Self-moving device and control method thereof

Abstract

The application provides a self-moving device and a control method thereof. After the self-moving device exits from a charging station, a to-be-recognized image is acquired, image recognition is performed on the to-be-recognized image, and installation information is acquired, the installation information being used for indicating whether the charging station is correctly installed. The application can accurately detect whether the charging station is correctly installed by performing image recognition on the to-be-recognized image acquired after the self-moving device exits from the charging station, and avoids the problem that the robot cannot return to the charging station due to incorrect installation of the charging station.

Description

Technical Field

[0001] This invention relates to the field of lawnmower robot technology, specifically to a self-moving device and its control method. Background Technology

[0002] The charging station for the lawnmower robot is used to provide the robot with power, enabling it to automatically return to charge after completing the lawnmower task, thereby achieving automated operation.

[0003] The charging station requires installation upon first use. Incorrect installation, such as placing it on uneven grass or obstructing the station or its signage, can prevent the robot from accurately returning to the charging station.

[0004] Therefore, ensuring that the charging station is installed correctly and that the robot can accurately return to the charging station is a problem that urgently needs to be solved. Summary of the Invention

[0005] In view of this, embodiments of the present invention aim to provide a self-moving device and its control method, which can accurately detect whether the charging station is correctly installed, and avoid the robot being unable to return to the charging station due to incorrect installation.

[0006] The objective of this application is achieved through the following technical solution:

[0007] In a first aspect, this application provides a control method for a self-moving device, the method comprising:

[0008] Control the self-moving device to exit from the charging station;

[0009] After the self-mobile device exits the self-charging station, the image acquisition module is used to acquire the image to be identified.

[0010] Image recognition is performed on the image to be identified to obtain installation information, which is used to indicate whether the charging station is installed correctly.

[0011] In some embodiments, the installation information includes first identification information, which indicates whether the charging station has been detected.

[0012] The control method further includes:

[0013] If the first identification information indicates that the charging station has not been identified, a first error message is issued, which indicates that the charging station has not been identified.

[0014] In some embodiments, the first identification information includes charging station coordinates, which are used to indicate the location of the charging station in the image to be identified;

[0015] The step of performing image recognition on the image to be recognized to obtain installation information includes:

[0016] Image recognition is performed on the image to be recognized to obtain the recognition box of the charging station, wherein the recognition box is a rectangular box that marks the charging station in the image to be recognized;

[0017] The coordinates of the charging station are determined based on a preset first coordinate system and the recognition frame.

[0018] In some embodiments, the charging station is provided with visual signage, and the installation information further includes second identification information indicating the visual signage in the image to be identified;

[0019] The control method further includes:

[0020] If the second identification information indicates that the visual identifier is not identified, a second error message is issued, which indicates that the visual identifier is obscured or that the charging station is installed abnormally.

[0021] In some embodiments, the visual identifier is a color strip, and there are two color strips, which are arranged horizontally and symmetrically on both sides of the charging station.

[0022] The step of performing image recognition on the image to be recognized to obtain installation information also includes:

[0023] The image to be identified is processed to obtain a processed image;

[0024] Based on the two color bands in the processed image, determine the center extension lines of the two color bands;

[0025] Based on a preset second coordinate system, the coordinates of the intersection point of the center extension line and the bottom edge of the image to be identified are determined. The intersection point coordinates are used to indicate whether the color band has deviated. The second coordinate system is a Cartesian coordinate system with the vertical central axis of the image to be identified as the vertical axis.

[0026] In some embodiments, the step of performing image recognition on the image to be recognized to obtain installation information further includes:

[0027] Determine the tilt angle of the center extension line in the second coordinate system, the tilt angle being used to indicate whether the color band has deviated.

[0028] In some embodiments, the step of performing image recognition on the image to be recognized to obtain installation information further includes:

[0029] Based on the second coordinate system, the distance between the two color bands and the bottom edge of the image to be identified is obtained, and the distance is used to indicate whether the color bands have deviated.

[0030] In some embodiments, the image processing of the image to be identified to obtain a processed image includes:

[0031] Convert the image to be identified into an HSV format image;

[0032] Information containing the visual identifier in the HSV format image is extracted according to a preset threshold to obtain a preset threshold binarized image;

[0033] The image to be identified is subjected to texture extraction to obtain a texture image;

[0034] The first binary image is obtained by fusing the pixels representing the visual identifier in the preset threshold binarized image and the texture image through a logical AND operation.

[0035] The HSV format image is binarized according to an adaptive threshold to obtain a second binarized image;

[0036] The processed image is obtained by fusing the pixels representing the visual identifier in the first binarized image and the second binarized image using a logical AND operation.

[0037] In some embodiments, the method further includes:

[0038] Based on the installation information, determine any abnormalities in the installation of the charging station;

[0039] The system outputs a prompt message based on the abnormal situation, and the prompt message is used to indicate the installation and adjustment direction of the charging station.

[0040] Secondly, this application provides a self-moving device, which includes a control module and an image acquisition module, wherein the control module is used to execute the control method of the self-moving device described above.

[0041] The self-moving device control method of this application acquires an image to be identified after the self-moving device exits the charging station, and performs image recognition on the image to obtain installation information. This installation information is used to indicate whether the charging station is correctly installed. By performing image recognition on the image to be identified acquired after the self-moving device exits the charging station, this application can accurately detect whether the charging station is correctly installed, avoiding the robot's inability to return to the charging station due to incorrect installation. Attached Figure Description

[0042] The above and other objects, features, and advantages of this application will become more apparent from the more detailed description of the embodiments of this application in conjunction with the accompanying drawings. The drawings are provided to further illustrate the embodiments of this application and form part of the specification. They are used together with the embodiments of this application to explain this application and do not constitute a limitation thereof. In the drawings, the same reference numerals generally represent the same components or steps.

[0043] Figure 1 The diagram shown is a flowchart illustrating a control method for a self-moving device according to an embodiment of this application.

[0044] Figure 2 The image shown is an example of an image to be identified according to an embodiment of this application;

[0045] Figure 3 The diagram shown is a flowchart of step S13 provided in an embodiment of this application;

[0046] Figure 4 The diagram shown is a schematic flowchart of an image processing procedure for an image to be recognized, according to an embodiment of this application.

[0047] Figure 5 The image shown is an example of a charging station installed in a recess according to an embodiment of this application;

[0048] Figure 6 The image shown is an example of a charging station installed on a protruding part according to an embodiment of this application. Detailed Implementation

[0049] The technical solutions of the embodiments of the present invention will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some embodiments of the present invention, and not all embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those skilled in the art without creative effort are within the scope of protection of the present invention.

[0050] Furthermore, in exemplary embodiments, since the same reference numerals denote the same components having the same structure or the same steps of the same method, if one embodiment has been described by way of example, then in other exemplary embodiments only structures or methods different from those described in the embodiment will be described.

[0051] Throughout the specification and claims, when a component is described as being “connected” to another component, that component may be “directly connected” to the other component or “electrically connected” to the other component via a third component. Furthermore, unless explicitly stated otherwise, the term “comprising” and its corresponding terms should be understood only to include components and not to exclude any other components.

[0052] To ensure proper operation, self-moving devices need to return to charging stations periodically. Therefore, it's crucial to ensure these devices can return smoothly. Taking a lawnmower as an example, the lawnmower typically remains at the charging station during installation. After installation, it leaves to complete its mowing task. When charging is needed, the lawnmower must accurately return to the charging station. Incorrect installation, such as on uneven ground (protrusions or depressions), will prevent it from returning to the charging station smoothly.

[0053] To accurately detect whether the charging station is correctly installed and ensure that the self-moving robot can return to the charging station, this application provides a control method for a self-moving device. The self-moving device is equipped with an image acquisition module. For example... Figure 1 As shown, the control method for the self-moving device includes:

[0054] Step S11: Control the self-moving device to exit from the charging station.

[0055] After the charging station is installed, when controlling the self-moving device to exit the charging station, a specific exit distance can be set, and then images are captured for recognition. This specific exit distance ensures that the self-moving device obtains a complete image of the charging station. Of course, the exit distance of the self-moving device can also be not limited; image acquisition can begin as long as the self-moving device completely exits the charging station.

[0056] Step S12: After exiting the self-charging station of the self-moving device, use the image acquisition module to acquire the image to be recognized.

[0057] After the self-mobile device exits the charging station, the image acquisition module on the self-mobile device can acquire an image to be recognized. The timing for acquiring the image can be either when the self-mobile device has traveled a certain distance from the charging station, or after the self-mobile device has completely exited the charging station. The image to be recognized can be the original image captured by the image acquisition module of the charging station, or an image captured by the image acquisition module and then preprocessed. For example, obtaining... Figure 2 The image to be identified is shown, which includes a charging station 20 and a color strip 200. Subsequent image recognition is performed based on this acquired image to determine whether the charging station is correctly installed.

[0058] Step S13: Perform image recognition on the image to be identified to obtain installation information, which is used to indicate whether the charging station is installed correctly.

[0059] Installation information indicating whether a charging station is correctly installed can be obtained by recognizing the image to be recognized, such as the recognition status of the charging station, the recognition status of relevant visual signs, and related location information. The image to be recognized is acquired by the image acquisition module on the self-moving device. If the charging station is installed abnormally, such as on uneven ground (protruding or concave), the relative position of the self-moving device to the charging station will also deviate after it leaves the charging station. As a result, the image to be recognized acquired by the image acquisition module on the self-moving device will differ from the image to be recognized under normal installation conditions. That is, the position of the charging station in the image to be recognized will be off, and there may even be cases where the charging station cannot be recognized.

[0060] In this embodiment, after the self-moving device exits the charging station, it acquires an image to be identified through the image acquisition module set in the self-moving device. Based on the image to be identified, it identifies installation information used to indicate whether the charging station is correctly installed. This can accurately detect whether the charging station is correctly installed and avoid the robot being unable to return to the charging station due to incorrect installation.

[0061] To accurately identify charging stations and subsequently determine whether they are correctly installed, in some embodiments of this application, the installation information includes first identification information, which indicates whether a charging station has been identified. The control method for the self-moving device further includes: if the first identification information indicates that a charging station has not been identified, issuing a first error message, which indicates that a charging station has not been identified.

[0062] If the charging station is installed correctly, it should be able to be identified from the image to be recognized. If not, it means the charging station is not installed correctly. It should be noted that the first identification information here can be a partial or complete outline of the charging station. If the outline of the charging station can be clearly identified from the image to be recognized, it means the charging station has been identified. If the first identification information indicates that the charging station has not been identified, a first error message is issued. This first error message can be indicated by an indicator light, an audible warning, or a direct voice broadcast; there are no specific limitations on this.

[0063] To more accurately identify charging stations, in some embodiments of this application, the first identification information includes charging station coordinates, which indicate the location of the charging station in the image to be identified. Thus, when performing image recognition on the image to be identified to obtain installation information, image recognition is performed on the image to be identified to obtain a bounding box for the charging station, which is a rectangular box marking the charging station in the image to be identified; based on a preset first coordinate system and the bounding box, the coordinates of the charging station are determined.

[0064] The preset first coordinate system is a coordinate system established based on the image to be recognized. Its origin can be a vertex in the image, another point on the edge of the image, or another point in the image; no specific restrictions are imposed here. After the recognition box of the charging station is recognized, the coordinates of the recognition box in the first coordinate system are determined, thus obtaining the coordinates of the charging station.

[0065] In some embodiments of this application, multiple images to be identified can be acquired. Image recognition is performed on each image to identify the bounding box of the charging station and its corresponding recognition accuracy. The bounding box with the highest recognition accuracy is selected as the recognition result. The coordinates of the bounding box in the corresponding image are obtained based on a preset first coordinate system to obtain the coordinates of the charging station. The coordinates of the charging station can be represented by the coordinates of the two diagonals of the rectangular bounding box, such as the coordinates of the upper left and lower right corners, or the coordinates of the lower left and upper right corners.

[0066] To accurately identify whether a charging station is correctly installed, it can also be achieved by identifying whether the visual identifiers in the image to be identified are abnormal. Therefore, in some embodiments of this application, the charging station is provided with visual identifiers, and the installation information also includes second identification information indicating the visual identifiers in the image to be identified. Based on this, the control method for the self-moving device further includes: if the second identification information indicates that the visual identifier has not been identified, issuing a second error message, the second error message being used to indicate that the visual identifier is obstructed or that the charging station is installed abnormally.

[0067] The visual signs are preferably signs that can represent important information about the charging station, and can be prominent signs placed on the charging station. If the charging station is installed correctly, these visual signs can be accurately identified. Otherwise, it indicates that the charging station is not installed correctly. Similarly, the second error message can be indicated by an indicator light, an audible warning, or a direct voice broadcast; there are no specific limitations.

[0068] In some embodiments of this application, the visual identifier is a color strip, and there are two color strips, which are horizontally and symmetrically arranged on both sides of the charging station. Using the color strip as a visual identifier, image recognition is performed on the image to be identified to obtain installation information; see details below. Figure 3 ,include:

[0069] Step S200: Perform image processing on the image to be recognized to obtain a processed image.

[0070] This process involves performing a series of binarization processes on the image to be recognized, resulting in a processed image that clearly displays the two color bands. In this embodiment, the binarization process can be performed based on a certain threshold, or multiple channels of the image to be recognized can be binarized separately, and then the binarized images can be fused.

[0071] Step S201: Based on the two color bands in the processed image, determine the center extension lines of the two color bands.

[0072] Based on the processed image, two color bands of the charging station are determined, and then the center extension line located between these two color bands is determined. Since the two color bands are horizontally symmetrically arranged on both sides of the charging station, after determining the two color bands, the same edge line of the two color bands can be taken (either the inner edge line or the outer edge line). Then, the center line located between these two edge lines is determined, and the center line is extended to obtain its extension line, i.e., the center extension line.

[0073] Step S202: Based on the preset second coordinate system, determine the coordinates of the intersection point of the center extension line and the bottom edge of the image to be recognized. The intersection point coordinates are used to indicate whether the color band has deviated. The second coordinate system is a Cartesian coordinate system with the vertical centerline of the image to be recognized as the vertical axis.

[0074] The preset second coordinate system is also based on the image to be recognized. This second coordinate system can be the same as or different from the first coordinate system. For example, both the first and second coordinate systems use the midpoint of the bottom edge of the image to be recognized as the origin, the vertical central axis of the image to be recognized as the ordinate, and the bottom edge of the image to be recognized as the abscissa. Alternatively, the second coordinate system can be the aforementioned coordinate system, and the first coordinate system can use the upper left corner of the image to be recognized as the origin, with the two edges of the image to be recognized as the abscissa and the ordinate, respectively.

[0075] The second preset coordinate system is independent of any specific image acquisition module. It is understandable that different image acquisition modules may have different hardware characteristics such as pixel size and sensor size, leading to different image sizes for the images to be recognized. The second preset coordinate system, with the vertical central axis of the image to be recognized as its ordinate, is independent of the specific hardware parameters of the image acquisition module, thus improving the applicability of the method.

[0076] In the second coordinate system, determine the coordinates of the intersection point between the center extension line and the bottom edge of the image to be recognized. If the coordinates of this intersection point are within a preset range of the midpoint of the bottom edge of the image to be recognized, it indicates that the two color bands are in the correct position and have not deviated. If the coordinates of this intersection point are outside the preset range, it indicates that the two color bands have deviated and the charging station has not been installed correctly. For example... Figure 2The intersection point A of the center extension line in the image and the bottom edge of the image to be identified is located near the center of the bottom edge of the image to be identified, indicating that the charging station is installed correctly.

[0077] It should be noted that the preset range can be set as needed and is related to the distance the self-moving device leaves the charging station when the image acquisition module acquires the image to be recognized. The larger this distance, the larger the preset range. This embodiment can control the self-moving device to move a fixed distance before acquiring the image to be recognized. Alternatively, the relationship between the distance the self-moving device leaves the charging station when the image acquisition module acquires the image to be recognized and the preset range can be pre-stored. When judging the coordinates of this intersection point, the preset range corresponding to the distance the self-moving device leaves the charging station when the image acquisition module acquires the image to be recognized is searched, and then a relevant judgment is made. This embodiment can accurately determine whether the two color bands have deviated by judging whether the coordinates of the intersection point of the center extension lines of the two color bands and the bottom edge of the image to be recognized exceed the preset range, and thus accurately determine whether the charging station has been correctly installed.

[0078] To further improve the accuracy of determining whether a charging station is correctly installed, in some embodiments of this application, image recognition is performed on the image to be identified to obtain installation information, and the method further includes: determining the tilt angle of the center extension line in the second coordinate system, wherein the tilt angle is used to indicate whether the color band has deviated.

[0079] The tilt angle can be the angle between the center extension line and the vertical line of the bottom edge of the image to be recognized, specifically the angle between the center extension line and the vertical axis in the second coordinate system. In this embodiment, the deviation of the color bands can be determined by whether the tilt angle is less than or equal to a preset angle. If the tilt angle is less than or equal to the preset angle, it indicates that the center extension line is close to the middle of the image to be recognized, the two color bands have not deviated, and the charging station is installed correctly. If the tilt angle is greater than the preset angle, it indicates that the two color bands have deviated, meaning the charging station is not installed correctly.

[0080] To further improve the accuracy of determining whether a charging station is correctly installed, in some embodiments of this application, image recognition is performed on the image to be identified to obtain installation information. This further includes: based on a second coordinate system, obtaining the distance between the two color bands and the bottom edge of the image to be identified; the distance is used to indicate whether the color bands have deviated. For example... Figure 2 The distance H between the color band indicated in the image and the bottom edge of the image to be identified.

[0081] The process involves comparing the distances between the two color strips and the bottom edge of the image to be recognized with a preset distance. If the distances are less than or equal to the preset distance, it indicates that the two color strips are not deviated and the charging station is installed correctly. If the distances are greater than the preset distance, it indicates that the two color strips have deviated, meaning the charging station is not installed correctly.

[0082] It should be noted that the preset distance can be set as needed and is related to the distance the mobile device travels from the charging station when the image acquisition module acquires the image to be recognized. The greater the distance the mobile device travels from the charging station when the image acquisition module acquires the image to be recognized, the greater the preset distance. Similarly, in this embodiment, the mobile device can be controlled to move a fixed distance before acquiring the image to be recognized. Alternatively, the relationship between the distance the mobile device travels from the charging station when the image acquisition module acquires the image to be recognized and the preset distance can be pre-stored. When judging the distance between the two color bands and the bottom edge of the image to be recognized, the preset distance corresponding to the distance the mobile device travels from the charging station when the image acquisition module acquires the image to be recognized is looked up, and then the relevant judgment is made.

[0083] In some embodiments of this application, see Figure 4 Image processing is performed on the image to be recognized to obtain a processed image, including:

[0084] Step 301: Convert the image to be recognized into an HSV format image.

[0085] Converting the image to be recognized into HSV format allows for better utilization of color information in subsequent processing. In the HSV color space, color information is decomposed into three dimensions: hue, saturation, and value. HSV format images can then be processed based on these different dimensions.

[0086] Step 302: Extract visual identifier information from the HSV format image according to the preset threshold to obtain the preset threshold binarized image.

[0087] The preset threshold, for example, indicates a specified range of values ​​for chroma, saturation, and brightness. This specified range is determined, for example, based on the corresponding parameters of the visual identifier. Pixels that do not meet the criteria are filtered out from the HSV format image according to the preset threshold to relatively highlight the visual identifier, generating a preset threshold binarized image. Specifically, based on the specified range of values ​​for chroma, saturation, and brightness, the pixel values ​​of pixels in the HSV format image whose chroma, saturation, and brightness all fall within the corresponding specified range are set to 1, while the pixel values ​​of pixels in the HSV format image whose chroma, saturation, and brightness are at least outside the corresponding specified range are set to 0, thus generating a preset threshold binarized image.

[0088] Step 303: Extract texture from the image to be recognized to obtain a texture image.

[0089] It should be noted that the execution order of steps 302 and 303 is not limited in the embodiments of this application; they can be performed simultaneously or sequentially.

[0090] Step 304: Perform a logical AND operation on the pair The pixels representing visual identifiers in the binarized image and the texture image with a preset threshold are fused to obtain the first binarized image.

[0091] In one possible implementation, pixels representing visual identifiers in the pre-threshold binarized image have a value of 1 (represented as white), while pixels representing visual identifiers in the texture image have a value of 0 (represented as black). A logical AND operation is performed on the portions of the pre-threshold binarized image where pixels have a value of 1 and the texture image where pixels have a value of 0 to obtain a first binarized image. In this first binarized image, the portions where pixels in the pre-threshold binarized image have a value of 1 and the texture image have a value of 0 have a corresponding pixel value of 1 (represented as white), while the remaining pixels have a value of 0 (represented as black). This fusion of color and texture information enhances the stability of color recognition, while the texture features significantly improve target identification capabilities in complex environments. The resulting first binarized image exhibits good adaptability to changes in lighting conditions, effectively recognizing visual identifiers even in scenes with drastically changing lighting conditions. Furthermore, the logical AND operation between the pre-threshold binarized image and the texture image ensures that the final image retains only the most relevant information, effectively eliminating interfering information and reducing the possibility of false detection.

[0092] Step 305: Binarize the HSV format image according to the adaptive threshold to obtain the second binarized image.

[0093] Images based on the HSV format retain only saturation information. In the three dimensions of the HSV color space, highly saturated colors appear more vibrant and pure, while low-saturation colors are closer to gray. Visual identifiers are often designed with bright colors for easy recognition; therefore, processing the saturation channel image can more accurately highlight these vibrant color features. Under complex lighting conditions, chroma and brightness can fluctuate significantly due to changes in light intensity, affecting color consistency and recognition stability. In contrast, focusing on the saturation channel can reduce the impact of these lighting changes to some extent. Even with changing lighting conditions, the saturation changes of the visual identifier and charging station in the image to be identified remain relatively stable. Further processing the saturation channel image using an adaptive thresholding method can more reliably distinguish the visual identifier.

[0094] In this embodiment, the `adaptiveThreshold` function from OpenCV is used to binarize the saturation channel image, resulting in a second binarized image. OpenCV is an open-source computer vision and machine learning software library containing numerous programming functions and algorithms for various computer vision tasks such as real-time image processing, video analysis, image recognition, and object detection. The `adaptiveThreshold` function is an image processing function provided by the OpenCV library used to implement adaptive threshold binarization. More specifically, a binarization threshold is determined for each pixel in the saturation channel image; the saturation channel image is then binarized using the binarization threshold corresponding to each pixel to obtain the second binarized image. By using the `adaptiveThreshold` function to binarize the saturation channel image, a threshold can be dynamically determined for each pixel based on the average brightness or weighted average brightness of the area surrounding each pixel in the saturation channel image, thereby achieving adaptive binarization. When there is uneven lighting in the image, the binarization threshold of each region will be automatically adjusted according to the actual brightness of the region, so that good contrast and edge definition can be obtained at different brightness levels, effectively dealing with uneven lighting and color gradation problems, and forming a clear black and white boundary between the visual signage and the background (such as a charging station or lawn).

[0095] This application utilizes saturation information for processing, focusing on color purity rather than brightness, reducing misidentification caused by changes in lighting conditions and improving the accuracy of visual identifier recognition. Secondly, by applying an adaptive thresholding method to the saturation channel, it can more effectively cope with interference from changes in lighting and objects with similar colors, significantly improving the robustness of visual identifier recognition. Simultaneously, applying the adaptive thresholding method to a single saturation channel image avoids complex global threshold calculations across the entire image or multiple channels, thereby improving the speed and efficiency of image processing to a certain extent.

[0096] Step 306: The pixels representing visual identifiers in the first and second binarized images are fused using a logical AND operation to obtain the processed image.

[0097] By fusing the pixels representing visual identifiers in the first and second binarized images using logical AND operations, erroneous pixels that might be introduced by applying the binarization image can be removed, enhancing the purity and reliability of target recognition. The resulting fused binarized image has a clearer and more defined outline of the visual identifiers. By combining the stability of a preset threshold with the flexibility of an adaptive threshold, the recognition accuracy of visual identifiers under different viewing angles is significantly improved. It can effectively distinguish visual identifiers even in strong light, shadow, or color interference conditions, giving the lawnmower robot stronger environmental adaptability. Furthermore, based on the fused binarized image, accurate visual identifiers can be obtained, thereby accurately determining whether the charging station is installed correctly.

[0098] The following example illustrates the control method for the self-moving device of this application. See [link to relevant documentation]. Figure 5 ,in, Figure 5 Image 'a' is a schematic diagram of the image to be identified, collected after the mobile device leaves the charging station. Figure 5 b is a schematic diagram of the installation information extracted based on the image to be identified. Figure 5 The red dot below the image to be recognized in b represents the intersection of the center extension line and the bottom edge of the image to be recognized. The extracted installation includes: (124 25 371250)0.933957, p 0.93, x0=-138, y0=334, y1=282, num=2. Among them, (124 25371 250) represents the coordinates of the upper left and lower right corners of the charging station recognition box in the first coordinate system, that is, the coordinates of the charging station; 0.933957(0.93) is the charging station recognition accuracy p; x0 is the coordinate of the intersection of the center extension line and the bottom edge of the image to be recognized in the second coordinate system; y0 and y1 represent the distances of the left and right color bands from the bottom edge of the image to be recognized, respectively; num is the number of color bands recognized. According to the installation information obtained, the charging station can be identified, but x0 = -138 is outside the preset range, indicating that the color band has deviated, which means that the charging station is installed abnormally. This abnormality is caused by the charging station being installed in a recessed area.

[0099] See Figure 6 ,in, Figure 6 Image 'a' is a schematic diagram of the image to be identified, collected after the mobile device leaves the charging station. Figure 6 b is a schematic diagram illustrating the installation information extracted from the image to be identified. The extracted installation information includes: (0 4 640183)0.925302, p = 0.93, x0 = 700, y0 = 372, y1 = 700, num = 1. See [link to documentation] for the meaning of each parameter. Figure 5The explanation is as follows: According to the installation information obtained, the charging station can be identified, but due to the height, the color band on the right side of the image is short and cannot be fully identified. That is, only one color band can be identified, indicating that the color band is deviated, which confirms that the charging station is installed abnormally. This abnormality is caused by the charging station being installed on a protruding part.

[0100] If an abnormality is detected in the installation of the charging station, adjustments to the installation are necessary. Therefore, in some embodiments of this application, the control method for the self-moving device further includes: determining the abnormality in the charging station installation based on installation information; and outputting a prompt message based on the abnormality, the prompt message indicating the direction for adjusting the charging station installation. For example, Figure 5 The system determines that the color ribbon has deviated based on the installation information and outputs a prompt message indicating that the charging station is installed in a recessed area and needs to be set up on flat ground. Figure 6 Based on the installation information, if the color strip is found to be obstructed, a corresponding prompt message is output indicating that the charging station is installed on a raised surface and needs to be set up on flat ground. In case of abnormalities, a prompt message is directly output indicating the direction of installation adjustment for the charging station, facilitating immediate adjustment and improving installation efficiency and accuracy.

[0101] This application also provides a self-moving device, including a control module and an image acquisition module, wherein the control module is used to execute the control method of the self-moving device described above.

[0102] The basic principles of this application have been described above with reference to specific embodiments. However, it should be noted that the advantages, benefits, and effects mentioned in this application are merely examples and not limitations, and should not be considered as essential features of each embodiment of this application. Furthermore, the specific details disclosed above are for illustrative and facilitative purposes only, and are not limitations. These details do not limit the application to the necessity of employing the aforementioned specific details for implementation.

[0103] The block diagrams of devices, apparatuses, devices, and systems involved in this application are merely illustrative examples and are not intended to require or imply that they must be connected, arranged, or configured in the manner shown in the block diagrams. As those skilled in the art will recognize, these devices, apparatuses, devices, and systems can be connected, arranged, and configured in any manner. Words such as “comprising,” “including,” “having,” etc., are open-ended terms meaning “including but not limited to,” and are used interchangeably with them. The terms “or” and “and” as used herein refer to the terms “and / or,” and are used interchangeably with them unless the context clearly indicates otherwise. The term “such as” as used herein refers to the phrase “such as but not limited to,” and is used interchangeably with it.

[0104] The embodiments described above are merely illustrative of several implementation methods outlined in this specification. While the descriptions are specific and detailed, they should not be construed as limiting the scope of the solutions provided in this specification. It should be noted that those skilled in the art can make various modifications and improvements without departing from the concept of this specification, and these modifications and improvements all fall within the scope of protection of this specification.

Claims

1. A control method for a self-moving device, wherein the self-moving device is equipped with an image acquisition module; characterized in that, The control method includes: Control the self-moving device to exit from the charging station; After the self-mobile device exits the self-charging station, the image acquisition module is used to acquire the image to be identified. Image recognition is performed on the image to be identified to obtain installation information, which is used to indicate whether the charging station is installed correctly.

2. The control method according to claim 1, characterized in that, The installation information includes first identification information, which indicates whether the charging station has been detected. The control method further includes: If the first identification information indicates that the charging station has not been identified, a first error message is issued, which indicates that the charging station has not been identified.

3. The control method according to claim 2, characterized in that, The first identification information includes charging station coordinates, which are used to indicate the position of the charging station in the image to be identified; The step of performing image recognition on the image to be recognized to obtain installation information includes: Image recognition is performed on the image to be recognized to obtain the recognition box of the charging station, wherein the recognition box is a rectangular box that marks the charging station in the image to be recognized; The coordinates of the charging station are determined based on a preset first coordinate system and the recognition frame.

4. The control method according to claim 3, characterized in that, The charging station is equipped with visual signs, and the installation information also includes second identification information indicating the visual signs in the image to be identified; The control method further includes: If the second identification information indicates that the visual identifier is not identified, a second error message is issued, which indicates that the visual identifier is obscured or that the charging station is installed abnormally.

5. The control method according to claim 4, characterized in that, The visual identifier is a color strip, and there are two color strips, which are arranged horizontally and symmetrically on both sides of the charging station. The step of performing image recognition on the image to be recognized to obtain installation information also includes: The image to be identified is processed to obtain a processed image; Based on the two color bands in the processed image, determine the center extension lines of the two color bands; Based on a preset second coordinate system, the coordinates of the intersection point of the center extension line and the bottom edge of the image to be identified are determined. The intersection point coordinates are used to indicate whether the color band has deviated. The second coordinate system is a Cartesian coordinate system with the vertical centerline of the image to be identified as the vertical axis.

6. The control method according to claim 5, characterized in that, The step of performing image recognition on the image to be recognized to obtain installation information also includes: Determine the tilt angle of the center extension line in the second coordinate system, the tilt angle being used to indicate whether the color band has deviated.

7. The control method according to claim 5, characterized in that, The step of performing image recognition on the image to be recognized to obtain installation information also includes: Based on the second coordinate system, the distance between the two color bands and the bottom edge of the image to be identified is obtained, and the distance is used to indicate whether the color bands have deviated.

8. The control method according to claim 5, characterized in that, The step of performing image processing on the image to be identified to obtain a processed image includes: Convert the image to be identified into an HSV format image; Information containing the visual identifier in the HSV format image is extracted according to a preset threshold to obtain a preset threshold binarized image; The image to be identified is subjected to texture extraction to obtain a texture image; The first binary image is obtained by fusing the pixels representing the visual identifier in the preset threshold binarized image and the texture image through a logical AND operation. The HSV format image is binarized according to an adaptive threshold to obtain a second binarized image; The processed image is obtained by fusing the pixels representing the visual identifier in the first binarized image and the second binarized image using a logical AND operation.

9. The control method according to claim 1, characterized in that, The method further includes: Based on the installation information, determine any abnormalities in the installation of the charging station; The system outputs a prompt message based on the abnormal situation, and the prompt message is used to indicate the installation and adjustment direction of the charging station.

10. A self-moving device, the self-moving device comprising a control module and an image acquisition module, characterized in that, The control module is used to execute the control method of the self-moving device according to any one of claims 1-9.

Images