CN106530326A - Change detection method based on image texture features and DSM - Google Patents
Change detection method based on image texture features and DSM Download PDFInfo
- Publication number
- CN106530326A CN106530326A CN201610962666.4A CN201610962666A CN106530326A CN 106530326 A CN106530326 A CN 106530326A CN 201610962666 A CN201610962666 A CN 201610962666A CN 106530326 A CN106530326 A CN 106530326A
- Authority
- CN
- China
- Prior art keywords
- change
- dsm
- image
- detection sensor
- raw video
- 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
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T2207/00—Indexing scheme for image analysis or image enhancement
- G06T2207/10—Image acquisition modality
- G06T2207/10032—Satellite or aerial image; Remote sensing
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T2207/00—Indexing scheme for image analysis or image enhancement
- G06T2207/10—Image acquisition modality
- G06T2207/10032—Satellite or aerial image; Remote sensing
- G06T2207/10044—Radar image
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T2207/00—Indexing scheme for image analysis or image enhancement
- G06T2207/30—Subject of image; Context of image processing
- G06T2207/30181—Earth observation
Landscapes
- Image Processing (AREA)
- Image Analysis (AREA)
Abstract
The invention provides a change detection method based on image texture features and DSM. The method comprises the steps that surface features are divided into a plurality of types of surface features; according to the characteristics of each surface feature type, the elevation change threshold range corresponding to each type of surface feature is set; statistical analysis is carried out on texture features corresponding to each type of surface feature; for each sub-region, the corresponding texture features set in the first step and the corresponding elevation change threshold range are retrieved according to the surface feature type corresponding to the sub-region; the texture features and the elevation change threshold range corresponding to the surface feature type are used to further determine a preliminary change detection result; and whether the preliminary change detection result is correct is determined. The change detection method provided by the invention has the advantages that the texture features and the DSM information are integrated into a change detection process with different surface feature thresholds, and the change detection precision is effectively improved.
Description
Technical field
The invention belongs to change detection techniques field, and in particular to a kind of change based on image texture feature and DSM is examined
Survey method.
Background technology
Remote sensing image change detection techniques are referred to：By analyzing two secondary or several figures in different time from areal
Picture, detects the change information that the atural object of this area occurred with the time.At present, change detection techniques quickly grow, and extensively apply
In fields such as environmental monitoring, Land_use change, crop growth condition monitoring, the condition of a disaster estimations.
Level of the change detection techniques according to processing information, is divided into Pixel-level, three levels of feature level and decision level, with
Complexity and the multifarious increase of remotely-sensed data of land cover pattern change, at new change detecting method and new image
Adjustment method is continued to bring out, and builds the emphasis direction that stable, reliable change detection algorithm is always change-detection area research.
Existing change detection techniques, only select single image feature in two-dimensional space as dealing with objects and sentence
Other foundation.This kind of change detecting method is primarily present following deficiency：Requirement of this kind of change detecting method to image data is very
Strictly.But, how uneven different image-forming conditions, the image of different phases, quality be, therefore, using traditional change-detection
Method, the problem with change-detection limited precision, it is difficult to meet the demand of the high measurement accuracy of specific area.
The content of the invention
For the defect that prior art is present, the present invention provides a kind of based on image texture feature and the change-detection of DSM
Method, can effectively solving the problems referred to above.
The technical solution used in the present invention is as follows：
The present invention provides a kind of based on image texture feature and the change detecting method of DSM, comprises the following steps：
Atural object is divided into various types of ground objects by step 1；According to the characteristics of every kind of type of ground objects, every kind of atural object pair is set
The elevation change threshold scope answered；Meanwhile, statistical analysiss obtain the corresponding textural characteristics of every kind of atural object；
Step 2, the two width remote sensing images that same region different time is obtained are referred to as the 1st raw video and the 2nd original shadow
Picture；Respectively the 1st raw video and the 2nd raw video are carried out after pretreatment, to the 1st raw video and described
2nd raw video carries out initial change-detection, determines the 1st raw video relative to the preliminary of the 2nd raw video
Region of variation, obtains preliminary change-detection result；
Step 3, is split by type of ground objects to the preliminary region of variation, is divided into only comprising a type atural object
Subregion；
Step 4, for every sub-regions, according to the corresponding type of ground objects of the subregion, is deployed into the correspondence of step 1 setting
Textural characteristics and corresponding elevation change threshold scope；Changed using textural characteristics corresponding with the type of ground objects and elevation
Threshold range, is further judged to the preliminary change-detection result, whether just to judge the preliminary change-detection result
Really.
Preferably, in step 1, the elevation change threshold scope is prepared by the following：
Detection sensor is carried in ground surface platform, space platform or airborne platform；By the detection sensor, obtain every
Plant the corresponding elevation change threshold scope of atural object.
Preferably, following detection sensor is carried in ground surface platform：Three-dimensional laser scanner or digital camera；
Following detection sensor is carried in space platform：Spaceborne three-dimensional laser radar, satellite-borne synthetic aperture radar and spaceborne
One kind in multispectral sensor；
Following detection sensor is carried in airborne platform：Image data detection sensor, three-dimensional laser point cloud data detection
Sensor and radar data detection sensor.
Preferably, the corresponding textural characteristics of every kind of atural object pass through statistical texture analysis or structural texture analysis is obtained.
Preferably, numerical characteristic of the textural characteristics for being obtained by statistical texture analysis for statistic texture, including image office
One or more in the auto-correlation function in portion region, gray level co-occurrence matrixes, the gray scale distance of swimming and intensity profile.
Preferably, the textural characteristics for being obtained by structural texture analysis are included：Energy, contrast, correlation, entropy, unfavourable balance away from,
Intermediate value, covariance, homogeneity, contrast, heterogeneity, second order one or more in, auto-correlation.
What the present invention was provided has advantages below based on the change detecting method of image texture feature and DSM：
During textural characteristics and DSM information are incorporated into change-detection in the way of different atural object threshold values by the present invention, from
And effectively improve change-detection precision.
Description of the drawings
Fig. 1 for the present invention provide based on image texture feature and the schematic flow sheet of the change detecting method of DSM.
Specific embodiment
In order that technical problem solved by the invention, technical scheme and beneficial effect become more apparent, below in conjunction with
Drawings and Examples, the present invention will be described in further detail.It should be appreciated that specific embodiment described herein only to
The present invention is explained, is not intended to limit the present invention.
In order to weaken the impact of single features index and the quality of image to change-detection, the present invention provides a kind of based on shadow
As textural characteristics and the change detecting method of DSM (Digital Surface Model, DSM), by remote sensing imagery change detection from two dimension
Spatial spread improves change-detection precision to three dimensions.The change based on image texture feature and DSM that the present invention is provided is examined
Survey method, comprises the following steps：
Atural object is divided into various types of ground objects by step 1；According to the characteristics of every kind of type of ground objects, every kind of atural object pair is set
The elevation change threshold scope answered；Meanwhile, statistical analysiss obtain the corresponding textural characteristics of every kind of atural object；
In this step, elevation change threshold scope is prepared by the following：It is flat in ground surface platform, space platform or aviation
Platform carries detection sensor；By the detection sensor, the corresponding elevation change threshold scope of every kind of atural object is obtained.
Specifically, following detection sensor is carried in ground surface platform：Three-dimensional laser scanner or digital camera (can be constituted vertical
Body image to).
Following detection sensor is carried in space platform：Spaceborne three-dimensional laser radar (LIDAR), satellite-borne synthetic aperture radar
(INSAR) one kind and in satellite-borne multispectral sensor (stereogram can be constituted)；
Following detection sensor is carried in airborne platform：Image data detection sensor, three-dimensional laser point cloud data detection
Sensor and radar data detection sensor.Specifically include：Aviation digital camera, high pixel aviation digital camera, RC30 aviations
Photographing unit, RMKTOP aeroplane photography instrument, LMK2000 aerial surveying cameras, the digital aerial surveying cameras of DMC, Nikon cameras, Canon's camera, three-dimensional
In laser radar (LIDAR), low latitude number remote sensing system, airborne synthetic aperture radar (INSAR), airborne imaging spectrum instrument one
Plant or several.
The corresponding textural characteristics of every kind of atural object pass through statistical texture analysis or structural texture analysis is obtained.Wherein, by system
Numerical characteristic of the textural characteristics that meter texture analysiss are obtained for statistic texture, including auto-correlation function, the ash of image local area
One or more in degree co-occurrence matrix, the gray scale distance of swimming and intensity profile.The textural characteristics obtained by structural texture analysis
Including：Energy, contrast, correlation, entropy, unfavourable balance away from, intermediate value, covariance, homogeneity, contrast, heterogeneity, second order is away from, auto-correlation
In one or more.
Step 2, the two width remote sensing images that same region different time is obtained are referred to as the 1st raw video and the 2nd original shadow
Picture；Respectively the 1st raw video and the 2nd raw video are carried out after pretreatment, to the 1st raw video and described
2nd raw video carries out initial change-detection, determines the 1st raw video relative to the preliminary of the 2nd raw video
Region of variation, obtains preliminary change-detection result；
On implementing, preliminary change-detection result is obtained by the following method：
The raw video of two phases is carried out Yunnan snub-nosed monkey, including radiation calibration, atmospheric correction, geometry school respectively
Just, visual fusion, image registration, extraction image texture feature, obtain pretreated remote sensing image；Two phases are extracted simultaneously
DSM data, DSM data acquisition time will be consistent with piece acquisition time is defended.
Two phase images choose common sample (suitable sample is selected in non-region of variation), add image feature
Parameter, carries out image supervised classification, and algorithm can obtain classification results with method of maximum likelihood, mahalanobis distance method etc..
Based on the classification results of phase data when two, change detection after being classified by the algorithm of difference or conversion, obtain
Preliminary result is arrived, while its change to attributes and direction can also be obtained.
Step 3, is split by type of ground objects to the preliminary region of variation, is divided into only comprising a type atural object
Subregion；
Step 4, for every sub-regions, according to the corresponding type of ground objects of the subregion, is deployed into the correspondence of step 1 setting
Textural characteristics and corresponding elevation change threshold scope；Changed using textural characteristics corresponding with the type of ground objects and elevation
Threshold range, is further judged to the preliminary change-detection result, whether just to judge the preliminary change-detection result
Really.
In the present invention, by arranging the corresponding elevation change threshold scope of different atural objects, for example, when forest information occurs to become
During change, an elevation change threshold scope is drafted, meet the rule of local trees average height change；And work as building site generation
During change, an elevation change threshold scope is also drafted, and notified and there is larger difference with the threshold interval of trees.
The change-detection of elevation information is added, the decision condition of region of variation is increased, is greatly reduced because " jljl is different
The change information erroneous judgement that the light spectrum of defect of spectrum, the same spectrum of foreign body " is caused, in addition, the altitude data for adding precision higher, obtains more
Accurately orthography, can reduce the error caused because of atural object shadow region or height displacement.
As can be seen here, what the present invention was provided has advantages below based on the change detecting method of image texture feature and DSM：
During textural characteristics and DSM information are incorporated into change-detection in the way of different atural object threshold values by the present invention, from
And effectively improve change-detection precision.
The above is only the preferred embodiment of the present invention, it is noted that for the ordinary skill people of the art
For member, under the premise without departing from the principles of the invention, some improvements and modifications can also be made, these improvements and modifications also should
Depending on protection scope of the present invention.
Claims (6)
1. it is a kind of based on image texture feature and the change detecting method of DSM, it is characterised in that to comprise the following steps：
Atural object is divided into various types of ground objects by step 1；According to the characteristics of every kind of type of ground objects, every kind of atural object is set corresponding
Elevation change threshold scope；Meanwhile, statistical analysiss obtain the corresponding textural characteristics of every kind of atural object；
Step 2, the two width remote sensing images that same region different time is obtained are referred to as the 1st raw video and the 2nd raw video；Point
It is other that 1st raw video and the 2nd raw video are carried out after pretreatment, to the 1st raw video and described 2nd former
Beginning image carries out initial change-detection, determines preliminary variation zone of the 1st raw video relative to the 2nd raw video
Domain, obtains preliminary change-detection result；
Step 3, is split by type of ground objects to the preliminary region of variation, is divided into the only sub-district comprising a type atural object
Domain；
Step 4, for every sub-regions, according to the corresponding type of ground objects of the subregion, is deployed into the corresponding stricture of vagina of step 1 setting
Reason feature and corresponding elevation change threshold scope；Using textural characteristics corresponding with the type of ground objects and elevation change threshold
Scope, is further judged to the preliminary change-detection result, judges whether the preliminary change-detection result is correct.
2. it is according to claim 1 based on image texture feature and the change detecting method of DSM, it is characterised in that step 1
In, the elevation change threshold scope is prepared by the following：
Detection sensor is carried in ground surface platform, space platform or airborne platform；By the detection sensor, obtain every kind ofly
The corresponding elevation change threshold scope of thing.
3. it is according to claim 2 based on image texture feature and the change detecting method of DSM, it is characterised in that on ground
Face platform carries following detection sensor：Three-dimensional laser scanner or digital camera；
Following detection sensor is carried in space platform：Spaceborne three-dimensional laser radar, satellite-borne synthetic aperture radar and spaceborne light more
One kind in spectrum sensor；
Following detection sensor is carried in airborne platform：Image data detection sensor, three-dimensional laser point cloud data detection sensing
Device and radar data detection sensor.
4. it is according to claim 1 based on image texture feature and the change detecting method of DSM, it is characterised in that every kind of
The corresponding textural characteristics of atural object pass through statistical texture analysis or structural texture analysis is obtained.
5. it is according to claim 4 based on image texture feature and the change detecting method of DSM, it is characterised in that to pass through
The textural characteristics that statistical texture analysis are obtained for statistic texture numerical characteristic, including image local area auto-correlation function,
One or more in gray level co-occurrence matrixes, the gray scale distance of swimming and intensity profile.
6. it is according to claim 4 based on image texture feature and the change detecting method of DSM, it is characterised in that to pass through
The textural characteristics that structural texture analysis is obtained include：Energy, contrast, correlation, entropy, unfavourable balance away from, intermediate value, covariance, homogeneity,
Contrast, heterogeneity, second order one or more in, auto-correlation.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201610962666.4A CN106530326B (en) | 2016-11-04 | 2016-11-04 | Change detecting method based on image texture feature and DSM |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201610962666.4A CN106530326B (en) | 2016-11-04 | 2016-11-04 | Change detecting method based on image texture feature and DSM |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN106530326A true CN106530326A (en) | 2017-03-22 |
| CN106530326B CN106530326B (en) | 2019-07-12 |
Family
ID=58326191
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201610962666.4A Active CN106530326B (en) | 2016-11-04 | 2016-11-04 | Change detecting method based on image texture feature and DSM |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN106530326B (en) |
Cited By (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN110310246A (en) * | 2019-07-05 | 2019-10-08 | 广西壮族自治区基础地理信息中心 | A kind of cane -growing region remote sensing information extracting method based on three-line imagery |
| CN113920266A (en) * | 2021-11-03 | 2022-01-11 | 泰瑞数创科技(北京)有限公司 | Artificial intelligence generation method and system for semantic information of city information model |
Citations (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20070292581A1 (en) * | 2001-04-20 | 2007-12-20 | Novozymes A/S | Lipoxygenase |
| CN104049259A (en) * | 2014-07-01 | 2014-09-17 | 南京大学 | Lidar three-dimensional imaging system based on virtual instrument |
-
2016
- 2016-11-04 CN CN201610962666.4A patent/CN106530326B/en active Active
Patent Citations (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20070292581A1 (en) * | 2001-04-20 | 2007-12-20 | Novozymes A/S | Lipoxygenase |
| CN104049259A (en) * | 2014-07-01 | 2014-09-17 | 南京大学 | Lidar three-dimensional imaging system based on virtual instrument |
Non-Patent Citations (2)
| Title |
|---|
| 刘龙飞等: "遥感影像纹理分析方法综述与展望", 《遥感技术与应用》 * |
| 连浩东: "基于无人机影像的建筑物变化量提取研究", 《中国优秀硕士学位论文全文数据库基础科学辑》 * |
Cited By (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN110310246A (en) * | 2019-07-05 | 2019-10-08 | 广西壮族自治区基础地理信息中心 | A kind of cane -growing region remote sensing information extracting method based on three-line imagery |
| CN110310246B (en) * | 2019-07-05 | 2023-04-11 | 广西壮族自治区基础地理信息中心 | Sugarcane planting area remote sensing information extraction method based on three-linear array image |
| CN113920266A (en) * | 2021-11-03 | 2022-01-11 | 泰瑞数创科技(北京)有限公司 | Artificial intelligence generation method and system for semantic information of city information model |
| CN113920266B (en) * | 2021-11-03 | 2022-10-21 | 泰瑞数创科技(北京)股份有限公司 | Artificial intelligence generation method and system for semantic information of city information model |
Also Published As
| Publication number | Publication date |
|---|---|
| CN106530326B (en) | 2019-07-12 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| Piermattei et al. | Suitability of ground-based SfM–MVS for monitoring glacial and periglacial processes | |
| Lu et al. | Object-oriented change detection for landslide rapid mapping | |
| CN107560592B (en) | Precise distance measurement method for photoelectric tracker linkage target | |
| CN111832518B (en) | Space-time fusion-based TSA remote sensing image land utilization method | |
| CN108731587A (en) | A kind of the unmanned plane dynamic target tracking and localization method of view-based access control model | |
| WO2013088175A1 (en) | Image processing method | |
| CN110988909B (en) | TLS-based vegetation coverage measuring method for sand vegetation in severe cold fragile area | |
| CN106156758B (en) | A kind of tidal saltmarsh method in SAR seashore image | |
| CN103226819A (en) | Segmental counting-based relative radiation correction method | |
| CN108428220A (en) | Satellite sequence remote sensing image sea island reef region automatic geometric correction method | |
| CN112445241A (en) | Ground surface vegetation identification method and system based on unmanned aerial vehicle remote sensing technology and readable storage medium | |
| Li et al. | Individual tree delineation in windbreaks using airborne-laser-scanning data and unmanned aerial vehicle stereo images | |
| Demir | Using UAVs for detection of trees from digital surface models | |
| CN110197185A (en) | A kind of method and system based on Scale invariant features transform algorithm monitoring space under bridge | |
| Ming et al. | Cropland extraction based on OBIA and adaptive scale pre-estimation | |
| Guldogan et al. | Automated tree detection and density calculation using unmanned aerial vehicles | |
| CN117848503B (en) | Multi-spectral-band polarization intelligent detection device and method for three-dimensional restoration of high-precision target | |
| CN106530326B (en) | Change detecting method based on image texture feature and DSM | |
| Agarwal et al. | Development of machine learning based approach for computing optimal vegetation index with the use of sentinel-2 and drone data | |
| CN117274900A (en) | Method and device for identifying bad weather facing expressway | |
| Daengsi et al. | Irrigation Management: A Pilot Study for Automatic Water Level Measurement and Report System Development Using Machine Learning Associated with Modified Images | |
| Papasaika et al. | Fusion of digital elevation models from various data sources | |
| CN110070513A (en) | The radiation correction method and system of remote sensing image | |
| Liu | Comparing the different seasonal CBERS 04 images to map the quasi-circular vegetation patches in the Yellow River Delta, China | |
| Piermattei et al. | Analysis of glacial and periglacial processes using structure from motion. |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| C06 | 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 |