System and method for reducing smoke in an image

Abstract

A method for reducing haze in an image includes accessing an RGB image of an object obscured by haze; determining a dark channel matrix of the RGB image; estimating an airlight matrix of the RGB image based on the dark channel; determining a transmission map based on the airlight matrix and the dark channel matrix; dehazing the RGB image based on the transmission map to reduce the haze in the RGB image; and displaying the dehazed RGB image on a display device. The RGB image includes a plurality of pixels. For each pixel of the plurality of pixels, the dark channel matrix includes a minimum color component intensity of a respective pixel region centered at the respective pixel. The airlight matrix includes an airlight component value for each of the plurality of pixels.

Description

Technical Field

[0001] This disclosure relates to apparatus, systems, and methods for reducing smoke in images, and more specifically, to reducing smoke in images during surgical procedures. Background Technology

[0002] Endoscopes are introduced through incisions or natural body openings to visualize internal features of the body. Conventional endoscopes are used for visualization during endoscopic or laparoscopic surgery. During these procedures, smoke may be generated when energy surgical instruments are used, such as when cutting tissue with electrosurgical energy during surgery. Therefore, the images acquired by the endoscope may be blurred due to this smoke. While the surgeon waits for the smoke to dissipate, it may obscure features of the surgical site and delay the procedure. Similar problems can arise in other procedures due to the presence of smoke during image capture. Therefore, there is interest in improving imaging techniques. Summary of the Invention

[0003] This disclosure relates to apparatus, systems, and methods for reducing smoke in images. According to various aspects of this disclosure, a method for reducing smoke in an image includes: accessing an RGB image of an object obscured by smoke; determining a dark channel matrix of the RGB image; estimating an atmospheric light matrix of the RGB image based on the dark channel matrix; determining a transmission map based on the atmospheric light matrix and the dark channel matrix; dehazing the RGB image based on the transmission map to reduce smoke in the RGB image; and displaying the dehazed RGB image on a display device. The RGB image includes a plurality of pixels. For each of the plurality of pixels, the dark channel matrix includes the minimum color component intensity of a corresponding pixel region centered on the corresponding pixel. The atmospheric light matrix includes atmospheric light component values ​​for each of the plurality of pixels.

[0004] In one aspect of this disclosure, dehazing an RGB image includes converting the RGB image to a YUV image; performing a dehazing operation on the YUV image to provide a Y'UV image; and converting the Y'UV image to a dehazed RGB image.

[0005] In one aspect of this disclosure, performing a dehazing operation on a YUV image includes, for each pixel x among a plurality of pixels, determining Y' as... T(x) is the transmission component of pixel x. A(x) is the atmospheric light component of pixel x.

[0006] In another aspect of this disclosure, performing a dehazing operation on a YUV image further includes replacing the Y channel of the YUV image with the determined Y' to provide a Y'UV image.

[0007] In one aspect of this disclosure, for each pixel x among a plurality of pixels, estimating the atmospheric light matrix includes: determining the atmospheric light component values ​​of pixel x as: A(x) = max(min(I c (y)))*coef, where all y∈Ω(x), where Ω(x) is the pixel region centered at pixel x, and y is the number of pixels in the pixel region Ω(x). c (y) represents the intensity value of the color component c of pixel y, and coef is a predetermined coefficient value.

[0008] In one aspect of this disclosure, determining the transmission map includes, for each pixel x among a plurality of pixels, determining the transmission components as follows: Where ω is a predetermined constant, I_DARK(x) is the dark channel matrix value of pixel x, and A(x) is the atmospheric light component value of pixel x.

[0009] According to various aspects of this disclosure, a method for reducing haze in an image is proposed. The method includes accessing an image obscured by haze; for each of a plurality of pixels: (i) determining the dark channel matrix value of the corresponding pixel as the minimum color component intensity value of the corresponding pixel region centered on the corresponding pixel; and (ii) estimating the atmospheric light component value of pixel x based on the minimum color component intensity value of each pixel in the pixel region; dehazing the image based on the atmospheric light component values ​​of the plurality of pixels; and displaying the dehazed image on a display device. The image comprises a plurality of pixels, wherein each pixel of the image comprises a plurality of color components.

[0010] In another aspect of this disclosure, dehazing an image includes determining the transmission map value of each pixel x among a plurality of pixels as follows: Convert the image to a YUV image; determine the Y' of each pixel x in the multiple pixels. And replace the Y channel of the YUV image with the determined Y' to provide a Y'UV image, where ω is a predetermined constant, I_DARK(x) is the dark channel matrix value of pixel x, and A(x) is the atmospheric light component value of pixel x.

[0011] In one aspect of this disclosure, dehazing an image also includes converting a Y'UV image into a dehazed image.

[0012] In another aspect of this disclosure, the image includes at least one of an RGB image, a CMYK image, a CIELAB image, or a CIEXYZ image.

[0013] In one aspect of this disclosure, for each pixel x among a plurality of pixels, estimating the atmospheric light matrix includes: determining the atmospheric light component values ​​of pixel x as A(x) = max(min(I c(y)))*coef, where all y∈Ω(x), where Ω(x) is the pixel region centered at pixel x, and y is the number of pixels in the pixel region Ω(x). c (y) represents the intensity value of the color component c of pixel y, and coef is a predetermined coefficient value.

[0014] According to various aspects of this disclosure, a system for reducing haze in an image is proposed. The system may include a light source configured to provide light; an imaging device configured to acquire an image; and an imaging device control unit configured to control the imaging device. The image includes a plurality of pixels, wherein each pixel of the image may include a plurality of color components. The control unit may include a processor and a memory storing instructions. When executed by the processor, the instructions cause the system to access the image, for each pixel: determine the dark channel matrix value of the corresponding pixel as the minimum color component intensity value of the corresponding pixel region centered on the corresponding pixel; estimate the atmospheric light component value of each pixel based on the minimum color component intensity value of each pixel in the pixel region; dehaze the image based on the atmospheric light component value of each pixel; and display the dehazed image on a display device.

[0015] In another aspect of this disclosure, the instructions, when dehazing an image, can also cause the system to determine the transmission map value of each pixel x among a plurality of pixels as follows: Convert the image to a YUV image; determine Y' as... And replace the Y channel of the YUV image with the determined Y' to provide a Y'UV image, where ω is a predetermined constant, I_DARK(x) is the dark channel matrix value of pixel x, and A(x) is the atmospheric light component value of pixel x.

[0016] In another aspect of this disclosure, the instructions may also cause the system to convert a Y'UV image into a dehazed image when dehazing an image.

[0017] In another aspect of this disclosure, the image includes at least one of an RGB image, a CMYK image, a CIELAB image, or a CIEXYZ image.

[0018] In one aspect of this disclosure, estimating the atmospheric light matrix includes determining the atmospheric light component value of pixel x as A(x) = max(min(I c (y)))*coef, where all y∈Ω(x). Here, y is a pixel, I c (y) represents the intensity value of the color component c of pixel y, and coef is a predetermined coefficient value.

[0019] Further details and aspects of various embodiments of this disclosure are described in more detail below with reference to the accompanying drawings. Attached Figure Description

[0020] Embodiments of this disclosure are described herein with reference to the accompanying drawings, in which:

[0021] Figure 1 A diagram of an exemplary visualization or endoscope system according to this disclosure;

[0022] Figure 2 for Figure 1 A schematic configuration of a visualization or endoscope system;

[0023] Figure 3 For illustration Figure 1 A diagram illustrating another schematic configuration of the system's optical system;

[0024] Figure 4 A schematic configuration of a visualization or endoscopy system according to embodiments of the present disclosure;

[0025] Figure 5 A flowchart of a method for reducing smoke according to an exemplary embodiment of the present disclosure;

[0026] Figure 6 An exemplary input image including pixel regions according to this disclosure;

[0027] Figure 7 Here is a flowchart of a method for performing defogging according to this disclosure;

[0028] Figure 8 An exemplary image with smoke according to this disclosure;

[0029] Figure 9 An exemplary dehazed image with constant atmospheric light; and

[0030] Figure 10 An exemplary dehazed image with atmospheric light calculated according to this disclosure.

[0031] Further details and aspects of exemplary embodiments of the present disclosure are described in more detail below with reference to the accompanying drawings. Any of the above aspects and embodiments of the present disclosure may be combined without departing from the scope of the present disclosure. Detailed Implementation

[0032] Embodiments of the currently disclosed devices, systems, and processing methods are described in detail with reference to the accompanying drawings, wherein in each of the several views, the same reference numerals designate the same or corresponding elements. As used herein, the term "distal" refers to the portion of the structure farther from the user, while the term "proximal" refers to the portion of the structure closer to the user. The term "clinician" refers to a doctor, nurse, or other care provider, and may include assistants.

[0033] This disclosure applies to situations involving the capture of images of surgical sites. Endoscopic systems are provided as examples, but it should be understood that such descriptions are exemplary and do not limit the scope and applicability of this disclosure to other systems and processes.

[0034] First refer to Figure 1-3 According to this disclosure, the endoscope system 1 includes an endoscope 10, a light source 20, a video system 30, and a display device 40. (Continue to reference) Figure 1 A light source 20 (such as an LED / xenon light source) is connected to the endoscope 10 via a fiber guide 22, which is operatively coupled to the light source 20 and to an internal coupler 16 disposed on or near the handle 18 of the endoscope 10. The fiber guide 22 includes, for example, an optical fiber cable that extends through the elongated body 12 of the endoscope 10 and terminates at the distal end 14 of the endoscope 10. Thus, light from the light source 20 is transmitted through the fiber guide 22 and exits at the distal end 14 of the endoscope 10 towards a targeted internal feature (such as tissue or organ) of the patient's body. Because the light transmission path in this configuration is relatively long (e.g., the length of the fiber guide 22 can be from about 1.0 m to about 1.5 m), only about 15% (or less) of the luminous flux emitted from the light source 20 is output from the distal end 14 of the endoscope 10.

[0035] refer to Figure 2 and Figure 3 The video system 30 is operatively connected to the image sensor 32, which is mounted to or housed within the handle 18 of the endoscope 10 via a data cable 34. An objective lens 36 is positioned at the distal end 14 of the elongated body 12 of the endoscope 10, and a series of spaced-apart relay lenses 38 (such as rod lenses) are positioned along the length of the elongated body 12 between the objective lens 36 and the image sensor 32. Images captured by the objective lens 36 are relayed via the relay lenses 38 through the elongated body 12 of the endoscope 10 to the image sensor 32, then transmitted to the video system 30 for processing and output to the display device 40 via a cable 39. The image sensor 32 is positioned within or mounted on the handle 18 of the endoscope 10, which may be up to approximately 30 cm from the distal end 14 of the endoscope 10.

[0036] refer to Figure 4-7The flowchart includes various blocks described in an ordered order. However, those skilled in the art will understand that one or more blocks of the flowchart may be performed, repeated, and / or omitted in a different order without departing from the scope of this disclosure. The following description of the flowchart relates to various actions or tasks performed by one or more video systems 30, but those skilled in the art will understand that the video system 30 is exemplary. In various embodiments, the disclosed operations may be performed by another component, device, or system. In various embodiments, the video system 30 or other components / devices perform actions or tasks via one or more software applications executing on a processor. In various embodiments, at least some of the operations may be implemented by firmware, programmable logic devices, and / or hardware circuitry. Other implementations are considered to be within the scope of this disclosure.

[0037] refer to Figure 4 The diagram illustrates a schematic configuration of the system, which can be... Figure 1 The endoscopic system may be of different types (e.g., visualization systems, etc.). According to this disclosure, the system includes an imaging device 410, a light source 420, a video system 430, and a display device 440. The light source 420 is configured to provide light to the surgical site via a fiber guide 422 through the imaging device 410. The distal end 414 of the imaging device 410 includes an objective lens 436 for capturing images at the surgical site. The objective lens 436 forwards the images to an image sensor 432. The images are then transmitted to the video system 430 for processing. The video system 430 includes an imaging device controller 450 for controlling the endoscope and processing the images. The imaging device controller 450 includes a processor 452 connected to a computer-readable storage medium or memory 454, which may be volatile memory (such as RAM), non-volatile memory (such as flash memory, disk media), or other types of memory. In various embodiments, processor 452 may be another type of processor, such as, but not limited to, digital signal processor, microprocessor, ASIC, graphics processing unit (GPU), field programmable gate array (FPGA), or central processing unit (CPU).

[0038] In various embodiments, memory 454 may be random access memory, read-only memory, disk storage, solid-state memory, optical disk storage, and / or another type of memory. In various embodiments, memory 454 may be separable from imaging device controller 450 and may communicate with processor 452 via a communication bus on a circuit board and / or via a communication cable such as a serial ATA cable or other types of cable. Memory 454 includes computer-readable instructions executable by processor 452 to operate imaging device controller 450. In various embodiments, imaging device controller 450 may include network interface 540 for communicating with other computers or servers.

[0039] Now for reference Figure 5 This illustrates operations used for smoke reduction in images. In various embodiments, Figure 5 The operation can be performed by the endoscopic system 1 described above herein. In various embodiments, Figure 5 The operation can be performed by another type of system and / or during another type of process. The following description will refer to an endoscopic system, but it should be understood that such description is exemplary and does not limit the scope and applicability of this disclosure to other systems and processes. The following description will refer to RGB (red, green, blue) images or RGB color models, but it should be understood that such description is exemplary and does not limit the scope and applicability of this disclosure to other types of images or color models (e.g., CMYK (cyan, magenta, yellow, key colors), CIELAB, or CIEXYZ). Image sensor 32 can capture raw data. The format of the raw data can be RGGB, RGBG, GRGB, or BGGR. Video system 30 can use a demosaicing algorithm to convert the raw data to RGB. The demosaicing algorithm is a digital image processing technique used to reconstruct a full-color image from incomplete color samples output by an image sensor covered with a color filter array (CFA). It is also known as CFA interpolation or color reconstruction. The RGB image can be further converted to another color model, such as CMYK, CIELAB, or CIEXYZ, via the video system 30.

[0040] Initially, in step 502, an image of the surgical site is captured via objective lens 36 and forwarded to image sensor 32 of endoscopy system 1. As used herein, the term "image" can include still images or moving images (e.g., video). In various embodiments, the captured image is transmitted to video system 30 for processing. For example, during an endoscopic examination, a surgeon may cut tissue using electrosurgical instruments. During this cutting, smoke may be generated. When an image is captured, it may include the smoke. Smoke is typically a turbid medium in the atmosphere (such as particles, water droplets). The irradiance received by objective lens 36 from the scene point is attenuated by the line of sight. This incident light mixes with ambient light (air light) and is reflected into the line of sight by atmospheric particles (such as smoke). This smoke degrades image quality, causing it to lose contrast and color fidelity.

[0041] Figure 6An exemplary pixel representation of the image captured in step 502 is shown. In various embodiments, the captured image may or may not be processed during or after the capture process. In various embodiments, image 600 comprises a plurality of pixels, and the size of image 600 is typically represented as a number of pixels in an X by Y format, such as 500 × 500 pixels. According to aspects of this disclosure, and as will be explained in more detail hereafter, each pixel of image 600 may be processed based on a pixel region 602, 610 centered on the pixel, which is also referred to herein as a color patch. In various embodiments, each color patch / pixel region of the image may have the same size. In various embodiments, different pixel regions or color patches may have different sizes. Each pixel region or color patch may be represented as Ω(x), which is a pixel region / color patch centered on a particular pixel x. Figure 6 In the illustrative example, pixel region 602 is 3×3 pixels in size and centered at a specific pixel x1 606. If the image has 18×18 pixels, the color patch size can be 3×3 pixels. The illustrated image size and color patch size are exemplary, and other image sizes and color patch sizes are also considered to be within the scope of this disclosure.

[0042] Continue to refer to Figure 6 Each pixel 601 in image 600 may have a combination of color components 612, such as red, green, and blue, which are also referred to herein as color channels. c (y) is used herein to represent the intensity value of the color component c of a specific pixel y in image 600. For pixel 601, each of the color components 612 has an intensity value representing the luminance intensity of said color component. For example, for a 24-bit RGB image, each of the color components 612 has 8 bits, which corresponds to each color component having 256 possible intensity values.

[0043] Refer again Figure 5 In step 504, the video system 30 determines the dark channel matrix of the image 600. As used herein, the phrase "dark channel" for a pixel refers to the lowest color component intensity value among all pixels of a color patch Ω(x) 602 centered at a particular pixel x. As used herein, the term "dark channel matrix" for an image refers to the matrix of the dark channels of each pixel in the image. The dark channel of pixel x will be represented as I_DARK(x). In various embodiments, the video system 30 calculates the dark channel of a pixel as follows:

[0044] I_DARK(x)=min(min(I c (y))), where all c∈{r, g, b}y∈Ω(x)

[0045] Where y represents the pixel of color block Ω(x), c represents the color component, and I c (y) represents the intensity value of the color component c of pixel y. Therefore, the dark channel of pixel x is the result of two minimum operations across two variables, c and y, which together determine the lowest color component intensity value among all pixels in the color patch centered at pixel x. In various embodiments, the video system 30 can calculate the dark channel of a pixel by obtaining the lowest color component intensity value for each pixel in the color patch and then finding the minimum of all these values. For cases where the center pixel of the color patch is at or near an image edge, only a portion of the color patch in the image is used.

[0046] For example, refer to Figure 6 For the image 600 captured in step 502, the height and width of the image 600 can be 18×18 pixels, and the pixel region (color patch) size can be 3×3 pixels. For example, the 3×3 pixel region Ω(x1)602 centered at x1606 can have the following intensities for the R, G, and B channels of each of the 9 pixels in the color patch:

[0047]

[0048] In this example, for the top-left pixel in pixel region Ω(x1)602, the intensity of the R channel can be 1, the intensity of the G channel can be 3, and the intensity of the B channel can be 6. Here, the R channel has the minimum intensity value (value 1) of the RGB channels of the pixel.

[0049] The minimum color component intensity value for each pixel will be determined. For example, for a 3×3 pixel region Ω(x1)602 centered at x1, the minimum color component intensity value for each pixel in pixel region Ω(x1)602 is:

[0050]

[0051] Therefore, for the exemplary 3×3 pixel region Ω(x)602 centered at x1, the intensity value of the dark channel of the pixel is 0.

[0052] Refer again Figure 5 In step 506, the video system 30 estimates the atmospheric light component of each pixel, and the atmospheric light components of all pixels are collectively referred to herein as the "atmospheric light matrix". The estimated atmospheric light component of pixel x will be represented herein as A(x). In various embodiments, A(x) can be determined based on the lowest color component intensity value of each pixel y 604 in pixel region Ω(x) 602, which can be expressed as:

[0053] A(x)=f(min(I c(y))), where all c∈{r,g,b}y∈Ω(x),

[0054] Where f() is the operation used to estimate the atmospheric light component based on the lowest color component intensity value of each pixel y 604 in color patch Ω(x1)602. In various embodiments, the operation f() can determine min(I c The maximum value in (y) for y∈Ω(x). In various embodiments, the maximum value may be scaled by a coefficient "coef", the value of which may be between 0 and 1 in various embodiments, such as 0.85. Embodiments of the above atmospheric light components may be provided as follows:

[0055] A(x)=f(min(I c (y)))=max(min(I c (y)))*coef, where all c∈{r,g,b}y∈Ω(x)

[0056] For example, for the intensity value in color block Ω(x1)602, using the same example as above, video system 30 determines the atmospheric light component A(x1) as 9*coef.

[0057] In step 508, the video system 30 determines the content referred to herein as the transmission map T. The transmission map T is determined based on the dark channel matrix and atmospheric light matrix determined in steps 504 and 506. The transmission map includes a transmission component T(x) for each pixel x. In various embodiments, the transmission components may be determined as follows:

[0058]

[0059] Here, ω is a parameter with a value between 0 and 1 (e.g., 0.85). In reality, even in clear images, there are some particles. Therefore, some haze exists when observing distant objects. The presence of haze suggests human perception of depth. If all haze were eliminated, the perception of depth might be lost. Therefore, to preserve some haze, the parameter ω (0 < ω <= 1) is introduced. In various embodiments, the value of ω can vary based on the specific application. Therefore, the transmittance map is equal to 1 minus ω multiplied by the dark channel (I-DARK(x)) of the pixel divided by the atmospheric light component A(x) of the pixel.

[0060] In step 510, the video system 30 performs dehazing on the image based on the transmission map. Figure 7 The illustration shows one way to perform a defogging operation.

[0061] refer to Figure 7The illustrated operation assumes the original image is an RGB image. The operation attempts to preserve as much of the original RGB image 600's color as possible during the dehazing process. In various embodiments, the dehazing operation converts image 600 from the RGB color space to the YUV color space (Y for luminance, U and V for chrominance or color), and applies dehazing to the Y (luminance) channel, which is typically a weighted sum of the RGB color channels.

[0062] Initially, in step 702, the video system 30 converts the RGB image 600 into a YUV image represented as I-YUV. The conversion of each pixel from RGB to YUV can be performed as follows:

[0063]

[0064] Next, in step 704, the video system 30 performs a dehazing operation on channel Y (luminance) of the I-YUV image. According to various aspects of this disclosure, the dehazing operation is as follows:

[0065]

[0066] Where Y′(x) is the Y (luminance) channel of the blurred image IY′UV. A(x) is the estimated atmospheric light component of pixel x, and T(x) is the transmission map value of pixel x. Therefore, the Y (luminance) channel of the dehazed image IY′UV is equal to the difference between the Y (luminance) channel of the image I-YUV and the estimated atmospheric light component A(x) calculated in step 506, divided by the transmission map value T(x) determined in step 508.

[0067] Finally, in step 706, the video system 30 converts the YUV image IY′UV into a dehazed RGB image. The conversion from YUV to RGB is as follows:

[0068]

[0069] In various embodiments, the video system 30 may transmit the resulting dehazed RGB image to the display device 40, or save it to a memory or external storage device for later retrieval or further processing. Although Figure 7 The operations described are for RGB images, but it should be understood that the operations disclosed can also be applied to other color spaces.

[0070] Figure 8-10 Example results of the methods described in the preceding sections are shown. Figure 8An image 800 is shown capturing smoke during a surgical procedure using an endoscopic system 1. For example, during an endoscopic examination, a surgeon may use an electrosurgical instrument 802 to cut tissue 804. During this cutting, smoke 806 may be generated. The smoke 806 will be captured in image 800.

[0071] Figure 9 Image 900, which has been dehazed, is shown. Figure 8 Image 800 is dehazed based on a constant atmospheric light value. Image 1000, still somewhat obscured by smoke 806, may include electrosurgical instruments 802 and tissue 804. For example, in the case where a constant atmospheric light value A is used instead of the atmospheric light matrix A estimated by the formula used in step 506.

[0072] Figure 10 It shows the use of Figure 5 and 7 The method described herein involves dehazing a dehazed RGB image 1000. The dehazed RGB image 1000 may include an electrosurgical instrument 802 and tissue 804. The method can be used to dehaze images captured during surgical procedures. Figure 8 The image 800 begins, as in step 502 using the endoscope system 1. For example, the image may be approximately 20 × 20 pixels. Next, as in step 504, the video system 30 determines the dark channel matrix of the image. For example, the size of the pixel region Ω(x) may be set to approximately 3 × 3 pixels.

[0073] As in step 506, the video system 30 estimates the maximum value of the minimum color component intensity of each pixel in the pixel region and multiplies this maximum value by a coefficient (e.g., 0.85), thereby using... Figure 8 The atmospheric light matrix is ​​estimated using the determined dark channel matrix of the image. Next, as in step 508, the video system 30 calculates the transmission map (T) based on the dark channel matrix and the estimated atmospheric light matrix.

[0074] Transmission maps (T) are used as... Figure 7 In the described dehazing operation, in step 702, the video system 30 converts the RGB image I into a YUV image I-YUV. Next, in step 704, the video system 30 applies a dehazing operation to the Y (luminance) channel of the I-YUV image by subtracting the estimated atmospheric light component A(x) from the Y (luminance) channel and then dividing this difference by the determined transmittance map, thereby producing the image IY′UV. Finally, in step 706, the IY′UV image is converted into a dehazed RGB image 1000 (see...). Figure 10 ).

[0075] The embodiments disclosed herein are examples of this disclosure and may be implemented in various forms. For example, although some embodiments herein are described as separate embodiments, each of the embodiments herein may be combined with one or more other embodiments herein. Therefore, the specific structural and functional details disclosed herein should not be construed as limiting, but merely as a basis for the claims and as a representative basis for teaching those skilled in the art to adopt this disclosure differently with virtually any suitable detailed structure. Throughout the description with reference to the drawings, the same reference numerals denote similar or identical elements.

[0076] The phrases “in one embodiment,” “in an embodiment,” “in some embodiments,” or “in other embodiments” may each refer to one or more of the same or different embodiments according to this disclosure. The phrase “A or B” means “(A), (B), or (A and B).” The phrase “at least one of A, B, or C” means “(A); (B); (C); (A and B); (A and C); (B and C); or (A, B, and C).” The term “clinician” may refer to a clinician or any medical professional performing a medical procedure, such as a doctor, nurse, technician, medical assistant, etc.

[0077] The system described herein may also utilize one or more controllers to receive various information and transform the received information to generate output. The controller may include any type of computing device, computing circuitry, or any type of processor or processing circuitry capable of executing a series of instructions stored in memory. The controller may include multiple processors and / or a multi-core central processing unit (CPU), and may include any type of processor such as a microprocessor, digital signal processor, microcontroller, programmable logic device (PLD), field-programmable gate array (FPGA), etc. The controller may also include memory for storing data and / or instructions that, when executed by one or more processors, cause the one or more processors to perform one or more methods and / or algorithms.

[0078] Any method, program, algorithm, or code described herein can be translated into or expressed in a programming language or computer program. As used herein, the terms "programming language" and "computer program" each include any language used to specify computer instructions, and include (but are not limited to) the following languages ​​and their derivatives: assembler, Basic, batch file, BCPL, C, C+, C++, Delphi, Fortran, Java, JavaScript, machine code, operating system command languages, Pascal, Perl, PL1, scripting languages, visual Basic, self-defined program meta-languages, and all first-, second-, third-, fourth-, fifth-, or next-generation computer languages. Databases and other data schemas, and any other meta-languages, are also included. There is no distinction between languages ​​that are interpreted, compiled, or use compilation and interpretation methods. There is no distinction between a compiled version of a program and its source version. Therefore, a reference to a program in which a programming language may exist in more than one state (such as source, compilation, object, or link) is a reference to any and all such states. A reference to a program may encompass the actual instructions and / or the intent of those instructions.

[0079] Any methods, programs, algorithms, or code described herein may be contained on one or more machine-readable media or memories. The term "memory" may include a means of providing (e.g., storing and / or transmitting) information in a machine-readable form, such as a processor, computer, or digital processing device. For example, memory may include read-only memory (ROM), random access memory (RAM), disk storage media, optical storage media, flash memory devices, or any other volatile or non-volatile memory storage devices. Code or instructions contained thereon may be represented by carrier signals, infrared signals, digital signals, and other similar signals.

[0080] It should be understood that the foregoing description is merely illustrative of this disclosure. Various alternatives and modifications can be devised by those skilled in the art without departing from this disclosure. Therefore, this disclosure is intended to cover all such alternatives, modifications, and variations. The embodiments described with reference to the accompanying drawings are merely illustrative of certain examples of this disclosure. Other elements, steps, methods, and techniques that are not substantially different from those described in the foregoing and / or appended claims are also intended to fall within the scope of this disclosure.

Claims

1. A method for reducing smoke in an image, comprising: Access an RGB image of an object obscured by smoke, the RGB image comprising multiple pixels; Determine the dark channel matrix of the RGB image, wherein for each of the plurality of pixels, the dark channel matrix includes the minimum color component intensity of the corresponding pixel region centered on the corresponding pixel; The atmospheric light matrix of the RGB image is estimated based on the dark channel matrix, wherein the atmospheric light matrix includes the atmospheric light component value of each of the plurality of pixels; The transmission map is determined based on the atmospheric light matrix and the dark channel matrix; The RGB image is dehazed based on the transmission map to reduce the haze in the RGB image; and Display the dehazed RGB image on the display device. Wherein, for each pixel x among the plurality of pixels, the estimation of the atmospheric light matrix includes: The atmospheric light component value of pixel x is determined as follows: A(x) = max(min(I) c (y))) * coef, where all y∈ Ω(x), in: Ω(x) represents the pixel region centered at pixel x. y represents the pixel in the pixel region Ω(x). I c (y) is the intensity value of the color component c of pixel y, and coef is a predetermined coefficient value.

2. The method according to claim 1, wherein dehazing the RGB image comprises: Convert the RGB image to a YUV image; Perform a dehazing operation on the YUV image to provide a Y'UV image; and The Y'UV image is converted into the dehazed RGB image.

3. The method of claim 2, wherein for each pixel x of the plurality of pixels, performing the dehazing operation on the YUV image comprises: Define Y' as , in: T(x) is the transmission component of pixel x, and A(x) is the atmospheric light component value of pixel x.

4. The method of claim 3, wherein performing the dehazing operation on the YUV image further comprises replacing the Y channel of the YUV image with the determined Y' to provide a Y'UV image.

5. The method of claim 1, wherein determining the transmission map comprises, for each pixel x of the plurality of pixels, determining the transmission component value as: ， in: ω is a predetermined constant. I_DARK(x) is the dark channel matrix value of pixel x, and A(x) is the atmospheric light component value of pixel x.

6. A method for reducing smoke in an image, comprising: Access an image obscured by smoke, the image comprising multiple pixels, wherein each pixel of the image comprises multiple color components; For each of the plurality of pixels: The dark matrix channel value of the corresponding pixel is determined as the minimum color component intensity value of the corresponding pixel region centered on the corresponding pixel; and The atmospheric light component value of pixel x is estimated based on the minimum color component intensity value of each pixel in the pixel region; The image is dehazed based on the atmospheric light component value of each of the plurality of pixels; and Display the dehazed image on the display device. For each pixel x among the plurality of pixels, the estimation of the atmospheric light component value includes: The atmospheric light component value of pixel x is determined as follows: A(x) = max(min(I) c (y))) * coef, where all y∈ Ω(x), in: Ω(x) represents the pixel region centered at pixel x. y represents the pixel in the pixel region Ω(x). I c (y) is the intensity value of the color component c of pixel y, and coef is a predetermined coefficient value.

7. The method according to claim 6, wherein dehazing the image comprises: For each pixel x among the plurality of pixels, the transmission map is determined as follows: ， in: ω is a predetermined constant. I_DARK(x) is the dark channel matrix value of pixel x, and A(x) is the atmospheric light component value of pixel x. Convert the image to a YUV image; For each pixel x among the plurality of pixels, Y' is determined as ;and Replace the Y channel of the YUV image with the determined Y' to provide a Y'UV image.

8. The method of claim 7, wherein dehazing the image further comprises converting the Y'UV image into a dehazed image.

9. The method of claim 8, wherein the image comprises at least one of a CMYK image, a CIELAB image, or a CIEXYZ image.

10. A system for reducing smoke in an image, comprising: A light source, configured to provide light; An imaging device configured to acquire images; An imaging device control unit configured to control the imaging device, the control unit comprising: processor; and A memory for storing instructions that, when executed by the processor, cause the system to: The imaging device captures an image of an object obscured by smoke, the image comprising multiple pixels, wherein each pixel of the image comprises multiple color components; Access the image; For each of the pixels: The dark channel matrix value of the corresponding pixel is determined as the minimum color component intensity value of the corresponding pixel region centered on the corresponding pixel; and The atmospheric light component value of each pixel is estimated based on the minimum color component intensity value of each pixel in the pixel region; The image is dehazed based on the atmospheric light component value of each of the pixels; and Display the dehazed image on the display device. The instructions also enable the system to: The atmospheric light component value of pixel x is determined as follows: A(x) =max(min(I c (y))) * coef, Where all y∈ Ω(x), in: Ω(x) represents the pixel region centered at pixel x. y represents the pixel in the pixel region Ω(x). I c (y) is the intensity value of the color component c of pixel y, and coef is a predetermined coefficient value.

11. The system of claim 10, wherein the instruction further causes the system to: For each pixel x among the plurality of pixels, the transmission map is determined as follows: ， in: ω is a predetermined constant. I_DARK(x) is the dark channel matrix value of pixel x, and A(x) is the atmospheric light component value of pixel x. Convert the image to a YUV image; Define Y' as ; and Replace the Y channel of the YUV image with the determined Y' to provide a Y'UV image.

12. The system of claim 11, wherein the instruction, when dehazing the image, further causes the system to convert the Y'UV image into a dehazed image.

13. The system of claim 12, wherein the image comprises at least one of an RGB image, a CMYK image, a CIELAB image, or a CIEXYZ image.

Images