CN106530326B - Change detecting method based on image texture feature and DSM - Google Patents
Change detecting method based on image texture feature and DSM Download PDFInfo
- Publication number
- CN106530326B CN106530326B CN201610962666.4A CN201610962666A CN106530326B CN 106530326 B CN106530326 B CN 106530326B CN 201610962666 A CN201610962666 A CN 201610962666A CN 106530326 B CN106530326 B CN 106530326B
- Authority
- CN
- China
- Prior art keywords
- image
- dsm
- threshold range
- variation
- atural object
- 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
- 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
Abstract
The present invention provides a kind of change detecting method based on image texture feature and DSM, comprising the following steps: step 1, atural object is divided into a variety of types of ground objects；The characteristics of according to every kind of type of ground objects, the corresponding elevation change threshold range of every kind of atural object of setting；Meanwhile statistical analysis obtains the corresponding textural characteristics of every kind of atural object；For each subregion, according to the corresponding type of ground objects of the subregion, it is deployed into the corresponding textural characteristics and corresponding elevation change threshold range that step 1 is set；Using textural characteristics corresponding with the type of ground objects and elevation change threshold range, further determine determine whether the preliminary variation testing result is correct to the preliminary variation testing result.Have the advantage that textural characteristics and DSM information are integrated into variation detection process by the present invention in a manner of different atural object threshold values, to effectively improve variation detection accuracy.
Description
Technical field
The invention belongs to change detection techniques fields, and in particular to a kind of variation inspection based on image texture feature and DSM
Survey method.
Background technique
Remote sensing image change detection techniques refer to: by analyzing two from areal secondary or several figures in different time
Picture detects the change information that the atural object of this area occurs at any time.Currently, change detection techniques are quickly grown, it is widely applied
In fields such as environmental monitoring, land use, crop growth condition monitoring, the condition of a disaster estimations.
Change detection techniques are divided into three Pixel-level, feature level and decision level levels according to the level of processing information, with
The complexity and the multifarious increase of remotely-sensed data of land cover pattern variation, at new change detecting method and new image
Adjustment method continues to bring out, and building is stablized, reliable change detection algorithm is always the emphasis direction for changing detection field research.
Existing change detection techniques only select single image feature as process object and are sentenced in two-dimensional space
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 the image of different image-forming conditions, different phases, how irregular quality is, therefore, is detected using traditional variation
Method, the problem for having variation detection accuracy limited, it is difficult to meet the demand of the high measurement accuracy of specific area.
Summary of the invention
In view of the defects existing in the prior art, the present invention provides a kind of variation detection based on image texture feature and DSM
Method can effectively solve the above problems.
The technical solution adopted by the invention is as follows:
The present invention provides a kind of change detecting method based on image texture feature and DSM, comprising the following steps:
Step 1, atural object is divided into a variety of types of ground objects；The characteristics of according to every kind of type of ground objects, sets every kind of atural object pair
The elevation change threshold range answered；Meanwhile statistical analysis obtains the corresponding textural characteristics of every kind of atural object；
Step 2, the two width remote sensing images that same region different time obtains are known as the 1st raw video and the 2nd original shadow
Picture；After being pre-processed respectively to the 1st raw video and the 2nd raw video, to the 1st raw video and described
2nd raw video carries out initial variation detection, determines the 1st raw video relative to the preliminary of the 2nd raw video
Region of variation obtains tentatively changing testing result；
Step 3, the preliminary region of variation is split by type of ground objects, being divided into only includes a seed type atural object
Subregion；
Step 4, the correspondence of step 1 setting is deployed into according to the subregion corresponding type of ground objects for each subregion
Textural characteristics and corresponding elevation change threshold range；Changed using textural characteristics corresponding with the type of ground objects and elevation
Threshold range further determines whether just to determine the preliminary variation testing result to the preliminary variation testing result
Really.
Preferably, in step 1, the elevation change threshold range is prepared by the following:
Detection sensor is carried in ground surface platform, space platform or airborne platform；By the detection sensor, obtain every
The corresponding elevation change threshold range of kind atural object.
Preferably, following detection sensor: three-dimensional laser scanner or digital camera is carried in ground surface platform；
Following detection sensor is carried in space platform: spaceborne three-dimensional laser radar, satellite-borne synthetic aperture radar and spaceborne
One of multispectral sensor；
Following detection sensor: image data detection sensor, three-dimensional laser point cloud data detection is carried in airborne platform
Sensor and radar data detection sensor.
Preferably, the corresponding textural characteristics of every kind of atural object are analyzed to obtain by statistical texture analysis or structural texture.
It preferably, is the numerical characteristic of statistic texture, including image office by the textural characteristics that statistical texture analysis obtains
One or more of auto-correlation function, gray level co-occurrence matrixes, the gray scale distance of swimming and the intensity profile in portion region.
Preferably, by the textural characteristics that structural texture is analyzed include: energy, contrast, correlation, entropy, unfavourable balance away from,
Intermediate value, covariance, homogeney, contrast, heterogeneity, second order are away from one or more of, auto-correlation.
Change detecting method provided by the invention based on image texture feature and DSM has the advantage that
Textural characteristics and DSM information are integrated into variation detection process by the present invention in a manner of different atural object threshold values, from
And effectively improve variation detection accuracy.
Detailed description of the invention
Fig. 1 is the flow diagram of the change detecting method provided by the invention based on image texture feature and DSM.
Specific embodiment
In order to which the technical problems, technical solutions and beneficial effects solved by the present invention is more clearly understood, below in conjunction with
Accompanying drawings and embodiments, the present invention will be described in further detail.It should be appreciated that specific embodiment described herein only to
It explains the present invention, is not intended to limit the present invention.
In order to weaken the influence of single features index and the quality of image to variation detection, the present invention provides a kind of based on shadow
As the change detecting method of textural characteristics and DSM (Digital Surface Model, DSM), by remote sensing imagery change detection from two dimension
Spatial spread improves variation detection accuracy to three-dimensional space.Variation inspection provided by the invention based on image texture feature and DSM
Survey method, comprising the following steps:
Step 1, atural object is divided into a variety of types of ground objects；The characteristics of according to every kind of type of ground objects, sets every kind of atural object pair
The elevation change threshold range answered；Meanwhile statistical analysis obtains the corresponding textural characteristics of every kind of atural object；
In this step, elevation change threshold range is prepared by the following: flat in ground surface platform, space platform or aviation
Platform carries detection sensor；By the detection sensor, the corresponding elevation change threshold range of every kind of atural object is obtained.
Specifically, carrying following detection sensor in ground surface platform: three-dimensional laser scanner or digital camera (constitute vertical
Body image to).
Following detection sensor: spaceborne three-dimensional laser radar (LIDAR), satellite-borne synthetic aperture radar is carried in space platform
(INSAR) and one of satellite-borne multispectral sensor (composable stereogram)；
Following detection sensor: image data detection sensor, three-dimensional laser point cloud data detection is carried in airborne platform
Sensor and radar data detection sensor.It specifically includes: aviation digital camera, high pixel aviation digital camera, RC30 aviation
Camera, RMKTOP aeroplane photography instrument, LMK2000 aerial surveying camera, the digital aerial surveying camera of DMC, Nikon camera, Canon's camera, three-dimensional
Laser radar (LIDAR), low latitude number remote sensing system, airborne synthetic aperture radar (INSAR), one in airborne imaging spectrum instrument
Kind is several.
The corresponding textural characteristics of every kind of atural object are analyzed to obtain by statistical texture analysis or structural texture.Wherein, pass through system
The textural characteristics that meter texture analysis obtains are the numerical characteristic of statistic texture, auto-correlation function, ash including image local area
Spend one or more of co-occurrence matrix, the gray scale distance of swimming and intensity profile.The textural characteristics analyzed by structural texture
Include: energy, contrast, correlation, entropy, unfavourable balance away from, intermediate value, covariance, homogeney, contrast, heterogeneity, second order be away from, auto-correlation
One or more of.
Step 2, the two width remote sensing images that same region different time obtains are known as the 1st raw video and the 2nd original shadow
Picture；After being pre-processed respectively to the 1st raw video and the 2nd raw video, to the 1st raw video and described
2nd raw video carries out initial variation detection, determines the 1st raw video relative to the preliminary of the 2nd raw video
Region of variation obtains tentatively changing testing result；
In specific implementation, obtain tentatively changing testing result by the following method:
The raw video of two phases is subjected to 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 are chosen common sample (suitable sample is selected in non-region of variation), and image feature is added
Parameter, carries out image supervised classification, and algorithm can use maximum likelihood method, mahalanobis distance method etc., obtain classification results.
Based on the classification results of phase data when two, change detection after being classified by the algorithm of difference or transformation is obtained
To preliminary as a result, its change to attributes and direction can also be obtained simultaneously.
Step 3, the preliminary region of variation is split by type of ground objects, being divided into only includes a seed type atural object
Subregion；
Step 4, the correspondence of step 1 setting is deployed into according to the subregion corresponding type of ground objects for each subregion
Textural characteristics and corresponding elevation change threshold range；Changed using textural characteristics corresponding with the type of ground objects and elevation
Threshold range further determines whether just to determine the preliminary variation testing result to the preliminary variation testing result
Really.
In the present invention, by the corresponding elevation change threshold range of the different atural objects of setting, for example, when forest information becomes
When change, an elevation change threshold range is drafted, meets the rule of local trees average height variation；And work as building site
When variation, an elevation change threshold range is also drafted, and has notified that there are larger differences with the threshold interval of trees.
The variation detection of elevation information is added, increases the decision condition of region of variation, greatly reduces because " jljl is different
Change information caused by the spectrum defect of spectrum, the same spectrum of foreign matter " is judged by accident, in addition, the higher altitude data of precision is added, is obtained more
Accurately orthography, error caused by reducing because of atural object shadow region or height displacement.
It can be seen that the change detecting method provided by the invention based on image texture feature and DSM has the advantage that
Textural characteristics and DSM information are integrated into variation detection process by the present invention in a manner of different atural object threshold values, from
And effectively improve variation detection accuracy.
The above is only a preferred embodiment of the present invention, it is noted that for the ordinary skill people of the art
For member, various improvements and modifications may be made without departing from the principle of the present invention, these improvements and modifications are also answered
Depending on protection scope of the present invention.
Claims (6)
1. a kind of change detecting method based on image texture feature and DSM, which comprises the following steps:
Step 1, atural object is divided into a variety of types of ground objects；The characteristics of according to every kind of type of ground objects, every kind of atural object of setting are corresponding
Elevation change threshold range；Meanwhile statistical analysis obtains the corresponding textural characteristics of every kind of atural object；
Step 2, the two width remote sensing images that same region different time obtains are known as the 1st raw video and the 2nd raw video；Point
It is other 1st raw video and the 2nd raw video are pre-processed after, to the 1st raw video and described 2nd former
Beginning image carries out initial variation detection, determines preliminary variation zone of the 1st raw video relative to the 2nd raw video
Domain obtains tentatively changing testing result；
In specific implementation, obtain tentatively changing testing result by the following method:
The raw video of two phases is subjected to Yunnan snub-nosed monkey, including radiation calibration, atmospheric correction, geometric correction, shadow respectively
As fusion, image registration, image texture feature is extracted, obtains pretreated remote sensing image；The DSM of two phases is extracted simultaneously
Data, DSM data acquisition time will be consistent with piece acquisition time is defended；
Two phase images choose common sample, i.e., suitable sample is selected in non-region of variation, and image feature parameter is added,
Image supervised classification is carried out, method maximum likelihood method, mahalanobis distance method obtain classification results；
Based on the classification results of phase data when two, change detection after being classified by the method for difference or transformation is obtained
It is preliminary as a result, also obtaining its change to attributes and direction simultaneously；
Step 3, the preliminary region of variation is split by type of ground objects, is divided into sub-district only comprising a seed type atural object
Domain；
Step 4, the corresponding line of step 1 setting is deployed into according to the subregion corresponding type of ground objects for each subregion
Manage feature and corresponding elevation change threshold range；Using textural characteristics corresponding with the type of ground objects and elevation change threshold
Range further determines determine whether the preliminary variation testing result is correct to the preliminary variation testing result；
By the corresponding elevation change threshold range of the different atural objects of setting, including when forest information changes, draft one
Elevation change threshold range meets the rule of local trees average height variation；And when building site changes, also draft
One elevation change threshold range, and notified that there are larger differences with the threshold range of trees；
The variation detection of elevation information is added, increases the decision condition of region of variation, reduces because " the different spectrum of jljl, foreign matter are same
Change information caused by the spectrum defect of spectrum " is judged by accident, in addition, the higher altitude data of precision is added, is obtained more accurately just
Projection picture, error caused by reducing because of atural object shadow region or height displacement.
2. the change detecting method according to claim 1 based on image texture feature and DSM, which is characterized in that step 1
In, the elevation change threshold range is prepared by the following:
Detection sensor is carried in ground surface platform, space platform or airborne platform；By the detection sensor, every kind of ground is obtained
The corresponding elevation change threshold range of object.
3. the change detecting method according to claim 2 based on image texture feature and DSM, which is characterized in that on ground
Face platform carries following detection sensor: three-dimensional laser scanner or digital camera；
Following detection sensor: spaceborne three-dimensional laser radar, satellite-borne synthetic aperture radar and spaceborne mostly light is carried in space platform
One of spectrum sensor；
Following detection sensor: image data detection sensor, three-dimensional laser point cloud data detection sensing is carried in airborne platform
Device and radar data detection sensor.
4. the change detecting method according to claim 1 based on image texture feature and DSM, which is characterized in that every kind
The corresponding textural characteristics of atural object are analyzed to obtain by statistical texture analysis or structural texture.
5. the change detecting method according to claim 4 based on image texture feature and DSM, which is characterized in that pass through
The textural characteristics that statistical texture analysis obtains are the numerical characteristic of statistic texture, auto-correlation function including image local area,
One or more of gray level co-occurrence matrixes, the gray scale distance of swimming and intensity profile.
6. the change detecting method according to claim 4 based on image texture feature and DSM, which is characterized in that pass through
The textural characteristics that structural texture is analyzed include: energy, contrast, correlation, entropy, unfavourable balance away from, intermediate value, covariance, homogeney,
Contrast, heterogeneity, second order are away from one or more of, 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 CN106530326A (en) | 2017-03-22 |
| CN106530326B true 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) |
Families Citing this family (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| 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 |
| 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 |
Citations (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN104049259A (en) * | 2014-07-01 | 2014-09-17 | 南京大学 | Lidar three-dimensional imaging system based on virtual instrument |
Family Cites Families (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| DE60234822D1 (en) * | 2001-04-20 | 2010-02-04 | Novozymes As | LIPOXYGENASE VARIANTS AND THEIR USE |
-
2016
- 2016-11-04 CN CN201610962666.4A patent/CN106530326B/en active Active
Patent Citations (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| 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 |
|---|
| 基于无人机影像的建筑物变化量提取研究;连浩东;《中国优秀硕士学位论文全文数据库基础科学辑》;20140415(第04期);第38-62页 |
| 遥感影像纹理分析方法综述与展望;刘龙飞等;《遥感技术与应用》;20040130;第441-447页 |
Also Published As
| Publication number | Publication date |
|---|---|
| CN106530326A (en) | 2017-03-22 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| Lu et al. | Object-oriented change detection for landslide rapid mapping | |
| Piermattei et al. | Suitability of ground-based SfM–MVS for monitoring glacial and periglacial processes | |
| CN111079556A (en) | Multi-temporal unmanned aerial vehicle video image change area detection and classification method | |
| CN102567977B (en) | Self-adaptive fusing method of infrared polarization image based on wavelets | |
| CN111832518B (en) | Space-time fusion-based TSA remote sensing image land utilization method | |
| CN107560592B (en) | Precise distance measurement method for photoelectric tracker linkage target | |
| CN108731587A (en) | A kind of the unmanned plane dynamic target tracking and localization method of view-based access control model | |
| Huang et al. | Quality assessment of panchromatic and multispectral image fusion for the ZY-3 satellite: From an information extraction perspective | |
| CN105139375B (en) | Combining global DEM and stereoscopic vision a kind of satellite image cloud detection method of optic | |
| CN110988909B (en) | TLS-based vegetation coverage measuring method for sand vegetation in severe cold fragile area | |
| CN103226819A (en) | Segmental counting-based relative radiation correction method | |
| CN109377480A (en) | Arable land use change detection method based on deep learning | |
| CN113537018A (en) | Water and soil conservation monitoring method based on multi-temporal satellite remote sensing and unmanned aerial vehicle technology | |
| CN108230375A (en) | Visible images and SAR image registration method based on structural similarity fast robust | |
| Li et al. | Individual tree delineation in windbreaks using airborne-laser-scanning data and unmanned aerial vehicle stereo images | |
| CN102175993A (en) | Radar scene matching feature reference map preparation method based on satellite SAR (synthetic aperture radar) images | |
| Li et al. | An improved approach of information extraction for earthquake-damaged buildings using high-resolution imagery | |
| Demir | Using UAVs for detection of trees from digital surface models | |
| CN106530326B (en) | Change detecting method based on image texture feature and DSM | |
| Ming et al. | Cropland extraction based on OBIA and adaptive scale pre-estimation | |
| CN107194917A (en) | In-orbit SAR image change detection based on DAP and ARELM | |
| Bandyopadhyay et al. | On the fusion of lidar and aerial color imagery to detect urban vegetation and buildings | |
| Singh et al. | Advanced image processing approach for color-texture analysis of UAV imagery for weed detection in sugarcane crop | |
| Jacq et al. | Structure-from-motion, multi-view stereo photogrammetry applied to line-scan sediment core images | |
| Broncano Mateos et al. | Relative radiometric normalization of multitemporal images |
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 |