CN117372678A - Polarization significance calculating method and system - Google Patents
Polarization significance calculating method and system Download PDFInfo
- Publication number
- CN117372678A CN117372678A CN202311326353.6A CN202311326353A CN117372678A CN 117372678 A CN117372678 A CN 117372678A CN 202311326353 A CN202311326353 A CN 202311326353A CN 117372678 A CN117372678 A CN 117372678A
- Authority
- CN
- China
- Prior art keywords
- polarization
- image
- saliency
- difference
- calculating
- 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
- 230000010287 polarization Effects 0.000 title claims abstract description 313
- 238000000034 method Methods 0.000 title claims abstract description 70
- 238000004364 calculation method Methods 0.000 claims abstract description 54
- 238000001514 detection method Methods 0.000 claims abstract description 11
- 238000012545 processing Methods 0.000 claims abstract description 8
- 239000011159 matrix material Substances 0.000 claims description 29
- 230000008569 process Effects 0.000 claims description 21
- 230000008859 change Effects 0.000 claims description 7
- 238000013441 quality evaluation Methods 0.000 claims description 4
- 230000004927 fusion Effects 0.000 abstract description 3
- 238000004590 computer program Methods 0.000 description 9
- 238000003384 imaging method Methods 0.000 description 7
- 230000000694 effects Effects 0.000 description 4
- 230000008092 positive effect Effects 0.000 description 4
- 238000011160 research Methods 0.000 description 3
- 238000011156 evaluation Methods 0.000 description 2
- 230000006870 function Effects 0.000 description 2
- 230000011218 segmentation Effects 0.000 description 2
- 230000000007 visual effect Effects 0.000 description 2
- 238000012512 characterization method Methods 0.000 description 1
- 238000002059 diagnostic imaging Methods 0.000 description 1
- 238000010586 diagram Methods 0.000 description 1
- 238000005516 engineering process Methods 0.000 description 1
- 238000005286 illumination Methods 0.000 description 1
- 230000003993 interaction Effects 0.000 description 1
- 239000000463 material Substances 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 238000012544 monitoring process Methods 0.000 description 1
- 230000003287 optical effect Effects 0.000 description 1
- 238000003672 processing method Methods 0.000 description 1
- 238000013139 quantization Methods 0.000 description 1
- 238000001228 spectrum Methods 0.000 description 1
Landscapes
- Image Analysis (AREA)
Abstract
The invention belongs to the technical field of polarized image processing, and discloses a polarized saliency calculation method and a polarized saliency calculation system. The polarized light images of four angles are acquired through a polarization camera, and the light intensity image is obtained through calculationAnd polarization degree imageThe method comprises the steps of carrying out a first treatment on the surface of the Calculating and obtaining an intensity imageAnd polarization degree imageIs a polarization difference image of (a)The method comprises the steps of carrying out a first treatment on the surface of the Calculating and obtaining polarization significant difference matrixes in different directionsThe method comprises the steps of carrying out a first treatment on the surface of the Calculating and obtaining polarization salient feature imagesThe method comprises the steps of carrying out a first treatment on the surface of the Calculating and obtaining polarization salient feature images in different directionsCorresponding weight coefficients; calculating and obtaining polarization saliency images. The calculating method for highlighting the polarization difference between the polarized image target and the background can enhance the specific polarization information in the polarized image; the invention highlights key areas in the polarized images and provides a technical basis for high-precision polarized image fusion and polarized target detection and classification tasks.
Description
Technical Field
The invention belongs to the technical field of polarized image processing, and particularly relates to a polarized saliency calculation method and a polarized saliency calculation system.
Background
Polarization is a basic property of light, and after polarized light interacts with a target, scattered light contains polarization information determined by the characteristics of the target itself, and is different from common information such as spectrum, light intensity, phase and the like. Advantages of polarized imaging include robustness to various material characterizations, and compared to conventional imaging methods, polarized imaging can obtain polarized information of a target while obtaining light intensity information of the target. Since the fine information in the light intensity image is easily affected by illumination, the polarization imaging technology can describe the inherent polarization characteristics of a scene and is more sensitive to surface changes invisible to human eyes, and therefore, the method is widely applied to the fields of target identification, remote sensing detection and the like.
Image salient region detection research is becoming a hot content in the field of computer vision. However, the conventional saliency calculation method based on image pixels can highlight the target in the image to a certain extent, but the effect is not ideal for polarized images. For the calculation method of the polarization significance, the method is still in the blank research field at present, related researches are few and lack theoretical basis, the effect is not outstanding enough, and the target significant region of the polarization image can not be accurately obtained. Due to the special properties of polarization imaging, more sufficient highlighting and detection can be realized on objects in certain specific scenes, and particularly, polarization highlighting can provide effective help for advanced visual tasks such as subsequent target detection, segmentation and the like.
Disclosure of Invention
In order to overcome the problems in the related art, the disclosed embodiments of the present invention provide a method and a system for calculating polarization saliency, which are used for highlighting the calculation method of the polarization difference between a polarized image target and a background, and can enhance the specific polarization information in the polarized image. The invention aims to provide a saliency calculation method for polarized images, which highlights key areas in the polarized images and provides a technical basis for high-precision polarized image fusion and polarized target detection and classification tasks.
The technical scheme is as follows: a polarization saliency calculation method, comprising the steps of:
s1, acquiring polarized light images at four angles through a polarization camera, and obtaining a light intensity image through calculationAnd polarization degree image->；
S2, calculating and obtaining a light intensity imageAnd polarization degree image->Polarization difference image->；
S3, calculating and obtaining polarization significant difference matrixes in different directions；
S4, calculating and obtaining a polarization salient feature image；
S5, calculating and obtaining polarization salient feature images in different directionsCorresponding weight coefficients;
s6, calculating and obtaining a polarization saliency image。
In step S1, a light intensity image is obtained by resolutionAnd polarization degree image->Comprising:
polarized image acquisition using a cameraObtain->Polarized light intensity image of polarization direction, < >>The method comprises the steps of carrying out a first treatment on the surface of the Resolving to obtain light intensity image->And polarization degree image->；
Wherein,respectively representing four different polarization directions.
In step S2, a light intensity image is calculated and obtainedAnd polarization degree image->Polarization difference image->Comprising:
image the degree of polarizationAnd light intensity image->Corresponding pixels in the image are calculated to obtain a polarized difference image +.>The calculation formula is as follows:
，
in the method, in the process of the invention,for polarization difference image, +.>For pixel value +.>Corresponding pixel histogram, < >>For the length of the image->Is the width of the image->Is polarization degree image->At->Pixel value at +.>For light intensity image +.>At->Pixel value at +.>Is polarization degree image->At->Pixel value at +.>For light intensity image +.>At the position ofValues of pixels at>For pixel value, +.>For pixel coordinates, +.>Is the pixel point coordinates.
In step S3, polarization saliency difference matrices in different directions are calculated and obtainedComprising:
image of polarization differenceQuantized to->After several grey levels, a polarization difference image is recorded +.>At->Pixel point in polarization direction->The value of (2) and the pixel point larger than the value +.>The frequency of paired occurrence, the salient information in the image is reserved; statistics of significant difference pixel pairs ++for each polarization direction>The frequency of occurrence is compared with the total frequency of occurrence of all the significant difference pixel pairs to obtain the frequency of occurrence of each significant difference pixel pair in four different directions, which is arranged into a +.>Square matrix of size, which is a polarization significant difference matrix +.>，/>，/>Respectively representing four different polarization directions.
Further, polarization significant difference matrixThe calculation formula of (2) is as follows:
，
，
in the method, in the process of the invention,is at->Polarization significance difference matrix in polarization direction>First->The value of the individual element(s),representation->The degree of difference of each polarization in the set is +.>Frequency of occurrence, ++>For pixel coordinates, +.>For the purpose of polarization difference image->Upper pixel +.>Is +.>Degree of polarization significant difference in target region pair +.>Set of->Is pixel dot +.>Pixel value of>Is one of the polarization significant difference degree pairs, +.>Is the other of the polarization significant difference degree pair, +.>Is a polarized difference image->Upper pixel +.>At->Degree of significant contrast difference in polarization direction, +.>Respectively is->Polarization difference image in polarization direction->At->Gray values at that point.
In step S4, a polarization salient feature image is calculated and obtainedComprising:
calculating each of the whole imagePolarization significant difference matrix in target area +.>The polarization significant feature quantity of the (2) is calculated as follows:
，
in the method, in the process of the invention,for polarization direction characteristic image, +.>Is polarization difference matrix>For the distance in the current polarization direction, +.>Is polarization direction +.>Is a polarization significant difference matrix->In->Individual element->The polarization direction distance is->Is a value of an element of (a).
In step S5, polarization salient feature images of different directions are calculated and obtainedThe formula of the corresponding weight coefficient is as follows:
，
in the method, in the process of the invention,polarization salient feature image for different directions +.>Corresponding weight coefficient, ++>，/>Respectively iteration coefficients;for no reference image quality evaluation, < >>Entropy of information,,>is the information entropy; />Balance coefficient of IQA, +.>Balance coefficient of EN, +.>Is a control constant.
In step S6, a polarization saliency image is calculated and obtainedComprising: changing the image with polarization saliency features in different polarization directions +.>Weighting is carried out to obtain a final polarization significance image, and the formula is as follows:
，
in the method, in the process of the invention,for polarized saliency image, ">An image of a change in polarization salient features; />Image for polarization salient feature change->Corresponding weight coefficients.
Another object of the present invention is to provide a polarization saliency calculation system, which implements the polarization saliency calculation method, the system comprising:
a polarization difference image acquisition module for calculating a polarization difference image from pixel differences between the light intensity image and the polarization degree image；
A polarization significant difference matrix acquisition module for utilizing the polarization difference imageCalculating and obtaining polarization significant difference matrixes in different directions>，
A polarization salient feature image calculation module for calculating a polarization salient feature image corresponding to each direction；
A polarization saliency image calculation module for calculating each polarization saliency feature imageAfter the corresponding weight coefficient, finally obtaining polarization significance image +.>。
Further, the system is mounted on an image recognition instrument in the fields of target recognition and remote sensing detection and is used for detecting the image salient region.
By combining all the technical schemes, the invention has the advantages and positive effects that: the polarization saliency calculation method of the invention considers the salient characteristics of the polarized image and suppresses redundant information in the polarized image, and can highlight important areas even in an image with a complex environment, compared with a saliency calculation method of image pixels using only light intensity images.
According to the polarization significance calculating method, the polarization significance is obtained based on the calculated polarization difference image, so that the difference information of the light intensity image and the polarization image is increased, and the information of the multi-mode image can be utilized more effectively.
According to the polarization saliency calculation method, the polarization characteristics in different directions can be represented based on the calculated polarization saliency difference matrixes in different directions and the corresponding polarization saliency characteristic images, so that the completeness and reliability of polarization information utilization are ensured.
According to the polarization saliency calculation method, the weight coefficient corresponding to the polarization saliency characteristic image is calculated by using NR-IQA and EN. Firstly, NR-IQA is used for measuring the quality of an image, and a polarization significant image is expected to have higher image quality; however, NR-IQA is merely an evaluation of image quality, and it is difficult to make a correct evaluation of polarization information in a polarized image; therefore, the invention introduces EN to ensure that the polarized significant image has enough information on the basis of NR-IQA.
In a word, compared with the traditional image pixel saliency calculation method, the polarization saliency calculation method is more suitable for polarized images, can highlight key areas in the polarized images, and is convenient to cooperate with fusion, target detection and classification tasks based on polarization imaging.
(1) The polarization saliency calculation method is a new polarization image processing method, can provide more accurate target polarization information than the traditional saliency calculation method, and has important application value in the fields of industrial detection, biotechnology, medical imaging, remote sensing monitoring, modern military and the like.
(2) The main processing object of the traditional saliency calculation method is a light intensity image, and the polarization saliency calculation method can extract the saliency information of the polarization image by utilizing the polarization characteristics and the difference between the polarization image and the light intensity image.
(3) The polarization saliency calculation method can be applied to the field of polarization image processing, and avoids errors caused by the traditional saliency calculation method, so that the reliability of the follow-up computer vision task result is ensured.
Drawings
The accompanying drawings, which are incorporated in and constitute a part of this specification, illustrate embodiments consistent with the disclosure and together with the description, serve to explain the principles of the disclosure;
FIG. 1 is a flow chart of a method for calculating polarization saliency provided by an example of the present invention;
FIG. 2 is a schematic illustration of an embodiment of the present inventionAn intensity image;
FIG. 3 is a schematic illustration of an embodiment of the present inventionPolarization degree image;
FIG. 4 is an image of a change in polarization salient features in the 0 polarization direction provided by an example of the present invention;
FIG. 5 is an image of a change in polarization salient features in the 45 polarization direction provided by an example of the present invention;
FIG. 6 is an image of a change in polarization salient features in the 90 polarization direction provided by an example of the present invention;
FIG. 7 is a representation of the polarization salient feature variation in 135 polarization direction provided by an example of the present invention;
FIG. 8 is a schematic illustration of an embodiment of the present inventionA pixel saliency image;
FIG. 9 is a polarization saliency image provided by an example of the present invention;
FIG. 10 is a schematic diagram of a polarization saliency calculation system provided by an example of the present invention;
in the figure: 1. a polarization difference image acquisition module; 2. a polarization significant difference matrix acquisition module; 3. a polarization salient feature image calculation module; 4. and a polarization saliency image calculation module.
Detailed Description
In order that the above objects, features and advantages of the invention will be readily understood, a more particular description of the invention will be rendered by reference to the appended drawings. In the following description, numerous specific details are set forth in order to provide a thorough understanding of the present invention. The invention may be embodied in many other forms than described herein and similarly modified by those skilled in the art without departing from the spirit or scope of the invention, which is therefore not limited to the specific embodiments disclosed below.
Embodiment 1, as shown in fig. 1, the method for calculating polarization saliency provided by the embodiment of the invention includes the following steps:
s1, acquiring polarized light images at four angles through a polarization camera, and obtaining a light intensity image through calculationAnd polarization degree image->；
S2, calculating and obtaining a light intensity imageAnd polarization degree image->Polarization difference image->；
S3, calculating and obtaining polarization significant difference matrixes in different directions；
S4, calculating and obtaining a polarization salient feature image；
S5, calculating and obtaining polarization salient feature images in different directionsCorresponding weight coefficients;
s6, calculating and obtaining a polarization saliency image。
In step S1, a light intensity image is obtained by resolutionAnd polarization degree image->Comprising:
polarized image acquisition using a cameraObtain->Polarized light intensity image of polarization direction, < >>The method comprises the steps of carrying out a first treatment on the surface of the Obtaining a light intensity map by calculationImage->And polarization degree image->The method comprises the steps of carrying out a first treatment on the surface of the Wherein (1)>Respectively representing four different polarization directions.
In step S2, a light intensity image is calculated and obtainedAnd polarization degree image->Polarization difference image->Comprising:
image the degree of polarizationAnd light intensity image->The corresponding pixels of the pixels in (a) are calculated to obtain a polarization difference image +.>The calculation formula is as follows:
，
in the method, in the process of the invention,for polarization difference image, +.>Pixel value +.>Corresponding pixel straight squareFigure (S)>For the length of the image->Is the width of the image->Is polarization degree image->At->Pixel value at +.>For light intensity image +.>At->Pixel value at +.>Is polarization degree image->At->Pixel value at +.>For light intensity image +.>At->Values of pixels at>For pixel value, +.>For pixel coordinates, +.>Is the pixel point coordinates.
In step S3, polarization saliency difference matrices in different directions are calculated and obtainedComprising:
image of polarization differenceQuantized to->After several grey levels, a polarization difference image is recorded +.>At->In the polarization direction, pixel point->The value of (2) and the pixel point larger than the value +.>The frequency of pairwise occurrences, thereby preserving salient information in the image; statistics of significant difference pixel pairs ++for each polarization direction>The frequency of occurrence is then compared with the total frequency of occurrence of all the significant difference pixel pairs to obtain the frequency of occurrence of each significant difference pixel pair in four different directions, and then the significant difference pixel pairs are arranged into a +.>Square matrix of size, which is a polarization significant difference matrix +.>，/>，/>Respectively representing four different polarization directions.
In the embodiment of the invention, the polarization significant difference matrixThe calculation formula of (2) is as follows:
，
，
in the method, in the process of the invention,is at->Polarization significance difference matrix in polarization direction>First->The value of the individual element(s),representation->The degree of difference of each polarization in the set is +.>Frequency of occurrence, ++>For pixel coordinates, +.>For the purpose of polarization difference image->Upper pixel +.>Is +.>Degree of polarization significant difference in target region pair +.>Set of->Is pixel dot +.>Pixel value of>Is one of the polarization significant difference degree pairs, +.>Is the other of the polarization significant difference degree pair, +.>Is a polarized difference image->Upper pixel +.>At->Degree of significant contrast difference in polarization direction, +.>Respectively is->Polarization difference image in polarization direction->At->Gray values at that point.
Polarization significant difference matrixThe positive effects are as follows: polarization significant difference matrix->The joint probability density of pixels at two positions is defined to reflect not only the distribution characteristics of the difference between the pixels of the light intensity image and the polarized image, but also the position distribution characteristics between pixels having the same or similar significance.
In step S4, a polarization salient feature image is calculated and obtainedComprising: calculating each +.>Polarization significant difference matrix in target area +.>The polarization significant feature quantity of the (2) is calculated as follows:
，
wherein,for polarization direction characteristic image, +.>Is a polarization significant difference matrix->In->Individual element->The polarization direction distance is->Values of elements of>Is polarization difference matrix>For the distance in the current polarization direction, +.>Is the polarization direction.
Polarization salient feature imageThe positive effects are as follows: polarization saliency feature image->The distribution condition of the significant information of the polarized image in different directions is reflected more carefully, and the final polarized significant degree image is obtained.
In step S5, polarization salient feature images of different directions are calculated and obtainedThe formula of the corresponding weight coefficient is as follows:
，
in the method, in the process of the invention,is a polarization salient feature of different directionsImage->Corresponding weight coefficient, ++>，/>Is an iteration coefficient; />For no reference image quality evaluation, < >>For information entropy->Is the information entropy; />Balance coefficient of IQA, +.>Is the equilibrium coefficient of EN and,is a control constant.
In step S6, a polarization saliency image is calculated and obtainedComprising: changing the image with polarization saliency features in different polarization directions +.>Weighting is carried out to obtain a final polarization significance image, and the formula is as follows:
，
in the method, in the process of the invention,is polarized toSaliency image->An image of a change in polarization salient features; />Image for polarization salient feature change->Corresponding weight coefficient, ++>Image for polarization salient feature change->Corresponding weight coefficients.
Polarization saliency imageThe positive effects are as follows: polarization saliency image->The method can well reflect the importance degree of different areas in the polarized image, can fully highlight and detect object information in different scenes by utilizing the special attribute of the polarized imaging, and has a guiding effect on the follow-up target detection, segmentation and other advanced visual tasks.
Example 2, as another embodiment of the present invention, the polarization saliency calculation method provided by the example of the present invention includes:
step 1, acquiring a picture by using a polarization camera, and controlling the angle of a rotating polaroid to beObtaining polarized intensity image of corresponding angle>；
Step 2, for polarized intensity imagePerforming a solution to obtain a polarized parametric image +.>(as in FIG. 2) and->(as in figure 3);
，
，
step 3, calculating and obtainingAnd->Polarization difference image->；
，
In the method, in the process of the invention,for polarization difference image, +.>Pixel value +.>Corresponding pixel histogram, < >>For the length of the image->For the width of the image to be a wide,/>is polarization degree image->At->Pixel value at +.>For light intensity image +.>At->Pixel value at +.>Is polarization degree image->At->Pixel value at +.>For light intensity image +.>At->Values of pixels at>For pixel value, +.>For pixel coordinates, +.>Is the pixel point coordinates.
Step 4, calculating and obtainingPolarization significant difference matrix in direction->The method comprises the steps of carrying out a first treatment on the surface of the As shown in fig. 4-7;
image of polarization differenceAfter quantization to 8 grey levels +.>At->In the polarization direction, pixel point->The value of (2) and the pixel point larger than the value +.>The frequency of occurrence in pairs, thereby preserving the salient information in the image. Statistics of significant difference pixel pairs ++for each polarization direction>The frequency of occurrence is then compared with the total frequency of occurrence of all the significantly different pixel pairs to obtain the frequency of occurrence of each significantly different pixel pair in four different directions, and then arranged into a +.>Square matrix of size, i.e. polarization significance difference matrix +.>，/>。
，
，
In the method, in the process of the invention,is at->Polarization significance difference matrix in polarization direction>First->The value of the individual element(s),representation->The degree of difference of each polarization in the set is +.>Frequency of occurrence, ++>For pixel coordinates, +.>For the purpose of polarization difference image->Upper pixel +.>Is +.>Degree of polarization significant difference in target region pair +.>Is a set of (a) and (b),/>is pixel dot +.>Pixel value of>Is one of the polarization significant difference degree pairs, +.>Is the other of the polarization significant difference degree pair, +.>Is a polarized difference image->Upper pixel +.>At->Degree of significant contrast difference in polarization direction, +.>Respectively is->Polarization difference image in polarization direction->At->Gray values at that point.
Step 5, calculating and obtaining the polarization salient feature imageComprising: calculating each +.>Polarization significant difference matrix in target area +.>The polarization significant feature quantity of the (2) is calculated as follows:
，
wherein,for polarization direction characteristic image, +.>Is a polarization significant difference matrix->In->Individual element->The polarization direction distance is->Values of elements of>Is polarization difference matrix>For the distance in the current polarization direction, +.>Is the polarization direction.
Step 6, calculating polarization salient feature images in four directionsCorresponding weight coefficients; as shown in fig. 9;
calculating and obtaining polarization salient feature images in different directionsThe formula of the corresponding weight coefficient is as follows:
，
in the method, in the process of the invention,polarization salient feature image for different directions +.>Corresponding weight coefficient, ++>，/>Is an iteration coefficient; />For no reference image quality evaluation, < >>Entropy of information,,>is the information entropy; />Balance coefficient of IQA, +.>Balance coefficient of EN, +.>Is a control constant.
Step 7, calculating and obtaining polarization saliency imagesComprising: to be used forPolarization salient feature variation image in different polarization directions +.>Weighting is carried out to obtain a final polarization significance image, and the formula is as follows:
，
in the method, in the process of the invention,for polarized saliency image, ">An image of a change in polarization salient features; />Image for polarization salient feature change->Corresponding weight coefficient, ++>Image for polarization salient feature change->Corresponding weight coefficients.
Embodiment 3 as shown in fig. 10, the polarization saliency calculation system provided by the embodiment of the present invention includes:
a polarization difference image acquisition module 1 for calculating a polarization difference image from pixel differences between the light intensity image and the polarization degree image；
A polarization significant difference matrix acquisition module 2 for utilizing the polarization difference imageCalculating and obtaining polarization significant difference matrixes in different directions>，
A polarization salient feature image calculating module 3 for calculating a polarization salient feature image corresponding to each direction；
A polarization saliency image calculation module 4 for calculating each polarization saliency feature imageAfter the corresponding weight coefficient, finally obtaining polarization significance image +.>。
In the foregoing embodiments, the descriptions of the embodiments are emphasized, and in part, not described or illustrated in any particular embodiment, reference is made to the related descriptions of other embodiments.
The content of the information interaction and the execution process between the devices/units and the like is based on the same conception as the method embodiment of the present invention, and specific functions and technical effects brought by the content can be referred to in the method embodiment section, and will not be described herein.
It will be apparent to those skilled in the art that, for convenience and brevity of description, only the above-described division of the functional units and modules is illustrated, and in practical application, the above-described functional distribution may be performed by different functional units and modules according to needs, i.e. the internal structure of the apparatus is divided into different functional units or modules to perform all or part of the above-described functions. The functional units and modules in the embodiment may be integrated in one processing unit, or each unit may exist alone physically, or two or more units may be integrated in one unit, where the integrated units may be implemented in a form of hardware or a form of a software functional unit. In addition, the specific names of the functional units and modules are only for distinguishing from each other, and are not used for limiting the protection scope of the present invention. For specific working processes of the units and modules in the system, reference may be made to corresponding processes in the foregoing method embodiments.
Based on the technical solutions described in the embodiments of the present invention, the following application examples may be further proposed.
According to an embodiment of the present application, the present invention also provides a computer apparatus, including: at least one processor, a memory, and a computer program stored in the memory and executable on the at least one processor, which when executed by the processor performs the steps of any of the various method embodiments described above.
Embodiments of the present invention also provide a computer readable storage medium storing a computer program which, when executed by a processor, performs the steps of the respective method embodiments described above.
The embodiment of the invention also provides an information data processing terminal, which is used for providing a user input interface to implement the steps in the method embodiments when being implemented on an electronic device, and the information data processing terminal is not limited to a mobile phone, a computer and a switch.
The embodiment of the invention also provides a server, which is used for realizing the steps in the method embodiments when being executed on the electronic device and providing a user input interface.
Embodiments of the present invention also provide a computer program product which, when run on an electronic device, causes the electronic device to perform the steps of the method embodiments described above.
The integrated units, if implemented in the form of software functional units and sold or used as stand-alone products, may be stored in a computer readable storage medium. Based on such understanding, the present application implements all or part of the flow of the method of the above embodiments, and may be implemented by a computer program to instruct related hardware, where the computer program may be stored in a computer readable storage medium, where the computer program, when executed by a processor, may implement the steps of each of the method embodiments described above. Wherein the computer program comprises computer program code which may be in source code form, object code form, executable file or some intermediate form etc. The computer readable medium may include at least: any entity or device capable of carrying computer program code to a photographing device/terminal apparatus, recording medium, computer Memory, read-Only Memory (ROM), random access Memory (Random Access Memory, RAM), electrical carrier signals, telecommunications signals, and software distribution media. Such as a U-disk, removable hard disk, magnetic or optical disk, etc.
While the invention has been described with respect to what is presently considered to be the most practical and preferred embodiments, it is to be understood that the invention is not limited to the disclosed embodiments, but on the contrary, is intended to cover various modifications, equivalents, and alternatives falling within the spirit and scope of the invention.
Claims (10)
1. A method for calculating polarization saliency, the method comprising the steps of:
s1, acquiring polarized light images at four angles through a polarization camera, and obtaining a light intensity image through calculationAnd polarization degree image；
S2, calculating and obtaining a light intensity imageAnd polarization degree image->Polarization difference image->；
S3, calculating and obtaining polarization significant difference matrixes in different directions；
S4, calculating and obtaining a polarization salient feature image；
S5, calculating and obtaining polarization salient feature images in different directionsCorresponding weight coefficients;
s6, calculating and obtaining a polarization saliency image。
2. The polarization saliency calculation method according to claim 1, wherein in step S1, a light intensity image is obtained by the calculationAnd polarization degree image->Comprising:
polarized image acquisition using a cameraObtain->Polarized light intensity image of polarization direction, < >>The method comprises the steps of carrying out a first treatment on the surface of the Resolving to obtain light intensity image->And polarization degree image->；
Wherein,respectively representing four different polarization directions.
3. The polarization saliency calculation method according to claim 1, wherein in step S2, a light intensity image is calculated and obtainedAnd polarization degree image->Polarization difference image->Comprising:
image the degree of polarizationAnd light intensity image->Corresponding pixels in the image are calculated to obtain a polarized difference image +.>The calculation formula is as follows:
，
in the method, in the process of the invention,for polarization difference image, +.>For pixel value +.>Corresponding pixel histogram, < >>For the length of the image->Is the width of the image->Is polarization degree image->At->Pixel value at +.>For light intensity image +.>At->Pixel value at +.>Is polarization degree image->At->Pixel value at +.>For light intensity image +.>At->Values of pixels at>For pixel value, +.>For pixel coordinates, +.>Is the pixel point coordinates.
4. The polarization saliency calculation method of claim 1, wherein in step S3, polarization saliency difference matrices in different directions are calculated and obtainedComprising:
image of polarization differenceQuantized to->After several grey levels, a polarization difference image is recorded +.>At->Pixel point in polarization direction->The value of (2) and the pixel point larger than the value +.>The frequency of paired occurrence, the salient information in the image is reserved; statistics of significant difference pixel pairs ++for each polarization direction>The frequency of occurrence is compared with the total frequency of occurrence of all the significant difference pixel pairs to obtain the frequency of occurrence of each significant difference pixel pair in four different directions, which is arranged into a +.>Square matrix of size, which is a polarization significant difference matrix +.>，/>，/>Respectively representing four different polarization directions.
5. The polarization saliency calculation method of claim 4, wherein a polarization saliency difference matrixThe calculation formula of (2) is as follows:
，
，
in the method, in the process of the invention,is at->Polarization significance difference matrix in polarization direction>First->The value of the individual element(s),representation->The degree of difference of each polarization in the set is +.>Frequency of occurrence, ++>For pixel coordinates, +.>For the purpose of polarization difference image->Upper pixel +.>Is +.>Degree of polarization significant difference in target region pair +.>Set of->Is pixel dot +.>Pixel value of>Is one of the polarization significant difference degree pairs, +.>Is the other of the polarization significant difference degree pair, +.>Is a polarized difference image->Upper pixel +.>At->Degree of significant contrast difference in polarization direction, +.>Respectively is->Polarization difference image in polarization direction->At->Gray values at that point.
6. The polarization saliency calculation method according to claim 1, wherein in step S4, a polarization saliency feature image is calculated and obtainedComprising: calculate the whole widthEach +.>Polarization significant difference matrix in target area +.>The polarization significant feature quantity of the (2) is calculated as follows:
，
in the method, in the process of the invention,for polarization direction characteristic image, +.>Is polarization difference matrix>For the distance in the current polarization direction, +.>Is polarization direction +.>Is a polarization significant difference matrix->In->Individual element->The polarization direction distance is->Is a value of an element of (a).
7. The polarization saliency calculation method of claim 1, wherein in step S5, polarization saliency feature images of different directions are calculated and obtainedThe formula of the corresponding weight coefficient is as follows:
，
in the method, in the process of the invention,polarization salient feature image for different directions +.>Corresponding weight coefficient, ++>，/>Respectively iteration coefficients; />For no reference image quality evaluation, < >>Entropy of information,,>is the information entropy; />Balance coefficient of IQA, +.>Balance coefficient of EN, +.>Is a control constant.
8. The polarization saliency calculation method according to claim 1, wherein in step S6, a polarization saliency image is calculated and obtainedComprising: changing the image with polarization saliency features in different polarization directions +.>Weighting is carried out to obtain a final polarization significance image, and the formula is as follows:
，
in the method, in the process of the invention,for polarized saliency image, ">An image of a change in polarization salient features; />Image for polarization salient feature change->Corresponding weight coefficients.
9. A polarization saliency calculation system, wherein the system implements the polarization saliency calculation method of any one of claims 1 to 8, the system comprising:
a polarization difference image acquisition module (1) for calculating a polarization difference from a pixel difference between the light intensity image and the polarization degree imageImage processing apparatus；
A polarization significant difference matrix acquisition module (2) for utilizing the polarization difference imageCalculating and obtaining polarization significant difference matrixes in different directions>，
A polarization salient feature image calculation module (3) for calculating a polarization salient feature image corresponding to each direction；
A polarization saliency image calculation module (4) for calculating each polarization saliency feature imageAfter the corresponding weight coefficient, finally obtaining polarization significance image +.>。
10. The polarization saliency calculation system according to claim 9, wherein the system is mounted on an image recognition instrument in the fields of object recognition and remote sensing detection, and is used for detecting an image saliency area.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202311326353.6A CN117372678A (en) | 2023-10-13 | 2023-10-13 | Polarization significance calculating method and system |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202311326353.6A CN117372678A (en) | 2023-10-13 | 2023-10-13 | Polarization significance calculating method and system |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN117372678A true CN117372678A (en) | 2024-01-09 |
Family
ID=89388609
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202311326353.6A Pending CN117372678A (en) | 2023-10-13 | 2023-10-13 | Polarization significance calculating method and system |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN117372678A (en) |
-
2023
- 2023-10-13 CN CN202311326353.6A patent/CN117372678A/en active Pending
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| US11570423B2 (en) | System and methods for calibration of an array camera | |
| CN110717942B (en) | Image processing method and device, electronic equipment and computer readable storage medium | |
| JP4950290B2 (en) | Imaging apparatus, method, system integrated circuit, and program | |
| JP4772839B2 (en) | Image identification method and imaging apparatus | |
| RU2647670C1 (en) | Automated methods and systems of identifying image fragments in document-containing images to facilitate extraction of information from identificated document-containing image fragments | |
| US9007490B1 (en) | Approaches for creating high quality images | |
| KR101524548B1 (en) | Apparatus and method for alignment of images | |
| Finlayson | Colour and illumination in computer vision | |
| EP3093822B1 (en) | Displaying a target object imaged in a moving picture | |
| US20130170756A1 (en) | Edge detection apparatus, program and method for edge detection | |
| Bianco et al. | Robust smile detection using convolutional neural networks | |
| CN110120012B (en) | Video stitching method for synchronous key frame extraction based on binocular camera | |
| CN112102404B (en) | Object detection tracking method and device and head-mounted display equipment | |
| Wang et al. | LBP-based edge detection method for depth images with low resolutions | |
| CN117372678A (en) | Polarization significance calculating method and system | |
| Zhou et al. | On contrast combinations for visual saliency detection | |
| CN117726666B (en) | Cross-camera monocular picture measurement depth estimation method, device, equipment and medium | |
| CN116416251B (en) | Method and related device for detecting quality of whole-core flame-retardant conveying belt based on image processing | |
| WO2022253043A1 (en) | Facial deformation compensation method for facial depth image, and imaging apparatus and storage medium | |
| CN113706429B (en) | Image processing method, device, electronic equipment and storage medium | |
| CN117115488B (en) | Water meter detection method based on image processing | |
| US11232314B2 (en) | Computer vision based approach to image injection detection | |
| Bi et al. | Multi-object Paper Money Recognition Technology Based on AlexNet Model | |
| Wei et al. | Research on Abnormal Target Recognition of Full Information Mobile Monitoring Based on Machine Vision | |
| Yu et al. | Beijing, China |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication |