CN115909033A - Method and device for evaluating freezing state of camera lens - Google Patents
Method and device for evaluating freezing state of camera lens Download PDFInfo
- Publication number
- CN115909033A CN115909033A CN202211490598.8A CN202211490598A CN115909033A CN 115909033 A CN115909033 A CN 115909033A CN 202211490598 A CN202211490598 A CN 202211490598A CN 115909033 A CN115909033 A CN 115909033A
- Authority
- CN
- China
- Prior art keywords
- freezing
- image
- texture
- evaluated
- evaluation
- 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.)
- Pending
Links
Images
Landscapes
- Image Analysis (AREA)
Abstract
The application discloses a camera lens freezing state assessment method and device, and the method comprises the following steps: acquiring an icing image of a power grid during a low-temperature freezing disaster; performing texture feature extraction on the partitioned power grid icing image to construct a texture knowledge base, wherein the texture knowledge base comprises a plurality of texture image blocks, and each texture image block belongs to a preset freezing grade; determining the estimated freezing grade of the frozen image block to be estimated according to the texture knowledge base based on the texture matching degree, wherein the frozen image block to be estimated is obtained by blocking the image to be estimated; and performing freezing state distribution analysis on the image to be evaluated according to the evaluation freezing grades corresponding to all the freezing image blocks to be evaluated to obtain a freezing state evaluation result, wherein the freezing state evaluation result comprises a freezing degree value and a freezing distribution state image. The method and the device can solve the technical problems that the quality of the images acquired under the condition of freezing of the existing monitoring camera is uneven, and the utility value of the image information cannot be determined.
Description
Technical Field
The application relates to the technical field of image processing, in particular to a camera lens freezing state assessment method and device.
Background
The low-temperature freezing disaster can cause the icing of the overhead transmission line, and the safe and stable operation of the power system can be threatened. The power grid company realizes an ice observation system which takes on-line monitoring as a main part and manual ice observation as an auxiliary part, and the ice coating condition of the power transmission line is visually observed by using a large number of ice coating on-line monitoring devices provided with cameras. However, lens freezing may occur in winter in a conventional camera, so that the line icing condition of a shot image cannot be effectively reflected, and the frozen invalid image is transmitted to a background system through data, thereby wasting transmission bandwidth and storage memory.
Disclosure of Invention
The application provides a camera lens congeals state aassessment and device for solve the image quality that obtains under the present monitoring camera congeals and freeze the condition uneven, can't make clear of the technical problem of image information utility value.
In view of the above, a first aspect of the present application provides a camera lens freezing state evaluation method, including:
acquiring an icing image of a power grid during a low-temperature freezing disaster;
performing texture feature extraction on the partitioned power grid icing image to construct a texture knowledge base, wherein the texture knowledge base comprises a plurality of texture image blocks, and each texture image block belongs to a preset freezing grade;
determining the estimated freezing grade of the frozen image block to be estimated according to the texture knowledge base based on the texture matching degree, wherein the frozen image block to be estimated is obtained by partitioning the image to be estimated;
and performing freezing state distribution analysis on the image to be evaluated according to the evaluation freezing grades corresponding to all the image blocks to be evaluated to obtain a freezing state evaluation result, wherein the freezing state evaluation result comprises a freezing degree value and a freezing distribution state image.
Preferably, the texture feature extraction is performed on the partitioned power grid icing image, and a texture knowledge base is constructed, including:
carrying out equal-size segmentation on the power grid icing image to obtain a plurality of icing image blocks;
dividing the icing image block into three preset freezing grades based on a preset classification rule, wherein the preset freezing grades comprise non-freezing, partial freezing and total freezing;
performing texture feature extraction on the icing image block based on a preset LBP operator to obtain a texture image block, wherein the texture image block corresponds to the icing image block one by one;
and constructing a texture knowledge base according to the texture image blocks.
Preferably, the extracting texture features of the ice-coated image block based on a preset LBP operator to obtain a texture image block includes:
after the icing image block is converted into a gray image block, extracting texture features of the gray image block based on a preset LBP operator to obtain an initial texture block;
and extracting the texture histogram of each sub image block in the initial texture block after blocking to obtain a texture image block.
Preferably, the determining, based on the texture matching degree, the estimated freezing level of the frozen image block to be estimated according to the texture knowledge base, where the frozen image block to be estimated is obtained by partitioning the image to be estimated, includes:
calculating the texture matching degree of the frozen image block to be evaluated and each texture image block in the texture knowledge base to obtain a texture matching sequence;
and selecting the preset freezing grade corresponding to the maximum texture matching degree as the evaluation freezing grade of the to-be-evaluated freezing image block.
Preferably, the performing freezing state distribution analysis on the image to be evaluated according to the evaluation freezing grades corresponding to all the image blocks to be evaluated to obtain a freezing state evaluation result includes:
drawing a freezing distribution state image of the image to be evaluated according to the evaluation freezing grade corresponding to the freezing image block to be evaluated in a pixel assignment mode;
calculating the freezing degree value of the image to be evaluated according to the evaluation freezing grade and the number of the frozen image blocks to be evaluated corresponding to each grade;
the freezing state evaluation result comprises a freezing degree value and a freezing distribution state image.
Preferably, the analyzing the freezing state distribution of the image to be evaluated according to the evaluation freezing grades corresponding to all the freezing image blocks to be evaluated to obtain a freezing state evaluation result, and then further comprising:
and evaluating the image information value of the image to be evaluated based on the freezing degree value and the freezing distribution state image to obtain an image value evaluation result.
The second aspect of the present application provides a camera lens frozen state evaluation device, including:
the image acquisition unit is used for acquiring an ice coating image of the power grid during the low-temperature freezing disaster;
the characteristic extraction unit is used for extracting the texture characteristics of the partitioned power grid icing images to construct a texture knowledge base, wherein the texture knowledge base comprises a plurality of texture image blocks, and each texture image block belongs to a preset freezing grade;
the local evaluation unit is used for determining the evaluation freezing grade of the to-be-evaluated frozen image block according to the texture knowledge base based on the texture matching degree, and the to-be-evaluated frozen image block is obtained by partitioning the to-be-evaluated image;
and the global evaluation unit is used for carrying out freezing state distribution analysis on the image to be evaluated according to the evaluation freezing grades corresponding to all the freezing image blocks to be evaluated to obtain a freezing state evaluation result, and the freezing state evaluation result comprises a freezing degree value and a freezing distribution state image.
Preferably, the feature extraction unit is specifically configured to:
carrying out equal-size segmentation on the power grid icing image to obtain a plurality of icing image blocks;
dividing the icing image block into three preset freezing grades based on a preset classification rule, wherein the preset freezing grades comprise non-freezing, partial freezing and total freezing;
extracting texture features of the ice-coated image blocks based on a preset LBP operator to obtain texture image blocks, wherein the texture image blocks correspond to the ice-coated image blocks one by one;
and constructing a texture knowledge base according to the texture image blocks.
Preferably, the local evaluation unit is specifically configured to:
calculating the texture matching degree of the frozen image block to be evaluated and each texture image block in the texture knowledge base to obtain a texture matching sequence;
and selecting the preset freezing grade corresponding to the maximum texture matching degree as the evaluation freezing grade of the to-be-evaluated freezing image block.
Preferably, the global evaluation unit is specifically configured to:
drawing a freezing distribution state image of the image to be evaluated according to the evaluation freezing grade corresponding to the freezing image block to be evaluated in a pixel assignment mode;
calculating the freezing degree value of the image to be evaluated according to the evaluation freezing grade and the number of the frozen image blocks to be evaluated corresponding to each grade;
the freezing state evaluation result comprises a freezing degree value and a freezing distribution state image.
According to the technical scheme, the embodiment of the application has the following advantages:
the application provides a camera lens freezing state assessment method, which comprises the following steps: acquiring an icing image of a power grid during a low-temperature freezing disaster; performing texture feature extraction on the partitioned power grid icing image to construct a texture knowledge base, wherein the texture knowledge base comprises a plurality of texture image blocks, and each texture image block belongs to a preset freezing grade; determining the estimated freezing grade of the frozen image block to be estimated according to the texture knowledge base based on the texture matching degree, wherein the frozen image block to be estimated is obtained by partitioning the image to be estimated; and performing freezing state distribution analysis on the image to be evaluated according to the evaluation freezing grades corresponding to all the image blocks to be evaluated to obtain a freezing state evaluation result, wherein the freezing state evaluation result comprises a freezing degree value and a freezing distribution state image.
According to the camera lens freezing state assessment method, texture analysis is carried out on the power grid icing image acquired during the low-temperature freezing disaster, the local state of the acquired image is assessed through the texture matching degree of the image blocks, and the overall freezing state of the acquired image is analyzed and assessed through the assessment freezing grades of all the image blocks, so that a more accurate and reliable freezing state assessment result is obtained; but also more accords with the actual freezing condition of the power grid; the quality conditions of different images acquired by the monitoring camera can be reflected, so that the information value of the acquired images can be controlled. Therefore, the technical problems that the quality of images acquired under the condition of freezing of the existing monitoring camera is uneven and the utility value of image information cannot be determined can be solved.
Drawings
Fig. 1 is a schematic flowchart of a method for evaluating a freezing state of a camera lens according to an embodiment of the present disclosure;
fig. 2 is a schematic structural diagram of a camera lens freezing state evaluation device according to an embodiment of the present disclosure;
fig. 3 is a schematic diagram of a blank image frame to be assigned according to an embodiment of the present application;
fig. 4 is a schematic diagram of an assigned frozen state after color replacement according to an embodiment of the present application.
Detailed Description
In order to make the technical solutions of the present application better understood, the technical solutions in the embodiments of the present application will be clearly and completely described below with reference to the drawings in the embodiments of the present application, and it is obvious that the described embodiments are only a part of the embodiments of the present application, and not all of the embodiments. 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 application.
For easy understanding, referring to fig. 1, an embodiment of a method for evaluating a freezing state of a camera lens provided by the present application includes:
The icing images in the low-temperature freezing disaster period can be collected through the monitoring device, then a certain number of sample images are selected from the icing images for subsequent image processing and analysis, and since the sizes of the images shot by different cameras are possibly different, all the images need to be subjected to equal-size cutting processing before a data set of the power grid icing images is formed, and the sizes are unified.
And 102, extracting texture features of the partitioned power grid icing image to construct a texture knowledge base, wherein the texture knowledge base comprises a plurality of texture image blocks, and each texture image block belongs to a preset freezing grade.
Further, step 102 includes:
performing equal-size segmentation processing on the power grid icing image to obtain a plurality of icing image blocks;
dividing the icing image block into three preset freezing grades based on a preset classification rule, wherein the preset freezing grades comprise non-freezing, partial freezing and total freezing;
extracting texture features of the ice-coated image blocks based on a preset LBP operator to obtain texture image blocks, wherein the texture image blocks correspond to the ice-coated image blocks one to one;
and constructing a texture knowledge base according to the texture image blocks.
Further, extracting texture features of the ice-coated image block based on a preset LBP operator to obtain a texture image block, including:
after the icing image block is converted into a gray image block, extracting texture features of the gray image block based on a preset LBP operator to obtain an initial texture block;
and extracting the texture histogram of each sub image block in the initial texture block after the block division to obtain a texture image block.
The icing image of the power grid is subjected to equal-size segmentation processing to obtain a plurality of icing image blocks, and subsequent image processing and analysis are performed on the basis of the image blocks, so that the operation is more accurate and reliable; the preset classification rules are configured for image characteristics, or for freezing conditions of the power equipment in the image, and may be configured according to actual conditions without limitation. The preset freezing grades in the embodiment mainly include three types, and more detailed grades can be set according to actual conditions, which is not limited herein.
The LBP operator is a local binary pattern calculation method, and is a visual operator in the field of computer vision. It can be determined that the power grid icing image can be divided into a plurality of icing image blocks. The specific texture extraction process needs to perform gray scale conversion on the ice-covered image block to obtain a gray scale image block, and the conversion mode is expressed as Y =0.299r +0.587g +0.114b, where Y is a gray scale pixel value and R, G, B are three channel pixel values of a color image block respectively; then calculating a texture map corresponding to the gray image block based on an LBP operator, namely an initial texture block; then, the initial texture block is further required to be subjected to equal-size block division to obtain k × k small image blocks, that is, sub image blocks, and then a texture histogram of each sub image block can be extracted, and a texture image block corresponding to the ice-covered image block can be formed by a global texture histogram formed by the texture histograms corresponding to all the sub image blocks. The texture features represented by the texture image blocks in the embodiment include k × k × 59 dimensions, where k may be set according to an actual situation; in addition, the texture image blocks correspond to the ice-coated image blocks one by one, so that each texture image block belongs to the preset freezing grade of the corresponding ice-coated image block.
And 103, determining the estimated freezing grade of the frozen image block to be estimated according to the texture knowledge base based on the texture matching degree, wherein the frozen image block to be estimated is obtained by partitioning the image to be estimated.
Further, step 103 includes:
calculating the texture matching degree of the frozen image block to be evaluated and each texture image block in the texture knowledge base to obtain a texture matching sequence;
and selecting a preset freezing grade corresponding to the maximum texture matching degree as an evaluation freezing grade of the freezing image block to be evaluated.
The image block of the frozen image to be evaluated is obtained by equal-size segmentation from the image to be evaluated, and the image to be evaluated is a current main research object and can be an image shot in real time through the lens of a camera; the freezing state of the lens can be reflected according to the image to be evaluated shot by the lens. The partitioning mode of the image to be evaluated is the partitioning process of the image blocks in the texture knowledge base; it is noted that the current image to be evaluated can be partitioned into m × n frozen image blocks to be evaluated, and also graying conversion operation and texture feature extraction operation need to be performed, and the specific process is described above and is not described herein any more, so that the image to be evaluated needs to be processed into image blocks having a format consistent with that of texture image blocks in a texture knowledge base, and comparison and analysis are facilitated.
Each frozen image block of the image to be evaluated and all texture image blocks in the texture knowledge base can calculate a texture matching degree, so that a texture matching sequence { a } is formed 1 ,a 2 ,......,a i }; and i is the number of the texture image blocks, a maximum texture matching degree can be found in the texture matching sequence, and the preset freezing grade of the texture image block which participates in comparison and corresponds to the maximum texture matching degree is used as the estimated freezing grade of the current frozen image block to be estimated. The texture matching degree can be calculated as follows:
wherein H 1 、H 2 Histograms of a texture image block and a frozen image block to be evaluated in the texture knowledge base are respectively,
respectively the arithmetic mean value of the texture image block and the frozen image block to be evaluated, I is the abscissa value, sigma of the matching element in the corresponding histogram of the two image blocks I The abscissa is traversed for all matching elements in the texture histogram.
And 104, performing freezing state distribution analysis on the image to be evaluated according to the evaluation freezing grades corresponding to all the freezing image blocks to be evaluated to obtain a freezing state evaluation result, wherein the freezing state evaluation result comprises a freezing degree value and a freezing distribution state image.
Further, step 104 includes:
drawing a freezing distribution state image of the image to be evaluated according to the evaluation freezing grade corresponding to the freezing image block to be evaluated in a pixel assignment mode;
calculating the freezing degree value of the image to be evaluated according to the evaluation freezing grade and the number of the frozen image blocks to be evaluated corresponding to each grade;
the freezing state evaluation result comprises a freezing degree value and a freezing distribution state image.
In the above, the frozen state analysis and evaluation is performed on the local part of the image to be evaluated, and the embodiment can also realize the global evaluation of the image to be evaluated. Referring to fig. 3 and 4, for an image to be evaluated, which is divided into m × n frozen image blocks to be evaluated, a blank image frame to be assigned with the same size may be created, and the freezing level of each image block to be evaluated may be determined according to the freezing level to be evaluated corresponding to each image block to be evaluated. If no freezing exists, assigning 1 to the area block corresponding to the blank image frame to be assigned; if the image is partially frozen, assigning a value of 0.5 to the corresponding area block of the blank image to be assigned; if all the blocks are frozen, assigning 0 to the corresponding area block of the blank image to be assigned to form a frozen value-assigning graph; for a more intuitive presentation, the pixel value 0 may be represented by black, the pixel value 0.5 may be represented by gray, and the pixel value 1 may be represented by white, so that the freeze distribution state image may be formed.
In addition, the number of frozen image blocks to be evaluated corresponding to various freezing levels can be counted according to three different freezing levels, and the following judgment and calculation can be carried out according to the number of the image blocks:
if the estimated freezing grades of the mxn frozen image blocks to be estimated are all non-frozen, directly judging that the frozen state estimation result is that the lens is not frozen;
if the estimated freezing grades of the mxn frozen image blocks to be estimated are all frozen, directly judging that the frozen state estimation result is that the lens is all frozen;
if the estimated freezing grade of the m multiplied by n frozen image blocks to be estimated is local freezing, calculating a freezing degree value:
w and p are the number of all frozen image blocks and the number of local frozen image blocks respectively, and mn is the total number of frozen image blocks to be evaluated. The freezing degree value f ranges from [0,1], the closer to 1, the more serious the lens freezing is, and otherwise, the lower the freezing degree is.
Further, step 104, thereafter, further includes:
and evaluating the image information value of the image to be evaluated based on the freezing degree value and the freezing distribution state image to obtain an image value evaluation result.
The information value which can be provided by the image is related to the freezing degree value and the freezing distribution state of the lens, and the image which is obtained only when the lens has continuous regions which are not frozen has the information value; in the present embodiment, when the continuous non-frozen region of the lens is smaller than 0.3 of the total lens region, that is, the freezing degree value is smaller than 0.3, the image acquired at this time is considered to have no information value, and based on this, the following analysis can be performed:
when the freezing degree value f is larger than 0.7, no matter how the lens freezing distribution state is, the continuous non-frozen area of the lens is smaller than 0.3, so that the acquired image is judged to have no information value, is not uploaded to a background system for storage and occupies a memory.
When the freezing degree value f is less than or equal to 0.7, analyzing the freezing distribution state image, marking each connected domain on the freezing distribution state image based on the non-zero connected domain, summing pixel values in each connected domain, finding out the maximum value SS = max (s 1, s 2.. Once.) of the pixel value sum, and taking the maximum pixel sum as the region which is not frozen, if:
it indicates that the image in this case still has information value.
According to the method for evaluating the freezing state of the camera lens, texture analysis is carried out on the power grid icing image acquired during the low-temperature freezing disaster, the local state of the acquired image is evaluated according to the texture matching degree of the image block, and the overall freezing state of the acquired image is analyzed and evaluated according to the evaluation freezing grades of all the image blocks, so that a more accurate and reliable freezing state evaluation result is obtained; but also more accords with the actual freezing condition of the power grid; the quality conditions of different images acquired by the monitoring camera can be reflected, so that the information value of the acquired images can be controlled. Therefore, the technical problems that the quality of images obtained under the condition that the existing monitoring camera is frozen is uneven, and the utility value of image information cannot be determined can be solved.
For easy understanding, please refer to fig. 2, the present application provides an embodiment of a camera lens freezing state evaluation apparatus, including:
an image acquisition unit 201, configured to acquire an image of icing on a power grid during a low-temperature freezing disaster;
the feature extraction unit 202 is configured to perform texture feature extraction on the partitioned power grid icing image, and construct a texture knowledge base, where the texture knowledge base includes a plurality of texture image blocks, and each texture image block belongs to a preset freezing grade;
the local evaluation unit 203 is used for determining the evaluation freezing grade of the frozen image block to be evaluated according to the texture knowledge base based on the texture matching degree, and the frozen image block to be evaluated is obtained by blocking the image to be evaluated;
and the global evaluation unit 204 is configured to perform freezing state distribution analysis on the image to be evaluated according to the evaluation freezing grades corresponding to all the freezing image blocks to be evaluated to obtain a freezing state evaluation result, where the freezing state evaluation result includes a freezing degree value and a freezing distribution state image.
Further, the feature extraction unit 202 is specifically configured to:
performing equal-size segmentation processing on the power grid icing image to obtain a plurality of icing image blocks;
dividing the icing image block into three preset freezing grades based on a preset classification rule, wherein the preset freezing grades comprise non-freezing, partial freezing and total freezing;
extracting texture features of the ice-coated image blocks based on a preset LBP operator to obtain texture image blocks, wherein the texture image blocks correspond to the ice-coated image blocks one to one;
and constructing a texture knowledge base according to the texture image blocks.
Further, the local evaluation unit 203 is specifically configured to:
calculating the texture matching degree of the frozen image block to be evaluated and each texture image block in the texture knowledge base to obtain a texture matching sequence;
and selecting a preset freezing grade corresponding to the maximum texture matching degree as an evaluation freezing grade of the image block to be evaluated.
Further, the global evaluation unit 204 is specifically configured to:
drawing a freezing distribution state image of the image to be evaluated according to the evaluation freezing grade corresponding to the freezing image block to be evaluated in a pixel assignment mode;
calculating the freezing degree value of the image to be evaluated according to the evaluation freezing grade and the number of the frozen image blocks to be evaluated corresponding to each grade;
the freezing state evaluation result comprises a freezing degree value and a freezing distribution state image.
In the several embodiments provided in the present application, it should be understood that the disclosed apparatus and method may be implemented in other ways. For example, the above-described apparatus embodiments are merely illustrative, and for example, the division of the units is only one logical division, and other divisions may be realized in practice, 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 an indirect coupling or communication connection through some interfaces, 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 application 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 may be implemented in the form of hardware, or may also be implemented in the form of a software functional unit.
The integrated 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, the technical solutions of the present application, or portions or all or portions of the technical solutions that contribute to the prior art, may be embodied in the form of a software product, which is stored in a storage medium and includes several instructions for executing all or part of the steps of the methods described in the embodiments of the present application through a computer device (which may be a personal computer, a server, or a network device). And the aforementioned storage medium includes: a U disk, a removable hard disk, a Read-Only Memory (ROM), a Random Access Memory (RAM), a magnetic disk, or an optical disk.
The above embodiments are only used for illustrating the technical solutions of the present application, and not for limiting the same; although the present application has been described in detail with reference to the foregoing embodiments, it should 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; and such modifications or substitutions do not depart from the spirit and scope of the corresponding technical solutions in the embodiments of the present application.
Claims (10)
1. A camera lens freezing state assessment method is characterized by comprising the following steps:
acquiring an icing image of a power grid during a low-temperature freezing disaster;
performing texture feature extraction on the partitioned power grid icing image to construct a texture knowledge base, wherein the texture knowledge base comprises a plurality of texture image blocks, and each texture image block belongs to a preset freezing grade;
determining the evaluation freezing grade of the to-be-evaluated frozen image block according to the texture knowledge base based on the texture matching degree, wherein the to-be-evaluated frozen image block is obtained by partitioning the to-be-evaluated image;
and performing freezing state distribution analysis on the image to be evaluated according to the evaluation freezing grades corresponding to all the image blocks to be evaluated to obtain a freezing state evaluation result, wherein the freezing state evaluation result comprises a freezing degree value and a freezing distribution state image.
2. The camera lens freezing state evaluation method according to claim 1, wherein the texture feature extraction is performed on the partitioned power grid icing image to construct a texture knowledge base, and the texture knowledge base comprises:
carrying out equal-size segmentation on the power grid icing image to obtain a plurality of icing image blocks;
dividing the icing image block into three preset freezing grades based on a preset classification rule, wherein the preset freezing grades comprise non-freezing, partial freezing and total freezing;
extracting texture features of the ice-coated image blocks based on a preset LBP operator to obtain texture image blocks, wherein the texture image blocks correspond to the ice-coated image blocks one by one;
and constructing a texture knowledge base according to the texture image blocks.
3. The camera lens freezing state evaluation method according to claim 2, wherein the performing texture feature extraction on the ice-coated image block based on a preset LBP operator to obtain a texture image block comprises:
after the icing image block is converted into a gray image block, extracting texture features of the gray image block based on a preset LBP operator to obtain an initial texture block;
and extracting the texture histogram of each sub-image block in the initial texture block after blocking to obtain a texture image block.
4. The camera lens freezing state evaluation method according to claim 1, wherein the determining an evaluation freezing grade of a frozen image block to be evaluated according to the texture knowledge base based on the texture matching degree, the frozen image block to be evaluated being obtained by blocking an image to be evaluated, comprises:
calculating the texture matching degree of the frozen image block to be evaluated and each texture image block in the texture knowledge base to obtain a texture matching sequence;
and selecting the preset freezing grade corresponding to the maximum texture matching degree as the evaluation freezing grade of the to-be-evaluated freezing image block.
5. The camera lens freezing state evaluation method according to claim 1, wherein the performing freezing state distribution analysis on the image to be evaluated according to the evaluation freezing grades corresponding to all the freezing image blocks to be evaluated to obtain a freezing state evaluation result comprises:
drawing a freezing distribution state image of the image to be evaluated according to the evaluation freezing grade corresponding to the freezing image block to be evaluated in a pixel assignment mode;
calculating the freezing degree value of the image to be evaluated according to the evaluation freezing grade and the number of the frozen image blocks to be evaluated corresponding to each grade;
the freezing state evaluation result comprises a freezing degree value and a freezing distribution state image.
6. The camera lens freezing state evaluation method according to claim 1, wherein the freezing state distribution analysis is performed on the image to be evaluated according to the evaluation freezing grades corresponding to all the image blocks of the freezing image to be evaluated to obtain a freezing state evaluation result, and then the method further comprises:
and evaluating the image information value of the image to be evaluated based on the freezing degree value and the freezing distribution state image to obtain an image value evaluation result.
7. A camera lens frost state evaluation device, comprising:
the image acquisition unit is used for acquiring an ice coating image of the power grid during the low-temperature freezing disaster;
the characteristic extraction unit is used for extracting the texture characteristics of the partitioned power grid icing images to construct a texture knowledge base, wherein the texture knowledge base comprises a plurality of texture image blocks, and each texture image block belongs to a preset freezing grade;
the local evaluation unit is used for determining the evaluation freezing grade of the to-be-evaluated frozen image block according to the texture knowledge base based on the texture matching degree, wherein the to-be-evaluated frozen image block is obtained by partitioning the to-be-evaluated image;
and the global evaluation unit is used for carrying out freezing state distribution analysis on the image to be evaluated according to the evaluation freezing grades corresponding to all the freezing image blocks to be evaluated to obtain a freezing state evaluation result, and the freezing state evaluation result comprises a freezing degree value and a freezing distribution state image.
8. The camera lens frost state evaluation apparatus according to claim 7, wherein the feature extraction unit is specifically configured to:
performing equal-size segmentation processing on the power grid icing image to obtain a plurality of icing image blocks;
dividing the icing image block into three preset freezing grades based on a preset classification rule, wherein the preset freezing grades comprise non-freezing, partial freezing and total freezing;
extracting texture features of the ice-coated image blocks based on a preset LBP operator to obtain texture image blocks, wherein the texture image blocks correspond to the ice-coated image blocks one by one;
and constructing a texture knowledge base according to the texture image blocks.
9. The camera lens frost state evaluation apparatus according to claim 7, wherein the local evaluation unit is specifically configured to:
calculating the texture matching degree of the frozen image block to be evaluated and each texture image block in the texture knowledge base to obtain a texture matching sequence;
and selecting the preset freezing grade corresponding to the maximum texture matching degree as the evaluation freezing grade of the to-be-evaluated freezing image block.
10. The camera lens frost state evaluation apparatus according to claim 7, wherein the global evaluation unit is specifically configured to:
drawing a freezing distribution state image of the image to be evaluated according to the evaluation freezing grade corresponding to the freezing image block to be evaluated in a pixel assignment mode;
calculating the freezing degree value of the image to be evaluated according to the evaluation freezing grade and the number of the frozen image blocks to be evaluated corresponding to each grade;
the freezing state evaluation result comprises a freezing degree value and a freezing distribution state image.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202211490598.8A CN115909033A (en) | 2022-11-25 | 2022-11-25 | Method and device for evaluating freezing state of camera lens |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202211490598.8A CN115909033A (en) | 2022-11-25 | 2022-11-25 | Method and device for evaluating freezing state of camera lens |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN115909033A true CN115909033A (en) | 2023-04-04 |
Family
ID=86489231
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202211490598.8A Pending CN115909033A (en) | 2022-11-25 | 2022-11-25 | Method and device for evaluating freezing state of camera lens |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN115909033A (en) |
Cited By (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN116193240B (en) * | 2023-04-27 | 2023-10-03 | 天津奇立软件技术有限公司 | Electronic equipment state evaluation method and system |
| CN118015384A (en) * | 2024-04-08 | 2024-05-10 | 江西省天驰高速科技发展有限公司 | Pier column concrete disease automatic identification method and system |
-
2022
- 2022-11-25 CN CN202211490598.8A patent/CN115909033A/en active Pending
Cited By (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN116193240B (en) * | 2023-04-27 | 2023-10-03 | 天津奇立软件技术有限公司 | Electronic equipment state evaluation method and system |
| CN118015384A (en) * | 2024-04-08 | 2024-05-10 | 江西省天驰高速科技发展有限公司 | Pier column concrete disease automatic identification method and system |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN112379231B (en) | Equipment detection method and device based on multispectral image | |
| CN108108772B (en) | Insulator pollution flashover state detection method based on aerial image of distribution line | |
| CN108564588B (en) | Built-up area automatic extraction method based on depth features and graph segmentation method | |
| CN108682039B (en) | Binocular stereo vision measuring method | |
| CN108510496B (en) | Fuzzy detection method for SVD (singular value decomposition) based on image DCT (discrete cosine transformation) domain | |
| CN111402247A (en) | Machine vision-based method for detecting defects of suspension clamp on power transmission line | |
| CN112164086A (en) | Refined image edge information determining method and system and electronic equipment | |
| CN115909033A (en) | Method and device for evaluating freezing state of camera lens | |
| CN112837313A (en) | Image segmentation method for foreign matters in power transmission line | |
| CN110782409A (en) | Method for removing shadow of multi-motion object | |
| CN108345898A (en) | A kind of novel line insulator Condition assessment of insulation method | |
| CN115588192A (en) | Cell image classification method, image classification system, electronic device, and storage medium | |
| CN114004834A (en) | Method, equipment and device for analyzing foggy weather condition in image processing | |
| CN110544262B (en) | Cervical cell image segmentation method based on machine vision | |
| CN115311623A (en) | Equipment oil leakage detection method and system based on infrared thermal imaging | |
| CN114998251A (en) | Air multi-vision platform ground anomaly detection method based on federal learning | |
| Tan et al. | Image haze removal based on superpixels and Markov random field | |
| CN112884795A (en) | Power transmission line inspection foreground and background segmentation method based on multi-feature significance fusion | |
| CN108765337B (en) | Single color image defogging processing method based on dark channel prior and non-local MTV model | |
| CN114708532A (en) | Monitoring video quality evaluation method, system and storage medium | |
| Fuh et al. | Mcpa: A fast single image haze removal method based on the minimum channel and patchless approach | |
| CN111489333B (en) | No-reference night natural image quality evaluation method | |
| Pal | Visibility enhancement of fog degraded image sequences on SAMEER TU dataset using dark channel strategy | |
| Ding et al. | Traffic image dehazing based on HSV color space | |
| Li et al. | Laplace dark channel attenuation-based single image defogging in ocean scenes |
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 |