CN114581644B - Imaging method and device for infrared image of high-temperature target - Google Patents
Imaging method and device for infrared image of high-temperature target Download PDFInfo
- Publication number
- CN114581644B CN114581644B CN202210493768.1A CN202210493768A CN114581644B CN 114581644 B CN114581644 B CN 114581644B CN 202210493768 A CN202210493768 A CN 202210493768A CN 114581644 B CN114581644 B CN 114581644B
- Authority
- CN
- China
- Prior art keywords
- image
- molten steel
- target
- correction
- 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.)
- Active
Links
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/23—Clustering techniques
-
- Y—GENERAL TAGGING OF NEW TECHNOLOGICAL DEVELOPMENTS; GENERAL TAGGING OF CROSS-SECTIONAL TECHNOLOGIES SPANNING OVER SEVERAL SECTIONS OF THE IPC; TECHNICAL SUBJECTS COVERED BY FORMER USPC CROSS-REFERENCE ART COLLECTIONS [XRACs] AND DIGESTS
- Y02—TECHNOLOGIES OR APPLICATIONS FOR MITIGATION OR ADAPTATION AGAINST CLIMATE CHANGE
- Y02P—CLIMATE CHANGE MITIGATION TECHNOLOGIES IN THE PRODUCTION OR PROCESSING OF GOODS
- Y02P90/00—Enabling technologies with a potential contribution to greenhouse gas [GHG] emissions mitigation
- Y02P90/30—Computing systems specially adapted for manufacturing
Landscapes
- Engineering & Computer Science (AREA)
- Data Mining & Analysis (AREA)
- Theoretical Computer Science (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Bioinformatics & Cheminformatics (AREA)
- Bioinformatics & Computational Biology (AREA)
- Artificial Intelligence (AREA)
- Evolutionary Biology (AREA)
- Evolutionary Computation (AREA)
- Physics & Mathematics (AREA)
- General Engineering & Computer Science (AREA)
- General Physics & Mathematics (AREA)
- Life Sciences & Earth Sciences (AREA)
- Radiation Pyrometers (AREA)
Abstract
An imaging unit of the infrared imaging device acquires an infrared image comprising molten steel, and an image correction unit comprises a target identification module used for identifying the molten steel of a high-temperature target, a molten steel related object and a background target according to the temperature of the infrared image; the central processing unit executes an image compression module and an image segmentation module of the image correction unit, and compresses and segments the high-temperature target corresponding to the molten steel image by using a gray level compression algorithm; the central processing unit and the graphic processor jointly execute the image enhancement of the image enhancement module; and the graphic synthesis display unit performs image pixel balanced rendering, synthesizes the gray levels of the high-temperature target molten steel, the molten steel related objects and the background target image to obtain a target image, and renders and displays the target image. The infrared image processed by the method has prominent high-temperature target details and soft and clear and recognizable background, and the image detail information identification capability of an imaging system is improved.
Description
Technical Field
The invention relates to the technical field of infrared imaging, in particular to an imaging method and device for an infrared image of a high-temperature target.
Background
For an observation environment with large temperature difference between a target and a background, particularly for image monitoring of high-temperature molten steel, an infrared imaging device with a scene containing a high-temperature target all the time has the advantages that the gray level difference between the target and the background is large, the dynamic range reaches the limit of an infrared detector, the image is enhanced by directly using a traditional infrared image enhancement algorithm, the high-temperature target is easily excessively enhanced, the details of the high-temperature target are lost, or the background is excessively enhanced, so that the details of the background are blurred, and an ideal effect of clearly seeing the background and the details of the target is difficult to obtain.
Moreover, due to the distance between the infrared imaging device and the molten steel of the high-temperature target, the temperature of the components such as the central processing unit of the infrared imaging device will also rise with time, which affects the image processing efficiency of the infrared imaging device, and thus the image imaging quality of the infrared imaging device is affected.
Therefore, the problems of the prior art are to be further improved and developed.
Disclosure of Invention
The object of the invention is: to solve the above problems in the prior art, it is an object of the present invention to provide an imaging method and an imaging apparatus for infrared imaging of a high temperature target.
The technical scheme is as follows: in order to solve the technical problem, the technical scheme provides an imaging method of a high-temperature target infrared image, which is applied to imaging of a steel plant molten steel image and specifically comprises the following steps:
firstly, an imaging unit of an infrared imaging device acquires an infrared image comprising molten steel; the image correction unit comprises a target identification module, and the target identification module is used for identifying high-temperature target molten steel, molten steel related objects and background targets according to the temperature distribution of the infrared image;
step two, the central processing unit executes an image compression module and an image segmentation module of the image correction unit, and compresses and segments high-temperature target molten steel, molten steel related objects and background targets corresponding to molten steel images by using a gray level compression algorithm;
thirdly, the central processing unit and the graphic processor jointly execute and complete the image enhancement of the image enhancement module, so that different enhancement modes of the high-temperature target molten steel, the molten steel related object and the background object in the image are selected to obtain an enhanced image of the high-temperature target molten steel, the molten steel related object and the background object;
and step four, the image synthesis display unit receives the images of the high-temperature target molten steel, the molten steel related objects and the background target after enhancement, performs image pixel balanced rendering, synthesizes the gray levels of the high-temperature target molten steel, the molten steel related objects and the background target image to obtain a target image, and renders and displays the target image.
The imaging method of the high-temperature target infrared image is characterized in that the temperature of the high-temperature target molten steel is above a first threshold value, and the temperature of a molten steel related object is in a numerical interval between a second threshold value and the first threshold value.
The imaging method of the infrared image of the high-temperature target is characterized in that the first threshold is preferably 1000 ℃, and the second threshold is preferably 500 ℃, namely the temperature of the liquid steel related object is between 500 ℃ and 1000 ℃.
The imaging method of the high-temperature target infrared image comprises the following steps that the image enhancement module has two modes of a standard enhancement mode and an optimized enhancement mode: the standard enhancement mode is applicable to the performance of the central processing unit and is more than or equal to a third threshold, and the optimized enhancement mode is applicable to the performance of the central processing unit and is less than the third threshold; the central processing unit is provided with a mode switch, and the graphic processor is controlled to switch between a standard enhancement mode and an optimized enhancement mode according to the performance of the central processing unit.
The imaging method of the infrared image of the high-temperature target is characterized in that the third threshold value is 90%.
According to the imaging method of the high-temperature target infrared image, the image processor is provided with two parallel correction pipelines for each frame of image, the first correction pipeline is a standard correction pipeline, and the second correction pipeline is an optimized correction pipeline;
the standard correction pipeline comprises three correction pipelines which are arranged in parallel, the first correction pipeline corresponds to high-temperature target molten steel, the second correction pipeline corresponds to a molten steel related object, the third correction pipeline corresponds to a background target, and the standard correction pipeline corresponds to a standard enhancement mode;
the optimized correction pipeline comprises three parallel correction pipelines, a first auxiliary correction pipeline corresponds to high-temperature target molten steel, a second auxiliary correction pipeline corresponds to a molten steel related object, a third auxiliary correction pipeline corresponds to a background target, and the optimized correction pipeline corresponds to an optimized enhancement mode.
According to the imaging method of the high-temperature target infrared image, the standard enhancement mode, the first correction pipeline, the second correction pipeline and the third correction pipeline adopt a standard gray scale linear transformation algorithm, and a video memory of the graphic processor stores general gray scale enhancement coefficients corresponding to different correction pipelines.
According to the imaging method of the high-temperature target infrared image, in the optimization enhancement mode, a first auxiliary modification pipeline adopts a gray scale enhancement algorithm of gray scale power conversion and Gamma correction, a second auxiliary modification pipeline adopts a gray scale enhancement algorithm of gray scale power conversion, and a third auxiliary modification pipeline adopts a gray scale logarithm conversion enhancement algorithm.
The imaging device of the infrared image of the high-temperature target is applied to the imaging of the molten steel image of the steel plant, and comprises an imaging unit, an image correction unit and a graph synthesis display unit;
the imaging unit acquires an infrared image comprising molten steel; the image correction unit comprises a target identification module, and the target identification module is used for identifying high-temperature target molten steel, molten steel related objects and background targets according to the temperature distribution corresponding to the infrared image;
the central processing unit executes an image compression module and an image segmentation module of the image correction unit, and compresses and segments the high-temperature target molten steel, the molten steel related object and the background object corresponding to the molten steel image by using a gray level compression algorithm;
the central processor and the graphic processor jointly execute and complete the image enhancement of the image enhancement module, so that the high-temperature target molten steel, the molten steel related object and the background object in the image are enhanced in different enhancement modes to obtain an enhanced image of the high-temperature target molten steel, the molten steel related object and the background object;
and the graphic synthesis display unit receives the enhanced images of the high-temperature target molten steel, the molten steel related object and the background target, performs image pixel balanced rendering, synthesizes the gray levels of the high-temperature target molten steel, the molten steel related object and the background target image to obtain a target image, and renders and displays the target image.
(III) the beneficial effects are as follows: after the imaging method of the high-temperature target infrared image provided by the invention processes the infrared image of the high-temperature target, the details of the high-temperature target are prominent, the background is soft and clear and can be distinguished, and the image detail information identification capability of the high-temperature target infrared imaging system is obviously improved.
Drawings
FIG. 1 is a schematic diagram of the steps of the method for imaging an infrared image of a high temperature target according to the present invention;
FIG. 2 is a comparison graph of the effect of infrared images including molten steel before and after being processed by the imaging method of infrared images of high temperature targets of the present invention.
Detailed Description
The present invention will be described in further detail with reference to preferred embodiments, and more details are set forth in the following description in order to provide a thorough understanding of the present invention, but it is apparent that the present invention can be embodied in many other forms different from the description herein and can be similarly generalized and deduced by those skilled in the art based on the practical application without departing from the spirit of the present invention, and therefore, the scope of the present invention should not be limited by the contents of this detailed embodiment.
The drawings are schematic representations of embodiments of the invention, and it is noted that the drawings are intended only as examples and are not drawn to scale and should not be construed as limiting the true scope of the invention.
The invention relates to an imaging method of a high-temperature target infrared image, which is applied to imaging of a steel mill molten steel image, wherein an infrared imaging device comprises an imaging unit, an image correction unit and an image synthesis display unit; the image correction unit comprises a target recognition module, and the target recognition module is used for recognizing high-temperature target molten steel, molten steel related objects and background targets according to the temperature distribution corresponding to the infrared image, preferably the temperature distribution of the pixel group. The temperature of the high temperature target molten steel is above a first threshold value, preferably 1000 ℃, and the temperature of the molten steel related object is within a numerical range between a second threshold value, preferably 500 ℃, and the first threshold value, i.e. the temperature of the molten steel related object is between 500 ℃ and 1000 ℃. The invention not only identifies the image of the high-temperature target molten steel, but also identifies the high-temperature molten steel related objects around the target molten steel so as to identify the high-temperature molten steel related objects including molten steel steam, the periphery of molten steel bearing objects and the like, namely the image of a high-temperature object adjacent to the target molten steel. According to the invention, through identifying the molten steel related object, the infrared image enhancement processing range is increased, and the high-temperature target molten steel, the molten steel related object and the background target are processed by different enhancement modes and/or different enhancement coefficients, so that the molten steel image is imaged more clearly, and more imaging details are displayed.
The infrared imaging device is specially used for shooting and applying to a steel plant to identify and display molten steel images, and in order to improve the processing speed of the images in a high-temperature environment, the infrared imaging device is provided with a unique Central Processing Unit (CPU) and a Graphic Processing Unit (GPU), and image processing methods for the CPU and the GPU are provided to improve the image processing speed and the image display effect.
The imaging method of the high-temperature target infrared image is applied to the imaging of the molten steel image in the steel plant, and specifically comprises the following steps as shown in figure 1:
firstly, an imaging unit of an infrared imaging device acquires an infrared image comprising molten steel; the image correction unit comprises a target identification module, wherein the target identification module is used for identifying high-temperature target molten steel, molten steel related objects and background targets according to the temperature distribution of the infrared image, preferably the temperature distribution corresponding to a pixel group of the infrared image;
the central processing unit executes an image compression module and an image segmentation module of the image correction unit, and compresses and segments high-temperature target molten steel, molten steel related objects and background targets corresponding to the molten steel image by using a gray compression algorithm;
thirdly, the central processing unit and the graphic processor jointly execute and complete the image enhancement of the image enhancement module, so that different enhancement modes and/or enhancement coefficients are selected for the high-temperature target molten steel, the molten steel related object and the background object in the image, and the enhanced image of the high-temperature target molten steel, the molten steel related object and the background object is obtained;
and step four, the image synthesis display unit receives the high-temperature target molten steel, the molten steel related object and the background target enhanced image, performs image pixel balanced rendering, synthesizes the gray levels of the high-temperature target molten steel, the molten steel related object and the background target image to obtain a target image, and renders and displays the target image.
The image correction unit comprises an image compression module, an image segmentation module and an image enhancement module, wherein the image compression module and the image segmentation module are executed by a central processing unit, and the image enhancement module selects different enhancement modes or enhancement coefficients for high-temperature target molten steel, molten steel related objects and background targets. The image enhancement module is realized by a central processing unit and a graphic processor.
The compression module realizes gray level compression of high-temperature target molten steel, molten steel related objects and background targets in the original image. The segmentation module carries out image segmentation on high-temperature target molten steel, molten steel related objects and a background target part in the original image. The segmented image is sent to different correction pipelines of the graphics processor for processing.
The compression module compresses the molten steel of the high-temperature target, the molten steel related objects and the gray scale of the background target, and comprises the following steps:
step 21, the compression module counts the histogram of the image
And accumulating the histogram.
And step 22, segmenting the three temperature intervals of the image by the compression module to obtain a high-temperature interval, a medium-temperature interval and a low-temperature interval of the image. The specific segmentation method is that a part of the square image pixel above a first threshold is taken as a high-temperature interval, a temperature interval range between the first threshold and a second threshold is a medium-temperature interval, and a part of the square image pixel below the second threshold is taken as a low-temperature interval.
And step 23, the compression module performs linear transformation on the high-temperature interval, the medium-temperature interval and the low-temperature interval of the image.
The stretching interval is 5% of the display range, the calculation formula is as follows,
in order to conform to the gray levels of the pixels in different temperature intervals,
the segmentation module segments high-temperature target molten steel, molten steel related objects and background targets. The segmentation module can segment the high-temperature target, the medium-temperature target and the low-temperature target in the original image by adopting a grayscale clustering segmentation method, namely, the grayscale region image (l, l +1 … h) between the high-temperature interval, the medium-temperature interval and the low-temperature interval, and specifically comprises the following steps:
step 31, the segmentation module sets the desired number of gray-scale classifications for the image
For the temperature of the gradation region, it is set that the segmentation expectation image includes three types of targets.
Step 32, the segmentation module randomly selects 3 types of gray levels from the image as initial clustering center gray values of 3 types; specifically, 3 gray values equally divided between l and h may be selected.
And step 33, the segmentation module calculates the distance between the gray level of each pixel in the image and the gray level of the 3 clustering centers in sequence, and divides each pixel into the class with the minimum gray level distance.
And step 34, the segmentation module respectively calculates the gray level mean values of all the newly generated pixels in each class and uses the gray level mean values as new clustering centers.
And 35, the segmentation module calculates a nonlinear target function, when the error function is smaller than 10, clustering is finished, segmentation is finished, 3 types of high-temperature target molten steel, molten steel related objects and background targets are obtained, and segmentation threshold values T1, T2 and T3 are carried out, otherwise, the steps 33 to 35 are repeated.
The nonlinear objective function is as follows:
is sent toComprising n grey levels
The constructed set is divided into k classes
And the gray level correlation in the class is strongest and the deviation of the gray level between the classes is maximized
Wherein:
for selecting objects in a data set
To the center of the cluster
The distance of (c).
The image enhancement module has a standard enhancement mode and an optimization enhancement mode, the standard enhancement mode is suitable for the performance of the central processing unit and is more than or equal to a third threshold, the third threshold is preferably 90%, namely the performance of the central processing unit occupies more than or equal to 90% due to temperature rise or process consumption and other reasons, and the image processor corrects the image by adopting the standard enhancement mode. The optimized enhancement mode is suitable for the graphics processor to perform image modification in the optimized enhancement mode only when the performance of the central processing unit is smaller than a third threshold, that is, the performance is less than 90%, and the central processing unit is provided with a mode switch to control mode switching of the graphics processor. The invention provides a graphic processor for central processing of an infrared imaging device, which aims to solve the technical problem that the performance of the central processing unit is reduced under the condition of high temperature for a long time and increase the image processing capability of the infrared imaging device. Under the optimized enhancement mode of the invention, the image processor carries out different gray level enhancement aiming at the high-temperature target molten steel, the molten steel related object and the background target image of the infrared image.
The graphic processor is provided with a graphic correction pipeline, two parallel correction pipelines are arranged for each frame of image, the first correction pipeline is a standard correction pipeline, the second correction pipeline is an optimized correction pipeline, and the standard correction pipeline and the optimized correction pipeline are connected in parallel on a graphic synthesis display unit of the graphic processor.
The standard correction pipeline comprises three correction pipelines which are arranged in parallel, the first correction pipeline corresponds to high-temperature target molten steel, the second correction pipeline corresponds to a molten steel related object, the third correction pipeline corresponds to a background target, and the standard correction pipeline corresponds to a standard enhancement mode. The optimized correction pipeline comprises three parallel correction pipelines, a first auxiliary correction pipeline corresponds to high-temperature target molten steel, a second auxiliary correction pipeline corresponds to a molten steel related object, a third auxiliary correction pipeline corresponds to a background target, and the optimized correction pipeline corresponds to an optimized enhancement mode.
The correction pipeline comprises a standard gray scale linear transformation algorithm and an optimization algorithm, and the gray scale linear transformation algorithm adopts a standard enhancement mode corresponding to the graphics processor. The optimization algorithm is corresponding to the image processor, different optimization and enhancement algorithms for optimizing and correcting pipelines are adopted, the gray level enhancement of the high-temperature target molten steel, the molten steel related objects and the background target image is calculated in detail, and the performance is optimized. And in the standard enhancement mode, namely under the condition that the load of the central processing unit is too heavy due to overhigh temperature, overlarge data processing amount and the like, the gray enhancement coefficient of the video memory threshold of the image processor is adopted, and the gray enhancement of the high-temperature target molten steel, the molten steel related objects and the background target image is rapidly calculated by adopting a standard gray linear transformation algorithm, so that the image after the infrared image enhancement is rapidly obtained.
In the standard enhancement mode, the first correction pipeline, the second correction pipeline and the third correction pipeline adopt a standard gray scale linear transformation algorithm, and the video memory of the graphics processor stores general gray scale enhancement coefficients corresponding to different correction pipelines.
In the gray scale linear transformation algorithm, a function of gray scale linear transformation is a common linear function.
g(x, y) = k · f(x, y) + d
Assuming that the gray-scale value of the source image is x, the gray-scale value after the gray-scale linear transformation is y = kx + b (0< = y < =255), and different effects of the linear transformation when the value of k is changed will be discussed below.
In the standard enhancement mode, the gray scale enhancement coefficient of the first correction pipeline stored in the video memory of the graphics processor is 0.2, the gray scale enhancement coefficient of the second correction pipeline is 0.4, and the gray scale enhancement coefficient of the third correction pipeline is 1.2. The present invention is merely exemplary of a set of preferred embodiments of the gamma enhancement factor and the other data is not limiting.
In the optimized enhancement mode, a first auxiliary modification pipeline adopts a gray enhancement algorithm of gray power transformation and Gamma correction, a second auxiliary modification pipeline adopts a gray enhancement algorithm of gray power transformation, and an auxiliary third modification pipeline adopts a gray logarithmic transformation enhancement algorithm.
The temperature of the high-temperature target molten steel is more than or equal to 1000 ℃, the non-linear transformation of the gray power transformation is adopted to carry out the exponential transformation on the gray value of the input image, the deviation on the brightness is corrected, and then the high-light part of the image is corrected by Gamma to be compressed, so that the image of the high-temperature target molten steel can display more detailed parts. The Gamma correction can be expressed by the following power function.
The second auxiliary correcting pipeline of the molten steel related object adopts gray scale power transformation to carry out gray scale enhancement, and because the temperature of the molten steel related object is lower than that of the high-temperature target molten steel, the gray scale power transformation is adopted, so that the detail display of the image at the temperature of between 500 and 1000 ℃ can be met.
The gray scale logarithmic transformation enhancement algorithm of the background target part and the processing effect of enhancing the details of the dark part are better, so the method is applied to a third auxiliary correction pipeline.
And the standard correction pipeline and the optimized correction pipeline of the graphics processor are respectively connected with the image synthesis display unit and the graphics synthesis display unit. The graphic synthesis display unit is a functional module of a graphic processor, receives the image after the pipeline correction processing, performs image pixel balanced rendering, synthesizes the gray levels of the high-temperature target molten steel, the molten steel related object and the background target image to obtain a target image, and renders and displays the target image.
The graphic synthesis display unit balances image pixels, namely balances the gray scale regions (pixels between l and h) of high-temperature target molten steel, molten steel related objects and a background target image by using the trimmed image histogram.
The invention provides an infrared image imaging device of a high-temperature target, namely an infrared imaging device, which comprises an imaging unit, an image correction unit and a graph synthesis display unit, wherein the imaging unit acquires an infrared image comprising molten steel; the image correction unit comprises a target identification module, and the target identification module is used for identifying high-temperature target molten steel, molten steel related objects and background targets according to the temperature distribution corresponding to the infrared image;
the central processing unit executes an image compression module and an image segmentation module of the image correction unit, and compresses and segments high-temperature target molten steel, molten steel related objects and background targets corresponding to the molten steel image by using a gray level compression algorithm;
the central processor and the graphic processor jointly execute and complete the image enhancement of the image enhancement module, so that different enhancement modes or enhancement coefficients of the high-temperature target molten steel, the molten steel related object and the background object in the image are selected to obtain an enhanced image of the high-temperature target molten steel, the molten steel related object and the background object;
and receiving the high-temperature target molten steel, the molten steel related object and the image after the background target is enhanced, performing image pixel balanced rendering, synthesizing the gray levels of the high-temperature target molten steel, the molten steel related object and the background target image to obtain a target image, and rendering and displaying the target image.
According to the imaging method and device for the infrared image of the high-temperature target, firstly, the target identification module identifies the molten steel of the high-temperature target, the molten steel related object and the background target, the invention not only identifies the high-temperature target and the background target, but also increases the molten steel related object of the high-temperature target, so that the medium-temperature object related to the high-temperature target can be properly enhanced, and the imaging range of the high-temperature target is increased, as shown in figure 2, the imaging method and device are very important for identifying and observing the actual image of the molten steel, the obtained infrared image with prominent high-temperature target details, increased high-temperature targets and soft and clear background is obtained, and the image detail information identification capability of the infrared imaging device of the high-temperature target is obviously improved.
The above description is provided for the purpose of illustrating the preferred embodiments of the present invention and will assist those skilled in the art in more fully understanding the technical solutions of the present invention. However, these examples are merely illustrative, and the embodiments of the present invention are not to be considered as being limited to the description of these examples. For those skilled in the art to which the invention pertains, several simple deductions and changes can be made without departing from the inventive concept, and all should be considered as falling within the protection scope of the invention.
Claims (7)
1. The imaging method of the high-temperature target infrared image is applied to the imaging of the molten steel image in a steel plant, and specifically comprises the following steps:
step one, an imaging unit of an infrared imaging device collects an infrared image comprising molten steel; the image correction unit comprises a target identification module, and the target identification module is used for identifying high-temperature target molten steel, molten steel related objects and background targets according to the temperature distribution of the infrared image;
step two, the central processing unit executes an image compression module and an image segmentation module of the image correction unit, and compresses and segments high-temperature target molten steel, molten steel related objects and background targets corresponding to molten steel images by using a gray level compression algorithm;
thirdly, the central processing unit and the graphic processor jointly execute and complete the image enhancement of the image enhancement module, so that the high-temperature target molten steel, the molten steel related object and the background object in the image are enhanced in different enhancement modes to obtain an image enhanced by the high-temperature target molten steel, the molten steel related object and the background object;
the image synthesis and display unit receives the high-temperature target molten steel, the molten steel related object and the background target enhanced image, performs image pixel balanced rendering, synthesizes the gray levels of the high-temperature target molten steel, the molten steel related object and the background target image to obtain a target image, and performs rendering display;
the image enhancement module has two modes of a standard enhancement mode and an optimized enhancement mode: the standard enhancement mode is applicable to the performance of the central processing unit and is more than or equal to a third threshold, and the optimized enhancement mode is applicable to the performance of the central processing unit and is less than the third threshold; the central processing unit is provided with a mode switch, and the image enhancement module is controlled by the graphic processor to be switched between a standard enhancement mode and an optimized enhancement mode according to the performance of the central processing unit;
the graphics processor is provided with two parallel correction pipelines for each frame of image, wherein the first correction pipeline is a standard correction pipeline, and the second correction pipeline is an optimized correction pipeline;
the standard correction pipeline comprises three correction pipelines which are arranged in parallel, the first correction pipeline corresponds to high-temperature target molten steel, the second correction pipeline corresponds to a molten steel related object, the third correction pipeline corresponds to a background target, and the standard correction pipeline corresponds to a standard enhancement mode;
the optimized correction pipeline comprises three parallel correction pipelines, a first auxiliary correction pipeline corresponds to high-temperature target molten steel, a second auxiliary correction pipeline corresponds to a molten steel related object, a third auxiliary correction pipeline corresponds to a background target, and the optimized correction pipeline corresponds to an optimized enhancement mode.
2. The method for imaging the infrared image of the high-temperature target according to claim 1, wherein the temperature of the molten steel of the high-temperature target is above a first threshold value, and the temperature of the molten steel related object is in a numerical range between a second threshold value and the first threshold value.
3. A method of imaging an infrared image of a high temperature target according to claim 2, characterized in that the first threshold value is preferably 1000 ℃ and the second threshold value is preferably 500 ℃, i.e. the temperature of the molten steel content is between 500 ℃ and 1000 ℃.
4. The method of claim 1, wherein the third threshold is 90%.
5. The method as claimed in claim 1, wherein in the standard enhancement mode, the first modification pipeline, the second modification pipeline and the third modification pipeline employ a standard gray scale linear transformation algorithm, and the video memory of the graphics processor stores general gray scale enhancement coefficients corresponding to different modification pipelines.
6. The method for imaging the infrared image of the high-temperature target according to claim 1, wherein in the optimized enhancement mode, a first sub-modification pipeline adopts a gray scale enhancement algorithm of gray scale power transformation and Gamma correction, a second sub-modification pipeline adopts a gray scale enhancement algorithm of gray scale power transformation, and a third sub-modification pipeline adopts a gray scale logarithm transformation enhancement algorithm.
7. The imaging device of the infrared image of the high-temperature target, apply to the molten steel image imaging of the steel plant, including the imaging unit, characterized by, also include image correction unit and figure and formate the display element, and dispose central processing unit and figure processor;
the imaging unit acquires an infrared image comprising molten steel; the image correction unit comprises a target identification module, and the target identification module is used for identifying high-temperature target molten steel, molten steel related objects and background targets according to the temperature distribution corresponding to the infrared image;
the central processing unit executes an image compression module and an image segmentation module of the image correction unit, and compresses and segments high-temperature target molten steel, molten steel related objects and background targets corresponding to the molten steel image by using a gray level compression algorithm;
the central processor and the graphic processor jointly execute and complete the image enhancement of the image enhancement module, so that the high-temperature target molten steel, the molten steel related object and the background object in the image are enhanced in different enhancement modes to obtain an enhanced image of the high-temperature target molten steel, the molten steel related object and the background object;
the image synthesis display unit receives the images of the high-temperature target molten steel, the molten steel related objects and the background target after enhancement, performs image pixel balanced rendering, synthesizes the gray levels of the high-temperature target molten steel, the molten steel related objects and the background target image to obtain a target image, and renders and displays the target image;
the image enhancement module has two modes of a standard enhancement mode and an optimized enhancement mode: the standard enhancement mode is applicable to the performance of the central processing unit and is more than or equal to a third threshold, and the optimized enhancement mode is applicable to the performance of the central processing unit and is less than the third threshold; the central processing unit is provided with a mode switch, and the image enhancement module is controlled by the graphic processor to be switched between a standard enhancement mode and an optimized enhancement mode according to the performance of the central processing unit;
the graphics processor is provided with two parallel correction pipelines for each frame of image, wherein the first correction pipeline is a standard correction pipeline, and the second correction pipeline is an optimized correction pipeline;
the standard correction pipeline comprises three correction pipelines which are arranged in parallel, the first correction pipeline corresponds to high-temperature target molten steel, the second correction pipeline corresponds to a molten steel related object, the third correction pipeline corresponds to a background target, and the standard correction pipeline corresponds to a standard enhancement mode;
the optimized correction pipeline comprises three parallel correction pipelines, a first auxiliary correction pipeline corresponds to high-temperature target molten steel, a second auxiliary correction pipeline corresponds to a molten steel related object, a third auxiliary correction pipeline corresponds to a background target, and the optimized correction pipeline corresponds to an optimized enhancement mode.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202210493768.1A CN114581644B (en) | 2022-05-08 | 2022-05-08 | Imaging method and device for infrared image of high-temperature target |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202210493768.1A CN114581644B (en) | 2022-05-08 | 2022-05-08 | Imaging method and device for infrared image of high-temperature target |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN114581644A CN114581644A (en) | 2022-06-03 |
| CN114581644B true CN114581644B (en) | 2022-07-29 |
Family
ID=81769162
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202210493768.1A Active CN114581644B (en) | 2022-05-08 | 2022-05-08 | Imaging method and device for infrared image of high-temperature target |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN114581644B (en) |
Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| KR101730886B1 (en) * | 2016-02-11 | 2017-04-28 | 주식회사 아이닉스 | Processing method for infrared image |
| CN106934782A (en) * | 2017-01-16 | 2017-07-07 | 中国计量大学 | A kind of infrared image enhancing method |
| CN113781368A (en) * | 2021-11-12 | 2021-12-10 | 国科天成科技股份有限公司 | Infrared imaging device based on local information entropy |
| CN114170103A (en) * | 2021-12-10 | 2022-03-11 | 国网上海市电力公司 | Electrical equipment infrared image enhancement method |
-
2022
- 2022-05-08 CN CN202210493768.1A patent/CN114581644B/en active Active
Patent Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| KR101730886B1 (en) * | 2016-02-11 | 2017-04-28 | 주식회사 아이닉스 | Processing method for infrared image |
| CN106934782A (en) * | 2017-01-16 | 2017-07-07 | 中国计量大学 | A kind of infrared image enhancing method |
| CN113781368A (en) * | 2021-11-12 | 2021-12-10 | 国科天成科技股份有限公司 | Infrared imaging device based on local information entropy |
| CN114170103A (en) * | 2021-12-10 | 2022-03-11 | 国网上海市电力公司 | Electrical equipment infrared image enhancement method |
Non-Patent Citations (1)
| Title |
|---|
| 基于自适应分数阶微分的红外目标增强算法;代少升等;《红外技术》;20200331(第03期);全文 * |
Also Published As
| Publication number | Publication date |
|---|---|
| CN114581644A (en) | 2022-06-03 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN101340511B (en) | Adaptive video image enhancing method based on lightness detection | |
| CN110555808B (en) | Image processing method, device, equipment and machine-readable storage medium | |
| CN110838091B (en) | Fully self-adaptive infrared image contrast enhancement method and system | |
| CN112348754B (en) | Low-illumination color image enhancement method and device | |
| KR20200089410A (en) | Low-light image correction method based on optimal gamma correction | |
| CN107409190A (en) | Signal processing apparatus, display device, signal processing method and program | |
| CN110189266B (en) | Self-adaptive rapid image enhancement method | |
| CN111340717A (en) | Image preprocessing device for uncooled thermal infrared imager | |
| CN113902641A (en) | Data center hot area distinguishing method and system based on infrared image | |
| CN111325685B (en) | Image enhancement algorithm based on multi-scale relative gradient histogram equalization | |
| CN114862722B (en) | Image brightness enhancement implementation method and processing terminal | |
| CN110969584B (en) | Low-illumination image enhancement method | |
| CN104065958A (en) | LED display screen brightness collecting system | |
| CN114581644B (en) | Imaging method and device for infrared image of high-temperature target | |
| CN107358592B (en) | Iterative global adaptive image enhancement method | |
| CN113450272A (en) | Image enhancement method based on sinusoidal curve change and application thereof | |
| CN113781368B (en) | Infrared imaging device based on local information entropy | |
| CN116452447A (en) | Low-illumination high-definition image processing method | |
| CN113393394B (en) | Low-illumination gray level image enhancement method and device based on gamma conversion and storage medium | |
| CN104065959A (en) | LED based display screen luminance uniformity assessment method | |
| CN114331925A (en) | Multi-scale relative gradient histogram equalization method and device | |
| CN113808045A (en) | Image brightness adjusting method and device | |
| CN112348760A (en) | Image processing method and system | |
| CN113822809A (en) | Dim light enhancement method and system | |
| CN106600554B (en) | Infrared image preprocessing method for vehicle-mounted night vision pedestrian detection |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |