CN117649363B - Real-time endoscope image smoke removing method - Google Patents
Real-time endoscope image smoke removing method Download PDFInfo
- Publication number
- CN117649363B CN117649363B CN202410117788.8A CN202410117788A CN117649363B CN 117649363 B CN117649363 B CN 117649363B CN 202410117788 A CN202410117788 A CN 202410117788A CN 117649363 B CN117649363 B CN 117649363B
- Authority
- CN
- China
- Prior art keywords
- image
- smoke
- haze
- defogging
- value
- 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
- 238000000034 method Methods 0.000 title claims abstract description 89
- 239000000779 smoke Substances 0.000 title claims abstract description 88
- 238000004364 calculation method Methods 0.000 claims abstract description 29
- 238000005282 brightening Methods 0.000 claims abstract description 10
- 238000005286 illumination Methods 0.000 claims abstract description 10
- 238000002834 transmittance Methods 0.000 claims abstract description 9
- 239000003086 colorant Substances 0.000 claims description 3
- 230000003044 adaptive effect Effects 0.000 claims description 2
- 230000008569 process Effects 0.000 abstract description 20
- 238000012545 processing Methods 0.000 abstract description 4
- 230000000694 effects Effects 0.000 description 11
- 238000004088 simulation Methods 0.000 description 10
- 238000001914 filtration Methods 0.000 description 9
- 230000002146 bilateral effect Effects 0.000 description 7
- 238000004422 calculation algorithm Methods 0.000 description 7
- 238000010586 diagram Methods 0.000 description 4
- 238000002324 minimally invasive surgery Methods 0.000 description 4
- 238000012795 verification Methods 0.000 description 4
- 230000006870 function Effects 0.000 description 3
- 238000001356 surgical procedure Methods 0.000 description 3
- 230000009286 beneficial effect Effects 0.000 description 2
- 230000008859 change Effects 0.000 description 2
- 238000009825 accumulation Methods 0.000 description 1
- 230000015556 catabolic process Effects 0.000 description 1
- 238000007796 conventional method Methods 0.000 description 1
- 238000006731 degradation reaction Methods 0.000 description 1
- 238000013461 design Methods 0.000 description 1
- 238000003745 diagnosis Methods 0.000 description 1
- 201000010099 disease Diseases 0.000 description 1
- 208000037265 diseases, disorders, signs and symptoms Diseases 0.000 description 1
- 238000003384 imaging method Methods 0.000 description 1
- 230000006872 improvement Effects 0.000 description 1
- 238000007689 inspection Methods 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 238000005457 optimization Methods 0.000 description 1
- 230000005855 radiation Effects 0.000 description 1
- 238000011084 recovery Methods 0.000 description 1
- 238000011160 research Methods 0.000 description 1
- 238000012827 research and development Methods 0.000 description 1
- 238000006467 substitution reaction Methods 0.000 description 1
- 230000001131 transforming effect Effects 0.000 description 1
- 230000000007 visual effect Effects 0.000 description 1
Landscapes
- Image Processing (AREA)
Abstract
The medical image processing technologyThe technical field, in particular to a real-time endoscopic image smoke removing method, which comprises the following steps: step S1: obtaining an endoscope original image from the lumen of a target object; step S2: judging whether the original image has smoke or not, if so, performing the next step, and if not, outputting the image; step S3: obtaining a relational expression between the haze-free image and the original image according to an atmospheric illumination theory:wherein, the method comprises the steps of, wherein,as the original image is to be taken,in the form of a haze-free image,the transmittance is that A is the atmospheric illumination value; step S4: defogging the original image according to the relation, and dynamically adjustingThe smoke removal intensity is controlled by the value of (2) and is continued until the smoke is completely removed, so that a haze-free image is obtained; step S5: and dynamically brightening the haze-free image through a calculation formula, and outputting the image. The invention improves the safety guarantee in the whole minimally invasive treatment process by dynamically adjusting the smoke removal intensity in the smoke removal process.
Description
Technical Field
The invention relates to the technical field of medical image processing, in particular to a real-time endoscopic image smoke removal method.
Background
At present, the medical level is better and better, the operation is also gradually minimally invasive, on one hand, the pain of a patient can be relieved through minimally invasive operation, on the other hand, the recovery speed of the patient can be increased, and meanwhile, the bed changing rate of a hospital is improved, so that the hospital can diagnose and treat more patients. An important component in minimally invasive surgery is an endoscope camera system, which is equivalent to the eyes of a doctor, and can provide the doctor with an image in a lumen after the endoscope camera system extends into the lumen of an observation object so as to be observed by the doctor, thereby being beneficial to the diagnosis of diseases and the implementation of surgery. It is important to ensure the stability and smoothness of the picture. However, during surgery, it is often necessary to cauterize or ablate tissue using a laser, which can generate a large amount of smoke that can interfere with the vision of the surgeon and present a certain risk to the surgery.
The conventional method for removing smoke of the endoscope mainly comprises a physical removing method, and different smoke removing devices are designed for different application scenes and matched with the endoscope for use so as to timely discharge smoke, so that the purpose of removing the smoke is achieved, but the implementation cost of the method is high, and the defogging effect is poor. Aiming at the problems in the prior art, a plurality of efforts are made by the person skilled in the art, for example, a Chinese patent application CN2022116997787 proposes a medical endoscope image rapid defogging method and a medical endoscope image rapid defogging system, defogging treatment is carried out on a smoke area image by utilizing a foggy day image degradation physical model, but the defogging effect is weaker, the image is easy to influence, and the safety guarantee in the whole minimally invasive treatment process is lower.
Disclosure of Invention
In order to solve the problems, the invention provides a real-time smoke removing method for an endoscope image, which dynamically adjusts the smoke removing intensity in the smoke removing process by dynamically adjusting the value of the transmissivity, improves the smoke removing effect of the endoscope image and improves the safety guarantee in the whole minimally invasive treatment process.
In order to achieve the above purpose, the technical scheme adopted by the invention is a real-time method for removing smoke from an endoscope image, comprising the following steps:
step S1: obtaining an endoscope original image from the lumen of a target object;
step S2: judging whether the original image has smoke or not, if so, performing the next step, and if not, outputting the image;
step S3: obtaining a relational expression between the haze-free image and the original image according to an atmospheric illumination theory:wherein, the method comprises the steps of, wherein,as the original image is to be taken,in the form of a haze-free image,the transmittance is that A is the atmospheric illumination value;
step S4: defogging the original image according to the relation, and dynamically adjustingThe smoke removal intensity is controlled by the value of (2) and is continued until the smoke is completely removed, so that a haze-free image is obtained;
step S5: and dynamically brightening the haze-free image through a calculation formula, and outputting the image.
Further, in step S2, the specific method for determining whether there is smoke in the original image is as follows:
step S2-1: computing dark channel imagesThe calculation formula is specifically as follows:
whereinIn the case of a dark channel image,r, G, B, R, G, B are the three basic colors of the image, red, green, blue,，for any subset within the local area window,，a window that is a local area;
step S2-2: counting the number of pixels with the pixel value between LumTh1 and LumTh2 in the dark channel image, and recording asThe calculation formula is as follows:
wherein LumTh1 and LumTh2 represent a first pixel threshold and a second pixel threshold, respectively,is a sum function;
step S2-3: counting the number of pixels with the pixel value between LumTh3 and LumTh4 of the dark channel image, and recording asThe calculation formula is as follows:
wherein LumTh3 and LumTh4 represent a third pixel threshold and a fourth pixel threshold, respectively;
step S2-4: the percentage of smoke concentration was calculated:the calculation formula is as follows:
；
step S2-5: setting the smoke concentration threshold value asAnd comparing the percentage smoke concentration with a smoke concentration threshold ifGreater thanAnd judging that smoke exists, otherwise, judging that no smoke exists.
Further, in step S4, the specific method for defogging the original image according to the relation is as follows:
step S4-1: calculating transmittanceThe calculation formula is as follows:
wherein, the method comprises the steps of, wherein,in order to adjust the control parameters of the smoke removal intensity,an offset value for the haze-free region;
step S4-2: setting A as a fixed value to enable；
Step S4-3: according toAndand calculating to obtain the haze-free image based on a relation between the haze-free image and the original image.
Further, in step S4-1, the process is performed byAnd (3) withAndRelational regulation and control betweenTo dynamically adjust the size of (a)Is a value of (2); the relation is:wherein, the method comprises the steps of, wherein,is thatIs set to be a minimum value of (c),is thatIs set at the maximum value of (c),is an integral multiplication factor.
Further, in step S4-3, the calculation formula for calculating the haze-free image is as follows:。
further, in step S5, a calculation formula for dynamically brightening the haze-free image specifically includes:wherein, the method comprises the steps of, wherein,in order to lighten the image after it has been rendered,is the self-adaptive gamma adjustment quantity.
Further, the self-adaptive gamma adjustment amountThe calculation formula of (2) is as follows:
whereinRepresentation ofIs set to be a minimum value of (c),representation ofIs set at the maximum value of (c),is a multiplication factor.
The technical scheme of the invention has the beneficial effects that:
1. the invention carries out defogging treatment on the original image through the relation between the defogging image and the original image, and is based on transmissivitySolving a haze-free image by the atmospheric illumination value A and dynamically adjustingThe smoke removing effect is improved, and the safety guarantee is provided for the minimally invasive surgery process. Meanwhile, the smoke removal intensity is dynamically adjusted in the defogging process, the influence on images during smoke removal is avoided, and the safety in the minimally invasive surgery process is further ensured.
2. Before defogging treatment is carried out on the original image, whether the original image has smoke or not is judged, the original image without the smoke can be protected from being influenced, the visual sense of the picture can be further ensured, and the burden in the image processing process is reduced.
3. According to the invention, after the smoke removal treatment is carried out on the original image, the dynamic brightening treatment is carried out on the non-fog image, so that the influence on the appearance caused by the darkness of the local area of the image is avoided, the safety in the minimally invasive surgery process is further ensured, and the fatigue of a doctor for watching the image is reduced.
Drawings
In order that the invention may be more readily understood, a more particular description of the invention will be rendered by reference to specific embodiments that are illustrated in the appended drawings.
Fig. 1 is a flow chart of a method of smoke removal of an endoscopic image in real time.
Fig. 2 is a simulation result diagram of an input image of the FPGA.
Fig. 3 is a diagram of simulation results after the FPGA process is completed.
Fig. 4 is a comparison of images before defogging and after defogging, wherein the left image is an image before defogging and the right image is an image after defogging.
Fig. 5 is an original image obtained by an endoscope.
Fig. 6 is a defogged image obtained by the dark channel defogging method.
FIG. 7 is a defogged image obtained by an adaptive histogram equalization method that limits contrast
Fig. 8 is a defogged image obtained by the defogging method of multi-scale Retinex.
Fig. 9 is a defogged image obtained by the rapid defogging method.
Fig. 10 is a defogged image obtained by a real-time defogging method based on bilateral filtering.
Fig. 11 is a defogged image obtained by the defogging method proposed by the present invention.
Detailed Description
The following description of the present invention is provided with reference to the accompanying drawings, but is not limited to the following description, and any modifications or equivalent substitutions of the present invention should be included in the scope of the present invention without departing from the spirit and scope of the present invention.
As shown in fig. 1, the present embodiment provides a real-time endoscopic image smoke removal method, including:
step S1: an original image of the endoscope is obtained from the lumen of the target object.
Step S2: judging whether the original smoke exists or not, if so, carrying out the next step, and if not, outputting an image. The specific operation comprises the following steps:
step S2-1: calculating dark channel images using a calculation formulaThe calculation formula is specifically as follows:wherein, thereinIs a dark channel image;r, G, B, R, G, B are the three basic colors of the image, red, green, blue,；for any subset within the local area window,，is a window of the local area.
Step S2-2: counting the number of pixels of the dark channel image between LumTh1 and LumTh2, and recording asThe calculation formula is as follows:
wherein LumTh1 and LumTh2 represent a first pixel threshold and a second pixel threshold, respectively,as a sum function. Since there are more black edges and overexposed areas in the endoscopic image, and these areas will be statistical of the smoke levelDeviations are generated and need to be excluded, so that values are assigned for LumTh1 and LumTh2, with LumTh1 being 10 and LumTh2 being 240.
Step S2-3: counting the number of pixels with the pixel value between LumTh3 and LumTh4 of the dark channel image, and recording asThe calculation formula is as follows:
wherein LumTh3 and LumTh4 represent the third pixel threshold and the fourth pixel threshold, respectively, with LumTh3 being 80 and LumTh4 being 150.
Step S2-4: the percentage of smoke concentration was calculated:the calculation formula is as follows:
；
step S2-5: setting the smoke concentration threshold value asAnd comparing the percentage smoke concentration with a smoke concentration threshold ifGreater thanAnd judging that smoke exists, otherwise, judging that no smoke exists.
Step S3: obtaining a relational expression between the haze-free image and the original image according to the atmospheric illumination model:wherein, the method comprises the steps of, wherein,as the original image is to be taken,in the form of a haze-free image,for transmittance, a is the atmospheric illumination value.
Step S4: according to the relation between the defogging image and the original image in the step S3, defogging the original image, and dynamically adjusting the transmissivity in the defogging processIs used to control the smoke removal intensity until a haze-free image is obtained. By dynamically adjusting the smoke removal intensity in the defogging process, the influence on the image caused by the overlarge or the overlarge defogging intensity in the defogging process can be avoided. The specific operation method comprises the following steps:
step S4-1: calculating transmittanceThe calculation formula is as follows:
whereinIs the offset value of the haze-free region,to adjust the control parameters of the smoke removal intensity.The value of (2) varies with the concentration of the percentage of smoke concentration,the relationship between the percentage of smoke concentration is:
. Wherein,is thatThe minimum value of (2) is 0.1,is thatTakes a value of 0.2,is the integral multiplication factor, takes the value of 1,for converting the values between 0 and 1. The percentage of smoke concentration is varied in real time during the removal of smoke, and therefore, based on the variation of the percentage of smoke concentration,the value of (2) is dynamically adjusted accordingly, thereby dynamically adjusting the transmittanceThe dynamic adjustment of the smoke removing intensity is realized, and the influence on the image caused by the overlarge or the overlarge defogging intensity in the defogging process is avoided.
Step S4-2: setting A as a fixed value to enableWhereinIs 255.
Step S4-3: according toAndsubstituting the values of the images into a relational expression between the haze-free image and the original image, and transforming the values to obtain a calculation formula for calculating the haze-free image:and solving the formula to obtain the haze-free image.
Step S5: by calculation formulaAnd dynamically brightening the haze-free image obtained by solving, and outputting the image after brightening is completed. Wherein the method comprises the steps ofIs the self-adaptive gamma adjustment quantity.The calculation formula of (2) is as follows:whereinRepresentation ofThe minimum value of (2) is 1.1,representation ofThe maximum value of (2),the value is 1 as a multiplication factor.
In order to evaluate the feasibility and effectiveness of the method provided by the invention, experimental verification is performed on the embodiment:
the invention is based on the principle of the dark channel first inspection method, and a brand new smoke removal algorithm is developed based on the principle. In the invention, the algorithm research and development process is divided into an initial simulation stage and an implementation stage, wherein the initial simulation stage uses a programming language python to research and develop, modify and rapidly verify the algorithm so as to realize optimization of algorithm functions and partial operation. As shown in fig. 2 and 3, in the simulation result diagram of the input image of the FPGA and the simulation result diagram after the FPGA processing is finished, after the initial simulation stage meets the requirements to be met by the algorithm, the FPGA implementation stage is entered, and the programmable gate array FPGA simulation is a process of verifying the correctness and performance of the FPGA design through software simulation and hardware description. The performance of the FPGA is utilized, the aim of low delay of the video stream can be fulfilled, and the realization verification of the algorithm is completed. As shown in fig. 4, in the comparison graph of the image before defogging and after defogging, after the FPGA finishes the simulation, the algorithm program can be compiled, verification and debugging of the effect can be performed through real-machine burn-in display, and the algorithm parameters can be adjusted according to the actual effect to meet the final requirement to be achieved.
Specifically, in the present verification example, the following is set、Counting the number of pixels of the dark channel image in the threshold interval, and recording asAnd is defined as a reasonable number of pixels. Setting up、Counting the number of pixels of the dark channel image in the threshold interval, and recording asThe smoke concentration percentage threshold was set to 0.4. Obtained by mixing in real timeAnd (3) withThe ratio between defines the real-time smoke concentration percentage of the obtained endoscope image, compares the smoke concentration percentage with a smoke concentration percentage threshold value of 0.4, and when the smoke concentration percentage is larger than smokeWhen the smoke concentration percentage threshold value is smaller than or equal to the smoke concentration percentage threshold value, no smoke exists in the image.
During dynamic smoke removal processThe maximum and minimum values of (2) are respectively set as follows:、setting the multiplication factor asThe offset value of the haze-free region is set as:and set up. Combined transmittanceAndis calculated according to the formula:
，
it is known that during defogging, the percentage of smoke concentration changes in real time, which results inThe value of (2) also varies, resulting inThe magnitude of the value of (c) varies in real time.The larger the value of (c), the less the picture is changed, the weaker the smoke removal intensity is,the smaller the screen variation, the greater the smoke removal intensity.
Setting when dynamically brightening an image，，Introducing self-adaptive gamma adjustment quantity by a gamma brightening mode, and combining the formula:and
it is known that during defogging, the percentage of smoke concentration changes in real time, resulting inThe value of (2) is also changed, so that the image brightness degree can be adaptively adjusted according to the change of the smoke concentration percentage in the smoke removal process, and the change of the image in the whole minimally invasive process is smaller.
Comparison of results:
in the prior art, common defogging methods are as follows: a rapid defogging method, a real-time defogging method based on bilateral filtering, a multi-scale Retinex defogging method, a self-adaptive histogram equalization method for limiting contrast and a dark channel defogging method. The rapid defogging method utilizes mean filtering to estimate the ambient light and the global atmosphere light. The real-time defogging method based on bilateral filtering estimates the atmospheric light intensity according to the dark primary prior statistical principle, uses a rapid bilateral filter to estimate the atmospheric light curtain, and restores the atmospheric radiation intensity under ideal illumination conditions by solving a physical equation of imaging with a foggy image to realize image defogging. The defogging method of the multi-scale Retinex is to obtain images under different scales by carrying out Gaussian filtering on an original image, then to carry out single-scale Retinex calculation on the images under each scale to obtain a reflection component under the scale, and then to carry out weighted average on the reflection components under all scales to obtain a final reflection component. And fusing the final reflection component with the original image to obtain a defogged image. The self-adaptive histogram equalization method for limiting the contrast ratio is characterized in that an image is segmented, the accumulation of each block is calculated by taking the block as a unit, block bilinear interpolation is carried out, and image color filtering mixing operation is carried out with an original image. The dark channel defogging method is intuitive prior, the characteristics of a plurality of clear images and foggy images are counted, a dark channel prior theory is put forward, the relation between the clear images and the foggy images is found, and the atmospheric physical model is used for recovering the foggy images.
Simulation experiments are carried out on a plurality of defogging methods in the prior art, and the running time of the plurality of defogging methods is compared with that of the invention:
| defogging method | Run time (millisecond) |
| Dark channel defogging method | 400.8 |
| Histogram equalization method | 96.06 |
| Multi-scale Retinex method | 1893.1409 |
| Quick removingMist method | 199 |
| Real-time defogging method based on bilateral filtering | 660 |
| The invention is that | 88 |
According to the comparison of data of a plurality of defogging methods, the defogging method provided by the invention has short running time and achieves good performance in terms of resources and effects.
As shown in fig. 5 to 11, comparing defogging images obtained by various defogging methods can be seen: only a small part of areas in an image obtained by a multi-scale Retinex defogging method by a self-adaptive histogram equalization method for limiting contrast have a certain defogging effect, and the overall defogging capacity is weak; in the images obtained by the dark channel defogging method and the real-time image defogging method based on bilateral filtering, although the images have a certain defogging effect, the overall color of the images is greatly influenced, the images darken, and especially the real-time image defogging method based on bilateral filtering leads to more improvement of the saturation of the images and larger influence on the images; the defogging effect of the image obtained by the rapid defogging method is similar to that of the defogged image, but the defogged image is prevented from being changed greatly by dynamically adjusting the defogging intensity in real time, and the defogging method has stronger adaptability and better defogging effect on the whole compared with the original image.
The foregoing description is only illustrative of the present invention and is not intended to limit the scope of the invention, and all equivalent structures or equivalent processes or direct or indirect application in other related technical fields are included in the scope of the present invention.
Claims (6)
1. A method for smoke removal of an endoscopic image in real time, the method comprising the steps of:
step S1: obtaining an endoscope original image from the lumen of a target object;
step S2: judging whether the original image has smoke or not, if so, performing the next step, and if not, outputting an image; the specific method comprises the following steps:
step S2-1: computing dark channel imagesThe calculation formula is specifically as follows:
wherein->For dark channel image->R, G, B, R, G, B is the three basic colors of the image, red, green, blue, respectively,/-for each of the three channels>，/>For any subset within the local area window, +.>;/>A window that is a local area;
step S2-2: counting the number of pixels with the pixel value between LumTh1 and LumTh2 in the dark channel image, and recording asThe calculation formula is as follows:
wherein LumTh1 and LumTh2 represent the first pixel threshold and the second pixel threshold, respectively, +.>Is a sum function;
step S2-3: counting the number of pixels with the pixel value between LumTh3 and LumTh4 of the dark channel image, and recording asThe calculation formula is as follows:
wherein LumTh3 and LumTh4 represent a third pixel threshold and a fourth pixel threshold, respectively;
step S2-4: the percentage of smoke concentration was calculated:the calculation formula is as follows:
；
step S2-5: setting the smoke concentration threshold value asAnd comparing said smoke concentration percentage with said smoke concentration threshold value, if +.>Is greater than->If the smoke is judged to be present,otherwise, judging that no smoke exists;
step S3: obtaining a relational expression between the haze-free image and the original image according to an atmospheric illumination theory:wherein->For the original image +.>Is a haze-free image->The transmittance is that A is the atmospheric illumination value;
step S4: defogging the original image according to the relation, and dynamically adjustingThe smoke removal intensity is controlled and is continued until the smoke is completely removed, so that the haze-free image is obtained;
step S5: and dynamically brightening the haze-free image through a calculation formula, and outputting an image.
2. The method for defogging an endoscope image in real time according to claim 1, wherein in step S4, the specific method for defogging the original image according to the relation is as follows:
step S4-1: calculating transmittanceThe calculation formula is as follows:
wherein->For adjusting the control parameters of the smoke removal intensity +.>An offset value for the haze-free region;
step S4-2: setting A as a fixed value to enable；
Step S4-3: according toAnd->And calculating the defogging image based on a relation between the defogging image and the original image.
3. The method for smoke removal of real-time endoscopic images according to claim 2, wherein in step S4-1, the smoke removal is performed byAnd->And +.>The relation between->To dynamically adjust +.>Is a value of (2); the relation is as follows:
wherein->Is->Minimum value->Is->Maximum value of>Is an integral multiplication factor.
4. The method for removing smoke from an endoscopic image in real time as claimed in claim 2, wherein in step S4-3, the calculation formula for calculating the haze-free image is:。
5. the method for removing smoke from an endoscopic image in real time according to claim 1, wherein in step S5, a calculation formula for dynamically brightening the haze-free image is specifically as follows:wherein->For the image after the lightening, +.>Is the self-adaptive gamma adjustment quantity.
6. The method for smoke removal of an endoscopic image in real time as defined in claim 5, wherein said adaptive gamma adjustment is based on a predetermined ratio of said image framesThe calculation formula of (2) is as follows:
wherein->Representation->Minimum value->Representation->Maximum value of>Is a multiplication factor.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202410117788.8A CN117649363B (en) | 2024-01-29 | 2024-01-29 | Real-time endoscope image smoke removing method |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202410117788.8A CN117649363B (en) | 2024-01-29 | 2024-01-29 | Real-time endoscope image smoke removing method |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN117649363A CN117649363A (en) | 2024-03-05 |
| CN117649363B true CN117649363B (en) | 2024-04-12 |
Family
ID=90043675
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202410117788.8A Active CN117649363B (en) | 2024-01-29 | 2024-01-29 | Real-time endoscope image smoke removing method |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN117649363B (en) |
Citations (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN112862721A (en) * | 2021-02-24 | 2021-05-28 | 中国矿业大学(北京) | Underground pipeline image defogging method based on dark channel and Retinex |
| CN114066780A (en) * | 2022-01-17 | 2022-02-18 | 广东欧谱曼迪科技有限公司 | 4k endoscope image defogging method and device, electronic equipment and storage medium |
| CN116385340A (en) * | 2022-12-28 | 2023-07-04 | 中国科学院苏州生物医学工程技术研究所 | Medical endoscope image rapid defogging method and system |
Family Cites Families (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN112767267B (en) * | 2021-01-11 | 2022-09-27 | 北京航空航天大学 | Image defogging method based on simulation polarization fog-carrying scene data set |
-
2024
- 2024-01-29 CN CN202410117788.8A patent/CN117649363B/en active Active
Patent Citations (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN112862721A (en) * | 2021-02-24 | 2021-05-28 | 中国矿业大学(北京) | Underground pipeline image defogging method based on dark channel and Retinex |
| CN114066780A (en) * | 2022-01-17 | 2022-02-18 | 广东欧谱曼迪科技有限公司 | 4k endoscope image defogging method and device, electronic equipment and storage medium |
| CN116385340A (en) * | 2022-12-28 | 2023-07-04 | 中国科学院苏州生物医学工程技术研究所 | Medical endoscope image rapid defogging method and system |
Also Published As
| Publication number | Publication date |
|---|---|
| CN117649363A (en) | 2024-03-05 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN105654436B (en) | A kind of backlight image enhancing denoising method based on prospect background separation | |
| WO2021031458A1 (en) | Method and device for image color correction applicable in endoscope, and storage medium | |
| CN109191390A (en) | A kind of algorithm for image enhancement based on the more algorithm fusions in different colours space | |
| Cao et al. | Retinal image enhancement using low-pass filtering and α-rooting | |
| CN110570360B (en) | Retinex-based robust and comprehensive low-quality illumination image enhancement method | |
| EP3155586A2 (en) | Improvements in and relating to the display of images | |
| CN114529475B (en) | Image enhancement method and system based on two-dimensional gamma correction and tone mapping | |
| Cao et al. | Enhancement of blurry retinal image based on non-uniform contrast stretching and intensity transfer | |
| CN106846259A (en) | A kind of the real-time of laparoscopic surgery video frame rate self adaptation goes smog method | |
| Kumar et al. | Luminosity and contrast enhancement of retinal vessel images using weighted average histogram | |
| Hussein et al. | Retinex theory for color image enhancement: A systematic review | |
| CN106780384A (en) | A kind of the real-time of cold light source abdominal cavity image parameters self adaptation that be applicable goes smog method | |
| Cao et al. | Detail-richest-channel based enhancement for retinal image and beyond | |
| Huang et al. | Deep unsupervised endoscopic image enhancement based on multi-image fusion | |
| CN117649363B (en) | Real-time endoscope image smoke removing method | |
| CN114584675B (en) | Self-adaptive video enhancement method and device | |
| WO2023103813A1 (en) | Image processing method and apparatus, device, storage medium, and program product | |
| CN116271386A (en) | Visual double-cavity trachea cannula with imaging enhancement function and imaging enhancement method thereof | |
| US11936989B2 (en) | Apparatuses, systems, and methods for gaze-based auto-exposure management of image frames | |
| Yadav et al. | Contrast enhancement of region of interest of backlit image for surveillance systems based on multi-illumination fusion | |
| CN110852977B (en) | Image enhancement method for fusing edge gray level histogram and human eye visual perception characteristics | |
| CN115802926A (en) | Apparatus, system, and method for discounting an object while managing automatic exposure of image frames depicting the object | |
| Yerramneni et al. | A generalized grayscale image processing framework for retinal fundus images | |
| Abel et al. | Automatic glare removal in endoscopic imaging | |
| Idowu et al. | Improved Enhancement Technique for Medical Image Processing |
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 |