CN110288557B - Infrared image restoration method, device, equipment and readable storage medium - Google Patents
Infrared image restoration method, device, equipment and readable storage medium Download PDFInfo
- Publication number
- CN110288557B CN110288557B CN201910599512.7A CN201910599512A CN110288557B CN 110288557 B CN110288557 B CN 110288557B CN 201910599512 A CN201910599512 A CN 201910599512A CN 110288557 B CN110288557 B CN 110288557B
- Authority
- CN
- China
- Prior art keywords
- matrix
- pixel
- value
- infrared image
- blind
- 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
- 238000000034 method Methods 0.000 title claims abstract description 59
- 238000003860 storage Methods 0.000 title claims abstract description 17
- 239000011159 matrix material Substances 0.000 claims abstract description 198
- 238000001514 detection method Methods 0.000 claims abstract description 27
- 238000004590 computer program Methods 0.000 claims description 11
- 238000010276 construction Methods 0.000 claims description 7
- 238000013507 mapping Methods 0.000 claims description 7
- 238000004364 calculation method Methods 0.000 abstract description 12
- 230000008439 repair process Effects 0.000 abstract description 10
- 238000004422 calculation algorithm Methods 0.000 abstract description 8
- 238000012937 correction Methods 0.000 abstract description 8
- 230000008569 process Effects 0.000 abstract description 8
- 238000005336 cracking Methods 0.000 abstract description 4
- 230000009286 beneficial effect Effects 0.000 abstract description 2
- 238000010586 diagram Methods 0.000 description 4
- 230000009471 action Effects 0.000 description 3
- 238000012545 processing Methods 0.000 description 3
- 230000000694 effects Effects 0.000 description 2
- 238000005516 engineering process Methods 0.000 description 2
- 238000013213 extrapolation Methods 0.000 description 2
- 238000003384 imaging method Methods 0.000 description 2
- 238000003331 infrared imaging Methods 0.000 description 2
- 238000012986 modification Methods 0.000 description 2
- 230000004048 modification Effects 0.000 description 2
- 238000012360 testing method Methods 0.000 description 2
- 238000013461 design Methods 0.000 description 1
- 238000011161 development Methods 0.000 description 1
- 230000006870 function Effects 0.000 description 1
- 238000004519 manufacturing process Methods 0.000 description 1
- 230000003287 optical effect Effects 0.000 description 1
- 230000000737 periodic effect Effects 0.000 description 1
- 230000000750 progressive effect Effects 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
- G06T5/90—Dynamic range modification of images or parts thereof
- G06T5/94—Dynamic range modification of images or parts thereof based on local image properties, e.g. for local contrast enhancement
-
- 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
- G06T2207/10048—Infrared image
Landscapes
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Engineering & Computer Science (AREA)
- Theoretical Computer Science (AREA)
- Image Processing (AREA)
Abstract
The invention discloses an infrared image restoration method, which comprises the following steps: acquiring an original infrared image, and calculating the average value of pixel difference values of each pixel and adjacent pixels in the original infrared image to obtain a first matrix; carrying out blind element point detection on the original infrared image by using the first matrix to obtain blind element points; repairing the pixel value of the blind pixel point by using the pixel mean value of the neighborhood pixel corresponding to the blind pixel point; the method does not need to carry out non-uniformity correction on the original infrared image, and the calculation process is simple, so that the algorithm complexity is reduced, the calculation amount is reduced, and the detection speed of the blind element points in the original infrared image and the repair speed of the blind element points in the original infrared image are accelerated; the method can also effectively reduce the false detection rate of the blind element points under the conditions of poor image quality such as image cracking and the like; the invention also provides an infrared image restoration device, equipment and a computer readable storage medium, and the infrared image restoration device, the equipment and the computer readable storage medium also have the beneficial effects.
Description
Technical Field
The present invention relates to the field of infrared image restoration, and in particular, to an infrared image restoration method, apparatus, device, and computer-readable storage medium.
Background
In recent years, the development of infrared imaging technology is very rapid, and the infrared imaging technology is widely applied to the fields of military affairs, buildings, safety, industry and the like.
Due to factors such as the manufacturing process, anomalies may occur in certain pixels of the infrared detector, which are collectively referred to as blind primitive points. When an infrared detector is used for imaging, the conditions of constant brightness, constant darkness or periodic flicker and the like can occur in the blind pixel points, the quality of the infrared image is affected, and the observation of a small target is particularly not facilitated. At present, when an infrared detector is used for acquiring an infrared image, a conventional non-uniformity correction cannot repair a blind primitive point, and the image after the non-uniformity correction needs to be subjected to secondary processing by using a linear extrapolation method, namely, the position of the blind primitive point is acquired by using the linear extrapolation method and the pixel value of the pixel around the blind primitive point is used for replacing the pixel value of the blind primitive point. The method can solve the imaging problem caused by the blind pixel points in real time, but the original infrared image needs to be processed twice, so the algorithm complexity is high, the calculated amount is large, and the processing speed is low. When the number of blind pixel points is large, it is difficult to quickly detect the blind pixel points and repair the infrared image.
Therefore, how to rapidly detect the blind spot and repair the infrared image is a problem to be solved by those skilled in the art.
Disclosure of Invention
The invention aims to provide an infrared image restoration method, an infrared image restoration device, an infrared image restoration apparatus and a computer-readable storage medium, so as to realize the functions of quickly detecting blind pixel points in an original infrared image and restoring the blind pixel points.
In order to solve the technical problem, the invention provides an infrared image restoration method, which comprises the following steps:
acquiring an original infrared image, and calculating the average value of pixel difference values of each pixel and adjacent pixels in the original infrared image to obtain a first matrix;
carrying out blind element point detection on the original infrared image by using the first matrix to obtain blind element points;
and repairing the pixel value of the blind pixel point by using the pixel average value of the neighborhood pixel corresponding to the blind pixel point.
Optionally, performing blind primitive point detection on the original infrared image by using the first matrix to obtain blind primitive points, including:
mapping the element values in the first matrix by using the maximum value in the element values of the elements in the first matrix to obtain a second matrix;
constructing an element maximum matrix and a threshold matrix by using the second matrix, and constructing a judgment matrix by using the maximum matrix and the threshold matrix;
determining whether the element value of the element in the second matrix is greater than the element value of a corresponding element in the determination matrix; if so, the pixel corresponding to the element is the dummy point; if not, the pixel corresponding to the element is a normal point.
Optionally, constructing an element maximum matrix and a threshold matrix by using the second matrix includes:
and comparing the element values of the neighborhood elements of each element in the second matrix to obtain a maximum element value, and constructing the maximum element value matrix by using the maximum element value.
Optionally, constructing an element maximum matrix and a threshold matrix by using the second matrix includes:
calculating an element mean value of the element values of the neighborhood elements in the second matrix, and constructing the threshold matrix using the element mean value.
Optionally, constructing a judgment matrix by using the maximum matrix and the threshold matrix, including:
and comparing the element values of the elements in the maximum element value matrix with the element values of the corresponding elements in the threshold value matrix to obtain a larger element value, and constructing the judgment matrix by using the larger element value.
Optionally, before repairing the pixel value of the dummy point by using the pixel average value of the neighboring pixel of the dummy point, the method further includes:
and calculating the pixel mean value by using the pixel values of the neighborhood pixels, and replacing the pixel values of the pixels by using the pixel mean value to obtain a mean value matrix.
Optionally, repairing the pixel value of the dummy point by using the pixel average value of the neighboring pixel of the dummy point includes:
replacing the pixel values of the blind pixels with the element values of the elements in the mean matrix corresponding to the blind pixel points.
The present invention also provides an infrared image restoration device, including:
the first matrix construction module is used for acquiring an original infrared image, and calculating a pixel difference value average value of a pixel and a neighborhood pixel in the original infrared image to obtain a first matrix;
the blind element point detection module is used for detecting the blind element points in the original infrared image by using the first matrix to obtain the blind element points;
and the repairing module is used for repairing the pixel value of the blind pixel point by using the pixel average value of the neighborhood pixel corresponding to the blind pixel point.
The invention also provides an infrared image restoration device, comprising a memory and a processor, wherein:
the memory is used for storing a computer program;
the processor is used for executing the computer program to realize the infrared image restoration method.
The present invention also provides a computer readable storage medium for storing a computer program, wherein the computer program, when executed by a processor, implements the infrared image restoration method described above.
Therefore, the method obtains the original infrared image, calculates the pixel difference value average value of each pixel and the adjacent pixel in the original infrared image, and obtains the first matrix. And carrying out blind element point detection on the original infrared image by using the first matrix to obtain blind element points. And repairing the pixel value of the blind pixel point by using the pixel mean value of the neighborhood pixel corresponding to the blind pixel point. The method does not need to carry out non-uniformity correction on the original infrared image, and the calculation process is simple, so that the algorithm complexity is reduced, the calculation amount is reduced, and the detection speed of the blind element points in the original infrared image and the repair speed of the blind element points in the original infrared image are accelerated. The method can also effectively reduce the error detection rate of the blind pixel points under the condition of poor image quality such as image cracking and the like.
In addition, the invention also provides an infrared image restoration device, equipment and a computer readable storage medium, and the infrared image restoration device, the equipment and the computer readable storage medium also have the beneficial effects.
Drawings
In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the drawings used in the description of the embodiments or the prior art will be briefly described below, it is obvious that the drawings in the following description are only embodiments of the present invention, and for those skilled in the art, other drawings can be obtained according to the provided drawings without creative efforts.
Fig. 1 is a flowchart of an infrared image restoration method according to an embodiment of the present invention;
FIG. 2 is a flowchart of another infrared image restoration method according to an embodiment of the present invention;
FIG. 3 is a flowchart of another infrared image restoration method according to an embodiment of the present invention;
fig. 4 is a schematic structural diagram of an infrared image restoration apparatus according to an embodiment of the present invention;
fig. 5 is a schematic structural diagram of an infrared image restoration device according to an embodiment of the present invention.
Detailed Description
In order to make the objects, technical solutions and advantages of the embodiments of the present invention clearer, the technical solutions in the embodiments of the present invention will be clearly and completely described below with reference to the drawings in the embodiments of the present invention, and it is obvious that the described embodiments are some, but not all, embodiments of the present invention. All other embodiments, which can be derived by a person skilled in the art from the embodiments given herein without making any creative effort, shall fall within the protection scope of the present invention.
The first embodiment is as follows:
referring to fig. 1, fig. 1 is a flowchart illustrating an infrared image restoration method according to an embodiment of the present invention. The method comprises the following steps:
s101: and acquiring an original infrared image, and calculating the pixel difference value average value of each pixel and the adjacent pixel in the original infrared image to obtain a first matrix.
Specifically, an infrared detector may be used to obtain an original infrared image, which is an image without any correction or processing. In the embodiment, the original infrared image does not need to be subjected to non-uniformity correction, so that the algorithm complexity is reduced, and the calculation amount is reduced. In this embodiment, the pixel value may represent an infrared irradiation intensity value.
In this embodiment, each pixel in the original infrared image needs to be subjected to the calculation of the pixel difference average value, and this embodiment does not limit the order of the pixels for calculating the difference average value, for example, the calculation may be performed in the order from small to large in the number of rows, and the calculation may be performed in the order from small to large in the number of columns in the same row. The specific number of the neighborhood pixels is not limited in this embodiment, for example, four pixels above, below, to the left, and to the right of the central pixel may be selected as the neighborhood pixels; or eight pixels surrounding the central pixel may be selected as neighborhood pixels of the central pixel. If the central pixel is located at the edge position of the original infrared image, the number of the neighboring pixels is reduced, and the method for calculating the pixel difference average value of the central pixel located at the edge position is not limited in this embodiment, for example, the pixel difference average value may be calculated only with the existing neighboring pixels.
Preferably, the present embodiment selects eight pixels surrounding the central pixel as the neighborhood pixels, and utilizes
And (3) calculating the pixel with the coordinate of (i, j), namely the average value of the pixel difference values of the ith row and the jth column in the original infrared image and the adjacent pixels, and constructing a first matrix. Wherein, F is a first matrix, F (I, j) is an element value of an element with a coordinate (I, j) in the first matrix, and I (I, j) is a pixel value of a pixel with a coordinate (I, j) in the original infrared image.
S102: and carrying out blind element point detection on the original infrared image by using the first matrix to obtain blind element points.
In this embodiment, the order of performing blind pixel detection on each pixel in the original infrared image by using the first matrix is not limited, and for example, blind pixel detection may be performed on each pixel in sequence; or firstly detecting the region with higher probability of the blind pixel point. Referring to fig. 2, fig. 2 is a flowchart of another infrared image restoration method according to an embodiment of the present invention, including:
s201: and mapping the element values in the first matrix by using the maximum value in the element values of the elements in the first matrix to obtain a second matrix.
Specifically, the element values of each element in the first matrix are compared to obtain the maximum value, and it is preferable in this embodiment to use
F1(i,j)＝[F(i,j)*1023]/Max
Mapping the first matrix, mapping element values of elements in the first matrix to 0-1023, and constructing a second matrix; wherein, F1Is a second matrix, F1(i, j) is the element value of the element with coordinate (i, j) in the second matrix, and Max is the maximum value. And after the second matrix is obtained, constructing an element maximum matrix and a threshold matrix by using the second matrix.
S202: and comparing the element values of the neighborhood elements of all the elements in the second matrix to obtain the maximum element value, and constructing a maximum element value matrix by using the maximum element value.
The specific number of neighborhood elements is not limited in this embodiment, for example, four elements above, below, to the left, and to the right of the central element may be selected as neighborhood elements; or eight elements surrounding the center element may be selected as neighborhood elements of the center element. The present embodiment selects the neighborhood elements that are preferable, that is, eight elements surrounding the center element are selected as the center element.
By using
Comparing the element values of the neighborhood elements of all the elements in the second matrix to obtain a maximum element value, and constructing a maximum element value matrix; where MaxN is the maximum matrix, and MaxN (i, j) is the element value of the element with coordinate (i, j) in the maximum matrix.
S203: and calculating the element mean value of the element values of the neighborhood elements in the second matrix, and constructing a threshold matrix by using the element mean value.
By using
Calculating the element mean value of the element values of the neighborhood elements in the second matrix, and constructing an element mean value matrix; the AVG is an element mean matrix, and the AVG (i, j) is an element value of an element with a coordinate (i, j) in the element mean matrix.
And multiplying the element mean matrix and the comparison coefficient to obtain a threshold matrix. The magnitude of the comparison coefficient is not limited in this embodiment. Test tests show that the detection effect is better when the comparison coefficient is 4, so that the threshold matrix is preferably 4 × AVG in the embodiment.
The execution sequence of steps S202 and S203 is not limited in this embodiment. For example, step S202 may be performed first, and then step S203 may be performed; or the step S203 may be executed first, and the step S202 is executed; or the step S202 and the step S203 are executed simultaneously. It is sufficient that the steps S202 and S203 are executed before the step S204. In order to increase the speed of detecting the blind spot and reduce the time required for detection, it is preferable that the steps S202 and S203 are performed simultaneously.
S204: and comparing the element values of the elements in the maximum element value matrix with the element values of the corresponding elements in the threshold value matrix to obtain a larger element value, and constructing a judgment matrix by using the larger element value.
In this embodiment, the elements in the maximum element value matrix correspond to the elements in the threshold value matrix, that is, the coordinates of the elements in the maximum element value matrix are the same as the coordinates of the elements in the threshold value matrix. Similarly, the correspondence between the pixels and the elements in the original infrared image is that the coordinates of the pixels are the same as the coordinates of the elements.
The maximum matrix and the threshold matrix are used to construct the judgment matrix, and in this embodiment, the maximum matrix and the threshold matrix may be used
Maxim(i,j)＝max[MaxN(i,j),4*AVG(i,j)]
Constructing a judgment matrix; wherein, Maxim is a judgment matrix, and Maxim (i, j) is an element value with a coordinate of (i, j) in the judgment matrix;
s205: and judging whether the element value of the element in the second matrix is larger than the element value of the corresponding element in the judgment matrix.
In particular, the values of the elements of the second matrix are determined and the values of the corresponding elements of the matrix are determinedAnd judging whether the pixel in the original infrared image corresponding to the element is a blind pixel or not according to the value of the element. When the element values of the elements in the second matrix are larger, i.e. when F1If (i, j) > Maxim, it indicates that the pixel value of the pixel corresponding to the element is outside the normal range, that is, the pixel is a blind pixel, then step S206 is performed, that is, the pixel corresponding to the element is determined to be a blind pixel; when the element value of an element in the second matrix is smaller than the element value of the corresponding element in the decision matrix, i.e. when F1If the value of the pixel corresponding to the element is less than or equal to Maxim, the pixel value of the pixel corresponding to the element is in the normal range, that is, the pixel is a normal point, then step S207 is entered, that is, the pixel corresponding to the element is determined to be a normal point.
S103: and repairing the pixel value of the blind pixel point by using the pixel mean value of the neighborhood pixel corresponding to the blind pixel point.
After the blind pixel point is detected, the pixel value of the blind pixel point needs to be repaired, and then the original infrared image needs to be repaired. The present embodiment is not limited to the method for repairing the pixel value of the blind primitive point, and for example, the pixel value of a certain neighborhood pixel of the blind primitive point may be used to replace the pixel value of the blind primitive point. In order to improve the restoration effect and make the restored infrared image more realistic, in this embodiment, it is preferable to calculate a pixel mean value of a neighborhood pixel corresponding to the blind pixel point, and replace the pixel value of the blind pixel point with the pixel mean value. In this embodiment, the repair sequence when repairing the pixel values of the blind pixel points is not limited, for example, the pixel mean value of all the blind pixel points may be calculated first, and then the blind pixel points are repaired at the same time; or firstly calculating the pixel mean value of one blind element point, and after the blind element point is repaired, repairing the next blind element point until all the blind element points are repaired.
By applying the infrared image restoration method provided by the embodiment of the invention, the original infrared image is obtained, and the pixel difference value average value of each pixel and the adjacent pixel in the original infrared image is calculated to obtain the first matrix. And carrying out blind element point detection on the original infrared image by using the first matrix to obtain blind element points. And repairing the pixel value of the blind pixel point by using the pixel mean value of the neighborhood pixel corresponding to the blind pixel point. The method does not need to carry out non-uniformity correction on the original infrared image, and the calculation process is simple, so that the algorithm complexity is reduced, the calculation amount is reduced, and the detection speed of the blind element points in the original infrared image and the repair speed of the blind element points in the original infrared image are accelerated. The method can also effectively reduce the error detection rate of the blind pixel points under the condition of poor image quality such as image cracking and the like.
Example two:
based on the first embodiment, in order to accelerate the infrared image restoration speed, before restoring the pixel values of the blind pixel points, the pixel mean value may be calculated by using the pixel values of the neighboring pixels, and a mean value matrix may be constructed. When the pixel values of the blind pixel points are repaired, the pixel values can be directly replaced by using the corresponding element values in the mean value matrix. Referring to fig. 3, fig. 3 is a flowchart of another infrared image restoration method according to an embodiment of the present invention, including:
s101: and acquiring an original infrared image, and calculating the pixel difference value average value of each pixel and the adjacent pixel in the original infrared image to obtain a first matrix.
This step is described in detail in the first embodiment, and reference may be made to the first embodiment, which is not described herein again.
S102: and carrying out blind element point detection on the original infrared image by using the first matrix to obtain blind element points.
This step is described in detail in the first embodiment, and reference may be made to the first embodiment, which is not described herein again.
S301: and calculating a pixel mean value by using the pixel values of the neighborhood pixels, and replacing the pixel values of the pixels by using the pixel mean value to obtain a mean value matrix.
By using
And calculating the pixel mean value of the neighborhood pixels and constructing a pixel mean value matrix. Where, MidN is the mean matrix, and MidN (i, j) is the element value of the element with coordinate (i, j) in the mean matrix.
S302: and replacing the pixel value of the blind pixel point by the element value of the element corresponding to the blind pixel point in the mean value matrix.
After detecting the blind pixel point, replacing the pixel value of the blind pixel point with the element value of the element corresponding to the blind pixel point in the mean matrix, i.e. using
And repairing the pixel value of the dummy point. Wherein IO is the repaired infrared image, and IO (i, j) is the pixel value of the pixel with the coordinate (i, j) in the repaired infrared image.
Preferably, in order to reduce the time required for infrared image restoration, in this embodiment, the step S301 may be executed simultaneously with the step S101; or simultaneously with the step S102.
By applying the infrared image restoration method provided by the embodiment of the invention, the pixel mean value is calculated by using the pixel values of the neighborhood pixels, and the pixel mean value is used for replacing the pixel values of the pixels to obtain a mean value matrix; and replacing the pixel value of the blind pixel point by the element value of the element corresponding to the blind pixel point in the mean value matrix. The method can directly replace the pixel value of the blind pixel point by the element value of the corresponding element in the mean value matrix when the pixel value of the blind pixel point is repaired, thereby reducing the time required by the repairing process and further reducing the time required by the whole infrared image repairing process.
In the following, the infrared image restoration apparatus, the device, and the computer-readable storage medium according to the embodiments of the present invention are introduced, and the infrared image restoration apparatus, the device, and the computer-readable storage medium described below may be referred to in correspondence with the infrared image restoration method described above.
Example three:
referring to fig. 4, fig. 4 is a schematic structural diagram of an infrared image restoration apparatus according to an embodiment of the present invention, including:
the first matrix building module 100 is configured to obtain an original infrared image, and calculate a pixel difference average value between a pixel in the original infrared image and a neighboring pixel to obtain a first matrix;
the blind pixel point detection module 200 is configured to perform blind pixel point detection on the original infrared image by using a first matrix to obtain a blind pixel point;
the repairing module 300 repairs the pixel value of the blind pixel point by using the pixel mean value of the neighborhood pixel corresponding to the blind pixel point.
By applying the infrared image restoration device provided by the embodiment of the invention, the original infrared image is obtained, and the pixel difference value average value of each pixel and the adjacent pixel in the original infrared image is calculated to obtain the first matrix. And carrying out blind element point detection on the original infrared image by using the first matrix to obtain blind element points. And repairing the pixel value of the blind pixel point by using the pixel mean value of the neighborhood pixel corresponding to the blind pixel point. The device does not need to carry out non-uniformity correction on the original infrared image, and the calculation process is simple, so that the algorithm complexity is reduced, the calculation amount is reduced, and the detection speed of the blind element points in the original infrared image and the repair speed of the blind element points in the original infrared image are accelerated. The device can also effectively reduce the false detection rate of the blind pixel points under the condition of poor image quality such as image cracking and the like.
Optionally, the blind pixel detection module 200 includes:
the second matrix construction unit is used for mapping the element values in the first matrix by using the maximum value in the element values of the elements in the first matrix to obtain a second matrix;
the matrix construction unit is used for constructing an element maximum matrix and a threshold matrix by using the second matrix and constructing a judgment matrix by using the maximum matrix and the threshold matrix;
the judging unit is used for judging whether the element value of the element in the second matrix is larger than the element value of the corresponding element in the judging matrix; if yes, the pixel corresponding to the element is a blind pixel; and if not, the pixel corresponding to the element is the normal point.
Optionally, the matrix building unit includes:
and the maximum element value matrix constructing subunit is used for comparing the element values of the neighborhood elements of each element in the second matrix to obtain a maximum element value, and constructing a maximum element value matrix by using the maximum element value.
Optionally, the matrix building unit includes:
and the threshold matrix constructing subunit is used for calculating the element mean value of the element values of the neighborhood elements in the second matrix and constructing the threshold matrix by using the element mean value.
Optionally, the matrix building unit includes:
and the judgment matrix constructing subunit is used for comparing the element values of the elements in the maximum element value matrix with the element values of the corresponding elements in the threshold value matrix to obtain a larger element value, and constructing the judgment matrix by using the larger element value.
Optionally, the method further includes:
and the mean matrix construction module is used for calculating a pixel mean value by using the pixel values of the neighborhood pixels and replacing the pixel values of the pixels by using the pixel mean value to obtain a mean matrix.
Optionally, the repair module 300 includes:
and the pixel value replacing unit is used for replacing the pixel value of the blind pixel by using the element value of the element corresponding to the blind pixel in the mean value matrix.
Example four:
referring to fig. 5, fig. 5 is a schematic structural diagram of an infrared image restoration device according to an embodiment of the present invention, where the infrared image restoration device includes a memory and a processor, where:
a memory 10 for storing a computer program;
a processor 20 for executing a computer program to implement the infrared image restoration method as described above.
Example five:
the invention further provides a computer readable storage medium, on which a computer program is stored, which when executed by a processor implements the steps of the infrared image restoration method described above.
The computer-readable storage medium may include: various media capable of storing program codes, such as a usb disk, a removable hard disk, a Read-Only Memory (ROM), a Random Access Memory (RAM), a magnetic disk, or an optical disk.
The embodiments are described in a progressive manner in the specification, each embodiment focuses on differences from other embodiments, and the same and similar parts among the embodiments are referred to each other. The device, the apparatus and the computer-readable storage medium disclosed in the embodiments correspond to the method disclosed in the embodiments, so that the description is simple, and the relevant points can be referred to the description of the method.
Those of skill would further appreciate that the various illustrative elements and algorithm steps described in connection with the embodiments disclosed herein may be implemented as electronic hardware, computer software, or combinations of both, and that the various illustrative components and steps have been described above generally in terms of their functionality in order to clearly illustrate this interchangeability of hardware and software. 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.
The steps of a method or algorithm described in connection with the embodiments disclosed herein may be embodied directly in hardware, in a software module executed by a processor, or in a combination of the two. A software module may reside in Random Access Memory (RAM), memory, Read Only Memory (ROM), electrically programmable ROM, electrically erasable programmable ROM, registers, hard disk, a removable disk, a CD-ROM, or any other form of storage medium known in the art.
Finally, it should also be noted that, herein, relationships such as first and second, etc., are intended only to distinguish one entity or action from another entity or action without necessarily requiring or implying any actual such relationship or order between such entities or actions. Also, the terms "comprises," "comprising," or any other variation thereof, are intended to cover a non-exclusive inclusion, such that a process, method, article, or apparatus that comprises a list of elements does not include only those elements but may include other elements not expressly listed or inherent to such process, method, article, or apparatus.
The method, apparatus, device and computer readable storage medium for infrared image restoration provided by the present invention are described in detail above. The principles and embodiments of the present invention are explained herein using specific examples, which are presented only to assist in understanding the method and its core concepts. It should be noted that, for those skilled in the art, it is possible to make various improvements and modifications to the present invention without departing from the principle of the present invention, and those improvements and modifications also fall within the scope of the claims of the present invention.
Claims (8)
1. An infrared image restoration method is characterized by comprising the following steps:
acquiring an original infrared image, and calculating the average value of pixel difference values of each pixel and adjacent pixels in the original infrared image to obtain a first matrix;
carrying out blind element point detection on the original infrared image by using the first matrix to obtain blind element points;
repairing the pixel value of the blind pixel point by using the pixel average value of the neighborhood pixel corresponding to the blind pixel point;
the method for detecting the blind element points of the original infrared image by using the first matrix to obtain the blind element points comprises the following steps:
mapping the element values in the first matrix by using the maximum value in the element values of the elements in the first matrix to obtain a second matrix;
constructing an element maximum matrix and a threshold matrix by using the second matrix, and constructing a judgment matrix by using the maximum matrix and the threshold matrix;
determining whether the element value of the element in the second matrix is greater than the element value of a corresponding element in the determination matrix; if so, the pixel corresponding to the element is the dummy point; if not, the pixel corresponding to the element is a normal point;
constructing a judgment matrix by using the maximum matrix and the threshold matrix, wherein the judgment matrix comprises the following steps:
and comparing the element values of the elements in the maximum element value matrix with the element values of the corresponding elements in the threshold value matrix to obtain a larger element value, and constructing the judgment matrix by using the larger element value.
2. The infrared image restoration method according to claim 1, wherein constructing an element maximum value matrix and a threshold value matrix using the second matrix comprises:
and comparing the element values of the neighborhood elements of each element in the second matrix to obtain a maximum element value, and constructing the maximum element value matrix by using the maximum element value.
3. The infrared image restoration method according to claim 2, wherein constructing an element maximum value matrix and a threshold value matrix using the second matrix comprises:
calculating an element mean value of the element values of the neighborhood elements in the second matrix, and constructing the threshold matrix using the element mean value.
4. The infrared image restoration method according to claim 1, wherein before restoring the pixel value of the dummy point by using the pixel average value of the neighborhood pixels of the dummy point, the method further comprises:
and calculating the pixel mean value by using the pixel values of the neighborhood pixels, and replacing the pixel values of the pixels by using the pixel mean value to obtain a mean value matrix.
5. The infrared image restoration method according to claim 4, wherein restoring the pixel value of the dummy point by using the pixel average value of the neighborhood pixels of the dummy point comprises:
replacing the pixel values of the blind pixels with element values of elements in the mean matrix corresponding to the blind pixel points.
6. An infrared image restoration device, comprising:
the first matrix construction module is used for acquiring an original infrared image, and calculating a pixel difference value average value of a pixel and a neighborhood pixel in the original infrared image to obtain a first matrix;
the blind element point detection module is used for detecting the blind element points in the original infrared image by using the first matrix to obtain the blind element points;
the repairing module is used for repairing the pixel value of the blind pixel point by using the pixel average value of the neighborhood pixel corresponding to the blind pixel point;
blind spot detection module 200, comprising:
the second matrix construction unit is used for mapping the element values in the first matrix by using the maximum value in the element values of the elements in the first matrix to obtain a second matrix;
the matrix construction unit is used for constructing an element maximum matrix and a threshold matrix by using the second matrix and constructing a judgment matrix by using the maximum matrix and the threshold matrix;
the judging unit is used for judging whether the element value of the element in the second matrix is larger than the element value of the corresponding element in the judging matrix; if yes, the pixel corresponding to the element is a blind pixel; if not, the pixel corresponding to the element is a normal point;
a matrix building unit comprising:
and the judgment matrix constructing subunit is used for comparing the element values of the elements in the maximum element value matrix with the element values of the corresponding elements in the threshold value matrix to obtain a larger element value, and constructing the judgment matrix by using the larger element value.
7. An infrared image restoration device, comprising a memory and a processor, wherein:
the memory is used for storing a computer program;
the processor is configured to execute the computer program to implement the infrared image restoration method according to any one of claims 1 to 5.
8. A computer-readable storage medium for storing a computer program, wherein the computer program, when executed by a processor, implements the infrared image restoration method according to any one of claims 1 to 5.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201910599512.7A CN110288557B (en) | 2019-07-04 | 2019-07-04 | Infrared image restoration method, device, equipment and readable storage medium |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201910599512.7A CN110288557B (en) | 2019-07-04 | 2019-07-04 | Infrared image restoration method, device, equipment and readable storage medium |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN110288557A CN110288557A (en) | 2019-09-27 |
| CN110288557B true CN110288557B (en) | 2021-07-13 |
Family
ID=68021850
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201910599512.7A Active CN110288557B (en) | 2019-07-04 | 2019-07-04 | Infrared image restoration method, device, equipment and readable storage medium |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN110288557B (en) |
Families Citing this family (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN111724320B (en) * | 2020-06-19 | 2021-01-08 | 北京波谱华光科技有限公司 | Blind pixel filling method and system |
| CN111879412B (en) * | 2020-08-03 | 2021-12-21 | 烟台艾睿光电科技有限公司 | Image generation method and device for refrigeration type infrared detector and readable storage medium |
| CN117611470B (en) * | 2024-01-18 | 2024-05-03 | 之江实验室 | Multi-temporal infrared image fusion method, device and medium |
Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN104330167A (en) * | 2014-11-24 | 2015-02-04 | 浙江大立科技股份有限公司 | Infrared focal plane array dynamic blind element processing method and device |
| CN108513075A (en) * | 2018-04-17 | 2018-09-07 | 烟台艾睿光电科技有限公司 | A kind of image processing method, device, equipment, medium and infrared imaging device |
| CN108805853A (en) * | 2017-04-28 | 2018-11-13 | 武汉多谱多勒科技有限公司 | A kind of infrared image blind pixel detection method |
| CN109360168A (en) * | 2018-10-16 | 2019-02-19 | 烟台艾睿光电科技有限公司 | Infrared image removes method, apparatus, infrared detector and the storage medium of striped |
| CN109584205A (en) * | 2018-10-19 | 2019-04-05 | 中国人民解放军海军工程大学 | Blind pixel detection method and device |
| CN109671035A (en) * | 2018-12-26 | 2019-04-23 | 哈工大机器人（山东）智能装备研究院 | A kind of infrared image enhancing method based on histogram |
-
2019
- 2019-07-04 CN CN201910599512.7A patent/CN110288557B/en active Active
Patent Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN104330167A (en) * | 2014-11-24 | 2015-02-04 | 浙江大立科技股份有限公司 | Infrared focal plane array dynamic blind element processing method and device |
| CN108805853A (en) * | 2017-04-28 | 2018-11-13 | 武汉多谱多勒科技有限公司 | A kind of infrared image blind pixel detection method |
| CN108513075A (en) * | 2018-04-17 | 2018-09-07 | 烟台艾睿光电科技有限公司 | A kind of image processing method, device, equipment, medium and infrared imaging device |
| CN109360168A (en) * | 2018-10-16 | 2019-02-19 | 烟台艾睿光电科技有限公司 | Infrared image removes method, apparatus, infrared detector and the storage medium of striped |
| CN109584205A (en) * | 2018-10-19 | 2019-04-05 | 中国人民解放军海军工程大学 | Blind pixel detection method and device |
| CN109671035A (en) * | 2018-12-26 | 2019-04-23 | 哈工大机器人（山东）智能装备研究院 | A kind of infrared image enhancing method based on histogram |
Non-Patent Citations (2)
| Title |
|---|
| 基于场景的红外成像系统盲元检测及校正;李召龙等;《激光与红外》;20170430;第47卷(第4期);第465-469页 * |
| 红外焦平面阵列的盲元自适应快速校正;李凌霄等;《光学精密工程》;20170430;第25卷(第4期);第477-486页 * |
Also Published As
| Publication number | Publication date |
|---|---|
| CN110288557A (en) | 2019-09-27 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN110288557B (en) | Infrared image restoration method, device, equipment and readable storage medium | |
| US9679216B2 (en) | Morphological automatic triangle orientation detection | |
| US8433104B2 (en) | Image processing method for background removal | |
| CN114066857A (en) | Infrared image quality evaluation method and device, electronic equipment and readable storage medium | |
| CN109002823B (en) | Region-of-interest determining method, device, equipment and readable storage medium | |
| JP2009237621A (en) | Ridge direction extracting device, ridge direction extracting program, and ridge direction extracting method | |
| JP2019066265A (en) | Crack detector, crack detection method, and computer program | |
| JP2017166942A (en) | Testing method of crack on rubber | |
| CN111539238A (en) | Two-dimensional code image restoration method and device, computer equipment and storage medium | |
| JP2019066266A (en) | Crack detector, crack detection method, and computer program | |
| JP2019066264A (en) | Crack detector, crack detection method, and computer program | |
| CN104794711B (en) | A kind of image processing method and device | |
| JP2013081171A (en) | Method for luminance correction of defective pixel in digital monochrome image | |
| US20060028233A1 (en) | Pixel testing method, method of correcting output voltage of pixel, defect pixel processing device, defect pixel processing program, defect pixel processing method, and recording medium having program | |
| CN107230195B (en) | Image processing method and device | |
| CN105469413A (en) | Normalized ringing weighting based no-reference comprehensive quality assessment method for fuzzy restored image | |
| CN111292300B (en) | Method and apparatus for detecting bright spot defect of display panel, and readable storage medium | |
| CN109350018B (en) | The palm detection method based on image applied to palm bleb detection system | |
| CN114241959B (en) | Abnormal lamp spot detection method, display device and storage medium | |
| CN113222843B (en) | Image restoration method and related equipment thereof | |
| CN115760653A (en) | Image correction method, device, equipment and readable storage medium | |
| JP2013509641A (en) | Method and system for processing data using nonlinear gradient compensation | |
| JP2019066267A (en) | Crack detector, crack detection method, and computer program | |
| JP2019066263A (en) | Crack detector, crack detection method, and computer program | |
| KR102279177B1 (en) | Apparatus and method for subpixel line localization |
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 | ||
| PE01 | Entry into force of the registration of the contract for pledge of patent right |
Denomination of invention: Infrared image restoration method, device, device and readable storage medium Effective date of registration: 20211230 Granted publication date: 20210713 Pledgee: Yantai Branch of China Merchants Bank Co.,Ltd. Pledgor: Yantai Airui Photo-Electric Technology Co.,Ltd. Registration number: Y2021980017076 |
|
| PE01 | Entry into force of the registration of the contract for pledge of patent right | ||
| PC01 | Cancellation of the registration of the contract for pledge of patent right |
Date of cancellation: 20230106 Granted publication date: 20210713 Pledgee: Yantai Branch of China Merchants Bank Co.,Ltd. Pledgor: Yantai Airui Photo-Electric Technology Co.,Ltd. Registration number: Y2021980017076 |
|
| PC01 | Cancellation of the registration of the contract for pledge of patent right | ||
| PE01 | Entry into force of the registration of the contract for pledge of patent right |
Denomination of invention: An infrared image restoration method, device, device and readable storage medium Effective date of registration: 20230113 Granted publication date: 20210713 Pledgee: Yantai Branch of China Merchants Bank Co.,Ltd. Pledgor: Yantai Airui Photo-Electric Technology Co.,Ltd. Registration number: Y2023980031040 |
|
| PE01 | Entry into force of the registration of the contract for pledge of patent right | ||
| PC01 | Cancellation of the registration of the contract for pledge of patent right |
Granted publication date: 20210713 Pledgee: Yantai Branch of China Merchants Bank Co.,Ltd. Pledgor: Yantai Airui Photo-Electric Technology Co.,Ltd. Registration number: Y2023980031040 |
|
| PC01 | Cancellation of the registration of the contract for pledge of patent right | ||
| EE01 | Entry into force of recordation of patent licensing contract |
Application publication date: 20190927 Assignee: INFIRAY TECHNOLOGIES CO.,LTD. Assignor: Yantai Airui Photo-Electric Technology Co.,Ltd. Contract record no.: X2024980006380 Denomination of invention: A method, device, device, and readable storage medium for infrared image restoration Granted publication date: 20210713 License type: Common License Record date: 20240530 |
|
| EE01 | Entry into force of recordation of patent licensing contract |