CN113869133A - Method, device and equipment for detecting change of remote sensing image and storage medium - Google Patents
Method, device and equipment for detecting change of remote sensing image and storage medium Download PDFInfo
- Publication number
- CN113869133A CN113869133A CN202111030253.XA CN202111030253A CN113869133A CN 113869133 A CN113869133 A CN 113869133A CN 202111030253 A CN202111030253 A CN 202111030253A CN 113869133 A CN113869133 A CN 113869133A
- Authority
- CN
- China
- Prior art keywords
- remote sensing
- target
- change
- sensing image
- feature
- 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.)
- Withdrawn
Links
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/24—Classification techniques
- G06F18/243—Classification techniques relating to the number of classes
- G06F18/24323—Tree-organised classifiers
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/25—Fusion techniques
- G06F18/253—Fusion techniques of extracted features
Landscapes
- Engineering & Computer Science (AREA)
- Data Mining & Analysis (AREA)
- Theoretical Computer Science (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Bioinformatics & Cheminformatics (AREA)
- Bioinformatics & Computational Biology (AREA)
- Artificial Intelligence (AREA)
- Evolutionary Biology (AREA)
- Evolutionary Computation (AREA)
- Physics & Mathematics (AREA)
- General Engineering & Computer Science (AREA)
- General Physics & Mathematics (AREA)
- Life Sciences & Earth Sciences (AREA)
- Image Processing (AREA)
- Image Analysis (AREA)
Abstract
The invention relates to the technical field of remote sensing, and discloses a method, a device, equipment and a storage medium for detecting changes of remote sensing images, wherein the method comprises the following steps: extracting spectral features, shape features and topographic features of the current remote sensing image of the target area; segmenting the spectral features, the shape features and the topographic features according to a preset multi-scale segmentation algorithm; detecting the obtained change characteristic sample and the non-change characteristic sample obtained by segmentation through a preset decision tree algorithm to obtain a target remote sensing change image within preset time; according to the invention, each feature of the current remote sensing image of the target area is segmented through the preset multi-scale segmentation algorithm, and the change feature sample and the non-change feature sample are detected according to the preset decision tree algorithm to obtain the target remote sensing change image, so that the change detection of the remote sensing image in the target area is realized, the detection of the remote sensing image in the complex area can be realized, and the accuracy of detecting the remote sensing image is improved.
Description
Technical Field
The invention relates to the technical field of remote sensing, in particular to a method, a device, equipment and a storage medium for detecting changes of remote sensing images.
Background
Land Use and Land Cover Change (LUCC) are core problems of global environment Change research and sustainable development research, the spatial pattern of the earth surface landscape is objectively recorded, the time-space Change process of changing the earth surface landscape by natural factors and human activities is intensively reflected, and the remote sensing technology becomes a main technical means for detecting the Land Cover Change due to the characteristics of rapidness, real time, macroscopicity, periodicity and the like, but the terrain conditions of different regions are different, and adverse factors such as obvious terrain effect, high spatial heterogeneity and the like are aimed at more complex terrain conditions.
The above is only for the purpose of assisting understanding of the technical aspects of the present invention, and does not represent an admission that the above is prior art.
Disclosure of Invention
The invention mainly aims to provide a method, a device, equipment and a storage medium for detecting the change of a remote sensing image, and aims to solve the technical problem that the prior art cannot effectively detect the remote sensing image in a complex area, so that the accuracy rate of detecting the remote sensing image is low.
In order to achieve the above object, the present invention provides a method for detecting changes in remote sensing images, comprising the steps of:
acquiring a current remote sensing image of a target area, and extracting spectral features, shape features and topographic features of the current remote sensing image;
segmenting the spectral feature, the shape feature and the topographic feature according to a preset multi-scale segmentation algorithm to obtain a target feature sample;
determining a change characteristic sample and a non-change characteristic sample according to the target characteristic sample;
and detecting the change characteristic sample and the non-change characteristic sample through a preset decision tree algorithm to obtain a target remote sensing change image in preset time so as to realize change detection of the remote sensing image in the target area.
Optionally, the acquiring a current remote sensing image of the target area includes:
acquiring terrain information, land coverage types and type change modes of all areas;
determining a target area according to the terrain information, the land coverage type and the type change mode;
and acquiring the current remote sensing image of the target area through an image capturing device in the GPS.
Optionally, the extracting spectral features, shape features and topographic features of the current remote sensing image includes:
obtaining the earth surface reflectivity, the shape index, the area index, the altitude and the gradient index of a target area according to the current remote sensing image;
calculating the earth surface reflectivity through a first calculation formula to obtain spectral characteristics;
performing data fusion on the shape index and the area index to obtain shape characteristics;
and carrying out data analysis on the altitude and gradient index to obtain the terrain feature.
Optionally, the segmenting the spectral feature, the shape feature and the topographic feature according to a preset multi-scale segmentation algorithm to obtain a target feature sample includes:
extracting a first wave band of the spectral features, a second wave band of the shape features and a third wave band of the terrain features;
respectively endowing corresponding weights to the first band, the second band and the third band through a target weight distribution strategy to obtain a first weight value, a second weight value and a third weight value;
obtaining a target homogeneity factor, and determining a target segmentation index according to the target homogeneity factor, a first weight value, a second weight value and a third weight value;
and segmenting the spectral feature, the shape feature and the topographic feature by a preset multi-scale segmentation algorithm based on the target segmentation index to obtain a target feature sample.
Optionally, the obtaining a target homogeneity factor, and determining a target segmentation index according to the target homogeneity factor, the first weight value, the second weight value, and the third weight value includes:
obtaining corresponding smoothness and compactness according to the shape characteristics;
obtaining a corresponding patch internal pixel according to the spectral characteristics;
determining a target homogeneity factor based on the smoothness, compactness, intra-patch pixels, and terrain features;
and determining a target segmentation index according to the target homogeneity factor, the first weight value, the second weight value and the third weight value.
Optionally, the determining a changed feature sample and a non-changed feature sample according to the target feature sample includes:
performing orthorectification on the target characteristic sample;
extracting the resolution of the target feature;
and registering the target characteristic sample after the orthorectification according to the resolution ratio to obtain a changed characteristic sample and a non-changed characteristic sample.
Optionally, the detecting the changed feature sample and the unchanged feature sample by using a preset decision tree algorithm to obtain a target remote sensing changed image within a preset time includes:
extracting a root node, a child node and a termination node in the preset decision tree algorithm;
dividing the change characteristic sample and the non-change characteristic sample according to the root node, the child node and the termination node to obtain change characteristics of each subset;
and detecting the change characteristics of each subset through a preset decision tree algorithm to obtain a target remote sensing change image within preset time.
In addition, in order to achieve the above object, the present invention further provides a remote sensing image change detection device, including:
the extraction module is used for acquiring a current remote sensing image of a target area and extracting spectral features, shape features and topographic features of the current remote sensing image;
the segmentation module is used for segmenting the spectral feature, the shape feature and the topographic feature according to a preset multi-scale segmentation algorithm to obtain a target feature sample;
the determining module is used for determining a change characteristic sample and a non-change characteristic sample according to the target characteristic sample;
and the detection module is used for detecting the change characteristic samples and the non-change characteristic samples through a preset decision tree algorithm to obtain a target remote sensing change image in preset time so as to realize change detection of the remote sensing image in the target area.
In addition, in order to achieve the above object, the present invention further provides a remote sensing image change detection apparatus, including: the remote sensing image change detection method comprises a memory, a processor and a remote sensing image change detection program stored on the memory and capable of running on the processor, wherein the remote sensing image change detection program is configured to realize the remote sensing image change detection method.
In addition, to achieve the above object, the present invention further provides a storage medium having a remote sensing image change detection program stored thereon, wherein the remote sensing image change detection program, when executed by a processor, implements the remote sensing image change detection method as described above.
The invention provides a remote sensing image change detection method, which comprises the steps of extracting spectral features, shape features and topographic features of a current remote sensing image by obtaining the current remote sensing image of a target area; segmenting the spectral feature, the shape feature and the topographic feature according to a preset multi-scale segmentation algorithm to obtain a target feature sample; determining a change characteristic sample and a non-change characteristic sample according to the target characteristic sample; detecting the change characteristic sample and the non-change characteristic sample by a preset decision tree algorithm to obtain a target remote sensing change image within preset time; according to the invention, each feature of the current remote sensing image of the target area is segmented through the preset multi-scale segmentation algorithm, and the change feature sample and the non-change feature sample are detected according to the preset decision tree algorithm to obtain the target remote sensing change image, so that the change detection of the remote sensing image in the target area is realized, the detection of the remote sensing image in the complex area can be realized, and the accuracy of detecting the remote sensing image is improved.
Drawings
Fig. 1 is a schematic structural diagram of a remote sensing image change detection device of a hardware operating environment according to an embodiment of the present invention;
FIG. 2 is a schematic flow chart of a method for detecting changes in remote sensing images according to a first embodiment of the present invention;
FIG. 3 is a schematic flow chart of a remote sensing image change detection method according to a second embodiment of the present invention;
FIG. 4 is a schematic flow chart of a method for detecting changes in remote sensing images according to a third embodiment of the present invention;
fig. 5 is a functional block diagram of a remote sensing image change detection apparatus according to a first embodiment of the present invention.
The implementation, functional features and advantages of the objects of the present invention will be further explained with reference to the accompanying drawings.
Detailed Description
It should be understood that the specific embodiments described herein are merely illustrative of the invention and are not intended to limit the invention.
Referring to fig. 1, fig. 1 is a schematic structural diagram of a remote sensing image change detection device of a hardware operating environment according to an embodiment of the present invention.
As shown in fig. 1, the remote sensing image change detection apparatus may include: a processor 1001, such as a Central Processing Unit (CPU), a communication bus 1002, a user interface 1003, a network interface 1004, and a memory 1005. Wherein a communication bus 1002 is used to enable connective communication between these components. The user interface 1003 may include a Display screen (Display), an input unit such as a Keyboard (Keyboard), and the optional user interface 1003 may also include a standard wired interface, a wireless interface. The network interface 1004 may optionally include a standard wired interface, a Wireless interface (e.g., a Wireless-Fidelity (Wi-Fi) interface). The Memory 1005 may be a Random Access Memory (RAM) Memory, or may be a Non-Volatile Memory (NVM), such as a disk Memory. The memory 1005 may alternatively be a storage device separate from the processor 1001.
Those skilled in the art will appreciate that the configuration shown in fig. 1 does not constitute a limitation of the telemetric image change detecting apparatus, and may include more or less components than those shown, or some components in combination, or a different arrangement of components.
As shown in fig. 1, a memory 1005, which is a storage medium, may include an operating system, a network communication module, a user interface module, and a remote sensing image change detection program.
In the remote sensing image change detection apparatus shown in fig. 1, the network interface 1004 is mainly used for data communication with the network remote sensing image detector; the user interface 1003 is mainly used for data interaction with a user; the processor 1001 and the memory 1005 of the remote sensing image change detection device of the present invention may be provided in the remote sensing image change detection device, and the remote sensing image change detection device calls the remote sensing image change detection program stored in the memory 1005 through the processor 1001 and executes the remote sensing image change detection method provided by the embodiment of the present invention.
Based on the hardware structure, the embodiment of the remote sensing image change detection method is provided.
Referring to fig. 2, fig. 2 is a schematic flow chart of a method for detecting changes in remote sensing images according to a first embodiment of the present invention.
In a first embodiment, the method for detecting changes in remote sensing images comprises the following steps:
and step S10, acquiring the current remote sensing image of the target area, and extracting the spectral feature, the shape feature and the topographic feature of the current remote sensing image.
It should be noted that the execution subject of the present embodiment is a remote sensing image change detection device, and may also be other devices that can implement the same or similar functions, such as a remote sensing image detector.
It should be understood that, after determining the target area for change detection, the current Remote Sensing Image is acquired through a Global Positioning System (GPS) located in the target area, and the current Remote Sensing Image (RS) may be a film or a photo recording electromagnetic waves of various surface features in the target area, and is mainly divided into an aerial photo and a satellite photo.
Further, step S10 includes: acquiring terrain information, land coverage types and type change modes of all areas; determining a target area according to the terrain information, the land coverage type and the type change mode; and acquiring the current remote sensing image of the target area through an image capturing device in the GPS.
It can be understood that, in order to improve the accuracy and effectiveness of change detection, the condition of the change detection area needs to be complex, in this case, the key area of change detection is defined as a mountain area, and the most suitable target area is selected from the mountain area, and the specific condition of selection is through the terrain information, the land cover type and the type change mode of each area, wherein the terrain information includes mountains, plateaus and hills, the land cover type can be the natural attribute of land, including the concentration of CO2, land surface utilization, vegetation area and the like, and the type change mode can be the soil cover type change mode, because of the effect of human activities, the appearance of the whole earth is gradually changed, and the land cover mode of the area is changed sharply, for example, vegetation is dominant in the a area, water flow is complementary, but because local human beings are in the breeding industry, the method comprises the steps of destroying original vegetation, transforming the original vegetation into a river for cultivation, determining a target area for change detection according to topographic information, land coverage types and type change modes, and acquiring a current remote sensing image of the target area through an influence capture device in a GPS after the target area is determined.
Further, step S10 includes: obtaining the earth surface reflectivity, the shape index, the area index, the altitude and the gradient index of a target area according to the current remote sensing image; calculating the earth surface reflectivity through a first calculation formula to obtain spectral characteristics; performing data fusion on the shape index and the area index to obtain shape characteristics; and carrying out data analysis on the altitude and gradient index to obtain the terrain feature.
It should be understood that the surface reflectivity may be the ratio of the total solar radiant flux reflected in all directions by a surface object within the target area to the total radiant flux reaching the surface of the object, the shape index may be an index of the patch within the target area, the area index may be the size of the area within the target area, the altitude may be the highest and lowest altitudes within the target area, and the grade index is the slope of the slope within the target area.
It can be understood that after the earth surface reflectivity is obtained, the earth surface reflectivity is calculated through a first formula to obtain spectral features, including the variation vector intensity, the vector similarity and the normalized vegetation index, specifically:
where CVI is the strength of the variation vector, xi，yi(i-1, 2, …, n) represents the surface reflectance of the object in the i-th wavelength band in the reference image and the detection image, respectively.
Wherein VS is vector similarity, RxyCos θ is the patch angle, which is the surface reflectance coefficient ratio.
Wherein NDVI is the normalized vegetation index, bi(i-2, 3, 4, 5) indicates that the subject is in the ith band of the TM imageThe surface reflectivity of the earth.
In specific implementation, a remote sensing image detector obtains a current remote sensing image of a target area, and extracts spectral features, shape features and topographic features of the current remote sensing image.
And step S20, segmenting the spectral feature, the shape feature and the topographic feature according to a preset multi-scale segmentation algorithm to obtain a target feature sample.
It should be understood that the preset multi-scale segmentation algorithm may be an algorithm for segmenting features according to the dimensions of feature objects, and is a region merging algorithm based on the principle of minimum heterogeneity, where segmentation manners adopted by different dimensions are different, the preset multi-scale segmentation algorithm may be a multi-scale image segmentation algorithm based on morphology, and may also be other multi-scale segmentation algorithms.
In specific implementation, the remote sensing image detector segments the spectral feature, the shape feature and the topographic feature according to a preset multi-scale segmentation algorithm to obtain a target feature sample.
And step S30, determining a change characteristic sample and a non-change characteristic sample according to the target characteristic sample.
It should be understood that, since the preset decision tree algorithm is greatly influenced by samples as a machine learning algorithm, especially in a complex mountain area, representativeness and comprehensiveness of the samples are key for improving the accuracy of change detection, and the detection process requires that the samples are substantially uniformly distributed in a target area and are changed feature samples and unchanged feature samples under different land coverage types, type change modes and terrain conditions, and the uncharacterized change is false change feature samples in the target feature samples, such as terrain occlusion, cloud and cloud shadow, vegetation phenology and the like.
Further, step S30 includes: performing orthorectification on the target characteristic sample; extracting the resolution of the target feature; and registering the target characteristic sample after the orthorectification according to the resolution ratio to obtain a changed characteristic sample and a non-changed characteristic sample.
It can be understood that after the target feature sample is obtained, the remote sensing image in the target feature sample is subjected to tilt correction and projection difference correction at the same time, and the remote sensing image is resampled into an orthoimage, because the higher the resolution of the whole image is, the difficulty in image registration is increased, and at this time, the position of a pixel element in the remote sensing image is deviated, and if registration is not performed in time, the pixel element which is deviated may be detected as a change feature sample, so that after orthorectification, the target feature sample after orthorectification needs to be registered, and a change feature sample and a non-change feature sample are obtained.
In specific implementation, the remote sensing image detector determines a change characteristic sample and a non-change characteristic sample according to the target characteristic sample.
And step S40, detecting the change characteristic samples and the non-change characteristic samples through a preset decision tree algorithm to obtain a target remote sensing change image within preset time so as to realize change detection of the remote sensing image in the target area.
It should be understood that the predetermined decision tree algorithm may be an algorithm based on classification, regression, and detection, through which the change detection may be performed on the feature sample, and the predetermined decision tree algorithm may be a C5.0 decision tree algorithm, or other decision tree algorithms, which is not limited in this embodiment, and is described by taking the C5.0 decision tree algorithm as an example.
It can be understood that after the change characteristic sample and the non-change characteristic sample are obtained, the change characteristic sample and the non-change characteristic sample are detected through a preset decision tree algorithm to obtain a target remote sensing change image within a preset time, and a leading factor causing land cover change can be obtained through analyzing the target remote sensing change image.
In specific implementation, the remote sensing image detector detects the change characteristic sample and the non-change characteristic sample through a preset decision tree algorithm to obtain a target remote sensing change image within a preset time, so as to realize change detection of the remote sensing image in the target area.
The method comprises the steps of extracting spectral features, shape features and topographic features of a current remote sensing image by obtaining the current remote sensing image of a target area; segmenting the spectral feature, the shape feature and the topographic feature according to a preset multi-scale segmentation algorithm to obtain a target feature sample; determining a change characteristic sample and a non-change characteristic sample according to the target characteristic sample; the method comprises the steps of detecting a change characteristic sample and a non-change characteristic sample through a preset decision tree algorithm to obtain a target remote sensing change image within preset time, and obtaining the target remote sensing change image according to the preset decision tree algorithm by segmenting each characteristic of a current remote sensing image of a target area through a preset multi-scale segmentation algorithm and detecting the change characteristic sample and the non-change characteristic sample according to the preset decision tree algorithm to realize change detection of the remote sensing image in the target area, so that detection of the remote sensing image in a complex area can be realized, and the accuracy of remote sensing image detection is improved.
In an embodiment, as shown in fig. 3, a second embodiment of the method for detecting changes in remote sensing images according to the present invention is provided based on the first embodiment, where step S20 includes:
step S201, extracting the first band of the spectral feature, the second band of the shape feature, and the third band of the topographic feature.
It should be understood that the wavelength band may be a spectral wavelength band of each feature in the current remote sensing image, where the wavelength band of the spectral feature is defined as a first wavelength band, the wavelength band of the shape feature is defined as a second wavelength band, and the wavelength band of the topographic feature is defined as a third wavelength band.
In a specific implementation, the remote sensing image detector extracts a first band of spectral features, a second band of shape features, and a third band of topographical features.
Step S202, corresponding weights are respectively given to the first wave band, the second wave band and the third wave band through a target weight distribution strategy, and a first weight value, a second weight value and a third weight value are obtained.
It can be understood that the target weight distribution policy is a policy for distributing corresponding weights based on the characteristic bands, in this embodiment, the weighting criteria for distributing the weight values are based on the bands, specifically, the information amount carried by the bands, that is, the more information amount is carried, the greater the weight value distributed to the band by the target weight distribution policy is, the greater the weight value is, the first weight value is the weight value of the first band, the second weight value is the weight value of the second band, and the third weight value is the weight value of the third band.
In specific implementation, the remote sensing image detector assigns corresponding weights to the first, second and third bands respectively through a target weight distribution strategy to obtain a first weight value, a second weight value and a third weight value.
Step S203, obtaining a target homogeneity factor, and determining a target segmentation index according to the target homogeneity factor, the first weight value, the second weight value and the third weight value.
It should be understood that the target homogeneity factor may be a factor of each feature in the current remote sensing image, since the spectral feature is the most important in the current remote sensing image, the factor of the set spectral feature accounts for more than 50%, and the target segmentation index may be an index when a preset multi-scale segmentation algorithm is used for segmentation.
Further, step S203 includes: obtaining corresponding smoothness and compactness according to the shape characteristics; obtaining a corresponding patch internal pixel according to the spectral characteristics; determining a target homogeneity factor based on the smoothness, compactness, intra-patch pixels, and terrain features; and determining a target segmentation index according to the target homogeneity factor, the first weight value, the second weight value and the third weight value.
It is understood that the smoothness may be a smoothness of an edge of the shape feature, the compactness may be a close proximity of each shape in the shape feature, the intra-patch pixel may be a minimum unit of a patch in the spectral feature, and the target homogeneity factor of the current remote sensing image is determined by the smoothness, the compactness, the intra-patch pixel, and the topographic feature, and the target homogeneity factor includes heterogeneity and homogeneity.
In specific implementation, the remote sensing image detector acquires a target homogeneity factor, and determines a target segmentation index according to the target homogeneity factor, a first weight value, a second weight value and a third weight value.
And S204, segmenting the spectral feature, the shape feature and the topographic feature through a preset multi-scale segmentation algorithm based on the target segmentation index to obtain a target feature sample.
It can be understood that after the target segmentation index is obtained, the segmentation scale of the preset multi-scale segmentation algorithm is determined according to the target segmentation index, the spectral feature, the shape feature and the terrain feature are segmented through the preset multi-scale segmentation algorithm based on the segmentation scale, and after the segmentation is completed, the target feature sample is obtained.
In specific implementation, the remote sensing image detector segments the spectral feature, the shape feature and the topographic feature through a preset multi-scale segmentation algorithm based on the target segmentation index to obtain a target feature sample.
The embodiment extracts a first wave band of the spectral feature, a second wave band of the shape feature and a third wave band of the terrain feature; respectively endowing corresponding weights to the first band, the second band and the third band through a target weight distribution strategy to obtain a first weight value, a second weight value and a third weight value; obtaining a target homogeneity factor, and determining a target segmentation index according to the target homogeneity factor, a first weight value, a second weight value and a third weight value; segmenting the spectral features, the shape features and the topographic features through a preset multi-scale segmentation algorithm based on the target segmentation index to obtain a target feature sample; the target feature sample is obtained by assigning a weighted value corresponding to a wave band of each feature through a target weight distribution strategy, determining a target segmentation index according to the weighted value and a target homogeneity factor, and segmenting spectral features, shape features and topographic features through a preset multi-scale segmentation algorithm according to the target segmentation index, so that the accuracy of obtaining the target feature sample is effectively improved.
In an embodiment, as shown in fig. 4, a third embodiment of the method for detecting changes in remote sensing images according to the present invention is provided based on the first embodiment, where step S40 includes:
step S401, extracting a root node, a child node and a termination node in the preset decision tree algorithm.
It can be understood that, when the preset decision tree algorithm is determined to be the C5.0 decision tree algorithm, the hierarchy of the C5.0 decision tree algorithm at this time is multi-level, the root node is the start node, the child nodes are hierarchy nodes, and the end node is the final node, and after the end node is reached, the node at this time is not divided into other child nodes.
In specific implementation, the remote sensing image detector extracts a root node, a child node and a termination node in the preset decision tree algorithm.
And S402, dividing the change characteristic sample and the non-change characteristic sample according to the root node, the child node and the termination node to obtain the change characteristics of each subset.
It can be understood that after obtaining each node in the preset decision tree algorithm, the changed feature sample and the unchanged feature sample are divided by each node, that is, the changed feature sample and the unchanged feature sample are divided into two at the root node, the upper part of each node represents the unchanged feature sample, the lower part of each node represents the changed feature sample, after the division is completed, the whole decision tree relationship is formed, and the changed features of each subset can be obtained by the decision tree.
In specific implementation, the remote sensing image detector divides the change characteristic sample and the non-change characteristic sample according to the root node, the child node and the termination node to obtain change characteristics of each subset.
And S403, detecting the change characteristics of each subset through a preset decision tree algorithm to obtain a target remote sensing change image within preset time.
It should be understood that after the change features of each subset are obtained, the change features of each subset are detected through a preset decision tree algorithm, when the detection is completed, a target remote sensing change image within a preset time can be obtained, the target remote sensing change image can be a remote sensing image of the current remote sensing change image changing within the preset time, and the leading factors causing the land cover change can be obtained by analyzing the current remote sensing image and the target remote sensing change image.
In specific implementation, the remote sensing image detector detects the change characteristics of each subset through a preset decision tree algorithm to obtain a target remote sensing change image within a preset time.
In the embodiment, the root node, the child node and the termination node in the preset decision tree algorithm are extracted; dividing the change characteristic sample and the non-change characteristic sample according to the root node, the child node and the termination node to obtain change characteristics of each subset; detecting the change characteristics of each subset through a preset decision tree algorithm to obtain a target remote sensing change image within preset time; the variable characteristic samples and the non-variable characteristic samples are divided through the root nodes, the sub-nodes and the termination nodes in the preset decision tree algorithm, and the variable characteristics of all the subsets obtained through division are detected according to the preset decision tree algorithm to obtain the target remote sensing variable image within the preset time, so that the accuracy of the target remote sensing variable image can be effectively improved, and the leading factors causing the remote sensing image to change can be known more quickly and efficiently.
In addition, an embodiment of the present invention further provides a storage medium, where a remote sensing image change detection program is stored on the storage medium, and when executed by a processor, the remote sensing image change detection program implements the steps of the remote sensing image change detection method described above.
Since the storage medium adopts all technical solutions of all the embodiments, at least all the beneficial effects brought by the technical solutions of the embodiments are achieved, and no further description is given here.
In addition, referring to fig. 5, an embodiment of the present invention further provides a remote sensing image change detection apparatus, where the remote sensing image change detection apparatus includes:
the extraction module 10 is configured to obtain a current remote sensing image of a target area, and extract spectral features, shape features, and topographic features of the current remote sensing image.
And the segmentation module 20 is configured to segment the spectral feature, the shape feature and the topographic feature according to a preset multi-scale segmentation algorithm to obtain a target feature sample.
And the determining module 30 is used for determining a changed characteristic sample and a non-changed characteristic sample according to the target characteristic sample.
And the detection module 40 is used for detecting the change characteristic samples and the non-change characteristic samples through a preset decision tree algorithm to obtain a target remote sensing change image within a preset time, so as to realize change detection of the remote sensing image in the target area.
The method comprises the steps of extracting spectral features, shape features and topographic features of a current remote sensing image by obtaining the current remote sensing image of a target area; segmenting the spectral feature, the shape feature and the topographic feature according to a preset multi-scale segmentation algorithm to obtain a target feature sample; determining a change characteristic sample and a non-change characteristic sample according to the target characteristic sample; the method comprises the steps of detecting a change characteristic sample and a non-change characteristic sample through a preset decision tree algorithm to obtain a target remote sensing change image within preset time, and obtaining the target remote sensing change image according to the preset decision tree algorithm by segmenting each characteristic of a current remote sensing image of a target area through a preset multi-scale segmentation algorithm and detecting the change characteristic sample and the non-change characteristic sample according to the preset decision tree algorithm to realize change detection of the remote sensing image in the target area, so that detection of the remote sensing image in a complex area can be realized, and the accuracy of remote sensing image detection is improved.
It should be noted that the above-described work flows are only exemplary, and do not limit the scope of the present invention, and in practical applications, a person skilled in the art may select some or all of them to achieve the purpose of the solution of the embodiment according to actual needs, and the present invention is not limited herein.
In addition, the technical details that are not described in detail in this embodiment may be referred to a method for detecting a change in a remote sensing image provided in any embodiment of the present invention, and are not described herein again.
In an embodiment, the extraction module 10 is further configured to obtain topographic information, a land cover type, and a type change manner of each area; determining a target area according to the terrain information, the land coverage type and the type change mode; and acquiring the current remote sensing image of the target area through an image capturing device in the GPS.
In an embodiment, the extraction module 10 is further configured to obtain a surface reflectivity, a shape index, an area index, an altitude, and a gradient index of the target area according to the current remote sensing image; calculating the earth surface reflectivity through a first calculation formula to obtain spectral characteristics; performing data fusion on the shape index and the area index to obtain shape characteristics; and carrying out data analysis on the altitude and gradient index to obtain the terrain feature.
In one embodiment, the segmentation module 20 is further configured to extract a first band of spectral features, a second band of shape features, and a third band of topographic features; respectively endowing corresponding weights to the first band, the second band and the third band through a target weight distribution strategy to obtain a first weight value, a second weight value and a third weight value; obtaining a target homogeneity factor, and determining a target segmentation index according to the target homogeneity factor, a first weight value, a second weight value and a third weight value; and segmenting the spectral feature, the shape feature and the topographic feature by a preset multi-scale segmentation algorithm based on the target segmentation index to obtain a target feature sample.
In an embodiment, the segmentation module 20 is further configured to obtain corresponding smoothness and compactness according to the shape characteristics; obtaining a corresponding patch internal pixel according to the spectral characteristics; determining a target homogeneity factor based on the smoothness, compactness, intra-patch pixels, and terrain features; and determining a target segmentation index according to the target homogeneity factor, the first weight value, the second weight value and the third weight value.
In an embodiment, the determining module 30 is further configured to perform an orthorectification on the target feature sample; extracting the resolution of the target feature; and registering the target characteristic sample after the orthorectification according to the resolution ratio to obtain a changed characteristic sample and a non-changed characteristic sample.
In an embodiment, the detection module 40 is further configured to extract a root node, a child node, and a termination node in the preset decision tree algorithm; dividing the change characteristic sample and the non-change characteristic sample according to the root node, the child node and the termination node to obtain change characteristics of each subset; and detecting the change characteristics of each subset through a preset decision tree algorithm to obtain a target remote sensing change image within preset time.
Other embodiments or methods of implementing the apparatus for detecting changes in remote sensing images according to the present invention can refer to the above embodiments, and are not redundant herein.
Further, it is to be noted that, in this document, the terms "comprises," "comprising," or any other variation thereof, are intended to cover a non-exclusive inclusion, such that a process, method, article, or system that comprises a list of elements does not include only those elements but may include other elements not expressly listed or inherent to such process, method, article, or system. Without further limitation, an element defined by the phrase "comprising an … …" does not exclude the presence of other like elements in a process, method, article, or system that comprises the element.
The above-mentioned serial numbers of the embodiments of the present invention are merely for description and do not represent the merits of the embodiments.
Through the above description of the embodiments, those skilled in the art will clearly understand that the method of the above embodiments can be implemented by software plus a necessary general hardware platform, and certainly can also be implemented by hardware, but in many cases, the former is a better implementation manner. Based on such understanding, the technical solution of the present invention or portions thereof that contribute to the prior art may be embodied in the form of a software product, where the computer software product is stored in a storage medium (e.g. Read Only Memory (ROM)/RAM, magnetic disk, optical disk), and includes several instructions for enabling a terminal device (e.g. a mobile phone, a computer, a remote sensing image detector, or a network device) to execute the method according to the embodiments of the present invention.
The above description is only a preferred embodiment of the present invention, and not intended to limit the scope of the present invention, and all modifications of equivalent structures and equivalent processes, which are made by using the contents of the present specification and the accompanying drawings, or directly or indirectly applied to other related technical fields, are included in the scope of the present invention.
Claims (10)
1. A remote sensing image change detection method is characterized by comprising the following steps:
acquiring a current remote sensing image of a target area, and extracting spectral features, shape features and topographic features of the current remote sensing image;
segmenting the spectral feature, the shape feature and the topographic feature according to a preset multi-scale segmentation algorithm to obtain a target feature sample;
determining a change characteristic sample and a non-change characteristic sample according to the target characteristic sample;
and detecting the change characteristic sample and the non-change characteristic sample through a preset decision tree algorithm to obtain a target remote sensing change image in preset time so as to realize change detection of the remote sensing image in the target area.
2. The method for detecting changes in remote-sensing images of claim 1, wherein said obtaining a current remote-sensing image of a target area comprises:
acquiring terrain information, land coverage types and type change modes of all areas;
determining a target area according to the terrain information, the land coverage type and the type change mode;
and acquiring the current remote sensing image of the target area through an image capturing device in the GPS.
3. The method for detecting changes in remote-sensing images of claim 1, wherein said extracting spectral features, shape features and topographical features of the current remote-sensing image comprises:
obtaining the earth surface reflectivity, the shape index, the area index, the altitude and the gradient index of a target area according to the current remote sensing image;
calculating the earth surface reflectivity through a first calculation formula to obtain spectral characteristics;
performing data fusion on the shape index and the area index to obtain shape characteristics;
and carrying out data analysis on the altitude and gradient index to obtain the terrain feature.
4. The method for detecting changes in remote-sensing images of claim 1, wherein said segmenting said spectral features, shape features and topographical features according to a predetermined multi-scale segmentation algorithm to obtain target feature samples comprises:
extracting a first wave band of the spectral features, a second wave band of the shape features and a third wave band of the terrain features;
respectively endowing corresponding weights to the first band, the second band and the third band through a target weight distribution strategy to obtain a first weight value, a second weight value and a third weight value;
obtaining a target homogeneity factor, and determining a target segmentation index according to the target homogeneity factor, a first weight value, a second weight value and a third weight value;
and segmenting the spectral feature, the shape feature and the topographic feature by a preset multi-scale segmentation algorithm based on the target segmentation index to obtain a target feature sample.
5. The method for detecting remote sensing image change according to claim 4, wherein the obtaining a target homogeneity factor and determining a target segmentation index according to the target homogeneity factor, a first weight value, a second weight value and a third weight value includes:
obtaining corresponding smoothness and compactness according to the shape characteristics;
obtaining a corresponding patch internal pixel according to the spectral characteristics;
determining a target homogeneity factor based on the smoothness, compactness, intra-patch pixels, and terrain features;
and determining a target segmentation index according to the target homogeneity factor, the first weight value, the second weight value and the third weight value.
6. The method for detecting changes in remote sensing images of claim 1, wherein said determining a changed feature sample and a non-changed feature sample from said target feature sample comprises:
performing orthorectification on the target characteristic sample;
extracting the resolution of the target feature;
and registering the target characteristic sample after the orthorectification according to the resolution ratio to obtain a changed characteristic sample and a non-changed characteristic sample.
7. The remote sensing image change detection method of any one of claims 1 to 6, wherein the detecting the changed characteristic sample and the unchanged characteristic sample through a preset decision tree algorithm to obtain the target remote sensing change image within a preset time comprises:
extracting a root node, a child node and a termination node in the preset decision tree algorithm;
dividing the change characteristic sample and the non-change characteristic sample according to the root node, the child node and the termination node to obtain change characteristics of each subset;
and detecting the change characteristics of each subset through a preset decision tree algorithm to obtain a target remote sensing change image within preset time.
8. A remote sensing image change detection device, characterized in that the remote sensing image change detection device comprises:
the extraction module is used for acquiring a current remote sensing image of a target area and extracting spectral features, shape features and topographic features of the current remote sensing image;
the segmentation module is used for segmenting the spectral feature, the shape feature and the topographic feature according to a preset multi-scale segmentation algorithm to obtain a target feature sample;
the determining module is used for determining a change characteristic sample and a non-change characteristic sample according to the target characteristic sample;
and the detection module is used for detecting the change characteristic samples and the non-change characteristic samples through a preset decision tree algorithm to obtain a target remote sensing change image in preset time so as to realize change detection of the remote sensing image in the target area.
9. A remote sensing image change detection apparatus characterized by comprising: a memory, a processor and a remote sensing image change detection program stored on the memory and operable on the processor, the remote sensing image change detection program being configured to implement the remote sensing image change detection method according to any one of claims 1 to 7.
10. A storage medium having stored thereon a remote sensing image change detection program which, when executed by a processor, implements the remote sensing image change detection method according to any one of claims 1 to 7.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202111030253.XA CN113869133A (en) | 2021-09-02 | 2021-09-02 | Method, device and equipment for detecting change of remote sensing image and storage medium |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202111030253.XA CN113869133A (en) | 2021-09-02 | 2021-09-02 | Method, device and equipment for detecting change of remote sensing image and storage medium |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN113869133A true CN113869133A (en) | 2021-12-31 |
Family
ID=78989496
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202111030253.XA Withdrawn CN113869133A (en) | 2021-09-02 | 2021-09-02 | Method, device and equipment for detecting change of remote sensing image and storage medium |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN113869133A (en) |
Cited By (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN114326754A (en) * | 2022-03-09 | 2022-04-12 | 中国科学院空天信息创新研究院 | Complex terrain path planning method and device, electronic equipment and storage medium |
| CN114882084A (en) * | 2022-05-07 | 2022-08-09 | 安徽农业大学 | Land use change pattern spot automatic identification method based on artificial intelligence |
-
2021
- 2021-09-02 CN CN202111030253.XA patent/CN113869133A/en not_active Withdrawn
Cited By (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN114326754A (en) * | 2022-03-09 | 2022-04-12 | 中国科学院空天信息创新研究院 | Complex terrain path planning method and device, electronic equipment and storage medium |
| CN114326754B (en) * | 2022-03-09 | 2022-06-14 | 中国科学院空天信息创新研究院 | Complex terrain path planning method and device, electronic equipment and storage medium |
| CN114882084A (en) * | 2022-05-07 | 2022-08-09 | 安徽农业大学 | Land use change pattern spot automatic identification method based on artificial intelligence |
| CN114882084B (en) * | 2022-05-07 | 2024-04-05 | 安徽农业大学 | Land utilization change pattern automatic identification method based on artificial intelligence |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| US20240249518A1 (en) | Systems and methods for analyzing remote sensing imagery | |
| Gonçalves et al. | SegOptim—A new R package for optimizing object-based image analyses of high-spatial resolution remotely-sensed data | |
| Saha et al. | An object-oriented approach to automated landform mapping: A case study of drumlins | |
| US9251420B2 (en) | System for mapping and identification of plants using digital image processing and route generation | |
| Teodoro et al. | Comparison of performance of object-based image analysis techniques available in open source software (Spring and Orfeo Toolbox/Monteverdi) considering very high spatial resolution data | |
| KR100678395B1 (en) | System and method for real time position correction of geometric information data using satellite and aerospace image | |
| Wang et al. | Segmentation of high spatial resolution remote sensing imagery based on hard-boundary constraint and two-stage merging | |
| CN102959946A (en) | Augmenting image data based on related 3d point cloud data | |
| Crommelinck et al. | SLIC superpixels for object delineation from UAV data | |
| CN113869133A (en) | Method, device and equipment for detecting change of remote sensing image and storage medium | |
| Kavzoglu et al. | Classification of semiurban landscapes from very high-resolution satellite images using a regionalized multiscale segmentation approach | |
| US11763488B2 (en) | Location determination in a GPS-denied environment with user annotation | |
| Sahu et al. | Conceptual framework of combined pixel and object-based method for delineation of debris-covered glaciers | |
| WO2018026094A1 (en) | Method and system for automatically generating ortho-photo texture by using dem data | |
| CN113516059B (en) | Solid waste identification method and device, electronic device and storage medium | |
| Fawzy et al. | Automatic Indices Based Classification Method for Map Updating Using VHR Satellite Images | |
| WO2023116359A1 (en) | Method, apparatus and system for classifying green, blue and gray infrastructures, and medium | |
| Teodoro et al. | Exploration of the OBIA methods available in SPRING non-commercial software to UAV data processing | |
| CN115019044A (en) | Individual plant segmentation method and device, terminal device and readable storage medium | |
| Belcore et al. | Towards a FOSS automatic classification of defects for bridges structural health monitoring | |
| CN110490069A (en) | A kind of Remote Sensing Target recognition methods based on down-sampled local Differential Binary | |
| Karimi et al. | Developing an automated procedure for extraction of road data from high-resolution satellite images for geospatial information systems | |
| Deng et al. | A Large-Scale Multipurpose Benchmark Dataset and Real-Time Interpretation Platform Based on Chinese Rural Buildings | |
| Yildiz et al. | An assessment of the effectiveness of segmentation methods on classification performance | |
| Brüstle et al. | Object extraction in the context of an image registration workflow |
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 | ||
| WW01 | Invention patent application withdrawn after publication | ||
| WW01 | Invention patent application withdrawn after publication |
Application publication date: 20211231 |