CN113763361A - Infrared image processing method and device for improving human eye identification degree and storage medium - Google Patents
Infrared image processing method and device for improving human eye identification degree and storage medium Download PDFInfo
- Publication number
- CN113763361A CN113763361A CN202111051956.0A CN202111051956A CN113763361A CN 113763361 A CN113763361 A CN 113763361A CN 202111051956 A CN202111051956 A CN 202111051956A CN 113763361 A CN113763361 A CN 113763361A
- Authority
- CN
- China
- Prior art keywords
- images
- infrared image
- human eye
- gray
- sub
- 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
- 238000003672 processing method Methods 0.000 title claims abstract description 30
- 238000013507 mapping Methods 0.000 claims abstract description 25
- 210000001525 retina Anatomy 0.000 claims abstract description 22
- 230000011218 segmentation Effects 0.000 claims abstract description 22
- 238000012545 processing Methods 0.000 claims abstract description 16
- 238000004364 calculation method Methods 0.000 claims abstract description 14
- 230000006870 function Effects 0.000 claims description 40
- 238000006073 displacement reaction Methods 0.000 claims description 10
- 238000010606 normalization Methods 0.000 claims description 3
- 238000000034 method Methods 0.000 abstract description 36
- 230000000007 visual effect Effects 0.000 description 10
- 238000012937 correction Methods 0.000 description 6
- 230000000694 effects Effects 0.000 description 6
- 238000010586 diagram Methods 0.000 description 5
- 238000001931 thermography Methods 0.000 description 5
- 230000003044 adaptive effect Effects 0.000 description 4
- 230000008569 process Effects 0.000 description 4
- 241001270131 Agaricus moelleri Species 0.000 description 3
- 230000009471 action Effects 0.000 description 3
- 238000003384 imaging method Methods 0.000 description 3
- 238000007781 pre-processing Methods 0.000 description 3
- 206010025421 Macule Diseases 0.000 description 2
- 230000009286 beneficial effect Effects 0.000 description 2
- 210000004556 brain Anatomy 0.000 description 2
- 238000006243 chemical reaction Methods 0.000 description 2
- 238000004590 computer program Methods 0.000 description 2
- 230000002708 enhancing effect Effects 0.000 description 2
- 230000010354 integration Effects 0.000 description 2
- 210000003205 muscle Anatomy 0.000 description 2
- 210000001328 optic nerve Anatomy 0.000 description 2
- 238000003491 array Methods 0.000 description 1
- 238000004422 calculation algorithm Methods 0.000 description 1
- 150000001875 compounds Chemical class 0.000 description 1
- 235000019800 disodium phosphate Nutrition 0.000 description 1
- 238000005516 engineering process Methods 0.000 description 1
- 230000007613 environmental effect Effects 0.000 description 1
- 238000009499 grossing Methods 0.000 description 1
- 230000006872 improvement Effects 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 235000001968 nicotinic acid Nutrition 0.000 description 1
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T7/00—Image analysis
- G06T7/0002—Inspection of images, e.g. flaw detection
- G06T7/0012—Biomedical image inspection
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T3/00—Geometric image transformations in the plane of the image
- G06T3/40—Scaling of whole images or parts thereof, e.g. expanding or contracting
- G06T3/4038—Image mosaicing, e.g. composing plane images from plane sub-images
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T5/00—Image enhancement or restoration
- G06T5/70—Denoising; Smoothing
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T5/00—Image enhancement or restoration
- G06T5/90—Dynamic range modification of images or parts thereof
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T7/00—Image analysis
- G06T7/10—Segmentation; Edge detection
- G06T7/11—Region-based segmentation
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T2200/00—Indexing scheme for image data processing or generation, in general
- G06T2200/32—Indexing scheme for image data processing or generation, in general involving image mosaicing
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T2207/00—Indexing scheme for image analysis or image enhancement
- G06T2207/10—Image acquisition modality
- G06T2207/10048—Infrared image
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T2207/00—Indexing scheme for image analysis or image enhancement
- G06T2207/30—Subject of image; Context of image processing
- G06T2207/30004—Biomedical image processing
- G06T2207/30041—Eye; Retina; Ophthalmic
Landscapes
- Engineering & Computer Science (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Theoretical Computer Science (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Health & Medical Sciences (AREA)
- General Health & Medical Sciences (AREA)
- Medical Informatics (AREA)
- Nuclear Medicine, Radiotherapy & Molecular Imaging (AREA)
- Radiology & Medical Imaging (AREA)
- Quality & Reliability (AREA)
- Image Processing (AREA)
Abstract
The application relates to an infrared image processing method, an infrared image processing device and a storage medium for improving the identification degree of human eyes, wherein the method comprises the steps of carrying out region segmentation on an original infrared image according to the field area of a fovea region of the retina of the human eyes and the distance between the human eyes and a display device to obtain a plurality of region sub-images; classifying the regional sub-images according to the gray distribution, and respectively performing gray integral calculation, gate function modulation and gray information distribution adjustment on each type of regional sub-images to generate sub-images to be spliced; and splicing the sub-images to be spliced, and performing nonlinear gray value mapping on the spliced images to obtain the infrared enhanced image with higher human eye identification degree. The method can improve the human eye identification degree of the infrared image and meet the human eye observation requirement.
Description
Technical Field
The present application relates to the field of infrared image processing technologies, and in particular, to an infrared image processing method and apparatus for improving human eye recognition, and a storage medium.
Background
The infrared image often has the characteristics of poor local contrast, large noise, dark overall, easy loss of details and the like. The gray scale statistical characteristics of the infrared image show that most of the gray scales of the infrared image are concentrated in the range of adjacent gray scales, the layering sense is poor, and the target finding by human eyes is not facilitated.
Although the traditional image enhancement methods such as adaptive histogram equalization and histogram equalization for limiting contrast can improve the contrast to a certain extent, the additional noise is large, the bright and dark sense of the central area of the image has obvious deviation with the four corners of the image, and the visual sense effect of the infrared image is poor, so that improvement is needed.
Disclosure of Invention
In order to solve the technical problems mentioned in the background art or at least partially solve the technical problems, the present application provides an infrared image processing method, an infrared image processing apparatus, and a storage medium for improving the human eye recognition level, which can improve the human eye recognition level of an infrared image and meet the human eye observation requirements.
In a first aspect, the present application provides an infrared image processing method for improving human eye identification, including:
according to the field area of a fovea region of a retina of a human eye and the distance between the human eye and display equipment, carrying out region segmentation on an original infrared image to obtain a plurality of region sub-images;
classifying the regional sub-images according to the gray distribution, and respectively performing gray integral calculation, gate function modulation and gray information distribution adjustment on each type of regional sub-images to generate sub-images to be spliced;
and splicing the sub-images to be spliced, and performing nonlinear gray value mapping on the spliced images to obtain the infrared enhanced image with higher human eye identification degree.
In this aspect, before performing region segmentation on the original infrared image according to the field area of the fovea region of the retina of the human eye and the distance between the human eye and the display device, the method can further include: and acquiring an original infrared image. The original infrared image can be an infrared thermal imaging image, and an infrared thermal imaging visual product (such as an infrared detector) converts an infrared light signal into an electric signal and then forms the original infrared image after digital-to-analog conversion.
In this aspect, after acquiring the original infrared image, before performing region segmentation on the original infrared image according to the field area of the foveal region of the retina of the human eye and the distance between the human eye and the display device, the method can further include: the original infrared image is preprocessed, and the preprocessing can refer to non-uniformity correction of the original infrared image.
In this embodiment, after obtaining the infrared-enhanced image with higher human eye identification, the method further includes: and outputting the infrared enhanced image. Specifically, the infrared-enhanced image is displayed by a display device.
In the scheme, the original infrared image is subjected to region segmentation by utilizing the imaging characteristics of human eyes (a fovea region, also called a macular region, exists in the retina of the human eyes, most of optic nerves are positioned at the fovea region, the fovea region is imaged as a gazing region, other parts of the retina are imaged as a residual light region, the macular region can scan the whole interesting visual field through the dragging of eye muscles, the whole interesting visual field is finally formed by the aid of the light and shade self-adaption capability of a visual system and a tracking and splicing system of a brain, the integral visual image system of the human eyes has the splicing property, the scanning property and the local high contrast property), different distances of comfortable pictures of the human eyes of different display equipment (namely the distance between the human eyes and the display equipment) are convenient for the human eyes to see the original infrared image, the segmented regions are classified according to the gray scale distribution condition, different gate functions of gray scale integration and adaptive modulation displacement are respectively carried out on different types of sub-images, and the gray scale information distribution adjustment is carried out to generate the sub-images to be spliced, the method can correspondingly adjust different types of sub-images to proper gray values, and can improve the contrast ratio and avoid the loss of details and reduce the additional noise by considering the human eye recognition degree while enhancing the images.
Preferably, the segmenting of the original infrared image according to the field area corresponding to the fovea region of the retina of the human eye and the distance between the human eye and the display device specifically includes:
the region segmentation formula is as follows:
where C denotes the number of region divisions, D denotes the linearity of the infrared image presented on the device, DfovLine degree of fovea region on retina of human eye, leyeIndicating the eye axis length, L the distance of the human eye from the display device in the comfortable position, and brackets indicating rounding down.
In the scheme, different display devices display different images, and the distance between the display devices and human eyes is considered during region segmentation, so that the requirement for observing the human eyes can be favorably met.
Preferably, classifying the plurality of the area sub-images according to the gray scale distribution specifically includes:
and calculating the gray level mean value and the gray level standard deviation of each regional sub-image, and classifying the regional sub-images according to the gray level mean value and the gray level standard deviation.
In the scheme, the area sub-images are classified by calculating the gray mean value and the gray standard difference value of the sub-images, so that the area segmentation and classification of different gray information of the infrared original image can be realized, different image processing modes are adopted for the different types of sub-images, and the image processing is more accurate compared with the direct integral unified processing of the original infrared image.
Preferably, classifying the region sub-images according to the mean grayscale value and the standard grayscale difference specifically includes:
if the gray level mean value is determined to be higher than a first preset gray level mean value, classifying the area sub-images into a class of object area sub-images, wherein the class of objects comprises a first class of targets with temperature in a near field;
if the gray mean value is lower than a second preset gray mean value, classifying the area subimages into two types of object area subimages, wherein the two types of objects comprise second type targets with higher temperature in a far field;
and if the gray standard deviation is determined to be larger than the preset standard deviation, classifying the area sub-images into three types of object area sub-images, wherein the three types of objects comprise cold backgrounds.
In the scheme, each area is judged according to the gray distribution characteristics of the sub-images of each area, and the sub-images are classified into a first-class object area, a second-class object area and the like. One type of object includes near-field objects with temperature, a second type of object, such as far-field objects with higher temperature, and a third type of object area, mainly a cold background area.
Preferably, the gray scale integral calculation, gate function modulation, and gray scale information distribution adjustment are performed on each type of the area sub-images respectively to generate sub-images to be spliced, and the method specifically includes:
counting the gray value information of the area sub-images to obtain the number f of each gray value information0(i) And integrated to obtain S0(i)，S0(i) Is f0(i) The calculation formula is as follows:
will S0(i) Transformed to S according with human eye resolution law1(i) The calculation formula is as follows:
m and N represent the number of length pixels and the number of width pixels of an original infrared image, L represents the number of available gray levels, and int represents an integer function;
will S1(i) Obtaining f after finding the difference1(i) Using a shift gate function gt,w(j) To f1(i) Modulating the function, and normalizing to obtain f2(i)，S2(i) Is f2(i) Is given by the formula:
wherein the Norm function is a normalization function, a shift gate function gt,w(j) The standard gate function is obtained after displacement and stretching, t represents displacement, w represents stretching amount, and the specific values of t and w are determined by the gray level distribution of the regional sub-images;
according to S2(i) And f2(i) And changing the gray information distribution of the sub-images of the regions to meet the observation requirement of human eyes.
Preferably, the sub-images to be spliced are spliced by adopting two-dimensional linear mapping.
In the scheme, the sub-images to be spliced are spliced by adopting two-dimensional linear mapping, so that the edge smoothness can be kept.
Preferably, a Log function is adopted to perform nonlinear mapping on the pixel gray value of the spliced image, and the formula is as follows:
wherein, σ (x, y) is the gray value output by the pixel point, and n is obtained by counting the gray information of the original infrared image.
Preferably, before performing region segmentation on the original infrared image according to the field area of the fovea region of the retina of the human eye and the distance between the human eye and the display device, the method further comprises the following steps: and performing linear stripe noise removal and nonlinear noise point compensation on the original infrared image.
In the scheme, the original infrared image is preprocessed before the region is divided, so that the image processing effect is improved.
In a second aspect, the present application further provides an infrared image processing apparatus for improving human eye recognition, including:
a memory for storing program instructions;
a processor, configured to invoke the program instructions stored in the memory to implement the infrared image processing method for improving human eye identification according to any one of the technical solutions of the first aspect.
In a third aspect, the present application further provides a computer-readable storage medium, where a program code is stored, and the program code is used to implement the infrared image processing method for improving human eye identification according to any one of the technical solutions in the first aspect.
Compared with the prior art, the technical scheme provided by the embodiment of the application has the following advantages: the method comprises dividing original infrared image into regions based on central fovea region field area and distance between human eyes and display device to obtain multiple regional sub-images, then classifying according to the gray distribution characteristics of the sub-images of the regions to obtain a first class object region sub-image, a second class object region sub-image and a third class object region sub-image, respectively carrying out gray scale integration, gate function modulation and gray scale information adjustment on a first class target with temperature in a near field, a second class target with higher temperature in a far field and a cold background of an original infrared image, adjusting the gray scale information to meet the requirement of human eye observation more accurately, and then smoothly splicing all the areas by adopting a two-dimensional linear mapping method, and finally performing one-time nonlinear gray value mapping on the spliced image by using a Log function to obtain an infrared enhanced image with higher human eye identification degree.
The method combines the characteristics of the gray level distribution of the infrared image, fully considers the characteristics of human eye imaging and the difference of distances which are convenient for human eyes to observe comfortably by different display devices, performs adaptive region segmentation on the original infrared image, further realizes adaptive gray level distribution adjustment on different targets and backgrounds of the original infrared image, enables the original infrared image to meet the requirement of human eye observation better, performs smooth splicing of two-dimensional linear mapping and nonlinear gray level mapping of a Log function on the adjusted image to be spliced, and achieves the effects of improving the human eye identification degree and enhancing the image.
Drawings
The accompanying drawings, which are incorporated in and constitute a part of this specification, illustrate embodiments consistent with the invention and together with the description, serve to explain the principles of the invention.
In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the drawings used in the description of the embodiments or the prior art will be briefly described below, and it is obvious for those skilled in the art that other drawings can be obtained according to the drawings without inventive exercise.
Fig. 1 is a schematic flowchart of an infrared image processing method for improving human eye identification according to an embodiment of the present disclosure.
Fig. 2 is a schematic diagram of the principle of the infrared image processing method for improving human eye recognition.
Fig. 3 is a schematic structural diagram of an infrared image processing device for improving human eye recognition.
Fig. 4 is a gray scale statistical distribution diagram of the preprocessed original infrared image.
Fig. 5 is a gray scale statistical distribution diagram of an image processed by the infrared image processing method for improving human eye identification provided in the embodiment of the present application.
Fig. 6 is a raw infrared image after preprocessing.
Fig. 7 is an image processed by the infrared image processing method for improving human eye identification provided in the embodiment of the present application.
Detailed Description
In order to make the objects, technical solutions and advantages of the embodiments of the present application clearer, 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 some embodiments of the present application, but not all 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 convenience of understanding, the following describes in detail an infrared image processing method, an infrared image processing apparatus, and a storage medium for improving human eye identification provided in an embodiment of the present application, and with reference to fig. 1, an infrared image processing method for improving human eye identification includes the following steps:
step S1, according to the field area of the fovea of the retina of the human eye and the distance between the human eye and the display device, carrying out region segmentation on the original infrared image to obtain a plurality of region sub-images;
step S2, classifying the area sub-images according to the gray distribution, and respectively performing gray integral calculation, gate function modulation and gray information distribution adjustment on each type of area sub-images to generate sub-images to be spliced;
and step S3, splicing the sub-images to be spliced, and carrying out nonlinear gray value mapping on the spliced images to obtain the infrared enhanced image with higher human eye identification degree.
In some embodiments of the present application, before performing the region segmentation on the original infrared image according to the field of view area of the foveal region of the retina of the human eye and the distance between the human eye and the display device, the method can further include: and acquiring an original infrared image. The original infrared image can be an infrared thermal imaging image, and an infrared thermal imaging visual product (such as an infrared detector) converts an infrared light signal into an electric signal and then forms the original infrared image after digital-to-analog conversion.
In some embodiments of the present application, after acquiring the original infrared image, before performing region segmentation on the original infrared image according to a field area of a foveal region of a retina of a human eye and a distance between the human eye and the display device, the method can further include: the original infrared image is preprocessed, and the preprocessing can refer to non-uniformity correction of the original infrared image.
In some embodiments of the present application, after obtaining the infrared-enhanced image with higher human eye identification, the method further comprises: and outputting the infrared enhanced image. Specifically, the infrared-enhanced image is displayed by a display device.
In some embodiments of the present application, the original infrared image is segmented by using the imaging characteristics of the human eye (the human eye retina has a fovea area, also called macula area, where most of the optic nerve is located, the fovea area is imaged as the fixation area, and other parts of the retina are imaged as the residual light area), the macula area can scan the whole interesting visual field by the dragging of the eye muscles, and the creation of the whole visual image of the object is finally formed by the light and shade self-adapting capability of the visual system and the tracking and splicing system of the brain Different displacement gate functions are adaptively modulated and gray information distribution is adjusted to generate images to be spliced, different types of sub-images can be correspondingly adjusted to appropriate gray values, human eye recognition degree is considered while the images are enhanced, details are prevented from being lost while contrast is improved, and additional noise is reduced.
In some specific embodiments of the present application, segmenting the original infrared image according to a field area corresponding to a fovea region of a retina of a human eye and a distance between the human eye and the display device specifically includes:
the region segmentation formula is as follows:
where C denotes the number of region divisions, D denotes the linearity of the infrared image presented on the device, DfovLine degree of fovea region on retina of human eye, leyeIndicating the length of the axis of the eye, L indicating the comfortThe distance between the eyes of the person in position and the display device, the square brackets indicating rounding down.
In some embodiments of the present application, different display devices display different images, and the distance between the display device and human eyes is considered during region segmentation, which is beneficial to meeting the requirement of human eyes for observation.
In some embodiments of the present application, classifying the plurality of region sub-images according to the gray-scale distribution specifically includes:
and calculating the gray level mean value and the gray level standard deviation of each regional sub-image, and classifying the regional sub-images according to the gray level mean value and the gray level standard deviation.
In some embodiments of the present application, the classification of the sub-images in each region is performed by calculating the gray level mean value and the gray level standard difference value of the sub-images, so that the region segmentation and classification of different gray level information of the infrared original image can be performed, and thus, different image processing methods are applied to the sub-images in different classes, and the image processing is more accurate compared with the direct unified processing of the original infrared image as a whole.
In some embodiments of the present application, classifying the region sub-images according to the mean grayscale value and the standard grayscale difference specifically includes:
if the gray level mean value is higher than a first preset gray level mean value, classifying the area sub-images into object area sub-images of one class, wherein the object of one class comprises a first class target with temperature in a near field;
if the gray average value is lower than a second preset gray average value, classifying the area subimages into second class object area subimages, wherein the second class objects comprise second class targets with higher temperature in a far field;
and if the gray standard deviation is determined to be larger than the preset standard deviation, classifying the area sub-images into three types of object area sub-images, wherein the three types of object areas comprise cold backgrounds.
In some embodiments of the present application, the determination is performed on each region based on the gray scale distribution characteristics of the sub-image of each region, and the regions are classified into a first-class object region, a second-class object region, and the like. One type of object includes near-field objects with temperature, a second type of object, such as far-field objects with higher temperature, and a third type of object area, mainly a cold background area.
In some embodiments of the present application, the classification of the region sub-images is based on the gray scale division of the original data in the divided regions, and the mean and standard deviation of the gray scale data in each region need to be counted. The temperature is higher, and the average value of the display gray scale of the object close to the temperature is high; the temperature is low, and the average value of the display gray scales of objects close to each other is low; the standard deviation of the display gray level of the boundary area is large.
In some specific embodiments of the present application, the performing gray scale integral calculation, gate function modulation, and gray scale information distribution adjustment on each type of the area sub-images respectively to generate sub-images to be spliced specifically includes:
counting the gray value information of the regional sub-images to obtain the number f of each gray value information0(i) And integrated to obtain S0(i)，S0(i) Is f0(i) The calculation formula is as follows:
will S0(i) Transformed to S according with human eye resolution law1(i) The calculation formula is as follows:
wherein, M and N represent the length pixel number and the width pixel number of the original infrared image, L represents the available gray level number, and int represents the integer function.
Will S1(i) Obtaining f after finding the difference1(i) Using a shift gate function gt,w(j) To f1(i) Modulating the function, and normalizing to obtain f2(i)，S2(i) Is f2(i) Is given by the formula:
wherein the Norm function is a normalization function, a shift gate function gt，w(j) The standard gate function is obtained after displacement and stretching, t represents displacement, w represents stretching amount, and the specific values of t and w are determined by the gray level distribution of the regional sub-images;
according to S2(i) And f2(i) Changing the gray scale information distribution of the sub-images of the respective regions (specifically, according to the input gray scale distribution and S)2(i) And f2(i) And determining the mapping relation from the original infrared image to the image with changed gray information. Because the image contrast of the multi-concave area is enhanced, the image after gray level adjustment meets the requirement of human eye observation.
In some embodiments of the present application, the sub-images to be stitched are stitched using a two-dimensional linear mapping.
The two-dimensional linear mapping has a smoothing effect on the edge line and the critical point, and satisfies the following conditions in the edge area:
in the formula (x)1,y1),(x2,y1),(x1,y2),(x2,y2) Is not at the boundary and the known gray scale is f (x)1,y1),f(x2,y1),f(x1,y2),f(x2,y2) The (x, y) is the pixel point to be solved on the edge line or the critical point.
In some embodiments of the present application, the two-dimensional linear mapping is used to splice the sub-images to be spliced, so that the edges can be kept smooth.
In some embodiments of the present application, a Log function is used to perform nonlinear mapping on pixel gray-scale values of a spliced image, and the formula is as follows:
wherein, σ (x, y) is the gray value output by the pixel point, and n is obtained by counting the gray value number information of the original infrared image.
In some embodiments of the present application, before performing the region segmentation on the original infrared image according to the field area of the fovea region of the retina of the human eye and the distance between the human eye and the display device, the method further includes: and performing linear stripe noise removal and nonlinear noise point compensation on the original infrared image.
As described in conjunction with the above embodiments, before performing region segmentation on the original infrared image, the method further includes: carrying out non-uniformity correction on the original infrared image, wherein the non-uniformity correction can comprise linear fringe noise removal and non-linear noise point compensation, and the formula is as follows:
in the formula (I), the compound is shown in the specification,
is the non-uniformity corrected gray value at (i, j),
is the gray value before the non-uniformity correction. Linear noise with offset VijSum gain UijTwo parameters, which can be corrected by a two-point method. The nonlinear noise point information cannot be corrected, and a noise method is generally covered by a two-point compensation method.
In some embodiments of the present application, the original infrared image is preprocessed before the region is divided, which is beneficial to improving the image processing effect.
For easy understanding, referring to fig. 2, the overall process and principle of the infrared image processing method for improving human eye identification provided by the present application are described, including:
the infrared detector obtains an original image (namely, the infrared thermal imaging device obtains an original infrared image);
carrying out non-uniformity correction (including linear stripe noise removal and non-linear noise point compensation) on the original image; as an example, the preprocessed original infrared image is shown in fig. 6, and the gray scale statistical distribution map of the preprocessed original infrared image is shown in fig. 4;
according to the scanning characteristics of the fovea region of the retina of the human eye, carrying out image region segmentation;
area identification: based on the gray scale distribution characteristics of each region, each region is determined and classified into a first-class object region (i.e., a first-class object region sub-image in the above-described embodiment), a second-class object region (i.e., a second-class object region sub-image in the above-described embodiment), and so on. Common object types include near-field temperature targets, two object types such as far-field temperature targets, and three object types with cold background regions.
Counting the gray information of each region to obtain the occurrence frequency f of each gray value0(i) And integrating it to obtain S0(i) I.e. integrating the gray distribution of the first class object region, integrating the gray distribution of the second class object region, etc. The calculation formula is described in the above embodiments, and is not described herein again;
respectively carrying out gate function modulation on each region (namely, a displacement gate function corresponding to the sub-image modulation of each type of region);
the information distribution is changed for each region (i.e. according to S)2(i) And f2(i) Changing the gray information distribution of each region to meet the observation requirement of human eyes);
splicing and fusing the images of all the areas by adopting two-dimensional linear mapping, and keeping the edges smooth;
and (3) carrying out nonlinear mapping by adopting a Log function (specifically, carrying out nonlinear mapping on pixel gray values of the spliced images by adopting the Log function), and displaying. The finally displayed image (i.e., the infrared enhanced image described in the above embodiment) has excellent human eye recognition, and compared with the conventional image mapping method, the method has the characteristics of low additional noise, strong environmental adaptability, high algorithm operation efficiency and the like. As described in the foregoing example, the image processed by the infrared image processing method for improving human eye identification provided in the embodiment of the present application refers to fig. 7, and the gray scale statistical distribution diagram of the image processed by the infrared image processing method for improving human eye identification provided in the embodiment of the present application refers to fig. 5.
In still other embodiments of the present application, referring to fig. 3, there is also provided an infrared image processing apparatus 100 for improving human eye recognition, including:
a memory 200 for storing program instructions;
a processor 300 for calling the program instructions stored in the memory to implement the infrared image processing method for improving the human eye identification as any one of the above embodiments.
The apparatus may be configured to execute the method provided by the corresponding method embodiment, and the specific implementation manner and the technical effect are similar and will not be described herein again.
The processor may be configured as one or more integrated circuits implementing the above method, for example: one or more Application Specific Integrated Circuits (ASICs), or one or more microprocessors (DSPs), or one or more Field Programmable Gate Arrays (FPGAs), among others. As another example, the processor may be a general-purpose processor, such as a Central Processing Unit (CPU) or other processor capable of invoking program code. For another example, these modules may be integrated together and implemented in the form of a system-on-a-chip (SOC).
Further, a computer program is stored in the memory and configured to be executed by the processor, the computer program comprising instructions for performing the method as in any of the embodiments above.
In still other embodiments of the present application, a computer-readable storage medium is further provided, where the computer-readable storage medium stores program codes for implementing the infrared image processing method for improving human eye identification as in any one of the above embodiments.
Compared with the prior art, the technical scheme provided by the embodiment of the application has the following advantages:
the method is based on the principle of bionics, simulates the scanning, reconstruction and splicing of human eyes to the image, and realizes the presentation of the infrared image with high identification degree. The method comprises the steps of dividing an original infrared image into regions according to the field area of a central concave region and the distance between human eyes and display equipment, classifying the regions according to the gray distribution of each region, integrating gray information, modulating and mapping different displacement gate functions, rationalizing the information distribution in sub-images of each region, smoothly splicing each region by adopting a two-dimensional linear mapping method, and performing nonlinear gray value mapping on the image by using a Log function, so that the finally obtained infrared enhanced image has excellent human eye identification degree.
It is noted that, in this document, relational terms such as "first" and "second," and the like, may be used solely to distinguish one entity or action from another entity or action without necessarily requiring or implying any actual such relationship or order between such entities or actions. Also, the terms "comprises," "comprising," or any other variation thereof, are intended to cover a non-exclusive inclusion, such that a process, method, article, or apparatus that comprises a list of elements does not include only those elements but may include other elements not expressly listed or inherent to such process, method, article, or apparatus. Without further limitation, an element defined by the phrase "comprising an … …" does not exclude the presence of other identical elements in a process, method, article, or apparatus that comprises the element.
The foregoing are merely exemplary embodiments of the present invention, which enable those skilled in the art to understand or practice the present invention. Various modifications to these embodiments will be readily apparent to those skilled in the art, and the generic principles defined herein may be applied to other embodiments without departing from the spirit or scope of the invention. Thus, the present invention is not intended to be limited to the embodiments shown herein but is to be accorded the widest scope consistent with the principles and novel features disclosed herein.
Claims (10)
1. An infrared image processing method for improving the identification degree of human eyes is characterized by comprising the following steps:
according to the field area of a fovea region of a retina of a human eye and the distance between the human eye and display equipment, carrying out region segmentation on an original infrared image to obtain a plurality of region sub-images;
classifying the regional sub-images according to the gray distribution, and respectively performing gray integral calculation, gate function modulation and gray information distribution adjustment on each type of regional sub-images to generate sub-images to be spliced;
and splicing the sub-images to be spliced, and performing nonlinear gray value mapping on the spliced images to obtain the infrared enhanced image with higher human eye identification degree.
2. The infrared image processing method for improving human eye identification according to claim 1, wherein segmenting the original infrared image according to the field area corresponding to the fovea region of the retina of the human eye and the distance between the human eye and the display device specifically comprises:
the region segmentation formula is as follows:
where C denotes the number of region divisions, D denotes the linearity of the infrared image presented on the device, DfovLine degree of fovea region on retina of human eye, leyeIndicating the eye axis length, L the distance of the human eye from the display device in the comfortable position, and brackets indicating rounding down.
3. The infrared image processing method for improving human eye recognition according to claim 1, wherein classifying the plurality of region sub-images according to gray scale distribution specifically comprises:
and calculating the gray level mean value and the gray level standard deviation of each regional sub-image, and classifying the regional sub-images according to the gray level mean value and the gray level standard deviation.
4. The infrared image processing method for improving human eye recognition according to claim 3, wherein classifying the region sub-images according to the mean grayscale value and the standard grayscale difference specifically comprises:
if the gray level mean value is determined to be higher than a first preset gray level mean value, classifying the area sub-images into a class of object area sub-images, wherein the class of objects comprises a first class of targets with temperature in a near field;
if the gray mean value is lower than a second preset gray mean value, classifying the area subimages into two types of object area subimages, wherein the two types of objects comprise second type targets with higher temperature in a far field;
and if the gray standard deviation is determined to be larger than the preset standard deviation, classifying the area sub-images into three types of object area sub-images, wherein the three types of object areas comprise cold backgrounds.
5. The infrared image processing method for improving human eye identification according to any one of claims 1, 2 or 4, wherein performing gray scale integral calculation, gate function modulation and gray scale information distribution adjustment on each type of region sub-image to generate sub-images to be spliced specifically comprises:
counting the gray value information of the area sub-images to obtain the number f of each gray value information0(i) And integrated to obtain S0(i)，S0(i) Is f0(i) The calculation formula is as follows:
will S0(i) Transformed to S according with human eye resolution law1(i) The calculation formula is as follows:
m and N represent the number of length pixels and the number of width pixels of an original infrared image, L represents the number of available gray levels, and int represents an integer function;
will S1(i) Obtaining f after finding the difference1(i) Using a shift gate function gt,w(j) To f1(i) Modulating the function, and normalizing to obtain f2(i)，S2(i) Is f2(i) Is given by the formula:
wherein the Norm function is a normalization function, a shift gate function gt,w(j) After displacement and stretching by standard gate functionObtaining t represents a displacement amount, w represents a stretching amount, and the specific values of t and w are determined by the gray level distribution of the regional sub-images;
according to S2(i) And f2(i) And changing the gray information distribution of the sub-images of the regions to meet the observation requirement of human eyes.
6. The infrared image processing method for improving human eye identification according to claim 1, wherein the sub-images to be spliced are spliced by two-dimensional linear mapping.
7. The infrared image processing method for improving human eye identification according to claim 1, wherein a Log function is used to perform nonlinear mapping on pixel gray values of the spliced images, and the formula is as follows:
wherein σ (x, y) is a gray value output by the pixel point, and n represents gray information of the original infrared image.
8. The infrared image processing method for improving human eye recognition as claimed in claim 1, further comprising, before performing region segmentation on the original infrared image according to the field area of fovea region of human retina and the distance between human eye and display device: and performing linear stripe noise removal and nonlinear noise point compensation on the original infrared image.
9. An infrared image processing apparatus for improving human eye recognition, comprising:
a memory for storing program instructions;
a processor for calling the program instructions stored in the memory to implement the infrared image processing method for improving human eye identification according to any one of claims 1 to 8.
10. A computer-readable storage medium, characterized in that the computer-readable storage medium stores program code for implementing the infrared image processing method for improving human eye recognition according to any one of claims 1 to 8.
Applications Claiming Priority (2)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN2021109911289 | 2021-08-26 | ||
| CN202110991128 | 2021-08-26 |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN113763361A true CN113763361A (en) | 2021-12-07 |
Family
ID=78794124
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202111051956.0A Pending CN113763361A (en) | 2021-08-26 | 2021-09-08 | Infrared image processing method and device for improving human eye identification degree and storage medium |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN113763361A (en) |
Citations (9)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20110091102A1 (en) * | 2004-12-24 | 2011-04-21 | Cimbalista Jr Mario | Method for improving visualization of infrared images |
| US20150124102A1 (en) * | 2013-11-01 | 2015-05-07 | Flir Systems Ab | Enhanced visual representation of infrared data values |
| US20180096194A1 (en) * | 2016-07-11 | 2018-04-05 | Her Majesty The Queen In Right Of Canada As Represented By The Minister Of Defence | Center-Surround Image Fusion |
| CN108257099A (en) * | 2018-01-11 | 2018-07-06 | 重庆邮电大学 | A kind of adaptive infrared image enhancing method of view-based access control model contrast resolution |
| CN108319966A (en) * | 2017-10-13 | 2018-07-24 | 西安科技大学 | The method for identifying and classifying of equipment in a kind of substation's complex background infrared image |
| CN109147005A (en) * | 2018-08-24 | 2019-01-04 | 电子科技大学 | It is a kind of for the adaptive colouring method of infrared image, system, storage medium, terminal |
| CN109859138A (en) * | 2019-02-14 | 2019-06-07 | 哈尔滨理工大学 | A kind of infrared image enhancing method based on human-eye visual characteristic |
| CN109886876A (en) * | 2019-02-25 | 2019-06-14 | 昀光微电子（上海）有限公司 | A kind of nearly eye display methods based on visual characteristics of human eyes |
| CN110458851A (en) * | 2019-08-12 | 2019-11-15 | 北京环境特性研究所 | Infrared Image Processing Method, device, computer equipment and storage medium |
-
2021
- 2021-09-08 CN CN202111051956.0A patent/CN113763361A/en active Pending
Patent Citations (9)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20110091102A1 (en) * | 2004-12-24 | 2011-04-21 | Cimbalista Jr Mario | Method for improving visualization of infrared images |
| US20150124102A1 (en) * | 2013-11-01 | 2015-05-07 | Flir Systems Ab | Enhanced visual representation of infrared data values |
| US20180096194A1 (en) * | 2016-07-11 | 2018-04-05 | Her Majesty The Queen In Right Of Canada As Represented By The Minister Of Defence | Center-Surround Image Fusion |
| CN108319966A (en) * | 2017-10-13 | 2018-07-24 | 西安科技大学 | The method for identifying and classifying of equipment in a kind of substation's complex background infrared image |
| CN108257099A (en) * | 2018-01-11 | 2018-07-06 | 重庆邮电大学 | A kind of adaptive infrared image enhancing method of view-based access control model contrast resolution |
| CN109147005A (en) * | 2018-08-24 | 2019-01-04 | 电子科技大学 | It is a kind of for the adaptive colouring method of infrared image, system, storage medium, terminal |
| CN109859138A (en) * | 2019-02-14 | 2019-06-07 | 哈尔滨理工大学 | A kind of infrared image enhancing method based on human-eye visual characteristic |
| CN109886876A (en) * | 2019-02-25 | 2019-06-14 | 昀光微电子（上海）有限公司 | A kind of nearly eye display methods based on visual characteristics of human eyes |
| CN110458851A (en) * | 2019-08-12 | 2019-11-15 | 北京环境特性研究所 | Infrared Image Processing Method, device, computer equipment and storage medium |
Non-Patent Citations (1)
| Title |
|---|
| 闫金铭等: "基于人眼视觉机理的红外图像边缘提取", 火力与指挥控制, vol. 34, no. 1, 31 January 2009 (2009-01-31), pages 60 - 62 * |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| Agrawal et al. | A novel joint histogram equalization based image contrast enhancement | |
| Tao et al. | Adaptive and integrated neighborhood-dependent approach for nonlinear enhancement of color images | |
| Lin et al. | Intensity and edge based adaptive unsharp masking filter for color image enhancement | |
| US20040213476A1 (en) | Detecting and correcting red-eye in a digital image | |
| Vonikakis et al. | Fast centre–surround contrast modification | |
| US7522314B2 (en) | Image sharpening | |
| US8705857B2 (en) | System and method of image processing perceptual visibility of imagery | |
| CN105303561A (en) | Image preprocessing grayscale space division method | |
| Lecca et al. | GRASS: a gradient-based random sampling scheme for Milano Retinex | |
| CN107622475A (en) | Gray correction method in image mosaic | |
| Lecca et al. | GREAT: a gradient-based color-sampling scheme for Retinex | |
| CN114202491B (en) | Method and system for enhancing optical image | |
| CN113450272B (en) | Image enhancement method based on sinusoidal variation and application thereof | |
| Provenzi | Formalizations of the retinex model and its variants with variational principles and partial differential equations | |
| Rao et al. | Retinex-centered contrast enhancement method for histopathology images with weighted CLAHE | |
| CN110969583A (en) | Image background processing method and system | |
| Khan et al. | Thin vessel detection and thick vessel edge enhancement to boost performance of retinal vessel extraction methods | |
| Rao et al. | A hybrid method for improving the luminosity and contrast of color retinal images using the JND model and multiple layers of CLAHE | |
| CN113763361A (en) | Infrared image processing method and device for improving human eye identification degree and storage medium | |
| Bhandari et al. | Gamma corrected reflectance for low contrast image enhancement using guided filter | |
| CN111738241A (en) | Pupil detection method and device based on double cameras | |
| CN114359083B (en) | High-dynamic thermal infrared image self-adaptive preprocessing method for interference environment | |
| Jawdekar et al. | A review of image enhancement techniques in medical imaging | |
| Poostchi et al. | Diabetic retinopathy dark lesion detection: preprocessing phase | |
| Sun et al. | Single-image dehazing based on dark channel prior and fast weighted guided filtering |
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 |