Method, system and equipment for removing flying dust interference in depth camera and medium
By acquiring depth maps and RGB images using a depth camera, aligning them, marking and growing pixels, and removing dust interference through region comparison, the problem of ranging errors by depth cameras in dusty environments is solved, improving data accuracy and adaptability.
Patent Information
- Application Number
- CN202311828568.8
- Authority / Receiving Office
- CN · China
- Patent Type
- Applications(China)
- Current Assignee / Owner
- Filing Date
- 2023-12-28
- Publication Date
- 2026-02-13
AI Technical Summary
In existing technologies, depth cameras suffer from ranging errors due to dust interference, and the data is poorly processed after removing dust interference, which affects the obstacle avoidance and navigation accuracy of mobile robots.
Depth and RGB images are acquired using a depth camera. After alignment, pixels that do not meet the set conditions are marked. Region growing is performed based on pixel depth difference and grayscale difference. Finally, the pixel regions of the depth image are compared with the pixel regions of the RGB image to remove dust interference.
It significantly improves the effectiveness of depth cameras in removing dust interference data, reduces residual erroneous data, and enhances adaptability in low-cleanliness environments.
Smart Images
Figure CN121531241A_ABST
Abstract
Description
TECHNICAL FIELD
[0001] The present application relates to the technical field of robot vision, and in particular to a method, system, device and medium for removing flying dust interference in a depth camera. BACKGROUND
[0002] With the rapid development of technology, the development of mobile robots is also advancing with the times. Depth cameras are increasingly widely used in the vision application of mobile robots.
[0003] However, in some scenes with low environmental cleanliness, the ranging of the depth camera will be interfered by flying dust in the space, resulting in ranging errors or noise points and thus making the depth camera unusable. The main reason for the flying dust interference is that the depth camera can detect flying dust that is relatively close to the depth distance camera when the depth camera is working, and the flying dust and the background will generate flying pixels, so that the flying dust data and the target data to be measured cannot be distinguished on the obtained depth map.
[0004] Currently, the commonly used method is a flying pixel removal algorithm, which has poor effect on removing flying dust interference data. When large-particle flying dust such as large-particle flying dust interference and fog droplets occurs, removing such flying dust interference is easy to cause residual error data, which makes the mobile robot perceive errors, and thus seriously affects the accuracy of the mobile robot in obstacle avoidance, navigation and other aspects. SUMMARY
[0005] (I) Technical problems to be solved
[0006] In view of the above-mentioned shortcomings and deficiencies of the prior art, the present application provides a method, system, device and medium for removing flying dust interference in a depth camera, which solves the technical problem of poor effect of removing flying dust interference data in a depth camera.
[0007] (II) Technical solutions
[0008] In order to achieve the above-mentioned purposes, the main technical solutions adopted by the present application include:
[0009] In a first aspect, the present application provides a method for removing flying dust interference in a depth camera, the depth camera being configured with a depth camera and an RGB camera, the method comprising:
[0010] obtaining a depth map and an RGB map by the depth camera;
[0011] aligning the depth map and the RGB map to obtain an aligned RGB map;
[0012] traversing each pixel point of the depth map, and marking the pixel points that do not meet the set conditions to obtain marked pixel points;
[0013] Based on the obtained pixel depth difference, region growing is performed on the marked pixels to obtain the pixel region of the depth map;
[0014] Based on the obtained grayscale difference, region growing is performed on the aligned RGB image pixels corresponding to the marked pixels to obtain the pixel regions of the RGB image;
[0015] By comparing the pixel regions of the depth map with those of the RGB image, a depth map with dust interference removed is obtained.
[0016] Optionally, before acquiring the depth map and RGB image via the depth camera, the following steps are also included:
[0017] When the depth camera is set up in front of the preset calibration board, two consecutive grayscale images are acquired through the depth camera.
[0018] The pixels of the second grayscale image and the first depth image are divided, and the mean and variance of the grayscale ratio image are obtained from the calculation result.
[0019] Optionally, before aligning the depth map and the RGB image to obtain the aligned RGB image, the following steps are also included:
[0020] The pixel ratio of the grayscale image acquired by the depth camera to the previous grayscale image is obtained by performing a division operation on the pixels of the grayscale image.
[0021] By calculating the absolute value of the difference between the pixel ratio and the mean of the grayscale ratio, we can determine the magnitude of the variance of the obtained absolute value compared to that of the grayscale ratio.
[0022] If the absolute value obtained is greater than the variance of the grayscale ratio map, then the depth map pixel corresponding to the pixel ratio has moving dust, and the depth map pixel corresponding to the pixel ratio is removed from the depth map.
[0023] Traverse every pixel in the depth map and remove pixels with moving dust interference to obtain a depth map with moving dust interference removed.
[0024] Optionally, the depth map and RGB image acquired by the depth camera are aligned to obtain an aligned RGB image, including:
[0025] Obtain the intrinsic parameter matrix of the RGB camera in the depth camera, the intrinsic parameter matrix of the depth camera, and the extrinsic rotation matrix and offset matrix between the RGB camera and the depth camera;
[0026] Establish a first coordinate system with the depth camera as the origin and a second coordinate system with the RGB camera as the origin;
[0027] The pixel coordinates of the depth map are transformed using the intrinsic parameter matrix of the depth camera and the depth value of the pixel to obtain the coordinates in the first coordinate system.
[0028] Based on the external parameter rotation matrix and offset matrix between the RGB camera and the depth camera, the coordinate point in the second coordinate system corresponding to the coordinate point in the first coordinate system is obtained;
[0029] The coordinates in the second coordinate system are projected through the intrinsic parameter matrix of the RGB camera to obtain the pixel coordinates of the RGB image;
[0030] The process involves iterating through each pixel in the depth map and aligning it with the pixels in the RGB image to obtain the aligned RGB image.
[0031] Optionally, each pixel in the depth map is traversed, and pixels that do not meet the set conditions are marked. The marked pixels include:
[0032] Traverse each pixel in the depth map as the center pixel;
[0033] The pixel depth difference between different pixels within a set radius of the center pixel is compared with a pre-set threshold, and the center pixel is marked based on the comparison result.
[0034] If the difference in pixel depth between different pixels within a set radius of the center pixel is greater than a preset threshold, the center pixel is marked.
[0035] Optionally, based on the acquired grayscale difference, region growing is performed on the aligned RGB image pixels corresponding to the marked pixels to obtain the pixel regions of the RGB image, including:
[0036] Get the corresponding pixel in the aligned RGB image for the marked pixel;
[0037] After converting the aligned RGB image into a grayscale image, the grayscale difference is obtained by using a grayscale difference algorithm.
[0038] Based on the obtained grayscale difference, region growing is performed on the pixels in the RGB image to obtain the pixel region of the RGB image.
[0039] Optionally, the pixel regions of the depth map are compared with the pixel regions of the RGB image to obtain a depth map free of dust interference, including:
[0040] The pixel region of the depth map is compared with the pixel region of the corresponding RGB image, and the comparison results are used to determine whether there is dust interference in the pixel region of the depth map.
[0041] If the comparison result shows that the pixel area of the depth map is consistent with the pixel area of the corresponding RGB image, then it is determined that the pixel area of the depth map is free from dust interference.
[0042] If the comparison result shows that the pixel area of the depth map is inconsistent with the pixel area of the corresponding RGB image, it is determined that the pixel area of the depth map has dust interference, and the pixel area of the depth map is removed to obtain a depth map with dust interference removed.
[0043] Secondly, embodiments of the present invention provide a system for removing dust interference in a depth camera, comprising:
[0044] The image acquisition module is used to acquire depth maps and RGB images captured by the depth camera;
[0045] The image alignment module is used to align the depth map and the RGB image to obtain an aligned RGB image.
[0046] The pixel marking module is used to traverse each pixel in the depth map, mark pixels that do not meet the set conditions, and obtain the marked pixels.
[0047] The depth map pixel region growth module is used to grow the marked pixels based on the acquired pixel depth difference to obtain the pixel region of the depth map.
[0048] The RGB image pixel region growth module is used to grow the RGB image pixels corresponding to the marked pixels based on the acquired grayscale difference to obtain the pixel region of the RGB image.
[0049] The dust interference removal module compares the pixel areas of the depth map with the pixel areas of the RGB image to obtain a depth map with dust interference removed.
[0050] Thirdly, embodiments of the present invention provide a device for removing dust interference in a depth camera, comprising:
[0051] At least one database; and
[0052] A memory that is communicatively connected to the at least one database;
[0053] The memory stores instructions that can be executed by the at least one database, which are then executed by the at least one database to enable the at least one database to perform the above-described method for removing dust interference in a depth camera.
[0054] Fourthly, embodiments of the present invention provide a computer-readable medium having computer-executable instructions stored thereon, wherein the executable instructions, when executed by a processor, implement the above-described method for removing dust interference in a depth camera.
[0055] (III) Beneficial Effects
[0056] The beneficial effects of this invention are as follows: The method for removing dust interference in a depth camera involves aligning the acquired depth map with an RGB image, marking pixels in the depth map that do not meet set conditions, performing region growing on the marked depth map pixels and their corresponding RGB image pixels, and finally comparing the pixel regions of the depth map with those of the RGB image to obtain a depth map free of dust interference. Compared to existing technologies, this invention significantly improves the effectiveness of removing dust interference data from depth cameras and reduces the amount of residual erroneous data during the removal of large dust particles and droplets, thereby enabling depth cameras to adapt to more scenes with low cleanliness. Attached Figure Description
[0057] Figure 1 This is a schematic diagram of a method for removing dust interference in a depth camera according to an embodiment of the present invention. Detailed Implementation
[0058] To better explain and facilitate understanding of the present invention, the present invention will be described in detail below with reference to the accompanying drawings and specific embodiments.
[0059] This invention discloses a method, system, device, and medium for removing dust interference from a depth camera. The depth camera is equipped with a depth camera and an RGB camera. The method includes: acquiring a depth map and an RGB image through the depth camera; aligning the depth map and the RGB image to obtain an aligned RGB image; traversing each pixel in the depth map and marking pixels that do not meet set conditions to obtain marked pixels; performing region growing on the marked pixels based on the acquired pixel depth difference to obtain pixel regions of the depth map; performing region growing on the aligned RGB image pixels corresponding to the marked pixels based on the acquired grayscale difference to obtain pixel regions of the RGB image; and comparing the pixel regions of the depth map with the pixel regions of the RGB image to obtain a depth map with dust interference removed.
[0060] This invention employs a technical solution that involves aligning the acquired depth map with an RGB image, marking pixels in the depth map that do not meet set conditions, then performing region growing on the marked depth map pixels and their corresponding RGB image pixels, and finally comparing the pixel regions of the depth map with those of the RGB image to obtain a depth map free of dust interference. Compared to existing technologies, this invention significantly improves the effectiveness of removing dust interference data from depth cameras and reduces the amount of residual erroneous data during the removal of large dust particles and droplets, thereby enabling depth cameras to adapt to more scenes with varying degrees of cleanliness.
[0061] To better understand the above technical solutions, exemplary embodiments of the present invention will be described in more detail below with reference to the accompanying drawings. Although exemplary embodiments of the present invention are shown in the drawings, it should be understood that the present invention can be implemented in various forms and should not be limited to the embodiments set forth herein. Rather, these embodiments are provided so that the present invention can be understood more clearly and thoroughly, and that the scope of the present invention can be fully conveyed to those skilled in the art.
[0062] Specifically, refer to Figure 1 As shown, the present invention provides a method for removing dust interference in a depth camera, comprising:
[0063] S1. Obtain depth map and RGB image using a depth camera.
[0064] Furthermore, prior to step S1, the following steps are also included:
[0065] F1. With the depth camera and the preset calibration board positioned in front of each other, acquire two consecutive grayscale images using the depth camera. The calibration board is a 90% reflectivity calibration board.
[0066] F2. Perform a division operation on the pixels of the second grayscale image and the first depth image, and obtain the mean and variance of the grayscale ratio image based on the calculation result.
[0067] S2. Align the depth map and the RGB map to obtain the aligned RGB map.
[0068] Furthermore, prior to step S2, the following steps are also included:
[0069] P1. Perform a division operation on the pixels of the grayscale image acquired by the depth camera and the previous grayscale image to obtain the pixel ratio of the grayscale image to the previous grayscale image.
[0070] P2. By calculating the absolute value of the difference between the pixel ratio and the mean of the grayscale ratio, determine the magnitude of the variance of the obtained absolute value compared to that of the grayscale ratio.
[0071] P3. If the absolute value obtained is greater than the variance of the grayscale ratio map, then the depth map pixel corresponding to the pixel ratio has moving dust, and the depth map pixel corresponding to the pixel ratio will be removed from the depth map.
[0072] P4. Traverse each pixel of the depth map, remove pixels that are affected by moving dust, and obtain the depth map after removing moving dust interference.
[0073] Further, step S2 includes:
[0074] S21. Obtain the intrinsic parameter matrix of the RGB camera in the depth camera, the intrinsic parameter matrix of the depth camera, and the extrinsic parameter rotation matrix and offset matrix between the RGB camera and the depth camera.
[0075] S22. Establish a first coordinate system with the depth camera as the origin and a second coordinate system with the RGB camera as the origin.
[0076] S23. The pixel coordinates of the depth map are transformed using the intrinsic parameter matrix of the depth camera and the depth value of the pixel to obtain the coordinates in the first coordinate system.
[0077] S24. Based on the external parameter rotation matrix and offset matrix between the RGB camera and the depth camera, obtain the coordinate point in the second coordinate system corresponding to the coordinate point in the first coordinate system.
[0078] S25. Project the coordinates of the second coordinate system through the intrinsic parameter matrix of the RGB camera to obtain the pixel coordinates of the RGB image.
[0079] S26. Traverse each pixel in the depth map and align it with the pixels in the RGB map to obtain the aligned RGB map.
[0080] S3. Traverse each pixel in the depth map and mark the pixels that do not meet the set conditions to obtain the marked pixels.
[0081] Further, step S3 includes:
[0082] S31. Traverse each pixel in the depth map as the center pixel.
[0083] S32. Compare the pixel depth difference between different pixels within the set radius of the center pixel with a pre-set threshold, and mark the center pixel based on the comparison result.
[0084] The larger the radius set for the center pixel, the more data is removed, which can lead to the removal of normal data. Therefore, the optimal radius parameter needs to be selected based on experience from several dust removal tests.
[0085] S33. When the difference in pixel depth between different pixels within a set radius of the center pixel is greater than a preset threshold, the center pixel is marked.
[0086] S4. Based on the obtained pixel depth difference, perform region growing on the marked pixels to obtain the pixel region of the depth map.
[0087] The method for obtaining pixel regions of a depth map is to use the marked center pixel as a seed and the pixel depth difference between different pixels within a set radius of the center pixel as the growth condition to perform region growth.
[0088] S5. Based on the obtained grayscale difference, perform region growing on the aligned RGB image pixels corresponding to the marked pixels to obtain the pixel region of the RGB image.
[0089] Further, step S5 includes:
[0090] S51. Obtain the pixel corresponding to the marked pixel in the aligned RGB image.
[0091] S52. After converting the aligned RGB image into a grayscale image, the grayscale difference of the grayscale image is obtained by using a grayscale difference algorithm.
[0092] S53. Based on the obtained grayscale difference, perform region growing on the pixels in the RGB image to obtain the pixel region of the RGB image.
[0093] To further explain, the method for obtaining the pixel region of the RGB image is to use the RGB image pixel corresponding to the center pixel of the marked image as the seed, and the grayscale difference of the grayscale image of the RGB image containing the pixel as the growth condition, and then perform region growth.
[0094] S6. Compare the pixel areas of the depth map with the pixel areas of the RGB image to obtain a depth map with dust interference removed.
[0095] Further, step S6 includes:
[0096] S61. Compare the pixel area of the depth map with the pixel area of the corresponding RGB image, and determine whether there is dust interference in the pixel area of the depth map based on the comparison result.
[0097] S62a. If the comparison result shows that the pixel area of the depth map is consistent with the pixel area of the corresponding RGB image, then it is determined that the pixel area of the depth map is free from dust interference.
[0098] S62b. If the comparison result shows that the pixel area of the depth map is inconsistent with the pixel area of the corresponding RGB image, then it is determined that the pixel area of the depth map has dust interference, and the pixel area of the depth map is removed to obtain a depth map with dust interference removed.
[0099] Furthermore, the present invention provides a system for removing dust interference in a depth camera, comprising:
[0100] The image acquisition module is used to acquire depth maps and RGB images captured by the depth camera.
[0101] The image alignment module is used to align the depth map and the RGB image to obtain an aligned RGB image.
[0102] The pixel marking module is used to traverse each pixel in the depth map, mark pixels that do not meet the set conditions, and obtain the marked pixels.
[0103] The depth map pixel region growth module is used to grow regions on marked pixels based on the acquired pixel depth difference to obtain the pixel regions of the depth map.
[0104] The RGB image pixel region growth module is used to grow regions based on the acquired grayscale difference between the aligned RGB image pixels corresponding to the marked pixels, thereby obtaining the pixel regions of the RGB image.
[0105] The dust interference removal module compares the pixel areas of the depth map with the pixel areas of the RGB image to obtain a depth map with dust interference removed.
[0106] Furthermore, embodiments of the present invention provide a device for removing dust interference in a depth camera, comprising: at least one database; and a memory communicatively connected to the at least one database; wherein the memory stores instructions executable by the at least one database, the instructions being executed by the at least one database to enable the at least one database to perform the aforementioned method for removing dust interference in a depth camera.
[0107] Meanwhile, embodiments of the present invention provide a computer-readable medium storing computer-executable instructions, which, when executed by a processor, implement the above-described method for removing dust interference in a depth camera.
[0108] In summary, this invention provides a method, system, device, and medium for removing dust interference from a depth camera. The method comprises the following steps: First, removing moving dust interference data from the depth map based on a grayscale ratio image; second, aligning the depth map with the RGB image and marking pixels in the depth map that do not meet set conditions; then, performing region growing on the marked depth map pixels and their corresponding RGB image pixels to obtain pixel regions for both the depth map and the RGB image; finally, removing pixel regions in the depth map that are inconsistent with the pixel regions of the RGB image to obtain a depth map free of dust interference. The technical solution adopted in this invention can greatly improve the effect of removing dust interference data from depth cameras.
[0109] Since the systems / devices described in the above embodiments of the present invention are systems / devices used to implement the methods of the above embodiments of the present invention, those skilled in the art can understand the specific structure and modifications of the systems / devices based on the methods described in the above embodiments of the present invention, and therefore will not be repeated here. All systems / devices used in the methods of the above embodiments of the present invention fall within the scope of protection of the present invention.
[0110] Those skilled in the art will understand that embodiments of the present invention can be provided as methods, systems, or computer program products. Therefore, the present invention can take the form of a completely hardware embodiment, a completely software embodiment, or an embodiment combining software and hardware aspects. Furthermore, the present invention can take the form of a computer program product embodied on one or more computer-usable storage media (including, but not limited to, disk storage, CD-ROM, optical storage, etc.) containing computer-usable program code.
[0111] This invention is described with reference to flowchart illustrations and / or block diagrams of methods, apparatus (systems), and computer program products according to embodiments of the invention. It will be understood that each block of the flowchart illustrations and / or block diagrams, as well as combinations of blocks in the flowchart illustrations and / or block diagrams, can be implemented by computer program instructions.
[0112] It should be noted that any reference numerals placed between parentheses in the claims should not be construed as limiting the claims. The word "comprising" does not exclude the presence of components or steps not listed in the claims. The word "a" or "an" preceding a component does not exclude the presence of a plurality of such components. The invention can be implemented by means of hardware comprising several different components and by means of a suitably programmed computer. In claims that enumerate several means, several of these means may be embodied by the same hardware. The use of the terms first, second, third, etc., is merely for convenience of expression and does not indicate any order. These terms can be understood as part of the component names.
[0113] Furthermore, it should be noted that in the description of this specification, the terms "one embodiment," "some embodiments," "embodiment," "example," "specific example," or "some examples," etc., refer to specific features, structures, materials, or characteristics described in connection with that embodiment or example, which are included in at least one embodiment or example of the present invention. In this specification, the illustrative expressions of the above terms do not necessarily refer to the same embodiment or example. Moreover, the specific features, structures, materials, or characteristics described may be combined in any suitable manner in one or more embodiments or examples. Furthermore, without contradiction, those skilled in the art can combine and integrate the different embodiments or examples described in this specification, as well as the features of different embodiments or examples.
[0114] Although preferred embodiments of the invention have been described, those skilled in the art, upon learning the basic inventive concept, can make other changes and modifications to these embodiments. Therefore, the claims should be interpreted to include both the preferred embodiments and all changes and modifications falling within the scope of the invention.
[0115] Obviously, those skilled in the art can make various modifications and variations to this invention without departing from its spirit and scope. Therefore, if these modifications and variations fall within the scope of the claims of this invention and their equivalents, then this invention should also include these modifications and variations.
Claims
1. A method for removing dust interference in a depth camera, the depth camera being equipped with a depth camera and an RGB camera, characterized in that, The methods include: Acquire depth maps and RGB images using a depth camera; Align the depth map and the RGB map to obtain the aligned RGB map; Traverse each pixel in the depth map and mark the pixels that do not meet the set conditions to obtain the marked pixels; Based on the obtained pixel depth difference, region growing is performed on the marked pixels to obtain the pixel region of the depth map; Based on the obtained grayscale difference, region growing is performed on the aligned RGB image pixels corresponding to the marked pixels to obtain the pixel regions of the RGB image; By comparing the pixel regions of the depth map with those of the RGB image, a depth map with dust interference removed is obtained.
2. The method for removing dust interference in a depth camera as described in claim 1, characterized in that, Before acquiring depth and RGB images using a depth camera, the process also includes: When the depth camera is set up in front of the preset calibration board, two consecutive grayscale images are acquired through the depth camera. The pixels of the second grayscale image and the first grayscale image are divided by a number, and the mean and variance of the grayscale ratio image are obtained from the calculation result.
3. The method for removing dust interference in a depth camera as described in claim 2, characterized in that, Before aligning the depth map and RGB image to obtain the aligned RGB image, the following steps are also included: The pixel ratio of the grayscale image acquired by the depth camera to the previous grayscale image is obtained by performing a division operation on the pixels of the grayscale image. By calculating the absolute value of the difference between the pixel ratio and the mean of the grayscale ratio, we can determine the magnitude of the variance of the obtained absolute value compared to that of the grayscale ratio. If the absolute value obtained is greater than the variance of the grayscale ratio map, then the depth map pixel corresponding to the pixel ratio has moving dust, and the depth map pixel corresponding to the pixel ratio is removed from the depth map. Traverse every pixel in the depth map and remove pixels with moving dust interference to obtain a depth map with moving dust interference removed.
4. The method for removing dust interference in a depth camera as described in claim 1, characterized in that, Aligning the depth map and the RGB image yields the aligned RGB values, including: Obtain the intrinsic parameter matrix of the RGB camera in the depth camera, the intrinsic parameter matrix of the depth camera, and the extrinsic rotation matrix and offset matrix between the RGB camera and the depth camera; Establish a first coordinate system with the depth camera as the origin and a second coordinate system with the RGB camera as the origin; The pixel coordinates of the depth map are transformed using the intrinsic parameter matrix of the depth camera and the depth value of the pixel to obtain the coordinates in the first coordinate system. Based on the external parameter rotation matrix and offset matrix between the RGB camera and the depth camera, the coordinate point in the second coordinate system corresponding to the coordinate point in the first coordinate system is obtained; The coordinates in the second coordinate system are projected through the intrinsic parameter matrix of the RGB camera to obtain the pixel coordinates of the RGB image; The process involves iterating through each pixel in the depth map and aligning it with the pixels in the RGB image to obtain the aligned RGB image.
5. The method for removing dust interference in a depth camera as described in claim 1, characterized in that, Iterate through each pixel in the depth map, marking pixels that do not meet the set conditions. The marked pixels include: Traverse each pixel in the depth map as the center pixel; The pixel depth difference between different pixels within a set radius of the center pixel is compared with a pre-set threshold, and the center pixel is marked based on the comparison result. If the difference in pixel depth between different pixels within a set radius of the center pixel is greater than a preset threshold, the center pixel is marked.
6. The method for removing dust interference in a depth camera as described in claim 1, characterized in that, Based on the acquired grayscale difference, region growing is performed on the aligned RGB image pixels corresponding to the marked pixels to obtain the pixel regions of the RGB image, including: Get the corresponding pixel in the aligned RGB image for the marked pixel; After converting the aligned RGB image into a grayscale image, the grayscale difference is obtained by using a grayscale difference algorithm. Based on the obtained grayscale difference, region growing is performed on the pixels in the RGB image to obtain the pixel region of the RGB image.
7. The method for removing dust interference in a depth camera as described in claim 1, characterized in that, By comparing the pixel regions of the depth map with those of the RGB image, a depth map with dust interference removed is obtained, including: The pixel region of the depth map is compared with the pixel region of the corresponding RGB image, and the comparison results are used to determine whether there is dust interference in the pixel region of the depth map. If the comparison result shows that the pixel area of the depth map is consistent with the pixel area of the corresponding RGB image, then it is determined that the pixel area of the depth map is free from dust interference. If the comparison result shows that the pixel area of the depth map is inconsistent with the pixel area of the corresponding RGB image, it is determined that the pixel area of the depth map has dust interference, and the pixel area of the depth map is removed to obtain a depth map with dust interference removed.
8. A system for removing dust interference in a depth camera, characterized in that, include: The image acquisition module is used to acquire depth maps and RGB images captured by the depth camera; The image alignment module is used to align the depth map and the RGB image to obtain an aligned RGB image. The pixel marking module is used to traverse each pixel in the depth map, mark pixels that do not meet the set conditions, and obtain the marked pixels. The depth map pixel region growth module is used to grow the marked pixels based on the acquired pixel depth difference to obtain the pixel region of the depth map. The RGB image pixel region growth module is used to grow the RGB image pixels corresponding to the marked pixels based on the acquired grayscale difference to obtain the pixel region of the RGB image. The dust interference removal module compares the pixel areas of the depth map with the pixel areas of the RGB image to obtain a depth map with dust interference removed.
9. A device for removing dust interference in a depth camera, characterized in that, include: At least one database; as well as A memory that is communicatively connected to the at least one database; The memory stores instructions that can be executed by the at least one database, which are executed by the at least one database to enable the at least one database to perform a method for removing dust interference in a depth camera as described in any one of claims 1-7.
10. A computer-readable medium having computer-executable instructions stored thereon, characterized in that, When the executable instructions are executed by the processor, they implement a method for removing dust interference in a depth camera as described in any one of claims 1-7.