CN117115029A - Infrared image edge enhancement method, device and equipment and storage medium - Google Patents
Infrared image edge enhancement method, device and equipment and storage medium Download PDFInfo
- Publication number
- CN117115029A CN117115029A CN202311094644.7A CN202311094644A CN117115029A CN 117115029 A CN117115029 A CN 117115029A CN 202311094644 A CN202311094644 A CN 202311094644A CN 117115029 A CN117115029 A CN 117115029A
- Authority
- CN
- China
- Prior art keywords
- edge
- infrared image
- matrix
- enhanced
- temperature
- 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
- 238000000034 method Methods 0.000 title claims abstract description 57
- 238000003860 storage Methods 0.000 title claims abstract description 12
- 239000011159 matrix material Substances 0.000 claims abstract description 255
- 238000003708 edge detection Methods 0.000 claims abstract description 34
- 230000003044 adaptive effect Effects 0.000 claims abstract description 22
- 238000012545 processing Methods 0.000 claims description 31
- 230000002708 enhancing effect Effects 0.000 claims description 20
- 238000004364 calculation method Methods 0.000 claims description 18
- 238000004590 computer program Methods 0.000 claims description 12
- 238000001914 filtration Methods 0.000 claims description 10
- 230000009466 transformation Effects 0.000 claims description 7
- 238000000605 extraction Methods 0.000 claims description 6
- 238000007619 statistical method Methods 0.000 claims description 4
- 230000000694 effects Effects 0.000 description 16
- 238000004422 calculation algorithm Methods 0.000 description 12
- 238000003331 infrared imaging Methods 0.000 description 12
- 230000008569 process Effects 0.000 description 10
- 230000004044 response Effects 0.000 description 10
- 238000003384 imaging method Methods 0.000 description 9
- 238000003672 processing method Methods 0.000 description 9
- 238000006243 chemical reaction Methods 0.000 description 6
- 238000010586 diagram Methods 0.000 description 6
- 230000005855 radiation Effects 0.000 description 5
- 230000002238 attenuated effect Effects 0.000 description 4
- 230000004927 fusion Effects 0.000 description 4
- 238000009826 distribution Methods 0.000 description 3
- 230000008901 benefit Effects 0.000 description 2
- 238000012937 correction Methods 0.000 description 2
- 230000006870 function Effects 0.000 description 2
- 238000007689 inspection Methods 0.000 description 2
- 230000014759 maintenance of location Effects 0.000 description 2
- 238000004519 manufacturing process Methods 0.000 description 2
- 230000003287 optical effect Effects 0.000 description 2
- 230000000717 retained effect Effects 0.000 description 2
- 230000001629 suppression Effects 0.000 description 2
- 230000000007 visual effect Effects 0.000 description 2
- 241001465754 Metazoa Species 0.000 description 1
- 230000009286 beneficial effect Effects 0.000 description 1
- 238000009529 body temperature measurement Methods 0.000 description 1
- 230000003749 cleanliness Effects 0.000 description 1
- 230000006835 compression Effects 0.000 description 1
- 238000007906 compression Methods 0.000 description 1
- 238000013135 deep learning Methods 0.000 description 1
- 238000001514 detection method Methods 0.000 description 1
- 238000011161 development Methods 0.000 description 1
- 238000005516 engineering process Methods 0.000 description 1
- 230000003631 expected effect Effects 0.000 description 1
- 238000010606 normalization Methods 0.000 description 1
- 238000005457 optimization Methods 0.000 description 1
- 230000009467 reduction Effects 0.000 description 1
- 238000012216 screening Methods 0.000 description 1
- 238000006467 substitution reaction Methods 0.000 description 1
- 238000001931 thermography Methods 0.000 description 1
- 238000012549 training Methods 0.000 description 1
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T5/00—Image enhancement or restoration
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T7/00—Image analysis
- G06T7/10—Segmentation; Edge detection
- G06T7/13—Edge detection
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- 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
- G06T2207/20—Special algorithmic details
- G06T2207/20172—Image enhancement details
- G06T2207/20192—Edge enhancement; Edge preservation
Landscapes
- Engineering & Computer Science (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Theoretical Computer Science (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Image Processing (AREA)
Abstract
The application provides an infrared image edge enhancement method, an infrared image edge enhancement device, infrared image edge enhancement equipment and a storage medium, wherein the method comprises the following steps: acquiring a temperature data matrix and an image data matrix corresponding to an infrared image to be enhanced; performing edge detection based on the image data matrix, and calculating corresponding edge gradient values according to gradients of each pixel point in the infrared image to be enhanced in at least two directions to obtain an edge gradient matrix of the infrared image to be enhanced; determining a temperature interval threshold according to the temperature data matrix, and respectively adopting different strategies to calculate corresponding weight values for the pixel points in different temperature intervals according to the comparison result of the temperature values corresponding to the pixel points in the infrared image to be enhanced and the temperature interval threshold to obtain an adaptive weight matrix of the infrared image to be enhanced; and carrying out self-adaptive weighted enhancement on the infrared image to be enhanced through the self-adaptive weight matrix and the edge gradient matrix to obtain an edge information enhanced image.
Description
Technical Field
The present application relates to the field of image processing technologies, and in particular, to an infrared image edge enhancement method and apparatus, an image processing device, and a computer readable storage medium.
Background
With the development of the production and manufacturing process of infrared detectors, the cost of infrared imaging devices is lower and lower, corresponding various types of infrared imaging devices are also popular in the life of people, and people start to get used to using the infrared imaging devices, such as thermal imagers, to detect the surrounding environment to find small animals in various activities, such as outdoor exploration, and to be used for outdoor inspection or indoor circuit inspection in work. In these activities, thermal imagers typically present ambient temperature information directly to the user in a thermal imaging manner. In an actual scene, the thermal imager is required to receive not only infrared radiation of a target but also background radiation, and the data are often subjected to global and local contrast stretching in the process of processing by an infrared imaging algorithm so as to display details and contours inside the target at different temperatures, so that the details of the target and the background in an image are clearly shown and accord with an optimization target of image processing. However, in the actual use process, although the definition and detail of the image are ensured, the distinguishing degree of the target and the background is often not obvious enough, which is not beneficial to quick and accurate positioning. It is often necessary to add an object highlighting function in the form of edge detection on this basis to accommodate different scene requirements.
At present, known edge detection algorithms are usually calculated by a thermal imager based on an imaged infrared image, in the infrared image, edges and details in the background are also detected and revealed due to the fact that the distinguishing degree of a target and the background is not obvious enough, the known edge detection algorithms are usually global edge detection, and then the contours inside the target are easily removed by simply screening through a threshold value, so that the detail observation of the heat source target is not facilitated. Some model algorithms based on deep learning generally require a certain computational effort, and model training is difficult, so that most of infrared imaging devices do not have a transplanting condition due to cost control.
Disclosure of Invention
In order to solve the existing technical problems, the application provides an infrared image edge enhancement method and device, image processing equipment and a computer readable storage medium, wherein the method and device are simple and convenient to calculate, easy to transplant on various equipment, have a prominent heat source target and can effectively reserve the internal details of the heat source target.
In order to achieve the above object, the technical solution of the embodiment of the present application is as follows:
in a first aspect, an embodiment of the present application provides an infrared image edge enhancement method, including:
Acquiring a temperature data matrix and an image data matrix corresponding to an infrared image to be enhanced;
performing edge detection based on the image data matrix, and calculating corresponding edge gradient values according to gradients of each pixel point in the infrared image to be enhanced in at least two directions to obtain an edge gradient matrix of the infrared image to be enhanced;
determining a temperature interval threshold according to the temperature data matrix, and respectively adopting different strategies to calculate corresponding weight values for the pixel points in different temperature intervals according to the comparison result of the temperature values corresponding to the pixel points in the infrared image to be enhanced and the temperature interval threshold to obtain an adaptive weight matrix of the infrared image to be enhanced;
and carrying out self-adaptive weighted enhancement on the infrared image to be enhanced through the self-adaptive weight matrix and the edge gradient matrix to obtain an edge information enhanced image.
In a second aspect, an embodiment of the present application provides an infrared image edge enhancement device, including:
the acquisition module is used for acquiring a temperature data matrix and an image data matrix corresponding to the infrared image to be enhanced;
the edge extraction module is used for carrying out edge detection based on the image data matrix, and calculating corresponding edge gradient values according to gradients of each pixel point in the infrared image to be enhanced in at least two directions respectively to obtain an edge gradient matrix of the infrared image to be enhanced;
The weight module is used for determining a temperature interval threshold according to the temperature data matrix, and calculating corresponding weight values of the pixel points in different temperature intervals by adopting different strategies according to a comparison result of the temperature values corresponding to the pixel points in the infrared image to be enhanced and the temperature interval threshold to obtain an adaptive weight matrix of the infrared image to be enhanced;
and the self-adaptive enhancement module is used for carrying out self-adaptive weighted enhancement on the infrared image to be enhanced through the self-adaptive weight matrix and the edge gradient matrix to obtain an edge information enhanced image.
In a third aspect, an embodiment of the present application provides an image processing apparatus including a processor, a memory connected to the processor, and a computer program stored on the memory and executable by the processor; the computer program when executed by the processor implements the infrared image edge enhancement method according to any of the embodiments of the present application.
In a fourth aspect, embodiments of the present application provide a computer readable storage medium having a computer program stored thereon, which when executed by the processor implements an infrared image edge enhancement method according to any of the embodiments of the present application.
According to the infrared image edge enhancement method provided by the embodiment, the temperature data matrix corresponding to the infrared image to be enhanced is obtained, the temperature data matrix is utilized to divide different temperature intervals of the infrared image to be enhanced, corresponding weight values are calculated according to different strategies for pixel points in different temperature intervals, so that the self-adaptive weight matrix capable of forming different degrees of enhanced prominence on the target edge information in different temperature intervals is obtained, the temperature data matrix and the image data matrix of the infrared image to be enhanced are comprehensively utilized, the target edge information belonging to different temperature intervals is identified through the temperature data matrix on the basis of extracting the edge information in the image through the image data matrix, for example, the edge information in the heat source target can be effectively identified and distinguished, the effect of enhancing the target edge information in different temperature intervals to different degrees is achieved through forming the self-adaptive weight matrix, the purposes of achieving the heat source target prominence, effectively retaining the internal details of the heat source target and better ignoring the clutter edge information in the background of the non-heat source target are achieved, the algorithm is relatively simple, the algorithm is excessively convenient, and the infrared image enhancement method is convenient to apply in various imaging devices, and the infrared image enhancement method is convenient to transplant.
In the above embodiments, the infrared image edge enhancement device, the infrared imaging apparatus, and the computer readable storage medium belong to the same concept as the corresponding infrared image edge enhancement method embodiments, so that the same technical effects as the corresponding infrared image edge enhancement method embodiments are respectively achieved, and are not described herein.
Drawings
FIG. 1 is a schematic diagram of an application scenario of an infrared image edge processing method according to an embodiment;
FIG. 2 is a flow chart of an infrared image edge processing method according to an embodiment;
FIG. 3 is a flow chart of an infrared image edge processing method in an alternative embodiment;
FIG. 4 is an exemplary diagram of an original infrared image to be enhanced;
FIG. 5 is a graph showing the effect of the edge detection result obtained by adaptively weighting and enhancing the edge information in FIG. 4;
FIG. 6 is a graph showing the effect of edge highlighting obtained by fusing the edge information of FIG. 4 with the background after adaptively weighting and enhancing;
FIG. 7 is a schematic diagram of an infrared image edge processing apparatus according to an embodiment;
fig. 8 is a schematic structural diagram of an image processing apparatus in an embodiment.
Detailed Description
The technical scheme of the application is further elaborated below by referring to the drawings in the specification and the specific embodiments.
The present application will be further described in detail with reference to the accompanying drawings, for the purpose of making the objects, technical solutions and advantages of the present application more apparent, and the described embodiments should not be construed as limiting the present application, and all other embodiments obtained by those skilled in the art without making any inventive effort are within the scope of the present application.
In the following description, reference is made to the expression "some embodiments" which describe a subset of all possible embodiments, it being noted that "some embodiments" may be the same subset or different subsets of all possible embodiments and may be combined with each other without conflict.
In the following description, the terms "first, second, third" and the like are used merely to distinguish between similar objects and do not represent a specific ordering of the objects, it being understood that the "first, second, third" may be interchanged with a specific order or sequence, as permitted, to enable embodiments of the application described herein to be practiced otherwise than as illustrated or described herein.
Referring to fig. 1, a schematic diagram of an optional application scenario of an infrared image edge processing method according to an embodiment of the present application is shown, wherein an infrared imaging device 11 includes a processor 12, a memory 13 connected to the processor 12, and an infrared detector 14. The infrared detector 14 sequentially converts thermal radiation into an electric signal by receiving radiation emitted by the surrounding environment and the target, and then converts the electric signal into a digital signal, the digital signal can be used as a response signal for representing temperature data of each point in the detector array, then the relationship between the response and the temperature of each point in the detector array can be established through calibration and non-uniformity correction, a temperature data matrix corresponding to an infrared image can be obtained by utilizing the nonlinear relationship between the response and the temperature, and thus the obtained temperature data can relatively accurately reflect the temperature distribution condition of the environment in an imaging range, and the heat source target can be easily and accurately detected. The imaging of the infrared image is generally that the processor 12 directly compresses and maps the electrical signal containing the temperature data to the data of 8 bits according to the electrical signal obtained by photoelectric conversion of the infrared detector 14 to display the data in the form of an image, for example, on the response data of the 14bit detector after non-uniform correction, a series of image data processing flows including operations of data bit compression, filtering and noise reduction, contrast enhancement, detail enhancement and the like are performed, so that the imaging effect is improved in terms of picture cleanliness, contrast, detail expression and the like, but the operations influence the relationship between response and temperature to a certain extent, so that the characteristic of the imaged image is inaccurate in terms of the temperature distribution of the reaction environment. In this embodiment, the infrared detector 14 is configured to receive the thermal radiation and convert it into response signals representing temperature data at each point in the detector array, where the response signals are used to provide the processor 12 with a temperature data matrix using the relationship between the response and the temperature and with an image data matrix obtained by image data processing.
The processor 12 obtains a temperature data matrix by using the relationship between the response and the temperature through the electric signal generated by the photoelectric conversion of the infrared detector 14, and performs imaging of the infrared image through a series of image data processing procedures, and obtains an image data matrix corresponding to the infrared image. The memory 13 stores a computer program for implementing the method for processing the edge of the infrared image provided by the embodiment of the application, and the processor 12 performs enhancement of the edge information in the infrared image according to the obtained temperature data matrix and the image data matrix of the infrared image by executing the computer program, and combines the temperature data and the image data to obtain an edge information enhanced image after the heat source target and the background edge information are subjected to the distinguishing enhancement processing, namely, the accuracy of temperature measurement data is maintained, and the visual effect of the image is ensured.
Referring to fig. 2, an infrared image edge processing method according to an embodiment of the present application may be applied to an infrared imaging device in the application scenario shown in fig. 1. The infrared image edge processing method comprises the following steps:
s101, acquiring a temperature data matrix and an image data matrix corresponding to the infrared image to be enhanced.
The infrared image to be enhanced refers to an infrared image which needs to be subjected to image enhancement processing, and can refer to infrared video data or separated single Zhang Lei infrared picture data. The infrared image to be enhanced may refer to an infrared image acquired by an infrared imaging device in real time, for example, the infrared imaging device may collect an electric signal obtained by photoelectric conversion of an infrared signal in an imaging scene by using an infrared detector in a process of acquiring the infrared image in real time, and form the infrared image according to the electric signal to obtain an image data matrix corresponding to the infrared image, and obtain a temperature data matrix corresponding to the current infrared image according to the electric signal. Optionally, the infrared image to be enhanced may also refer to an infrared image acquired by any infrared imaging device having an infrared image capturing function, for example, in a process of acquiring an infrared image, an infrared detector is used to collect an electric signal obtained by photoelectric conversion of an infrared signal in an imaging scene, an infrared image is formed according to the electric signal to obtain an image data matrix corresponding to the infrared image, and a temperature data matrix corresponding to a current infrared image is obtained according to the electric signal at the same time, and the temperature data matrix and the infrared image are stored in an associated manner for subsequent calling.
The image data matrix is a data matrix formed by gray values corresponding to pixel points in the infrared image. The temperature data matrix refers to a data matrix formed by original temperature values corresponding to all pixel points in an infrared image, wherein the original temperature value of each pixel point is a temperature value obtained by utilizing a relation between response and temperature according to an electric signal obtained by photoelectric conversion of an infrared detector, and the temperature value directly and accurately reflects temperature distribution information in an imaging scene.
And S103, performing edge detection based on the image data matrix, and calculating corresponding edge gradient values according to gradients of each pixel point in the infrared image to be enhanced in at least two directions to obtain an edge gradient matrix of the infrared image to be enhanced.
The edge detection is performed on the infrared image to be enhanced based on the image data matrix, and any known edge detection algorithm, such as a Sobel edge detection operator, a Roberts edge detection operator and the like, is adopted to extract edge information in the image, and corresponding edge gradient values are calculated according to gradients of each pixel point in the infrared image to be enhanced in at least two directions respectively, so that the edge gradient matrix of the infrared image to be enhanced is obtained as preliminary edge detection information. In the edge gradient matrix, each element is an edge gradient value calculated by each pixel point in the image according to gradients in at least two directions, and the magnitude of the edge gradient value correspondingly represents whether the pixel point belongs to an edge in the image.
S105, determining a temperature interval threshold according to the temperature data matrix, and calculating corresponding weight values of the pixel points in different temperature intervals by adopting different strategies according to comparison results of the temperature values corresponding to the pixel points in the infrared image to be enhanced and the temperature interval threshold to obtain the self-adaptive weight matrix of the infrared image to be enhanced.
The temperature section threshold value is a division value that can divide the middle temperature value of the temperature data matrix into different temperature sections according to the middle temperature value. The temperature interval may be two or more, and different temperature intervals may correspond to the division of different types of heat source targets, backgrounds, etc. image areas in the image. By identifying different temperature intervals in the image, corresponding weight values are calculated for pixel points in the image falling into the different temperature intervals by adopting different strategies, so that whether the pixel points are positioned at edges in image areas of different types of heat source targets, backgrounds and the like can be distinguished, the edge enhancement degree is adjusted by adopting different strategies to assign the weight values to the pixel points, and the edge enhancement effect of the expected effect is obtained. The self-adaptive weight matrix is a data matrix formed by weight values corresponding to all pixel points in the infrared image.
And S107, carrying out self-adaptive weighted enhancement on the infrared image to be enhanced through the self-adaptive weight matrix and the edge gradient matrix to obtain an edge information enhanced image.
The edge gradient matrix represents all edge information extracted based on gray values of all pixel points in the image, and the adaptive weight matrix represents enhancement degree information of the pixel points contained in different areas, wherein the different heat source targets or areas are corresponding to the areas and are divided based on temperature values of all pixel points in the image. The self-adaptive weight matrix and the edge gradient matrix are used for carrying out self-adaptive weighted enhancement on the infrared image to be enhanced, so that the suppression or retention enhancement on the edge information in different temperature areas can be realized, for example, the retention enhancement is carried out on the edge information in a high temperature area, and the suppression on the edge information in a low temperature area is carried out, thereby ensuring that the detail and the contour information in a heat source target area in the image can be completely retained and projected for display, and the extracted edge information in the background is suppressed, so that the heat source target edge detail information can be better enhanced under a relatively complex background. The adaptive weighting enhancement expresses the adaptive adjustment of the enhancement processing degree of the edge information extracted in different temperature areas.
According to the infrared image edge enhancement method provided by the embodiment, the temperature data matrix corresponding to the infrared image to be enhanced is obtained, the temperature data matrix is utilized to divide different temperature intervals of the infrared image to be enhanced, corresponding weight values are calculated according to different strategies for pixel points in different temperature intervals, so that the self-adaptive weight matrix capable of forming different degrees of enhanced prominence on the target edge information in different temperature intervals is obtained, the temperature data matrix and the image data matrix of the infrared image to be enhanced are comprehensively utilized, the target edge information belonging to different temperature intervals is identified through the temperature data matrix on the basis of extracting the edge information in the image through the image data matrix, for example, the edge information in the heat source target can be effectively identified and distinguished, the effect of enhancing the target edge information in different temperature intervals to different degrees is achieved through forming the self-adaptive weight matrix, the purposes of achieving the heat source target prominence, effectively retaining the internal details of the heat source target and better ignoring the clutter edge information in the background of the non-heat source target are achieved, the algorithm is relatively simple, the algorithm is excessively convenient, and the infrared image enhancement method is convenient to apply in various imaging devices, and the infrared image enhancement method is convenient to transplant.
In some embodiments, before the adaptively weighting enhancing the infrared image to be enhanced by the adaptive weight matrix and the edge gradient matrix to obtain an edge information enhanced image, the method includes:
and carrying out enhancement processing on the edge information of the infrared image to be enhanced, which is obtained based on the edge gradient matrix, so as to obtain an updated edge gradient matrix after enhancement.
The size of each element in the edge gradient matrix correspondingly represents whether each pixel point in the infrared image to be enhanced belongs to an edge in the image. The edge gradient matrix is obtained by extracting edges based on the image data matrix, comprises edges of the outer contours and the internal details of the background and all targets in the image, enhances the edge information of the infrared image to be enhanced based on the edge gradient matrix, and can outline the edges of the outer contours and the internal details of the background and all targets together to obtain an updated edge gradient matrix after enhancement.
In the above embodiment, since the signal intensity of the extracted edge information is usually far weaker than the average gray level of the image, the enhancement of the absolute intensity of the edge signal in the image can be achieved by performing the enhancement processing on the edge information in the image according to the edge gradient matrix.
In some embodiments, the enhancing the edge information of the to-be-enhanced infrared image obtained based on the edge gradient matrix to obtain an updated edge gradient matrix after enhancement includes:
obtaining an updated edge gradient matrix after enhancement based on the product of the edge gradient matrix and a preset enhancement multiple; or alternatively, the first and second heat exchangers may be,
and determining a gradient value range according to the edge gradient matrix, normalizing the edge gradient matrix according to the gradient value range, and multiplying the normalized edge gradient matrix by a preset linear stretch coefficient to obtain an enhanced updated edge gradient matrix.
According to the enhancement of the edge gradient matrix to the edge information in the image, the enhancement can be carried out by simply and directly multiplying the edge gradient matrix by a certain preset enhancement multiple. The difference between the magnitude of the gradient value in the preset enhancement multiple visual edge gradient matrix and the magnitude of the average gray value of the image is considered, or may be directly preset according to an empirical value.
According to the enhancement of the edge gradient matrix to the edge information in the image, the linear stretching enhancement can be performed after the gradient value range is calculated. The gradient value range of the edge gradient matrix G is expressed as a maximum value grad_max and a minimum value grad_min, and the preset linear stretching coefficient is range, and then normalization calculation is performed according to the gradient value range, and then the calculation of linear stretching to the upper limit range can be shown in the following formula 1:
G_enhancement [ i, j ] = (G [ i, j ] -grad_min)/(grad_max-grad_min) ×range (formula 1)
Where G [ i, j ] refers to the edge gradient matrix and G_enhancement [ i, j ] refers to the edge gradient matrix updated after enhancement. The preset linear stretch coefficient range is larger than the maximum gray value 255, and generally has a value between one and five times of 255.
In some embodiments, the enhanced updated edge gradient matrix comprises:
dividing the edge gradient matrix after the enhancement treatment according to a set threshold value, and setting the values of elements smaller than the set threshold value in the edge gradient matrix to zero to obtain an updated edge gradient matrix after the enhancement treatment.
Dividing the edge gradient matrix according to the set threshold value, and setting the value of the element smaller than the set threshold value in the edge gradient matrix after the enhancement treatment to zero, so that the gradient information still smaller after the enhancement in the edge gradient matrix after the enhancement treatment is abandoned. In one example, the threshold is set to be a hard threshold level, the level may take a value less than one tenth of range, if the data of the ith row and j column in g_enhancement [ i, j ] is less than level, the data of the ith row and j column is set to zero, and the edge gradient matrix after enhancement is updated again, so as to obtain the edge gradient matrix updated after enhancement.
In some embodiments, the edge detection based on the image data matrix calculates corresponding edge gradient values according to gradients of each pixel point in the infrared image to be enhanced in at least two directions, so as to obtain an edge gradient matrix of the infrared image to be enhanced, including:
performing Gaussian filtering based on the image data matrix;
performing edge detection on the Gaussian filtered image data matrix, and calculating gradients of each pixel point in the infrared image to be enhanced in at least two directions;
and summing absolute values according to the gradients of each pixel point in all directions, and calculating the corresponding edge gradient values to obtain an edge gradient matrix of the infrared image to be enhanced.
The infrared image to be enhanced is subjected to Gaussian filtering based on an image data matrix, so that weak details can be ignored, main contours and strong details are reserved, meanwhile, noise in the image can be erased, and the edge information extracted later is ensured to be cleaner. The standard deviation sigma and the filter window in the Gaussian filter can be taken into consideration according to the size of image noise, and the smaller the image noise is, the smaller the value can be, so that excessive loss of contour information in an image is avoided, and the edge information in the image can be ensured to be more completely reserved. Edge detection is essentially the detection of where the gray value between adjacent regions in the image is discontinuous or abrupt. The gradient is a vector with a direction and a magnitude, the gradient direction represents a local direction of an estimated edge, and a gradient modulus value is found by using the gradient direction to judge whether the estimated edge is edge information. It should be noted that, the edge detection may be implemented by selecting some currently known edge detection algorithms.
Optionally, the edge detection is performed on the image data matrix after the gaussian filtering, and the gradient of each pixel point in the infrared image to be enhanced in at least two directions is calculated, including:
performing edge detection on the Gaussian filtered image data matrix, and respectively setting corresponding convolution kernels for the directions of a plurality of preset angles;
and aiming at each pixel point in the infrared image to be enhanced, obtaining gradients of the pixel points in the directions of the preset angles according to convolution calculation of the convolution kernels in the directions of the preset angles respectively.
In this embodiment, the edge detection uses the Sobel operator in four directions as an example, and calculates gradients of each pixel point in the four directions of horizontal and vertical directions, that is, 0 degrees, 45 degrees, 90 degrees and 135 degrees, and then sums absolute values, and the obtained edge gradient matrix is used as the preliminary edge detection information output of the infrared image to be enhanced based on the image data matrix. Wherein, for four directions of 0 degree, 45 degrees, 90 degrees, 135 degrees, the corresponding convolution kernels are set as shown in the following formula 2:
the data of the ith row and the jth column in the image data matrix I are recorded as I [ I, j ], and the gradients of the pixel points in all directions are respectively shown in the following formula 3:
Taking absolute value summation according to the gradient of each pixel point in each direction, and calculating the corresponding edge gradient value can be shown in the following formula 4:
grad=abs (grad_0) +abs (grad_45) +abs (grad_90) +abs (grad_135) (equation 4)
The same operation is performed for each pixel point in the image data matrix, respectively, and an edge gradient matrix G [ i, j ] based on the image data matrix can be obtained.
In the above embodiment, an implementation scheme is provided that the edge detection information is output by calculating the gradient information of the infrared image to be enhanced in four directions, so that better effects can be obtained in balancing the calculated amount and obtaining more complete edge information.
In some embodiments, the determining a temperature interval threshold according to the temperature data matrix, and calculating corresponding weight values for the pixel points in different temperature intervals by using different strategies according to a comparison result of the temperature values corresponding to the pixel points in the infrared image to be enhanced and the temperature interval threshold, to obtain an adaptive weight matrix of the infrared image to be enhanced includes:
according to the temperature data matrix, obtaining a statistical data index through statistical analysis to serve as a temperature interval threshold for dividing the temperature data into a plurality of temperature intervals; the statistical data index is selected from one of the following: average, median, mode, quartile;
Determining the temperature interval in which each pixel point is respectively positioned according to the comparison result of the temperature value corresponding to each pixel point in the infrared image to be enhanced and the temperature interval threshold value;
and respectively adopting different strategies to calculate corresponding weight values for the pixel points in different temperature intervals to obtain the self-adaptive weight matrix of the infrared image to be enhanced.
The temperature interval can be two or more, and different temperature intervals can distinguish different heat source targets and areas where no heat source background is respectively located in the infrared image to be enhanced. The temperature interval threshold value can be set according to the temperature ranges respectively corresponding to different heat source targets and heat source-free backgrounds which are required to be distinguished. The temperature interval threshold value can be obtained through statistical analysis of temperature values in a temperature data matrix corresponding to the current infrared image to be enhanced, and different temperature interval divisions are performed by using the self-adaptive calculation temperature interval threshold value of the global temperature information of the infrared image to be enhanced. Corresponding weight values are calculated by adopting different strategies aiming at pixel points in different temperature intervals, so that the enhancement and highlighting effects of different degrees can be realized aiming at the edge information extracted in different temperature intervals.
In some embodiments, the temperature interval threshold comprises a temperature mean, the temperature interval comprising a high temperature interval and a low temperature interval divided by the temperature mean; the method for obtaining the self-adaptive weight matrix of the infrared image to be enhanced comprises the following steps of:
for each pixel point in the low temperature interval, taking the normalized value of the temperature data of the pixel point as the corresponding weight value;
for each pixel point in the high temperature interval, multiplying the product of the difference between the temperature data of the pixel point and the temperature average value and the weighted intensity control parameter, and adding the temperature average value as a corresponding weight value;
and obtaining the self-adaptive weight matrix of the infrared image to be enhanced according to the weight value of each pixel point.
In this embodiment, the distinction of the infrared image to be enhanced may be made only as the division of the high temperature region and the low temperature region according to whether it is the heat source target. The temperature interval threshold value is a temperature mean value t_mean calculated according to the temperature data matrix. For the pixel point of the ith row and jth column in the temperature data matrix T, if T [ i, i ] < t_mean, the pixel point belongs to a low temperature zone, and the corresponding weight value calculation adopts a value obtained by normalizing temperature data, as shown in the following formula 5:
W [ i, j ] =T [ i, j ]/t_mean (equation 5)
The weight value of each pixel point obtained by calculation in the low-temperature interval is generally smaller than 1, and the edge information in the low-temperature interval after the weighted calculation is restrained;
if T [ i, i ]. Gtoreq.t_mean, the pixel point is in a high temperature zone, a larger weight should be obtained, and the calculation of the corresponding weight value is as shown in the following formula 6:
w [ i, j ] = (T [ i, j ] -t_mean) ×k+t_mean (formula 6)
Where k is a weighted intensity control parameter, generally greater than 1, the greater the value, the greater the weighted times of the edges in the high temperature interval, the more prominent the edges and details of the high temperature interval, and the more obvious the difference between the temperature and the height is in the enhanced intensity of the edges.
The calculation of the adaptive weight matrix is not limited to dividing the temperature interval and then calculating, but may be that the temperature average value is obtained according to the temperature data matrix T and recorded as t_mean, and the normalized value of the temperature data matrix is used as the initial value of the weight matrix W, namely: w [ i, j ] =t [ i, j ]/t_mean. Then taking the temperature average value as a threshold value for judging the high temperature and the low temperature, if T [ i, i ] < t_mean, the temperature of the point is lower, so that the weight is unchanged, namely W [ i, j ] =W [ i, j ]; if T [ i, i ]. Gtoreq.t_mean, the point is in a high temperature area, and the calculation of the weight value is updated as a formula 6, wherein k is a weight intensity control parameter.
In the implementation scheme for setting two or more temperature intervals, the calculation method shown in formula 6 may be used for calculating the weight value in the temperature interval to which the heat source target in different temperature ranges corresponds, and only the adjustment of the weight intensity control parameter k value is needed to be different, which may be a calculation method using different weight values for the weight values in the temperature interval to which the heat source target in different heat source targets corresponds.
In some embodiments, the adaptively weighting enhancing the infrared image to be enhanced by the adaptive weight matrix and the edge gradient matrix to obtain an edge information enhanced image, including:
weighting and enhancing the edge gradient matrix by utilizing the self-adaptive weight matrix to obtain an edge information matrix;
and carrying out nonlinear transformation on the image data matrix of the infrared image to be enhanced to extract a background data matrix, and overlapping the background data matrix with the edge information matrix after attenuation according to a preset proportion to obtain an edge information enhanced image.
The self-adaptive weighting enhancement is performed on the infrared image to be enhanced, namely, the self-adaptive weighting matrix is utilized to perform the weighting enhancement on the edge gradient matrix, and then an edge information matrix is obtained, as shown in the following formula 7:
Edge [ i, j ] =g_enhancement [ i, j ]. W [ i, j ] (equation 7)
The Edge information matrix is Edge [ i, j ], the self-adaptive weight matrix is W [ i, j ], the Edge gradient matrix is G_enhancement [ i, j ], and the Edge information matrix Edge can be overlapped to the original infrared image to be enhanced to achieve the effect of enhancing the saliency after the Edge information matrix Edge is rounded in the range of [0,255 ]. In general, the original infrared image to be enhanced has a certain brightness, and further overlapping of the edge information matrix is convex for display, which may cause that the brightness of the edge information which is convex for display in the image is too high to influence the comfort of human eyes. In order to meet better observation requirements, in the embodiment, a nonlinear transformation low-dark area part is performed on an image data matrix of an original infrared image to be enhanced so as to extract a background data matrix, the background data matrix is attenuated according to a preset proportion, then an edge information matrix is overlapped so as to be fused, and a final edge information enhanced image is obtained after the infrared image to be enhanced is subjected to edge enhancement. Here, the nonlinear transformation of the image data matrix may be an exponential transformation, as shown in the following equation 8:
Back[i,j] ＝ (I[i,j]/255) γ *255 (equation 8)
Wherein, gamma is a gamma coefficient, and the value is more than 1.
The background data matrix is back, the attenuation ratio is ratio, the Edge information matrix is Edge, and the background data matrix is attenuated according to the preset ratio and then is overlapped with the Edge information matrix, so that the formula 9 can be expressed as:
Fusion=back ratio+edge (equation 9)
And finally, limiting Fusion image information Fusion to be rounded within the range of the interval of [0,255], and outputting an edge information enhanced image.
In order to provide a more general understanding of the method for processing an edge of an infrared image according to an embodiment of the present application, please refer to fig. 3, and take an original infrared image as an example shown in fig. 4, the method for processing an edge of an infrared image includes:
s11, acquiring a temperature data matrix T and an image data matrix I of the infrared detector;
s12, performing Gaussian filtering on the infrared image data I; the main contour and the strong details are reserved through Gaussian filtering, so that image noise is reduced.
S13, extracting edge information from the filtered infrared image data I to obtain an edge gradient matrix; the calculation of the gradient value corresponding to each pixel point and the obtaining of the edge gradient matrix may be shown in the foregoing formulas 2-4, which are not described herein.
S14, enhancing edge information; the enhancement may be simply and directly multiplied by a multiple to perform enhancement, or normalized and then linearly stretched to enhance after calculating the value range of the edge information, as shown in the foregoing formula 1, which is not described herein.
S15, carrying out self-adaptive weighting on edge information by combining temperature data; and extracting temperature data corresponding to the infrared image, weighting the edge image according to the temperature data to ensure that the edge image retains high-temperature edge information and suppresses low-temperature area edge information, thereby ensuring that the detail and contour information of the heat source target area can be completely retained. The high-low temperature cut-off threshold is calculated by using global temperature information in a self-adaptive manner so as to better enhance the heat source target edge detail information under a relatively complex background, and the calculation of the self-adaptive weight matrix can be shown in the foregoing formulas 5-6 and is not repeated here. As shown in fig. 5, the effect of adaptively weighted edge detection on edge information is illustrated.
S16, extracting background information; the non-linear transformation is performed on the original infrared image data to reduce the dark area as a background image data matrix, as shown in the foregoing formula 8, and will not be described herein.
S17, the background information is attenuated according to a certain proportion, the enhanced edge information is overlapped, and an edge information enhanced image with prominent edges is output. The edge information enhanced image is a fusion of the attenuated background and the enhanced edge information, as shown in the foregoing formula 9, and will not be described herein. As shown in fig. 6, an edge salient effect diagram is obtained by fusing an edge detection result obtained by adaptively weighting edge information with a background.
The infrared image edge processing method provided in the above embodiment has at least the following characteristics:
firstly, the original temperature data provided by the infrared detector is utilized to carry out self-adaptive edge enhancement on the infrared image, so that the advantage of clearly representing local detail textures in an image processing algorithm is reserved, and the temperature data is also utilized to highlight a heat source target and distinguish background information.
Secondly, by combining temperature data and image data, a heat source area and a background are effectively distinguished, area edge details of a heat source target are reserved and adaptively enhanced, and the target is more prominent and clearer.
Thirdly, the self-adaptive calculation is carried out by combining temperature data without complex algorithm, the calculated amount is small, the calculation is convenient, and the method can be transplanted to various terminals and mobile infrared equipment.
Referring to fig. 7, another aspect of the present application provides an infrared image edge enhancement device, including: an acquisition module 21, configured to acquire a temperature data matrix and an image data matrix corresponding to an infrared image to be enhanced; the edge extraction module 22 is configured to perform edge detection based on the image data matrix, and calculate corresponding edge gradient values according to gradients of each pixel point in the infrared image to be enhanced in at least two directions, so as to obtain an edge gradient matrix of the infrared image to be enhanced; the weight module 23 is configured to determine a temperature interval threshold according to the temperature data matrix, and calculate corresponding weight values for the pixel points in different temperature intervals by using different strategies according to a comparison result of the temperature value corresponding to each pixel point in the infrared image to be enhanced and the temperature interval threshold, so as to obtain an adaptive weight matrix of the infrared image to be enhanced; the adaptive enhancement module 24 is configured to perform adaptive weighted enhancement on the infrared image to be enhanced through the adaptive weight matrix and the edge gradient matrix, so as to obtain an edge information enhanced image.
The edge extraction module 22 is further configured to perform enhancement processing based on edge information of the to-be-enhanced infrared image obtained by the edge gradient matrix, so as to obtain an edge gradient matrix updated after enhancement.
The edge extraction module 22 is further configured to obtain an edge gradient matrix updated after enhancement based on a product of the edge gradient matrix and a preset enhancement multiple; or determining a gradient value range according to the edge gradient matrix, normalizing the edge gradient matrix according to the gradient value range, and multiplying the normalized edge gradient matrix by a preset linear stretch coefficient to obtain an enhanced updated edge gradient matrix.
The edge extraction module 22 is further configured to segment the edge gradient matrix after the enhancement processing according to a set threshold, and zero values of elements smaller than the set threshold in the edge gradient matrix, so as to obtain an updated edge gradient matrix after the enhancement processing.
Wherein the weight module 23 is further configured to perform gaussian filtering based on the image data matrix; performing edge detection on the Gaussian filtered image data matrix, and calculating gradients of each pixel point in the infrared image to be enhanced in at least two directions; and summing absolute values according to the gradients of each pixel point in all directions, and calculating the corresponding edge gradient values to obtain an edge gradient matrix of the infrared image to be enhanced.
The weight module 23 is further configured to perform edge detection on the image data matrix after gaussian filtering, and set corresponding convolution kernels for directions of a plurality of preset angles respectively; and aiming at each pixel point in the infrared image to be enhanced, obtaining gradients of the pixel points in the directions of the preset angles according to convolution calculation of the convolution kernels in the directions of the preset angles respectively.
Wherein, the weight module 23 is further configured to obtain, according to the temperature data matrix, a statistical data index as a temperature interval threshold value for dividing the temperature data into a plurality of temperature intervals through statistical analysis; the statistical data index is selected from one of the following: average, median, mode, quartile; determining the temperature interval in which each pixel point is respectively positioned according to the comparison result of the temperature value corresponding to each pixel point in the infrared image to be enhanced and the temperature interval threshold value; and respectively adopting different strategies to calculate corresponding weight values for the pixel points in different temperature intervals to obtain the self-adaptive weight matrix of the infrared image to be enhanced.
The weight module 23 is further configured to normalize, for each pixel point in the low temperature range, the temperature data of the pixel point to obtain a corresponding weight value; for each pixel point in the high temperature interval, multiplying the product of the difference between the temperature data of the pixel point and the temperature average value and the weighted intensity control parameter, and adding the temperature average value as a corresponding weight value; and obtaining the self-adaptive weight matrix of the infrared image to be enhanced according to the weight value of each pixel point.
Wherein, the adaptive enhancement module 24 is further configured to perform weighted enhancement on the edge gradient matrix by using the adaptive weight matrix to obtain an edge information matrix; and carrying out nonlinear transformation on the image data matrix of the infrared image to be enhanced to extract a background data matrix, and overlapping the background data matrix with the edge information matrix after attenuation according to a preset proportion to obtain an edge information enhanced image.
It should be noted that: in the process of implementing the edge adaptive enhancement highlighting, the infrared image edge enhancement device provided in the foregoing embodiment is only exemplified by the division of each program module, and in practical application, the processing allocation may be completed by different program modules according to needs, that is, the internal structure of the device may be divided into different program modules, so as to complete all or part of the method steps described above. In addition, the infrared image edge enhancement device provided in the above embodiment and the infrared image edge processing method embodiment belong to the same concept, and detailed implementation processes of the infrared image edge enhancement device are referred to in the method embodiment, and are not repeated here.
In another aspect, referring to fig. 8, an optional hardware structure of an image processing apparatus according to an embodiment of the present application is shown, where the image processing apparatus includes a processor 111, a memory 112 connected to the processor 111, and a computer program for storing various types of data in the memory 112 to support operation of an image processing device, where the computer program is used to implement the method for processing an infrared image edge according to any embodiment of the present application, and when the computer program is executed by the processor, the steps of the method for processing an infrared image edge according to any embodiment of the present application are implemented, and the same technical effects can be achieved, so that repetition is avoided and no further description is given here.
The embodiment of the application also provides a computer readable storage medium, on which a computer program is stored, which when executed by a processor, implements the processes of the above embodiment of the infrared image edge processing method, and can achieve the same technical effects, so that repetition is avoided, and no further description is given here. Wherein, the computer readable storage medium is Read-only memory (ROM), random Access Memory (RAM), magnetic disk or optical disk, etc.
It should be noted that, in this document, 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 one … …" does not exclude the presence of other like elements in a process, method, article, or apparatus that comprises the element.
From the above description of the embodiments, it will be clear to those skilled in the art that the above-described embodiment method may be implemented by means of software plus a necessary general hardware platform, but of course may also be implemented by means of hardware, but in many cases the former is a preferred embodiment. Based on such understanding, the technical solution of the present application may be embodied essentially or in a part contributing to the prior art in the form of a software product stored in a storage medium (e.g. ROM/RAM, magnetic disk, optical disk) comprising instructions for causing a terminal (which may be a mobile phone, a computer, an infrared imaging device, etc.) to perform the method according to the embodiments of the present application.
The foregoing is merely illustrative of the present application, and the present application is not limited thereto, and any person skilled in the art will readily recognize that variations or substitutions are within the scope of the present application. Therefore, the protection scope of the present application shall be subject to the protection scope of the claims.
Claims (12)
1. A method for infrared image edge enhancement, comprising:
Acquiring a temperature data matrix and an image data matrix corresponding to an infrared image to be enhanced;
performing edge detection based on the image data matrix, and calculating corresponding edge gradient values according to gradients of each pixel point in the infrared image to be enhanced in at least two directions to obtain an edge gradient matrix of the infrared image to be enhanced;
determining a temperature interval threshold according to the temperature data matrix, and respectively adopting different strategies to calculate corresponding weight values for the pixel points in different temperature intervals according to the comparison result of the temperature values corresponding to the pixel points in the infrared image to be enhanced and the temperature interval threshold to obtain an adaptive weight matrix of the infrared image to be enhanced;
and carrying out self-adaptive weighted enhancement on the infrared image to be enhanced through the self-adaptive weight matrix and the edge gradient matrix to obtain an edge information enhanced image.
2. The method for enhancing an edge of an infrared image according to claim 1, wherein said adaptively weighting enhancing the infrared image to be enhanced by the adaptive weight matrix and the edge gradient matrix comprises, before obtaining an edge information enhanced image:
And carrying out enhancement processing on the edge information of the infrared image to be enhanced, which is obtained based on the edge gradient matrix, so as to obtain an updated edge gradient matrix after enhancement.
3. The method for enhancing an edge of an infrared image according to claim 2, wherein the enhancing the edge information of the infrared image to be enhanced obtained based on the edge gradient matrix to obtain an updated edge gradient matrix after enhancement comprises:
obtaining an updated edge gradient matrix after enhancement based on the product of the edge gradient matrix and a preset enhancement multiple; or alternatively, the first and second heat exchangers may be,
and determining a gradient value range according to the edge gradient matrix, normalizing the edge gradient matrix according to the gradient value range, and multiplying the normalized edge gradient matrix by a preset linear stretch coefficient to obtain an enhanced updated edge gradient matrix.
4. The method of infrared image edge enhancement as set forth in claim 2, wherein the post-enhancement updated edge gradient matrix comprises:
dividing the edge gradient matrix after the enhancement treatment according to a set threshold value, and setting the values of elements smaller than the set threshold value in the edge gradient matrix to zero to obtain an updated edge gradient matrix after the enhancement treatment.
5. The method for enhancing an edge of an infrared image according to claim 1, wherein the edge detection based on the image data matrix calculates corresponding edge gradient values according to gradients of each pixel point in the infrared image to be enhanced in at least two directions, respectively, to obtain an edge gradient matrix of the infrared image to be enhanced, and the method comprises:
performing Gaussian filtering based on the image data matrix;
performing edge detection on the Gaussian filtered image data matrix, and calculating gradients of each pixel point in the infrared image to be enhanced in at least two directions;
and summing absolute values according to the gradients of each pixel point in all directions, and calculating the corresponding edge gradient values to obtain an edge gradient matrix of the infrared image to be enhanced.
6. The method for enhancing an infrared image edge according to claim 5, wherein said edge detecting said image data matrix after gaussian filtering, calculating gradients of each pixel point in said infrared image to be enhanced in at least two directions, respectively, comprises:
performing edge detection on the Gaussian filtered image data matrix, and respectively setting corresponding convolution kernels for the directions of a plurality of preset angles;
And aiming at each pixel point in the infrared image to be enhanced, obtaining gradients of the pixel points in the directions of the preset angles according to convolution calculation of the convolution kernels in the directions of the preset angles respectively.
7. The method for enhancing an edge of an infrared image according to claim 1, wherein determining a temperature interval threshold according to the temperature data matrix, and calculating corresponding weight values for the pixel points in different temperature intervals according to a comparison result of the temperature values corresponding to the pixel points in the infrared image to be enhanced and the temperature interval threshold by using different strategies to obtain an adaptive weight matrix of the infrared image to be enhanced, comprises:
according to the temperature data matrix, obtaining a statistical data index through statistical analysis to serve as a temperature interval threshold for dividing the temperature data into a plurality of temperature intervals; the statistical data index is selected from one of the following: average, median, mode, quartile;
determining the temperature interval in which each pixel point is respectively positioned according to the comparison result of the temperature value corresponding to each pixel point in the infrared image to be enhanced and the temperature interval threshold value;
And respectively adopting different strategies to calculate corresponding weight values for the pixel points in different temperature intervals to obtain the self-adaptive weight matrix of the infrared image to be enhanced.
8. The method of claim 1, wherein the temperature interval threshold comprises a temperature average value, and the temperature interval comprises a high temperature interval and a low temperature interval divided by the temperature average value; the method for obtaining the self-adaptive weight matrix of the infrared image to be enhanced comprises the following steps of:
for each pixel point in the low temperature interval, taking the normalized value of the temperature data of the pixel point as the corresponding weight value;
for each pixel point in the high temperature interval, multiplying the product of the difference between the temperature data of the pixel point and the temperature average value and the weighted intensity control parameter, and adding the temperature average value as a corresponding weight value;
and obtaining the self-adaptive weight matrix of the infrared image to be enhanced according to the weight value of each pixel point.
9. The method for enhancing an edge of an infrared image according to claim 1, wherein said adaptively weighting enhancing the infrared image to be enhanced by the adaptive weight matrix and the edge gradient matrix to obtain an edge information enhanced image comprises:
Weighting and enhancing the edge gradient matrix by utilizing the self-adaptive weight matrix to obtain an edge information matrix;
and carrying out nonlinear transformation on the image data matrix of the infrared image to be enhanced to extract a background data matrix, and overlapping the background data matrix with the edge information matrix after attenuation according to a preset proportion to obtain an edge information enhanced image.
10. An infrared image edge enhancement device, comprising:
the acquisition module is used for acquiring a temperature data matrix and an image data matrix corresponding to the infrared image to be enhanced;
the edge extraction module is used for carrying out edge detection based on the image data matrix, and calculating corresponding edge gradient values according to gradients of each pixel point in the infrared image to be enhanced in at least two directions respectively to obtain an edge gradient matrix of the infrared image to be enhanced;
the weight module is used for determining a temperature interval threshold according to the temperature data matrix, and calculating corresponding weight values of the pixel points in different temperature intervals by adopting different strategies according to a comparison result of the temperature values corresponding to the pixel points in the infrared image to be enhanced and the temperature interval threshold to obtain an adaptive weight matrix of the infrared image to be enhanced;
And the self-adaptive enhancement module is used for carrying out self-adaptive weighted enhancement on the infrared image to be enhanced through the self-adaptive weight matrix and the edge gradient matrix to obtain an edge information enhanced image.
11. An image processing apparatus comprising a processor, a memory coupled to the processor, and a computer program stored on the memory and executable by the processor;
the computer program, when executed by the processor, implements the infrared image edge enhancement method as claimed in any one of claims 1 to 9.
12. A computer readable storage medium, characterized in that the computer readable storage medium has stored thereon a computer program which, when executed by the processor, implements the infrared image edge enhancement method according to any of claims 1 to 9.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202311094644.7A CN117115029A (en) | 2023-08-28 | 2023-08-28 | Infrared image edge enhancement method, device and equipment and storage medium |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202311094644.7A CN117115029A (en) | 2023-08-28 | 2023-08-28 | Infrared image edge enhancement method, device and equipment and storage medium |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN117115029A true CN117115029A (en) | 2023-11-24 |
Family
ID=88807239
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202311094644.7A Pending CN117115029A (en) | 2023-08-28 | 2023-08-28 | Infrared image edge enhancement method, device and equipment and storage medium |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN117115029A (en) |
-
2023
- 2023-08-28 CN CN202311094644.7A patent/CN117115029A/en active Pending
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| Liu et al. | Automatic cloud detection for all-sky images using superpixel segmentation | |
| KR102336064B1 (en) | Imaging apparatus and imaging method thereof, image processing apparatus and image processing method thereof, and program | |
| CN108197546B (en) | Illumination processing method and device in face recognition, computer equipment and storage medium | |
| KR101662846B1 (en) | Apparatus and method for generating bokeh in out-of-focus shooting | |
| CN109003249B (en) | Method, device and terminal for enhancing image details | |
| US9619708B2 (en) | Method of detecting a main subject in an image | |
| US8184196B2 (en) | System and method to generate depth data using edge detection | |
| CN105100632B (en) | The method of adjustment and device of imaging device automatic exposure, imaging device | |
| US20180225522A1 (en) | Ir or thermal image enhancement method based on background information for video analysis | |
| KR101361644B1 (en) | Image processing device and image defogging method | |
| CN111444555B (en) | Temperature measurement information display method and device and terminal equipment | |
| CN114584700B (en) | Focusing marking method, marking device and electronic equipment | |
| WO2017091268A2 (en) | Measurement of non-uniformity noise | |
| CN114529566B (en) | Image processing method, device, equipment and storage medium | |
| JP2013542528A (en) | Night scene image blur detection system | |
| CN114140481A (en) | Edge detection method and device based on infrared image | |
| CN117011296B (en) | Method, equipment and storage medium for quickly detecting tracking precision of photoelectric pod | |
| Chen et al. | Hybrid saliency detection for images | |
| CN111062954B (en) | Infrared image segmentation method, device and equipment based on difference information statistics | |
| CN116543022A (en) | Gas infrared image processing method, gas leak detector and storage medium | |
| CN114764771A (en) | Image quality evaluation method, device, equipment, chip and storage medium | |
| CN110688926B (en) | Subject detection method and apparatus, electronic device, and computer-readable storage medium | |
| CN108805883B (en) | Image segmentation method, image segmentation device and electronic equipment | |
| CN117115029A (en) | Infrared image edge enhancement method, device and equipment and storage medium | |
| CN115115653A (en) | Refined temperature calibration method for cold and hot impact test box |
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 |