Skin burn area calculation method based on multi-band infrared structured light system

Abstract

The present invention provides a method for calculating the area of ​​skin burns based on a multi-band infrared structured light system. The method for calculating the area of ​​skin burns based on a multi-band infrared structured light system comprises: projecting a preset code onto the burn area through a projector; collecting a coded image and a texture image of the preset code presented in the burn area through a camera; determining the depth information of each pixel point in the texture image in three-dimensional space based on the mapping relationship between the coded image and the three-dimensional space point; performing image segmentation processing on the texture image through an image segmentation model to obtain a mask image of the burn area; performing triangulated mesh processing on the point cloud corresponding to the mask image based on the depth information of each pixel point in the texture image in three-dimensional space to obtain a triangular mesh model; performing calculation processing based on each triangular facet in the triangular mesh model to obtain the area of ​​the burn area. The method for calculating the area of ​​skin burns of the present invention improves the reconstruction accuracy and reliability.

Description

Technical Field

[0001] The present invention relates to the field of computer vision technology, and in particular to a method for calculating skin burn area based on a multi-band infrared structured light system. Background Art

[0002] In clinical practice, there are many burn patients. Treatment and prognosis plans vary for patients with different skin burn areas and burn severity. During treatment, a sterile environment must be maintained. Therefore, the burn area can only be estimated through non-contact methods.

[0003] Currently, skin burn area calculation based on 3D reconstruction can be broadly categorized into two types. The first is reconstruction based on a single depth camera. This method uses a single existing depth camera (such as Kinect) to acquire a point cloud from multiple angles at the location of the burned skin. These point clouds are then stitched together to reconstruct the burn wound location. After triangulating the reconstructed model, the area of ​​the triangular facets is used to approximate the surface area of ​​the burn. However, this method has the following challenges: During multi-angle scanning, the reconstructed region cannot undergo non-rigid transformations. For areas with high degrees of freedom, such as the palm or face, maintaining a completely stationary state is difficult, resulting in significant errors. The second method uses multiple 2D images to fit a parametric human body model. Key points of the human body are identified in the 2D images and fitted to the parametric human body model. After applying the texture, the burn area is segmented, and the area is finally calculated using a 3D application. This method also has the following challenges: The sum of the mesh areas accurately approximates the true burn area only when the point cloud is dense. However, the parametric human body model provides a limited number of points, resulting in low accuracy.

[0004] Therefore, the existing skin burn area calculation methods based on three-dimensional reconstruction are mostly applied to situations where the burn area is large and the skin near the burn location is relatively flat, and the reconstruction accuracy and reliability are low. Summary of the Invention

[0005] In view of this, the present invention provides a method for calculating skin burn area based on a multi-band infrared structured light system to solve the above problems.

[0006] According to a first aspect of the present invention, a method for calculating the area of ​​skin burns based on a multi-band infrared structured light system is provided, which is characterized by comprising: projecting a preset code onto the burn area through a projector; acquiring a coded image and a texture image of the preset code presented in the burn area through a camera; determining the depth information of each pixel point in the texture image in three-dimensional space based on a mapping relationship between the coded image and the three-dimensional space point; performing image segmentation processing on the texture image through an image segmentation model to obtain a mask image of the burn area; performing triangulated meshing processing on the point cloud corresponding to the mask image based on the depth information of each pixel point in the texture image in three-dimensional space to obtain a triangular mesh model; and performing calculation processing based on each triangular facet in the triangular mesh model to obtain the area of ​​the burn area.

[0007] In another implementation of the present invention, the method for calculating the skin burn area based on the multi-band infrared structured light system also includes: connecting each projector through an external trigger; obtaining a set of preset codes through a spatial coding scheme of Gray code plus line shift method; projecting the preset codes onto the burn area through the projector, including: the trigger sends a signal to trigger the projector to project a set of preset codes onto the burn area according to a preset angle, wherein the projector includes at least 3.

[0008] In another implementation of the present invention, a camera is used to capture a coded image and a texture image presented in the burn area according to a preset code, including: after the projector projects a code in the burn area, the camera is triggered by a trigger line to capture a coded image, wherein the first all-white image captured by the camera is a texture image.

[0009] In another implementation of the present invention, the method for calculating the skin burn area based on the multi-band infrared structured light system further includes: determining a mapping relationship between the encoded image and the three-dimensional space point based on the calibration parameters of the camera.

[0010] In another implementation of the present invention, based on the depth information of each pixel point in the texture image in the three-dimensional space, the point cloud corresponding to the mask image is triangulated to obtain a triangular mesh model, including: determining the point cloud corresponding to each pixel point in the mask image in the three-dimensional space according to the depth information of each pixel point in the texture image in the three-dimensional space; performing mesh encapsulation processing on the point cloud in the mask by a Poisson surface reconstruction algorithm to obtain a basic triangular mesh model; and performing mesh refinement processing on the triangular mesh model by a triangular mesh subdivision algorithm to obtain a target triangular mesh model.

[0011] In another implementation of the present invention, calculation processing is performed based on each triangular facet in the triangular mesh model to obtain the area of ​​the burn area, including: calculating the area of ​​each triangular facet in the target triangular mesh model; summing the areas of each triangular facet to obtain the area of ​​the burn area.

[0012] According to a second aspect of the present invention, a skin burn area calculation device based on a multi-band infrared structured light system is provided, which is characterized by comprising: an image acquisition module: used for projecting a preset code onto the burn area through a projector; collecting a coded image and a texture image of the preset code presented in the burn area through a camera; an image processing module: used for determining the depth information of each pixel point in the texture image in the three-dimensional space based on the mapping relationship between the coded image and the three-dimensional space point; performing image segmentation processing on the texture image through an image segmentation model to obtain a mask image of the burn area; a model generation module: used for performing triangulation processing on the point cloud corresponding to the mask image based on the depth information of each pixel point in the texture image in the three-dimensional space to obtain a triangulated mesh model; and an area calculation module: used for performing calculation processing based on each triangular facet in the triangulated mesh model to obtain the area of ​​the burn area.

[0013] According to a third aspect of the present invention, an electronic device is provided, comprising: a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein when the processor executes the computer program, the steps for calculating the skin burn area based on a multi-band infrared structured light system as described above are implemented.

[0014] According to a fourth aspect of the present invention, a computer storage medium is provided, on which a computer program is stored. When the computer program is executed by a processor, the steps in the method for calculating the skin burn area based on a multi-band infrared structured light system as described above are implemented.

[0015] In the skin burn area calculation method based on the multi-band infrared structured light system of the present invention, the burn area is reconstructed based on time-coded infrared structured light, and the object is reconstructed from three angles, so that high-precision, high-frame-rate, complete point cloud data and texture data can be obtained; because the present invention can obtain real-time point cloud data, it is superior to the existing method in terms of data collection time, which also reduces the errors caused by multiple imaging; when segmenting the burn area, the area segmented by the network can be adjusted to increase the accuracy of the segmentation, thereby accurately calculating the burn area, and this segmentation method does not require pre-training. BRIEF DESCRIPTION OF THE DRAWINGS

[0016] In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the following briefly introduces the drawings required for the embodiments or the description of the prior art. By reading the detailed description of the embodiments below, the advantages and benefits of the solutions will become clear to those skilled in the art. The drawings are only for the purpose of illustrating preferred embodiments and are not to be considered as limiting the present invention. In the drawings:

[0017] Figure 1 This is a flowchart of the steps of a method for calculating skin burn area based on a multi-band infrared structured light system according to an embodiment of the present invention.

[0018] Figure 2 This is a flowchart of the steps of a method for calculating skin burn area based on a multi-band infrared structured light system according to another embodiment of the present invention.

[0019] Figure 3 This is a coded image captured by a camera according to another embodiment of the present invention.

[0020] Figure 4 FIG. 4 is a schematic diagram of a structured light collection device according to another embodiment of the present invention.

[0021] Figure 5 This is a schematic diagram of a photograph of an arm taken by an infrared camera according to another embodiment of the present invention.

[0022] Figure 6 A schematic diagram of an interface using SAM interactive segmentation according to another embodiment of the present invention.

[0023] Figure 7 Schematic diagram of a mask generated by SAM segmentation according to another embodiment of the present invention.

[0024] Figure 8 This is a schematic diagram of the reconstruction results of the burn area and its surrounding skin after mesh refinement according to another embodiment of the present invention.

[0025] Figure 9 This is a structural block diagram of a skin burn area calculation device based on a multi-band infrared structured light system according to another embodiment of the present invention.

[0026] Figure 10 FIG. 4 is a schematic structural diagram of an electronic device according to another embodiment of the present invention. DETAILED DESCRIPTION

[0027] In order to enable those skilled in the art to better understand the technical solutions in the embodiments of the present invention, the technical solutions in the embodiments of the present invention will be clearly and detailedly described below in conjunction with the accompanying drawings in the embodiments of the present invention. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of them. All other embodiments obtained by those skilled in the art based on the embodiments in the embodiments of the present invention should fall within the scope of protection of the embodiments of the present invention.

[0028] Figure 1 A flowchart of a method for calculating skin burn area based on a multi-band infrared structured light system is provided in an embodiment of the present invention. Figure 1 As shown, this embodiment mainly includes the following steps:

[0029] S101 , projecting a preset code onto the burn area via a projector.

[0030] S102 : Capturing a code image and a texture image of the burn area with a preset code through a camera.

[0031] For example, Figure 3 As shown in the figure, the camera captures the coded image and texture image presented in the burn area with the preset code. 18 images are taken for reconstruction. The texture image corresponds to the completely white image in the coded image. A structured light system is built by using a camera and a projector, as shown in the figure. Figure 2 As shown, three point infrared structured light reconstruction systems are built to collect data on the burn area in real time to obtain high-precision point clouds and texture images. Among them, three point infrared structured light reconstruction systems are taken as an example in this application, and the number of point infrared structured light reconstruction systems can be adjusted according to user needs.

[0032] S103 : Determine depth information of each pixel point in the texture image in the three-dimensional space based on a mapping relationship between the encoded image and the three-dimensional space point.

[0033] Exemplarily, based on the mapping relationship between the encoded image and the three-dimensional space point, the depth information of each pixel point of the texture image in the three-dimensional space is determined, that is, the 18 captured 2D images are converted into 3D coordinates.

[0034] S104 , performing image segmentation processing on the texture image using an image segmentation model to obtain a mask image of the burn area.

[0035] For example, the mapping relationship between the texture image and the 3D space point is established according to the calibration parameters of the camera. The depth information of each pixel in the texture image in space can be obtained through the above imaging method. Therefore, segmenting the texture image is equivalent to segmenting the point cloud. The wound simulation uses a black body painting pen to simulate the wound. The segmentation effect of SAM is as follows: Figure 5 、 Figure 6 and Figure 7 As shown. The texture image can be segmented by SAM (Segment Anything Model). After using SAM to obtain the mask of the burn area in the texture image, the depth information Z′ of each point in the texture image is obtained. c(i,j) It can be expressed as:

[0036]

[0037] It should be understood that SAM is a state-of-the-art image segmentation model that can generalize to unfamiliar objects and images with zero-shot generalization, and can recognize any image without additional training. SAM was trained on a dataset of millions of images and over 1 billion masks. This dataset was carefully curated to cover a wide range of domains, objects, and scenes, ensuring that the model can generalize well to different tasks and return valid segmentation masks for any prompt. In terms of application, it currently supports interactive annotation, and the mask of the segmented part can be obtained by using a picture frame, mouse click, or text as a prompt.

[0038] S105 , performing triangular meshing processing on the point cloud corresponding to the mask image based on the depth information of each pixel point in the texture image in the three-dimensional space to obtain a triangular mesh model.

[0039] For example, based on the depth information of each pixel in the texture image in three-dimensional space, the mask image is transformed using reprojection to obtain a corresponding dense point cloud. The point cloud is then meshed and refined. Mesh encapsulation, also known as point cloud meshing, is the process of using a series of meshes to approximate the point cloud. In graphics, triangular meshes and quadrilateral meshes are generally used. Compared to quadrilateral meshes, triangular meshes have the advantages of strong stability, simple structure, and simple area calculation. Therefore, we triangulate the point cloud. The acquired 2D image is segmented using a segmentation model, and the corresponding dense point cloud is obtained using reprojection transformation. After mesh encapsulation and refinement, the precise burn area is finally obtained.

[0040] S106 , performing calculations based on each triangular facet in the triangular mesh model to obtain the area of ​​the burn region.

[0041] In the skin burn area calculation method based on the multi-band infrared structured light system of the present invention, the burn area is reconstructed based on time-coded infrared structured light, and the object is reconstructed from three angles, so that high-precision, high-frame-rate, complete point cloud data and texture data can be obtained; because the present invention can obtain real-time point cloud data, it is superior to the existing method in terms of data collection time, which also reduces the errors caused by multiple imaging; when segmenting the burn area, the area segmented by the network can be adjusted to increase the accuracy of the segmentation, thereby accurately calculating the burn area, and this segmentation method does not require pre-training.

[0042] In another implementation of the present invention, it also includes: connecting each projector through an external trigger; obtaining a set of preset codes through a spatial coding scheme of Gray code plus line shift method; projecting the preset codes onto the burn area through the projector, including: the trigger sends a signal to trigger the projector to project a set of preset codes onto the burn area according to a preset angle, wherein the projector includes at least 3.

[0043] In another implementation of the present invention, a camera is used to capture a coded image and a texture image presented in the burn area according to a preset code, including: after the projector projects a code in the burn area, the camera is triggered by a trigger line to capture a coded image, wherein the first all-white image captured by the camera is a texture image.

[0044] For example, the structured light collection device is as follows: Figure 4 As shown, the structured light system uses an industrial camera equipped with a narrowband filter adapted to the projection light source. The wavelengths of the three structured light systems are 730nm, 850nm, and 950nm, respectively. The projection light source is a Texas Instruments 4500 DLP projector, and the projected pattern utilizes a spatial encoding scheme using Gray code plus line shifting. By synchronously controlling the camera exposure time, exposure fusion is achieved across the entire scanning field, resulting in a complete structured light projection image. The projection frame rate can reach over 2800Hz, ensuring real-time 3D scanning. After determining the positional relationship between the camera and projector using Zhang's calibration method, depth information is derived using epipolar constraints and triangulation.

[0045] Furthermore, an external trigger is used to connect the projectors of the three structured light systems, and a trigger line is used to connect the projectors and cameras. After the trigger sends a signal, it triggers the three projectors to project a set of the above-mentioned codes at the same time; after each projector projects a code, it triggers the camera to capture a coded image, ensuring the synchronous control of the three systems.

[0046] It should be understood that among current 3D imaging methods, structured light vision technology, with its simple hardware structure, large range, wide field of view, simple extraction of light streak image information, and strong real-time performance, has been widely used in many fields such as industry, medical aesthetics, virtual reality, and cultural heritage protection. Compared to traditional binocular vision, structured light-based 3D reconstruction technology is an active 3D reconstruction technology. It uses a projector to project one or a set of pre-defined light streaks at a specific angle onto the surface of the object to be reconstructed. A camera at another angle captures the fringe pattern distorted by the object's surface. Combining the calibration parameters of the projector and camera, the surface topography data of the object to be measured can be calculated.

[0047] The hardware device in this application is mainly used for real-time three-dimensional imaging of the burn area. Based on the principle of coded structured light three-dimensional scanning, in order to ensure the integrity of the imaging, three structured light devices are used to reconstruct the burn area at different angles; in order to avoid mutual interference of structured light projected between devices in the burn area, the structured light system uses three infrared projection light sources with different bands; the synchronization between the projectors and cameras in the three structured light systems is completed through the synchronization control module, and a high-speed scanning process is realized; based on the built-in GPU module of the imaging device, real-time three-dimensional point cloud reconstruction of the burn area is realized.

[0048] In another implementation of the present invention, the method further includes: determining a mapping relationship between the encoded image and the three-dimensional space point based on the calibration parameters of the camera.

[0049] Exemplarily, the calibration parameters of the camera are divided into internal parameters and external parameters. The internal parameters include the focal length, distortion factor, etc. of the camera, and the external parameters include the positional relationship between the camera and the projector.

[0050] In another implementation of the present invention, based on the depth information of each pixel point in the texture image in the three-dimensional space, the point cloud corresponding to the mask image is triangulated to obtain a triangular mesh model, including: based on the depth information of each pixel point in the texture image in the three-dimensional space, determining the point cloud corresponding to each pixel point in the mask image in the three-dimensional space; performing mesh encapsulation processing on the point cloud in the mask by a Poisson surface reconstruction algorithm to obtain a basic triangular mesh model; and performing mesh refinement processing on the triangular mesh model by a triangular mesh subdivision algorithm to obtain a target triangular mesh model.

[0051] For example, based on the depth information of each pixel in the texture image in three-dimensional space, the mask image is transformed by reprojection to obtain the corresponding dense point cloud, and the point cloud is meshed using the Poisson surface reconstruction algorithm. The specific algorithm process is as follows:

[0052] 1. Construct an octree. Create an octree based on the spatial points of the point cloud M. The node function F corresponding to the vertex o in the octree o It can be expressed as:

[0053]

[0054] Among them, c o and w o Represents the center and width of the octree node respectively.

[0055] 2. Calculate the vector field. For each data point m in the point cloud M, perform trilinear interpolation of the eight nodes in the neighborhood to construct the vector field:

[0056]

[0057] p m Indicates the current node, Represents the normal vector of the current node, Nr D (m) represents the current node p m The eight neighboring nodes, λ o,m represents the interpolation weight.

[0058] 3. Solve Poisson's equation. The indicator function used here can be expressed as:

[0059]

[0060] The gradient of this function should be equal to the vector field Right now But in fact the vector field It is not integrable. So we use the divergence operator to transform the original equation into the Poisson equation and solve it:

[0061]

[0062] The equation is solved using multiple grids, and then the isosurface is extracted using the moving solid surface method according to the Poisson equation. Finally, the calculated triangular facets are stitched together to complete the grid encapsulation.

[0063] It should be understood that mesh refinement refers to dividing the mesh on the original model into more meshes, thereby making the model more refined. Typical triangular mesh subdivision algorithms can be simply divided into two categories: interpolation method and approximation method. Since there are no sharp features on the human skin, the present invention uses the Loop algorithm in the approximation method, which is simple to implement and the limit points and tangent planes can be accurately calculated. This is a method that can only be used on triangular meshes. The basic idea is to divide a triangle into four triangles (a new triangle is generated at the midpoint of each edge), distinguish new vertices from old vertices, and assign weights to nearby vertices to change their positions, ultimately making the model surface smoother. After the above operations, the result of the refined mesh in the burn area is as follows. Figure 8 shown.

[0064] In another implementation of the present invention, calculation processing is performed based on each triangular facet in the triangular mesh model to obtain the area of ​​the burn area, including: calculating the area of ​​each triangular facet in the target triangular mesh model; summing the areas of each triangular facet to obtain the area of ​​the burn area.

[0065] For example, after obtaining a high-precision point cloud and generating a refined triangular mesh, the area of ​​the triangular mesh of the burn area is used to represent the true area of ​​the burn area. i , b i , c i Represent the three side lengths of a triangular mesh respectively, and the area S can be expressed as:

[0066]

[0067]

[0068]

[0069] Using the SAM segmentation model to segment the burn area in the texture image, medical staff can use the picture frame or mouse clicks as prompts to adjust the burn area to obtain the precise burn area, and finally reproject it into 3D space to accurately calculate the burn area.

[0070] Figure 9 A schematic diagram of a skin burn area calculation device 900 based on a multi-band infrared structured light system provided in an embodiment of the present invention is shown in FIG. Figure 9 As shown, this embodiment mainly includes:

[0071] Image acquisition module 901: used to project the preset code onto the burn area through a projector; and to capture the coded image and texture image of the preset code in the burn area through a camera;

[0072] Image processing module 902: used to determine the depth information of each pixel in the texture image in the three-dimensional space based on the mapping relationship between the encoded image and the three-dimensional space points; perform image segmentation processing on the texture image using the image segmentation model to obtain a mask image of the burn area;

[0073] Model generation module 903: for performing triangulation processing on the point cloud corresponding to the mask image based on the depth information of each pixel point in the texture image in three-dimensional space to obtain a triangulated mesh model;

[0074] The area calculation module 904 is used to perform calculations based on each triangular facet in the triangular mesh model to obtain the area of ​​the burn area.

[0075] In the skin burn area calculation device 900 based on the multi-band infrared structured light system of the present invention, the burn area is reconstructed based on time-coded infrared structured light, and the object is reconstructed from three angles, so that high-precision, high-frame-rate, complete point cloud data and texture data can be obtained; because the present invention can obtain real-time point cloud data, it is superior to the existing method in terms of data collection time, which also reduces the errors caused by multiple imaging; when segmenting the burn area, the area segmented by the network can be adjusted to increase the accuracy of the segmentation, thereby accurately calculating the burn area, and this segmentation method does not require pre-training.

[0076] In another implementation of the present invention, the image acquisition module 901 is also used to connect each projector through an external trigger; obtain a set of preset codes through a spatial coding scheme of Gray code plus line shift method; the trigger sends a signal to trigger the projector to project a set of preset codes onto the burn area at a preset angle, wherein the projector includes at least 3.

[0077] In another implementation of the present invention, the image acquisition module 901 is also used to trigger the camera to capture a coded image through a trigger line after the projector projects a coded image in the burn area, wherein the first all-white image captured by the camera is a texture image.

[0078] In another implementation of the present invention, the image processing module 902 is further configured to determine a mapping relationship between the encoded image and the three-dimensional space point based on calibration parameters of the camera.

[0079] In another implementation of the present invention, the model generation module 903 is also used to determine the point cloud corresponding to each pixel point in the mask image in the three-dimensional space based on the depth information of each pixel point in the texture image in the three-dimensional space; the point cloud in the mask is meshed by the Poisson surface reconstruction algorithm to obtain a basic triangular mesh model; the triangular mesh model is meshed by the triangular mesh subdivision algorithm to obtain a target triangular mesh model.

[0080] In another implementation of the present invention, the area calculation module 904 is further configured to calculate the area of ​​each triangular facet in the target triangular mesh model; and to sum the areas of each triangular facet to obtain the area of ​​the burn region.

[0081] like Figure 10 As shown, the electronic device 1000 may include: a processor (processor) 1001 , a memory (memory) 1003 , a communication bus 1004 , and a communication interface (Communications Interface) 1005 .

[0082] in:

[0083] The processor 1001 , the memory 1003 and the communication interface 1005 communicate with each other via the communication bus 1004 .

[0084] The communication interface 1005 is used to communicate with other electronic devices or servers.

[0085] The processor 1001 is configured to execute the program 1002 , and specifically may execute the steps of any one of the methods for calculating the skin burn area based on the multi-band infrared structured light system in the above embodiments.

[0086] Specifically, the program 1002 may include program codes, which include computer operating instructions.

[0087] The processor 1001 may be a central processing unit (CPU), an application-specific integrated circuit (ASIC), or one or more integrated circuits configured to implement the embodiments of the present application. The one or more processors included in the smart device may be processors of the same type, such as one or more CPUs, or may be processors of different types, such as one or more CPUs and one or more ASICs.

[0088] The memory 1003 is used to store the program 1002. The memory 1003 may include a high-speed RAM memory, and may also include a non-volatile memory (non-volatile memory), such as at least one disk memory.

[0089] Program 1002 can specifically be used to cause processor 1001 to execute the steps of any of the methods for calculating skin burn area based on a multi-band infrared structured light system described in the embodiments. The specific implementation of each step in program 1002 can be found in the corresponding descriptions of the steps and units executed in any of the aforementioned methods for calculating skin burn area based on a multi-band infrared structured light system, and will not be repeated here. Those skilled in the art will clearly understand that for ease and brevity of description, the specific operating processes of the devices and modules described above can refer to the corresponding process descriptions in the aforementioned method embodiments.

[0090] The exemplary embodiments of the present application further provide a non-transitory computer-readable storage medium storing computer instructions, wherein the computer instructions are used to enable a computer to execute the methods of the various embodiments of the present application.

[0091] The method according to the embodiment of the present invention described above can be implemented in hardware, firmware, or as software or computer code that can be stored in a recording medium (such as a CD ROM, RAM, floppy disk, hard disk or magneto-optical disk), or as computer code that is originally stored in a remote recording medium or a non-temporary machine-readable medium downloaded via a network and will be stored in a local recording medium, so that the method described herein can be stored in such software processing on a recording medium using a general-purpose computer, a dedicated processor or programmable or dedicated hardware (such as an ASIC or FPGA). It can be understood that a computer, a processor, a microprocessor controller or programmable hardware includes a storage component (e.g., RAM, ROM, flash memory, etc.) that can store or receive software or computer code, and when the software or computer code is accessed and executed by a computer, a processor or hardware, the method described herein is implemented. In addition, when a general-purpose computer accesses the code for implementing the method shown here, the execution of the code converts the general-purpose computer into a dedicated computer for executing the method shown here.

[0092] Thus far, specific embodiments of the present invention have been described. Other embodiments are within the scope of the appended claims. In some cases, the actions recited in the claims can be performed in a different order and still achieve the desired results. Furthermore, the processes depicted in the accompanying drawings do not necessarily require the specific order shown or sequential order to achieve the desired results. In certain embodiments, multitasking and parallel processing may be advantageous.

[0093] It should be noted that all directional indications in the embodiments of the present invention (such as up, down, left, right, back, etc.) are only used to explain the relative position relationship, movement status, etc. between the various components under a certain specific posture (as shown in the accompanying drawings). If the specific posture changes, the directional indication will also change accordingly.

[0094] In the description of the present invention, the terms "first" and "second" are used solely to facilitate description of different components or names and should not be construed as indicating or implying a sequential relationship, relative importance, or implicitly specifying the quantity of the technical features being described. Therefore, features specified as "first" or "second" may explicitly or implicitly include at least one of such features.

[0095] Unless otherwise defined, all technical and scientific terms used herein have the same meaning as those commonly understood by those skilled in the art of the present invention. The terms used in this specification of the present invention are only for the purpose of describing specific embodiments and are not intended to limit the present invention.

[0096] It should be noted that although the specific embodiments of the present invention are described in detail in conjunction with the accompanying drawings, this should not be construed as limiting the scope of protection of the present invention. Within the scope described by the claims, various modifications and variations that can be made by those skilled in the art without creative effort still fall within the scope of protection of the present invention.

[0097] The examples of the embodiments of the present invention are intended to briefly illustrate the technical features of the embodiments of the present invention so that those skilled in the art can intuitively understand the technical features of the embodiments of the present invention, and are not intended to improperly limit the embodiments of the present invention.

[0098] Finally, it should be noted that the above embodiments are only used to illustrate the technical solutions of the present invention, rather than to limit it. Although the present invention has been described in detail with reference to the aforementioned embodiments, those skilled in the art should understand that they can still modify the technical solutions described in the aforementioned embodiments, or make equivalent replacements for some of the technical features therein. However, these modifications or replacements do not deviate the essence of the corresponding technical solutions from the spirit and scope of the technical solutions of the various embodiments of the present invention.

Claims

1. A method for calculating skin burn area based on a multi-band infrared structured light system, characterized in that: include: Connect individual projectors via external triggers; A set of preset codes is obtained by a spatial coding scheme of Gray code plus line shift method; Project the preset codes onto the burn area via a projector, including: The trigger sends a signal to trigger the projector to project the set of preset codes onto the burn area at a preset angle, wherein the projector comprises at least three; The method includes: collecting a code image and a texture image of the burn area by using a camera, comprising: After each code is projected on the burn area, the projector triggers the camera to capture a code image through a trigger line, wherein the first all-white image captured by the camera is a texture image; Determining depth information of each pixel point in the texture image in the three-dimensional space based on a mapping relationship between the encoded image and the three-dimensional space point; Performing image segmentation processing on the texture image using an image segmentation model to obtain a mask image of the burn area; Based on the depth information of each pixel point in the texture image in three-dimensional space, performing triangular mesh processing on the point cloud corresponding to the mask image to obtain a triangular mesh model; The area of ​​the burn region is obtained by performing calculations based on each triangular facet in the triangular mesh model.

2. The method according to claim 1, characterized in that Also includes: A mapping relationship between the encoded image and a three-dimensional space point is determined based on calibration parameters of the camera.

3. The method according to claim 1, characterized in that The method of performing triangular meshing on the point cloud corresponding to the mask image based on the depth information of each pixel point in the texture image in the three-dimensional space to obtain a triangular mesh model includes: Determining a point cloud corresponding to each pixel in the mask image in the three-dimensional space based on depth information of each pixel in the texture image in the three-dimensional space; Performing mesh encapsulation processing on the point cloud using a Poisson surface reconstruction algorithm to obtain a basic triangular mesh model; The triangular mesh model is subjected to mesh refinement processing by a triangular mesh subdivision algorithm to obtain a target triangular mesh model.

4. The method according to claim 3, characterized in that The calculating and processing based on each triangular facet in the triangular mesh model to obtain the area of ​​the burn region includes: Calculating the area of ​​each triangular facet in the target triangular mesh model; The areas of the triangular facets are summed to obtain the area of ​​the burn region.

5. A skin burn area calculation device based on a multi-band infrared structured light system, characterized in that: include: Image acquisition module: used to connect various projectors through external triggers; A set of preset codes is obtained by a spatial coding scheme of Gray code plus line shift method; Projecting a preset code onto the burn area via a projector, comprising: the trigger sending a signal to trigger the projector to project the set of preset codes onto the burn area at a preset angle, wherein the projector comprises at least three; capturing a code image and a texture image of the preset codes presented in the burn area via a camera, comprising: after each code is projected onto the burn area by the projector, triggering the camera via a trigger line to capture a code image, wherein the first all-white image captured by the camera is the texture image; An image processing module is configured to determine the depth information of each pixel point in the texture image in the three-dimensional space based on the mapping relationship between the encoded image and the three-dimensional space point; perform image segmentation processing on the texture image using an image segmentation model to obtain a mask image of the burn area; Model generation module: used for performing triangulation processing on the point cloud corresponding to the mask image based on the depth information of each pixel point in the texture image in three-dimensional space to obtain a triangulated mesh model; Area calculation module: used for performing calculation based on each triangular facet in the triangular mesh model to obtain the area of ​​the burn area.

6. An electronic device, characterized in that: include: A memory, a processor, and a computer program stored in the memory and executable on the processor, wherein when the processor executes the computer program, the steps of the method for calculating the skin burn area based on a multi-band infrared structured light system as described in any one of claims 1 to 4 are implemented.

7. A computer storage medium, characterized in that The computer storage medium stores a computer program, which, when executed by a processor, implements the steps of the skin burn area calculation method based on a multi-band infrared structured light system according to any one of claims 1 to 4.

Images