CN111241935B - Automatic matching and comparing method for multi-period aerial images - Google Patents
Automatic matching and comparing method for multi-period aerial images Download PDFInfo
- Publication number
- CN111241935B CN111241935B CN201911402952.5A CN201911402952A CN111241935B CN 111241935 B CN111241935 B CN 111241935B CN 201911402952 A CN201911402952 A CN 201911402952A CN 111241935 B CN111241935 B CN 111241935B
- Authority
- CN
- China
- Prior art keywords
- image
- compared
- images
- batch
- automatic matching
- 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.)
- Active
Links
- 238000000034 method Methods 0.000 title claims abstract description 28
- 230000008676 import Effects 0.000 claims abstract description 20
- 238000007781 pre-processing Methods 0.000 claims abstract description 6
- 230000008859 change Effects 0.000 claims description 23
- 238000001514 detection method Methods 0.000 claims description 12
- 239000007787 solid Substances 0.000 claims description 3
- 238000009795 derivation Methods 0.000 abstract 1
- 238000005516 engineering process Methods 0.000 description 3
- 238000012544 monitoring process Methods 0.000 description 3
- 238000004458 analytical method Methods 0.000 description 1
- 238000004364 calculation method Methods 0.000 description 1
- 238000010276 construction Methods 0.000 description 1
- 230000007123 defense Effects 0.000 description 1
- 238000010586 diagram Methods 0.000 description 1
- 238000003384 imaging method Methods 0.000 description 1
- 230000008569 process Effects 0.000 description 1
- 238000009877 rendering Methods 0.000 description 1
- 230000011218 segmentation Effects 0.000 description 1
- 230000003595 spectral effect Effects 0.000 description 1
- 230000002123 temporal effect Effects 0.000 description 1
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V20/00—Scenes; Scene-specific elements
- G06V20/10—Terrestrial scenes
- G06V20/13—Satellite images
-
- 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
-
- 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
- G06F16/587—Retrieval characterised by using metadata, e.g. metadata not derived from the content or metadata generated manually using geographical or spatial information, e.g. location
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V20/00—Scenes; Scene-specific elements
- G06V20/60—Type of objects
- G06V20/64—Three-dimensional objects
Landscapes
- Engineering & Computer Science (AREA)
- Theoretical Computer Science (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Library & Information Science (AREA)
- Multimedia (AREA)
- Data Mining & Analysis (AREA)
- Databases & Information Systems (AREA)
- General Engineering & Computer Science (AREA)
- Astronomy & Astrophysics (AREA)
- Remote Sensing (AREA)
- Processing Or Creating Images (AREA)
Abstract
The invention discloses a multi-period aerial image automatic matching and comparing method, which comprises the steps that a terminal imports image data in batches, and updates the import state of the batches; preprocessing image data, calculating coordinates of an image center point, and storing the coordinates in a database; positioning, browsing and importing three-dimensional spherical scenes of batch images; and a specific position is appointed in the three-dimensional spherical scene, the request server acquires the images to be compared and the images to be compared in a certain range of the position, and automatic matching of the images to be compared and the images to be compared is carried out. The method is based on homologous remote sensing images obtained by the same sensor at different time points, comparison is directly carried out by using original data, and intelligent automatic matching is realized through automatic matching of the coordinate position of the central point of the original data. The invention adopts a multi-period high-resolution image automatic matching method, supports quick automatic matching in upper, lower, left and right directions, quickly identifies and marks specific positions of compared images, and supports automatic derivation of batch comparison results.
Description
Technical Field
The invention belongs to the technical field of remote sensing image processing, and particularly relates to a multi-period aerial image automatic matching and comparing method.
Background
In recent years, the aviation and aerospace remote sensing technology in China has been developed rapidly, and remote sensing data has the characteristics of three high and three more, wherein the three high respectively refer to high spatial resolution, high spectral resolution and high temporal resolution, and the three more respectively refer to multi-sensor, multi-platform and multi-angle.
The remote sensing image change monitoring technology is an important field of current remote sensing scientific research, is a main research direction of current remote sensing data processing, and is widely applied to the fields of national economy and national defense construction. The change monitoring is essentially to change the target ground object characteristics at different periods, a series of preprocessing operations such as registration position analysis and the like are required to be carried out on the original data to generate result data in the traditional multi-temporal remote sensing data comparison, and the processing mode consumes a large amount of labor cost and time.
Disclosure of Invention
The purpose of the invention is as follows: aiming at the problems, the invention provides a multi-period aerial image automatic matching and comparing method, which realizes the rapid automatic matching change monitoring of target characteristic ground objects.
The technical scheme is as follows: in order to realize the purpose of the invention, the technical scheme adopted by the invention is as follows: a multi-period aerial image automatic matching comparison method comprises the following steps:
(1) the terminal imports image data in batches and updates the batch import state;
(2) preprocessing image data, calculating coordinates of an image center point, and storing the coordinates in a database;
(3) positioning, browsing and importing three-dimensional spherical scenes of batch images;
(4) and a specific position is appointed in the three-dimensional spherical scene, the request server acquires the images to be compared and the images to be compared within a certain range of the position, automatic matching of the images to be compared and the images to be compared is carried out, and a detection change result is identified and exported.
Further, the step 1 specifically includes the steps of:
(1.1) storing the image data to a specified directory of a file server, wherein the directory is named according to a batch number;
(1.2) the server scans the directory, judges whether the directory is imported and marked, and records the batch number through a database engine;
(1.3) the terminal requests the server side, acquires the image data of the uploaded file server, distinguishes and marks the import state of each batch number, executes the batch import task of the un-imported batch images, and updates the import state of the image batch.
Further, the step 2 specifically includes the steps of:
(2.1) the server calls a file server interface to obtain image attribute information;
and (2.2) calculating and recording the coordinate position of the image center point according to the image attribute information.
Further, the step 3 specifically includes the steps of:
(3.1) selecting the imported image batch by the terminal, and acquiring east-west, south-north direction extreme values of the image batch through the server interface;
(3.2) constructing a minimum circumscribed rectangle entity based on four-direction extremum in the three-dimensional spherical scene;
and (3.3) positioning the three-dimensional spherical scene view to the solid object in a flying way.
Further, the step 4 specifically includes the steps of:
(4.1) the terminal specifies a specific position in the three-dimensional spherical scene, acquires image data in a certain range of the position through the server interface, and selects images to be compared and compared;
and (4.2) acquiring image data to be compared and compared at the appointed position through a server buffer query interface, dragging the image data to be compared and compared in an automatic matching manner in an upper direction, a lower direction, a left direction and a right direction, identifying a detection change result and exporting the result.
Further, the step 4.1 specifically includes the steps of:
(4.1.1) setting the terminal designated position as a reference point and setting a query range;
(4.1.2) taking the reference point as the circle center and the query range as the radius, calling a map engine buffer query interface to obtain all image data in the range of the reference point and marking the linear distance between the reference point and the reference point;
and (4.1.3) sorting the data of the search result of the last step according to the distance through a database engine, and returning the result with the minimum distance value to the terminal.
Further, the step 4.2 specifically includes the steps of:
(4.2.1) assuming that the current image center point is p, when the page image to be compared is dragged to move towards the right direction, the server side searches the image center point closest to the point p in the right area, and simultaneously automatically activates dragging in the direction of consistency of the compared page image, and vice versa;
(4.2.2) identifying the feature change of the ground features of the images to be compared and compared, identifying the position information of the change area by the terminal, and saving and exporting the change detection result in batches by one key.
Has the advantages that: the method is based on homologous remote sensing images obtained by the same sensor at different time points, comparison is directly carried out by using original data, and intelligent automatic matching is realized through automatic matching of the coordinate position of the central point of the original data.
The method is suitable for multi-temporal remote sensing image change detection, and based on an unsupervised classified automatic matching technology, the method supports batch import of data and key preprocessing to obtain position information such as image longitude and latitude; the method supports automatic matching in the upper, lower, left and right directions to realize synchronization of images to be compared and compared, and is particularly suitable for a multi-temporal remote sensing image characteristic ground object change detection scene with high updating frequency.
The invention adopts browser/server (B/S) framework software, adopts a multi-period high-resolution image automatic matching method, supports quick automatic matching in upper, lower, left and right directions, quickly identifies and marks specific positions of compared images, and supports automatic export of batch comparison results.
Drawings
FIG. 1 is a schematic view of sensor emission imaging;
FIG. 2 is a schematic view of a minimum circumscribed rectangle configuration;
FIG. 3 is a flowchart of batch entity rendering of images;
fig. 4 is a schematic diagram of automatic matching region segmentation.
Detailed Description
The technical solution of the present invention is further described below with reference to the accompanying drawings and examples.
The invention relates to a multi-period aerial image automatic matching and comparing method, which comprises the following steps:
(1) importing image data in batches;
the method comprises the following steps that a terminal manages image data batch import, defaults a non-import state, triggers an import switch by the terminal, executes a batch image import task, and marks that the batch is completed after the task is completed, and the method specifically comprises the following steps:
(1.1) storing the image data to a specified directory of a file server, wherein the directory is named according to a batch number;
(1.2) the server scans the directory, judges whether the directory is imported and marked, and records the batch number through a database engine;
(1.3) the terminal requests the server side, acquires the image data of the uploaded file server, distinguishes and marks the import state of each batch number, executes the batch import task of the images of the un-imported batch, and updates the import state of the image batch.
(2) Preprocessing image data;
the server side calls a file server interface to obtain image attribute information, such as an image name, an image storage path and the like, then combines longitude and latitude, height, azimuth angle, pitch angle and the like of a sensor during aerial photography to calculate an image center point coordinate, and stores the obtained image basic information and coordinate information in a database through a database engine, and the method specifically comprises the following steps:
(2.1) the server calls a file server interface to obtain image attribute information such as an image name, an image storage path, the longitude and latitude of a sensor, the height, an azimuth angle, a pitch angle and the like;
(2.2) calculating and recording the coordinate position of the image center point by using the information obtained in the step 2.1, wherein the calculation method comprises the following steps:
x2＝x1+sinθ*tan(90-|α|)*h/111000
y2＝y1+cosθ*tan(90-|α|)*h/(111000*cos y1)
wherein x is1、y1Is longitude and latitude of the shooting point, h is relative height of the shooting point and a ground projection point, α is an inclination angle, theta is an azimuth angle, and x2、y2The longitude and latitude of the central point of the photo.
As shown in fig. 1, the distance between the ground projection point of the shooting point and the central point of the picture is calculated according to the inclination angle α and the relative height h, and then the distance and the longitude and latitude x of the shooting point are calculated1、y1Calculating the azimuth theta to obtain the longitude and latitude x of the central point of the photo2、y2。
(3) Browsing and positioning the image;
the terminal requests the server for image batch data in different time periods, analyzes a returned result by the terminal page and marks whether each batch of images is imported into the library, and selects the imported batch to position and preview the frame range of the images in the batch, as shown in fig. 2, the method specifically comprises the following steps:
(3.1) selecting the imported image batch by the terminal, and acquiring east-west, south-north-direction extreme values of the image batch through the server interface, wherein the east-south-north-direction extreme values are respectively set as west, south, east and normal;
(3.2) constructing a minimum circumscribed rectangle entity based on four-direction extremum in the three-dimensional spherical scene, as shown in FIG. 3;
and (3.3) finally, the three-dimensional spherical scene view is positioned to the solid object in a flying way.
(4) Automatic matching;
the terminal appoints a specific position in a three-dimensional spherical scene, the request server acquires an image to be compared and a comparison image which are (configurable) in a certain range of the position and are closest to the position, the terminal can be dragged up, down, left and right to realize automatic matching of the image to be compared and the comparison image, and a recognition detection change result is automatically derived, and the method specifically comprises the following steps:
(4.1) the terminal specifies a specific position in the three-dimensional spherical scene, acquires image data in a certain range of the position through the server interface, and individually supports selection of a version to be compared and a comparison version; the image acquisition method comprises the following steps:
(4.1.1) setting the terminal designated position as a reference point and setting a query range;
(4.1.2) taking the reference point as the circle center and the query range as the radius, calling a map engine buffer query interface to obtain all image data in the reference point range and marking the linear distance between the reference point and the reference point;
and (4.1.3) sorting the data of the search result of the last step according to the distance through a database engine, and returning the result with the minimum distance value to the terminal.
And (4.2) acquiring image data to be compared and compared at a specified position through a server buffer query interface when the front-end page to be compared and the comparison page are initialized, supporting automatic matching comparison of up-down, left-right and four-direction dragging, identifying a detection change result and exporting the result.
As shown in fig. 4, the detailed process of the automated matching is as follows:
(4.2.1) assuming that the current image center point is p, when the to-be-compared page image is dragged to move towards the right direction, the server side searches the image center point closest to the point p in the right area shown in figure 4, and simultaneously automatically activates dragging in the consistency direction of the compared page image, and vice versa;
(4.2.2) identifying the feature change of the ground features of the images to be compared and compared in an unsupervised mode, identifying the position information of the change area by the terminal, supporting one-key batch storage of the detection result of the derived change, and enabling the content of the derived result to comprise a changed local picture, detailed description of the change, a grid manager, latitude and longitude information and the like.
Claims (5)
1. A multi-period aerial image automatic matching comparison method is characterized by comprising the following steps:
(1) the terminal imports image data in batches and updates the batch import state;
(2) preprocessing image data, calculating coordinates of an image center point, and storing the coordinates in a database;
(3) positioning, browsing and importing three-dimensional spherical scenes of batch images;
(4) appointing a specific position in a three-dimensional spherical scene, requesting a server to acquire an image to be compared and a comparison image within a certain range of the position, automatically matching the image to be compared and the comparison image, identifying a detection change result and deriving the result;
in the step (4), the method specifically comprises the following steps:
(4.1) the terminal specifies a specific position in the three-dimensional spherical scene, acquires image data in a certain range of the position through the server interface, and selects images to be compared and compared;
(4.2) acquiring image data to be compared and compared at a specified position through a server buffer query interface, dragging the image data to be compared and compared in an automatic matching manner in four directions, namely, up, down, left and right, identifying a detection change result and exporting the detection change result;
in the step (4.2), the method specifically comprises the following steps:
(4.2.1) assuming that the current image center point is p, when the page image to be compared is dragged to move towards the right direction, the server side searches the image center point closest to the point p in the right area, and simultaneously automatically activates dragging in the direction of consistency of the compared page image, and vice versa;
(4.2.2) identifying the feature change of the ground features of the images to be compared and compared, identifying the position information of the change area by the terminal, and saving and exporting the change detection result in batches by one key.
2. The method according to claim 1, wherein the step (1) comprises the following steps:
(1.1) storing the image data to a specified directory of a file server, wherein the directory is named according to a batch number;
(1.2) the server scans the directory, judges whether the directory is imported and marked, and records the batch number through a database engine;
(1.3) the terminal requests the server side, acquires the image data of the uploaded file server, distinguishes and marks the import state of each batch number, executes the batch import task of the un-imported batch images, and updates the import state of the image batch.
3. The method according to claim 1, wherein the step (2) comprises the following steps:
(2.1) the server calls a file server interface to obtain image attribute information;
and (2.2) calculating and recording the coordinate position of the image center point according to the image attribute information.
4. The method according to claim 1, wherein the step (3) comprises the following steps:
(3.1) selecting the imported image batch by the terminal, and acquiring east-west, south-north direction extreme values of the image batch through the server interface;
(3.2) constructing a minimum circumscribed rectangle entity based on four-direction extremum in the three-dimensional spherical scene;
and (3.3) positioning the three-dimensional spherical scene view to the solid object in a flying way.
5. The method according to claim 1, wherein the step (4.1) comprises the following steps:
(4.1.1) setting the terminal designated position as a reference point and setting a query range;
(4.1.2) taking the reference point as the circle center and the query range as the radius, calling a map engine buffer query interface to obtain all image data in the range of the reference point and marking the linear distance between the reference point and the reference point;
and (4.1.3) sorting the data of the search result of the last step according to the distance through a database engine, and returning the result with the minimum distance value to the terminal.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201911402952.5A CN111241935B (en) | 2019-12-31 | 2019-12-31 | Automatic matching and comparing method for multi-period aerial images |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201911402952.5A CN111241935B (en) | 2019-12-31 | 2019-12-31 | Automatic matching and comparing method for multi-period aerial images |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN111241935A CN111241935A (en) | 2020-06-05 |
| CN111241935B true CN111241935B (en) | 2020-10-13 |
Family
ID=70872276
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201911402952.5A Active CN111241935B (en) | 2019-12-31 | 2019-12-31 | Automatic matching and comparing method for multi-period aerial images |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN111241935B (en) |
Citations (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| WO2011086803A1 (en) * | 2010-01-12 | 2011-07-21 | 日本電気株式会社 | Image matching system, image matching method, computer program |
| CN102930585A (en) * | 2012-09-19 | 2013-02-13 | 浙江大学 | Method for using Flash to achieve three-dimensional network map diorama |
| CN103268358A (en) * | 2013-06-05 | 2013-08-28 | 国家测绘地理信息局卫星测绘应用中心 | Method for constructing and updating multi-source control-point image database |
| CN103700110A (en) * | 2013-12-27 | 2014-04-02 | 重庆交通大学 | Full-automatic image matching method |
| CN103822616A (en) * | 2014-03-18 | 2014-05-28 | 武汉大学 | Remote-sensing image matching method with combination of characteristic segmentation with topographic inequality constraint |
| CN109934914A (en) * | 2019-03-28 | 2019-06-25 | 东南大学 | A kind of embedded urban design scene simulation method and system |
| CN110533766A (en) * | 2019-08-06 | 2019-12-03 | 陕西土豆数据科技有限公司 | It is a kind of based on exempt from as control PPK data oblique photograph image intelligence wiring method |
Family Cites Families (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20110075146A1 (en) * | 2009-09-29 | 2011-03-31 | Nathan Moroney | Color measurement device |
-
2019
- 2019-12-31 CN CN201911402952.5A patent/CN111241935B/en active Active
Patent Citations (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| WO2011086803A1 (en) * | 2010-01-12 | 2011-07-21 | 日本電気株式会社 | Image matching system, image matching method, computer program |
| CN102930585A (en) * | 2012-09-19 | 2013-02-13 | 浙江大学 | Method for using Flash to achieve three-dimensional network map diorama |
| CN103268358A (en) * | 2013-06-05 | 2013-08-28 | 国家测绘地理信息局卫星测绘应用中心 | Method for constructing and updating multi-source control-point image database |
| CN103700110A (en) * | 2013-12-27 | 2014-04-02 | 重庆交通大学 | Full-automatic image matching method |
| CN103822616A (en) * | 2014-03-18 | 2014-05-28 | 武汉大学 | Remote-sensing image matching method with combination of characteristic segmentation with topographic inequality constraint |
| CN109934914A (en) * | 2019-03-28 | 2019-06-25 | 东南大学 | A kind of embedded urban design scene simulation method and system |
| CN110533766A (en) * | 2019-08-06 | 2019-12-03 | 陕西土豆数据科技有限公司 | It is a kind of based on exempt from as control PPK data oblique photograph image intelligence wiring method |
Also Published As
| Publication number | Publication date |
|---|---|
| CN111241935A (en) | 2020-06-05 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN108564647B (en) | A method of establishing virtual three-dimensional map | |
| CN107516077B (en) | Traffic sign information extraction method based on fusion of laser point cloud and image data | |
| CN107133325B (en) | Internet photo geographic space positioning method based on street view map | |
| Fan et al. | Registration of optical and SAR satellite images by exploring the spatial relationship of the improved SIFT | |
| CN110443898A (en) | A kind of AR intelligent terminal target identification system and method based on deep learning | |
| CN111383205B (en) | Image fusion positioning method based on feature points and three-dimensional model | |
| CN110866079A (en) | Intelligent scenic spot real scene semantic map generating and auxiliary positioning method | |
| Wang et al. | Bottle detection in the wild using low-altitude unmanned aerial vehicles | |
| CN110263716B (en) | Remote sensing image super-resolution land cover mapping method based on street view image | |
| CN109741325B (en) | Intelligent detection method for wiring verticality | |
| CN109033989A (en) | Target identification method, device and storage medium based on three-dimensional point cloud | |
| CN113901874A (en) | Tea tender shoot identification and picking point positioning method based on improved R3Det rotating target detection algorithm | |
| CN114549871A (en) | Unmanned aerial vehicle aerial image and satellite image matching method | |
| CN112946679B (en) | Unmanned aerial vehicle mapping jelly effect detection method and system based on artificial intelligence | |
| CN114580559A (en) | Speed measuring method based on monocular vision system | |
| CN111241935B (en) | Automatic matching and comparing method for multi-period aerial images | |
| Zhang et al. | Dense 3d mapping for indoor environment based on feature-point slam method | |
| CN117496401A (en) | Full-automatic identification and tracking method for oval target points of video measurement image sequences | |
| CN111627059A (en) | Method for positioning center point position of cotton blade | |
| CN106603888A (en) | Image color extraction processing structure | |
| CN113642430B (en) | VGG+ NetVLAD-based high-precision visual positioning method and system for underground parking garage | |
| CN116309871A (en) | Ecological garden scene-oriented laser radar and camera online calibration method | |
| CN109118576A (en) | Large scene three-dimensional reconstruction system and method for reconstructing based on BDS location-based service | |
| CN113163139A (en) | High-altitude unmanned aerial vehicle reconnaissance image information real-time processing method | |
| Li et al. | Low-cost 3D building modeling via image processing |
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 | ||
| TR01 | Transfer of patent right |
Effective date of registration: 20231206 Address after: Room 06, 16 / F, Hejing international, No. 616, Minzhu Road, Wuchang District, Wuhan City, Hubei Province 430060 Patentee after: Feiyan Aviation Remote Sensing Technology Co.,Ltd. Patentee after: Zhejiang New Vision Geographic Information Technology Co.,Ltd. Address before: Room 06, 16 / F, Hejing international, No. 616, Minzhu Road, Wuchang District, Wuhan City, Hubei Province 430060 Patentee before: Feiyan Aviation Remote Sensing Technology Co.,Ltd. |
|
| TR01 | Transfer of patent right |