CN112927150B - Water reflection area spectrum recovery method of hyperspectral image and terminal device - Google Patents
Water reflection area spectrum recovery method of hyperspectral image and terminal device Download PDFInfo
- Publication number
- CN112927150B CN112927150B CN202110192482.5A CN202110192482A CN112927150B CN 112927150 B CN112927150 B CN 112927150B CN 202110192482 A CN202110192482 A CN 202110192482A CN 112927150 B CN112927150 B CN 112927150B
- Authority
- CN
- China
- Prior art keywords
- image
- water body
- reflectivity
- water
- reflection
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Active
Links
- XLYOFNOQVPJJNP-UHFFFAOYSA-N water Substances O XLYOFNOQVPJJNP-UHFFFAOYSA-N 0.000 title claims abstract description 359
- 238000001228 spectrum Methods 0.000 title claims abstract description 107
- 238000000034 method Methods 0.000 title claims abstract description 42
- 238000011084 recovery Methods 0.000 title claims description 25
- 238000002310 reflectometry Methods 0.000 claims abstract description 171
- 210000000746 body region Anatomy 0.000 claims abstract description 30
- 238000012545 processing Methods 0.000 claims abstract description 7
- 230000003595 spectral effect Effects 0.000 claims description 25
- 238000004590 computer program Methods 0.000 claims description 21
- 238000012937 correction Methods 0.000 claims description 15
- 238000003708 edge detection Methods 0.000 claims description 10
- 238000001914 filtration Methods 0.000 claims description 4
- 238000004364 calculation method Methods 0.000 claims description 2
- 238000010586 diagram Methods 0.000 description 8
- 230000006870 function Effects 0.000 description 7
- 230000008569 process Effects 0.000 description 6
- 230000008878 coupling Effects 0.000 description 3
- 238000010168 coupling process Methods 0.000 description 3
- 238000005859 coupling reaction Methods 0.000 description 3
- 238000004891 communication Methods 0.000 description 2
- 239000006185 dispersion Substances 0.000 description 2
- 238000004458 analytical method Methods 0.000 description 1
- 230000009286 beneficial effect Effects 0.000 description 1
- 238000004422 calculation algorithm Methods 0.000 description 1
- 238000007405 data analysis Methods 0.000 description 1
- 238000013461 design Methods 0.000 description 1
- 230000008030 elimination Effects 0.000 description 1
- 238000003379 elimination reaction Methods 0.000 description 1
- 230000007613 environmental effect Effects 0.000 description 1
- 238000009499 grossing Methods 0.000 description 1
- 238000003384 imaging method Methods 0.000 description 1
- 230000006872 improvement Effects 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 230000003287 optical effect Effects 0.000 description 1
- 230000005855 radiation Effects 0.000 description 1
- 238000006467 substitution reaction Methods 0.000 description 1
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T5/00—Image enhancement or restoration
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T7/00—Image analysis
- G06T7/10—Segmentation; Edge detection
- G06T7/13—Edge detection
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T7/00—Image analysis
- G06T7/10—Segmentation; Edge detection
- G06T7/136—Segmentation; Edge detection involving thresholding
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V20/00—Scenes; Scene-specific elements
- G06V20/10—Terrestrial scenes
- G06V20/13—Satellite images
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T2207/00—Indexing scheme for image analysis or image enhancement
- G06T2207/10—Image acquisition modality
- G06T2207/10032—Satellite or aerial image; Remote sensing
- G06T2207/10036—Multispectral image; Hyperspectral image
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T2207/00—Indexing scheme for image analysis or image enhancement
- G06T2207/20—Special algorithmic details
- G06T2207/20024—Filtering details
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V20/00—Scenes; Scene-specific elements
- G06V20/10—Terrestrial scenes
- G06V20/194—Terrestrial scenes using hyperspectral data, i.e. more or other wavelengths than RGB
-
- 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
- Y02A90/00—Technologies having an indirect contribution to adaptation to climate change
- Y02A90/30—Assessment of water resources
Abstract
The invention is suitable for the technical field of image processing, and provides a method for restoring a spectrum of a water reflection area of a hyperspectral image and terminal equipment, wherein the method comprises the following steps: carrying out region identification on the acquired hyperspectral image of the water body to obtain a water body region image and a water body reflection region image; counting a first reflectivity mean sequence and a first reflectivity standard deviation sequence of the corresponding spectrum of the water body region image, and counting a second reflectivity mean sequence and a second reflectivity standard deviation sequence of the corresponding spectrum of the water body reflection region image; and obtaining the spectrum reflectivity sequence after the water reflection area image is recovered according to the first reflectivity mean value sequence, the first reflectivity standard deviation sequence, the second reflectivity mean value sequence and the second reflectivity standard deviation sequence. The invention can obtain complete water body spectrum information, thereby improving the accuracy of identification and utilization by using the water body spectrum information.
Description
Technical Field
The invention belongs to the technical field of image processing, and particularly relates to a method for restoring a spectrum of a water reflection area of a hyperspectral image and terminal equipment.
Background
At present, the key of the difference between a hyperspectral image and a traditional RGB image is that the spectral resolution in an imaging waveband range reaches the nanometer level, so that ground objects which cannot be identified in conventional remote sensing can be effectively identified and quantitatively inverted in hyperspectral remote sensing.
However, with the improvement of the spatial resolution of the hyperspectral remote sensing, the reflection phenomenon of the water body in the hyperspectral image gradually increases, the reflection can be simply eliminated from the water body in the past, but the difference between the spectrum information of the reflection in the water body and the water body spectrum is large, and the simple elimination of the reflection from the water body can cause the water body spectrum information of the reflection part to be lost in the water body spectrum information, so that the accuracy of the identification and utilization of the water body spectrum information is influenced.
Disclosure of Invention
In view of this, the embodiment of the invention provides a method for restoring a water reflection region spectrum of a hyperspectral image and a terminal device, so as to solve the problem in the prior art that the accuracy is not high when water spectrum information obtained based on the hyperspectral image is identified and utilized.
The embodiment of the invention provides a method for restoring a spectrum of a water reflection area of a hyperspectral image, which comprises the following steps:
carrying out regional identification on the acquired hyperspectral image of the water body to obtain a water body regional image and a water body reflection regional image;
counting a first reflectivity mean sequence and a first reflectivity standard deviation sequence of the corresponding spectrum of the water body region image, and counting a second reflectivity mean sequence and a second reflectivity standard deviation sequence of the corresponding spectrum of the water body reflection region image;
and obtaining the spectrum reflectivity sequence of the restored water reflection area image according to the first reflectivity mean sequence, the first reflectivity standard deviation sequence, the second reflectivity mean sequence and the second reflectivity standard deviation sequence.
A second aspect of an embodiment of the present invention provides a device for recovering a spectrum of a water reflection area of a hyperspectral image, including:
the identification module is used for carrying out region identification on the acquired water body hyperspectral image to obtain a water body region image and a water body reflection region image;
the statistical module is used for counting a first reflectivity mean sequence and a first reflectivity standard deviation sequence of the corresponding spectrum of the water body region image, and counting a second reflectivity mean sequence and a second reflectivity standard deviation sequence of the corresponding spectrum of the water body reflection region image;
and the recovery module is used for obtaining the spectrum reflectivity sequence after the water reflection area image is recovered according to the first reflectivity mean sequence, the first reflectivity standard deviation sequence, the second reflectivity mean sequence and the second reflectivity standard deviation sequence.
A third aspect of the embodiments of the present invention provides a terminal device, which includes a memory, a processor, and a computer program stored in the memory and executable on the processor, where the processor implements the steps of the method for recovering the spectrum of the reflection region of the hyperspectral image in the water body according to any one of the above methods when executing the computer program.
A fourth aspect of the embodiments of the present invention provides a computer-readable storage medium, which stores a computer program, and when the computer program is executed by a processor, the computer program implements the steps of the method for restoring the spectrum of the reflection region of the water body of the hyperspectral image.
Compared with the prior art, the embodiment of the invention has the following beneficial effects: according to the embodiment of the invention, the acquired water body hyperspectral image is subjected to area identification to obtain the water body area image and the water body reflection area image, a first reflectivity mean sequence and a first reflectivity standard deviation sequence of a spectrum corresponding to the water body area image and a second reflectivity mean sequence and a second reflectivity standard deviation sequence of a spectrum corresponding to the water body reflection area image can be respectively counted, the spectrum reflectivity sequence after the water body reflection area image is recovered is obtained according to the first reflectivity mean sequence, the first reflectivity standard deviation mean sequence, the second reflectivity mean sequence and the second reflectivity standard deviation sequence, the spectrum of the water body reflection area image can be recovered by utilizing the spectrum information corresponding to the water body area image and the spectrum information corresponding to the water body reflection area image, complete water body spectrum information is obtained, and the accuracy of identification and utilization by utilizing the water body spectrum information is further improved.
Drawings
In order to more clearly illustrate the technical solutions in the embodiments of the present invention, the drawings needed to be used in the embodiments or the prior art descriptions will be briefly described below, and it is obvious that the drawings in the following description are only some embodiments of the present invention, and it is obvious for those skilled in the art to obtain other drawings based on these drawings without inventive exercise.
FIG. 1 is a schematic flow chart of an implementation of a method for restoring a spectrum of a water reflection region of a hyperspectral image according to an embodiment of the invention;
FIG. 2 is a schematic diagram of a hyperspectral image of a water body provided by an embodiment of the invention;
FIG. 3 is a schematic illustration of a water body region image provided by an embodiment of the invention;
FIG. 4 is a schematic diagram of a water reflection region image provided by an embodiment of the invention;
fig. 5 is a graph illustrating a first reflectivity mean sequence and a first reflectivity standard deviation sequence, and a second reflectivity mean sequence and a second reflectivity standard deviation sequence according to an embodiment of the present invention;
FIG. 6 is a schematic diagram of curves corresponding to sequences of spectral reflectivities before and after restoring an image of a water reflection region according to an embodiment of the present invention;
FIG. 7 is an exemplary diagram of a device for recovering spectra of a reflection region of a water body of a hyperspectral image according to an embodiment of the invention;
FIG. 8 is an exemplary diagram of a recovery module provided by embodiments of the invention;
fig. 9 is a schematic diagram of a terminal device according to an embodiment of the present invention.
Detailed Description
In the following description, for purposes of explanation and not limitation, specific details are set forth, such as particular system structures, techniques, etc. in order to provide a thorough understanding of the embodiments of the invention. It will be apparent, however, to one skilled in the art that the present invention may be practiced in other embodiments that depart from these specific details. In other instances, detailed descriptions of well-known systems, devices, circuits, and methods are omitted so as not to obscure the description of the present invention with unnecessary detail.
In order to explain the technical means of the present invention, the following description will be given by way of specific examples.
Fig. 1 is a schematic flow chart illustrating an implementation process of a method for recovering a spectrum of a water reflection area of a hyperspectral image according to an embodiment of the present invention, which is described in detail below.
As shown in fig. 2, when water quality analysis or environmental data analysis is performed according to a hyperspectral image, after a hyperspectral image of a water body in a planned water area is obtained, because trees, houses, mountains and the like are often found around lakes or rivers, the hyperspectral image of the water body also contains inverted images of the trees, the houses, the mountains and the like, and because the spectra of the inverted image area in the hyperspectral image of the water body are greatly affected by the trees, the houses, the mountains and the like, the spectrum information of the water body cannot be directly reflected, and the normal inversion of water quality parameters of the water body is affected, so that the spectra of the inverted image area in the hyperspectral image of the water body needs to be restored.
And S101, carrying out region identification on the acquired water body hyperspectral image to obtain a water body region image and a water body reflection region image.
Optionally, before performing region identification on the acquired hyperspectral image of the water body, the method may further include: and performing atmospheric correction on the acquired water body hyperspectral image to obtain an image after atmospheric correction.
Wherein, carry out regional discernment to the water hyperspectral image who acquires, obtain water regional image and water reflection regional image, can include: and carrying out area identification on the image after atmospheric correction to obtain a water body area image and a water body reflection area image.
The atmospheric correction can comprise lens correction, radiation correction, reflectivity correction and the like, and the image subjected to atmospheric correction is subjected to region identification, so that a water body region image and a water body reflection region image can be obtained more accurately.
Optionally, performing area identification on the acquired hyperspectral image of the water body to obtain an image of the water body area and an image of the water body reflection area, which may include: calculating the water body index of the water body hyperspectral image to obtain the water body index of the water body hyperspectral image; according to the characteristics of water reflection in the water hyperspectral image, calculating a reflection index of the water hyperspectral image to obtain a reflection index of the water hyperspectral image; and carrying out region identification on the water body hyperspectral image according to the water body index and the reflection index to obtain a water body region image and a water body reflection region image.
The acquired hyperspectral image of the water body may contain real objects such as trees, houses and mountains, reflection of sky, water and real objects in the water body and the like, and the complete spectral information of the water body can be accurately acquired only by carrying out region identification on the hyperspectral image of the water body. When the region identification is carried out, the Difference and the ratio of a green wave band and a near infrared wave band can be selected according to the characteristics of a Water body spectral curve, a Water body Index (NDWI) is calculated, the reflection Index can be calculated according to the characteristics of a real object reflection spectral curve in a Water body hyperspectral image, the region identification is carried out on the Water body hyperspectral image according to the Water body Index to obtain a Water body region image, and the region identification is carried out on the Water body hyperspectral image according to the reflection Index to obtain a Water body reflection region image.
For example, because the tree, house, mountain, and other objects and their reflection in the water body have similar spectral characteristics, when the object reflection in the water body is mainly a tree, the Difference and ratio between the red band and the near infrared band can be selected according to the characteristics of the tree spectral curve, and the Vegetation Index (NDVI) can be calculated. When the real object reflection in the water body is mainly a house, the building index can be calculated according to the characteristics of the house spectral curve. The method comprises the steps of carrying out region identification on the water body hyperspectral image according to reflection indexes corresponding to object reflection in the water body, and obtaining the water body reflection region image more accurately.
Optionally, the area identification is performed on the water body hyperspectral image according to the water body index and the reflection index, so that a water body area image and a water body reflection area image are obtained, and the method can include the following steps: performing region identification on the water body hyperspectral image according to the water body index and the reflection index to obtain an initial water body region image containing a water body and sky and an initial water body reflection region image containing a real object and a reflection; performing region identification on the initial water body region image based on single-band thresholds of the water body and the sky to obtain a water body region image; and carrying out region identification on the initial water body reflection region image based on the symmetry of the real object and the reflection and edge detection to obtain the water body reflection region image.
When the hyperspectral image of the water body is directly identified by the water body index, the obtained initial water body area image contains the water body and the sky, and the obtained initial water body reflection area image contains trees, houses, mountains and other real objects and reflection of the real objects in the water body, so that the initial water body area image and the initial water body reflection area image need to be further identified to obtain a water body area image only containing water bodies and a water body reflection area image only containing reflection.
For example, referring to fig. 3, according to the spectral difference between the water body and the sky, a single-band threshold of the water body and the sky may be selected to perform region identification on the initial water body region image, so as to obtain a water body region image. For example, an image corresponding to a single band B12 (430.9 nm) smaller than a threshold of 0.35 may be selected to distinguish the water body from the sky, and obtain a water body region image.
In an exemplary embodiment, because the real objects such as trees, houses, mountains, and the like and the reflection thereof in the water body have symmetry, and the difference between the edges of the real objects such as trees, houses, mountains, and the reflection thereof in the water body and the water body is large, the contour images of the real objects and the reflection thereof can be obtained based on edge detection, the contour images of the real objects and the reflection thereof are divided into two parts according to the symmetry, and the reflection region image of the water body is obtained according to the characteristic that the reflection is close to the water body.
Optionally, performing region identification on the initial water body reflection region image based on the symmetry of the real object and the reflection and edge detection to obtain a water body reflection region image, which may include: carrying out Gaussian filtering processing on the initial water reflection area image to obtain a filtered gray level image; obtaining a water body reflection threshold according to a reflection image and a gray level image in the initial water body reflection area image; performing edge detection on the initial water body reflection region image according to a water body reflection threshold value, and identifying an edge water body reflection region image in the initial water body reflection region image; and carrying out region identification on the edge water body reflection region image based on the symmetry of the real object and the reflection to obtain a water body reflection region image.
For example, referring to fig. 4, after the initial water reflection region image is obtained, smoothing may be performed through gaussian filtering to remove noise in the initial water reflection region image. The method comprises the steps of obtaining real objects such as trees, houses, mountain bodies and the like and water body reflection thresholds of reflection of the real objects in a water body based on a filtered gray image, carrying out edge detection on an initial water body reflection area image according to the water body reflection thresholds, identifying the real objects such as trees, houses, mountain bodies and the like in the initial water body reflection area image and the edges of the reflection of the real objects in the water body, namely the edge water body reflection area image, and obtaining the water body reflection area image based on the symmetry of the real objects and the reflection and the characteristic that the reflection of the real objects in the water body is close to the water body.
Step S102, a first reflectivity mean sequence and a first reflectivity standard deviation sequence of the corresponding spectrum of the water body region image are counted, and a second reflectivity mean sequence and a second reflectivity standard deviation sequence of the corresponding spectrum of the water body reflection region image are counted.
Referring to fig. 5, after the water body area image is obtained, a first reflectivity mean sequence and a first reflectivity standard deviation sequence of the corresponding spectrum can be obtained through statistics according to the water body area image, a curve M1 reflecting the reflectivity mean trend of each wave band of the water body area image can be obtained through the first reflectivity mean sequence, and a curve S1 reflecting the dispersion degree of the reflectivity of each wave band of the water body area image can be obtained through the first reflectivity standard deviation sequence. Similarly, after the water reflection region image is obtained, a second reflectivity mean sequence and a second reflectivity standard deviation sequence of the corresponding spectrum can be obtained through statistics according to the water reflection region image, a curve M2 reflecting the reflectivity mean trend of each wave band of the water reflection region image can be obtained through the second reflectivity mean sequence, and a curve S2 reflecting the dispersion degree of the reflectivity of each wave band of the water reflection region image can be obtained through the second reflectivity standard deviation sequence. It can be seen from the curves M1 and M2 that the spectral information corresponding to the water body area image and the water body reflection area image are very different, and the corresponding water quality parameters cannot be accurately inverted by directly using the spectral information of the water body reflection area image or simply excluding the spectral information of the water body reflection area image.
And S103, obtaining a spectral reflectance sequence after the water reflection area image is restored according to the first reflectance mean sequence, the first reflectance standard deviation sequence, the second reflectance mean sequence and the second reflectance standard deviation sequence.
Optionally, obtaining the spectrum reflectivity sequence of the restored water reflection region image according to the first reflectivity mean sequence, the first reflectivity standard deviation sequence, the second reflectivity mean sequence, and the second reflectivity standard deviation sequence may include:
according toThe spectrum reflectivity recovered by each wave band corresponding to the water reflection area image is obtained, the spectrum reflectivity recovered by all the wave bands corresponding to the water reflection area image is obtained according to the method for obtaining the spectrum reflectivity recovered by each wave band corresponding to the water reflection area image, and the spectrum reflectivity sequence recovered by the water reflection area image is obtained according to the spectrum reflectivity recovered by all the wave bands corresponding to the water reflection area image.
Wherein s is the spectral reflectivity of each recovered wave band corresponding to the water reflection region image, and s is 1 Spectral reflectance, s, for each band corresponding to the atmosphere corrected image 2 A second reflectivity mean, s, corresponding to each band in the second reflectivity mean sequence 3 A second standard deviation of reflectivity, s, corresponding to each band in the second sequence of standard deviations of reflectivity 4 A first standard deviation of reflectivity, s, corresponding to each band in the first sequence of standard deviations of reflectivity 5 And the first reflectivity mean value corresponds to each wave band in the first reflectivity mean value sequence.
A curve s1 corresponding to the sequence of spectral reflectances before the restoration of the image of the water reflection region and a curve s2 corresponding to the sequence of spectral reflectances after the restoration of the image of the water reflection region are shown in fig. 6, and it can be seen from the curve s2 in fig. 6 and the curve M1 in fig. 5 that the present embodiment is based on the embodimentObtaining the spectrum reflectivity after each wave band recovery corresponding to the water reflection region image, and further obtaining the water reflection region imageThe spectrum reflectivity sequence after recovery can relatively accurately recover the spectrum reflectivity of the water reflection area image to the spectrum reflectivity of the normal water body image, so that the spectrum information of the complete water body image can be obtained, the water quality parameter inversion is carried out by utilizing the spectrum information of the complete water body image, and the accuracy of the water quality parameter inversion result is favorably improved.
According to the water reflection area spectrum recovery method of the hyperspectral image, the acquired water hyperspectral image is subjected to area identification to obtain a water area image and a water reflection area image, a first reflectivity mean sequence and a first reflectivity standard deviation sequence of a spectrum corresponding to the water area image and a second reflectivity mean sequence and a second reflectivity standard deviation sequence of a spectrum corresponding to the water reflection area image can be respectively counted, the spectrum reflectivity sequence after the water reflection area image is recovered is obtained according to the first reflectivity mean sequence, the first reflectivity standard deviation mean sequence, the second reflectivity mean sequence and the second reflectivity standard deviation sequence, the spectrum of the water reflection area image can be recovered by utilizing the spectrum information corresponding to the water area image and the spectrum information corresponding to the water reflection area image, complete water body spectrum information is obtained, and the accuracy of identification and utilization by utilizing the water body spectrum information is improved.
It should be understood that, the sequence numbers of the steps in the foregoing embodiments do not imply an execution sequence, and the execution sequence of each process should be determined by its function and inherent logic, and should not constitute any limitation to the implementation process of the embodiments of the present invention.
Fig. 7 shows an exemplary diagram of a device for restoring spectra of a reflection area of a water body of a hyperspectral image according to an embodiment of the present invention, which corresponds to the method for restoring spectra of a reflection area of a water body of a hyperspectral image according to the embodiment described above. As shown in fig. 7, the apparatus may include: an identification module 71, a statistics module 72 and a recovery module 73.
The identification module 71 is configured to perform area identification on the acquired hyperspectral image of the water body to obtain a water body area image and a water body reflection area image;
the counting module 72 is configured to count a first reflectivity mean sequence and a first reflectivity standard deviation sequence of the spectrum corresponding to the water body region image, and count a second reflectivity mean sequence and a second reflectivity standard deviation sequence of the spectrum corresponding to the water body reflection region image;
and a restoring module 73, configured to obtain a spectrum reflectivity sequence after the water reflection region image is restored according to the first reflectivity mean sequence, the first reflectivity standard deviation sequence, the second reflectivity mean sequence, and the second reflectivity standard deviation sequence.
Optionally, the identification module 71 may be configured to perform water body index calculation on the water body hyperspectral image to obtain a water body index of the water body hyperspectral image; according to the characteristic of water reflection in the water body hyperspectral image, calculating a reflection index of the water body hyperspectral image to obtain a reflection index of the water body hyperspectral image; and carrying out region identification on the water body hyperspectral image according to the water body index and the reflection index to obtain a water body region image and a water body reflection region image.
Optionally, the identifying module 71 may be configured to perform region identification on the water body hyperspectral image according to the water body index and the reflection index, so as to obtain an initial water body region image containing a water body and a sky and an initial water body reflection region image containing a real object and a reflection; performing region identification on the initial water body region image based on single-band thresholds of a water body and a sky to obtain a water body region image; and carrying out region identification on the initial water body reflection region image based on the symmetry of the real object and the reflection and edge detection to obtain a water body reflection region image.
Optionally, the identifying module 71 may be configured to perform gaussian filtering on the initial water reflection region image to obtain a filtered grayscale image; obtaining a water body reflection threshold according to the reflection in the initial water body reflection area image and the gray level image; performing edge detection on the initial water body reflection region image according to the water body reflection threshold value, and identifying an edge water body reflection region image in the initial water body reflection region image; and carrying out region identification on the edge water body reflection region image based on the symmetry of the real object and the reflection to obtain a water body reflection region image.
Optionally, the identification module 71 may be further configured to perform atmospheric correction on the acquired water body hyperspectral image to obtain an atmospheric corrected image;
and carrying out area identification on the image after atmospheric correction to obtain a water body area image and a water body reflection area image.
Optionally, referring to fig. 8, the recovery module 73 may include:
a first calculating unit 731 for calculatingObtaining the spectrum reflectivity after each wave band recovery corresponding to the water reflection area image;
wherein s is the spectral reflectivity of the restored each wave band corresponding to the water reflection region image, and s is 1 Spectral reflectance, s, for each band corresponding to the atmospheric corrected image 2 A second reflectivity mean value s corresponding to each wave band in the second reflectivity mean value sequence 3 A second reflectivity standard deviation, s, corresponding to each band in the second reflectivity standard deviation sequence 4 A first reflectivity standard deviation s corresponding to each wave band in the first reflectivity standard deviation sequence 5 A first reflectivity mean value corresponding to each wave band in the first reflectivity mean value sequence;
a second calculating unit 732, configured to obtain the recovered spectral reflectances of all the wave bands corresponding to the water reflection region image according to a method for obtaining the recovered spectral reflectances of each wave band corresponding to the water reflection region image;
the recovery unit 733 is configured to obtain a sequence of spectral reflectivities of the restored water reflection region images according to the recovered spectral reflectivities of all the wave bands corresponding to the water reflection region images.
The water reflection area spectrum recovery device of the hyperspectral image obtains a water area image and a water reflection area image by performing area identification on the obtained water hyperspectral image, can respectively count a first reflectivity mean sequence and a first reflectivity standard deviation sequence of a spectrum corresponding to the water area image, and a second reflectivity mean sequence and a second reflectivity standard deviation sequence of a spectrum corresponding to the water reflection area image, obtains a spectrum reflectivity sequence after the water reflection area image is recovered according to the first reflectivity mean sequence, the first reflectivity standard deviation mean sequence, the second reflectivity mean sequence and the second reflectivity standard deviation sequence, and can recover the spectrum of the water reflection area image by using the spectrum information corresponding to the water area image and the spectrum information corresponding to the water reflection area image to obtain complete water body spectrum information, thereby improving the accuracy of identification and utilization by using the water body spectrum information.
Fig. 9 is a schematic diagram of a terminal device according to an embodiment of the present invention. As shown in fig. 9, the terminal apparatus 900 of this embodiment includes: a processor 901, a memory 902 and a computer program 903 stored in said memory 902 and operable on said processor 901, such as a water reflection area spectrum recovery program of a hyperspectral image. When the processor 901 executes the computer program 903, the steps in the embodiment of the method for restoring the spectrum of the reflection region of the water body of the hyperspectral image, such as the steps S101 to S103 shown in fig. 1, are implemented, and when the processor 901 executes the computer program 903, the functions of the modules in the embodiments of the apparatuses, such as the functions of the modules 71 to 73 shown in fig. 7, are implemented.
Illustratively, the computer program 903 may be divided into one or more program modules, which are stored in the memory 902 and executed by the processor 901 to implement the present invention. The one or more program modules may be a series of computer program instruction segments capable of performing certain functions for describing the execution process of the computer program 903 in the apparatus for restoring spectra in a reflection region of a body of water of the hyperspectral image or the terminal device 900. For example, the computer program 903 may be divided into an identification module 71, a statistics module 72, and a recovery module 73, and specific functions of the modules are shown in fig. 7, which are not described in detail herein.
The terminal device 900 may be a computing device such as a desktop computer, a notebook, a palm computer, and a cloud server. The terminal device may include, but is not limited to, a processor 901, a memory 902. Those skilled in the art will appreciate that fig. 9 is merely an example of a terminal device 900 and does not constitute a limitation of terminal device 900 and may include more or fewer components than shown, or some of the components may be combined, or different components, e.g., the terminal device may also include input-output devices, network access devices, buses, etc.
The Processor 901 may be a Central Processing Unit (CPU), other general purpose Processor, a Digital Signal Processor (DSP), an Application Specific Integrated Circuit (ASIC), an off-the-shelf Programmable Gate Array (FPGA) or other Programmable logic device, discrete Gate or transistor logic, discrete hardware components, etc. A general purpose processor may be a microprocessor or the processor may be any conventional processor or the like.
The storage 902 may be an internal storage unit of the terminal device 900, such as a hard disk or a memory of the terminal device 900. The memory 902 may also be an external storage device of the terminal device 900, such as a plug-in hard disk, a Smart Media Card (SMC), a Secure Digital (SD) Card, a Flash memory Card (Flash Card), or the like, provided on the terminal device 900. Further, the memory 902 may also include both an internal storage unit and an external storage device of the terminal apparatus 900. The memory 902 is used for storing the computer programs and other programs and data required by the terminal device 900. The memory 902 may also be used to temporarily store data that has been output or is to be output.
It will be apparent to those skilled in the art that, for convenience and brevity of description, only the above-mentioned division of the functional units and modules is illustrated, and in practical applications, the above-mentioned function distribution may be performed by different functional units and modules according to needs, that is, the internal structure of the apparatus is divided into different functional units or modules to perform all or part of the above-mentioned functions. Each functional unit and module in the embodiments may be integrated in one processing unit, or each unit may exist alone physically, or two or more units are integrated in one unit, and the integrated unit may be implemented in a form of hardware, or in a form of software functional unit. In addition, specific names of the functional units and modules are only for convenience of distinguishing from each other, and are not used for limiting the protection scope of the present application. The specific working processes of the units and modules in the system may refer to the corresponding processes in the foregoing method embodiments, and are not described herein again.
In the above embodiments, the descriptions of the respective embodiments have respective emphasis, and reference may be made to the related descriptions of other embodiments for parts that are not described or illustrated in a certain embodiment.
Those of ordinary skill in the art will appreciate that the various illustrative elements and algorithm steps described in connection with the embodiments disclosed herein may be implemented as electronic hardware, or combinations of computer software and electronic hardware. Whether such functionality is implemented as hardware or software depends upon the particular application and design constraints imposed on the implementation. Skilled artisans may implement the described functionality in varying ways for each particular application, but such implementation decisions should not be interpreted as causing a departure from the scope of the present invention.
In the embodiments provided in the present invention, it should be understood that the disclosed apparatus/terminal device and method may be implemented in other ways. For example, the above-described embodiments of the apparatus/terminal device are merely illustrative, and for example, the division of the modules or units is only one logical division, and there may be other divisions when actually implemented, for example, a plurality of units or components may be combined or integrated into another system, or some features may be omitted, or not executed. In addition, the shown or discussed mutual coupling or direct coupling or communication connection may be through some interfaces, indirect coupling or communication connection of devices or units, and may be in an electrical, mechanical or other form.
The units described as separate parts may or may not be physically separate, and parts displayed as units may or may not be physical units, may be located in one place, or may be distributed on a plurality of network units. Some or all of the units can be selected according to actual needs to achieve the purpose of the solution of the embodiment.
In addition, functional units in the embodiments of the present invention may be integrated into one processing unit, or each unit may exist alone physically, or two or more units are integrated into one unit. The integrated unit can be realized in a form of hardware, and can also be realized in a form of a software functional unit.
The integrated module/unit, if implemented in the form of a software functional unit and sold or used as a stand-alone product, may be stored in a computer readable storage medium. Based on such understanding, all or part of the flow of the method according to the embodiments of the present invention may also be implemented by a computer program, which may be stored in a computer-readable storage medium, and when the computer program is executed by a processor, the steps of the method embodiments may be implemented. Wherein the computer program comprises computer program code, which may be in the form of source code, object code, an executable file or some intermediate form, etc. The computer-readable medium may include: any entity or device capable of carrying the computer program code, recording medium, usb disk, removable hard disk, magnetic disk, optical disk, computer Memory, read-Only Memory (ROM), random Access Memory (RAM), electrical carrier wave signals, telecommunications signals, software distribution medium, and the like. It should be noted that the computer readable medium may contain content that is subject to appropriate increase or decrease as required by legislation and patent practice in jurisdictions, for example, in some jurisdictions, computer readable media does not include electrical carrier signals and telecommunications signals as is required by legislation and patent practice.
The above-mentioned embodiments are only used for illustrating the technical solutions of the present invention, and not for limiting the same; although the present invention has been described in detail with reference to the foregoing embodiments, it will be understood by those of ordinary skill in the art that: the technical solutions described in the foregoing embodiments may still be modified, or some technical features may be equivalently replaced; such modifications and substitutions do not substantially depart from the spirit and scope of the embodiments of the present invention, and are intended to be included within the scope of the present invention.
Claims (7)
1. A method for restoring a spectrum of a water reflection region of a hyperspectral image is characterized by comprising the following steps of:
carrying out regional identification on the acquired hyperspectral image of the water body to obtain a water body regional image and a water body reflection regional image;
counting a first reflectivity mean sequence and a first reflectivity standard deviation sequence of the corresponding spectrum of the water body region image, and counting a second reflectivity mean sequence and a second reflectivity standard deviation sequence of the corresponding spectrum of the water body reflection region image;
obtaining a spectrum reflectivity sequence after the water reflection area image is recovered according to the first reflectivity mean sequence, the first reflectivity standard deviation sequence, the second reflectivity mean sequence and the second reflectivity standard deviation sequence;
before carrying out region identification on the acquired water body hyperspectral image, the method further comprises the following steps:
carrying out atmospheric correction on the acquired hyperspectral image of the water body to obtain an atmospheric corrected image;
the regional identification is carried out to the water hyperspectral image who obtains, obtains water regional image and water reflection regional image, includes:
carrying out area identification on the image after atmospheric correction to obtain a water body area image and a water body reflection area image;
the obtaining the spectrum reflectivity sequence of the restored water reflection area image according to the first reflectivity mean sequence, the first reflectivity standard deviation sequence, the second reflectivity mean sequence and the second reflectivity standard deviation sequence includes:
according toObtaining the spectrum reflectivity after recovery of each wave band corresponding to the water reflection area image;
wherein s is the spectrum reflectivity of each wave band corresponding to the water reflection region image after recovery, s 1 Spectral reflectance, s, for each band corresponding to the atmospheric corrected image 2 A second reflectivity mean value s corresponding to each wave band in the second reflectivity mean value sequence 3 A second reflectivity standard deviation, s, corresponding to each band in the second reflectivity standard deviation sequence 4 A first reflectivity standard deviation, s, corresponding to each band in the first reflectivity standard deviation sequence 5 A first reflectivity mean value corresponding to each wave band in the first reflectivity mean value sequence;
according to the method for obtaining the spectrum reflectivity after the restoration of each wave band corresponding to the water body reflection region image, obtaining the spectrum reflectivity after the restoration of all the wave bands corresponding to the water body reflection region image;
and obtaining a spectrum reflectivity sequence of the restored water body reflection region image according to the restored spectrum reflectivity of all wave bands corresponding to the water body reflection region image.
2. The method for restoring the water reflection region spectrum of the hyperspectral image according to claim 1, wherein the step of performing region recognition on the acquired water hyperspectral image to obtain a water region image and a water reflection region image comprises the following steps:
calculating the water body index of the water body hyperspectral image to obtain the water body index of the water body hyperspectral image;
according to the characteristics of water reflection in the water hyperspectral image, calculating a reflection index of the water hyperspectral image to obtain the reflection index of the water hyperspectral image;
and carrying out region identification on the water body hyperspectral image according to the water body index and the reflection index to obtain a water body region image and a water body reflection region image.
3. The method for restoring the water reflection region spectrum of the hyperspectral image according to claim 2, wherein the step of performing region recognition on the water hyperspectral image according to the water body index and the reflection index to obtain a water body region image and a water reflection region image comprises the following steps:
performing region identification on the water body hyperspectral image according to the water body index and the reflection index to obtain an initial water body region image containing a water body and a sky and an initial water body reflection region image containing a real object and a reflection;
performing region identification on the initial water body region image based on single-band threshold values of the water body and the sky to obtain a water body region image;
and carrying out region identification on the initial water body reflection region image based on the symmetry of the real object and the reflection and edge detection to obtain a water body reflection region image.
4. The method for restoring the spectrum of the inverted water area of the hyperspectral image according to claim 3, wherein the step of performing area recognition on the initial inverted water area image based on the symmetry of the real object and the inverted image and edge detection to obtain the inverted water area image comprises the following steps:
carrying out Gaussian filtering processing on the initial water reflection area image to obtain a filtered gray level image;
obtaining a water body reflection threshold according to the reflection in the initial water body reflection area image and the gray level image;
performing edge detection on the initial water body reflection region image according to the water body reflection threshold value, and identifying an edge water body reflection region image in the initial water body reflection region image;
and carrying out region identification on the edge water body reflection region image based on the symmetry of the real object and the reflection to obtain a water body reflection region image.
5. The utility model provides a water reflection region spectrum recovery unit of high spectral image which characterized in that includes:
the identification module is used for carrying out regional identification on the acquired hyperspectral image of the water body to obtain a water body regional image and a water body reflection regional image;
the statistical module is used for counting a first reflectivity mean sequence and a first reflectivity standard deviation sequence of the corresponding spectrum of the water body region image, and counting a second reflectivity mean sequence and a second reflectivity standard deviation sequence of the corresponding spectrum of the water body reflection region image;
the recovery module is used for obtaining a spectrum reflectivity sequence after the water reflection area image is recovered according to the first reflectivity mean sequence, the first reflectivity standard deviation sequence, the second reflectivity mean sequence and the second reflectivity standard deviation sequence;
the identification module is specifically used for performing atmospheric correction on the acquired water body hyperspectral image before performing region identification on the acquired water body hyperspectral image to obtain an image after atmospheric correction;
the identification module is further specifically used for carrying out region identification on the image after the atmospheric correction to obtain a water body region image and a water body reflection region image;
the recovery module includes:
a first computing unit for computing based onObtaining the spectrum reflectivity after recovery of each wave band corresponding to the water reflection area image;
wherein s is the spectrum reflectivity of each wave band corresponding to the water reflection region image after recovery, s 1 For each corresponding one of the atmosphere corrected imagesSpectral reflectance of the wavelength band, s 2 A second reflectivity mean, s, corresponding to each band in the second reflectivity mean sequence 3 A second reflectivity standard deviation, s, corresponding to each band in the second reflectivity standard deviation sequence 4 A first reflectivity standard deviation s corresponding to each wave band in the first reflectivity standard deviation sequence 5 A first reflectivity mean value corresponding to each wave band in the first reflectivity mean value sequence;
the second calculation unit is used for obtaining the spectrum reflectivity after recovery of all wave bands corresponding to the water reflection region image according to the method for obtaining the spectrum reflectivity after recovery of each wave band corresponding to the water reflection region image;
and the recovery unit is used for obtaining the spectrum reflectivity sequence of the water reflection region image after recovery according to the spectrum reflectivity of the water reflection region image after recovery of all wave bands.
6. A terminal device comprising a memory, a processor and a computer program stored in the memory and executable on the processor, characterized in that the processor implements the steps of the method according to any of claims 1 to 4 when executing the computer program.
7. A computer-readable storage medium, in which a computer program is stored which, when being executed by a processor, carries out the steps of the method according to any one of claims 1 to 4.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN202110192482.5A CN112927150B (en) | 2021-02-20 | 2021-02-20 | Water reflection area spectrum recovery method of hyperspectral image and terminal device |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN202110192482.5A CN112927150B (en) | 2021-02-20 | 2021-02-20 | Water reflection area spectrum recovery method of hyperspectral image and terminal device |
Publications (2)
Publication Number | Publication Date |
---|---|
CN112927150A CN112927150A (en) | 2021-06-08 |
CN112927150B true CN112927150B (en) | 2023-04-07 |
Family
ID=76169962
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN202110192482.5A Active CN112927150B (en) | 2021-02-20 | 2021-02-20 | Water reflection area spectrum recovery method of hyperspectral image and terminal device |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN112927150B (en) |
Citations (4)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN107764758A (en) * | 2017-09-26 | 2018-03-06 | 中国神华能源股份有限公司 | Mining area monitoring method and device, storage medium and processor |
CN110186822A (en) * | 2019-05-13 | 2019-08-30 | 中国科学院遥感与数字地球研究所 | A kind of aerosol optical depth remote sensing inversion method |
CN111307727A (en) * | 2020-03-13 | 2020-06-19 | 生态环境部卫星环境应用中心 | Water body water color abnormity identification method and device based on time sequence remote sensing image |
CN112381013A (en) * | 2020-11-18 | 2021-02-19 | 南通市测绘院有限公司 | Urban vegetation inversion method and system based on high-resolution remote sensing image |
Family Cites Families (7)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN102622738B (en) * | 2012-03-08 | 2014-04-02 | 北京师范大学 | Method for recovering spectral information of hill shade area of Landsat thematic mapper/enhanced thematic mapper plus (TM/ETM+) image |
WO2016114148A1 (en) * | 2015-01-16 | 2016-07-21 | 日本電気株式会社 | Image-processing device, image-processing method, and recording medium |
CN105046087B (en) * | 2015-08-04 | 2017-12-08 | 中国资源卫星应用中心 | A kind of Water-Body Information extraction method of remote sensing satellite multispectral image |
CN107067377B (en) * | 2017-03-02 | 2019-10-29 | 中国科学院遥感与数字地球研究所 | A kind of method and device of the shadow Detection of high spectrum image and spectrum recovery |
CN107145891B (en) * | 2017-05-08 | 2020-12-11 | 中国科学院遥感与数字地球研究所 | Water body extraction method and system based on remote sensing image |
CN108051371B (en) * | 2017-12-01 | 2018-10-02 | 河北省科学院地理科学研究所 | A kind of shadow extraction method of ecology-oriented environment parameter remote-sensing inversion |
CN111738916B (en) * | 2020-08-21 | 2020-11-13 | 湖南省有色地质勘查研究院 | Remote sensing image generalized shadow spectrum reconstruction method and system based on statistics |
-
2021
- 2021-02-20 CN CN202110192482.5A patent/CN112927150B/en active Active
Patent Citations (4)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN107764758A (en) * | 2017-09-26 | 2018-03-06 | 中国神华能源股份有限公司 | Mining area monitoring method and device, storage medium and processor |
CN110186822A (en) * | 2019-05-13 | 2019-08-30 | 中国科学院遥感与数字地球研究所 | A kind of aerosol optical depth remote sensing inversion method |
CN111307727A (en) * | 2020-03-13 | 2020-06-19 | 生态环境部卫星环境应用中心 | Water body water color abnormity identification method and device based on time sequence remote sensing image |
CN112381013A (en) * | 2020-11-18 | 2021-02-19 | 南通市测绘院有限公司 | Urban vegetation inversion method and system based on high-resolution remote sensing image |
Also Published As
Publication number | Publication date |
---|---|
CN112927150A (en) | 2021-06-08 |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
CN110473242B (en) | Texture feature extraction method, texture feature extraction device and terminal equipment | |
CN111079764B (en) | Low-illumination license plate image recognition method and device based on deep learning | |
JP6822569B2 (en) | Image processing device, image processing method and image processing program | |
CN111767819A (en) | Image identification method and device, electronic equipment and computer readable medium | |
CN112183212A (en) | Weed identification method and device, terminal equipment and readable storage medium | |
CN112528866A (en) | Cross-modal face recognition method, device, equipment and storage medium | |
CN112507897A (en) | Cross-modal face recognition method, device, equipment and storage medium | |
CN115439759A (en) | Method and device for extracting vegetation in remote sensing image, electronic equipment and medium | |
CN113421273B (en) | Remote sensing extraction method and device for forest and grass collocation information | |
CN117496560B (en) | Fingerprint line identification method and device based on multidimensional vector | |
CN112927150B (en) | Water reflection area spectrum recovery method of hyperspectral image and terminal device | |
CN109034274B (en) | Method, device and equipment for improving hyperspectral image classification precision and storage medium | |
CN111311573B (en) | Branch determination method and device and electronic equipment | |
CN110175509B (en) | All-weather eye circumference identification method based on cascade super-resolution | |
CN115631419B (en) | Rice planting area and spatial distribution extraction method and device based on change detection | |
CN117475301A (en) | Side slope vegetation classification method and device based on multi-mode depth features | |
CN110766708B (en) | Image comparison method based on contour similarity | |
CN112163443A (en) | Code scanning method, code scanning device and mobile terminal | |
CN111311610A (en) | Image segmentation method and terminal equipment | |
CN113239738B (en) | Image blurring detection method and blurring detection device | |
CN114648627A (en) | Method and system for inhibiting vegetation information of optical remote sensing image in arid and semi-arid region | |
CN108984601B (en) | Image retrieval method and system based on probability histogram area similarity | |
CN111027441A (en) | Road extraction method based on airborne hyperspectral remote sensing image | |
CN111693463A (en) | Antarctic peninsula optimized lichen coverage index extraction method | |
CN116468958B (en) | Communication tower safety detection method and system |
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 |