A method and system for mapping three-dimensional point cloud using infrared thermal information

Abstract

The present invention discloses a method for mapping infrared thermal information to a three-dimensional point cloud, comprising: placing a virtual camera in a three-dimensional point cloud scene, setting it to the same posture parameter A as a camera for shooting infrared thermal images, and generating a point cloud image; preprocessing the point cloud image first, and then matching the infrared thermal image with the preprocessed point cloud image to correct the posture of the infrared camera; resetting the virtual camera in the three-dimensional point cloud scene, and rasterizing the point cloud within the current visual domain of the virtual camera; filtering the point information of the object, screening and retaining the points on the plane close to the camera; assigning the infrared thermal value on the infrared thermal map to the point on the point cloud of the corresponding pixel, and generating an infrared thermal value file of the point cloud. A system for mapping infrared thermal information to a three-dimensional point cloud is also disclosed. The present invention can solve the technical problem of accurately mapping a two-dimensional infrared remote sensing image to a three-dimensional point cloud model, and realize three-dimensional visualization of infrared remote sensing images.

Description

Technical Field

[0001] The invention relates to the field of infrared remote sensing technology, and in particular to a method and a system for mapping three-dimensional point clouds with infrared thermal information. Background Art

[0002] At present, infrared remote sensing technology can be used for plant distribution planning, equipment detection, equipment power consumption analysis, and fault troubleshooting. Based on infrared remote sensing data, physical simulation of equipment in the plant can also be performed to optimize and verify distribution planning and prevent faults in advance. However, infrared remote sensing images taken by infrared cameras can only display local infrared information of objects in two dimensions. Since the image itself does not carry depth information, it cannot be restored to a three-dimensional scene. At the same time, there are inevitable mechanical errors and measurement errors (including camera posture, etc.) when infrared cameras take infrared remote sensing images. How to map infrared remote sensing images to three-dimensional point clouds one by one is also a technical problem that needs to be solved.

[0003] Therefore, there is an urgent need to provide a new method of infrared thermal information mapping three-dimensional point cloud to solve the above problems. Summary of the invention

[0004] The technical problem to be solved by the present invention is to provide a method and system for mapping infrared thermal information to a three-dimensional point cloud, which can solve the technical problem of accurately mapping a two-dimensional infrared remote sensing image to a three-dimensional point cloud model.

[0005] In order to solve the above technical problems, the first technical solution adopted by the present invention is to provide a method for mapping three-dimensional point clouds using infrared thermal information, comprising the following steps:

[0006] Step 1: Place a virtual camera in the 3D point cloud scene, set the camera internal parameters and posture parameters A to be the same as the camera that shoots the infrared thermal image, and generate a point cloud image;

[0007] Step 2: Preprocess the point cloud image first, and then perform feature matching between the infrared thermal map and the preprocessed point cloud image;

[0008] Step 3: Obtain the three-dimensional coordinates of each feature point of the infrared image in the point cloud through the feature correspondence between the infrared and point cloud images, and recalculate the pose parameter B of the infrared camera through the two-dimensional and three-dimensional coordinates of the infrared feature points;

[0009] Step 4: Reset the virtual camera in the 3D point cloud scene with the pose parameter B, rasterize the point cloud in the current visual field of the virtual camera, and record the points of the point cloud that can be observed by each pixel when the current camera is rasterized;

[0010] Step 5: Filter the point information of the object, select and retain the points on the plane close to the camera;

[0011] Step 6: Assign the infrared thermal values ​​on the infrared thermal map to the points on the point cloud of the corresponding pixels, and generate an infrared thermal value file of the point cloud.

[0012] In a preferred embodiment of the present invention, in step 1, the posture parameter A includes the position of the camera and the rotation angle of the camera, and the internal parameters include the viewport size of the camera, the near plane and far plane of the camera, and the distortion parameters of the camera.

[0013] In a preferred embodiment of the present invention, in step 2, the step of preprocessing the point cloud image includes:

[0014] Step 2.1: Apply histogram equalization to the point cloud image;

[0015] Step 2.2: Use the Wiener filter to reduce noise on the point cloud image;

[0016] Step 2.3: Use a Gaussian filter to smooth the point cloud image to remove noise and improve image quality.

[0017] In a preferred embodiment of the present invention, in step 3, the PnP algorithm is used to recalculate the posture parameter B of the infrared camera through the two-dimensional and three-dimensional coordinates of the infrared feature points.

[0018] In a preferred embodiment of the present invention, in step 4, the specific steps of rasterizing the point cloud within the current visual range of the virtual camera include:

[0019] The point cloud data within the viewing cone is loaded according to the position of the virtual camera, and the point cloud is projected onto a two-dimensional rasterized plane through perspective projection. At the same time, the position information of the pixel points on each grid is recorded, that is, the point cloud is generated into a point information map of the same size as the infrared image, and the infrared information is mapped to the three-dimensional point cloud using the point information map as the intermediate layer.

[0020] In a preferred embodiment of the present invention, in step 5, filtering the point information of the object adopts a filtering method based on screen space mapping, and the specific steps include:

[0021] Each projected point in screen space is considered as a surface. When a point is projected onto the grid and passes the depth test, its position information is recorded, and points on distant planes are culled by updating the neighborhood depth information.

[0022] In a preferred embodiment of the present invention, in step 6, the infrared thermal value file of the point cloud is generated including the temperature value corresponding to each point of the point cloud file, and special value marks are used for points without infrared value mapping.

[0023] In order to solve the above technical problems, the second technical solution adopted by the present invention is to provide a system for mapping three-dimensional point clouds with infrared thermal information, comprising:

[0024] The point cloud image generation module is used to place a virtual camera in the three-dimensional point cloud scene, set the camera internal parameters and posture parameters A to be the same as those of the camera shooting the infrared thermal image, and generate a point cloud image;

[0025] The point cloud image processing module is used to pre-process the point cloud image first, and then perform feature matching between the infrared thermal map and the pre-processed point cloud image;

[0026] The virtual camera posture adjustment module is used to obtain the three-dimensional coordinates of each feature point of the infrared image in the point cloud through the feature correspondence between the infrared and point cloud images, and recalculate the posture parameter B of the infrared camera through the two-dimensional and three-dimensional coordinates of the infrared feature points;

[0027] The pixel and point cloud conversion module resets the virtual camera in the 3D point cloud scene with the pose parameter B, and rasterizes the point cloud in the current visual field of the virtual camera, recording the points of the point cloud that can be observed by each pixel when the current camera is rasterized;

[0028] A point information processing module, used to filter the point information of the object obtained by the pixel and point cloud conversion module, and only retain the points on the plane closest to the camera;

[0029] The infrared information assignment module is used to assign the infrared thermal values ​​on the infrared thermal map to the points on the point cloud of the corresponding pixels and generate the infrared thermal value file of the point cloud.

[0030] To solve the above technical problems, the third technical solution adopted by the present invention is: to provide a device for mapping three-dimensional point clouds with infrared thermal information, the device comprising: a memory, a processor, and a program for mapping three-dimensional point clouds with infrared thermal information stored in the memory and runnable on the processor, the program for mapping three-dimensional point clouds with infrared thermal information being configured to implement the steps of the method for mapping three-dimensional point clouds with infrared thermal information as described in any of the above items.

[0031] In order to solve the above technical problems, the fourth technical solution adopted by the present invention is: to provide a storage medium, on which is stored a program for mapping infrared thermal information to three-dimensional point clouds. When the program for mapping infrared thermal information to three-dimensional point clouds is executed by a processor, the steps of the method for mapping infrared thermal information to three-dimensional point clouds as described in any of the above items are implemented.

[0032] The beneficial effects of the present invention are as follows: the present invention can combine infrared remote sensing images with point cloud data to realize three-dimensional visualization of infrared remote sensing images, and can solve the technical problem of accurately mapping two-dimensional infrared remote sensing images to three-dimensional point cloud models. In practical applications in different fields, this technology can more intuitively and comprehensively understand the information in infrared images, so as to better analyze and make decisions, including facilitating the maintenance of power equipment, analyzing the distribution of power energy, etc. BRIEF DESCRIPTION OF THE DRAWINGS

[0033] Figure 1 It is a flow chart of the method for mapping three-dimensional point cloud with infrared thermal information of the present invention;

[0034] Figure 2 is a stereoscopic schematic diagram of the point cloud rasterization projection;

[0035] Figure 3 It is a schematic diagram of the mapping of infrared thermal image information to point cloud;

[0036] Figure 4 It is the effect diagram of the projection point with and without filtering in the projection test of the transformer;

[0037] Figure 5 It is a system structure block diagram of the infrared thermal information mapping three-dimensional point cloud. DETAILED DESCRIPTION

[0038] The preferred embodiments of the present invention are described in detail below in conjunction with the accompanying drawings so that the advantages and features of the present invention can be more easily understood by those skilled in the art, thereby making a clearer and more definite definition of the protection scope of the present invention.

[0039] See also Figure 1 , the embodiment of the present invention includes:

[0040] A method for mapping infrared thermal information to a three-dimensional point cloud. An infrared image is a two-dimensional image generated by an infrared sensor capturing the heat radiation of an object, which can instantly provide feedback on the temperature information of the object's surface. A point cloud is a three-dimensional model composed of a set of discrete three-dimensional points, which can be generated by a laser scanner or imaging device. Fusion of infrared images and point clouds to generate a point cloud model with infrared information can combine the advantages of both and assist in tasks such as analyzing energy consumption, monitoring equipment, troubleshooting, and diagnosing medical records. This technology has important application value in the fields of construction, industrial production, and medicine. The method includes the following steps:

[0041] Step 1: In the 3D point cloud scene, place a virtual camera according to the real scene, set the camera internal parameters and posture parameters A to be the same as the camera taking the infrared thermal image, and generate a point cloud image;

[0042] It should be noted here that the infrared thermal map needs to be taken with an infrared camera first, so the camera's position, angle and other parameter information are known. The internal and external parameters of the virtual camera must be consistent with the data taken by the infrared camera to obtain accurate mapping results.

[0043] The camera parameters include the camera's external parameters and internal parameters. The external parameters, namely the pose parameters A, include the camera's position (x, y, z) and the camera's rotation angle (x, y, z). The internal parameters include the camera's viewport size (the length and width of the image), the camera's near plane and far plane, and the camera's distortion parameters.

[0044] Step 2: Preprocess the point cloud image first, and then perform feature matching between the infrared thermal map and the preprocessed point cloud image;

[0045] Due to the differences between visible light images and point cloud images, in order to ensure the accurate registration of infrared images and point cloud images, the point cloud images need to be preprocessed before registration to improve the accuracy of matching. The specific steps include:

[0046] Step 2.1: Apply histogram equalization to the point cloud image to effectively enhance its contrast;

[0047] Step 2.2: Use Wiener filter to reduce noise on the point cloud image;

[0048] Step 2.3: Use a Gaussian filter to smooth the point cloud image to eliminate noise and improve image quality.

[0049] In addition, since there are inevitable mechanical errors and measurement errors when infrared cameras shoot infrared remote sensing images, infrared images and point cloud images are used for feature matching. Specifically, a point feature-based matching algorithm is used to match the infrared thermal image with the preprocessed point cloud image, including the following steps:

[0050] Step 2.4: Detect contours and extract corner features;

[0051] Step 2.5: Calculate the main direction of the corner point;

[0052] Step 2.6: Extract the improved SIFT descriptor of corner points;

[0053] Step 2.7: Bilateral filtering descriptor;

[0054] Step 2.8: Eliminate obvious wrong matching points;

[0055] Step 2.9: Use the RANSAC random optimization algorithm to calculate the matching results.

[0056] Step 3: Obtain the three-dimensional coordinates of each feature point of the infrared image in the point cloud through the feature correspondence between the infrared and point cloud images, and use the PnP algorithm to recalculate the pose parameter B of the infrared camera through the two-dimensional and three-dimensional coordinates of the infrared feature points;

[0057] The PnP algorithm is a method for estimating the camera pose by giving n three-dimensional space points. In practical applications, commonly used algorithms include DLT (Direct Linear Transform), P3P (Projective 3Point) and EPnP (Efficient Perspective-n-Point). In this example, the EPnP algorithm is preferred for camera pose estimation. It should be noted that in addition to n three-dimensional points, the PnP algorithm also requires the provision of the camera's internal parameters, including field of view angle, focal length, camera distortion and other related parameters.

[0058] Step 4: Reset the virtual camera in the 3D point cloud scene with the pose parameter B, and then correct the pose of the current virtual camera. Then, rasterize the point cloud in the current visual field of the virtual camera, and record the points of the point cloud that can be observed by each pixel when the current camera is rasterized.

[0059] Rasterization is a method of discretizing objects within the camera's field of view and projecting them onto a plane image. Infrared images are images generated by infrared cameras by capturing infrared thermal radiation information, discretizing it, and projecting it onto a plane. Generate a point information map of the same size as the infrared image from the point cloud, and use the point information map as the intermediate layer to map the infrared information to a three-dimensional point cloud. The rasterization method is used to generate the information map, and it is used as the intermediate layer for 2D to 3D mapping. By establishing a correspondence between pixels and grids, the temperature information in the infrared image is assigned to the point cloud data.

[0060] The point information map is not a visual graph, it records a two-dimensional list array of point cloud point information. The point information map is calculated to facilitate the search for all points projected into the image space from the camera's perspective. The coordinates corresponding to each pixel in the point information map contain the index of the point in the point cloud that can be mapped to this pixel. The structure of the point information map is as follows: Figure 3 shown.

[0061] Specifically, the point cloud data in the viewing cone is loaded according to the position of the virtual camera, and the point cloud is projected onto a two-dimensional rasterized plane through perspective projection, while recording the position information of each pixel on the grid. Perspective projection simulates the observation method of human eyes and cameras, such as Figure 2 As shown, objects in the projection have the characteristic of being larger when they are closer and smaller when they are farther away.

[0062] like Figure 3As shown, the point information mapped to the virtual camera screen space at this time is calculated by the rasterization method, so as to calculate the point information of all points on the point cloud that each pixel point of the infrared image should be mapped to.

[0063] Step 5: Filter the point information of the object and only keep the points on the plane closest to the camera;

[0064] Since the point cloud model is composed of discrete data points, even distant points may be projected onto the screen through nearby points during the projection transformation process. Therefore, if the infrared values ​​in the infrared image are directly mapped onto the screen, it will result in erroneous penetration effects, such as Figure 4 As shown.

[0065] In order to mask distant points, the present invention adopts a method of treating each point on the point cloud as having a certain volume. In the screen space, a neighborhood range (which can be circular or square) is defined for the points projected onto the grid, and the position information is recorded in the corresponding grid. At the same time, the grid and its neighborhood grid are updated using depth information, the projected point is treated as a surface, and the points on the distant plane are eliminated by updating the neighborhood depth information.

[0066] Using rasterization mapping, each pixel only records the point closest to the camera, and then searches for adjacent points through the neighborhood search method.

[0067] Using the ray tracing method, record the points hit by the rays emitted from each pixel, and then find the adjacent points through the neighborhood search method.

[0068] Step 6: Assign the infrared thermal values ​​on the infrared thermal map to the points on the point cloud of the corresponding pixels, and generate an infrared thermal value file of the point cloud.

[0069] The infrared remote sensing image and point cloud data are used as input data, and the infrared information is mapped to the corresponding position points of the point cloud using the above method, and the infrared information is interpreted as a color value. Therefore, the infrared thermal value file of the generated point cloud includes the temperature value corresponding to each point of the point cloud file, and special value marks are used for points without infrared value mapping.

[0070] In the present invention, refer to Figure 5 , and also provides a system for mapping three-dimensional point clouds with infrared thermal information, including:

[0071] The point cloud image generation module is used to place a virtual camera in the three-dimensional point cloud scene, set the camera internal parameters and posture parameters A to be the same as those of the camera shooting the infrared thermal image, and generate a point cloud image;

[0072] The point cloud image processing module is used to pre-process the point cloud image first, and then perform feature matching between the infrared thermal map and the pre-processed point cloud image;

[0073] The virtual camera posture adjustment module is used to obtain the three-dimensional coordinates of each feature point of the infrared image in the point cloud through the feature correspondence between the infrared and point cloud images, and recalculate the posture parameter B of the infrared camera through the two-dimensional and three-dimensional coordinates of the infrared feature points;

[0074] The pixel and point cloud conversion module resets the virtual camera in the 3D point cloud scene with the pose parameter B, and rasterizes the point cloud in the current visual field of the virtual camera, recording the points of the point cloud that can be observed by each pixel when the current camera is rasterized;

[0075] A point information processing module, used to filter the point information of the object obtained by the pixel and point cloud conversion module, and only retain the points on the plane closest to the camera;

[0076] The infrared information assignment module is used to assign the infrared thermal values ​​on the infrared thermal map to the points on the point cloud of the corresponding pixels and generate the infrared thermal value file of the point cloud.

[0077] The system of infrared thermal information mapping three-dimensional point cloud in this example can execute the method of infrared thermal information mapping three-dimensional point cloud provided by the present invention, and can execute any combination of implementation steps of the method example, and has the corresponding functions and beneficial effects of the method.

[0078] The present invention can combine infrared remote sensing images with point cloud data to achieve three-dimensional visualization of infrared remote sensing images, and can solve the technical problem of accurately mapping two-dimensional infrared remote sensing images to three-dimensional point cloud models. In practical applications in different fields, this technology can more intuitively and comprehensively understand the information in infrared images, thereby better analyzing and making decisions.

[0079] An embodiment of the present invention also provides a device for mapping three-dimensional point clouds with infrared thermal information, the device comprising: a memory, a processor, and a program for mapping three-dimensional point clouds with infrared thermal information stored in the memory and executable on the processor, the program for mapping three-dimensional point clouds with infrared thermal information being configured to implement the steps of the method for mapping three-dimensional point clouds with infrared thermal information as described in any one of the above items.

[0080] An embodiment of the present invention also provides a storage medium, on which is stored a program for mapping infrared thermal information to three-dimensional point clouds. When the program for mapping infrared thermal information to three-dimensional point clouds is executed by a processor, the steps of the method for mapping infrared thermal information to three-dimensional point clouds as described in any of the above items are implemented.

[0081] Those skilled in the art will appreciate that the embodiments of the present application may be provided as methods, systems, or computer program products. Therefore, the present application may adopt the form of a complete hardware embodiment, a complete software embodiment, or an embodiment in combination with software and hardware. Moreover, the present application may adopt the form of a computer program product implemented in one or more computer-usable storage media (including but not limited to disk storage, CD-ROM, optical storage, etc.) that include computer-usable program code.

[0082] The present application is described with reference to the flowcharts and / or block diagrams of the methods, devices (systems), and computer program products according to the embodiments of the present application. It should be understood that each process and / or box in the flowchart and / or block diagram, as well as the combination of the processes and / or boxes in the flowchart and / or block diagram, can be implemented by computer program instructions. These computer program instructions can be provided to a processor of a general-purpose computer, a special-purpose computer, an embedded processor, or other programmable data processing device to generate a machine, so that the instructions executed by the processor of the computer or other programmable data processing device generate instructions for implementing the processes in the flowchart and / or block diagram. Figure 1 A process or multiple processes and / or boxes Figure 1 A device that provides the functions specified in a block or multiple blocks.

[0083] These computer program instructions may also be stored in a computer-readable memory capable of directing a computer or other programmable data processing device to operate in a specific manner, so that the instructions stored in the computer-readable memory produce an article of manufacture comprising an instruction device, which implements the process Figure 1 A process or multiple processes and / or boxes Figure 1 A function specified in one or more boxes.

[0084] These computer program instructions can also be loaded onto a computer or other programmable data processing device so that a series of operating steps are executed on the computer or other programmable device to produce a computer-implemented process, thereby providing instructions for implementing the process. Figure 1 A process or multiple processes and / or boxes Figure 1 The steps for the functions specified in one or more boxes.

[0085] 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 above embodiments, ordinary technicians in the relevant field should understand that the specific implementation methods of the present invention can still be modified or replaced by equivalents. Any modification or equivalent replacement that does not depart from the spirit and scope of the present invention should be covered within the scope of protection of the claims of the present invention.

Claims

1. A method for mapping three-dimensional point clouds using infrared thermal information, characterized in that: The following steps are involved: Step 1: Place a virtual camera in the 3D point cloud scene, set the camera internal parameters and posture parameters A to be the same as the camera that shoots the infrared thermal image, and generate a point cloud image; Step 2: Preprocess the point cloud image first, and then perform feature matching between the infrared thermal map and the preprocessed point cloud image; Step 3: Obtain the three-dimensional coordinates of each feature point of the infrared thermal image in the point cloud through the feature correspondence between the infrared thermal image and the point cloud image, and recalculate the pose parameter B of the infrared camera through the two-dimensional and three-dimensional coordinates of the infrared feature point; Step 4: Reset the virtual camera in the 3D point cloud scene with the pose parameter B, rasterize the point cloud in the current visual domain of the virtual camera, and record the points of the point cloud that can be observed by each pixel when the current virtual camera is rasterized; Step 5: Filter the point information of the object, select and retain the points on the plane closest to the camera; Step 6: Assign the infrared thermal values ​​on the infrared thermal map to the points on the point cloud of the corresponding pixels, and generate an infrared thermal value file of the point cloud.

2. The method for mapping three-dimensional point cloud using infrared thermal information according to claim 1, characterized in that: In step 1, the pose parameter A includes the position of the camera and the rotation angle of the camera, and the internal parameters include the viewport size of the camera, the near plane and far plane of the camera, and the distortion parameters of the camera.

3. The method for mapping three-dimensional point cloud using infrared thermal information according to claim 1, characterized in that: In step 2, the steps of preprocessing the point cloud image include: Step 2.1: Apply histogram equalization to the point cloud image; Step 2.2: Use the Wiener filter to reduce noise on the point cloud image; Step 2.3: Use a Gaussian filter to smooth the point cloud image to remove noise and improve image quality.

4. The method for mapping three-dimensional point cloud using infrared thermal information according to claim 1, characterized in that: In step 3, the PnP algorithm is used to recalculate the pose parameter B of the infrared camera through the two-dimensional and three-dimensional coordinates of the infrared feature points.

5. The method for mapping three-dimensional point cloud using infrared thermal information according to claim 1, characterized in that: In step 4, the specific steps of rasterizing the point cloud within the current visual range of the virtual camera include: The point cloud data within the viewing cone is loaded according to the position of the virtual camera, and the point cloud is projected onto a two-dimensional rasterized plane through perspective projection. At the same time, the position information of the pixel points on each grid is recorded, that is, the point cloud is generated into a point information map of the same size as the infrared thermal map, and the infrared information is mapped to the three-dimensional point cloud using the point information map as the intermediate layer.

6. The method for mapping three-dimensional point cloud using infrared thermal information according to claim 1, characterized in that: In step 5, the point information of the object is filtered using a filtering method based on screen space mapping, and the specific steps include: Each projected point in screen space is considered as a surface. When a point is projected onto the grid and passes the depth test, its position information is recorded, and points on the far plane are culled by updating the neighborhood depth information.

7. The method for mapping three-dimensional point cloud using infrared thermal information according to claim 1, characterized in that: In step 6, an infrared thermal value file of the point cloud is generated, including the temperature value corresponding to each point of the point cloud file, and a special value mark is used for points without infrared value mapping.

8. A system for mapping three-dimensional point clouds using infrared thermal information, characterized in that: include: The point cloud image generation module is used to place a virtual camera in the three-dimensional point cloud scene, set the camera internal parameters and posture parameters A to be the same as those of the camera shooting the infrared thermal image, and generate a point cloud image; The point cloud image processing module is used to pre-process the point cloud image first, and then perform feature matching between the infrared thermal map and the pre-processed point cloud image; The virtual camera posture adjustment module is used to obtain the three-dimensional coordinates of each feature point of the infrared thermal image in the point cloud through the feature correspondence between the infrared thermal image and the point cloud image, and recalculate the posture parameter B of the infrared camera through the two-dimensional and three-dimensional coordinates of the infrared feature point; The pixel and point cloud conversion module resets the virtual camera in the 3D point cloud scene with the pose parameter B, and rasterizes the point cloud in the current visual field of the virtual camera, recording the points of the point cloud that can be observed by each pixel when the current virtual camera is rasterized; A point information processing module, used to filter the point information of the object obtained by the pixel and point cloud conversion module, and only retain the points on the plane closest to the camera; The infrared information assignment module is used to assign the infrared thermal values ​​on the infrared thermal map to the points on the point cloud of the corresponding pixels and generate the infrared thermal value file of the point cloud.

9. A device for mapping three-dimensional point clouds using infrared thermal information, characterized in that: The device includes: a memory, a processor, and a program for mapping three-dimensional point clouds with infrared thermal information stored in the memory and executable on the processor, wherein the program for mapping three-dimensional point clouds with infrared thermal information is configured to implement the steps of the method for mapping three-dimensional point clouds with infrared thermal information as described in any one of claims 1 to 7.

10. A storage medium, characterized in that: The storage medium stores a program for mapping infrared thermal information to three-dimensional point clouds. When the program for mapping infrared thermal information to three-dimensional point clouds is executed by a processor, the steps of the method for mapping infrared thermal information to three-dimensional point clouds as described in any one of claims 1 to 7 are implemented.

Images