CN115344729A - Remote sensing image overall planning system and method based on user feedback - Google Patents
Remote sensing image overall planning system and method based on user feedback Download PDFInfo
- Publication number
- CN115344729A CN115344729A CN202211271034.5A CN202211271034A CN115344729A CN 115344729 A CN115344729 A CN 115344729A CN 202211271034 A CN202211271034 A CN 202211271034A CN 115344729 A CN115344729 A CN 115344729A
- Authority
- CN
- China
- Prior art keywords
- image
- feedback
- retrieval
- information
- user
- 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.)
- Granted
Links
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
- G06F16/50—Information retrieval; Database structures therefor; File system structures therefor of still image data
- G06F16/53—Querying
- G06F16/532—Query formulation, e.g. graphical querying
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
- G06F16/50—Information retrieval; Database structures therefor; File system structures therefor of still image data
- G06F16/53—Querying
- G06F16/535—Filtering based on additional data, e.g. user or group profiles
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
- G06F16/50—Information retrieval; Database structures therefor; File system structures therefor of still image data
- G06F16/58—Retrieval characterised by using metadata, e.g. metadata not derived from the content or metadata generated manually
- G06F16/583—Retrieval characterised by using metadata, e.g. metadata not derived from the content or metadata generated manually using metadata automatically derived from the content
Landscapes
- Engineering & Computer Science (AREA)
- Theoretical Computer Science (AREA)
- Physics & Mathematics (AREA)
- Data Mining & Analysis (AREA)
- Databases & Information Systems (AREA)
- General Engineering & Computer Science (AREA)
- General Physics & Mathematics (AREA)
- Library & Information Science (AREA)
- Mathematical Physics (AREA)
- Information Retrieval, Db Structures And Fs Structures Therefor (AREA)
Abstract
The invention discloses a remote sensing image overall planning system and a method based on user feedback, which relate to the technical field of remote sensing image overall planning and comprise an image retrieval module, a first search result and a second search result, wherein the image retrieval module is configured to acquire retrieval information of a user and perform image group retrieval according to the retrieval information; the user feedback module is configured to obtain feedback of the user on the first retrieval result and integrate the feedback of the user into full feedback information; and the image replacement module is configured to perform image replacement on the image in the first retrieval result according to the full feedback information to obtain a second retrieval result, and recommend the second retrieval result to the user. The invention can realize feedback type overall planning of the remote sensing image, fully excavate the user requirement in an intelligent user feedback mode and improve the accuracy of the remote sensing image overall planning system.
Description
Technical Field
The invention relates to the field of remote sensing image overall planning, in particular to a remote sensing image overall planning system and method based on user feedback.
Background
With the development and progress of earth observation technology, remote sensing platforms for various applications are continuously increased, so that the quantity, quality and variety of remote sensing image data are increased day by day, and people face massive space and earth remote sensing image data every day. How to organize and manage these vastly data in order to better utilize these remote sensing images is a constant subject of research and development by researchers.
The technology of managing and searching according to the content, the attribute and the related characteristics of the remote sensing image becomes a problem generally concerned by remote sensing image library managers. However, these "contents" are often a visual perception, which is difficult to describe accurately with language or words, and it is difficult to find a uniform, precise and concrete expression. Text-based and content-based image retrieval techniques currently exist. Both methods have their drawbacks, however.
In the image retrieval method based on the text attribute, the visual perception of the image is difficult to describe by using short and effective characters, secondly, the information mass contained in the existing remote sensing image is difficult to describe completely, effectively and accurately, and finally, the character description mode needs certain priori knowledge to understand the image, so that the efficiency is low. The retrieval accuracy of content-based image retrieval techniques is often not ideal. The related feedback technology can compensate the above disadvantages to some extent.
The remote sensing image has different characteristics from the common image, and a feedback method of the conventional image cannot be directly used. In the field of remote sensing data, the remote sensing data relates to spatial attributes, each piece of data corresponds to an actual area, in the practical application of remote sensing image overall planning, a group of images covering a target area are required by a user, the images obtained by searching take scenes as units, the image data volume is large, the types of contained remote sensing image ground objects are various, and clear subjects or subject characteristics do not exist, so that the related feedback technology of images cannot be directly used for the remote sensing image overall planning.
Disclosure of Invention
In order to solve the technical problems, the invention provides a remote sensing image overall planning system and a remote sensing image overall planning method based on user feedback, and solves the problem that feedback of multi-scene images containing large-scale and complicated land features is difficult to realize in remote sensing image overall planning. And through intelligent interactive design, the maximization excavation of overall demands of users is realized, and the customized image overall planning is realized.
In order to achieve the technical purpose, the technical scheme of the invention is as follows:
a remote sensing image orchestration system based on user feedback, the system comprising:
the image retrieval module is configured to acquire retrieval information of a user, and perform image group retrieval according to the retrieval information to obtain a first retrieval result;
the user feedback module is configured to obtain feedback of the user on the first retrieval result and integrate the feedback of the user into full feedback information;
and the image replacement module is configured to perform image replacement on the image in the first retrieval result according to the full feedback information to obtain a second retrieval result, and recommend the second retrieval result to the user.
In an embodiment of the present invention, the image retrieving module includes:
the retrieval system comprises a retrieval information input unit, a retrieval information input unit and a retrieval information output unit, wherein the retrieval information comprises inherent retrieval options, text information and voice information, and the inherent retrieval options comprise a target area range, an image acquisition time range, an image space resolution, a star source, a sensor, an image grade and an image format;
a voice information conversion unit configured to convert the voice information into text information and then input the text information into a text information conversion unit;
the text information conversion unit is configured to perform word segmentation processing on the text information by adopting a word segmentation tool, acquire a keyword to be retrieved from a word segmentation result through a keyword extraction algorithm and convert the keyword into label information;
a search algorithm unit configured to generate an image group search path according to the inherent retrieval option and the tag information based on a preset image group search algorithm;
and the image group searching unit is configured to perform image searching according to the image group searching path to obtain a first searching result.
In one embodiment of the present invention, the image resolution, the star source, and the sensor type are associated search information.
In an embodiment of the present invention, the user feedback module includes:
the feedback image acquisition unit is configured to acquire an image selection result of a user on a first search result to obtain a feedback image, and the feedback image is a single image or a plurality of images;
the feedback area acquisition unit is configured to acquire a target feedback area in a feedback image, wherein the target feedback area is selected by a user on the feedback image in a polygon frame checking mode;
a feedback information acquiring unit configured to acquire feedback information in the target feedback region, where the feedback information is positive feedback information or negative feedback information, and the feedback information is at least one of a null value, an image quality item, and a ground object type;
and the user feedback integration unit is configured to integrate the feedback image, the target feedback area and the feedback information to obtain full feedback information.
In an embodiment of the present invention, the image replacement module includes:
the feedback understanding unit is configured to perform semantic understanding on the full feedback information to obtain a feedback label;
the feedback retrieval unit is configured to perform image retrieval according to the feedback image to obtain a candidate image;
the image recommendation unit is configured to perform image recommendation according to the correlation degree of the candidate image and the feedback label to obtain a recommended image;
and the image replacing unit is configured to screen the recommended images based on the replacing rule to obtain replacing images, and replace the corresponding feedback images with the replacing images to obtain a second retrieval result.
In an embodiment of the present invention, when the feedback information is negative feedback information, the candidate images are sorted according to an ascending order of the degree of correlation and image recommendation is performed, and the top K candidate images are selected as recommended images;
and when the feedback information is positive feedback information, sorting the candidate images according to the descending order of the correlation degree and recommending the images, and selecting the first K candidate images as recommended images.
In an embodiment of the present invention, the replacement rule is:
selecting a single feedback image, and sorting the recommended images in an ascending order or a descending order according to the relevance according to the feedback information corresponding to the feedback image;
and secondly, selecting from the first recommended image until the selected recommended image completely covers the target feedback area of the feedback image, and taking the selected recommended image as a replacement image.
In an embodiment of the present invention, the system further includes:
the image external expansion module is configured to perform extended retrieval on the existing retrieval information, and the result obtained by the extended retrieval is merged into the first retrieval result;
the image expansion module is connected with the image retrieval module.
In an embodiment of the present invention, the image expanding module includes:
the external expansion rule unit is configured to provide three external expansion rules for a user to select, wherein the three rules respectively correspond to higher image resolution, external expansion image acquisition time and lower image resolution, and the user selects at least one of the three rules for conditional external expansion;
the external expansion condition display unit is configured to display the corresponding selectable external expansion retrieval information items and the corresponding non-selectable external expansion retrieval information items according to the selected retrieval information items and the external expansion rules, and set prompts for distinguishing the selectable external expansion retrieval information items and the non-selectable external expansion retrieval information items;
and the external expansion condition selection unit is configured to select the selectable external expansion search information items, and the selection modes comprise manual selection by a user and automatic system selection, wherein the external expansion mode of the image acquisition time is that the external expansion mode is expanded by a specified number of days forward or backward in the existing image acquisition time.
The invention also provides a remote sensing image overall planning method based on user feedback, and the method is applied to any one of the systems.
The invention has the beneficial effects that:
(1) The feedback type retrieval method is adaptively changed and then applied to the remote sensing image overall system. The system solves the problem that the feedback of multi-scene images containing large-scale and complicated land features is difficult to realize in the remote sensing image overall planning by simultaneously selecting a single image or a plurality of images, checking out a specific feedback area by a polygonal frame and adding positive and negative feedback information.
(2) Through intelligent interactive design, the maximization excavation of overall user demand is realized, and the customized image overall is realized.
(3) The image overall expansion function is provided, when an image group meeting the user requirements cannot be obtained in the initial retrieval, the user requirements can be met by utilizing the existing image resources to the maximum extent, and the resource waste caused by secondary image purchasing is avoided.
(4) The image overall external expansion function can guide a user to reasonably expand the retrieval information, the overall demand of the user is met through minimum external expansion of the image, and the threshold of the user for using the overall system is reduced.
Drawings
In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the drawings needed in the embodiments will be briefly described below, and it is obvious that the drawings in the following description are only some embodiments of the present invention, and it is obvious for those skilled in the art to obtain other drawings without creative efforts.
Fig. 1 is a schematic structural diagram of a remote sensing image overall planning system based on user feedback according to an embodiment of the present invention;
fig. 2 is a flowchart illustrating a work flow of the remote sensing image overall planning system based on user feedback according to an embodiment of the present invention;
FIG. 3 is a schematic diagram of an image retrieval module according to an embodiment of the present invention;
FIG. 4 is a schematic structural diagram of a user feedback module according to an embodiment of the present invention;
FIG. 5 is a schematic structural diagram of an image replacement module according to an embodiment of the present invention;
fig. 6 is a schematic structural diagram of a remote sensing image overall planning system based on user feedback according to another embodiment of the present invention;
fig. 7 is a schematic structural diagram of an image expanding module according to an embodiment of the invention;
FIG. 8 is a schematic interface diagram illustrating an image expansion function according to an embodiment of the present invention;
fig. 9 is a schematic flow chart of a remote sensing image overall planning method based on user feedback according to an embodiment of the present invention.
Detailed Description
The technical solutions in the embodiments of the present invention will be clearly and completely described below with reference to the drawings in the embodiments of the present invention, and it is obvious that the described embodiments are only a part of the embodiments of the present invention, and not all of the embodiments. All other embodiments, which can be derived from the embodiments of the present invention by a person skilled in the art, are within the scope of the present invention.
Referring to fig. 1 and fig. 2, fig. 1 is a schematic structural diagram of a remote sensing image overall planning system based on user feedback according to the present invention, and fig. 2 is a flowchart of a work flow of the remote sensing image overall planning system based on user feedback according to the present invention, where the system includes an image retrieval module, a user feedback module, and an image replacement module.
The image retrieval module is configured to acquire retrieval information of a user, and perform image group retrieval according to the retrieval information to obtain a first retrieval result.
Specifically, referring to fig. 3, in one embodiment, the image retrieving module includes:
a retrieval information input unit configured to receive retrieval information input by a user, the retrieval information including inherent retrieval options, text information, and voice information. Specifically, the inherent search options in the search information input by the user include a target area, image acquisition time, image spatial resolution, star source, sensor, image level, and image format. The target area is the most important search parameter, can not be changed, and is obtained by menu selection or manual polygon frame delineation. The image grade is an L0-L6 grade specified by GB/T38028-2019 remote sensing satellite panchromatic data product grading, and corresponding options are clicked for selection. The image quality comprises an image quality grade, an available domain proportion and an image quality defect proportion, wherein the image quality grade is good, good or poor, the available domain proportion is used for evaluating the proportion of a usable area of the whole image to the whole image, the image quality defect proportion is used for evaluating the proportion of a quality defect item to the whole image, and the quality defect item comprises a null value, a cloud cover and a high exposure. The image type is an integration item of image levels, and one image type can have a plurality of image levels, and different image types are set for different application scenes.
Specifically, in one embodiment, the image resolution, the star source and the sensor type are mutually associated retrieval information, when one item of the image resolution, such as 2m, is selected, the star source and the sensor type corresponding to the image resolution are also displayed, when one item of the star source is selected, the image resolution and the sensor type corresponding to the star source are also displayed, and when one item of the sensor is selected, the star source and the image resolution corresponding to the sensor type are displayed.
And the voice information conversion unit is configured to convert the voice information into text information and then input the text information into the text information conversion unit.
And the text information conversion unit is configured to perform word segmentation processing on the text information by adopting a word segmentation tool, acquire the keywords to be retrieved from the word segmentation result through a keyword extraction algorithm and convert the keywords into the label information.
And the searching algorithm unit is configured to generate an image group searching path according to the inherent retrieval option and the label information based on a preset image group searching algorithm. When a plurality of selected inherent retrieval options are available, for example, the image resolution is selected to be 0.65m, 1m, 2m, 2.5m and 16m at the same time, the searching algorithm preferentially selects the image with high resolution on the premise of comprehensively considering the coverage rate and the image quality. And searching the path end point to completely cover the target area. In one embodiment, the search algorithm unit determines an evaluation condition according to the tag information, evaluates a plurality of preset retrieval algorithms, and selects an algorithm with the best evaluation for searching the actual image group.
And the image group searching unit is configured to perform image searching according to the image group searching path to obtain a first searching result. It should be noted that the overall system searches for a set of images that completely cover the target area and meet other requirements of the user as much as possible.
And the user feedback module is configured to acquire the feedback of the user to the first retrieval result and integrate the feedback of the user into full feedback information. The schematic structure of the user feedback module is shown in fig. 4.
Specifically, in one embodiment, the user feedback module comprises:
and the feedback image acquisition unit is configured to acquire an image selection result of the user on the first search result to obtain a feedback image, and the feedback image is a single image or a plurality of images. Specifically, the image selection may be implemented by clicking an image at a corresponding position on a map or clicking a corresponding image item in an image list output by the image retrieval module.
The feedback area obtaining unit is configured to obtain a target feedback area in a feedback image, wherein the target feedback area is obtained by a user through selection on the feedback image in a polygon frame checking mode. Specifically, after a scene image is selected, a target feedback area can be selected on the scene image. Further, the feedback area obtaining unit may further obtain a target feedback area corresponding to the administrative division by inputting an administrative division name.
A feedback information acquiring unit configured to acquire feedback information in the target feedback region, wherein the feedback information is positive feedback information or negative feedback information, and the feedback information is at least one of a null value, an image quality item, and a ground feature type.
Specifically, after positive and negative feedback information is obtained in a target feedback area on a selected scene image and confirmed by a user, the feedback of the scene image is finished, and feedback of other images or finishing feedback can be performed.
It should be noted that the positive feedback information represents that the related content in the target feedback area approaches or reaches the expectation of the user, and the negative feedback information represents that the related content in the target feedback area is far away from the expectation of the user.
And the user feedback integration unit is configured to integrate the feedback image, the target feedback area and the feedback information to obtain full feedback information.
And the image replacement module is configured to perform image replacement on the image in the first retrieval result according to the full feedback information to obtain a second retrieval result, and recommend the second retrieval result to the user.
Specifically, referring to fig. 5, in one embodiment, the image replacement module includes:
the feedback understanding unit is configured to perform semantic understanding on the full feedback information to obtain a feedback label;
the feedback retrieval unit is configured to perform image retrieval according to the feedback image to obtain a candidate image;
the image recommendation unit is configured to perform image recommendation according to the correlation degree of the candidate image and the feedback label to obtain a recommended image;
and the image replacing unit is configured to screen the recommended images based on the replacing rule to obtain replaced images, and replace the corresponding feedback images with the replaced images to obtain a second retrieval result.
Specifically, in one embodiment, when the feedback information is negative feedback information, the candidate images are sorted in an ascending order of the degree of correlation and image recommendation is performed, and the top K candidate images are selected as recommended images; and when the feedback information is positive feedback information, sorting the candidate images according to the descending order of the correlation degree and recommending the images, and selecting the first K candidate images as recommended images. K may be determined according to the specific situation and the number of candidate images, for example, if 50 candidate images are provided, and the number of candidate images correlated with the feedback tag reaches 0.5 or more exceeds 20, K may be set to 10.
Specifically, in one embodiment, the full feedback information includes a target feedback area that is selected by the user using the polygon frame, and the feedback information is { (1. Negative feedback, null), (2. Negative feedback, cloud amount) }. For the feedback information 1, because the feedback information is a null value, a feedback understanding unit is required to carry out semantic understanding on the feedback information to obtain a feedback label, the feedback understanding unit judges that the ground object in the target feedback area is wheat through a machine learning target detection method, the feedback information is corrected to be { (1. Negative feedback, wheat), (2. Negative feedback, cloud amount) }, and then the feedback label of the feedback image is wheat and cloud amount. The same target feedback area may correspond to multiple pieces of feedback information. The feedback retrieval unit performs image retrieval by using conditions such as time phase of the feedback image, a sensor, and a covering position of the target feedback area in the target area, and obtains a candidate image capable of completely covering the feedback image. The image recommending unit sequences the candidate images according to the wheat areas and the cloud cover in the candidate images, and the sequencing sequence is realized according to the ascending sequence of the wheat areas and the cloud cover due to negative feedback information. The image replacement unit selects the first K candidate images as recommended images according to specific conditions, and realizes image replacement based on replacement rules, wherein the replacement rules are as follows: selecting a single feedback image, and sorting the recommended images in an ascending order or a descending order according to the relevance according to the feedback information corresponding to the feedback image; and secondly, selecting from the first recommended image until the selected recommended image completely covers the target feedback area of the feedback image, and taking the selected recommended image as a replacement image.
Optionally, referring to fig. 6, in another embodiment of the present invention, an image extension module may be further included, which is configured to perform extension and then search on the existing search information, and merge the extended result into the search result. The retrieval information that can be expanded includes image resolution, star source, sensor type, image acquisition time. It should be noted that the image expansion module is used as a selectable item for the user to freely select, and is connected to the image retrieval module for expanding the retrieval result.
Specifically, referring to fig. 7, in one embodiment, the conditional expansion module includes:
and the external expansion rule unit is configured to provide three external expansion rules for a user to select, wherein the three rules respectively correspond to higher image resolution, external expansion image acquisition time and lower image resolution, and the user selects at least one of the three rules for conditional external expansion.
And the external expansion condition display unit is configured to display the corresponding selectable external expansion retrieval information items and the corresponding non-selectable external expansion retrieval information items according to the selected retrieval information items and the external expansion rules, and set prompts for distinguishing the selectable external expansion retrieval information items from the non-selectable external expansion retrieval information items. The selectable external expansion retrieval information items comprise a lossy external expansion option and a recommended external expansion option, wherein the lossy external expansion option is a specific condition item corresponding to an external expansion rule with lower image resolution, and the recommended external expansion option is a specific condition item corresponding to an external expansion rule with higher image resolution
And the external expansion condition selection unit is configured to select the selectable external expansion search information items, and the selection modes comprise manual selection by a user and automatic system selection, wherein the external expansion mode of the image acquisition time is that the external expansion mode is expanded by a specified number of days forward or backward in the existing image acquisition time.
Specifically, as shown in fig. 8, the above-mentioned content is described by an embodiment of the present invention: the method comprises the steps that a currently used retrieval information is displayed in a checked state in an external expansion interface in a default mode, a user firstly selects an external expansion rule, one or more of higher image resolution, external expansion image acquisition time and lower image resolution can be selected, the current resolution is 2m, after the higher image resolution rule is selected, options of 0.65m and 1m and star sources corresponding to the options are automatically selected, and the options are distinguished from selected options through option fonts of different colors. When a lower image resolution is selected, the 2.5m and 16m options and the star sources corresponding to the options are automatically selected, and the options corresponding to the lower image resolution and the selected options are distinguished through option fonts with different colors. After the external expansion image acquisition time is selected, the current image acquisition time can be expanded, and the number of days to be expanded is represented by x days before selection and y days after selection. The user can also directly click on specific condition items, and the system automatically selects the corresponding external expansion rule. When the retrieval result image is not enough to completely cover the target area range, the system can automatically carry out minimum external expansion on the condition to obtain the image completely covering the target area range.
Referring to fig. 9, the present invention also provides a remote sensing image overall planning method based on user feedback, and the method is applied to any one of the above systems.
In one embodiment of the invention, the method may comprise:
s1, acquiring user retrieval information, and performing image group retrieval according to the retrieval information to obtain a retrieval result, wherein the retrieval information comprises inherent retrieval options, text information and voice information;
s2, feedback of the user is obtained and integrated into full feedback information, wherein the feedback of the user comprises a feedback image, a target feedback area selected by a polygonal frame and feedback information;
s3, performing semantic understanding on the full feedback information to obtain a feedback label, performing image retrieval according to the feedback image, performing image recommendation according to the correlation degree of the candidate image and the feedback label, selecting a replacement image from the recommended image, and replacing the corresponding feedback image with the replacement image to obtain a second retrieval result;
and S4, recommending the second retrieval result to the user as a recommendation result.
The invention has the beneficial effects that:
(1) The feedback retrieval method is adaptively changed and then applied to a remote sensing image overall planning system. The system solves the problem that the feedback of multi-scene images containing large-scale and complicated land features is difficult to realize in the remote sensing image overall planning by simultaneously selecting a single image or a plurality of images, checking out a specific feedback area by a polygonal frame and adding positive and negative feedback information.
(2) Through intelligent interactive design, the maximization excavation of overall demands of users is realized, and the customized image overall planning is realized.
(3) The image overall expanding function is provided, when an image group meeting the user requirements cannot be obtained in the primary retrieval, the user requirements can be met by utilizing the existing image resources to the maximum extent, and the resource waste caused by secondary image purchasing is avoided.
(4) The image overall external expansion function can guide a user to reasonably expand the retrieval information, the overall demand of the user is met through minimum external expansion of the image, and the threshold of the user for using the overall system is reduced.
It should be noted that, in this document, the terms "comprises," "comprising," or any other variation thereof, are intended to cover a non-exclusive inclusion, such that a process, method, article, or apparatus that comprises a list of elements does not include only those elements but may include other elements not expressly listed or inherent to such process, method, article, or apparatus. Without further limitation, an element defined by the phrase "comprising a … …" does not exclude the presence of another identical element in a process, method, article, or apparatus that comprises the element.
The above description is only for the purpose of illustrating the preferred embodiments of the present invention and should not be taken as limiting the scope of the present invention, which is intended to cover any modifications, equivalents, improvements, etc. within the spirit and scope of the present invention.
Claims (10)
1. The utility model provides a remote sensing image overall planning system based on user feedback which characterized in that includes:
the image retrieval module is configured to acquire retrieval information of a user, and perform image group retrieval according to the retrieval information to obtain a first retrieval result;
the user feedback module is configured to obtain feedback of the user on the first retrieval result and integrate the feedback of the user into full feedback information;
and the image replacement module is configured to perform image replacement on the image in the first retrieval result according to the full feedback information to obtain a second retrieval result, and recommend the second retrieval result to the user.
2. The system of claim 1, wherein the image retrieval module comprises:
the retrieval system comprises a retrieval information input unit, a retrieval information input unit and a retrieval information output unit, wherein the retrieval information comprises inherent retrieval options, text information and voice information, and the inherent retrieval options comprise a target area range, an image acquisition time range, an image space resolution, a star source, a sensor, an image grade and an image format;
a voice information conversion unit configured to convert the voice information into text information and then input the text information into a text information conversion unit;
the text information conversion unit is configured to perform word segmentation processing on the text information by adopting a word segmentation tool, acquire a keyword to be retrieved from a word segmentation result through a keyword extraction algorithm and convert the keyword into label information;
a search algorithm unit configured to generate an image group search path according to the inherent retrieval option and the tag information based on a preset image group search algorithm;
and the image group searching unit is configured to perform image searching according to the image group searching path to obtain a first searching result.
3. The system of claim 2, wherein the image resolution, the star source, and the sensor type are interrelated search information.
4. The system of claim 2, wherein the user feedback module comprises:
the feedback image acquisition unit is configured to acquire an image selection result of a user on a first search result to obtain a feedback image, and the feedback image is a single image or a plurality of images;
the feedback area acquisition unit is configured to acquire a target feedback area in a feedback image, wherein the target feedback area is selected by a user on the feedback image in a polygon frame checking mode;
a feedback information acquisition unit configured to acquire feedback information in the target feedback region, wherein the feedback information is positive feedback information or negative feedback information, and the feedback information is at least one of a null value, an image quality item and a ground feature type;
and the user feedback integration unit is configured to integrate the feedback image, the target feedback area and the feedback information to obtain full feedback information.
5. The system of claim 4, wherein the image replacement module comprises:
the feedback understanding unit is configured to perform semantic understanding on the full feedback information to obtain a feedback label;
a feedback retrieval unit configured to perform image retrieval according to the feedback image to obtain a candidate image;
the image recommendation unit is configured to perform image recommendation according to the correlation degree of the candidate image and the feedback label to obtain a recommended image;
and the image replacing unit is configured to screen the recommended images based on the replacing rule to obtain replacing images, and replace the corresponding feedback images with the replacing images to obtain a second retrieval result.
6. The system according to claim 5, wherein when the feedback information is negative feedback information, the candidate images are sorted in ascending order of the degree of correlation and image recommendation is performed, and the top K candidate images are selected as recommended images;
and when the feedback information is positive feedback information, sorting the candidate images according to the descending order of the correlation degree and recommending the images, and selecting the first K candidate images as recommended images.
7. The system of claim 6, wherein the replacement rule is:
selecting a single feedback image, and sorting the recommended images in an ascending order or a descending order according to the relevance according to the feedback information corresponding to the feedback image;
and secondly, selecting from the first recommended image until the selected recommended image completely covers the target feedback area of the feedback image, and taking the selected recommended image as a replacement image.
8. The system of claim 2, further comprising: the image external expansion module is configured to perform extended retrieval on the existing retrieval information, and the result obtained by the extended retrieval is merged into the first retrieval result;
the image expansion module is connected with the image retrieval module.
9. The system of claim 8, wherein the image expansion module comprises:
the external expansion rule unit is configured to provide three external expansion rules for a user to select, wherein the three rules respectively correspond to higher image resolution, external expansion image acquisition time and lower image resolution, and the user selects at least one of the three rules for conditional external expansion;
the external expansion condition display unit is configured to display the corresponding selectable external expansion retrieval information items and the corresponding non-selectable external expansion retrieval information items according to the selected retrieval information items and the external expansion rules, and set prompts for distinguishing the selectable external expansion retrieval information items and the non-selectable external expansion retrieval information items;
and the external expansion condition selection unit is configured to select the selectable external expansion search information items, and the selection modes comprise manual selection by a user and automatic system selection, wherein the external expansion mode of the image acquisition time is that the external expansion mode is expanded by a specified number of days forward or backward in the existing image acquisition time.
10. A remote sensing image pooling method based on user feedback, wherein the method is applied to the system of any one of claims 1-9.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202211271034.5A CN115344729B (en) | 2022-10-18 | 2022-10-18 | Remote sensing image overall planning system and method based on user feedback |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202211271034.5A CN115344729B (en) | 2022-10-18 | 2022-10-18 | Remote sensing image overall planning system and method based on user feedback |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN115344729A true CN115344729A (en) | 2022-11-15 |
| CN115344729B CN115344729B (en) | 2022-12-16 |
Family
ID=83957619
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202211271034.5A Active CN115344729B (en) | 2022-10-18 | 2022-10-18 | Remote sensing image overall planning system and method based on user feedback |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN115344729B (en) |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN115660721A (en) * | 2022-12-11 | 2023-01-31 | 北京数慧时空信息技术有限公司 | Remote sensing image overall planning system and method based on user demands |
Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN102467564A (en) * | 2010-11-12 | 2012-05-23 | 中国科学院烟台海岸带研究所 | Remote sensing image retrieval method based on improved support vector machine relevance feedback |
| US20150331890A1 (en) * | 2013-02-19 | 2015-11-19 | Digitalglobe, Inc. | Crowdsourced feature identification and orthorectification |
| CN106845557A (en) * | 2017-02-14 | 2017-06-13 | 中国科学院遥感与数字地球研究所 | A kind of Intelligence Feedback method of Remote Sensing Imagery Change information retrieval |
| CN113158035A (en) * | 2021-03-25 | 2021-07-23 | 武汉大学 | Aerospace resource searching method and system considering user preference |
| CN114579778A (en) * | 2022-03-07 | 2022-06-03 | 江苏天汇空间信息研究院有限公司 | Data retrieval management system and method based on remote sensing number |
| CN115017418A (en) * | 2022-08-10 | 2022-09-06 | 北京数慧时空信息技术有限公司 | Remote sensing image recommendation system and method based on reinforcement learning |
-
2022
- 2022-10-18 CN CN202211271034.5A patent/CN115344729B/en active Active
Patent Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN102467564A (en) * | 2010-11-12 | 2012-05-23 | 中国科学院烟台海岸带研究所 | Remote sensing image retrieval method based on improved support vector machine relevance feedback |
| US20150331890A1 (en) * | 2013-02-19 | 2015-11-19 | Digitalglobe, Inc. | Crowdsourced feature identification and orthorectification |
| CN106845557A (en) * | 2017-02-14 | 2017-06-13 | 中国科学院遥感与数字地球研究所 | A kind of Intelligence Feedback method of Remote Sensing Imagery Change information retrieval |
| CN113158035A (en) * | 2021-03-25 | 2021-07-23 | 武汉大学 | Aerospace resource searching method and system considering user preference |
| CN114579778A (en) * | 2022-03-07 | 2022-06-03 | 江苏天汇空间信息研究院有限公司 | Data retrieval management system and method based on remote sensing number |
| CN115017418A (en) * | 2022-08-10 | 2022-09-06 | 北京数慧时空信息技术有限公司 | Remote sensing image recommendation system and method based on reinforcement learning |
Non-Patent Citations (1)
| Title |
|---|
| 李峰等: "遥感影像数据库基于内容检索***的构建", 《武汉大学学报(信息科学版)》 * |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN115660721A (en) * | 2022-12-11 | 2023-01-31 | 北京数慧时空信息技术有限公司 | Remote sensing image overall planning system and method based on user demands |
Also Published As
| Publication number | Publication date |
|---|---|
| CN115344729B (en) | 2022-12-16 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN101398834B (en) | Processing method and device for input information and input method system | |
| KR100371513B1 (en) | Method and apparatus of summerizing and browsing video sequences using fidelity values of key frame stored in its edge of key frame hierarchy | |
| JP4812661B2 (en) | Map display system and map display method | |
| CN107368614A (en) | Image search method and device based on deep learning | |
| CN114996488B (en) | Skynet big data decision-level fusion method | |
| CN111694965A (en) | Image scene retrieval system and method based on multi-mode knowledge graph | |
| CN115934990B (en) | Remote sensing image recommendation method based on content understanding | |
| CN115374303B (en) | Satellite image recommendation method based on user demand understanding | |
| CN115344729B (en) | Remote sensing image overall planning system and method based on user feedback | |
| CN112948575B (en) | Text data processing method, apparatus and computer readable storage medium | |
| CN112231554B (en) | Search recommended word generation method and device, storage medium and computer equipment | |
| CN116245177B (en) | Geographic environment knowledge graph automatic construction method and system and readable storage medium | |
| CN114528477A (en) | Scientific research application-oriented automatic machine learning implementation method, platform and device | |
| CN105164672A (en) | Content classification | |
| CN110110143B (en) | Video classification method and device | |
| Laaksonen et al. | Content-based image retrieval using self-organizing maps | |
| CN117875293A (en) | Method for generating service form template in quick digitization mode | |
| JP5973309B2 (en) | Distribution apparatus and computer program | |
| KR102258419B1 (en) | Animaiton contents resource service system based on intelligent information technology | |
| CN117171355A (en) | Cultural gene knowledge graph construction method and device | |
| CN115797795A (en) | Remote sensing image question-answering type retrieval system and method based on reinforcement learning | |
| CN111931256A (en) | Color matching recommendation method, device, equipment and storage medium | |
| CN115329850A (en) | Information comparison method and device, electronic equipment and storage medium | |
| CN109753579B (en) | Picture labeling recommendation method based on frequent item set | |
| CN113722577B (en) | Feedback information processing method, device, 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 | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |