not all zero, the pixel value corresponding to the sparse matrix is not a black pixel value, and no flaw is indicated to the corresponding remote sensing image.
Specifically, when the current sparse matrix, the forward sparse matrix and the backward sparse matrix are determined to be continuous non-zero element matrices, the next boundary point can be obtained, all boundary points in the first remote sensing image are traversed until the sparse matrices corresponding to all the boundary points are continuous non-zero element matrices, and the integrity result corresponding to the first remote sensing image can be determined to be the non-complete image.
Otherwise, when the current sparse matrix, the forward sparse matrix and the backward sparse matrix are determined to be discontinuous all-zero element matrices, or when the current sparse matrix, the forward sparse matrix and the backward sparse matrix are determined to be non-all-zero element matrices, the integrity result corresponding to the first remote sensing image can be determined to be a complete image.
In one embodiment, as shown in fig. 8, the method further includes:
In order to ensure the image quality of the spliced target remote sensing image, the spliced target remote sensing image needs to be detected, specifically, the target remote sensing image is determined to be the first remote sensing image, the step of obtaining the current effective pixel value corresponding to the current boundary point of the first remote sensing image is performed again until all boundary points of all boundaries of the target remote sensing image are traversed, the integrity result corresponding to the target remote sensing image can be determined to be a complete image, namely, the spliced target remote sensing image can overcome the image quality problems of the first remote sensing image and the second remote sensing image.
In a specific application scenario, the remote sensing image stitching method is described by the following steps:
in the embodiment of the disclosure, firstly, any point on the effective pixel value boundary of a remote sensing image (a first remote sensing image) is acquired, the boundary point is traversed, whether five continuous pixels are black pixels or not is judged, if yes, the remote sensing image is an incomplete remote sensing image, if not, the remote sensing image is a complete remote sensing image, then the complete remote sensing image is stored in a complete remote sensing image database, then the line number of the incomplete remote sensing image is calculated, whether the remote sensing image is in the incomplete remote sensing image database or not is judged, if not, the incomplete remote sensing image is stored in a library, and if yes, the incomplete remote sensing image is combined with the incomplete remote sensing image (a second remote sensing image) matched in the library, so that a target remote sensing image is obtained. And finally judging whether the boundary points of the effective pixel values of the combined target remote sensing images are black pixels or not, and circularly traversing the process until all new remote sensing images are traversed, so as to finish the lossless splicing of the remote sensing images.
Firstly, any point on the boundary of an effective pixel value of a remote sensing image is acquired, boundary points are traversed, whether five continuous pixels are black pixels or not is judged, if yes, the remote sensing image is an incomplete remote sensing image, and if not, the remote sensing image is a complete remote sensing image;
then storing the complete remote sensing image into a complete remote sensing image database, calculating the row number of the incomplete remote sensing image, judging whether the remote sensing image is in the incomplete remote sensing image database, storing the remote sensing image into a library if the remote sensing image is not in the incomplete remote sensing image database, and merging the remote sensing image with the remote sensing image matched with the library if the remote sensing image is in the incomplete remote sensing image database to obtain a target remote sensing image;
and finally judging whether the boundary points of the effective pixel values of the combined target remote sensing images are black pixels or not, and circularly traversing the process until all new remote sensing images are traversed, so as to finish lossless splicing of the remote sensing images.
In the disclosed example, the execution steps may be summarized as:
screening a complete remote sensing image;
firstly, obtaining the total number of lines and the total number of columns of a current image, performing cyclic traversal according to the total number of lines and the total number of columns, reading 256 lines and 256 columns of blocks each time, converting pixel values of each block into a sparse matrix for faster positioning to an effective value boundary point, pointing a pointer to a first array, then selecting front and rear arrays, judging whether all the five arrays are 0 elements, and if so, judging that the remote sensing image is an incomplete remote sensing image; if the non-zero element array is empty, the next array is continuously read, and the process is continuously performed, if all arrays are traversed, the continuous 5 arrays with boundaries are not all composed of 0 elements, the remote sensing image is a complete remote sensing image, and the remote sensing image is stored in a complete remote sensing image database.
Step two incomplete remote sensing image merging
Traversing the incomplete remote sensing image library according to the row and column numbers of the incomplete remote sensing images, and searching whether the incomplete remote sensing image library exists.
If the remote sensing image corresponding to the rank number does not exist in the incomplete remote sensing image library, storing the remote sensing image into the incomplete remote sensing image library;
if the remote sensing image corresponding to the rank number exists in the incomplete remote sensing image library, the pixels of the remote sensing image matched with the remote sensing image in the library are converted into sparse matrixes, then the two matrixes are combined, and the combined target remote sensing image is named according to the rank number.
Step three, judging whether the target remote sensing image has black edges or not
And (3) converting each pixel of the combined target remote sensing image into a sparse matrix, and repeating the step one. And if the target remote sensing image is the incomplete target remote sensing image, executing the second step.
Step four, entering a complete remote sensing image into a library
And if the remote sensing image is a complete remote sensing image, storing the complete remote sensing image into a complete remote sensing image library.
Step five, new remote sensing image lossless splicing
The process is cycled through until there is no new remote sensing image.
It should be understood that, although the steps in the above-described flowcharts are shown in order as indicated by the arrows, these steps are not necessarily performed in order as indicated by the arrows. The steps are not strictly limited to the order of execution unless explicitly recited herein, and the steps may be executed in other orders. Moreover, at least some of the steps in the flowcharts described above may include a plurality of sub-steps or stages that are not necessarily performed at the same time, but may be performed at different times, and the order of execution of the sub-steps or stages is not necessarily sequential, but may be performed alternately or alternately with at least a part of the sub-steps or stages of other steps or other steps.
In one embodiment, as shown in fig. 9, a remote sensing image stitching apparatus 900 is provided, including: a first obtaining module 902, a processing module 904, a second obtaining module 906, a judging module 908, a third obtaining module 910, and a splicing module 912, wherein:
the first obtaining module 902 is configured to obtain a current valid pixel value corresponding to a current boundary point of the first remote sensing image, where the current boundary point is any boundary point.
A processing module 904, configured to determine a corresponding forward boundary point and a corresponding backward boundary point according to the current boundary point.
A second obtaining module 906, configured to obtain a forward valid pixel value corresponding to the forward boundary point and a backward valid pixel value corresponding to the backward boundary point.
The determining module 908 is configured to determine an integrity result corresponding to the first remote sensing image according to the current effective pixel value, the forward effective pixel value, and the backward effective pixel value.
The third obtaining module 910 is configured to obtain a second remote sensing image corresponding to the first remote sensing image when the integrity result indicates that the first remote sensing image is an incomplete image.
And the stitching module 912 is configured to stitch the first remote sensing image and the second remote sensing image to obtain a target remote sensing image.
In one embodiment, the processing module 904 determines that two boundary points in the first direction are forward boundary points based on the current boundary point as a starting point and determines that two boundary points in the second direction are backward boundary points based on the current boundary point as a starting point.
In one embodiment, the determining module 908 determines whether the current active pixel value, the forward active pixel value, and the backward active pixel value are consecutive black pixel values, determines the integrity result corresponding to the first remote sensing image as a non-complete image when the consecutive black pixel values are determined, and determines the integrity result corresponding to the first remote sensing image as a complete image when the non-consecutive black pixel values are determined.
In one embodiment, when the determining module 908 determines that the black pixel value is discontinuous, a next boundary point of the current boundary point in the first remote sensing image is obtained, the next boundary point is determined to be the current boundary point, and the step of obtaining the current valid pixel value corresponding to the current boundary point of the first remote sensing image by the first obtaining module 902 is performed again until all the boundary points of the first remote sensing image are traversed, and the integrity result corresponding to the first remote sensing image is determined to be a complete image.
In one embodiment, the third obtaining module 910 obtains a remote sensing image line and column number associated with the first remote sensing image, and obtains a second remote sensing image with the same remote sensing image line and column number from the incomplete remote sensing image library according to the remote sensing image line and column number.
In one embodiment, the determining module 908 generates a corresponding current sparse matrix according to the current effective pixel value, generates a corresponding forward sparse matrix according to the forward effective pixel value, generates a corresponding backward sparse matrix according to the backward effective pixel value, determines whether the current sparse matrix, the forward sparse matrix, and the backward sparse matrix are continuous all-zero element matrices, determines an integrity result corresponding to the first remote sensing image as a complete image when the discontinuous all-zero element matrices are determined, and determines an integrity result corresponding to the first remote sensing image as a non-complete image when the continuous all-zero element matrices are determined.
In one embodiment, the remote sensing image stitching apparatus 900 determines the target remote sensing image as the first remote sensing image, and returns to execute the step of acquiring the current valid pixel value corresponding to the current boundary point of the first remote sensing image by the first acquisition module 902 until the integrity result corresponding to the target remote sensing image is the complete image.
For specific limitation of the remote sensing image stitching device, reference may be made to the limitation of the remote sensing image stitching method hereinabove, and the description thereof will not be repeated here. All or part of each module in the remote sensing image splicing device can be realized by software, hardware and a combination thereof. The above modules may be embedded in hardware or may be independent of a processor in the computer device, or may be stored in software in a memory in the computer device, so that the processor may call and execute operations corresponding to the above modules.
In one embodiment, a computer device is provided, which may be a server, and the internal structure of which may be as shown in fig. 10. The computer device includes a processor, a memory, a network interface, and a database connected by a system bus. Wherein the processor of the computer device is configured to provide computing and control capabilities. The memory of the computer device includes a non-volatile storage medium and an internal memory. The non-volatile storage medium stores an operating system, computer programs, and a database. The internal memory provides an environment for the operation of the operating system and computer programs in the non-volatile storage media. The database of the computer device is used to store the integrity results. The network interface of the computer device is used for communicating with an external terminal through a network connection. The computer program when executed by the processor is used for realizing a remote sensing image stitching method.
In one embodiment, a computer device is provided, which may be a terminal, and the internal structure thereof may be as shown in fig. 11. The computer device includes a processor, a memory, a network interface, a display screen, and an input device connected by a system bus. Wherein the processor of the computer device is configured to provide computing and control capabilities. The memory of the computer device includes a non-volatile storage medium and an internal memory. The non-volatile storage medium stores an operating system and a computer program. The internal memory provides an environment for the operation of the operating system and computer programs in the non-volatile storage media. The network interface of the computer device is used for communicating with an external terminal through a network connection. The computer program when executed by the processor is used for realizing a remote sensing image stitching method. The display screen of the computer equipment can be a liquid crystal display screen or an electronic ink display screen, and the input device of the computer equipment can be a touch layer covered on the display screen, can also be keys, a track ball or a touch pad arranged on the shell of the computer equipment, and can also be an external keyboard, a touch pad or a mouse and the like.
It will be appreciated by those skilled in the art that the structures shown in fig. 10 or 11 are merely block diagrams of portions of structures related to the aspects of the present application and are not intended to limit the computer devices to which the aspects of the present application may be applied, and that a particular computer device may include more or fewer components than shown, or may combine certain components, or may have a different arrangement of components.
In one embodiment, a computer device is provided comprising a memory, a processor, and a computer program stored on the memory and executable on the processor, the processor implementing the steps of when executing the computer program: the method comprises the steps of obtaining a current effective pixel value corresponding to a current boundary point of a first remote sensing image, determining a corresponding forward boundary point and a corresponding backward boundary point according to the current boundary point, obtaining a corresponding forward effective pixel value corresponding to the forward boundary point and a corresponding backward effective pixel value corresponding to the backward boundary point, determining an integrity result corresponding to the first remote sensing image according to the current effective pixel value, the forward effective pixel value and the backward effective pixel value, obtaining a second remote sensing image corresponding to the first remote sensing image when the integrity result indicates that the first remote sensing image is an incomplete image, and splicing the first remote sensing image and the second remote sensing image to obtain a target remote sensing image.
In one embodiment, the processor when executing the computer program further performs the steps of: two boundary points in the first direction are determined to be forward boundary points based on the current boundary point as a starting point, and two boundary points in the second direction are determined to be backward boundary points based on the current boundary point as a starting point.
In one embodiment, the processor when executing the computer program further performs the steps of: judging whether the current effective pixel value, the forward effective pixel value and the backward effective pixel value are continuous black pixel values, when the continuous black pixel value is judged, determining that the integrity result corresponding to the first remote sensing image is an incomplete image, and when the discontinuous black pixel value is judged, determining that the integrity result corresponding to the first remote sensing image is an complete image.
In one embodiment, the processor when executing the computer program further performs the steps of: when the discontinuous black pixel value is determined, acquiring a next boundary point of the current boundary point in the first remote sensing image; and determining the next boundary point as a current boundary point, and returning to the step of acquiring the current effective pixel value corresponding to the current boundary point of the first remote sensing image until all the boundary points of the first remote sensing image are traversed, and determining the integrity result corresponding to the first remote sensing image as a complete image.
In one embodiment, the processor when executing the computer program further performs the steps of: and acquiring the remote sensing image row and column numbers associated with the first remote sensing image, and acquiring a second remote sensing image with the same remote sensing image row and column number from the incomplete remote sensing image library according to the remote sensing image row and column numbers.
In one embodiment, the processor when executing the computer program further performs the steps of: generating a corresponding current sparse matrix according to the current effective pixel value, generating a corresponding forward sparse matrix according to the forward effective pixel value, generating a corresponding backward sparse matrix according to the backward effective pixel value, judging whether the current sparse matrix, the forward sparse matrix and the backward sparse matrix are continuous all-zero element matrixes, determining an integrity result corresponding to the first remote sensing image as a complete image when the discontinuous all-zero element matrixes are judged, and determining an integrity result corresponding to the first remote sensing image as a non-complete image when the discontinuous all-zero element matrixes are judged.
In one embodiment, the processor when executing the computer program further performs the steps of: and determining the target remote sensing image as a first remote sensing image, and returning to the step of acquiring the current effective pixel value corresponding to the current boundary point of the first remote sensing image until the integrity result corresponding to the target remote sensing image is a complete image.
In one embodiment, a computer readable storage medium is provided having a computer program stored thereon, which when executed by a processor, performs the steps of: the method comprises the steps of obtaining a current effective pixel value corresponding to a current boundary point of a first remote sensing image, determining a corresponding forward boundary point and a corresponding backward boundary point according to the current boundary point, obtaining a corresponding forward effective pixel value corresponding to the forward boundary point and a corresponding backward effective pixel value corresponding to the backward boundary point, determining an integrity result corresponding to the first remote sensing image according to the current effective pixel value, the forward effective pixel value and the backward effective pixel value, obtaining a second remote sensing image corresponding to the first remote sensing image when the integrity result indicates that the first remote sensing image is an incomplete image, and splicing the first remote sensing image and the second remote sensing image to obtain a target remote sensing image.
In one embodiment, the processor when executing the computer program further performs the steps of: two boundary points in the first direction are determined to be forward boundary points based on the current boundary point as a starting point, and two boundary points in the second direction are determined to be backward boundary points based on the current boundary point as a starting point.
In one embodiment, the processor when executing the computer program further performs the steps of: judging whether the current effective pixel value, the forward effective pixel value and the backward effective pixel value are continuous black pixel values, when the continuous black pixel value is judged, determining that the integrity result corresponding to the first remote sensing image is an incomplete image, and when the discontinuous black pixel value is judged, determining that the integrity result corresponding to the first remote sensing image is an complete image.
In one embodiment, the processor when executing the computer program further performs the steps of: when the discontinuous black pixel value is determined, acquiring a next boundary point of the current boundary point in the first remote sensing image; and determining the next boundary point as a current boundary point, and returning to the step of acquiring the current effective pixel value corresponding to the current boundary point of the first remote sensing image until all the boundary points of the first remote sensing image are traversed, and determining the integrity result corresponding to the first remote sensing image as a complete image.
In one embodiment, the processor when executing the computer program further performs the steps of: and acquiring the remote sensing image row and column numbers associated with the first remote sensing image, and acquiring a second remote sensing image with the same remote sensing image row and column number from the incomplete remote sensing image library according to the remote sensing image row and column numbers.
In one embodiment, the processor when executing the computer program further performs the steps of: generating a corresponding current sparse matrix according to the current effective pixel value, generating a corresponding forward sparse matrix according to the forward effective pixel value, generating a corresponding backward sparse matrix according to the backward effective pixel value, judging whether the current sparse matrix, the forward sparse matrix and the backward sparse matrix are continuous all-zero element matrixes, determining an integrity result corresponding to the first remote sensing image as a complete image when the discontinuous all-zero element matrixes are judged, and determining an integrity result corresponding to the first remote sensing image as a non-complete image when the discontinuous all-zero element matrixes are judged.
In one embodiment, the processor when executing the computer program further performs the steps of: and determining the target remote sensing image as a first remote sensing image, and returning to the step of acquiring the current effective pixel value corresponding to the current boundary point of the first remote sensing image until the integrity result corresponding to the target remote sensing image is a complete image.
Those skilled in the art will appreciate that implementing all or part of the above described methods may be accomplished by way of a computer program stored on a non-transitory computer readable storage medium, which when executed, may comprise the steps of the embodiments of the methods described above. Any reference to memory, storage, database, or other medium used in the various embodiments provided herein may include non-volatile and/or volatile memory. The nonvolatile memory can include Read Only Memory (ROM), programmable ROM (PROM), electrically Programmable ROM (EPROM), electrically Erasable Programmable ROM (EEPROM), or flash memory. Volatile memory can include Random Access Memory (RAM) or external cache memory. By way of illustration and not limitation, RAM is available in a variety of forms such as Static RAM (SRAM), dynamic RAM (DRAM), synchronous DRAM (SDRAM), double Data Rate SDRAM (DDRSDRAM), enhanced SDRAM (ESDRAM), synchronous Link DRAM (SLDRAM), memory bus direct RAM (RDRAM), direct memory bus dynamic RAM (DRDRAM), and memory bus dynamic RAM (RDRAM), among others.
The technical features of the above embodiments may be arbitrarily combined, and all possible combinations of the technical features in the above embodiments are not described for brevity of description, however, as long as there is no contradiction between the combinations of the technical features, they should be considered as the scope of the description.
The above examples merely represent a few embodiments of the present application, which are described in more detail and are not to be construed as limiting the scope of the invention. It should be noted that it would be apparent to those skilled in the art that various modifications and improvements could be made without departing from the spirit of the present application, which would be within the scope of the present application. Accordingly, the scope of protection of the present application is to be determined by the claims appended hereto.
Claims (10)
1. A remote sensing image stitching method, the method comprising:
acquiring a current effective pixel value corresponding to a current boundary point of a first remote sensing image, wherein the current boundary point is any boundary point;
determining corresponding forward boundary points and backward boundary points according to the current boundary points;
acquiring a forward effective pixel value corresponding to the forward boundary point and a backward effective pixel value corresponding to the backward boundary point;
Determining an integrity result corresponding to the first remote sensing image according to the current effective pixel value, the forward effective pixel value and the backward effective pixel value;
when the integrity result indicates that the first remote sensing image is an incomplete image, acquiring a second remote sensing image corresponding to the first remote sensing image;
and splicing the first remote sensing image and the second remote sensing image to obtain a target remote sensing image.
2. The method of claim 1, wherein said determining forward and backward boundary points from said current boundary point comprises:
determining two boundary points in a first direction as forward boundary points based on the current boundary point as a starting point;
and determining two boundary points in the second direction as backward boundary points based on the current boundary point as a starting point.
3. The method of claim 1, wherein the determining the integrity result corresponding to the first remote sensing image from the current valid pixel value, the forward valid pixel value, and the backward valid pixel value comprises:
judging whether the current effective pixel value, the forward effective pixel value and the backward effective pixel value are continuous black pixel values or not;
When the continuous black pixel value is determined, determining that the integrity result corresponding to the first remote sensing image is an incomplete image;
and when the discontinuous black pixel value is determined, determining that the integrity result corresponding to the first remote sensing image is a complete image.
4. The method of claim 3, wherein determining that the integrity result corresponding to the first remote sensing image is a complete image when the discontinuous black pixel values are determined, comprises:
when the discontinuous black pixel value is determined, acquiring a next boundary point of the current boundary point in the first remote sensing image;
determining the next boundary point as the current boundary point, and returning to the step of executing the current effective pixel value corresponding to the current boundary point of the obtained first remote sensing image;
and determining the integrity result corresponding to the first remote sensing image as a complete image until all boundary points of the first remote sensing image are traversed.
5. The method of claim 1, wherein the acquiring the second remote sensing image corresponding to the first remote sensing image comprises:
acquiring a remote sensing image row number associated with the first remote sensing image;
And acquiring a second remote sensing image with the same remote sensing image row and column number from the incomplete remote sensing image library according to the remote sensing image row and column number.
6. The method of claim 1, wherein the determining the integrity result corresponding to the first remote sensing image from the current valid pixel value, the forward valid pixel value, and the backward valid pixel value comprises:
generating a corresponding current sparse matrix according to the current effective pixel value;
generating a corresponding forward sparse matrix according to the forward effective pixel value;
generating a corresponding backward sparse matrix according to the backward effective pixel value;
judging whether the current sparse matrix, the forward sparse matrix and the backward sparse matrix are continuous all-zero element matrixes or not;
when the discontinuous all-zero element matrix is determined, determining that an integrity result corresponding to the first remote sensing image is a complete image;
and when the continuous all-zero element matrix is determined, determining that the integrity result corresponding to the first remote sensing image is an incomplete image.
7. The method according to claim 1, wherein the method further comprises:
determining the target remote sensing image as the first remote sensing image, and returning to the step of acquiring the current effective pixel value corresponding to the current boundary point of the first remote sensing image;
And until the integrity result corresponding to the target remote sensing image is a complete image.
8. A remote sensing image stitching device, the device comprising:
the first acquisition module is used for acquiring a current effective pixel value corresponding to a current boundary point of the first remote sensing image, wherein the current boundary point is any boundary point;
the processing module is used for determining corresponding forward boundary points and backward boundary points according to the current boundary points;
the second acquisition module is used for acquiring a forward effective pixel value corresponding to the forward boundary point and a backward effective pixel value corresponding to the backward boundary point;
the judging module is used for determining an integrity result corresponding to the first remote sensing image according to the current effective pixel value, the forward effective pixel value and the backward effective pixel value;
the third acquisition module is used for acquiring a second remote sensing image corresponding to the first remote sensing image when the integrity result indicates that the first remote sensing image is an incomplete image;
and the splicing module is used for splicing the first remote sensing image and the second remote sensing image to obtain a target remote sensing image.
9. A computer device comprising a memory, a processor and a computer program stored on the memory and executable on the processor, characterized in that the processor implements the steps of the method according to any one of claims 1 to 7 when the computer program is executed by the processor.
10. A computer readable storage medium, on which a computer program is stored, characterized in that the computer program, when being executed by a processor, implements the steps of the method of any of claims 1 to 7.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202310240878.1A CN116309057A (en) | 2023-03-14 | 2023-03-14 | Remote sensing image splicing method, device, computer equipment and storage medium |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202310240878.1A CN116309057A (en) | 2023-03-14 | 2023-03-14 | Remote sensing image splicing method, device, computer equipment and storage medium |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN116309057A true CN116309057A (en) | 2023-06-23 |
Family
ID=86781053
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202310240878.1A Pending CN116309057A (en) | 2023-03-14 | 2023-03-14 | Remote sensing image splicing method, device, computer equipment and storage medium |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN116309057A (en) |
Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN108154471A (en) * | 2017-11-15 | 2018-06-12 | 北京海致网聚信息技术有限公司 | A kind of method and apparatus for remote sensing image splicing |
| CN111050210A (en) * | 2018-10-12 | 2020-04-21 | 奥多比公司 | Video patching via confidence weighted motion estimation |
| CN112508988A (en) * | 2021-01-14 | 2021-03-16 | 西安中科星图空间数据技术有限公司 | Method and device for accurately extracting mosaic lines of remote sensing images |
| CN114066915A (en) * | 2021-09-27 | 2022-02-18 | 中国航空无线电电子研究所 | Edge processing method for overlaying aviation video images |
-
2023
- 2023-03-14 CN CN202310240878.1A patent/CN116309057A/en active Pending
Patent Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN108154471A (en) * | 2017-11-15 | 2018-06-12 | 北京海致网聚信息技术有限公司 | A kind of method and apparatus for remote sensing image splicing |
| CN111050210A (en) * | 2018-10-12 | 2020-04-21 | 奥多比公司 | Video patching via confidence weighted motion estimation |
| CN112508988A (en) * | 2021-01-14 | 2021-03-16 | 西安中科星图空间数据技术有限公司 | Method and device for accurately extracting mosaic lines of remote sensing images |
| CN114066915A (en) * | 2021-09-27 | 2022-02-18 | 中国航空无线电电子研究所 | Edge processing method for overlaying aviation video images |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN113592950B (en) | Multi-camera calibration method and related equipment in large space environment based on optical dynamic capturing | |
| CN110751149B (en) | Target object labeling method, device, computer equipment and storage medium | |
| CN114020756A (en) | Remote sensing image real-time map service publishing method and device | |
| CN112508988A (en) | Method and device for accurately extracting mosaic lines of remote sensing images | |
| CN113963072A (en) | Binocular camera calibration method and device, computer equipment and storage medium | |
| CN111445513B (en) | Plant canopy volume acquisition method and device based on depth image, computer equipment and storage medium | |
| CN116309057A (en) | Remote sensing image splicing method, device, computer equipment and storage medium | |
| CN111582013A (en) | Ship retrieval method and device based on gray level co-occurrence matrix characteristics | |
| CN115731442A (en) | Image processing method, image processing device, computer equipment and storage medium | |
| CN114359232B (en) | Image change detection method and device based on context covariance matrix | |
| CN116310899A (en) | YOLOv 5-based improved target detection method and device and training method | |
| CN115272470A (en) | Camera positioning method and device, computer equipment and storage medium | |
| CN113160126A (en) | Hardware Trojan horse detection method and device, computer equipment and storage medium | |
| CN117576645B (en) | Parking space detection method and device based on BEV visual angle and computer equipment | |
| CN111968727B (en) | Image data display method, device, computer equipment and storage medium | |
| CN110751627B (en) | Image processing method, device, computer equipment and storage medium | |
| CN116527908B (en) | Motion field estimation method, motion field estimation device, computer device and storage medium | |
| CN117392317B (en) | Live three-dimensional modeling method, device, computer equipment and storage medium | |
| CN116295031B (en) | Sag measurement method, sag measurement device, computer equipment and storage medium | |
| CN114750147B (en) | Space pose determining method and device of robot and robot | |
| CN111858824B (en) | Terrain data fusion method, device, computer equipment and storage medium | |
| CN116758146A (en) | Unmanned aerial vehicle cluster target positioning method, device, equipment and medium based on image | |
| CN118052860A (en) | Vehicle depth information estimation method, device, computer equipment and storage medium | |
| CN118229585A (en) | Depth image restoration method, device, computer equipment and storage medium | |
| CN117910008A (en) | File decryption method, device, computer equipment and storage medium |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination |