CN106991424B - A kind of specific region based on object-oriented automatically changes monitoring method - Google Patents
A kind of specific region based on object-oriented automatically changes monitoring method Download PDFInfo
- Publication number
- CN106991424B CN106991424B CN201710211968.2A CN201710211968A CN106991424B CN 106991424 B CN106991424 B CN 106991424B CN 201710211968 A CN201710211968 A CN 201710211968A CN 106991424 B CN106991424 B CN 106991424B
- Authority
- CN
- China
- Prior art keywords
- specific region
- image
- reference images
- carried out
- orthography
- 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
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V10/00—Arrangements for image or video recognition or understanding
- G06V10/70—Arrangements for image or video recognition or understanding using pattern recognition or machine learning
- G06V10/74—Image or video pattern matching; Proximity measures in feature spaces
- G06V10/75—Organisation of the matching processes, e.g. simultaneous or sequential comparisons of image or video features; Coarse-fine approaches, e.g. multi-scale approaches; using context analysis; Selection of dictionaries
- G06V10/751—Comparing pixel values or logical combinations thereof, or feature values having positional relevance, e.g. template matching
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V10/00—Arrangements for image or video recognition or understanding
- G06V10/20—Image preprocessing
- G06V10/26—Segmentation of patterns in the image field; Cutting or merging of image elements to establish the pattern region, e.g. clustering-based techniques; Detection of occlusion
- G06V10/267—Segmentation of patterns in the image field; Cutting or merging of image elements to establish the pattern region, e.g. clustering-based techniques; Detection of occlusion by performing operations on regions, e.g. growing, shrinking or watersheds
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V10/00—Arrangements for image or video recognition or understanding
- G06V10/40—Extraction of image or video features
- G06V10/46—Descriptors for shape, contour or point-related descriptors, e.g. scale invariant feature transform [SIFT] or bags of words [BoW]; Salient regional features
- G06V10/462—Salient features, e.g. scale invariant feature transforms [SIFT]
Landscapes
- Engineering & Computer Science (AREA)
- Theoretical Computer Science (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Multimedia (AREA)
- General Physics & Mathematics (AREA)
- Physics & Mathematics (AREA)
- Evolutionary Computation (AREA)
- General Health & Medical Sciences (AREA)
- Medical Informatics (AREA)
- Software Systems (AREA)
- Databases & Information Systems (AREA)
- Computing Systems (AREA)
- Artificial Intelligence (AREA)
- Health & Medical Sciences (AREA)
- Image Processing (AREA)
Abstract
The invention belongs to a kind of specific regions based on object-oriented automatically to change monitoring method, comprising the following steps: obtains the geographic coordinate range of input image;Then it is screened according to the information of specific region basic database;RPC correction in region is carried out to the image after screening, is registrated in conjunction with reference images into automatic row image essence;Then image cutting is carried out to input image according to reference images range, obtains image slice;Then automatic relative detector calibration is carried out by image slice and reference images, then object-oriented variation detection is carried out automatically with reference images, change testing result in conjunction with basic database automatic evaluation, output variation detection information is finally updated fixed target basic database.The present invention not only can full-automatic ground quick obtaining specific region change information, moreover it is possible to realize business batch processing, be formed simultaneously sequence reference image, can be used for carrying out Time-Series analysis to specific region.
Description
Technical field
The present invention relates to Remote Sensing Image Processing Technology fields, complete more particularly to a kind of specific region based on object-oriented
Automatic variation monitoring method.
Background technique
The important research field that target dynamic monitoring is remote sensing information science is carried out using remote sensing image, is remote sensing information section
The subject technologies crossing domain such as, earth system science, statistics and computer technology is current Remote Sensing Data Processing technology
One of the main direction of development.Remote sensing change detection is exactly to determine and analyze using the remote sensing image of same earth surface area multidate
Earth's surface variation, provides the spatial distribution of atural object and its qualitative and quantitative information of variation.
The specific region feature on ground is obvious and spatial position immobilizes, can be clear on high-resolution remote sensing image
Chu's identification can use high-resolution satellite image there are many method and carry out automatic identification and extraction to these specific regions.
But the model that many ground installations are not fixed, harbour, road, bridge, airport and traffic pivot in different image in different resolution
The specific regions such as knob, model are different from, traditional heterogeneous vulnerable to high resolution image part based on the classification method of pixel
Big influence and interference.
Summary of the invention
Object-oriented method is a kind of very effective information extracting method, its most basic feature is exactly with Image Segmentation
The imaged object of acquisition is basic operating unit, is had a good application prospect in terms of the dynamic monitoring of specific region.This hair
The advantages of bright abundant excavation high-resolution satellite image, is based on Object--oriented method, for the variation monitoring of specific region, leads to
Cross satellite image is just being penetrated correction, Image registration, radiant correction and object-oriented variation detection etc. technologies combine, grind
Study carefully the innovation of key technology, process flow and application model, realizes to specific region automation, the dynamic monitoring of procedure, mention
For effective qualitative and quantitative information.
The technical scheme is that a kind of specific region based on object-oriented automatically changes monitoring method, including with
Lower step:
Step 1, the corresponding ground areas of input image is obtained;
Step 2, in the basic database of specific region, correspondingly by the geographical coordinate and input image of specific region
Face range, Automatic sieve selects the image for having specific region in the corresponding ground areas of input image, and shows on Online Map
The ground areas of input image corresponding ground areas and specific region out;
Step 3, part RPC is carried out to the imagery zone comprising specific region to correct, obtain the orthography of specific region;
Step 4, by the corresponding reference images in specific region to be processed current in the basic database of specific region to specific
The orthography in region carries out automatic image essence registration, the orthography after obtaining essence registration;
Step 5, according to reference images geographic coordinate range, image cutting is carried out to the orthography after essence registration, is obtained
The image slice being completely coincident with reference images;
Step 6, automatic relative detector calibration is carried out to image slice and reference images;
Step 7, in conjunction with the invariant features of specific region atural object, image slice and reference images are split, then adopted
It is changed detection with object variation vector analysis, extracts abnormal region, exports variation range;
Step 8, in conjunction with specific region basic database, for the atural object classification of specific region, automatic Evaluation variation detection
As a result, the output effective change information in specific region, realizes the dynamic monitoring to specific region;
Step 9, by the change information of specific region and image slice typing basic database, basic database is carried out
It updates.
Moreover, the specific embodiment of the step 4 is, feature is extracted in reference images using SIFT and conventional method
Point is used as registration control points RCP, is matched by the orthography with specific region and obtains corresponding dot pair, carried out on this basis most
Small two multiply matching, construct the triangulation network, correct using small patches differential, obtain the essence registration knot of the orthography of specific region
Fruit, the orthography after obtaining essence registration.
Moreover, carrying out automatic relative detector calibration by using one kind to image slice and reference images in the step 6
It is realized based on the smooth radiation consistency processing method of low-and high-frequency separation and object level.
Moreover, being split image slice and reference images by full size or multiscale analysis side in the step 7
Method is realized.
Moreover, in the step 7 object variation vector analysis be changed detection specific embodiment it is as follows,
Assuming that O1And O2It is two phase image f respectively1And f2Corresponding two objects of same position, their feature vector
Respectively p1(p11,p12,…,p1n) and p2(p21,p22,…,p2n), n is the feature quantity of object, then O1And O2Two objects
Difference value vector be pc(p21-p11,p22-p12,…,p2n-p1n), by analyzing PcCharacteristic, judge object O1And O2What has occurred
Kind variation.
Compared with prior art, beneficial effects of the present invention: processing method of the present invention is clear, strong operability, sufficiently benefit
With the information of high-resolution satellite image, shape, geometry and the texture information of atural object inside specific region are effectively tied
Multi-scale division is carried out altogether, it is with strong points using object as minimal processing unit, avoid " the different spectrum of jljl, foreign matter are with spectrum "
The interference of phenomenon, not only can full-automatic ground quick obtaining specific region change information, moreover it is possible to realize at businessization batch
Reason, solves the problems, such as specific region dynamic monitoring, has been formed simultaneously sequence reference image, when can be used for carrying out specific region
Sequence analysis.
Detailed description of the invention
Fig. 1 is the flow chart of the embodiment of the present invention.
Fig. 2 is the image ground areas and target floor range schematic diagram of the embodiment of the present invention.
Fig. 3 is that the local RPC of the embodiment of the present invention corrects schematic illustration.
Fig. 4 is the Image registration effect diagram of the embodiment of the present invention, and Fig. 4 A is before essence is registrated, after Fig. 4 B is essence registration.
Fig. 5 is the image relative detector calibration effect diagram of the embodiment of the present invention, and Fig. 5 A is figure before relative detector calibration
5B is after relative detector calibration.
Fig. 6 is that the object-oriented of the embodiment of the present invention changes detection effect schematic diagram, and Fig. 6 A is benchmark image, and Fig. 6 B is defeated
Enter image.
Specific embodiment
A kind of specific region based on object-oriented provided by the present invention, which automatically changes monitoring method, is, to input
1A grades of products of high-resolution satellite image, without decompression, the corresponding geographic coordinate range of directly calculation image;Then according to spy
The information for determining region base information bank screens it;RPC correction in region is carried out to the image after screening, in conjunction with benchmark shadow
As being registrated into automatic row image essence;Then image cutting is carried out to input image according to reference images range, obtains image slice;
Then automatic relative detector calibration is carried out by image slice and reference images, then carries out object-oriented change automatically with reference images
Change detection, changes testing result, output variation detection information, finally to fixed target basis in conjunction with basic database automatic evaluation
Information bank is updated, formation sequence reference images.
Technical solution that the present invention will be described in detail with reference to the accompanying drawings and examples.
As shown in Figure 1, the process of the embodiment of the present invention specifically includes the following steps:
Step 1, the corresponding ground areas of input image is obtained.In original high resolution image data compressed package, include
Raw video file corresponding RPC Parameter File.Without decompression, RPC parameter text in compressed package is directly extracted
Then part information corrects model (RFM) using rational function, directly calculates four angle points of image by image RPC parameter iteration
Corresponding ground areas.
Step 2, in the basic database of specific region, the geographic coordinate range of each specific region is stored, by specific
The corresponding ground areas of geographical coordinate and input image in region, Automatic sieve, which is selected in the corresponding ground areas of input image, spy
Determine the image in region, and show the ground areas of input image corresponding ground areas and specific region on Online Map,
As shown in Fig. 2, big rectangle frame represents input image corresponding ground range in figure, small rectangle frame represents the ground model of specific region
It encloses, circle indicates the position where specific region, and crosshair expression has selected current specific region;
Step 3, not right in conjunction with the range of specific region without decompression by the compressed package of the input image after screening
Whole scape image is corrected, and is only carried out part RPC to the imagery zone comprising specific region and is corrected, obtains just penetrating for specific region
Image, as shown in figure 3, wherein the small figure on the left side is the corresponding reference images in specific region, the small figure on the right is to carry out part RPC
The orthography of correction.Directly from compressed package from extracting image data and carrying out part RPC correction, processing institute can be greatly reduced
The time needed.
Implementation method are as follows: directly extract raw video data from compressed package using the prior art, then creating a width just
Projection picture, orthography coordinate range be based on the range of specific region on extend out 100 pixels and obtain, by RFM model
The corresponding raw video pixel coordinate of each pixel of orthography is calculated, each pixel is gone out using bilinear interpolation method interpolation
Pixel value, to obtain the orthography of specific region.
Step 4, by the corresponding reference images in specific region to be processed current in the basic database of specific region to specific
The orthography in region carries out automatic image essence registration, the orthography after obtaining essence registration.
Implementation method are as follows: using SIFT and conventional method on reference images (being obtained from the basic database of specific region)
Characteristic point is extracted as registration control points RCP (Registration Control Point), by just penetrating with specific region
Image Matching obtains corresponding dot pair, carries out Least squares matching on this basis, constructs the triangulation network, entangles using small patches differential
Just, the smart registration result of the orthography of specific region is obtained.Image essence registration after orthography and reference images it is of the same name
Pixel can correspond, and registration effect is as shown in Figure 4, and Fig. 4 A indicates that reference images and orthography pixel misplace before being registrated
Greatly, Fig. 4 B indicates reference images and orthography dislocation-free after registration.
Step 5, according to reference images geographic coordinate range, image cutting is carried out to the orthography after essence registration, is obtained
The image slice being completely coincident with reference images.
Step 6, using a kind of radiation consistency processing method smooth based on low-and high-frequency separation and object level, image is cut
Piece and reference images carry out automatic relative detector calibration.
Implementation method are as follows: in image be to have the high frequency for representing prospect ground object target texture information and to represent background radiation information
Low frequency it is dimerous it is true on the basis of, first image slice and reference images are all carried out with the smoothing processing of object level,
Weaken or eliminate highlighted or special dark foreground target and image background radiation information extraction bring is interfered, it is flat to object level is carried out
Two images after cunning are converted by image carries out low-and high-frequency separation, and then low frequency part after isolation carries out the flat of spatial domain
It is sliding, reference images high-frequency information is reduced to greatest extent and is mixed into image slice, carries out ratio in the smoothed out low frequency part of spatial domain
Or difference radiation adjustment, it obtains after image slice radiation adjusts finally by image inverse transformation as a result, image relative radiation school
For positive result as shown in figure 5, wherein Fig. 5 A is the image before relative detector calibration, Fig. 5 B is the image after relative detector calibration.
Step 7, in conjunction with the invariant features of specific region atural object, a kind of image fusion for taking ground object target type into account is utilized
Dividing method is split image slice and reference images, is then changed detection using object variation vector analysis,
Abnormal region is extracted, variation range is exported.
Specific implementation method are as follows: full size/multiscale analysis method is taken in cutting procedure, so that segmentation can be based on
The classification of specific region takes different segmentation scales, reaches preferable segmentation result.For example, being directed to traffic pattern Objective extraction
When be primarily upon the extraction of long and straight type area feature, can use that the reflection of runway wave spectrum is relatively strong, has abundant straight line and angle at this time
The characteristics such as point information are split the adjustment of criterion;Full size/multiscale analysis method is taken in cutting procedure simultaneously, to the greatest extent maximum
Effort enables atural object, and inherently dimensional properties are embodied in segmentation result, for example, airfield runway by full size/
Multi-scale division can enough merge into a section object as far as possible.After segmentation, the spies such as the spectrum, texture, structure of image are recycled
Sign building object variation feature vector, is changed detection using object variation vector analysis.
Object variation method of vector analysis are as follows: assuming that O1And O2It is two phase image f respectively1And f2Same position is corresponding
Two objects, their feature vector are respectively p1(p11,p12,…,p1n) and p2(p21,p22,…,p2n), n is the feature of object
Quantity.Object is included at least in general features vector in the spectral value of each wave band and the standard deviation of each wave band, therefore n is generally extremely
Few twice image wave band number.So O1And O2The difference value vector of two objects is pc(p21-p11,p22-p12,…,p2n-p1n).Cause
This passes through analysis PcCharacteristic, so that it may judge object O1And O2Which kind of variation whether changed and had occurred, is specifically sentenced
Disconnected method can consult relevant references: change vector analytic approach [C] .The in Sun Kaimin, Chen Yan object-level change detection,
International Conference on Computational Intelligence and Industrial
Application.2010.
Step 8, in conjunction with specific region basic database, for the atural object classification of specific region, automatic Evaluation variation detection
As a result, the output effective change information in specific region, realizes the dynamic monitoring to the region, as shown in Figure 6, wherein Fig. 6 A is
Reference images, Fig. 6 B are input image, have marked out changed region with vector in fig. 6b.
Specific implementation method are as follows: according to the category setting empirical value of specific region, if anomaly occurring in inside specific region
And scale is when being greater than empirical value, then the variation that is determined as the exception inside atural object;If abnormal keep the range of specific region big
It is small to be changed, which is determined as area's extension of a field or diminution, and further using historical data variation testing result
Judge type belonging to each variation.
Step 9, by the change information of specific region and image slice typing basic database, basic database is carried out
It updates.
Specific implementation method are as follows: the expansion on specific region boundary is reduced, the increase and decrease information of atural object is for updating specific region
Essential information, image slice can form reference images sequence when there is more phase reference images as new reference images typing
Column, can be not only used for Time-Series analysis, the changing rule of analyzed area can also trace the state in specific region a certain period.
When it is implemented, computer software technology, which can be used, in the above process realizes automatic flow operation.
Specific embodiment described herein is only an example for the spirit of the invention.The neck of technology belonging to the present invention
The technical staff in domain can make various modifications or additions to the described embodiments or replace by a similar method
In generation, however, it does not deviate from the spirit of the invention or beyond the scope of the appended claims.
Claims (5)
1. a kind of specific region based on object-oriented automatically changes monitoring method, which comprises the steps of:
Step 1, the corresponding ground areas of input image is obtained;
Step 2, in the basic database of specific region, pass through the corresponding ground model of the geographical coordinate and input image of specific region
It encloses, Automatic sieve selects the image for having specific region in the corresponding ground areas of input image, and shows on Online Map defeated
Enter the ground areas of image corresponding ground areas and specific region;
Step 3, part RPC is carried out to the imagery zone comprising specific region to correct, obtain the orthography of specific region;
Step 4, by the corresponding reference images in specific region to be processed current in the basic database of specific region to specific region
Orthography carry out automatic image essence registration, obtain essence registration after orthography;
Step 5, according to reference images geographic coordinate range, image cutting is carried out to the orthography after essence registration, is obtained and base
The image slice that quasi- image is completely coincident;
Step 6, automatic relative detector calibration is carried out to image slice and reference images;
Step 7, in conjunction with the invariant features of specific region atural object, image slice and reference images are split, then using pair
As change vector analytic approach is changed detection, abnormal region is extracted, exports variation range;
Step 8, in conjunction with specific region basic database, for the atural object classification of specific region, automatic Evaluation changes testing result,
The effective change information in specific region is exported, realizes the dynamic monitoring to specific region;
Step 9, by the change information of specific region and image slice typing basic database, basic database is carried out more
Newly.
2. a kind of specific region based on object-oriented as described in claim 1 automatically changes monitoring method, feature exists
In: the specific embodiment of the step 4 is to extract characteristic point in reference images using SIFT and conventional method as registration
Control point RCP is matched by the orthography with specific region and is obtained corresponding dot pair, carries out least square on this basis
Match, construct the triangulation network, corrected using small patches differential, obtain the smart registration result of the orthography of specific region, obtains essence
Orthography after registration.
3. a kind of specific region based on object-oriented as claimed in claim 2 automatically changes monitoring method, feature exists
In: automatic relative detector calibration is carried out to image slice and reference images in the step 6 and is based on low-and high-frequency by using one kind
Separation and the smooth radiation consistency processing method of object level are realized.
4. a kind of specific region based on object-oriented as claimed in claim 3 automatically changes monitoring method, feature exists
In: image slice and reference images are split through full size or multiscale analysis method realization in the step 7.
5. a kind of specific region based on object-oriented as claimed in claim 4 automatically changes monitoring method, feature exists
In: in the step 7 object variation vector analysis be changed detection specific embodiment it is as follows,
Assuming that O1And O2It is two phase image f respectively1And f2Corresponding two objects of same position, their feature vector are respectively
p1(p11,p12,…,p1n) and p2(p21,p22,…,p2n), n is the feature quantity of object, then O1And O2The difference of two objects
Vector is pc(p21-p11,p22-p12,…,p2n-p1n), by analyzing PcCharacteristic, judge object O1And O2Which kind of change has occurred
Change.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201710211968.2A CN106991424B (en) | 2017-04-01 | 2017-04-01 | A kind of specific region based on object-oriented automatically changes monitoring method |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201710211968.2A CN106991424B (en) | 2017-04-01 | 2017-04-01 | A kind of specific region based on object-oriented automatically changes monitoring method |
Publications (2)
Publication Number | Publication Date |
---|---|
CN106991424A CN106991424A (en) | 2017-07-28 |
CN106991424B true CN106991424B (en) | 2019-08-20 |
Family
ID=59415965
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN201710211968.2A Active CN106991424B (en) | 2017-04-01 | 2017-04-01 | A kind of specific region based on object-oriented automatically changes monitoring method |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN106991424B (en) |
Cited By (1)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
EP3845283A1 (en) * | 2019-12-31 | 2021-07-07 | Giga-Byte Technology Co., Ltd. | Electronic device and method of automatically triggering hot key using display image |
Families Citing this family (2)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN110929782B (en) * | 2019-11-20 | 2021-05-18 | 天津大学 | River channel abnormity detection method based on orthophoto map comparison |
CN112579677B (en) * | 2020-11-27 | 2023-07-18 | 福建省星云大数据应用服务有限公司 | Automatic processing method for satellite remote sensing image |
Citations (1)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN104006802A (en) * | 2014-05-06 | 2014-08-27 | 国家基础地理信息中心 | Information fusion-based earth's surface three-dimensional change detection method and system |
Family Cites Families (2)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
JP6044522B2 (en) * | 2013-11-19 | 2016-12-14 | 横河電機株式会社 | Slow change detection system |
US10311302B2 (en) * | 2015-08-31 | 2019-06-04 | Cape Analytics, Inc. | Systems and methods for analyzing remote sensing imagery |
-
2017
- 2017-04-01 CN CN201710211968.2A patent/CN106991424B/en active Active
Patent Citations (1)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN104006802A (en) * | 2014-05-06 | 2014-08-27 | 国家基础地理信息中心 | Information fusion-based earth's surface three-dimensional change detection method and system |
Non-Patent Citations (4)
Title |
---|
Algorithm for relative radiometric consistency process of remote sensing images based on object-oriented smoothing and contourlet transforms;Wenzhuo Li;《 Journal of Applied Remote Sensing》;20140630;1-13页 |
一种改进型面向对象的遥感变化检测方法;闫利 等;《遥感信息》;20160630;31-36页 |
基于多尺度分割的对象级影像平滑算法;孙开敏 等;《武汉大学学报》;20090430;423-426页 |
对象级变化检测中的变化向量分析法;孙开敏 等;《 2011 International conferemce on Intelligent Computation and Industrial Application》;20111231;382-388页 |
Cited By (1)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
EP3845283A1 (en) * | 2019-12-31 | 2021-07-07 | Giga-Byte Technology Co., Ltd. | Electronic device and method of automatically triggering hot key using display image |
Also Published As
Publication number | Publication date |
---|---|
CN106991424A (en) | 2017-07-28 |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
CN104751478B (en) | Object-oriented building change detection method based on multi-feature fusion | |
Achard et al. | Tropical forest mapping from coarse spatial resolution satellite data: production and accuracy assessment issues | |
CN106991424B (en) | A kind of specific region based on object-oriented automatically changes monitoring method | |
CN101937079A (en) | Remote sensing image variation detection method based on region similarity | |
CN107067405B (en) | Remote sensing image segmentation method based on scale optimization | |
CN104834942B (en) | Remote sensing image variation detection method and system based on mask classification | |
AU2021100848A4 (en) | A Regional Extraction Method of Ecological Restoration Project in the Grassland Based on the High-resolution Remote Sensing Images | |
CN107330875A (en) | Based on the forward and reverse heterogeneous water body surrounding enviroment change detecting method of remote sensing images | |
Jamil et al. | Tree species extraction and land use/cover classification from high-resolution digital orthophoto maps | |
CN109615637A (en) | A kind of improved remote sensing image Hybrid Techniques | |
CN109726705A (en) | Extracting method, device and the electronic equipment of mangrove information | |
CN112307901A (en) | Landslide detection-oriented SAR and optical image fusion method and system | |
CN108492288B (en) | Random forest based multi-scale layered sampling high-resolution satellite image change detection method | |
Rao et al. | Spatiotemporal data fusion using temporal high-pass modulation and edge primitives | |
Ivits et al. | Object-oriented remote sensing tools for biodiversity assessment: A European approach | |
CN102063722B (en) | Image change detecting method based on principle component general inverse transformation | |
An et al. | Object-oriented urban dynamic monitoring—A case study of Haidian district of Beijing | |
CN114170503A (en) | Processing method of meteorological satellite remote sensing cloud picture | |
CN109063577A (en) | Method is determined based on the satellite image segmentation best segmental scale of information gain-ratio | |
Tiwari et al. | Potential of IRS P-6 LISS IV for agriculture field boundary delineation | |
CN112883823A (en) | Land cover category sub-pixel positioning method based on multi-source remote sensing data fusion | |
Kumar et al. | Utilizing the potential of World View− 2 for discriminating urban and vegetation features using object based classification techniques | |
Sakieh et al. | An integrated spectral-textural approach for environmental change monitoring and assessment: analyzing the dynamics of green covers in a highly developing region | |
Jiménez et al. | Segmentation as postprocessing for hyperspectral image classification | |
Zhao et al. | Assessment of SPOT-6 optical remote sensing data against GF-1 using NNDiffuse image fusion algorithm |
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 |