WO2023130547A1 - Endoscopic image dehazing method and apparatus, electronic device, and storage medium - Google Patents
Endoscopic image dehazing method and apparatus, electronic device, and storage medium Download PDFInfo
- Publication number
- WO2023130547A1 WO2023130547A1 PCT/CN2022/078031 CN2022078031W WO2023130547A1 WO 2023130547 A1 WO2023130547 A1 WO 2023130547A1 CN 2022078031 W CN2022078031 W CN 2022078031W WO 2023130547 A1 WO2023130547 A1 WO 2023130547A1
- Authority
- WO
- WIPO (PCT)
- Prior art keywords
- original image
- channel pixel
- brightness value
- atmospheric brightness
- image
- Prior art date
Links
- 238000000034 method Methods 0.000 title claims abstract description 58
- 238000012545 processing Methods 0.000 claims abstract description 34
- 230000006870 function Effects 0.000 claims description 30
- 238000012546 transfer Methods 0.000 claims description 27
- 238000001914 filtration Methods 0.000 claims description 22
- 238000004364 calculation method Methods 0.000 claims description 11
- 238000004590 computer program Methods 0.000 claims description 9
- 230000000694 effects Effects 0.000 abstract description 10
- 230000008901 benefit Effects 0.000 abstract description 5
- 230000008569 process Effects 0.000 description 5
- 238000004891 communication Methods 0.000 description 4
- 238000010586 diagram Methods 0.000 description 4
- 230000008878 coupling Effects 0.000 description 3
- 238000010168 coupling process Methods 0.000 description 3
- 238000005859 coupling reaction Methods 0.000 description 3
- 238000005286 illumination Methods 0.000 description 2
- 238000012986 modification Methods 0.000 description 2
- 230000004048 modification Effects 0.000 description 2
- 239000000779 smoke Substances 0.000 description 2
- 230000003068 static effect Effects 0.000 description 2
- 238000001356 surgical procedure Methods 0.000 description 2
- 238000012935 Averaging Methods 0.000 description 1
- 238000013459 approach Methods 0.000 description 1
- 230000009286 beneficial effect Effects 0.000 description 1
- 238000009499 grossing Methods 0.000 description 1
- 125000001475 halogen functional group Chemical group 0.000 description 1
- 230000007246 mechanism Effects 0.000 description 1
- 230000003287 optical effect Effects 0.000 description 1
- 230000008520 organization Effects 0.000 description 1
- 230000009467 reduction Effects 0.000 description 1
Images
Classifications
-
- G06T5/70—
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T5/00—Image enhancement or restoration
- G06T5/20—Image enhancement or restoration by the use of local operators
-
- G06T5/73—
-
- 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
- G06T2207/10068—Endoscopic image
Abstract
The present application relates to the technical field of image processing, and provides an endoscopic image dehazing method and apparatus, an electronic device, and a storage medium. The key point of the technical solution is that: the method comprises: acquiring an original image collected by an endoscope; calculating an atmospheric brightness value corresponding to each channel pixel of the original image; and performing dehazing processing according to the original image and the atmospheric brightness value corresponding to each channel pixel of the original image. The endoscopic image dehazing method and apparatus, the electronic device, and the storage medium provided by the present application have the advantage of a good dehazing effect.
Description
本申请涉及图像处理技术领域，具体而言，涉及一种内窥镜图像去雾方法、装置、电子设备及存储介质。The present application relates to the technical field of image processing, in particular, to a method, device, electronic device and storage medium for defogging an endoscope image.
目前常用的去雾方法有暗通道先验去雾方法、CLAHE方法、多尺度Retinex图像方法等，其中暗通道先验去雾方法根据大气散射模型，利用暗通道先验的方式得到图像传输函数，并完成去雾，在多种场景下均能得到很好的去雾效果。At present, the commonly used defogging methods include dark channel prior defogging method, CLAHE method, multi-scale Retinex image method, etc. Among them, the dark channel prior defogging method uses the dark channel prior method to obtain the image transfer function according to the atmospheric scattering model. And complete the defogging, and can get good defogging effects in various scenarios.
然而在内窥镜的图像处理中，烟雾场景较多，但用于内窥镜图像的去雾方法较少，实际运用中，仅有同态滤波或中值滤波相关方法，去雾效果有限。暗通道先验去雾方法对于自然图像有比较好的处理效果，却对内窥图像的处理效果不佳，这是由于光源与目标距离较近，图像亮度不均匀等问题，暗通道先验在一定程度上并不成立，因此将暗通道先验去雾方法直接用于内窥图像，会出现图像过饱和、对比度降低、图像偏色、偏暗等诸多问题。However, in endoscopic image processing, there are many smoky scenes, but there are few defogging methods for endoscopic images. In practical applications, there are only homomorphic filtering or median filtering related methods, and the dehazing effect is limited. The dark channel prior defogging method has a better processing effect on natural images, but the processing effect on endoscopic images is not good. This is due to the short distance between the light source and the target and the uneven brightness of the image. The dark channel prior is in To a certain extent, it is not true. Therefore, if the dark channel prior defogging method is directly applied to the endoscopic image, many problems such as image oversaturation, contrast reduction, image color cast, and dark cast will appear.
针对上述问题，申请人提出了一种新的解决方案。In view of the above problems, the applicant proposes a new solution.
发明内容Contents of the invention
本申请的目的在于提供一种内窥镜图像去雾方法、装置、电子设备及存储介质，具有去雾效果好的优点。The purpose of this application is to provide a method, device, electronic equipment and storage medium for defogging endoscopic images, which have the advantage of good defogging effect.
第一方面，本申请提供了一种内窥镜图像去雾方法，技术方案如下：In the first aspect, the present application provides a method for defogging an endoscope image, and the technical solution is as follows:
包括：include:
获取内窥镜采集的原始图像；Obtain the original image collected by the endoscope;
计算所述原始图像每个通道像素对应的大气亮度值；Calculate the atmospheric brightness value corresponding to each channel pixel of the original image;
根据所述原始图像以及所述原始图像每个通道像素对应的大气亮度值进行去雾处理。Dehaze processing is performed according to the original image and the atmospheric brightness value corresponding to each channel pixel of the original image.
通过计算每个通道像素对应的大气亮度值，利用每个通道像素对应的大气亮度值进行去雾处理，可以解决内窥图像亮度不均的问题。By calculating the atmospheric brightness value corresponding to each channel pixel, and using the atmospheric brightness value corresponding to each channel pixel to perform defogging processing, the problem of uneven brightness of the endoscopic image can be solved.
进一步地，在本申请中，所述计算所述原始图像每个通道像素对应的大气亮度值的步骤包括：Further, in this application, the step of calculating the atmospheric brightness value corresponding to each channel pixel of the original image includes:
对所述原始图像进行高斯滤波得到每个通道像素的灰度值；Gaussian filtering is performed on the original image to obtain the gray value of each channel pixel;
设置所述原始图像每个通道像素的大气亮度值权重；Setting the atmospheric brightness value weight of each channel pixel of the original image;
根据所述每个通道像素的灰度值以及所述原始图像每个通道像素的大气亮度值权重计算所述 原始图像每个通道像素对应的大气亮度值。Calculate the atmospheric brightness value corresponding to each channel pixel of the original image according to the gray value of each channel pixel and the atmospheric brightness value weight of each channel pixel of the original image.
根据上述方案，可以解决内窥图像红外线散射较多，红色通道亮度偏高，三个通道用同一个传输函数时会出现比较明显的色差等问题。According to the above scheme, it can solve the problems of more infrared scattering in the endoscopic image, high brightness of the red channel, and obvious color difference when the three channels use the same transfer function.
进一步地，在本申请中，所述设置所述原始图像每个通道像素的大气亮度值权重的步骤包括：Further, in this application, the step of setting the atmospheric brightness value weight of each channel pixel of the original image includes:
获取所述原始图像的均值以及方差；Obtain the mean and variance of the original image;
根据所述原始图像的均值以及方差计算得出所述原始图像每个通道像素的大气亮度值权重。The atmospheric brightness value weight of each channel pixel of the original image is calculated according to the mean value and the variance of the original image.
根据上述方案，通过计算得出所述原始图像每个通道像素的大气亮度值权重，然后利用每个通道像素的大气亮度值权重得出每个通道像素的大气亮度值，利用每个通道像素对应的大气亮度值进行去雾处理，可以解决内窥图像亮度不均的问题。According to the above scheme, the atmospheric brightness value weight of each channel pixel of the original image is obtained by calculating, and then the atmospheric brightness value of each channel pixel is obtained by using the atmospheric brightness value weight of each channel pixel, and the corresponding Atmospheric brightness value can be dehazed, which can solve the problem of uneven brightness of endoscopic images.
进一步地，在本申请中，所述根据所述原始图像以及所述原始图像每个通道像素对应的大气亮度值进行去雾处理的步骤还包括：Further, in the present application, the step of performing defogging processing according to the original image and the atmospheric brightness value corresponding to each channel pixel of the original image further includes:
根据所述原始图像每个通道像素对应的大气亮度值得到每个通道像素对应的传输函数；Obtain the transfer function corresponding to each channel pixel according to the atmospheric brightness value corresponding to each channel pixel of the original image;
根据所述每个通道像素对应的传输函数、所述原始图像以及所述原始图像每个通道像素对应的大气亮度值进行去雾处理。Dehaze processing is performed according to the transfer function corresponding to each channel pixel, the original image, and the atmospheric brightness value corresponding to each channel pixel of the original image.
进一步地，在本申请中，所述根据所述每个通道像素对应的传输函数、所述原始图像以及所述原始图像每个通道像素对应的大气亮度值进行去雾处理的步骤还包括：Further, in the present application, the step of performing defogging processing according to the transfer function corresponding to each channel pixel, the original image, and the atmospheric brightness value corresponding to each channel pixel of the original image further includes:
通过导向滤波细化所述每个通道像素对应的传输函数；refine the transfer function corresponding to each channel pixel by guided filtering;
根据细化后的所述每个通道像素对应的传输函数、所述原始图像以及所述原始图像每个通道像素对应的大气亮度值进行去雾处理。Dehazing is performed according to the refined transfer function corresponding to each channel pixel, the original image, and the atmospheric brightness value corresponding to each channel pixel of the original image.
进一步地，在本申请中，所述根据所述每个通道像素的灰度值以及所述原始图像每个通道像素的大气亮度值权重计算所述原始图像每个通道像素对应的大气亮度值的公式为：Further, in this application, the calculation of the atmospheric brightness value corresponding to each channel pixel of the original image according to the gray value of each channel pixel and the atmospheric brightness value weight of each channel pixel of the original image The formula is:
A
c(x)＝255*Pwt
c(x)+(1-Pwt
c(x))*G
c(x)；
A c (x)=255*Pwt c (x)+(1-Pwt c (x))*G c (x);
其中，A
c(x)为第c个通道像素对应的大气亮度值、Pwt
c(x)为第c个通道像素的大气亮度值权重、G
c(x)为高斯滤波后第c个通道像素的灰度值。
Among them, A c (x) is the atmospheric brightness value corresponding to the cth channel pixel, Pwt c (x) is the atmospheric brightness value weight of the cth channel pixel, G c (x) is the cth channel pixel after Gaussian filtering the gray value of .
进一步地，在本申请中，所述根据所述原始图像的均值以及方差计算得出所述原始 图像每个通道像素的大气亮度值权重的公式为：Further, in the present application, the formula for calculating the atmospheric brightness value weight of each channel pixel of the original image according to the mean value and variance of the original image is:
其中，Pwt
c(x)为第c个通道像素的大气亮度值权重、e为自然常数、f
mean为所述原始图像的均值、f
std为所述原始图像的方差。
Wherein, Pwt c (x) is the atmospheric brightness value weight of the cth channel pixel, e is a natural constant, f mean is the mean value of the original image, and f std is the variance of the original image.
第二方面，本申请还提供一种内窥镜图像去雾装置，包括：In a second aspect, the present application also provides an endoscopic image defogging device, including:
获取模块，用于获取内窥镜采集的原始图像；Obtaining module, for obtaining the raw image that endoscope collects;
计算模块，用于计算所述原始图像每个通道像素对应的大气亮度值；A calculation module, configured to calculate the atmospheric brightness value corresponding to each channel pixel of the original image;
处理模块，用于根据所述原始图像以及所述原始图像每个通道像素对应的大气亮度值进行去雾处理；A processing module, configured to perform defogging processing according to the original image and the atmospheric brightness value corresponding to each channel pixel of the original image;
所述计算所述原始图像每个通道像素对应的大气亮度值包括：The calculation of the atmospheric brightness value corresponding to each channel pixel of the original image includes:
对所述原始图像进行高斯滤波得到每个通道像素的灰度值；Gaussian filtering is performed on the original image to obtain the gray value of each channel pixel;
设置所述原始图像每个通道像素的大气亮度值权重；Setting the atmospheric brightness value weight of each channel pixel of the original image;
根据所述每个通道像素的灰度值以及所述原始图像每个通道像素的大气亮度值权重计算所述原始图像每个通道像素对应的大气亮度值。The atmospheric brightness value corresponding to each channel pixel of the original image is calculated according to the gray value of each channel pixel and the atmospheric brightness value weight of each channel pixel of the original image.
第三方面，本申请还提供一种电子设备，包括处理器以及存储器，所述存储器存储有计算机可读取指令，当所述计算机可读取指令由所述处理器执行时，运行如上任一项所述方法中的步骤。In a third aspect, the present application also provides an electronic device, including a processor and a memory, the memory stores computer-readable instructions, and when the computer-readable instructions are executed by the processor, any one of the above steps in the method described in the item.
第四方面，本申请还提供一种存储介质，其上存储有计算机程序，所述计算机程序被处理器执行时，运行如上任一项所述方法中的步骤。In a fourth aspect, the present application further provides a storage medium on which a computer program is stored, and when the computer program is executed by a processor, the steps in any one of the above methods are performed.
由上可知，本申请提供的一种内窥镜图像去雾方法、装置、电子设备及存储介质，通过计算内窥镜采集的原始图像的每个通道像素对应的大气亮度值，根据原始图像以及原始图像中每个通道像素对应的大气亮度值进行去雾处理，有效解决了传统的暗通道先验去雾方法无法适应内窥图像的问题，通过计算每个通道像素对应的大气亮度值，可以解决内窥图像亮度不均红外线散射较多，红色通道亮度偏高，三个通道用同一个传输函数时会出现比较明显的色差等问题，因此具有去雾效果好的有益效果。As can be seen from the above, the method, device, electronic device and storage medium for defogging an endoscope image provided by the present application calculate the atmospheric brightness value corresponding to each channel pixel of the original image collected by the endoscope, according to the original image and The atmospheric brightness value corresponding to each channel pixel in the original image is dehazed, which effectively solves the problem that the traditional dark channel prior defogging method cannot adapt to endoscopic images. By calculating the atmospheric brightness value corresponding to each channel pixel, it can Solve the problems of uneven brightness of endoscopic images, more infrared scattering, high brightness of red channel, obvious color difference when three channels use the same transfer function, so it has the beneficial effect of good defogging effect.
本申请的其他特征和优点将在随后的说明书阐述，并且，部分地从说明书中变得显 而易见，或者通过实施本申请了解。本申请的目的和其他优点可通过在所写的说明书、权利要求书、以及附图中所特别指出的结构来实现和获得。Additional features and advantages of the application will be set forth in the description which follows, and, in part, will be obvious from the description, or may be learned by practice of the application. The objectives and other advantages of the application may be realized and attained by the structure particularly pointed out in the written description and claims hereof as well as the appended drawings.
图1为本申请提供的一种内窥镜图像去雾方法流程图。FIG. 1 is a flow chart of a method for defogging an endoscope image provided by the present application.
图2为本申请提供的一种内窥镜图像去雾装置结构示意图。FIG. 2 is a schematic structural diagram of an endoscopic image defogging device provided by the present application.
图3为本申请提供的一种电子设备示意图。FIG. 3 is a schematic diagram of an electronic device provided by the present application.
图4为采用本申请提出的内窥镜图像去雾方法的内窥镜图像的前后对比图。FIG. 4 is a comparison diagram of an endoscopic image before and after using the method for defogging an endoscopic image proposed in the present application.
图5为采用本申请提出的内窥镜图像去雾方法的内窥镜图像的前后对比图。FIG. 5 is a comparison diagram of an endoscopic image before and after using the method for defogging an endoscopic image proposed in the present application.
图中：210、获取模块；220、计算模块；230、处理模块；300、电子设备；310、处理器；320、存储器。In the figure: 210, acquisition module; 220, calculation module; 230, processing module; 300, electronic device; 310, processor; 320, memory.
下面将结合本申请中附图，对本申请中的技术方案进行清楚、完整地描述，显然，所描述的实施例仅仅是本申请一部分实施例，而不是全部的实施例。通常在此处附图中描述和示出的本申请的组件可以以各种不同的配置来布置和设计。因此，以下对在附图中提供的本申请的实施例的详细描述并非旨在限制要求保护的本申请的范围，而是仅仅表示本申请的选定实施例。基于本申请的实施例，本领域技术人员在没有做出创造性劳动的前提下所获得的所有其他实施例，都属于本申请保护的范围。The technical solutions in this application will be clearly and completely described below in conjunction with the drawings in this application. Obviously, the described embodiments are only some of the embodiments of this application, not all of them. The components of the application generally described and illustrated in the figures herein may be arranged and designed in a variety of different configurations. Accordingly, the following detailed description of the embodiments of the application provided in the accompanying drawings is not intended to limit the scope of the claimed application, but merely represents selected embodiments of the application. Based on the embodiments of the present application, all other embodiments obtained by those skilled in the art without making creative efforts belong to the scope of protection of the present application.
应注意到：相似的标号和字母在下面的附图中表示类似项，因此，一旦某一项在一个附图中被定义，则在随后的附图中不需要对其进行进一步定义和解释。同时，在本申请的描述中，术语“第一”、“第二”等仅用于区分描述，而不能理解为指示或暗示相对重要性。It should be noted that like numerals and letters denote similar items in the following figures, therefore, once an item is defined in one figure, it does not require further definition and explanation in subsequent figures. Meanwhile, in the description of the present application, the terms "first", "second" and the like are only used to distinguish descriptions, and cannot be understood as indicating or implying relative importance.
暗通道先验方法是通过一个大气散射模型，然后利用大气亮度值对带雾的原始图像进行处理，从而求出无雾图像，具体的，通常其大气散射模型为：The dark channel prior method is to use an atmospheric scattering model, and then use the atmospheric brightness value to process the original image with fog, so as to obtain a fog-free image. Specifically, the atmospheric scattering model is usually:
I(x)＝J(x)*t(x)+A(1-t(x))；I(x)=J(x)*t(x)+A(1-t(x));
其中，I(x)为原始图像、J(x)为无雾图像、t(x)为传输函数、A为大气亮度值，其中的x表示的是范围内的任意一像素。Among them, I(x) is the original image, J(x) is the fog-free image, t(x) is the transfer function, and A is the atmospheric brightness value, where x represents any pixel within the range.
如果某个RGB图像无雾，则该RGB图像的每个像素的RGB三个通道的最小值必定为0，RGB三个通道之间的最小值称为暗通道，使用公式则可以描述为：If an RGB image has no fog, the minimum value of the RGB three channels of each pixel of the RGB image must be 0, and the minimum value between the three RGB channels is called the dark channel, and the formula can be described as:
其中，c表示通道、Ω(x)表示以x为中心的局部区域、I
dark(x)表示暗通道,y∈Ω(x)表示以x为中心的局部区域内的任意一点，J
c(y)表示无雾图像的第c个通道内像素y的值；
Among them, c represents the channel, Ω(x) represents the local area centered on x, I dark (x) represents the dark channel, y∈Ω(x) represents any point in the local area centered on x, J c ( y) represents the value of pixel y in the cth channel of the fog-free image;
暗通道先验指的是无雾图像的暗通道为0，即：The dark channel prior means that the dark channel of the haze-free image is 0, that is:
同时推导得到传输函数为：At the same time, the transfer function is derived as:
由上述可知：It can be seen from the above:
因此有：So there are:
其中，大气亮度值A代表照射整个场景的亮度值，一般情况下，设置为图像暗通道图像亮度前1％像素对应原图的像素最高亮度值，I
c(y)表示原始有雾图像的第c个通道内像素 y的值。
Among them, the atmospheric brightness value A represents the brightness value that illuminates the entire scene. In general, it is set to the highest brightness value of the pixel in the original image corresponding to the first 1% of the image brightness in the dark channel image, and I c (y) represents the first pixel brightness value of the original foggy image The value of pixel y in c channels.
在完成
和A的计算后，可以通过
求出J(x)，即无雾图像，其中，t
0是为了避免t(x)为0的情况，通常t
0设为0.1。
in completion After calculation of A and A, it can be obtained by Calculate J(x), that is, the fog-free image, where t 0 is to avoid the situation that t(x) is 0, and usually t 0 is set to 0.1.
暗通道先验去雾方法基于纯色图像暗通道为0的先验，一般用于处理自然图像，在处理自然图像时，其入射光为平行光，光照均匀，因此可以取得很好的去雾效果。The dark channel prior defogging method is based on the priori that the dark channel of the pure color image is 0, and is generally used to process natural images. When processing natural images, the incident light is parallel light and the illumination is uniform, so a good defogging effect can be obtained. .
然而，对于内窥镜图像而言，内窥镜用于探视生物内部组织的图像，光源距离目标很近，导致图像不同区域的光照差异大，图像亮度不均匀。对此，申请人提出了一种全新的去雾方法。However, for endoscopic images, the endoscope is used to view images of biological internal tissues, and the light source is very close to the target, resulting in large differences in illumination in different areas of the image and uneven image brightness. In this regard, the applicant proposed a brand-new defogging method.
请参照图1，一种内窥镜图像去雾方法，其技术方案具体包括：Please refer to Fig. 1, a method for defogging an endoscope image, and its technical solution specifically includes:
S110、获取内窥镜采集的原始图像；S110. Obtain the original image collected by the endoscope;
S120、计算原始图像每个通道像素对应的大气亮度值；S120. Calculate the atmospheric brightness value corresponding to each channel pixel of the original image;
S130、根据原始图像以及原始图像每个通道像素对应的大气亮度值进行去雾处理。S130. Perform defogging processing according to the original image and the atmospheric brightness value corresponding to each channel pixel of the original image.
通过上述技术方案，在获取内窥镜采集的原始图像后，通过计算原始图像中每个通道像素对应的大气亮度值，然后利用每个通道像素对应的大气亮度值进行去雾处理，可以解决内窥图像亮度不均的问题。Through the above technical solution, after obtaining the original image collected by the endoscope, by calculating the atmospheric brightness value corresponding to each channel pixel in the original image, and then using the atmospheric brightness value corresponding to each channel pixel to perform defogging processing, the internal Peek at the problem of uneven brightness of the image.
进一步地，在其中一些实施例中，计算原始图像每个通道像素对应的大气亮度值的步骤包括：Further, in some of these embodiments, the step of calculating the atmospheric brightness value corresponding to each channel pixel of the original image includes:
对原始图像进行高斯滤波得到每个通道像素的灰度值；Perform Gaussian filtering on the original image to obtain the gray value of each channel pixel;
设置原始图像每个通道像素的大气亮度值权重；Set the atmospheric brightness value weight of each channel pixel of the original image;
根据每个通道像素的灰度值以及原始图像每个通道像素的大气亮度值权重计算原始图像每个通道像素对应的大气亮度值。Calculate the atmospheric brightness value corresponding to each channel pixel of the original image according to the gray value of each channel pixel and the weight of the atmospheric brightness value of each channel pixel of the original image.
通过上述技术方案，首先对原始图像进行高斯滤波处理，高斯滤波是一种线性平滑滤波，用于消除高斯噪声，具体而言，高斯滤波就是对整幅图像进行加权平均的过程，每一个像素点的值，都由其本身和邻域内的其它像素值经过加权平均后得到；在进行高斯滤波处理后设置原始图像每个通道像素的大气亮度值权重，更新每个通道像素的大气亮度值，使最终获得的每个通道像素对应的大气亮度值更加准确。Through the above-mentioned technical scheme, firstly, Gaussian filtering is performed on the original image. Gaussian filtering is a linear smoothing filter used to eliminate Gaussian noise. Specifically, Gaussian filtering is a process of weighted averaging of the entire image. Each pixel The value of is obtained by the weighted average of itself and other pixel values in the neighborhood; after Gaussian filtering, the weight of the atmospheric brightness value of each channel pixel of the original image is set, and the atmospheric brightness value of each channel pixel is updated, so that The finally obtained atmospheric brightness value corresponding to each channel pixel is more accurate.
具体的，在一些实施方式中，根据每个通道像素的灰度值以及原始图像每个通道像 素的大气亮度值权重计算原始图像每个通道像素对应的大气亮度值的公式为：Specifically, in some implementations, the formula for calculating the atmospheric brightness value corresponding to each channel pixel of the original image according to the gray value of each channel pixel and the weight of the atmospheric brightness value of each channel pixel of the original image is:
A
c(x)＝255*Pwt
c(x)+(1-Pwt
c(x))*G
c(x)；
A c (x)=255*Pwt c (x)+(1-Pwt c (x))*G c (x);
其中，A
c(x)为第c个通道像素对应的大气亮度值、Pwt
c(x)为第c个通道像素的大气亮度值权重、G
c(x)为高斯滤波后第c个通道像素的灰度值、常数255是代表最大亮度值。
Among them, A c (x) is the atmospheric brightness value corresponding to the cth channel pixel, Pwt c (x) is the atmospheric brightness value weight of the cth channel pixel, G c (x) is the cth channel pixel after Gaussian filtering The grayscale value, the constant 255 represents the maximum brightness value.
在传统的暗通道先验方法中，大气亮度值会是255或者接近255的固定值，但是针对内窥镜的图像处理则不能这样算，因为内窥镜离光源近，生物体的内部组织复杂，因此获取的原始图像的亮度不均匀，对此增加设计了原始图像每个通道像素的大气亮度值权重，进一步更新每个通道像素的大气亮度值，使每个通道像素的大气亮度值更加准确。In the traditional dark channel prior method, the atmospheric brightness value will be a fixed value of 255 or close to 255, but the image processing for the endoscope cannot be calculated in this way, because the endoscope is close to the light source and the internal organization of the organism is complex , so the brightness of the acquired original image is not uniform, so the weight of the atmospheric brightness value of each channel pixel of the original image is designed to increase the atmospheric brightness value of each channel pixel, and the atmospheric brightness value of each channel pixel is further updated to make the atmospheric brightness value of each channel pixel more accurate .
具体的，通过设置高斯滤波核对原始图像进行高斯滤波，其窗值r＝nPatch*10，σ＝r，高斯滤波核可以描述为：Specifically, Gaussian filtering is performed on the original image by setting the Gaussian filter kernel, the window value r=nPatch*10, σ=r, and the Gaussian filter kernel can be described as:
其中，x和y是高斯滤波核中每个位置与高斯滤波核中心的距离，x是x轴的距离，u是y轴的距离，σ是高斯滤波核的边长、e是自然常数、nPatch为求暗通道时所用的最小值滤波窗值。Among them, x and y are the distance between each position in the Gaussian filter kernel and the center of the Gaussian filter kernel, x is the distance on the x-axis, u is the distance on the y-axis, σ is the side length of the Gaussian filter kernel, e is a natural constant, nPatch It is the minimum filter window value used when finding the dark channel.
进一步地，在其中一些实施例中，设置原始图像每个通道像素的大气亮度值权重的步骤包括：Further, in some of these embodiments, the step of setting the atmospheric brightness value weight of each channel pixel of the original image includes:
获取原始图像的均值以及方差；Get the mean and variance of the original image;
根据原始图像的均值以及方差计算得出原始图像每个通道像素的大气亮度值权重。The atmospheric brightness value weight of each channel pixel of the original image is calculated according to the mean and variance of the original image.
具体的，在一些实施方式中，根据原始图像的均值以及方差计算得出原始图像每个通道像素的大气亮度值权重的公式为：Specifically, in some implementations, the formula for calculating the weight of the atmospheric brightness value of each channel pixel of the original image according to the mean and variance of the original image is:
其中，Pwt
c(x)为第c个通道像素的大气亮度值权重、g为自然常数、f
mean为所述原始图像的均值、f
std为所述原始图像的方差；
Wherein, Pwt c (x) is the atmospheric brightness value weight of the cth channel pixel, g is a natural constant, f mean is the mean value of the original image, and f std is the variance of the original image;
通过上述技术方案，根据原始图像的均值以及方差获得原始图像每个通道像素的大气亮度值权重，然后根据原始图像每个通道像素的大气亮度值权重以及高斯滤波后每个通道像素的灰度值求出每个通道像素对应的大气亮度值，然后通过每个通道像素对应的大气亮度值进行去雾处理，最终求得无雾图像。Through the above technical scheme, the weight of the atmospheric brightness value of each channel pixel of the original image is obtained according to the mean and variance of the original image, and then according to the weight of the atmospheric brightness value of each channel pixel of the original image and the gray value of each channel pixel after Gaussian filtering Calculate the atmospheric brightness value corresponding to each channel pixel, and then perform dehazing processing through the atmospheric brightness value corresponding to each channel pixel, and finally obtain a fog-free image.
进一步地，在其中一些实施例中，根据原始图像以及原始图像每个通道像素对应的大气亮度值进行去雾处理的步骤还包括：Further, in some of these embodiments, the step of performing defogging processing according to the original image and the atmospheric brightness value corresponding to each channel pixel of the original image further includes:
根据原始图像每个通道像素对应的大气亮度值得到每个通道像素对应的传输函数；Obtain the transfer function corresponding to each channel pixel according to the atmospheric brightness value corresponding to each channel pixel of the original image;
根据每个通道像素对应的传输函数、原始图像以及原始图像每个通道像素对应的大气亮度值进行去雾处理。Dehazing is performed according to the transfer function corresponding to each channel pixel, the original image, and the atmospheric brightness value corresponding to each channel pixel of the original image.
通过上述技术方案，由于每个通道像素都对应一个大气亮度值，因此每个通道像素都将有一个传输函数与之对应。Through the above technical solution, since each channel pixel corresponds to an atmospheric brightness value, each channel pixel will have a transfer function corresponding to it.
具体的，根据原始图像每个通道像素对应的大气亮度值得到每个通道像素对应的传输函数为：Specifically, according to the atmospheric brightness value corresponding to each channel pixel of the original image, the transfer function corresponding to each channel pixel is obtained as:
其中，
为每个通道像素对应的传输函数、w为去雾强度，可以自定义进行设置、A
C(x)为每个通道像素对应的大气亮度值、I
dark(x)为暗通道。
in, is the transfer function corresponding to each channel pixel, w is the defogging intensity, which can be customized and set, A C (x) is the atmospheric brightness value corresponding to each channel pixel, and I dark (x) is the dark channel.
进一步地，在其中一些实施例中，根据每个通道像素对应的传输函数、原始图像以及原始图像每个通道像素对应的大气亮度值进行去雾处理的步骤还包括：Further, in some of these embodiments, the step of performing defogging processing according to the transfer function corresponding to each channel pixel, the original image, and the atmospheric brightness value corresponding to each channel pixel of the original image further includes:
通过导向滤波细化每个通道像素对应的传输函数；Refine the transfer function corresponding to each channel pixel through guided filtering;
根据细化后的每个通道像素对应的传输函数、原始图像以及原始图像每个通道像素对应的大气亮度值进行去雾处理。According to the transfer function corresponding to each channel pixel after refinement, the original image and the atmospheric brightness value corresponding to each channel pixel of the original image, the defogging process is performed.
通过上述技术方案，在计算完三个通道的传输函数后，通过导向滤波来细化传输函 数，从而提高传输函数的精确率，避免去雾后出现光晕。Through the above technical solution, after the transfer functions of the three channels are calculated, the transfer functions are refined through guided filtering, thereby improving the accuracy of the transfer functions and avoiding halos after defogging.
具体的，在一些实施方式中，导向滤波的公式为：Specifically, in some implementations, the formula for guided filtering is:
最终，根据原始图像以及原始图像每个通道像素对应的大气亮度值进行去雾处理可以表示为：Finally, according to the original image and the atmospheric brightness value corresponding to each channel pixel of the original image, the dehazing process can be expressed as:
其中，J
c(x)为求出的无雾图像、I
c(x)为内窥镜获取的原始图像、A
c(x)为第c个通道像素对应的大气亮度值、
为经过导向滤波后的第c个通道像素对应的传输函数，t
0为常数，通常将t
0设为0.1。
Among them, J c (x) is the calculated fog-free image, I c (x) is the original image acquired by the endoscope, A c (x) is the atmospheric brightness value corresponding to the cth channel pixel, is the transfer function corresponding to the c-th channel pixel after guided filtering, t 0 is a constant, and t 0 is usually set to 0.1.
本申请利用了暗通道先验去雾方法的优势，通过大气散射模型来完成图像去雾，图像去雾完成后处理效果自然，在手术中使用时不会产生明显不适感。通过详细研究了内窥镜图像的特点和暗通道先验去雾在内窥镜图像中使用存在的问题，提出通过每个通道像素的大气亮度值来进行去雾处理，解决了暗通道先验去雾方法存在的过饱和，图像偏暗问题，使得该方法可适用于内窥镜图像。弥补了现有内窥镜图像去雾方法处理方式较为简单、去雾效果不够自然的问题，从大气亮度值估计的角度，结合暗通道去雾先验方法提出了解决内窥镜图像去雾、除烟问题的新路径。This application takes advantage of the dark channel prior defogging method to complete the image defogging through the atmospheric scattering model. After the image defogging is completed, the processing effect is natural, and there will be no obvious discomfort when used in surgery. Through a detailed study of the characteristics of endoscopic images and the problems existing in the use of dark channel prior defogging in endoscopic images, it is proposed to use the atmospheric brightness value of each channel pixel to perform defogging processing, which solves the problem of dark channel prior The problem of oversaturation and dark image in the defogging method makes this method applicable to endoscopic images. It makes up for the problems that the existing endoscopic image defogging methods are relatively simple and the defogging effect is not natural enough. From the perspective of atmospheric brightness value estimation, combined with the prior method of dark channel defogging, a solution to the endoscopic image defogging, A new approach to the smoke removal problem.
具体可参照图4以及图5，图4的上下两幅图像分别为内窥镜获取的原始图像以及经过本申请提供的方法处理过以后的无雾图像，图5的上下两幅图像同样分别为内窥镜获取的原始图像以及经过本申请提供的方法处理过以后的无雾图像，可以明显看出，经过本申请提供的方法处理后的无雾图像其画面更加清晰锐利，不会被烟雾遮挡，对于信息的获取以及手术的执行均能够带来显著的帮助。Specifically, reference can be made to Fig. 4 and Fig. 5. The upper and lower images of Fig. 4 are respectively the original image acquired by the endoscope and the fog-free image after the method provided by the application is processed. The upper and lower images of Fig. 5 are also respectively From the original image obtained by the endoscope and the fog-free image processed by the method provided in this application, it can be clearly seen that the image of the fog-free image processed by the method provided in this application is clearer and sharper, and will not be blocked by smoke , which can bring significant help to the acquisition of information and the execution of surgery.
第二方面，如图2所示，本申请还提供一种内窥镜图像去雾装置，包括：In the second aspect, as shown in Figure 2, the present application also provides an endoscopic image defogging device, including:
获取模块210，用于获取内窥镜采集的原始图像；Obtaining module 210, for obtaining the original image that endoscope collects;
计算模块220，用于计算原始图像每个通道像素对应的大气亮度值； Calculation module 220, for calculating the atmospheric brightness value corresponding to each channel pixel of the original image;
处理模块230，用于根据原始图像以及原始图像每个通道像素对应的大气亮度值进行去雾处 理。The processing module 230 is configured to perform defogging processing according to the original image and the atmospheric brightness value corresponding to each channel pixel of the original image.
通过上述技术方案，利用获取模块210获取内窥镜采集的原始图像，然后通过计算模块220计算原始图像中每个通道像素对应的大气亮度值，最后利用处理模块230根据原始图像以及原始图像每个通道像素对应的大气亮度值进行去雾处理，可以有效解决内窥图像亮度不均的问题。Through the above technical solution, the acquisition module 210 is used to acquire the original image collected by the endoscope, and then the calculation module 220 is used to calculate the atmospheric brightness value corresponding to each channel pixel in the original image, and finally the processing module 230 is used to obtain the original image according to the original image and each of the original images. The atmospheric brightness value corresponding to the channel pixel is dehazed, which can effectively solve the problem of uneven brightness of the endoscopic image.
在一些优选的实施方式中，采用该内窥镜图像去雾装置执行上述第一方面提供的内窥镜图像去雾方法。In some preferred embodiments, the endoscopic image defogging device is used to implement the endoscopic image defogging method provided in the first aspect above.
第三方面，如图3所示，本申请还提供一种电子设备300，包括处理器310以及存储器320，存储器320存储有计算机可读取指令，当计算机可读取指令由处理器310执行时，运行上述方法中的步骤。In the third aspect, as shown in FIG. 3 , the present application also provides an electronic device 300, including a processor 310 and a memory 320. The memory 320 stores computer-readable instructions. When the computer-readable instructions are executed by the processor 310 , to run the steps in the method above.
通过上述技术方案，处理器310和存储器320通过通信总线和/或其他形式的连接机构(未标出)互连并相互通讯，存储器320存储有处理器可执行的计算机程序，当计算设备运行时，处理器310执行该计算机程序，以执行时执行上述实施例的任一可选的实现方式中的方法，以实现以下功能：获取内窥镜采集的原始图像；计算原始图像每个通道像素对应的大气亮度值；根据原始图像以及原始图像每个通道像素对应的大气亮度值进行去雾处理。Through the above technical solution, the processor 310 and the memory 320 are interconnected and communicate with each other through a communication bus and/or other forms of connection mechanisms (not shown), and the memory 320 stores a computer program executable by the processor. When the computing device is running , the processor 310 executes the computer program, so as to execute the method in any optional implementation manner of the above-mentioned embodiment, so as to realize the following functions: acquire the original image collected by the endoscope; calculate the pixel corresponding to each channel of the original image Atmospheric brightness value; Dehaze processing is performed according to the original image and the atmospheric brightness value corresponding to each channel pixel of the original image.
第四方面，本申请还提供一种存储介质，其上存储有计算机程序，计算机程序被处理器执行时，运行上述方法中的步骤。In a fourth aspect, the present application also provides a storage medium on which a computer program is stored, and when the computer program is executed by a processor, the steps in the above method are executed.
通过上述技术方案，计算机程序被处理器执行时，执行上述实施例的任一可选的实现方式中的方法，以实现以下功能：获取内窥镜采集的原始图像；计算原始图像每个通道像素对应的大气亮度值；根据原始图像以及原始图像每个通道像素对应的大气亮度值进行去雾处理。Through the above technical solution, when the computer program is executed by the processor, the method in any optional implementation manner of the above-mentioned embodiment is executed to realize the following functions: acquire the original image collected by the endoscope; calculate the pixels of each channel of the original image Corresponding atmospheric brightness value; perform defogging processing according to the original image and the atmospheric brightness value corresponding to each channel pixel of the original image.
其中，存储介质可以由任何类型的易失性或非易失性存储设备或者它们的组合实现，如静态随机存取存储器(Static Random Access Memory,简称SRAM)，电可擦除可编程只读存储器(Electrically Erasable Programmable Read-Only Memory,简称EEPROM)，可擦除可编程只读存储器(Erasable Programmable Read Only Memory,简称EPROM)，可编程只读存储器(Programmable Red-Only Memory,简称PROM)，只读存储器(Read-Only Memory,简称ROM)，磁存储器，快闪存储器，磁盘或光盘。Among them, the storage medium can be realized by any type of volatile or non-volatile storage device or their combination, such as Static Random Access Memory (Static Random Access Memory, referred to as SRAM), Electrically Erasable Programmable Read-Only Memory (Electrically Erasable Programmable Read-Only Memory, referred to as EEPROM), Erasable Programmable Read Only Memory (Erasable Programmable Read Only Memory, referred to as EPROM), Programmable Read-Only Memory (Programmable Red-Only Memory, referred to as PROM), read-only Memory (Read-Only Memory, referred to as ROM), magnetic memory, flash memory, magnetic disk or optical disk.
在本申请所提供的实施例中，应该理解到，所揭露装置和方法，可以通过其它的方式实现。以上所描述的装置实施例仅仅是示意性的，例如，所述单元的划分，仅仅为一种逻辑功能划分，实际实现时可以有另外的划分方式，又例如，多个单元或组件可以结合或者可 以集成到另一个系统，或一些特征可以忽略，或不执行。另一点，所显示或讨论的相互之间的耦合或直接耦合或通信连接可以是通过一些通信接口，装置或单元的间接耦合或通信连接，可以是电性，机械或其它的形式。In the embodiments provided in this application, it should be understood that the disclosed devices and methods may be implemented in other ways. The device embodiments described above are only illustrative. For example, the division of the units is only a logical function division. In actual implementation, there may be other division methods. For example, multiple units or components can be combined or May be integrated into another system, or some features may be ignored, or not implemented. In another point, the mutual coupling or direct coupling or communication connection shown or discussed may be through some communication interfaces, and the indirect coupling or communication connection of devices or units may be in electrical, mechanical or other forms.
另外，作为分离部件说明的单元可以是或者也可以不是物理上分开的，作为单元显示的部件可以是或者也可以不是物理单元，即可以位于一个地方，或者也可以分布到多个网络单元上。可以根据实际的需要选择其中的部分或者全部单元来实现本实施例方案的目的。In addition, the units described as separate components may or may not be physically separated, and the components displayed as units may or may not be physical units, that is, they may be located in one place, or may be distributed to multiple network units. Part or all of the units can be selected according to actual needs to achieve the purpose of the solution of this embodiment.
再者，在本申请各个实施例中的各功能模块可以集成在一起形成一个独立的部分，也可以是各个模块单独存在，也可以两个或两个以上模块集成形成一个独立的部分。Furthermore, each functional module in each embodiment of the present application may be integrated to form an independent part, each module may exist independently, or two or more modules may be integrated to form an independent part.
以上所述仅为本申请的实施例而已，并不用于限制本申请的保护范围，对于本领域的技术人员来说，本申请可以有各种更改和变化。凡在本申请的精神和原则之内，所作的任何修改、等同替换、改进等，均应包含在本申请的保护范围之内。The above descriptions are only examples of the present application, and are not intended to limit the scope of protection of the present application. For those skilled in the art, various modifications and changes may be made to the present application. Any modifications, equivalent replacements, improvements, etc. made within the spirit and principles of this application shall be included within the protection scope of this application.
Claims (9)
- 一种内窥镜图像去雾方法，其特征在于，包括：A method for defogging an endoscope image, comprising:获取内窥镜采集的原始图像；Obtain the original image collected by the endoscope;计算所述原始图像每个通道像素对应的大气亮度值；Calculate the atmospheric brightness value corresponding to each channel pixel of the original image;根据所述原始图像以及所述原始图像每个通道像素对应的大气亮度值进行去雾处理；performing defogging processing according to the original image and the atmospheric brightness value corresponding to each channel pixel of the original image;所述计算所述原始图像每个通道像素对应的大气亮度值包括：The calculation of the atmospheric brightness value corresponding to each channel pixel of the original image includes:对所述原始图像进行高斯滤波得到每个通道像素的灰度值；Gaussian filtering is performed on the original image to obtain the gray value of each channel pixel;设置所述原始图像每个通道像素的大气亮度值权重；Setting the atmospheric brightness value weight of each channel pixel of the original image;根据所述每个通道像素的灰度值以及所述原始图像每个通道像素的大气亮度值权重计算所述原始图像每个通道像素对应的大气亮度值。The atmospheric brightness value corresponding to each channel pixel of the original image is calculated according to the gray value of each channel pixel and the atmospheric brightness value weight of each channel pixel of the original image.
- 根据权利要求1所述的一种内窥镜图像去雾方法，其特征在于，所述设置所述原始图像每个通道像素的大气亮度值权重的步骤包括：A kind of endoscopic image defogging method according to claim 1, is characterized in that, the step of described setting the atmospheric brightness value weight of each channel pixel of described original image comprises:获取所述原始图像的均值以及方差；Obtain the mean and variance of the original image;根据所述原始图像的均值以及方差计算得出所述原始图像每个通道像素的大气亮度值权重。The atmospheric brightness value weight of each channel pixel of the original image is calculated according to the mean value and the variance of the original image.
- 根据权利要求1所述的一种内窥镜图像去雾方法，其特征在于，所述根据所述原始图像以及所述原始图像每个通道像素对应的大气亮度值进行去雾处理的步骤还包括：A method for defogging an endoscope image according to claim 1, wherein the step of performing defogging processing according to the original image and the atmospheric brightness value corresponding to each channel pixel of the original image further includes :根据所述原始图像每个通道像素对应的大气亮度值得到每个通道像素对应的传输函数；Obtain the transfer function corresponding to each channel pixel according to the atmospheric brightness value corresponding to each channel pixel of the original image;根据所述每个通道像素对应的传输函数、所述原始图像以及所述原始图像每个通道像素对应的大气亮度值进行去雾处理。Dehaze processing is performed according to the transfer function corresponding to each channel pixel, the original image, and the atmospheric brightness value corresponding to each channel pixel of the original image.
- 根据权利要求3所述的一种内窥镜图像去雾方法，其特征在于，所述根据所述每个通道像素对应的传输函数、所述原始图像以及所述原始图像每个通道像素对应的大气亮度值进行去雾处理的步骤还包括：The method for defogging an endoscopic image according to claim 3, wherein, according to the transfer function corresponding to each channel pixel, the original image, and each channel pixel corresponding to the original image The steps of performing dehazing processing on the atmospheric brightness value also include:通过导向滤波细化所述每个通道像素对应的传输函数；refine the transfer function corresponding to each channel pixel by guided filtering;根据细化后的所述每个通道像素对应的传输函数、所述原始图像以及所述原始图像每个通道像素对应的大气亮度值进行去雾处理。Dehazing is performed according to the refined transfer function corresponding to each channel pixel, the original image, and the atmospheric brightness value corresponding to each channel pixel of the original image.
- 根据权利要求1所述的一种内窥镜图像去雾方法，其特征在于，所述根据所述每个通道像素的灰度值以及所述原始图像每个通道像素的大气亮度值权重计算所述原始图像每个通道像素对应的大气亮度值的公式为：A kind of method for defogging endoscopic image according to claim 1, it is characterized in that, according to the gray value of each channel pixel and the atmospheric brightness value weight calculation of each channel pixel of the original image The formula of the atmospheric brightness value corresponding to each channel pixel of the original image is:A c(x)＝255*Pwt c(x)+(1-Pwt c(x))*G c(x)； A c (x)=255*Pwt c (x)+(1-Pwt c (x))*G c (x);其中，A c(x)为第c个通道像素对应的大气亮度值、Pwt c(x)为第c个通道像素的大气亮度值权重、G c(x)为高斯滤波后第c个通道像素的灰度值。 Among them, A c (x) is the atmospheric brightness value corresponding to the cth channel pixel, Pwt c (x) is the atmospheric brightness value weight of the cth channel pixel, G c (x) is the cth channel pixel after Gaussian filtering the gray value of .
- 根据权利要求2所述的一种内窥镜图像去雾方法，其特征在于，所述根据所述原始图像的均值以及方差计算得出所述原始图像每个通道像素的大气亮度值权重的公式为：A method for defogging an endoscope image according to claim 2, wherein the formula for calculating the atmospheric brightness value weight of each channel pixel of the original image according to the mean value and variance of the original image is for:
其中，Pwt c(x)为第c个通道像素的大气亮度值权重、e为自然常数、f mean为所述原始图像的均值、f std为所述原始图像的方差。 Wherein, Pwt c (x) is the atmospheric brightness value weight of the cth channel pixel, e is a natural constant, f mean is the mean value of the original image, and f std is the variance of the original image. - 一种内窥镜图像去雾装置，其特征在于，包括：An endoscopic image defogging device is characterized in that it comprises:获取模块，用于获取内窥镜采集的原始图像；Obtaining module, for obtaining the raw image that endoscope collects;计算模块，用于计算所述原始图像每个通道像素对应的大气亮度值；A calculation module, configured to calculate the atmospheric brightness value corresponding to each channel pixel of the original image;处理模块，用于根据所述原始图像以及所述原始图像每个通道像素对应的大气亮度值进行去雾处理；A processing module, configured to perform defogging processing according to the original image and the atmospheric brightness value corresponding to each channel pixel of the original image;所述计算所述原始图像每个通道像素对应的大气亮度值包括：The calculation of the atmospheric brightness value corresponding to each channel pixel of the original image includes:对所述原始图像进行高斯滤波得到每个通道像素的灰度值；Gaussian filtering is performed on the original image to obtain the gray value of each channel pixel;设置所述原始图像每个通道像素的大气亮度值权重；Setting the atmospheric brightness value weight of each channel pixel of the original image;根据所述每个通道像素的灰度值以及所述原始图像每个通道像素的大气亮度值权重计算所述原始图像每个通道像素对应的大气亮度值。The atmospheric brightness value corresponding to each channel pixel of the original image is calculated according to the gray value of each channel pixel and the atmospheric brightness value weight of each channel pixel of the original image.
- 一种电子设备，其特征在于，包括处理器以及存储器，所述存储器存储有计算机可读取指令，当所述计算机可读取指令由所述处理器执行时，运行如权利要求1-6任一项所述方法中的步骤。An electronic device, characterized in that it includes a processor and a memory, the memory stores computer-readable instructions, and when the computer-readable instructions are executed by the processor, it operates as claimed in any one of claims 1-6. A step in said method.
- 一种存储介质，其上存储有计算机程序，其特征在于，所述计算机程序被处理器执行时，运行如权利要求1-6任一项所述方法中的步骤。A storage medium, on which a computer program is stored, wherein, when the computer program is executed by a processor, the steps in the method according to any one of claims 1-6 are executed.
Applications Claiming Priority (2)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202210010941.8A CN114022397B (en) | 2022-01-06 | 2022-01-06 | Endoscope image defogging method and device, electronic equipment and storage medium |
| CN202210010941.8 | 2022-01-06 |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| WO2023130547A1 true WO2023130547A1 (en) | 2023-07-13 |
Family
ID=80069596
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| PCT/CN2022/078031 WO2023130547A1 (en) | 2022-01-06 | 2022-02-25 | Endoscopic image dehazing method and apparatus, electronic device, and storage medium |
Country Status (2)
| Country | Link |
|---|---|
| CN (1) | CN114022397B (en) |
| WO (1) | WO2023130547A1 (en) |
Families Citing this family (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN114022397B (en) * | 2022-01-06 | 2022-04-19 | 广东欧谱曼迪科技有限公司 | Endoscope image defogging method and device, electronic equipment and storage medium |
| CN114881896B (en) * | 2022-07-12 | 2022-10-04 | 广东欧谱曼迪科技有限公司 | Endoscope image real-time defogging method and device, electronic equipment and storage medium |
Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| EP1744279A1 (en) * | 2005-07-11 | 2007-01-17 | Thomson Licensing | Method and device for filtering an image using side information |
| CN111626962A (en) * | 2020-05-27 | 2020-09-04 | 重庆邮电大学 | CMOS endoscope image enhancement method |
| CN112419210A (en) * | 2020-12-08 | 2021-02-26 | 大连海事大学 | Underwater image enhancement method based on color correction and three-interval histogram stretching |
| CN112419162A (en) * | 2019-08-20 | 2021-02-26 | 浙江宇视科技有限公司 | Image defogging method and device, electronic equipment and readable storage medium |
| CN114022397A (en) * | 2022-01-06 | 2022-02-08 | 广东欧谱曼迪科技有限公司 | Endoscope image defogging method and device, electronic equipment and storage medium |
| 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 |
Family Cites Families (11)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US10537236B2 (en) * | 2013-01-17 | 2020-01-21 | Stryker Corporation | Anti-fogging device for endoscope |
| CN104766307A (en) * | 2015-03-13 | 2015-07-08 | 青岛海信电器股份有限公司 | Picture processing method and device |
| CN104732494A (en) * | 2015-03-23 | 2015-06-24 | 无锡中科智能农业发展有限责任公司 | Tissue culturing monitoring method and system based on image mist elimination |
| CN108230275A (en) * | 2018-02-05 | 2018-06-29 | 电子科技大学 | The method of image defogging |
| CN108765311A (en) * | 2018-04-26 | 2018-11-06 | 长安大学 | More air light value image defogging methods based on random walk cluster |
| CN108986049A (en) * | 2018-07-20 | 2018-12-11 | 百度在线网络技术（北京）有限公司 | Method and apparatus for handling image |
| CN113344796A (en) * | 2020-02-18 | 2021-09-03 | 腾讯科技（深圳）有限公司 | Image processing method, device, equipment and storage medium |
| CN111568352B (en) * | 2020-04-14 | 2023-12-05 | 广东欧谱曼迪科技有限公司 | Endoscope system capable of automatically adjusting light source spectrum and spectrum adjusting method thereof |
| CN112734679A (en) * | 2021-01-26 | 2021-04-30 | 西安理工大学 | Fusion defogging method for medical operation video images |
| CN113079361B (en) * | 2021-03-29 | 2022-06-07 | 鹰利视医疗科技有限公司 | Ultra-high-definition image enhancement system and method for medical endoscope |
| CN113436124B (en) * | 2021-06-29 | 2024-04-05 | 上海海事大学 | Single image defogging method applied to ocean foggy environment |
-
2022
- 2022-01-06 CN CN202210010941.8A patent/CN114022397B/en active Active
- 2022-02-25 WO PCT/CN2022/078031 patent/WO2023130547A1/en unknown
Patent Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| EP1744279A1 (en) * | 2005-07-11 | 2007-01-17 | Thomson Licensing | Method and device for filtering an image using side information |
| CN112419162A (en) * | 2019-08-20 | 2021-02-26 | 浙江宇视科技有限公司 | Image defogging method and device, electronic equipment and readable storage medium |
| CN111626962A (en) * | 2020-05-27 | 2020-09-04 | 重庆邮电大学 | CMOS endoscope image enhancement method |
| CN112419210A (en) * | 2020-12-08 | 2021-02-26 | 大连海事大学 | Underwater image enhancement method based on color correction and three-interval histogram stretching |
| CN114022397A (en) * | 2022-01-06 | 2022-02-08 | 广东欧谱曼迪科技有限公司 | Endoscope image defogging method and device, electronic equipment and storage medium |
| 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 |
Also Published As
| Publication number | Publication date |
|---|---|
| CN114022397B (en) | 2022-04-19 |
| CN114022397A (en) | 2022-02-08 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| WO2023130547A1 (en) | Endoscopic image dehazing method and apparatus, electronic device, and storage medium | |
| Sun et al. | Fast single image haze removal via local atmospheric light veil estimation | |
| WO2020151307A1 (en) | Automatic lesion recognition method and device, and computer-readable storage medium | |
| Khan et al. | A region growing and local adaptive thresholding-based optic disc detection | |
| Hsu et al. | Medical image enhancement using modified color histogram equalization | |
| WO2021083059A1 (en) | Image super-resolution reconstruction method, image super-resolution reconstruction apparatus, and electronic device | |
| Tchaka et al. | Chromaticity based smoke removal in endoscopic images | |
| WO2020038312A1 (en) | Multi-channel tongue body edge detection device and method, and storage medium | |
| CN114066780B (en) | 4k endoscope image defogging method and device, electronic equipment and storage medium | |
| CN111192205A (en) | Image defogging method and system and computer readable storage medium | |
| Singh et al. | Illumination estimation for nature preserving low-light image enhancement | |
| CN110473176B (en) | Image processing method and device, fundus image processing method and electronic equipment | |
| CN108629750A (en) | A kind of night defogging method, terminal device and storage medium | |
| CN113808054A (en) | Method for repairing optic disc region of fundus image and related product | |
| US20220130047A1 (en) | Diagnostic imaging for diabetic retinopathy | |
| CN113139929A (en) | Gastrointestinal tract endoscope image preprocessing method comprising information screening and fusion repairing | |
| Li et al. | Dr-Net: transmission steered single image dehazing network with weakly supervised refinement | |
| US20210365675A1 (en) | Method, apparatus and device for identifying body representation information in image, and computer readable storage medium | |
| Nguyen et al. | Image blurring effects due to depth discontinuitites: Blurring that creates emergent image details | |
| Badgujar et al. | MBO-SVM-based exudate classification in fundus retinal images of diabetic patients | |
| Poostchi et al. | Diabetic retinopathy dark lesion detection: preprocessing phase | |
| CN113470028A (en) | Chromosome karyotype image quality evaluation method, chromosome analyzer, and storage medium | |
| Lin et al. | Research on the illumination robust of target recognition | |
| CN115937016B (en) | Contrast enhancement method for guaranteeing image details | |
| Abel et al. | Automatic glare removal in endoscopic imaging |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| 121 | Ep: the epo has been informed by wipo that ep was designated in this application |
Ref document number: 22918014 Country of ref document: EP Kind code of ref document: A1 |