Supporting surface obstacle recognition method and device and ground brake control method

Abstract

The invention relates to a supporting surface obstacle recognition method and device and a ground brake control method. A first region of interest in a first image of a ground brake supporting surface and a second region of interest in a second image of the ground brake supporting surface are determined, a target contour is determined according to contour information of a target object in the first region of interest, and a comparison region of which the gradient changes suddenly in the second region of interest is determined, so that the ground brake supporting surface is obtained according to the target contour and the comparison region. And determining an obstacle identification result of the ground brake supporting surface. According to the method, the first image and the second image are processed at the same time, the target contour where the obstacle possibly exists in the first image and the comparison area where the obstacle possibly exists in the second image are obtained, and the obstacle recognition result is determined by combining the target contour and the comparison area, so that the obstacle recognition result is more accurate; therefore, the flatness and the stability of the medical equipment are improved.

Description

Technical Field

[0001] The present application relates to the technical field of medical equipment, and in particular to a support surface obstacle recognition method, device and ground brake control method. Background Art

[0002] There may be obstacles such as sand, dust, cables, etc. on the floor of the operating room, and the bottom space of the cart with medical equipment is small, and the floor brake support surface at the bottom of the cart is not easy to observe. If the medical equipment is turned on without observing the ground conditions, and the floor brake switch button is directly pressed to make the floor brake contact the ground, it is likely that the medical equipment will tilt and the support will be unstable due to the existence of obstacles. Therefore, how to improve the flatness and stability of medical equipment is an urgent problem to be solved. Summary of the invention

[0003] Based on this, it is necessary to provide a support surface obstacle identification method, device and ground brake control method that can improve the flatness and stability of medical equipment in response to the above technical problems.

[0004] In a first aspect, the present application provides a method for identifying obstacles on a support surface, the method comprising:

[0005] Determine a first region of interest in the first image of the floor brake support surface and a second region of interest in the second image;

[0006] Determine the target contour according to the contour information of the target object in the first region of interest;

[0007] Determine a comparison region in which a gradient mutation occurs in the second region of interest;

[0008] The obstacle recognition result of the floor brake support surface is determined according to the target contour and the comparison area.

[0009] In one embodiment, the determining of the first region of interest in the first image and the second region of interest in the second image of the floor brake support surface comprises:

[0010] Determine a mask image of an area of ​​interest in a reference image of the floor brake support surface; the reference image is an image corresponding to the floor brake in a lowered state;

[0011] determining a first region of interest in the first image according to the mask image and the first image;

[0012] A second region of interest in the second image is determined according to the mask image and the second image.

[0013] In one embodiment, determining the target contour according to the contour information of the target object in the first region of interest includes:

[0014] Determining a contour size of the contour of the target object according to contour information of the contour of the target object in the first region of interest;

[0015] The contour corresponding to the contour size greater than or equal to the preset size is used as the target contour.

[0016] In one embodiment, determining the obstacle recognition result of the floor brake support surface according to the target contour and the comparison area includes:

[0017] If the degree of overlap between the coordinate information of the bounding box of the target contour and the coordinate information of the comparison area is greater than a preset degree of overlap, determining that the obstacle recognition result is that an obstacle exists;

[0018] If the degree of overlap between the coordinate information of the bounding box of the target contour and the coordinate information of the comparison area is not greater than a preset degree of overlap, it is determined that the obstacle recognition result is that there is no obstacle.

[0019] In one embodiment, the method further comprises:

[0020] Performing grayscale processing on the first region of interest to obtain a grayscale image corresponding to the first region of interest;

[0021] Binarizing the grayscale image to obtain a binary image corresponding to the first region of interest;

[0022] The target object in the binary image is identified to obtain contour information of the contour of the target object.

[0023] In one embodiment, the first image is a color image; the second image is a depth image.

[0024] In one embodiment, the method further comprises:

[0025] When the floor brake is in a retracted state, acquiring an initial image of the floor brake support surface;

[0026] Determine a second height corresponding to the first height in the initial image; the first height is the height of the ground brake from the ground brake support surface when the ground brake is in a retracted state;

[0027] determining whether the ground brake is in a target retracted state according to the second height;

[0028] If the ground brake is in the target retracted state, the initial image is used as the first image or the second image;

[0029] If the floor brake is not in the target retracted state, the floor brake is controlled to rise, and the image of the floor brake support surface after the floor brake rises is reacquired, and the image of the floor brake support surface after the floor brake rises is used as the initial image.

[0030] In a second aspect, the present application further provides a ground brake control method, the method further comprising:

[0031] Get the tilt angle of the cart;

[0032] When the inclination angle is less than the preset inclination angle, determining the obstacle recognition result according to any one of the methods provided in the first aspect above;

[0033] If the obstacle recognition result is that there is no obstacle, controlling the ground brake to descend;

[0034] If the obstacle recognition result is that an obstacle exists, the type of the obstacle is determined, and the ground brake is controlled according to the type of the obstacle.

[0035] In one embodiment, controlling the ground brake according to the type of the obstacle includes:

[0036] If the type of the obstacle is a cleanable type, the ground brake is controlled to be at the current position, and the obstacle is cleaned. After the obstacle is cleaned, the obstacle recognition result is re-acquired, and the ground brake is controlled to be lowered when the obstacle recognition result is that there is no obstacle.

[0037] If the type of the obstacle is an uncleanable type, the floor brake is controlled to be at the current position and a prompt message is output; the prompt message is used to prompt that there is an uncleanable type obstacle on the floor brake support surface.

[0038] In a second aspect, the present application further provides a support surface obstacle identification device, the device comprising:

[0039] A first determining module, used to determine a first region of interest in the first image and a second region of interest in the second image of the floor brake support surface;

[0040] A second determining module, configured to determine a target contour according to contour information of the target object in the first region of interest;

[0041] A third determination module is used to determine a comparison area in which the gradient of the second region of interest is not within a preset gradient range;

[0042] The fourth determination module is used to determine the obstacle recognition result of the floor brake support surface according to the target contour and the comparison area.

[0043] In a third aspect, the present application further provides a computer device, the computer device comprising a memory and a processor, the memory storing a computer program, and the processor implementing the following steps when executing the computer program:

[0044] Determine a first region of interest in the first image of the floor brake support surface and a second region of interest in the second image;

[0045] Determine the target contour according to the contour information of the target object in the first region of interest;

[0046] Determine a comparison region in the second region of interest where the gradient is not within a preset gradient range;

[0047] The obstacle recognition result of the floor brake support surface is determined according to the target contour and the comparison area.

[0048] In a fourth aspect, the present application further provides a computer-readable storage medium. The computer-readable storage medium stores a computer program, and when the computer program is executed by a processor, the following steps are implemented:

[0049] Determine a first region of interest in the first image of the floor brake support surface and a second region of interest in the second image;

[0050] Determine the target contour according to the contour information of the target object in the first region of interest;

[0051] Determine a comparison region in which a gradient mutation occurs in the second region of interest;

[0052] The obstacle recognition result of the floor brake support surface is determined according to the target contour and the comparison area.

[0053] In a fifth aspect, the present application further provides a computer program product, the computer program product comprising a computer program, which implements the following steps when executed by a processor:

[0054] Determine a first region of interest in the first image of the floor brake support surface and a second region of interest in the second image;

[0055] Determine the target contour according to the contour information of the target object in the first region of interest;

[0056] Determine a comparison region in which a gradient mutation occurs in the second region of interest;

[0057] The obstacle recognition result of the floor brake support surface is determined according to the target contour and the comparison area.

[0058] The above-mentioned support surface obstacle identification method, floor brake control method and device, by determining the first region of interest in the first image of the floor brake support surface and the second region of interest in the second image, determine the target contour according to the contour information of the target object in the first region of interest, and determine the comparison area where the gradient suddenly changes in the second region of interest, thereby determining the obstacle identification result of the floor brake support surface according to the target contour and the comparison area. In the present application, the first image and the second image are processed at the same time to obtain the target contour where obstacles may exist in the first image and the comparison area where obstacles may exist in the second image, and the obstacle identification result is determined by combining the target contour and the comparison area, so that the obstacle identification result is more accurate, thereby improving the flatness and stability of the medical device. BRIEF DESCRIPTION OF THE DRAWINGS

[0059] Figure 1 A schematic diagram of pressing down an obstacle during ground brake support in one embodiment;

[0060] Figure 2 A schematic diagram of another embodiment of the invention showing a ground brake supporting and pressing down an obstacle;

[0061] Figure 3 A diagram showing an application environment of a method for identifying obstacles on a supporting surface in an embodiment;

[0062] Figure 4 A diagram showing an application environment of a method for identifying obstacles on a supporting surface in an embodiment;

[0063] Figure 5 is a flow chart of a method for identifying obstacles on a supporting surface in one embodiment;

[0064] Figure 6 A schematic diagram of the structure of a camera and a ground brake in one embodiment;

[0065] Figure 7 is a schematic diagram of the structure of a camera and a ground brake in another embodiment;

[0066] Figure 8 It is a schematic diagram of a flow chart of a method for determining a first region of interest and a second region of interest in one embodiment;

[0067] Fig. 9 A schematic diagram of a flow chart of a method for determining a target profile in one embodiment;

[0068] Fig.10 is a flow chart of a method for identifying obstacles on a supporting surface in another embodiment;

[0069] Fig.11 is a flow chart of a method for identifying obstacles on a supporting surface in another embodiment;

[0070] Fig.12A schematic diagram of a flow chart of a ground brake control method in an embodiment;

[0071] Fig.13 A schematic flow chart of a ground brake control method in another embodiment;

[0072] Fig.14 is a flow chart of a method for identifying obstacles on a supporting surface in another embodiment;

[0073] Fig.15 FIG. 4 is a structural block diagram of a support surface obstacle identification device in one embodiment. DETAILED DESCRIPTION

[0074] In order to make the purpose, technical solution and advantages of the present application more clearly understood, the present application is further described in detail below in conjunction with the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are only used to explain the present application and are not used to limit the present application.

[0075] The floor of the operating room may have obstacles such as sand, dust, cables, etc., and the bottom space of the cart with medical equipment is small, and the floor brake support surface at the bottom of the cart is not easy to observe. Figure 1 and Figure 2 As shown, if the medical device is turned on without observing the ground conditions, and the ground brake switch button is directly pressed to make the ground brake contact the ground, it is very likely that the medical device will tilt and the support will be unstable due to the existence of obstacles. Therefore, the present application proposes a support surface obstacle recognition method, a ground brake control method and a device to solve the above technical problems.

[0076] The support surface obstacle recognition method provided in the embodiment of the present application can be applied to Figure 3 and Figure 4 In the application environment shown. Figure 3 is a schematic diagram of a cart in one embodiment, Figure 4 FIG. 1 is a block diagram of the internal structure of a computer device in one embodiment. Figure 3 As shown, a floor brake A and a floor brake B are installed on the cart, and a camera C and a camera D are installed at the center of the bottom of the cart. The camera C is used to photograph the floor brake A, the floor brake B, and the floor brake supporting surfaces corresponding to the floor brake A and the floor brake B to obtain a first image. The camera D is used to photograph the floor brake A, the floor brake B, and the floor brake supporting surfaces corresponding to the floor brake A and the floor brake B to obtain a second image. The first image and the second image are sent to Figure 4 The computer device shown in the figure identifies obstacles on the support surface according to the first image and the second image. The computer device may be a server, and its internal structure diagram may be as shown in FIG. Figure 4As shown. The computer device includes a processor, a memory and a network interface connected via a system bus. Among them, the processor of the computer device is used to provide computing and control capabilities. The memory of the computer device includes a non-volatile storage medium and an internal memory. The non-volatile storage medium stores an operating system, a computer program and a database. The internal memory provides an environment for the operation of the operating system and the computer program in the non-volatile storage medium. The database of the computer device is used to store support surface obstacle identification related data. The network interface of the computer device is used to communicate with an external terminal through a network connection. When the computer program is executed by the processor, a support surface obstacle identification method is implemented. The server can be implemented as an independent server or a server cluster composed of multiple servers. There is no restriction on the number of ground brakes on the cart in this application environment. Figure 3 Just an example.

[0077] Those skilled in the art will understand that Figure 3 The structure shown in the figure is only a block diagram of a part of the structure related to the solution of the present application, and does not constitute a limitation on the computer device to which the solution of the present application is applied. The specific computer device may include more or fewer components than those shown in the figure, or combine certain components, or have a different arrangement of components.

[0078] In one embodiment, Figure 5 As shown, a support surface obstacle recognition method is provided, and the method is applied to Figure 4 The computer device in the example is used to illustrate, including the following steps:

[0079] S501, determining a first region of interest in a first image and a second region of interest in a second image of a floor brake support surface.

[0080] Optionally, the first image is a color image, and the second image is a depth image. The first image may be a color image captured by an RGB camera installed at the bottom center of the cart, and the second image may be a depth image directly captured by a depth camera installed at the bottom center; or, two RGB cameras may be installed, and a depth image may be determined based on the images captured by the two RGB cameras. In order to reduce costs, only one depth camera may be installed on the cart, and the depth camera may be used to capture both the color image and the depth image. Figure 6 and Figure 7As shown, the ground brake and ground brake support surface corresponding to the RGB camera or depth camera must be within the optimal field of view of the RGB camera or depth camera. When the ground brake is in the raised state, the field of view of the RGB camera or depth camera should be able to see the complete ground brake support surface under the ground brake. H1 is the height of the ground brake from the ground when it is folded, H2 is the height of the RGB camera or depth camera lens center from the ground, H3 is the installation height of the ground brake, and D2 is the shortest distance from the vertical line from the center of the RGB camera or depth camera lens to the ground to the vertical line on the ground brake.

[0081] In this embodiment, a mask image of the floor brake supporting surface can be determined based on a reference image of the floor brake in the lowered state, and the mask image is applied to the first image and the second image respectively to obtain a first region of interest in the first image and a second region of interest in the second image.

[0082] In a possible implementation, based on a first reference image taken by the first camera in the ground brake released state and a second reference image taken by the second camera, a first position relationship of the region of interest in the first reference image and a second position relationship of the region of interest in the second reference image can be obtained respectively, and a first region of interest can be determined from the first image according to the first position relationship, and a second region of interest can be determined from the second image according to the second position relationship.

[0083] S502: Determine a target contour according to contour information of the target object in the first region of interest.

[0084] In this embodiment, the target object in the first region of interest is identified to obtain contour information of the target object. The contour size of the contour of the target object can be determined based on the contour information, and the contour larger than the preset contour size can be used as the target contour. All contours corresponding to the identified contour information can also be used as the target contour.

[0085] S503, determining a comparison region in the second region of interest where a gradient mutation occurs.

[0086] In this embodiment, the second region of interest is differentiated to obtain the gradient of each pixel in the second region of interest, and the gradient of each pixel may be different from that of its adjacent pixel. In the region where no mutation occurs, the gradient difference of mutually adjacent pixel points is small, and it can be considered that the gradient of the mutually adjacent pixel points has not undergone a mutation; if there is an obstacle in a certain region, at this time, the gradient of multiple pixel points at the edge of the obstacle will undergo a mutation. In short, the gradient difference of mutually adjacent pixel points at the edge is large, and when the gradient difference is greater than or equal to a preset threshold, it is considered that the gradient in the region has undergone a mutation, and the region corresponding to the multiple pixel points is the region where the mutation occurs. If the region undergoes a mutation, it means that there may be an obstacle in the region.

[0087] S504: Determine the obstacle recognition result of the ground brake support surface according to the target contour and the comparison area.

[0088] In this embodiment, the position of the target contour is matched with the position of the comparison area for identification. If the degree of overlap between the position of the target contour and the position of the comparison area is greater than a preset degree of overlap, the obstacle recognition result of the floor brake support surface is determined to be the presence of an obstacle. If the degree of overlap between the position of the target contour and the position of the comparison area is not greater than a preset degree of overlap, the obstacle recognition result of the floor brake support surface is determined to be the absence of an obstacle.

[0089] In a possible implementation, the target object in the target outline and the target object in the comparison area can be identified separately, and the first image recognition result of the target object in the target outline is compared with the second image recognition result of the target object in the comparison area. If the first image recognition result and the second image recognition result are the same target object, the obstacle recognition result of the ground brake support surface is determined to be the existence of an obstacle.

[0090] In the above-mentioned support surface obstacle identification method, by determining the first region of interest in the first image of the floor brake support surface and the second region of interest in the second image, the target contour is determined according to the contour information of the target object in the first region of interest, and the comparison area where the gradient suddenly changes in the second region of interest is determined, thereby determining the obstacle identification result of the floor brake support surface according to the target contour and the comparison area. In the present application, the first image and the second image are processed at the same time to obtain the target contour where obstacles may exist in the first image and the comparison area where obstacles may exist in the second image, and the obstacle identification result is determined by combining the target contour and the comparison area, so that the obstacle identification result is more accurate, thereby improving the flatness and stability of the medical device.

[0091] Figure 8 FIG. 1 is a flow chart of a method for determining a first region of interest and a second region of interest in one embodiment. Figure 8 As shown, the embodiment of the present application relates to a possible implementation method of how to determine a first region of interest in a first image and a second region of interest in a second image of a floor brake support surface, including the following steps:

[0092] S801, determining a mask image of an area of ​​interest in a reference image of a floor brake support surface; the reference image is an image corresponding to a floor brake in a lowered state.

[0093] In this embodiment, when the floor brake is in the lowered state, a lighting environment as good as possible is selected or set, a reference image of the floor brake support surface is obtained by using a camera, the reference image is sent to a computer device, and the reference image is segmented by using an image segmentation algorithm to obtain a region of interest in the reference image, i.e., the floor brake support surface. The region of interest is converted into a grayscale image, and a grayscale value in the grayscale image that is less than a preset value is set to 0 and a grayscale value that is greater than the preset value is set to 255 by using a binarization method, to obtain a mask image of the region of interest.

[0094] It should be noted that due to the different installation positions of the camera and the floor brake, if the camera is located in the center of the bottom of the cart and the floor brake is located at the four corners of the cart, the floor brake support surface itself is a circle of R+Δd, which appears as an ellipse in the reference image. The ellipse is segmented from the reference image to obtain the region of interest, and then the mask image of the region of interest is determined based on the region of interest, and the obtained mask image is saved in the database.

[0095] S802: Determine a first region of interest in the first image according to the mask image and the first image.

[0096] S803: Determine a second region of interest in the second image according to the mask image and the second image.

[0097] In this embodiment, the mask image of the region of interest is multiplied by the first image to obtain the first region of interest, and the mask image of the region of interest is multiplied by the second image to obtain the second region of interest.

[0098] In the embodiment of the present application, by determining the mask image of the region of interest in the reference image of the floor brake support surface, the first region of interest in the first image is determined according to the mask image and the first image, and the second region of interest in the second image is determined according to the mask image and the second image. In the present embodiment, the first region of interest and the second region of interest are obtained by using the mask image, and the implementation method is simple, which improves the efficiency of determining the first region of interest and the second region of interest, thereby improving the efficiency of supporting surface obstacle recognition.

[0099] Fig. 9 FIG. 1 is a flow chart of a method for determining a target contour in an embodiment. Fig. 9 As shown, the embodiment of the present application relates to a possible implementation method of how to determine the target contour according to the contour information of the target object in the first region of interest, including the following steps:

[0100] S901, determining a contour size of a contour of a target object according to contour information of a contour of a target object in a first region of interest.

[0101] In this embodiment, the edge detection algorithm can be used to obtain the outline of the target object in the first region of interest. Optionally, the edge detection algorithm may include: Roberts edge detection algorithm, Sobel edge detection algorithm, Prewitt edge detection algorithm, first-order and second-order derivatives, spatial filters, Canny edge detection algorithm, Marr-Hildreth edge detection algorithm and connected domain method.

[0102] The outline size of the outline of the target object can be obtained according to the coordinate information of the outline of the target object. Optionally, the outline size can be the outline area, the outline perimeter, texture information, etc.

[0103] S902: Take a contour corresponding to a contour size greater than or equal to a preset size as a target contour.

[0104] In this embodiment, due to the existence of contours corresponding to noise, contours with very small sizes are first filtered out using a preset size, and contours corresponding to contour sizes greater than or equal to the preset size are taken as target contours. When a target contour exists, it indicates that there may be obstacles in the first area of ​​interest, or there may be a larger light spot in the first area of ​​interest due to an uneven lighting environment.

[0105] In the embodiment of the present application, the contour size of the contour of the target object is determined based on the contour information of the contour of the target object in the first area of ​​interest, and the contour corresponding to the contour size greater than or equal to the preset size is used as the target contour, thereby avoiding the influence of noise, making the determined target contour more targeted, and reducing data processing, so that obstacles can be quickly identified.

[0106] In one embodiment, the obstacle recognition result of the floor brake supporting surface is determined based on the target contour and the comparison area, including: if the degree of overlap between the coordinate information of the bounding box of the target contour and the coordinate information of the comparison area is greater than a preset overlap degree, then the obstacle recognition result is determined to be the presence of an obstacle; if the degree of overlap between the coordinate information of the bounding box of the target contour and the coordinate information of the comparison area is not greater than a preset overlap degree, then the obstacle recognition result is determined to be the absence of an obstacle.

[0107] In this embodiment, a bounding box of the target contour is determined, for example, an AABB bounding box or an OBB bounding box. If the degree of overlap between the coordinate information of the bounding box and the coordinate information of the comparison area is greater than a preset degree of overlap, it is proved that an obstacle may exist at the same position in the area of ​​interest of the first image and the area of ​​interest of the second image, and the obstacle recognition result is determined to be the existence of an obstacle.

[0108] If the degree of overlap between the coordinate information of the bounding box of the target contour and the coordinate information of the comparison area is not greater than the preset degree of overlap, for example, the coordinate information of the bounding box is in the upper left corner of the first area of ​​interest, and the coordinate information of the comparison area is in the lower right corner of the second area of ​​interest, then the obstacle recognition result is determined to be that there is no obstacle.

[0109] In an embodiment of the present application, whether there is an obstacle is determined by comparing the relationship between the degree of overlap between the coordinate information of the bounding box of the target contour and the coordinate information of the comparison area and the preset degree of overlap, and the obstacle is identified by combining the first image and the second image, so that the identification of the obstacle is more accurate.

[0110] Fig.10 FIG. 1 is a flow chart of a method for identifying obstacles on a supporting surface in another embodiment. Fig.10 As shown, the following steps are included:

[0111] S1001, performing grayscale processing on a first region of interest to obtain a grayscale image corresponding to the first region of interest.

[0112] In this embodiment, the maximum pixel value among all R, G, and B pixel values ​​in the first region of interest may be extracted, and the R, G, and B pixel values ​​are all set to the maximum pixel value to obtain a grayscale image corresponding to the first region of interest.

[0113] In one possible implementation, different weight values ​​can be set for the three colors R, G, and B according to the sensitivity of the human eye to the three colors. For example, the human eye is most sensitive to green, so the weight of green can be set to the largest. A weighted summation process is performed based on the R, G, and B pixel values ​​at each point and the corresponding weights to obtain a grayscale image corresponding to the first region of interest.

[0114] S1002, binarizing the grayscale image to obtain a binarized image corresponding to the first region of interest.

[0115] In this embodiment, a bilateral filtering algorithm, a mean filtering algorithm, a median filtering algorithm, a Gaussian filtering algorithm, a local adaptive region threshold method, and the like can be used to perform binarization processing on the grayscale image and convert the grayscale image into a binary image.

[0116] S1003, identifying the target object in the binary image to obtain contour information of the target object.

[0117] In this embodiment, the target object is identified by using an image recognition algorithm to obtain contour information of the target object, for example, the contour in the binary image is obtained by using an edge detection algorithm based on a canny operator.

[0118] In the embodiment of the present application, grayscale processing is performed on the first region of interest to obtain a grayscale image corresponding to the first region of interest, and the grayscale image is binarized to obtain a binarized image corresponding to the first region of interest, thereby identifying the target in the binarized image and obtaining contour information of the contour of the target. The embodiment of the present application converts the first image into a grayscale image, obtains a binarized image based on the grayscale image, and obtains contour information of the contour of the target based on the binarized image. The grayscale processing and binarization processing reduce the information content of the first region of interest. When identifying the target, only the information in the binarized image needs to be used, thereby improving the calculation speed of the target identification.

[0119] Fig.11 FIG. 1 is a flow chart of a method for identifying obstacles on a supporting surface in another embodiment. Fig.11 As shown, the following steps are included:

[0120] S1101, when the floor brake is in a retracted state, obtaining an initial image of the floor brake supporting surface.

[0121] In this embodiment, when the ground brake is in the retracted state, the first camera and / or the second camera is used to capture the initial image.

[0122] S1102, determining a second height corresponding to the first height in the initial image; the first height is the height of the ground brake from the ground brake supporting surface when the ground brake is in a retracted state.

[0123] In this embodiment, the first height of the ground brake from the ground when the ground brake is in the retracted state can be obtained by using the motor encoder, the limit switch signal or the current signal. For example, the first height of the ground brake from the ground is obtained by using the motor encoder. When the motor rotates 10 degrees, the height of the ground brake changes by 5 cm. The state of the ground brake at the previous moment is the lowered state. If the current rotation angle of the motor is 30 degrees, the height of the ground brake is determined to increase by 15 cm according to the rotation angle.

[0124] The first height may be converted to a corresponding second height in the initial image according to a conversion relationship between the world coordinate system and the image coordinate system.

[0125] In one possible implementation, a mask image of the area of ​​interest in the initial image is obtained. Since the reference image is an image obtained when the ground brake is in a lowered state, the distance between the mask image of the area of ​​interest in the reference image in the above embodiment and the mask image of the area of ​​interest in the initial image is calculated to obtain a second height corresponding to the first height in the initial image.

[0126] S1103, determining whether the ground brake is in a target retracted state according to the second height.

[0127] In this embodiment, a third image of the floor brake supporting surface is obtained when the floor brake is in the target retracted state, that is, when the floor brake is retracted to the highest position, and a mask image of the region of interest in the third image is determined. According to the mask image of the region of interest in the reference image and the mask image of the region of interest in the third image in the above embodiment, the standard height between the floor brake and the floor brake supporting surface when the floor brake is in the highest position can be determined.

[0128] The second height is compared with the standard height. If the second height is equal to the standard height, the ground brake is in the target retracted state. If the second height is less than the standard height, the ground brake is not in the target retracted state.

[0129] S1104: If the ground brake is in the target retracted state, the initial image is used as the first image or the second image.

[0130] In this embodiment, when the ground brake is in the target retracted state, the field of view of the camera should be able to see the complete ground brake supporting surface under the ground brake, and the initial image is directly used as the first image or the second image.

[0131] S1105, if the ground brake is not in the target retracted state, the ground brake is controlled to rise, and the image of the ground brake support surface after the ground brake is raised is reacquired, and the image of the ground brake support surface after the ground brake is raised is used as the initial image.

[0132] In an embodiment of the present application, if the ground brake is not in the target retracted state, the ground brake is continued to be controlled to rise. After the ground brake rises, the image of the ground brake supporting surface after the ground brake rises is reacquired, and the image of the ground brake supporting surface after the ground brake rises is used as the initial image. The initial image is used to recalculate a new second height, and it is determined whether the ground brake is in the target retracted state based on the second height of the information, until the ground brake is in the target retracted state, and the first image or the second image is acquired.

[0133] In an embodiment of the present application, when the ground brake is in a retracted state, an initial image of the ground brake support surface is acquired, a second height corresponding to the first height in the initial image is determined, and whether the ground brake is in a target retracted state is determined according to the second height. If the ground brake is in a target retracted state, the initial image is used as the first image or the second image. If the ground brake is not in a target retracted state, the ground brake is controlled to rise, and an image of the ground brake support surface after the ground brake rises is reacquired, and the image of the ground brake support surface after the ground brake rises is used as the initial image. In this embodiment, the conditions for acquiring the first image and the second image are limited. When the ground brake is in a target retracted state, the first image and the second image are acquired, so that the acquired first image and the second image can both include the complete ground brake support surface, and the image quality is higher, thereby improving the accuracy of the obstacle recognition result.

[0134] Fig.12 FIG. 1 is a flow chart of a method for controlling a ground brake in an embodiment. Fig.12 As shown, the following steps are included:

[0135] S1201, obtaining the tilt angle of the cart.

[0136] In this embodiment, if Fig.13 As shown, a gyroscope can be set on the cart. After pressing the ground brake down button, the gyroscope is used to cyclically measure the current inclination angle of the cart, and the obtained inclination angle is sent to the computing computer device. For example, a gyroscope with an accuracy of 0.01° is selected.

[0137] In a possible implementation, the disc-shaped liquid level can also be fixed on the cart with one or more brackets and exposed to the camera's field of view. The bubble image in the disc-shaped liquid level is obtained by using the camera, the center point of the bubble image is calculated, and the inclination angle of the cart is obtained by comparing the center point with the scale on the liquid level. For example, a disc-shaped liquid level with an accuracy of 0.25° is set. Optionally, the disc-shaped liquid level can also be replaced by two columnar levels. The angle of the bubble offset of the liquid level is determined by the RBG camera.

[0138] The above gyroscope can also be combined with a disk-shaped liquid level / column-shaped level to obtain the tilt angle of the cart.

[0139] S1202: When the tilt angle is less than a preset tilt angle, determine an obstacle recognition result according to the method provided in any of the above embodiments.

[0140] In this embodiment, when the tilt angle is less than the preset tilt angle, for example, the preset tilt angle is 3°. When the tilt angle is less than 3°, according to the above Figure 5-Figure 6 The method provided in the embodiment obtains the obstacle recognition result.

[0141] S1203: If the obstacle recognition result is that there is no obstacle, control the ground brake to descend.

[0142] In this embodiment, if the obstacle recognition result is that there is no obstacle, the computer device accepts the control instruction triggered by the user and controls the ground brake to descend according to the control instruction; it can also automatically trigger the control instruction when the obstacle recognition result is that there is no obstacle, and control the ground brake to descend according to the control instruction.

[0143] S1204: If the obstacle recognition result indicates that an obstacle exists, the type of the obstacle is determined, and the ground brake is controlled according to the type of the obstacle.

[0144] In this embodiment, if the obstacle recognition result is that there is an obstacle, it proves that the floor brake support surface cannot support the floor brake, and the first image or the second image can be image recognized to obtain the type of obstacle, and the floor brake is controlled according to the type of obstacle. For example, the area of ​​the obstacle is recognized by the image recognition algorithm to determine the type of obstacle. If the area of ​​the obstacle is larger than the preset area, the type of obstacle is determined to be an uncleanable type.

[0145] Optionally, the types of obstacles include a cleanable type and an uncleanable type.

[0146] Furthermore, the ground brake is controlled according to the type of obstacle, including: if the type of obstacle is a cleanable type, the ground brake is controlled to be in the current position and the obstacle is cleaned, and after the obstacle is cleaned, the obstacle identification result is re-acquired until the obstacle identification result is that there is no obstacle, and the ground brake is controlled to descend; if the type of obstacle is an uncleanable type, the ground brake is controlled to be in the current position and a prompt message is output; the prompt message is used to prompt that there is an uncleanable obstacle on the support surface of the ground brake.

[0147] In this embodiment, if the type of obstacle is a cleanable type, the ground brake is controlled to be in the current position, and the cleaning device on the cart is controlled to clean the obstacle. Alternatively, in manual cleaning, after the obstacle is cleaned, the first image and the second image after cleaning are re-acquired, and the support surface obstacle recognition result is obtained based on the first image and the second image after cleaning, until the obstacle recognition result is that there is no obstacle, and the ground brake is controlled to descend.

[0148] In this embodiment, if the type of obstacle is an uncleanable type, the floor brake is controlled to be in the current position, and a prompt message is output to remind the user that there is an uncleanable obstacle on the floor brake support surface. The position of the cart can be moved, and the first image and the second image after the cart position is changed can be re-acquired, and the obstacle recognition result can be obtained based on the first image and the second image after the cart position is changed.

[0149] In the embodiment of the present application, by obtaining the tilt angle of the cart, when the tilt angle is less than the preset tilt angle, the obstacle recognition result is determined, if the obstacle recognition result is that there is no obstacle, the ground brake is controlled to descend, if the obstacle recognition result is that there is an obstacle, the type of obstacle is determined, and the ground brake is controlled according to the type of obstacle. In this embodiment, by obtaining the tilt angle, when the tilt angle is less than the preset tilt angle, the ground brake is controlled according to the obstacle recognition result, so that the control of the ground brake is more accurate, and the flatness and stability of the medical device are improved.

[0150] In one embodiment, Fig.14As shown, an obstacle recognition method is provided, comprising the following steps: determining a mask image of an area of ​​interest in a reference image, applying the mask image to a first image and a second image respectively to obtain a first area of ​​interest in the first image and a second area of ​​interest in the second image, performing grayscale processing on the first area of ​​interest to obtain a grayscale image, performing binarization processing on the grayscale image to obtain a binarized image, recognizing a target object in the binarized image to obtain contour information of a contour of the target object, obtaining a contour size according to the contour information, filtering smaller contours according to a relationship between the contour size and a preset contour size to obtain a target contour, determining a bounding box of the target contour, comparing a comparison area of ​​the second area of ​​interest with the bounding box, detecting whether a gradient in the bounding box of the target contour undergoes a sudden change, and obtaining an obstacle recognition result.

[0151] It should be understood that, although the steps in the flowcharts involved in the above embodiments are displayed in sequence according to the indication of the arrows, these steps are not necessarily executed in sequence according to the order indicated by the arrows. Unless there is a clear explanation in this article, the execution of these steps is not strictly limited in order, and these steps can be executed in other orders. Moreover, at least a part of the steps in the flowcharts involved in the above embodiments may include multiple steps or multiple stages, and these steps or stages are not necessarily executed at the same time, but can be executed at different times, and the execution order of these steps or stages is not necessarily carried out in sequence, but can be executed in turn or alternately with other steps or at least a part of the steps or stages in other steps.

[0152] Based on the same inventive concept, the embodiment of the present application also provides a support surface obstacle identification device for implementing the support surface obstacle identification method involved above. The implementation scheme for solving the problem provided by the device is similar to the implementation scheme recorded in the above method, so the specific limitations in one or more support surface obstacle identification device embodiments provided below can refer to the limitations of the support surface obstacle identification method above, and will not be repeated here.

[0153] In one embodiment, Fig.15 As shown, a support surface obstacle recognition device is provided, comprising: a first determination module 11, a second determination module 12, a third determination module 13 and a fourth determination module 14, wherein:

[0154] A first determining module 11, for determining a first region of interest in the first image and a second region of interest in the second image of the floor brake support surface;

[0155] A second determination module 12 is used to determine the target contour according to the contour information of the target object in the first region of interest;

[0156] A third determination module 13 is used to determine a comparison region where a gradient mutation occurs in the second region of interest;

[0157] The fourth determination module 14 is used to determine the obstacle recognition result of the ground brake support surface according to the target contour and the comparison area.

[0158] In one embodiment, the first determining module includes:

[0159] A first determining unit is used to determine a mask image of an area of ​​interest in a reference image of a floor brake support surface; the reference image is an image corresponding to a floor brake in a lowered state;

[0160] a second determining unit, configured to determine a first region of interest in the first image according to the mask image and the first image;

[0161] The third determining unit is configured to determine a second region of interest in the second image according to the mask image and the second image.

[0162] In one embodiment, the second determining module includes:

[0163] A fourth determining unit, configured to determine a contour size of the contour of the target object according to contour information of the contour of the target object in the first region of interest;

[0164] The fifth determining unit is configured to use a contour corresponding to a contour size greater than or equal to a preset size as a target contour.

[0165] In one embodiment, the fourth determining module includes:

[0166] a sixth determining unit, configured to determine that the obstacle recognition result is that an obstacle exists if the degree of overlap between the coordinate information of the bounding box of the target contour and the coordinate information of the comparison area is greater than a preset degree of overlap;

[0167] The seventh determination unit is configured to determine that the obstacle recognition result is that there is no obstacle if the degree of overlap between the coordinate information of the bounding box of the target contour and the coordinate information of the comparison area is not greater than a preset degree of overlap.

[0168] In one embodiment, the support surface obstacle identification device further includes:

[0169] A first processing module, configured to perform grayscale processing on the first region of interest to obtain a grayscale image corresponding to the first region of interest;

[0170] A second processing module is used to perform binarization processing on the grayscale image to obtain a binarized image corresponding to the first region of interest;

[0171] The recognition module is used to recognize the target object in the binary image and obtain the contour information of the target object.

[0172] In one embodiment, the first image is a color image; and the second image is a depth image.

[0173] In one embodiment, the support surface obstacle identification device further includes:

[0174] A first acquisition module, used for acquiring an initial image of a floor brake support surface when the floor brake is in a retracted state;

[0175] A fifth determination module is used to determine a second height corresponding to the first height in the initial image; the first height is the height of the ground brake from the ground brake support surface when the ground brake is in a retracted state;

[0176] a sixth determination module, configured to determine whether the ground brake is in a target retracted state according to the second height;

[0177] a seventh determination module, configured to use the initial image as the first image or the second image if the ground brake is in a target retracted state;

[0178] The second acquisition module is used for controlling the ground brake to rise if the ground brake is not in the target retracted state, re-acquiring the image of the ground brake support surface after the ground brake rises, and using the image of the ground brake support surface after the ground brake rises as the initial image.

[0179] In one embodiment, a ground brake control device is provided, the device comprising:

[0180] A third acquisition module is used to obtain the tilt angle of the cart;

[0181] An eighth determination module, configured to determine an obstacle recognition result according to the method provided in any one of the above embodiments when the inclination angle is less than a preset inclination angle;

[0182] A first control module, configured to control the ground brake to lower if the obstacle recognition result is that there is no obstacle;

[0183] The second control module is used to determine the type of obstacle if the obstacle recognition result is that there is an obstacle, and control the ground brake according to the type of obstacle.

[0184] In one embodiment, the second control module includes:

[0185] A first control unit is used for controlling the ground brake to be at a current position and clearing the obstacle if the obstacle is of a clearable type, and reacquiring the obstacle recognition result after the obstacle is cleared, and controlling the ground brake to be lowered when the obstacle recognition result indicates that no obstacle exists;

[0186] The second control unit is used to control the floor brake to be in the current position and output a prompt message if the type of the obstacle is an uncleanable type; the prompt message is used to prompt that there is an uncleanable type obstacle on the floor brake support surface.

[0187] Each module in the above-mentioned support surface obstacle identification device can be implemented in whole or in part by software, hardware, or a combination thereof. Each of the above-mentioned modules can be embedded in or independent of a processor in a computer device in the form of hardware, or can be stored in a memory in a computer device in the form of software, so that the processor can call and execute the operations corresponding to each of the above modules.

[0188] In one embodiment, a computer device is provided, including a memory and a processor, wherein a computer program is stored in the memory, and when the processor executes the computer program, the following steps are implemented:

[0189] Determine a first region of interest in the first image of the floor brake support surface and a second region of interest in the second image;

[0190] Determine the target contour according to the contour information of the target object in the first region of interest;

[0191] Determine the alignment region where the gradient in the second region of interest abruptly occurs;

[0192] According to the target contour and the comparison area, the obstacle recognition result of the ground brake support surface is determined.

[0193] In one embodiment, when the processor executes the computer program, the processor further implements the following steps:

[0194] Determine a mask image of an area of ​​interest in a reference image of the floor brake support surface; the reference image is an image corresponding to the floor brake in a lowered state;

[0195] Determine a first region of interest in the first image according to the mask image and the first image;

[0196] A second region of interest in the second image is determined according to the mask image and the second image.

[0197] In one embodiment, when the processor executes the computer program, the processor further implements the following steps:

[0198] Determining the outline size of the outline of the target object according to the outline information of the outline of the target object in the first region of interest;

[0199] The contour corresponding to the contour size greater than or equal to the preset size is taken as the target contour.

[0200] In one embodiment, when the processor executes the computer program, the processor further implements the following steps:

[0201] If the degree of overlap between the coordinate information of the bounding box of the target contour and the coordinate information of the comparison area is greater than a preset degree of overlap, then the obstacle recognition result is determined to be that an obstacle exists;

[0202] If the degree of overlap between the coordinate information of the bounding box of the target contour and the coordinate information of the comparison area is not greater than a preset degree of overlap, it is determined that the obstacle recognition result is that there is no obstacle.

[0203] In one embodiment, when the processor executes the computer program, the processor further implements the following steps:

[0204] Performing grayscale processing on the first region of interest to obtain a grayscale image corresponding to the first region of interest;

[0205] Binarizing the grayscale image to obtain a binary image corresponding to the first region of interest;

[0206] The target object in the binary image is identified to obtain the contour information of the target object.

[0207] In one embodiment, the first image is a color image; and the second image is a depth image.

[0208] In one embodiment, when the processor executes the computer program, the processor further implements the following steps:

[0209] When the floor brake is in a retracted state, acquiring an initial image of the floor brake support surface;

[0210] Determine a second height corresponding to the first height in the initial image; the first height is the height of the ground brake from the ground brake support surface when the ground brake is in a retracted state;

[0211] determining whether the ground brake is in a target retracted state according to the second height;

[0212] If the ground brake is in the target retracted state, the initial image is used as the first image or the second image;

[0213] If the ground brake is not in the target retracted state, the ground brake is controlled to rise, and the image of the ground brake support surface after the ground brake rises is reacquired, and the image of the ground brake support surface after the ground brake rises is used as the initial image.

[0214] In one embodiment, when the processor executes the computer program, the processor further implements the following steps:

[0215] Get the tilt angle of the cart;

[0216] When the tilt angle is less than the preset tilt angle, the obstacle recognition result is determined according to the method provided in any of the above embodiments;

[0217] If the obstacle recognition result is that there is no obstacle, the ground brake is controlled to descend;

[0218] If the obstacle recognition result is that there is an obstacle, the type of the obstacle is determined and the ground brake is controlled according to the type of the obstacle.

[0219] In one embodiment, when the processor executes the computer program, the processor further implements the following steps:

[0220] If the obstacle is of a clearable type, the ground brake is controlled to be at the current position and the obstacle is cleared. After the obstacle is cleared, the obstacle recognition result is obtained again until the obstacle recognition result is that there is no obstacle, and the ground brake is controlled to be lowered;

[0221] If the type of obstacle is an uncleanable type, the floor brake is controlled to be at the current position and a prompt message is output; the prompt message is used to prompt that there is an uncleanable type obstacle on the floor brake support surface.

[0222] In one embodiment, a computer readable storage medium is provided, on which a computer program is stored, and when the computer program is executed by a processor, the following steps are implemented:

[0223] Determine a first region of interest in the first image of the floor brake support surface and a second region of interest in the second image;

[0224] Determine the target contour according to the contour information of the target object in the first region of interest;

[0225] Determine the alignment region where the gradient in the second region of interest abruptly occurs;

[0226] According to the target contour and the comparison area, the obstacle recognition result of the ground brake support surface is determined.

[0227] In one embodiment, when the computer program is executed by a processor, the following steps are also implemented:

[0228] Determine a mask image of an area of ​​interest in a reference image of the floor brake support surface; the reference image is an image corresponding to the floor brake in a lowered state;

[0229] Determine a first region of interest in the first image according to the mask image and the first image;

[0230] A second region of interest in the second image is determined according to the mask image and the second image.

[0231] In one embodiment, when the computer program is executed by a processor, the following steps are also implemented:

[0232] Determining the outline size of the outline of the target object according to the outline information of the outline of the target object in the first region of interest;

[0233] The contour corresponding to the contour size greater than or equal to the preset size is taken as the target contour.

[0234] In one embodiment, when the computer program is executed by a processor, the following steps are also implemented:

[0235] If the degree of overlap between the coordinate information of the bounding box of the target contour and the coordinate information of the comparison area is greater than a preset degree of overlap, then the obstacle recognition result is determined to be that an obstacle exists;

[0236] If the degree of overlap between the coordinate information of the bounding box of the target contour and the coordinate information of the comparison area is not greater than a preset degree of overlap, it is determined that the obstacle recognition result is that there is no obstacle.

[0237] In one embodiment, when the computer program is executed by a processor, the following steps are also implemented:

[0238] Performing grayscale processing on the first region of interest to obtain a grayscale image corresponding to the first region of interest;

[0239] Binarizing the grayscale image to obtain a binary image corresponding to the first region of interest;

[0240] The target object in the binary image is identified to obtain the contour information of the target object.

[0241] In one embodiment, the first image is a color image; and the second image is a depth image.

[0242] In one embodiment, when the computer program is executed by a processor, the following steps are also implemented:

[0243] When the floor brake is in a retracted state, acquiring an initial image of the floor brake support surface;

[0244] Determine a second height corresponding to the first height in the initial image; the first height is the height of the ground brake from the ground brake support surface when the ground brake is in a retracted state;

[0245] determining whether the ground brake is in a target retracted state according to the second height;

[0246] If the ground brake is in the target retracted state, the initial image is used as the first image or the second image;

[0247] If the ground brake is not in the target retracted state, the ground brake is controlled to rise, and the image of the ground brake support surface after the ground brake rises is reacquired, and the image of the ground brake support surface after the ground brake rises is used as the initial image.

[0248] In one embodiment, when the computer program is executed by a processor, the following steps are also implemented:

[0249] Get the tilt angle of the cart;

[0250] When the tilt angle is less than the preset tilt angle, the obstacle recognition result is determined according to the method provided in any of the above embodiments;

[0251] If the obstacle recognition result is that there is no obstacle, the ground brake is controlled to descend;

[0252] If the obstacle recognition result is that there is an obstacle, the type of the obstacle is determined and the ground brake is controlled according to the type of the obstacle.

[0253] In one embodiment, when the computer program is executed by a processor, the following steps are also implemented:

[0254] If the obstacle is of a clearable type, the ground brake is controlled to be at the current position and the obstacle is cleared. After the obstacle is cleared, the obstacle recognition result is obtained again until the obstacle recognition result is that there is no obstacle, and the ground brake is controlled to be lowered;

[0255] If the type of obstacle is an uncleanable type, the floor brake is controlled to be at the current position and a prompt message is output; the prompt message is used to prompt that there is an uncleanable type obstacle on the floor brake support surface.

[0256] In one embodiment, a computer program product is provided, comprising a computer program, which, when executed by a processor, implements the following steps:

[0257] Determine a first region of interest in the first image of the floor brake support surface and a second region of interest in the second image;

[0258] Determine the target contour according to the contour information of the target object in the first region of interest;

[0259] Determine the alignment region where the gradient in the second region of interest abruptly occurs;

[0260] According to the target contour and the comparison area, the obstacle recognition result of the ground brake support surface is determined.

[0261] In one embodiment, when the computer program is executed by a processor, the following steps are also implemented:

[0262] Determine a mask image of an area of ​​interest in a reference image of the floor brake support surface; the reference image is an image corresponding to the floor brake in a lowered state;

[0263] Determine a first region of interest in the first image according to the mask image and the first image;

[0264] A second region of interest in the second image is determined according to the mask image and the second image.

[0265] In one embodiment, when the computer program is executed by a processor, the following steps are also implemented:

[0266] Determining the outline size of the outline of the target object according to the outline information of the outline of the target object in the first region of interest;

[0267] The contour corresponding to the contour size greater than or equal to the preset size is taken as the target contour.

[0268] In one embodiment, when the computer program is executed by a processor, the following steps are also implemented:

[0269] If the degree of overlap between the coordinate information of the bounding box of the target contour and the coordinate information of the comparison area is greater than a preset degree of overlap, then the obstacle recognition result is determined to be that an obstacle exists;

[0270] If the degree of overlap between the coordinate information of the bounding box of the target contour and the coordinate information of the comparison area is not greater than a preset degree of overlap, it is determined that the obstacle recognition result is that there is no obstacle.

[0271] In one embodiment, when the computer program is executed by a processor, the following steps are also implemented:

[0272] Performing grayscale processing on the first region of interest to obtain a grayscale image corresponding to the first region of interest;

[0273] Binarizing the grayscale image to obtain a binary image corresponding to the first region of interest;

[0274] The target object in the binary image is identified to obtain the contour information of the target object.

[0275] In one embodiment, the first image is a color image; and the second image is a depth image.

[0276] In one embodiment, when the computer program is executed by a processor, the following steps are also implemented:

[0277] When the floor brake is in a retracted state, acquiring an initial image of the floor brake support surface;

[0278] Determine a second height corresponding to the first height in the initial image; the first height is the height of the ground brake from the ground brake support surface when the ground brake is in a retracted state;

[0279] determining whether the ground brake is in a target retracted state according to the second height;

[0280] If the ground brake is in the target retracted state, the initial image is used as the first image or the second image;

[0281] If the ground brake is not in the target retracted state, the ground brake is controlled to rise, and the image of the ground brake support surface after the ground brake rises is reacquired, and the image of the ground brake support surface after the ground brake rises is used as the initial image.

[0282] In one embodiment, when the computer program is executed by a processor, the following steps are also implemented:

[0283] Get the tilt angle of the cart;

[0284] When the tilt angle is less than the preset tilt angle, the obstacle recognition result is determined according to the method provided in any of the above embodiments;

[0285] If the obstacle recognition result is that there is no obstacle, the ground brake is controlled to descend;

[0286] If the obstacle recognition result is that there is an obstacle, the type of the obstacle is determined and the ground brake is controlled according to the type of the obstacle.

[0287] In one embodiment, when the computer program is executed by a processor, the following steps are also implemented:

[0288] If the obstacle is of a clearable type, the ground brake is controlled to be at the current position and the obstacle is cleared. After the obstacle is cleared, the obstacle recognition result is obtained again until the obstacle recognition result is that there is no obstacle, and the ground brake is controlled to be lowered;

[0289] If the type of obstacle is an uncleanable type, the floor brake is controlled to be at the current position and a prompt message is output; the prompt message is used to prompt that there is an uncleanable type obstacle on the floor brake support surface.

[0290] It should be noted that the user information (including but not limited to user device information, user personal information, etc.) and data (including but not limited to data used for analysis, stored data, displayed data, etc.) involved in this application are all information and data authorized by the user or fully authorized by all parties.

[0291] Those skilled in the art can understand that all or part of the processes in the above-mentioned embodiment methods can be completed by instructing the relevant hardware through a computer program, and the computer program can be stored in a non-volatile computer-readable storage medium. When the computer program is executed, it can include the processes of the embodiments of the above-mentioned methods. Among them, any reference to the memory, database or other medium used in the embodiments provided in the present application can include at least one of non-volatile and volatile memory. Non-volatile memory can include read-only memory (ROM), magnetic tape, floppy disk, flash memory, optical memory, high-density embedded non-volatile memory, resistive random access memory (ReRAM), magnetoresistive random access memory (MRAM), ferroelectric random access memory (FRAM), phase change memory (PCM), graphene memory, etc. Volatile memory can include random access memory (RAM) or external cache memory, etc. As an illustration and not limitation, RAM can be in various forms, such as static random access memory (SRAM) or dynamic random access memory (DRAM). The database involved in each embodiment provided in this application may include at least one of a relational database and a non-relational database. Non-relational databases may include distributed databases based on blockchains, etc., but are not limited to this. The processor involved in each embodiment provided in this application may be a general-purpose processor, a central processing unit, a graphics processor, a digital signal processor, a programmable logic device, a data processing logic device based on quantum computing, etc., but are not limited to this.

[0292] The technical features of the above embodiments may be combined arbitrarily. To make the description concise, not all possible combinations of the technical features in the above embodiments are described. However, as long as there is no contradiction in the combination of these technical features, they should be considered to be within the scope of this specification.

[0293] The above-described embodiments only express several implementation methods of the present application, and the descriptions thereof are relatively specific and detailed, but they cannot be understood as limiting the scope of the present application. It should be pointed out that, for a person of ordinary skill in the art, several variations and improvements can be made without departing from the concept of the present application, and these all belong to the protection scope of the present application. Therefore, the protection scope of the present application shall be subject to the attached claims.

Claims

1. A method for identifying obstacles on a supporting surface, characterized in that: The method comprises: Determine a first region of interest in the first image of the floor brake support surface and a second region of interest in the second image; Determine the target contour according to the contour information of the target object in the first region of interest; Determine a comparison region in which a gradient mutation occurs in the second region of interest; The obstacle recognition result of the floor brake support surface is determined according to the target contour and the comparison area.

2. The method according to claim 1, characterized in that The determining of the first region of interest in the first image and the second region of interest in the second image of the floor brake support surface comprises: Determine a mask image of an area of ​​interest in a reference image of the floor brake support surface; the reference image is an image corresponding to the floor brake in a lowered state; determining a first region of interest in the first image according to the mask image and the first image; A second region of interest in the second image is determined according to the mask image and the second image.

3. The method according to claim 1, characterized in that The determining the target contour according to the contour information of the target object in the first region of interest includes: Determining a contour size of the contour of the target object according to contour information of the contour of the target object in the first region of interest; The contour corresponding to the contour size greater than or equal to the preset size is used as the target contour.

4. The method according to claim 1, characterized in that: The step of determining the obstacle recognition result of the floor brake support surface according to the target contour and the comparison area includes: If the degree of overlap between the coordinate information of the bounding box of the target contour and the coordinate information of the comparison area is greater than a preset degree of overlap, determining that the obstacle recognition result is that an obstacle exists; If the degree of overlap between the coordinate information of the bounding box of the target contour and the coordinate information of the comparison area is not greater than a preset degree of overlap, it is determined that the obstacle recognition result is that there is no obstacle.

5. The method according to claim 1, characterized in that The method further comprises: Performing grayscale processing on the first region of interest to obtain a grayscale image corresponding to the first region of interest; Binarizing the grayscale image to obtain a binary image corresponding to the first region of interest; The target object in the binary image is identified to obtain contour information of the contour of the target object.

6. The method according to claim 1, characterized in that The first image is a color image; the second image is a depth image.

7. The method according to claim 1, characterized in that The method further comprises: When the floor brake is in a retracted state, acquiring an initial image of the floor brake support surface; Determine a second height corresponding to the first height in the initial image; the first height is the height of the ground brake from the ground brake support surface when the ground brake is in a retracted state; determining whether the ground brake is in a target retracted state according to the second height; If the ground brake is in the target retracted state, the initial image is used as the first image or the second image; If the floor brake is not in the target retracted state, the floor brake is controlled to rise, and the image of the floor brake support surface after the floor brake rises is reacquired, and the image of the floor brake support surface after the floor brake rises is used as the initial image.

8. A ground brake control method, characterized in that: The method further comprises: Get the tilt angle of the cart; When the inclination angle is less than the preset inclination angle, determining the obstacle recognition result according to the method according to any one of claims 1 to 7; If the obstacle recognition result is that there is no obstacle, controlling the ground brake to descend; If the obstacle recognition result is that an obstacle exists, the type of the obstacle is determined, and the ground brake is controlled according to the type of the obstacle.

9. The method according to claim 8, characterized in that The controlling the ground brake according to the type of the obstacle comprises: If the type of the obstacle is a cleanable type, the ground brake is controlled to be at the current position, and the obstacle is cleaned. After the obstacle is cleaned, the obstacle recognition result is re-acquired, and the ground brake is controlled to be lowered when the obstacle recognition result is that there is no obstacle. If the type of the obstacle is an uncleanable type, the floor brake is controlled to be at the current position and a prompt message is output; the prompt message is used to prompt that there is an uncleanable type obstacle on the floor brake support surface.

10. A support surface obstacle identification device, characterized in that: The device comprises: A first determining module, used to determine a first region of interest in the first image and a second region of interest in the second image of the floor brake support surface; A second determining module, configured to determine a target contour according to contour information of the target object in the first region of interest; A third determination module is used to determine a comparison region where a gradient mutation occurs in the second region of interest; The fourth determination module is used to determine the obstacle recognition result of the floor brake support surface according to the target contour and the comparison area.

Images