CN113850769B - Hyperspectral change detection method based on Simese space spectrum joint convolution network - Google Patents

Hyperspectral change detection method based on Simese space spectrum joint convolution network Download PDF

Info

Publication number
CN113850769B
CN113850769B CN202111092212.3A CN202111092212A CN113850769B CN 113850769 B CN113850769 B CN 113850769B CN 202111092212 A CN202111092212 A CN 202111092212A CN 113850769 B CN113850769 B CN 113850769B
Authority
CN
China
Prior art keywords
hyperspectral
pixel
change
pixels
tensor
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
Application number
CN202111092212.3A
Other languages
Chinese (zh)
Other versions
CN113850769A (en
Inventor
詹天明
宋博
徐超
吴泽彬
Current Assignee (The listed assignees may be inaccurate. Google has not performed a legal analysis and makes no representation or warranty as to the accuracy of the list.)
NANJING AUDIT UNIVERSITY
Original Assignee
NANJING AUDIT UNIVERSITY
Priority date (The priority date 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 date listed.)
Filing date
Publication date
Application filed by NANJING AUDIT UNIVERSITY filed Critical NANJING AUDIT UNIVERSITY
Priority to CN202111092212.3A priority Critical patent/CN113850769B/en
Publication of CN113850769A publication Critical patent/CN113850769A/en
Application granted granted Critical
Publication of CN113850769B publication Critical patent/CN113850769B/en
Active legal-status Critical Current
Anticipated expiration legal-status Critical

Links

Images

Classifications

    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
    • G06T7/00—Image analysis
    • G06T7/0002—Inspection of images, e.g. flaw detection
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
    • G06N3/00—Computing arrangements based on biological models
    • G06N3/02—Neural networks
    • G06N3/04—Architecture, e.g. interconnection topology
    • G06N3/045—Combinations of networks
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
    • G06N3/00—Computing arrangements based on biological models
    • G06N3/02—Neural networks
    • G06N3/08—Learning methods
    • 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
    • G06T2207/10052—Images from lightfield camera
    • 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
    • G06T2207/20—Special algorithmic details
    • G06T2207/20081—Training; Learning
    • Y—GENERAL TAGGING OF NEW TECHNOLOGICAL DEVELOPMENTS; GENERAL TAGGING OF CROSS-SECTIONAL TECHNOLOGIES SPANNING OVER SEVERAL SECTIONS OF THE IPC; TECHNICAL SUBJECTS COVERED BY FORMER USPC CROSS-REFERENCE ART COLLECTIONS [XRACs] AND DIGESTS
    • Y02—TECHNOLOGIES OR APPLICATIONS FOR MITIGATION OR ADAPTATION AGAINST CLIMATE CHANGE
    • Y02A—TECHNOLOGIES FOR ADAPTATION TO CLIMATE CHANGE
    • Y02A40/00—Adaptation technologies in agriculture, forestry, livestock or agroalimentary production
    • Y02A40/10—Adaptation technologies in agriculture, forestry, livestock or agroalimentary production in agriculture

Landscapes

  • Engineering & Computer Science (AREA)
  • Physics & Mathematics (AREA)
  • Theoretical Computer Science (AREA)
  • General Physics & Mathematics (AREA)
  • General Health & Medical Sciences (AREA)
  • General Engineering & Computer Science (AREA)
  • Biophysics (AREA)
  • Computational Linguistics (AREA)
  • Data Mining & Analysis (AREA)
  • Evolutionary Computation (AREA)
  • Artificial Intelligence (AREA)
  • Molecular Biology (AREA)
  • Computing Systems (AREA)
  • Biomedical Technology (AREA)
  • Life Sciences & Earth Sciences (AREA)
  • Mathematical Physics (AREA)
  • Software Systems (AREA)
  • Health & Medical Sciences (AREA)
  • Quality & Reliability (AREA)
  • Computer Vision & Pattern Recognition (AREA)
  • Image Analysis (AREA)

Abstract

The invention discloses a hyperspectral change detection method based on a Simese space spectrum combined convolutional network, which comprises the following steps of: collecting two hyperspectral images at different time points in the same area, and removing wave bands with low signal-to-noise ratio; sequentially extracting spectrums of a pixel to be detected and adjacent pixels thereof from hyperspectral images of the pixel at front and rear two time points to form two tensors and pairing the two tensors; selecting 10% of pixels as training pixels, and manually marking the change condition of tensor pairs; inputting a tensor pair for training into a Siamese network consisting of one-dimensional convolution and two-dimensional convolution, and obtaining a corresponding feature vector; the hyperspectral image change detection method based on the hyperspectral image retains the complete spectrum and spatial characteristics of hyperspectrum, is high in identification speed, fuses the spectrum characteristics and the spatial characteristics, reduces the influence caused by noise, can effectively identify the change area which is interested by people in two hyperspectral images at different time phases, and improves the change detection efficiency and precision.

Description

Hyperspectral change detection method based on Simese space spectrum joint convolution network
Technical Field
The invention relates to the technical field of image processing, in particular to a hyperspectral change detection method based on a Simese space spectrum joint convolution network.
Background
With the development of remote sensing technology, it becomes possible to obtain hyperspectral images of different time phases in the same area; the method has important application value in the fields of disaster assessment, terrain change analysis, city change detection analysis and the like by utilizing the multi-temporal remote sensing image data to carry out change detection; the hyperspectral images containing hundreds of wave bands have rich spectral information and spatial information, so that the ground object observation has a stronger data source.
Currently, many researchers have studied the task of detecting multispectral changes with a low number of bands, and proposed some excellent change detection algorithms. However, in the problem of hyperspectral change detection, a change detection algorithm adapted to a low-dimensional space has an insignificant effect in a hyperspectral high-dimensional space; in addition, because the relevance of adjacent wave bands in the hyperspectral image is strong, a large amount of unnecessary redundant information also provides challenges for feature extraction; noise in the hyperspectral image is inevitable, wherein the noise comes from internal noise brought by the hyperspectral imager and noise from external factors such as atmospheric scattering and the like; if the algorithm only mines the spectral characteristics of the pixels, the effect of change detection will be diminished; therefore, a hyperspectral change detection method based on the Siamese space spectrum combined convolution network needs to be designed.
Disclosure of Invention
The invention aims to overcome the defects of the prior art, provides a hyperspectral change detection method based on a Simase space spectrum combined convolution network for better and effectively solving related problems, effectively reduces the parameter quantity of network learning, improves the speed of change detection and also improves the accuracy of change detection.
In order to achieve the purpose, the technical scheme adopted by the invention is as follows:
a hyperspectral change detection method based on a Simese spatial spectrum joint convolution network comprises the following steps,
collecting hyperspectral images of two different time points in the same area, and removing wave bands with low signal-to-noise ratio;
sequentially extracting the spectrums of the pixel and the adjacent pixels thereof from the hyperspectral images of the pixel to be detected at front and back time points to form two tensors and matching;
selecting 10% of pixels as training pixels, and artificially marking the change condition of tensor pairs;
step (D), inputting tensor pairs for training into a Simese network consisting of one-dimensional convolution and two-dimensional convolution, and obtaining corresponding eigenvectors,
a step (D1) of performing spectral feature extraction on 2 hyperspectral tensors of 3 × c in the tensor pair by 5 layers of 3D convolution with a size of 1 × 3, to form 2 feature tensors of 3 × 80;
step (D2) of convolving 2 feature tensors of 3 × 80 by 3D of 3 layers of size 3 × 1Performing spatial feature extraction to form 2 feature vectors
Figure GDA0004052307360000021
And &>
Figure GDA0004052307360000022
Wherein d represents the dimension of the feature vector and d =80;
step (E), calculating Euclidean distance of the two eigenvectors as the similarity of the two tensors corresponding to the pixel point;
step (F), optimizing the Siamese network by comparing loss functions;
step (G), calculating the variation degree of the tensor of the pixel to the input optimized Siamese network;
and (H) binarizing the similarity by a threshold method to generate a final change detection result, which comprises the following steps,
step (H1), determining a change threshold T by utilizing the manual marking and the change degree metric of the training pixel through a traversal method, which comprises the following specific steps,
step (H11) of obtaining minimum and maximum degree of change metric t in training pixels min And t max ；
A step (H12) of setting a candidate change determination threshold T j ＝t min +0.0001j, wherein
Figure GDA0004052307360000031
And T is j ∈[t min ,t max ]Wherein T is j Is based on a measure for the change of the training pixel>
Figure GDA0004052307360000032
Predict the change if
Figure GDA0004052307360000033
Then a prediction is 0, <' >>
Figure GDA0004052307360000034
The prediction is 1;
step (H13), the prediction result and the manually marked Y i Comparing, calculating the number of pixels with correct prediction as
Figure GDA0004052307360000035
The variation threshold T is as shown in equation (1),
Figure GDA0004052307360000036
a step (H2) of determining the variation of all the pixels based on the variation threshold T and generating a variation detection result map CM, which comprises the steps of,
step (H21) of measuring a degree of change based on the pixel
Figure GDA0004052307360000037
And a change threshold T generates a change detection result>
Figure GDA0004052307360000038
As shown in the formula (2), the first,
Figure GDA0004052307360000039
step (H22) of converting CM i Deformation-resulting change detection map
Figure GDA00040523073600000310
In the hyperspectral change detection method based on the Siamese spatial spectrum combined convolution network, step (B), the spectra of the pixel and the adjacent pixels of the pixel are respectively extracted from the hyperspectral images of the pixel to be detected at the front and back time points in turn to form two tensors and the two tensors are paired, wherein the steps are as follows,
step (B1), let
Figure GDA00040523073600000311
Representing the hyperspectral image of the t-th time point, wherein h and w are respectivelyCorresponding to the height and width of a hyperspectral space, c represents the number of wave bands of a hyperspectral image, and t belongs to {1,2};
step (B2) of reacting X (t) The spectra of all the pixels and the spectra of the corresponding neighborhood pixels in the image are extracted to form a hyperspectral tensor
Figure GDA00040523073600000312
And &>
Figure GDA00040523073600000313
Where b represents the spatial dimension of the hyperspectral tensor, b =3, i ∈ {1,2, \8230;, hw };
step (B3), the hyperspectral tensors of the same pixel are paired to form a tensor pair set
Figure GDA0004052307360000041
In the hyperspectral change detection method based on the siemese space spectrum joint convolution network, in the step (C), 10% of pixels are selected as training pixels, the change condition of a tensor pair is marked artificially, wherein 10% of pixels are selected from hw pixels, and the tensor pair corresponding to the training pixels is marked artificially according to the actual change condition of the pixels to obtain Y i And Y is i =0 denotes no change in pixel, Y i =1 represents a pixel variation.
The hyperspectral change detection method based on the siemese space spectrum joint convolution network comprises the step (E) of calculating the Euclidean distance between two eigenvectors as the similarity of the pixel point corresponding to the two tensors, wherein the specific calculation content is that 2 eigenvectors are calculated
Figure GDA0004052307360000042
And &>
Figure GDA0004052307360000043
In a Euclidean distance>
Figure GDA0004052307360000044
And the formula of the calculation is as shown in formula (3),
Figure GDA0004052307360000045
the method comprises the following steps of (A) optimizing a Simese network through a comparison Loss function, wherein the specific steps are that a variation degree metric value corresponding to a training pixel and an artificially marked actual variation mark value are input into the comparison Loss function to calculate a Loss function value, parameters in the Simese network are reversely updated and optimized according to the Loss function value, and the comparison Loss function Loss is as shown in a formula (4),
Figure GDA0004052307360000046
where m represents the feature vector distance threshold, and m =1.5.
The hyperspectral change detection method based on the Simese spatial spectrum joint convolution network comprises the step (G) of calculating the change degree of the tensor of the pixel to the input optimized Simese network, wherein the change degree is calculated
Figure GDA0004052307360000051
As a measure of the degree of variation of the pixel.
The invention has the beneficial effects that: according to the hyperspectral change detection method based on the Simese spatial spectrum combined convolutional network, a high-dimensional tensor is processed by utilizing a deep learning theory, and a change detection problem is converted into a problem of measuring the similarity of two tensors by utilizing the Simese network, compared with a difference method, the hyperspectral complete spectrum and spatial features are reserved, the spectral features of the tensors are extracted through a one-dimensional convolutional network in the Simese network, the dimension is reduced, the parameter quantity of network learning is effectively reduced, and the change detection speed is improved; the two-dimensional convolution network extracts spatial features from the tensor after dimensionality reduction, the two features are fused to reduce the influence caused by noise, the accuracy of change detection is improved, and the method has the advantages of being scientific and reasonable, high in applicability, good in effect and the like.
Drawings
FIG. 1 is a flow chart of a hyperspectral change detection method based on a Simese spatial spectrum joint convolution network according to the invention;
FIG. 2 is a schematic view of a first time-phase hyperspectral image of the invention;
FIG. 3 is a high spectral schematic of a second phase of the present invention;
FIG. 4 is a schematic diagram of hyperspectral change detection results of the invention;
FIG. 5 is a schematic diagram of ground truth of an actual change area marked by an artificial marker according to the present invention.
Detailed Description
The invention will be further described with reference to the accompanying drawings.
As shown in FIG. 1, the hyperspectral change detection method based on the Simese spatial spectrum joint convolution network of the invention comprises the following steps,
collecting hyperspectral images of two different time points in the same area, and removing wave bands with low signal-to-noise ratio;
step (B), respectively extracting the spectra of the pixel and the adjacent pixels thereof from the hyperspectral images of the pixel to be detected at front and back time points in sequence to form two tensors and matching the two tensors, wherein the specific steps are as follows,
step (B1), let
Figure GDA0004052307360000061
Representing a hyperspectral image of a t-th time point, wherein h and w respectively correspond to the height and the width of a hyperspectral space, c represents the number of wave bands of the hyperspectral image, and t belongs to {1,2};
step (B2) of reacting X (t) The spectra of all the pixels and the spectra of the corresponding neighborhood pixels in the image are extracted to form a hyperspectral tensor
Figure GDA0004052307360000062
And &>
Figure GDA0004052307360000063
Where b represents the spatial dimension of the hyperspectral tensor, b =3, i ∈ {1,2, \8230;, hw };
step (B3), the hyperspectral tensors of the same pixel are paired to form a tensor pair set
Figure GDA0004052307360000064
And (C) selecting 10% of pixels as training pixels, and artificially marking the change condition of tensor pairs, wherein 10% of pixels are selected from hw pixels, and artificially marking the tensor pairs corresponding to the training pixels according to the actual change condition of the pixels to obtain Y i And Y is i =0 denotes no change in pixel, Y i =1 represents a pixel variation.
Step (D), inputting tensor pairs for training into a Simese network consisting of one-dimensional convolution and two-dimensional convolution, and obtaining corresponding eigenvectors,
step (D1), performing spectral feature extraction on 2 hyperspectral tensors of 3 × c in the tensor pair by 5 layers of 3D convolution with the size of 1 × 3 to form 2 feature tensors of 3 × 80;
and (D2) performing spatial feature extraction on the 2 feature tensors of 3 × 80 by 3D convolution with 3 layers of 3 × 1 in size to form 2 feature vectors
Figure GDA0004052307360000065
And &>
Figure GDA0004052307360000066
Where d represents the dimension of the feature vector and d =80.
Step (E), calculating Euclidean distance of two eigenvectors as the similarity of two tensors corresponding to the pixel point, wherein the specific content of calculation is to calculate 2 eigenvectors
Figure GDA0004052307360000067
And &>
Figure GDA0004052307360000068
Is greater than or equal to>
Figure GDA0004052307360000071
And the formula of the calculation is as shown in formula (3),
Figure GDA0004052307360000072
wherein the distance serves as a measure of the degree of change of the pixel at two points in time.
Step (F), optimizing the Siamese network by a contrast Loss function, wherein the specific steps are that the variation degree metric value corresponding to the training pixel and the actual variation marking value marked by manual work are input into the contrast Loss function to calculate the Loss function value, and then parameters in the Siamese network are updated and optimized reversely according to the Loss function value, and the contrast Loss function Loss is shown as a formula (4),
Figure GDA0004052307360000073
where m represents the feature vector distance threshold, and m =1.5.
Step (G), calculating the variation degree of the tensor of the pixel to the input optimized Simese network, wherein the variation degree is calculated
Figure GDA0004052307360000074
As a measure of the degree of variation of the pixel.
And (H) binarizing the similarity by a threshold method to generate a final change detection result, which comprises the following steps,
step (H1), determining a change threshold T by utilizing the manual marking and the change degree metric of the training pixel through a traversal method, which comprises the following specific steps,
step (H11) of obtaining minimum and maximum degree of change metric t in training pixels min And t max ；
A step (H12) of setting a candidate change determination threshold T j ＝t min +0.0001j, itIn (1)
Figure GDA0004052307360000075
And T j ∈[t min ,t max ]Wherein T is j Is based on a measure for the change of the training pixel>
Figure GDA0004052307360000076
Predict the change if
Figure GDA0004052307360000077
Is predicted to be 0 and/or be greater than or equal to>
Figure GDA0004052307360000078
The prediction is 1;
step (H13) of comparing the predicted result with the artificially labeled Y i Comparing, calculating the number of pixels with correct prediction as
Figure GDA0004052307360000081
The variation threshold T is as shown in equation (1),
Figure GDA0004052307360000082
a step (H2) of determining the variation of all pixels based on the variation threshold T and generating a variation detection result map CM, which is specifically as follows,
a step (H21) of measuring a degree of change based on the pixel
Figure GDA0004052307360000083
And the change threshold value T generates a change detection result>
Figure GDA0004052307360000084
As shown in the formula (2),
Figure GDA0004052307360000085
step (H22) of converting CM i Deformation-resulting change detection map
Figure GDA0004052307360000086
A specific embodiment of the hyperspectral change detection method based on the Simese space spectrum joint convolution network can show the effect of hyperspectral change detection, such as fig. 2-4, wherein fig. 2 and 3 are hyperspectral images of two different time points in the same area, fig. 4 is a change detection result of the method, and fig. 5 is a truth diagram of actual change ground change; as can be seen from the detection result and the actual ground change true value graph, the method can effectively identify the change area.
In summary, according to the hyperspectral change detection method based on the Simese spatial spectrum joint convolution network, a high-dimensional tensor is processed by utilizing a deep learning theory, and a change detection problem is converted into a problem of measuring the similarity of two tensors by utilizing the Simese network, so that compared with a difference method, the hyperspectral complete spectrum and spatial features are reserved, the spectral features of the tensors are extracted and reduced in dimension through the one-dimensional convolution network in the Simese network, the parameter quantity of network learning is effectively reduced, and the change detection speed is improved; the two-dimensional convolution network extracts spatial features from the tensor after dimensionality reduction, the two features are fused to reduce the influence caused by noise, the accuracy of change detection is improved, and the method is suitable for a change detection task of a hyperspectral image.
The foregoing shows and describes the general principles, principal features and advantages of the invention. It will be understood by those skilled in the art that the present invention is not limited to the embodiments described above, which are described in the specification and illustrated only to illustrate the principle of the present invention, but that various changes and modifications may be made therein without departing from the spirit and scope of the present invention, which fall within the scope of the invention as claimed. The scope of the invention is defined by the appended claims and equivalents thereof.

Claims (6)

1. A hyperspectral change detection method based on a Simese spatial spectrum joint convolution network is characterized by comprising the following steps: comprises the following steps of (a) carrying out,
collecting hyperspectral images of two different time points in the same area, and removing wave bands with low signal-to-noise ratio;
sequentially extracting the spectrums of the pixel and the adjacent pixels thereof from the hyperspectral images of the pixel to be detected at front and back time points to form two tensors and matching;
selecting 10% of pixels as training pixels, and artificially marking the change condition of tensor pairs;
step (D), inputting tensor pairs for training into a Simese network consisting of one-dimensional convolution and two-dimensional convolution, and obtaining corresponding eigenvectors,
step (D1), performing spectral feature extraction on 2 hyperspectral tensors of 3 × c in the tensor pair by 5 layers of 3D convolution with the size of 1 × 3 to form 2 feature tensors of 3 × 80;
and (D2) performing spatial feature extraction on the 2 feature tensors of 3 × 80 by 3D convolution with 3 layers of 3 × 1 in size to form 2 feature vectors
Figure FDA0004052307350000011
And &>
Figure FDA0004052307350000012
Wherein d represents the dimension of the feature vector and d =80;
step (E), calculating Euclidean distance of the two eigenvectors as the similarity of the two tensors corresponding to the pixel point;
step (F), optimizing the Siamese network by comparing loss functions;
step (G), calculating the variation degree of the tensor of the pixel to the input optimized Siamese network;
and (H) binarizing the similarity by a threshold method to generate a final change detection result, which comprises the following steps,
step (H1), determining a change threshold T by utilizing the manual marking and the change degree metric of the training pixel through a traversal method, which comprises the following specific steps,
step (H11) of obtaining minimum and maximum degree of change metric t in training pixels min And t max ；
A step (H12) of setting a candidate change determination threshold T j ＝t min +0.0001j, wherein
Figure FDA0004052307350000021
And T j ∈[t min ,t max ]Wherein T is j Is based on the value of a change of a training pixel>
Figure FDA0004052307350000022
Predict the change if
Figure FDA0004052307350000023
Then a prediction is 0, <' >>
Figure FDA0004052307350000024
The prediction is 1;
step (H13), the prediction result and the manually marked Y i Comparing, calculating the number of pixels with correct prediction as
Figure FDA0004052307350000025
The variation threshold T is as shown in equation (1),
Figure FDA0004052307350000026
a step (H2) of determining the variation of all the pixels based on the variation threshold T and generating a variation detection result map CM, which comprises the steps of,
a step (H21) of measuring a degree of change based on the pixel
Figure FDA0004052307350000027
And the change threshold value T generates a change detection result>
Figure FDA0004052307350000028
As shown in the formula (2),
Figure FDA0004052307350000029
/>
step (H22) of converting CM into i Deformation final change detection map
Figure FDA00040523073500000210
2. The method for detecting hyperspectral variation based on the Simese spatial spectrum joint convolutional network as claimed in claim 1, wherein: step (B), respectively extracting the spectra of the pixel and the adjacent pixels thereof from the hyperspectral images of the pixel to be detected at front and back time points in sequence to form two tensors and matching the two tensors, wherein the specific steps are as follows,
step (B1), let
Figure FDA00040523073500000211
Representing a hyperspectral image of a t-th time point, wherein h and w respectively correspond to the height and the width of a hyperspectral space, c represents the number of wave bands of the hyperspectral image, and t belongs to {1,2};
step (B2) of reacting X (t) The spectra of all the pixels and the spectra of the corresponding neighborhood pixels in the image are extracted to form a hyperspectral tensor
Figure FDA0004052307350000031
And &>
Figure FDA0004052307350000032
Where b represents the spatial dimension of the hyperspectral tensor, b =3, i ∈ {1,2, \8230;, hw };
step (B3), the hyperspectral tensors of the same pixel are paired to form a tensor pair set
Figure FDA0004052307350000033
3. The method for detecting the hyperspectral change based on the siense spatial spectrum joint convolutional network as claimed in claim 2, characterized in that: and (C) selecting 10% of pixels as training pixels, and artificially marking the change condition of tensor pairs, wherein 10% of pixels are selected from hw pixels, and artificially marking the tensor pairs corresponding to the training pixels according to the actual change condition of the pixels to obtain Y i And Y is i =0 denotes no change in pixel, Y i =1 represents a pixel change.
4. The method for detecting hyperspectral variation based on the Simese spatial spectrum joint convolutional network as claimed in claim 1, wherein: step (E), calculating Euclidean distance of two eigenvectors as the similarity of the pixel point corresponding to the two tensors, wherein the specific content of calculation is to calculate 2 eigenvectors
Figure FDA0004052307350000034
And &>
Figure FDA0004052307350000035
Euclidean distance of
Figure FDA0004052307350000036
And the formula of the calculation is as shown in formula (3),
Figure FDA0004052307350000037
5. the method for detecting hyperspectral variation based on the Simese spatial spectrum joint convolutional network as claimed in claim 4, wherein: step (F), optimizing the Siamese network by a contrast Loss function, wherein the specific steps are that the variation degree metric value corresponding to the training pixel and the actual variation marking value marked by manual work are input into the contrast Loss function to calculate the Loss function value, and then parameters in the Siamese network are updated and optimized reversely according to the Loss function value, and the contrast Loss function Loss is shown as a formula (4),
Figure FDA0004052307350000038
where m represents the feature vector distance threshold, and m =1.5.
6. The method for detecting hyperspectral variation based on the Simese spatial spectrum joint convolutional network as claimed in claim 5, wherein: step (G), calculating the variation degree of the tensor of the pixel to the input optimized Siamese network, wherein the variation degree is calculated through calculation
Figure FDA0004052307350000041
As a measure of the degree of variation of the pixel. />
CN202111092212.3A 2021-09-17 2021-09-17 Hyperspectral change detection method based on Simese space spectrum joint convolution network Active CN113850769B (en)

Priority Applications (1)

Application Number Priority Date Filing Date Title
CN202111092212.3A CN113850769B (en) 2021-09-17 2021-09-17 Hyperspectral change detection method based on Simese space spectrum joint convolution network

Applications Claiming Priority (1)

Application Number Priority Date Filing Date Title
CN202111092212.3A CN113850769B (en) 2021-09-17 2021-09-17 Hyperspectral change detection method based on Simese space spectrum joint convolution network

Publications (2)

Publication Number Publication Date
CN113850769A CN113850769A (en) 2021-12-28
CN113850769B true CN113850769B (en) 2023-04-07

Family

ID=78974540

Family Applications (1)

Application Number Title Priority Date Filing Date
CN202111092212.3A Active CN113850769B (en) 2021-09-17 2021-09-17 Hyperspectral change detection method based on Simese space spectrum joint convolution network

Country Status (1)

Country Link
CN (1) CN113850769B (en)

Families Citing this family (2)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN115240072B (en) * 2022-08-04 2024-03-12 南京审计大学 Hyperspectral multi-class change detection method based on multidirectional multi-scale spectrum-space residual convolution neural network
CN117765402B (en) * 2024-02-21 2024-05-17 山东科技大学 Hyperspectral image matching detection method based on attention mechanism

Citations (1)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN109785302A (en) * 2018-12-27 2019-05-21 中国科学院西安光学精密机械研究所 A kind of empty spectrum union feature learning network and multispectral change detecting method

Family Cites Families (3)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US11003933B2 (en) * 2017-08-15 2021-05-11 Noblis, Inc. Multispectral anomaly detection
CN111539316B (en) * 2020-04-22 2023-05-05 中南大学 High-resolution remote sensing image change detection method based on dual-attention twin network
CN112131421B (en) * 2020-09-23 2023-09-15 平安科技（深圳）有限公司 Medical image classification method, device, equipment and storage medium

Patent Citations (1)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN109785302A (en) * 2018-12-27 2019-05-21 中国科学院西安光学精密机械研究所 A kind of empty spectrum union feature learning network and multispectral change detecting method

Also Published As

Publication number Publication date
CN113850769A (en) 2021-12-28

Similar Documents

Publication Publication Date Title
CN110378196B (en) Road visual detection method combining laser point cloud data
CN103679675B (en) Remote sensing image fusion method oriented to water quality quantitative remote sensing application
CN113850769B (en) Hyperspectral change detection method based on Simese space spectrum joint convolution network
Li et al. DMNet: A network architecture using dilated convolution and multiscale mechanisms for spatiotemporal fusion of remote sensing images
CN111008664B (en) Hyperspectral sea ice detection method based on space-spectrum combined characteristics
CN111368691B (en) Unsupervised hyperspectral remote sensing image space spectrum feature extraction method
CN108537169B (en) High-resolution remote sensing image road extraction method based on center line and road width detection algorithm
CN107240130A (en) Remote Sensing Image Matching method, apparatus and system
CN109034213B (en) Hyperspectral image classification method and system based on correlation entropy principle
CN114022459A (en) Multi-temporal satellite image-based super-pixel change detection method and system
Gu et al. Hyperspectral intrinsic image decomposition with enhanced spatial information
Yuan et al. ROBUST PCANet for hyperspectral image change detection
CN111062267B (en) Time series remote sensing image dimension reduction method
CN116740418A (en) Target detection method based on graph reconstruction network
CN112329662B (en) Multi-view saliency estimation method based on unsupervised learning
Kim et al. Automatic pseudo-invariant feature extraction for the relative radiometric normalization of hyperion hyperspectral images
CN112381144B (en) Heterogeneous deep network method for non-European and Euclidean domain space spectrum feature learning
CN111047616B (en) Remote sensing image landslide target constraint active contour feature extraction method
CN117274627A (en) Multi-temporal snow remote sensing image matching method and system based on image conversion
CN107832793A (en) The sorting technique and system of a kind of high spectrum image
Zhang et al. Feature Bands Based Unsupervised Hyperspectral Underwater Target Detection Near the Coastline
CN115511928A (en) Matching method of multispectral image
CN112329654B (en) Hyperspectral image data classification method and system based on multi-manifold learning algorithm
CN116385477A (en) Tower image registration method based on image segmentation
Varma et al. HSIS-Net: Hyperspectral Image Segmentation Using Multi-view Active Learning Based FCSN.

Legal Events

Date Code Title Description
PB01 Publication
PB01 Publication
SE01 Entry into force of request for substantive examination
SE01 Entry into force of request for substantive examination
GR01 Patent grant
GR01 Patent grant