Cleaning robot control method and device

Abstract

The present application relates to the field of robot technology, and provides a cleaning robot control method and device. The method comprises: photographing a target image of an area to be cleaned by a camera provided on the cleaning robot; preprocessing the target image, wherein the preprocessing comprises: denoising, contrast enhancement and grayscale processing; extracting target image features from the preprocessed target image; determining the category of the ground material of the area to be cleaned based on the target image features; determining the cleaning method of the area to be cleaned based on the category of the ground material of the area to be cleaned; and controlling the cleaning robot to clean the area to be cleaned according to the cleaning method. The above-mentioned technical means are adopted to solve the problem of low efficiency of cleaning robots in cleaning complex and changeable ground environments in the prior art.

Description

Technical Field

[0001] The present application relates to the field of robotics technology, and in particular to a cleaning robot control method and device. Background Art

[0002] With the rapid development of robot technology, the use of cleaning robots is becoming more and more common. Currently, users are required to pre-set the cleaning method according to the use environment, and then the cleaning robot cleans the garbage according to the pre-set cleaning method. This method cannot cope with complex and changeable ground environments. Complex and changeable ground environments require robots to be able to identify specific environmental types and adopt corresponding cleaning modes. Summary of the invention

[0003] In view of this, the embodiments of the present application provide a cleaning robot control method, device, electronic device and computer-readable storage medium to solve the problem of low efficiency of cleaning robots in cleaning complex and changeable ground environments in the prior art.

[0004] According to a first aspect of an embodiment of the present application, a cleaning robot control method is provided, comprising: capturing a target image of an area to be cleaned by a camera arranged on the cleaning robot; preprocessing the target image, wherein the preprocessing comprises: denoising, contrast enhancement and grayscale processing; extracting target image features from the preprocessed target image; determining the category of a floor material of the area to be cleaned based on the target image features; determining a cleaning method for the area to be cleaned based on the category of the floor material of the area to be cleaned; and controlling the cleaning robot to clean the area to be cleaned according to the cleaning method.

[0005] According to a second aspect of an embodiment of the present application, a cleaning robot control device is provided, comprising: a shooting module, configured to shoot a target image of an area to be cleaned through a camera provided on the cleaning robot; a preprocessing module, configured to preprocess the target image, wherein the preprocessing includes: denoising processing, contrast enhancement processing and grayscale processing; an extraction module, configured to extract target image features from the preprocessed target image; an identification module, configured to determine the category of the floor material of the area to be cleaned based on the target image features; a determination module, configured to determine a cleaning method of the area to be cleaned based on the category of the floor material of the area to be cleaned; and a control module, configured to control the cleaning robot to clean the area to be cleaned according to the cleaning method.

[0006] According to a third aspect of an embodiment of the present application, an electronic device is provided, comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor implements the steps of the above method when executing the computer program.

[0007] According to a fourth aspect of an embodiment of the present application, a computer-readable storage medium is provided, which stores a computer program, and when the computer program is executed by a processor, the steps of the above method are implemented.

[0008] Compared with the prior art, the embodiments of the present application have the following beneficial effects: the target image of the area to be cleaned is captured by a camera provided on the cleaning robot; the target image is preprocessed, wherein the preprocessing includes: denoising, contrast enhancement and grayscale processing; the target image features are extracted from the preprocessed target image; the category of the ground material of the area to be cleaned is determined based on the target image features; the cleaning method of the area to be cleaned is determined based on the category of the ground material of the area to be cleaned; and the cleaning robot is controlled to clean the area to be cleaned according to the cleaning method. The above technical means can solve the problem of low efficiency of cleaning robots in cleaning complex and changeable ground environments in the prior art, thereby improving the cleaning efficiency of the cleaning robots. BRIEF DESCRIPTION OF THE DRAWINGS

[0009] In order to more clearly illustrate the technical solutions in the embodiments of the present application, the drawings required for use in the embodiments or the description of the prior art will be briefly introduced below. Obviously, the drawings described below are only some embodiments of the present application. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying any creative work.

[0010] Figure 1 It is a flow chart of a cleaning robot control method provided in an embodiment of the present application;

[0011] Figure 2 It is a flow chart of a material recognition model training method provided in an embodiment of the present application;

[0012] Figure 3 is a structural schematic diagram of a cleaning robot control device provided in an embodiment of the present application;

[0013] Figure 4 It is a structural schematic diagram of an electronic device provided in an embodiment of the present application. DETAILED DESCRIPTION

[0014] In the following description, specific details such as specific system structures, technologies, etc. are provided for the purpose of illustration rather than limitation, so as to provide a thorough understanding of the embodiments of the present application. However, it should be clear to those skilled in the art that the present application may also be implemented in other embodiments without these specific details. In other cases, detailed descriptions of well-known systems, devices, circuits, and methods are omitted to prevent unnecessary details from obstructing the description of the present application.

[0015] A cleaning robot control method and device according to an embodiment of the present application will be described in detail below with reference to the accompanying drawings.

[0016] Figure 1 It is a flow chart of a cleaning robot control method provided in an embodiment of the present application. Figure 1 The cleaning robot control method can be executed by a computer or a server, or software on the computer or the server. Figure 1 As shown, the cleaning robot control method includes:

[0017] S101, capturing a target image of the area to be cleaned by a camera provided on the cleaning robot;

[0018] S102, preprocessing the target image, wherein the preprocessing includes: denoising, contrast enhancement and grayscale processing;

[0019] S103, extracting target image features from the preprocessed target image;

[0020] S104, determining the type of the ground material of the area to be cleaned according to the target image features;

[0021] S105, determining a cleaning method for the area to be cleaned based on the type of the floor material of the area to be cleaned;

[0022] S106, controlling the cleaning robot to clean the area to be cleaned according to the cleaning method.

[0023] The types of floor materials in the area to be cleaned include carpets, tiles, and wooden tiles. Denoising can eliminate noise points in the image and improve image quality. Denoising includes Gaussian filtering, bilateral filtering, and the like. Contrast enhancement can highlight the characteristics of the floor material and facilitate subsequent feature extraction. Contrast enhancement can be achieved by using methods such as histogram equalization and adaptive histogram equalization. Grayscale processing can simplify the image processing process and improve computational efficiency. Generally, there are four methods for graying images: component method, maximum value method, average value method, and weighted average method. Extract target image features from the preprocessed target image, and determine the type of floor material in the area to be cleaned based on the target image features through a pre-trained material recognition model. The type of the area to be cleaned is replaced by the type of its floor material. Based on the type of floor material in the area to be cleaned, determine the cleaning method of the area to be cleaned, and then control the cleaning robot to clean the area to be cleaned.

[0024] According to the technical solution provided by the embodiment of the present application, a target image of the area to be cleaned is captured by a camera provided on the cleaning robot; the target image is preprocessed, wherein the preprocessing includes: denoising, contrast enhancement and grayscale processing; target image features are extracted from the preprocessed target image; the category of the ground material of the area to be cleaned is determined based on the target image features; the cleaning method of the area to be cleaned is determined based on the category of the ground material of the area to be cleaned; and the cleaning robot is controlled to clean the area to be cleaned according to the cleaning method. The above technical means can solve the problem of low efficiency of cleaning robots in cleaning complex and changeable ground environments in the prior art, thereby improving the cleaning efficiency of the cleaning robots.

[0025] Furthermore, before determining the category of the floor material of the area to be cleaned based on the target image features, the method also includes: obtaining target images at different positions of the area to be cleaned by photographing at different angles using various cameras set by the cleaning robot; preprocessing each target image; extracting image features of each preprocessed target image; and performing feature stitching processing on each image feature to obtain target image features.

[0026] The embodiment of the present application preprocesses each target image respectively, then extracts the image features of each preprocessed target image, and combines all the image features to determine the category of the floor material of the area to be cleaned.

[0027] Furthermore, before determining the category of the ground material of the area to be cleaned based on the target image features, the method also includes: obtaining target images of different positions of the area to be cleaned by photographing at different angles through various cameras set by the cleaning robot; performing image stitching processing on each target image to obtain a panoramic image; preprocessing the panoramic image; and extracting target image features from the preprocessed panoramic image.

[0028] The embodiment of the present application first uses all target images to stitch together a panoramic image, then preprocesses the panoramic image, extracts target image features from the panoramic image, and finally determines the category of the ground material of the area to be cleaned based on the target image features.

[0029] Furthermore, target image features are extracted from the preprocessed target image, including: extracting color features from the preprocessed target image; extracting texture features from the preprocessed target image; extracting edge features from the preprocessed target image; and performing feature splicing processing on color features, texture features and edge features to obtain target image features.

[0030] For color features, methods such as color space conversion and color threshold segmentation can be used; for texture features, methods such as gray-level co-occurrence matrix and local binary pattern can be used; for edge features, methods such as Canny edge detection and Sobel operator can be used. By combining multiple features, a more comprehensive and accurate description of the ground material can be formed, that is, feature splicing of color features, texture features and edge features can be performed to obtain the target image features.

[0031] Furthermore, the category of the ground material of the area to be cleaned is determined based on the target image features, including: the target image features include color features, texture features and edge features; the first probability distribution of the ground material of the area to be cleaned is determined based on the color features; the second probability distribution of the ground material of the area to be cleaned is determined based on the texture features; the third probability distribution of the ground material of the area to be cleaned is determined based on the edge features; the category of the ground material of the area to be cleaned is determined based on the first probability distribution, the second probability distribution and the third probability distribution.

[0032] Based on the color features, texture features, and edge features, the material recognition model outputs the first probability distribution, the second probability distribution, and the third probability distribution of the category of the floor material of the area to be cleaned. The first probability distribution, the second probability distribution, and the third probability distribution are all distributions representing the probability that the floor material of the area to be cleaned is of different categories. The first probability distribution, the second probability distribution, and the third probability distribution can be added together, and the category with the largest probability is taken as the category of the floor material of the area to be cleaned.

[0033] Before determining the type of the ground material of the area to be cleaned according to the target image features through the material recognition model, the material recognition model is trained.

[0034] Figure 2 Schematic diagram of a material recognition model training method provided in an embodiment of the present application. Figure 2 As shown, the method includes:

[0035] S201, obtaining a training image and preprocessing the training image;

[0036] S202, extracting training image features from the preprocessed training image;

[0037] S203, determining the category of the ground material corresponding to the training image according to the training image features through a material recognition model;

[0038] S204, using a cross entropy loss function to calculate the loss between the label of the training image and the category of its corresponding ground material, and optimizing the model parameters of the material recognition model based on the loss.

[0039] The label of the training image is the category of the ground material in the area corresponding to the training image that is annotated in advance. The training image output by the material recognition model corresponds to the category of the ground material, which is the classification result of the material recognition model. The cross entropy loss function can be used to calculate the loss between the label of the training image and the category of the corresponding ground material, thereby optimizing the material recognition model.

[0040] Furthermore, based on the category of the floor material of the area to be cleaned, the cleaning method of the area to be cleaned is determined, including: when the category of the floor material of the area to be cleaned is carpet, the cleaning method of the area to be cleaned is determined to be the first method; when the category of the floor material of the area to be cleaned is ceramic tile, the cleaning method of the area to be cleaned is determined to be the second method; when the category of the floor material of the area to be cleaned is wooden tiles, the cleaning method of the area to be cleaned is determined to be the third method.

[0041] Different cleaning methods include: cleaning frequency, whether to water during the cleaning process, different cleaning heads, etc. The first method is for carpets. Carpets easily absorb dust, stains and bacteria, and need to be vacuumed and deep cleaned regularly. At the same time, it is necessary to avoid using too much water to prevent damage to the carpet fibers or cause mildew. The second method is for tiles. The surface of tiles is hard and wear-resistant, but dust and dirt are easily accumulated at the joints, so the second method is mainly for the joints. The third method is for wood floor tiles. Wood flooring has the characteristics of natural beauty, but it is also sensitive to humidity and needs to be carefully maintained. Try to avoid direct water cleaning to avoid causing the wood to swell or deform.

[0042] In one embodiment, each camera set by the cleaning robot is used to capture target images at different positions of the area to be cleaned at different angles; each target image is stitched to obtain a panoramic image; the panoramic image is preprocessed; color features are extracted from the preprocessed panoramic image; texture features are extracted from the preprocessed panoramic image; edge features are extracted from the preprocessed panoramic image; a first probability distribution of the floor material of the area to be cleaned is determined based on the color features; a second probability distribution of the floor material of the area to be cleaned is determined based on the texture features; a third probability distribution of the floor material of the area to be cleaned is determined based on the edge features; based on the first probability distribution, the second probability distribution and the third probability distribution, the category of the floor material of the area to be cleaned is determined; when the category of the floor material of the area to be cleaned is carpet, the cleaning method of the area to be cleaned is determined to be the first method; when the category of the floor material of the area to be cleaned is ceramic tile, the cleaning method of the area to be cleaned is determined to be the second method; when the category of the floor material of the area to be cleaned is wooden brick, the cleaning method of the area to be cleaned is determined to be the third method.

[0043] According to the technical solution provided by the embodiment of the present application, a target image of the area to be cleaned is captured by a camera provided on the cleaning robot; the target image is preprocessed, wherein the preprocessing includes: denoising, contrast enhancement and grayscale processing; target image features are extracted from the preprocessed target image; the category of the ground material of the area to be cleaned is determined based on the target image features; the cleaning method of the area to be cleaned is determined based on the category of the ground material of the area to be cleaned; and the cleaning robot is controlled to clean the area to be cleaned according to the cleaning method. The above technical means can solve the problem of low efficiency of cleaning robots in cleaning complex and changeable ground environments in the prior art, thereby improving the cleaning efficiency of the cleaning robots.

[0044] All the above optional technical solutions can be arbitrarily combined to form optional embodiments of the present application, which will not be described one by one here.

[0045] The following is an embodiment of the device of the present application, which can be used to execute the embodiment of the method of the present application. For details not disclosed in the embodiment of the device of the present application, please refer to the embodiment of the method of the present application.

[0046] Figure 3 Schematic diagram of a cleaning robot control device provided in an embodiment of the present application. Figure 3 As shown, the cleaning robot control device includes:

[0047] The shooting module 301 is configured to shoot a target image of the area to be cleaned through a camera provided on the cleaning robot;

[0048] The preprocessing module 302 is configured to preprocess the target image, wherein the preprocessing includes: denoising, contrast enhancement and grayscale processing;

[0049] An extraction module 303 is configured to extract target image features from the preprocessed target image;

[0050] The recognition module 304 is configured to determine the type of the floor material of the area to be cleaned according to the target image features;

[0051] The determination module 305 is configured to determine a cleaning method of the area to be cleaned based on the type of the floor material of the area to be cleaned;

[0052] The control module 306 is configured to control the cleaning robot to clean the area to be cleaned according to the cleaning method.

[0053] The types of floor materials in the area to be cleaned include carpets, tiles, and wooden tiles. Denoising can eliminate noise points in the image and improve image quality. Denoising includes Gaussian filtering, bilateral filtering, and the like. Contrast enhancement can highlight the characteristics of the floor material and facilitate subsequent feature extraction. Contrast enhancement can be achieved by using methods such as histogram equalization and adaptive histogram equalization. Grayscale processing can simplify the image processing process and improve computational efficiency. Generally, there are four methods for graying images: component method, maximum value method, average value method, and weighted average method. Extract target image features from the preprocessed target image, and determine the type of floor material in the area to be cleaned based on the target image features through a pre-trained material recognition model. The type of the area to be cleaned is replaced by the type of its floor material. Based on the type of floor material in the area to be cleaned, determine the cleaning method of the area to be cleaned, and then control the cleaning robot to clean the area to be cleaned.

[0054] According to the technical solution provided by the embodiment of the present application, a target image of the area to be cleaned is captured by a camera provided on the cleaning robot; the target image is preprocessed, wherein the preprocessing includes: denoising, contrast enhancement and grayscale processing; target image features are extracted from the preprocessed target image; the category of the ground material of the area to be cleaned is determined based on the target image features; the cleaning method of the area to be cleaned is determined based on the category of the ground material of the area to be cleaned; and the cleaning robot is controlled to clean the area to be cleaned according to the cleaning method. The above technical means can solve the problem of low efficiency of cleaning robots in cleaning complex and changeable ground environments in the prior art, thereby improving the cleaning efficiency of the cleaning robots.

[0055] In some embodiments, the extraction module 303 is also configured to obtain target images at different positions of the area to be cleaned by photographing at different angles through various cameras set by the cleaning robot; preprocess each target image; extract image features of each preprocessed target image; perform feature stitching processing on each image feature to obtain target image features.

[0056] The embodiment of the present application preprocesses each target image respectively, then extracts the image features of each preprocessed target image, and combines all the image features to determine the category of the floor material of the area to be cleaned.

[0057] In some embodiments, the extraction module 303 is also configured to obtain target images at different positions of the area to be cleaned by photographing at different angles through various cameras set by the cleaning robot; perform image stitching processing on each target image to obtain a panoramic image; pre-process the panoramic image; and extract target image features from the pre-processed panoramic image.

[0058] The embodiment of the present application first uses all target images to stitch together a panoramic image, then preprocesses the panoramic image, extracts target image features from the panoramic image, and finally determines the category of the ground material of the area to be cleaned based on the target image features.

[0059] In some embodiments, the extraction module 303 is also configured to extract color features from the preprocessed target image; extract texture features from the preprocessed target image; extract edge features from the preprocessed target image; perform feature stitching processing on color features, texture features and edge features to obtain target image features.

[0060] For color features, methods such as color space conversion and color threshold segmentation can be used; for texture features, methods such as gray-level co-occurrence matrix and local binary pattern can be used; for edge features, methods such as Canny edge detection and Sobel operator can be used. By combining multiple features, a more comprehensive and accurate description of the ground material can be formed, that is, feature splicing of color features, texture features and edge features can be performed to obtain the target image features.

[0061] In some embodiments, the recognition module 304 is also configured such that the target image features include color features, texture features, and edge features; determine a first probability distribution of the floor material of the area to be cleaned based on the color features; determine a second probability distribution of the floor material of the area to be cleaned based on the texture features; determine a third probability distribution of the floor material of the area to be cleaned based on the edge features; and determine the category of the floor material of the area to be cleaned based on the first probability distribution, the second probability distribution, and the third probability distribution.

[0062] Based on the color features, texture features, and edge features, the material recognition model outputs the first probability distribution, the second probability distribution, and the third probability distribution of the category of the floor material of the area to be cleaned. The first probability distribution, the second probability distribution, and the third probability distribution are all distributions representing the probability that the floor material of the area to be cleaned is of different categories. The first probability distribution, the second probability distribution, and the third probability distribution can be added together, and the category with the largest probability is taken as the category of the floor material of the area to be cleaned.

[0063] Before determining the type of the ground material of the area to be cleaned according to the target image features through the material recognition model, the material recognition model is trained.

[0064] In some embodiments, the recognition module 304 is further configured to obtain a training image and preprocess the training image; extract training image features from the preprocessed training image; determine the category of the ground material corresponding to the training image based on the training image features through a material recognition model; use a cross entropy loss function to calculate the loss between the label of the training image and the category of the corresponding ground material, and optimize the model parameters of the material recognition model based on the loss.

[0065] The label of the training image is the category of the ground material in the area corresponding to the training image that is annotated in advance. The training image output by the material recognition model corresponds to the category of the ground material, which is the classification result of the material recognition model. The cross entropy loss function can be used to calculate the loss between the label of the training image and the category of the corresponding ground material, thereby optimizing the material recognition model.

[0066] In some embodiments, the determination module 305 is also configured to determine that the cleaning method of the area to be cleaned is the first method when the category of the floor material of the area to be cleaned is carpet; to determine that the cleaning method of the area to be cleaned is the second method when the category of the floor material of the area to be cleaned is ceramic tile; and to determine that the cleaning method of the area to be cleaned is the third method when the category of the floor material of the area to be cleaned is wooden tile.

[0067] Different cleaning methods include: cleaning frequency, whether to water during the cleaning process, different cleaning heads, etc. The first method is for carpets. Carpets easily absorb dust, stains and bacteria, and need to be vacuumed and deep cleaned regularly. At the same time, it is necessary to avoid using too much water to prevent damage to the carpet fibers or cause mildew. The second method is for tiles. The surface of tiles is hard and wear-resistant, but dust and dirt are easily accumulated at the joints, so the second method is mainly for the joints. The third method is for wood floor tiles. Wood flooring has the characteristics of natural beauty, but it is also sensitive to humidity and needs to be carefully maintained. Try to avoid direct water cleaning to avoid causing the wood to swell or deform.

[0068] In some embodiments, the determination module 305 is also configured to obtain target images of different positions of the area to be cleaned by photographing at different angles through various cameras set by the cleaning robot; perform image stitching processing on each target image to obtain a panoramic image; pre-process the panoramic image; extract color features from the pre-processed panoramic image; extract texture features from the pre-processed panoramic image; extract edge features from the pre-processed panoramic image; determine a first probability distribution of the floor material of the area to be cleaned based on the color features; determine a second probability distribution of the floor material of the area to be cleaned based on the texture features; determine a third probability distribution of the floor material of the area to be cleaned based on the edge features; determine the category of the floor material of the area to be cleaned based on the first probability distribution, the second probability distribution and the third probability distribution; when the category of the floor material of the area to be cleaned is carpet, determine that the cleaning method of the area to be cleaned is the first method; when the category of the floor material of the area to be cleaned is ceramic tile, determine that the cleaning method of the area to be cleaned is the second method; when the category of the floor material of the area to be cleaned is wooden bricks, determine that the cleaning method of the area to be cleaned is the third method.

[0069] According to the technical solution provided by the embodiment of the present application, a target image of the area to be cleaned is captured by a camera provided on the cleaning robot; the target image is preprocessed, wherein the preprocessing includes: denoising, contrast enhancement and grayscale processing; target image features are extracted from the preprocessed target image; the category of the ground material of the area to be cleaned is determined based on the target image features; the cleaning method of the area to be cleaned is determined based on the category of the ground material of the area to be cleaned; and the cleaning robot is controlled to clean the area to be cleaned according to the cleaning method. The above technical means can solve the problem of low efficiency of cleaning robots in cleaning complex and changeable ground environments in the prior art, thereby improving the cleaning efficiency of the cleaning robots.

[0070] It should be understood that the size of the serial numbers of the steps in the above embodiments does not mean the order of execution. The execution order of each process should be determined by its function and internal logic, and should not constitute any limitation on the implementation process of the embodiments of the present application.

[0071] Figure 4 Schematic diagram of an electronic device 4 provided in an embodiment of the present application. Figure 4 As shown, the electronic device 4 of this embodiment includes: a processor 401, a memory 402, and a computer program 403 stored in the memory 402 and executable on the processor 401. When the processor 401 executes the computer program 403, the steps in the above-mentioned method embodiments are implemented. Alternatively, when the processor 401 executes the computer program 403, the functions of the modules / units in the above-mentioned device embodiments are implemented.

[0072] The electronic device 4 may be a desktop computer, a notebook, a PDA, a cloud server, or other electronic device. The electronic device 4 may include, but is not limited to, a processor 401 and a memory 402. Those skilled in the art will appreciate that Figure 4 The electronic device 4 is merely an example and does not limit the electronic device 4 , and may include more or less components than those shown in the figure, or different components.

[0073] The processor 401 may be a central processing unit (CPU), or other general-purpose processors, digital signal processors (DSP), application-specific integrated circuits (ASIC), field-programmable gate arrays (FPGA), or other programmable logic devices, discrete gate or transistor logic devices, discrete hardware components, etc.

[0074] The memory 402 may be an internal storage unit of the electronic device 4, for example, a hard disk or memory of the electronic device 4. The memory 402 may also be an external storage device of the electronic device 4, for example, a plug-in hard disk, a smart media card (SMC), a secure digital (SD) card, a flash card, etc. equipped on the electronic device 4. The memory 402 may also include both an internal storage unit and an external storage device of the electronic device 4. The memory 402 is used to store computer programs and other programs and data required by the electronic device.

[0075] Those skilled in the art can clearly understand that for the convenience and simplicity of description, only the division of the above-mentioned functional units and modules is used as an example. In actual applications, the above-mentioned functions can be assigned to different functional units and modules as needed, that is, the internal structure of the device can be divided into different functional units or modules to complete all or part of the functions described above. The functional units and modules in the embodiments can be integrated into one processing unit, or each unit can exist physically separately, or two or more units can be integrated into one unit. The above-mentioned integrated unit can be implemented in the form of hardware or in the form of software functional units.

[0076] If the integrated module / unit is implemented in the form of a software functional unit and sold or used as an independent product, it can be stored in a computer-readable storage medium. Based on this understanding, the present application implements all or part of the processes in the above-mentioned embodiment method, and can also be completed by instructing the relevant hardware through a computer program. The computer program can be stored in a computer-readable storage medium, and the computer program can implement the steps of the above-mentioned various method embodiments when executed by the processor. The computer program may include computer program code, and the computer program code may be in source code form, object code form, executable file or some intermediate form. The computer-readable medium may include: any entity or device capable of carrying computer program code, recording medium, U disk, mobile hard disk, magnetic disk, optical disk, computer memory, read-only memory (ROM), random access memory (RAM), electric carrier signal, telecommunication signal and software distribution medium. It should be noted that the content contained in the computer-readable medium can be appropriately increased or decreased according to the requirements of legislation and patent practice in the jurisdiction. For example, in some jurisdictions, according to legislation and patent practice, the computer-readable medium does not include electric carrier signals and telecommunication signals.

[0077] The above embodiments are only used to illustrate the technical solutions of the present application, rather than to limit them. Although the present application 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. 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 embodiments of the present application, and should all be included in the protection scope of the present application.

Claims

1. A cleaning robot control method, characterized in that: include: The target image of the area to be cleaned is captured by a camera arranged on the cleaning robot; Preprocessing the target image, wherein the preprocessing includes: denoising, contrast enhancement and grayscale processing; Extracting target image features from the preprocessed target image; Determining the type of the floor material of the area to be cleaned according to the target image features; Determining a cleaning method for the area to be cleaned based on the type of the floor material of the area to be cleaned; The cleaning robot is controlled to clean the area to be cleaned according to the cleaning method.

2. The method according to claim 1, characterized in that Before determining the type of the floor material of the area to be cleaned according to the target image features, the method further includes: The target images at different positions of the area to be cleaned are obtained by shooting at different angles using various cameras provided on the cleaning robot; Performing the preprocessing on each target image; Extracting image features of each preprocessed target image; Perform feature splicing processing on each image feature to obtain the target image feature.

3. The method according to claim 1, characterized in that Before determining the type of the floor material of the area to be cleaned according to the target image features, the method further includes: The target images at different positions of the area to be cleaned are obtained by shooting at different angles using various cameras provided on the cleaning robot; Perform image stitching processing on each target image to obtain a panoramic image; performing the preprocessing on the panoramic image; The target image features are extracted from the preprocessed panoramic image.

4. The method according to claim 1, characterized in that Extracting target image features from the preprocessed target image includes: Extracting color features from the preprocessed target image; Extracting texture features from the preprocessed target image; Extracting edge features from the preprocessed target image; The color feature, the texture feature and the edge feature are subjected to feature splicing processing to obtain the target image feature.

5. The method according to claim 1, characterized in that Determining the type of the floor material of the area to be cleaned according to the target image features includes: The target image features include color features, texture features and edge features; Determine a first probability distribution of the floor material of the area to be cleaned according to the color feature; Determine a second probability distribution of the floor material of the area to be cleaned according to the texture feature; Determining a third probability distribution of the floor material of the area to be cleaned according to the edge feature; The type of the floor material of the area to be cleaned is determined according to the first probability distribution, the second probability distribution, and the third probability distribution.

6. The method according to claim 1, characterized in that Determining the type of the floor material of the area to be cleaned according to the target image features includes: Before determining the type of the floor material of the area to be cleaned according to the target image features through the material recognition model, the material recognition model is trained: Acquire a training image, and preprocess the training image; extracting training image features from the preprocessed training image; Determining the category of the ground material corresponding to the training image according to the training image features by the material recognition model; The cross entropy loss function is used to calculate the loss between the label of the training image and the category of the corresponding ground material, and the model parameters of the material recognition model are optimized according to the loss.

7. The method according to claim 1, characterized in that Determining a cleaning method for the area to be cleaned based on the type of the floor material of the area to be cleaned includes: When the type of the floor material of the area to be cleaned is carpet, determining that the cleaning method of the area to be cleaned is the first method; When the floor material type of the area to be cleaned is ceramic tile, determining that the cleaning method of the area to be cleaned is the second method; When the type of the floor material of the area to be cleaned is wooden bricks, it is determined that the cleaning method of the area to be cleaned is the third method.

8. A cleaning robot control device, characterized in that: include: A shooting module is configured to shoot a target image of the area to be cleaned through a camera provided on the cleaning robot; A preprocessing module is configured to preprocess the target image, wherein the preprocessing includes: denoising, contrast enhancement and grayscale processing; An extraction module, configured to extract target image features from the preprocessed target image; A recognition module, configured to determine the type of the floor material of the area to be cleaned according to the target image features; A determination module is configured to determine a cleaning method of the area to be cleaned based on the type of the floor material of the area to be cleaned; The control module is configured to control the cleaning robot to clean the area to be cleaned according to the cleaning method.

9. An electronic device comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, characterized in that: When the processor executes the computer program, the steps of the method according to any one of claims 1 to 7 are implemented.

10. A computer-readable storage medium storing a computer program, characterized in that: When the computer program is executed by a processor, the steps of the method according to any one of claims 1 to 7 are implemented.

Images