Water depth measuring method and device and multi-limb robot

Abstract

The invention relates to the technical field of water depth measurement. The invention provides a water depth measurement method and device and a multi-limb robot, and the method comprises the following steps: collecting images and inclination angles of forelimbs of the multi-limb robot, and marking scales on the forelimbs; carrying out image preprocessing on the collected image; a water surface line is positioned according to the image after image preprocessing, and a graph of scales above the water surface line in the image is obtained; according to the graph of the scale above the water surface line, identifying the numerical value of the scale above the water surface line in the image; according to the numerical value of the scale above the water surface line in the image, obtaining the scale value on the water surface line through fitting calculation; and calculating the water depth of the position of the forelimb according to the inclination angle and the scale value of the forelimb. According to the invention, the water depth can be measured with high efficiency and high precision, the measurement cost is low, the multi-limb robot can immediately judge the safety condition according to the fording depth of the multi-limb robot, and safe and sustainable water depth measurement is realized.

Description

Technical Field

[0001] The present invention relates to the technical field of water depth measurement, and in particular to a water depth measurement method, a water depth measurement device and a multi-limb robot. Background Art

[0002] Among the current water depth measurement schemes, the two more common ones are water depth sensor measurement method and numerical simulation method.

[0003] Water depth sensors are more dependent on environmental conditions when measuring water depth. In complex waters, factors such as water quality, water flow velocity and water level fluctuations may lead to measurement errors. In addition, water depth sensors are expensive to use, especially when used on a large scale or when multiple sensors are required for simultaneous measurements.

[0004] The numerical simulation method for measuring tunnel water depth is overly dependent on accurate geological exploration data, hydrological data and other related parameters, and is highly complex and computationally intensive, requiring a large amount of computing resources and time. At the same time, the numerical simulation method is very difficult to verify. In actual on-site situations, it is often difficult to obtain a large amount of real water depth data to verify the accuracy of the model.

[0005] When using robots to measure water depth, most robots perform water depth measurement according to the mission route and are unable to judge their own wading depth and safety conditions, which can easily cause key parts of the robot to malfunction when encountering water. Summary of the invention

[0006] In order to solve the above-mentioned technical problems, the present invention provides a water depth measurement method, device and multi-limb robot, which can measure the water depth at the location of the forelimbs of the multi-limb robot with high efficiency and high precision and have low measurement cost. It helps the multi-limb robot to instantly judge the safety situation according to its own wading depth, avoid malfunctions of key parts of the robot when encountering water, and realize safe and sustainable water depth measurement.

[0007] The technical solution adopted by the present invention is as follows:

[0008] A water depth measurement method comprises the following steps: S1, collecting images of the forelimbs of a multi-limbed robot and the inclination angles of the forelimbs, wherein the forelimbs of the multi-limbed robot are marked with scales; S2, performing image preprocessing on the collected images of the forelimbs; S3, locating the water surface line according to the images of the forelimbs after image preprocessing, and obtaining a graphic of the scales above the water surface line in the image; S4, identifying the values ​​of the scales above the water surface line in the image according to the graphic of the scales above the water surface line; S5, obtaining the scale values ​​on the water surface line by fitting calculation according to the values ​​of the scales above the water surface line in the image; S6, calculating the water depth at the location of the forelimb according to the inclination angle of the forelimb and the scale values.

[0009] In addition, the water depth measurement method proposed above according to the present invention may also have the following additional technical features:

[0010] According to one embodiment of the present invention, step S2 specifically includes: binarizing the collected image of the forelimb to obtain a binary image of a first contrast; performing dilation and erosion operations on the binary image of the first contrast to obtain a binary image of a second contrast, wherein the second contrast is higher than the first contrast.

[0011] According to one embodiment of the present invention, in step S3, connected domain processing is used to locate the water surface line.

[0012] According to one embodiment of the present invention, in step S4, an improved VGG16 model is used to identify the numerical value of the scale above the water surface line in the image.

[0013] A water depth measuring device comprises: an acquisition module, the acquisition module is used to acquire images of forelimbs of a multi-limbed robot and the inclination angle of the forelimbs, wherein the forelimbs of the multi-limbed robot are marked with scales; a preprocessing module, the preprocessing module is used to perform image preprocessing on the acquired images of the forelimbs; a positioning module, the positioning module is used to locate the water surface line according to the images of the forelimbs after image preprocessing, and obtain a graphic of the scales above the water surface line in the image; an identification module, the identification module is used to identify the values ​​of the scales above the water surface line in the image according to the graphic of the scales above the water surface line; a first calculation module, the first calculation module is used to obtain the scale values ​​on the water surface line by fitting calculation according to the values ​​of the scales above the water surface line in the image; and a second calculation module, the second calculation module is used to calculate the water depth at the location of the forelimb according to the inclination angle of the forelimb and the scale values.

[0014] In addition, the water depth measuring device proposed above according to the present invention may also have the following additional technical features:

[0015] According to one embodiment of the present invention, the preprocessing module specifically includes: a binarization submodule, which is used to binarize the collected image of the forelimb to obtain a binary image of a first contrast; and a dilation and corrosion submodule, which is used to perform dilation and corrosion operations on the binary image to obtain a binary image of a second contrast, wherein the second contrast is higher than the first contrast.

[0016] According to an embodiment of the present invention, the positioning module uses connected domain processing to locate the water surface line.

[0017] According to one embodiment of the present invention, the recognition module uses an improved VGG16 model to recognize the numerical value of the scale above the water surface line in the image.

[0018] A multi-limb robot comprises: a trunk; forelimbs, which are coupled to the trunk and marked with scales; hind limbs, which are coupled to the trunk and provided with cameras, and the shooting range of the camera includes the scales marked on the forelimbs; and a water depth measuring device, which is used to measure the water depth at the location of the forelimbs of the multi-limb robot.

[0019] In addition, the multi-limbed robot proposed in the present invention may also have the following additional technical features:

[0020] According to one embodiment of the present invention, the forelimbs and the hind limbs both include legs and feet, the scales are marked on the legs of the forelimbs, the legs are made of rigid material, and the feet are made of flexible material.

[0021] Beneficial effects of the present invention:

[0022] The water depth measurement method of the present invention realizes water depth measurement by collecting images and inclination angles of forelimbs of a multi-limbed robot, performing image preprocessing on the images of the forelimbs, locating the water surface line, identifying the values ​​of the scales above the water surface line, calculating the scale values ​​on the water surface line, and calculating the water depth at the position of the forelimbs according to the scale values ​​and the inclination angles. The method can measure the water depth at the position of the forelimbs of the multi-limbed robot efficiently and accurately with low measurement cost, which helps the multi-limbed robot to instantly judge the safety situation according to its own wading depth, avoid malfunctions of key parts of the robot when encountering water, and realize safe and sustainable water depth measurement. BRIEF DESCRIPTION OF THE DRAWINGS

[0023] Figure 1 is a flow chart of a water depth measurement method according to an embodiment of the present invention;

[0024] Figure 2 A flowchart of image preprocessing according to a specific embodiment of the present invention;

[0025] Figure 3 A process diagram of an etching operation according to a specific embodiment of the present invention;

[0026] Figure 4 A process diagram of an expansion operation according to a specific embodiment of the present invention;

[0027] Figure 5 Schematic diagram of a water depth measuring device according to an embodiment of the present invention. DETAILED DESCRIPTION

[0028] The following will be combined with the drawings in the embodiments of the present invention to clearly and completely describe the technical solutions in the embodiments of the present invention. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present invention.

[0029] like Figure 1 As shown, the water depth measurement method of the embodiment of the present invention includes the following steps:

[0030] S1, collecting images of the forelimbs of the multi-limb robot and the tilt angle of the forelimbs, wherein the forelimbs of the multi-limb robot are marked with scales.

[0031] In one embodiment of the present invention, a camera or a video camera may be used to capture images of the forelimbs of a multi-limbed robot, and the images of the forelimbs may include scales marked on the forelimbs.

[0032] In one embodiment of the present invention, the collected images of the forelimbs of the multi-limbed robot may include historical images of the forelimbs of the multi-limbed robot in different environmental conditions, including but not limited to different lighting, water depths, angles, etc.

[0033] S2, performing image preprocessing on the collected forelimb images.

[0034] In one embodiment of the present invention, step S2 specifically includes:

[0035] S21, performing binarization processing on the collected image of the forelimb to obtain a binary image of a first contrast.

[0036] It should be noted that the binary image of the forelimb obtained by the binarization process is convenient for distinguishing the foreground and background in the image. After the binarization process, it can be identified that the foreground object in the image is the scale set on the forelimb.

[0037] In one embodiment of the present invention, the collected image of the forelimb is a grayscale image, and the collected image of the forelimb can be directly subjected to binarization processing.

[0038] In another embodiment of the present invention, the collected image of the forelimb is a color image, and the collected image of the forelimb needs to be grayscaled first to obtain a grayscale image, and then the grayscale image needs to be binarized.

[0039] S22, performing a dilation operation and an erosion operation on the binary image of the first contrast to obtain a binary image of a second contrast, wherein the second contrast is higher than the first contrast.

[0040] It should be noted that the dilation operation can fill the holes in the image, connect the similar elements in the image, and enlarge the foreground objects in the image. The erosion operation can reduce the foreground objects in the image and eliminate the noise in the image. Therefore, the contrast of the forelimb image can be effectively improved through the dilation operation and the erosion operation.

[0041] In one embodiment of the present invention, after filtering the binary image of the forelimb, dilation and erosion operations may be performed on the filtered image to further improve the contrast.

[0042] like Figure 2 As shown, in a specific embodiment of the present invention, step S2 includes: graying the collected image of the forelimb to obtain a gray image; binarizing the gray image to obtain a binary image of a first contrast; dilating the binary image of the first contrast to obtain a dilated binary image; corroding the dilated binary image to obtain a binary image of a second contrast; debinarizing the binary image of the second contrast to obtain a second gray image; gray-scale expansion of the second gray image to obtain an RGB image. The process diagram of the dilation operation and the corrosion operation is as shown in FIG. Figure 3 and Figure 4 shown.

[0043] like Figure 3 As shown, a cross expansion operator is used in the expansion operation, that is, the expansion neighborhood of the pixel point in the image is set to a cross-shaped area centered on the pixel; the pixel starting point is selected, and the pixel starting point can be randomly selected or specified according to the actual situation; the position of each pixel in the image is judged as the center of the expansion operator in turn, and the pixel value of the image pixel corresponding to each position in the cross-shaped area of ​​the expansion operator is judged. If there is any pixel whose pixel value is a foreground value, the pixel value of the central pixel of the expansion operator is set to the foreground value, that is, the pixel is set to the foreground, otherwise the pixel is set to the background.

[0044] like Figure 4 As shown, a cross corrosion operator is used in the corrosion operation, that is, the corrosion neighborhood of the pixel point in the image is set to a cross-shaped area centered on the pixel; the pixel starting point is selected, and the pixel starting point can be randomly selected or specified according to the actual situation; the position of each pixel in the image is judged as the center of the corrosion operator in turn, and the pixel value of the image pixel corresponding to each position in the cross-shaped area of ​​the corrosion operator is judged. If the pixel values ​​of all pixels are foreground values, the pixel value of the central pixel of the corrosion operator is set to the foreground value, that is, the pixel is set to the foreground, otherwise the pixel is set to the background.

[0045] S3, locating the water surface line according to the image of the forelimb after image preprocessing, and obtaining a graphic of the scale above the water surface line in the image.

[0046] In one embodiment of the present invention, connected domain processing may be used to locate the water surface line.

[0047] It should be noted that a connected domain generally refers to an image area composed of foreground pixels with the same pixel value and adjacent positions. Connected domain processing can find and mark each connected area in the image. Therefore, connected domain processing can be used to locate the water surface line in the forelimb image, thereby obtaining a graphic of the scale above the water surface line in the image.

[0048] S4, identifying the numerical value of the scale above the water surface line in the image according to the graphic of the scale above the water surface line.

[0049] In one embodiment of the present invention, an improved VGG16 model is used to identify the numerical value of the scale above the water surface line in the image.

[0050] It should be noted that since water depth measurement only needs to identify the values ​​of the scales above the water surface line in the image, the collected image contains fewer features, and the network model with too many convolutional layers is prone to overfitting. The improved VGG16 model reduces the convolutional layers on the basis of the original VGG16 model, which not only avoids the occurrence of overfitting, but also reduces the training parameters, which is conducive to obtaining an accurate and lightweight network model and obtaining more accurate recognition results, which is conducive to efficient and high-precision water depth measurement.

[0051] In one embodiment of the present invention, the collected historical images of the forelimbs of a multi-limbed robot in different environmental conditions can be cleaned, screened and annotated to form a training data set for training the improved VGG16 model.

[0052] S5, according to the value of the scale above the water surface line in the image, obtain the scale value on the water surface line through fitting calculation;

[0053] It should be noted that in step S4, multiple scale values ​​above the water surface line may be identified, so these values ​​cannot represent the scale values ​​on the water surface line. It is necessary to obtain the value closest to the water surface line through fitting calculation, that is, the scale value on the water surface line.

[0054] In one embodiment of the present invention, the scale value on the water surface line can be obtained by polynomial curve fitting calculation.

[0055] S6, calculating the water depth at the location of the forelimb according to the tilt angle of the forelimb and the scale value.

[0056] Specifically, the water depth at the location of the forelimbs can be calculated using the following formula:

[0057] y=f(x,θ)=xsinθ

[0058] Among them, y is the water depth at the location of the forelimb, and x is the scale value, which is the tilt angle of the forelimb.

[0059] It should be noted that the water depth measurement method of the embodiment of the present invention only needs to collect images of the forelimbs of the multi-limbed robot and the inclination angle of the forelimbs, without the aid of other complex components, and the measurement cost is low; by performing image preprocessing on the collected image, locating the water surface line, identifying the numerical value of the scale above the water surface line, calculating the scale value on the water surface line, and using a second calculation module to calculate the scale value on the water surface line and calculate the water depth at the position of the forelimb according to the scale value and the inclination angle to achieve water depth measurement, the water depth at the position of the forelimbs of the multi-limbed robot can be measured efficiently and accurately; the measured water depth can also represent the wading depth of the forelimbs of the multi-limbed robot, that is, the wading depth of the multi-limbed robot itself. The multi-limbed robot can judge and control according to its own wading depth to avoid malfunctions of key parts of the multi-limbed robot when encountering water, thereby achieving safe and sustainable water depth measurement.

[0060] According to the water depth measurement method of the embodiment of the present invention, the water depth measurement is realized by collecting images and inclination angles of the forelimbs of the multi-limbed robot, performing image preprocessing on the images of the forelimbs, locating the water surface line, identifying the values ​​of the scales above the water surface line, calculating the scale values ​​on the water surface line, and calculating the water depth at the position of the forelimbs according to the scale values ​​and the inclination angle. The water depth at the position of the forelimbs of the multi-limbed robot can be measured efficiently and accurately with low measurement cost, which helps the multi-limbed robot to instantly judge the safety situation according to its own wading depth, avoid malfunctions of key parts of the robot when encountering water, and realize safe and sustainable water depth measurement.

[0061] Corresponding to the water depth measurement method of the above embodiment, the present invention further provides a water depth measurement device.

[0062] like Figure 5 As shown, the water depth measuring device of the embodiment of the present invention includes an acquisition module 10, a preprocessing module 20, a positioning module 30, an identification module 40, a first calculation module 50 and a second calculation module 60. The acquisition module is used to acquire images of the forelimbs of the multi-limbed robot and the inclination angle of the forelimbs, wherein the forelimbs of the multi-limbed robot are marked with scales; the preprocessing module is used to perform image preprocessing on the acquired images of the forelimbs; the positioning module is used to locate the water surface line according to the image of the forelimbs after image preprocessing, and obtain the figure of the scale above the water surface line in the image; the identification module is used to identify the value of the scale above the water surface line in the image according to the figure of the scale above the water surface line; the first calculation module is used to obtain the scale value on the water surface line by fitting calculation according to the value of the scale above the water surface line in the image; the second calculation module is used to calculate the water depth at the location of the forelimb according to the inclination angle and scale value of the forelimb.

[0063] It should be noted that most of the current depth measurement devices contain a wide variety of components and require complex construction and installation methods, which makes the depth measurement devices difficult to move and occupies a large space. They can only realize depth measurement at fixed positions and cannot adapt to the mobility and lightness of multi-limbed robots. The acquisition module of the water depth measuring device in the embodiment of the present invention only needs to collect the image of the forelimbs of the multi-limbed robot and the inclination angle of the forelimbs, and there is no need to set up other complex components to collect other data. Therefore, the device has a simple configuration and a small size, is suitable for multi-limbed robots and has a low measurement cost; a preprocessing module, a positioning module, an identification module, and a first calculation module are used to perform image preprocessing on the collected image, locate the water surface line, identify the numerical value of the scale above the water surface line, and calculate the scale value on the water surface line; a second calculation module is used to calculate the scale value on the water surface line and calculate the water depth at the position of the forelimb according to the scale value and the inclination angle to achieve water depth measurement, which can measure the water depth at the position of the forelimbs of the multi-limbed robot efficiently and accurately; the measured water depth can also represent the wading depth of the forelimbs of the multi-limbed robot, that is, the wading depth of the multi-limbed robot itself. The multi-limbed robot can judge and control according to its own wading depth to avoid malfunctions of key parts of the multi-limbed robot when they encounter water, thereby achieving safe and sustainable water depth measurement.

[0064] In one embodiment of the present invention, a camera or a video camera may be used to capture images of the forelimbs of a multi-limbed robot, and the images of the forelimbs may include scales marked on the forelimbs.

[0065] In a specific embodiment of the present invention, the camera has IP67 level waterproof performance, so that it can work in a wading environment, and can use a network camera with a resolution of 1080p and a recording video frame rate of 30Hz; it can also be equipped with a micro wide-angle lens so that the camera's field of view can cover the scale of the multi-limbed robot's forelimbs and part of the water surface information; it can also be equipped with a low-light sensor so that the camera can provide high-quality images even in low-light conditions; the camera can also output RTSP video streams while shooting images, and use H.264 / H.265 video compression technology to transmit the video to the operator in real time through the local area network.

[0066] In one embodiment of the present invention, the images of the forelimbs of the multi-limbed robot collected by the collection module may include historical images of the forelimbs of the multi-limbed robot in different environmental conditions, including but not limited to different lighting, water depths, angles, etc.

[0067] In one embodiment of the present invention, the preprocessing module specifically includes: a binarization submodule and a dilation and corrosion submodule.

[0068] The binarization submodule is used to perform binarization processing on the collected forelimb image to obtain a binary image of a first contrast.

[0069] It should be noted that the binary image of the forelimb obtained by the binarization process is convenient for distinguishing the foreground and background in the image. After the binarization process, it can be identified that the foreground object in the image is the scale set on the forelimb.

[0070] In one embodiment of the present invention, the collected image of the forelimb is a grayscale image, and the preprocessing module may use a binarization submodule to directly perform binarization processing on the collected image of the forelimb.

[0071] In another embodiment of the present invention, the collected image of the forelimb is a color image, and the preprocessing module needs to first grayscale the collected image of the forelimb to obtain a grayscale image, and then use the binarization submodule to binarize the grayscale image.

[0072] The dilation and corrosion submodule is used to perform dilation and corrosion operations on the binary image of the first contrast to obtain a binary image of the second contrast, wherein the second contrast is higher than the first contrast.

[0073] It should be noted that the dilation operation can fill the holes in the image, connect the similar elements in the image, and enlarge the foreground objects in the image. The erosion operation can reduce the foreground objects in the image and eliminate the noise in the image. Therefore, the contrast of the forelimb image can be effectively improved through the dilation operation and the erosion operation.

[0074] In one embodiment of the present invention, after filtering the binary image of the forelimb, dilation and erosion operations may be performed on the filtered image to further improve the contrast.

[0075] In one embodiment of the present invention, the positioning module uses connected domain processing to locate the water surface line.

[0076] It should be noted that a connected domain generally refers to an image area composed of foreground pixels with the same pixel value and adjacent positions. Connected domain processing can find and mark each connected area in the image. Therefore, connected domain processing can be used to locate the water surface line in the forelimb image, thereby obtaining a graphic of the scale above the water surface line in the image.

[0077] In one embodiment of the present invention, the water surface line can be located by performing threshold processing, structural element corrosion and connected domain processing on the image of the forelimb after image preprocessing, thereby obtaining a graphic of the scale above the water surface line in the image.

[0078] In one embodiment of the present invention, the recognition module uses an improved VGG16 model to recognize the numerical value of the scale above the water surface line in the image.

[0079] It should be noted that since water depth measurement only needs to identify the values ​​of the scales above the water surface line in the image, the collected image contains fewer features, and the network model with too many convolutional layers is prone to overfitting. The improved VGG16 model reduces the convolutional layers on the basis of the original VGG16 model, which not only avoids the occurrence of overfitting, but also reduces the training parameters, which is conducive to obtaining an accurate and lightweight network model and obtaining more accurate recognition results, which is conducive to efficient and high-precision water depth measurement.

[0080] In one embodiment of the present invention, the collected historical images of the forelimbs of a multi-limbed robot in different environmental conditions can be cleaned, screened and annotated to form a training data set for training the improved VGG16 model.

[0081] Since the recognition module may recognize multiple scale values ​​above the water surface line, these values ​​cannot represent the scale value on the water surface line. The first calculation module is required to obtain the value closest to the water surface line through fitting calculation, that is, the scale value on the water surface line.

[0082] In one embodiment of the present invention, the first calculation module can obtain the scale value on the water surface line through polynomial curve fitting calculation.

[0083] In one embodiment of the present invention, the second calculation module may calculate the water depth at the location of the forelimb using the following formula:

[0084] y=f(x,θ)=xsinθ

[0085] Among them, y is the water depth at the location of the forelimb, and x is the scale value, which is the tilt angle of the forelimb.

[0086] The water depth measuring device according to the embodiment of the present invention realizes water depth measurement by collecting images and inclination angles of the forelimbs of the multi-limbed robot, performing image preprocessing on the images of the forelimbs, locating the water surface line, identifying the values ​​of the scales above the water surface line, calculating the scale values ​​on the water surface line, and calculating the water depth at the location of the forelimbs according to the scale values ​​and the inclination angles. The device is capable of measuring the water depth at the location of the forelimbs of the multi-limbed robot with high efficiency and high precision, is suitable for the multi-limbed robot and has low measurement cost, which helps the multi-limbed robot to instantly judge the safety situation according to its own wading depth and realize safe and sustainable water depth measurement.

[0087] Based on the water depth measuring device of the above embodiment, the present invention also proposes a multi-limbed robot.

[0088] The multi-limbed robot of the embodiment of the present invention comprises: a trunk, forelimbs, hind limbs and a water depth measuring device. The forelimbs are coupled to the trunk, and scales are marked on the forelimbs; the hind limbs are coupled to the trunk, and cameras are provided on the hind limbs, and the camera shooting range includes the scales marked on the forelimbs; the water depth measuring device is used to measure the water depth at the location of the forelimbs of the multi-limbed robot.

[0089] It should be noted that the water depth measuring device in the embodiment of the present invention only needs to collect images and inclination angles of the forelimbs of the multi-limbed robot, without the need to set up a large number of complex components. It can follow the movement of the multi-limbed robot to measure the water depth, can adapt to the mobility and portability of the multi-limbed robot, and has high flexibility. Since the measured water depth can also represent the wading depth of the forelimbs of the multi-limbed robot, that is, the wading depth of the multi-limbed robot itself, the multi-limbed robot can judge and control according to its own wading depth to avoid malfunctions of key parts of the multi-limbed robot when encountering water.

[0090] In one embodiment of the present invention, the forelimbs and hindlimbs each include a leg and a foot, the scale is marked on the leg of the forelimb, the leg is made of a rigid material, and the foot is made of a flexible material, so that the robot can move in uneven and complex terrain. The rigid material can be metal, carbon fiber, etc., and the flexible material can be rubber, flexible plastic, etc.

[0091] It should be noted that since the legs of the multi-limbed robot are made of rigid materials and the feet are made of flexible materials, the multi-limbed robot can walk and dynamically balance autonomously and move freely in areas such as tunnels without relying on external support facilities. It can adapt to different terrains and environments, flexibly perform water depth measurement, and monitor water surface images and scale changes in real time, so as to accurately measure the water depth of tunnels.

[0092] In one embodiment of the present invention, the scale may be engraved on the legs of the multi-limbed robot in the form of a physical ruler, and may be marked with a color that has a clear contrast with the legs of the multi-limbed robot.

[0093] In one embodiment of the present invention, the camera may be a network camera, and the multi-limbed robot may transmit the measured data and collected images to the central control system where the operator is located in real time through the network camera. When the water depth measured by the multi-limbed robot exceeds the preset depth, a danger alarm is issued, wherein the preset depth is the minimum water ingress depth of the key parts of the multi-limbed robot set according to the multi-limbed robot's own conditions. This enables timely feedback and analysis of the measured water depth, and the operator can timely understand the water depth through the central control system, so that the operator can re-confirm the state of the multi-limbed robot and perform auxiliary control, thereby improving the fault tolerance of the multi-limbed robot's danger alarm and avoiding failures of the key parts of the multi-limbed robot when they encounter water.

[0094] In one embodiment of the present invention, a communication control device may also be provided on the multi-limb robot. The communication control device includes a power distribution module, a command controller, a communication module and a driving controller. The power distribution module is provided with an STM32 and a serial port for communicating with the command controller and executing power distribution related commands; the communication module may be a router supporting 5G point-to-point communication, which connects the multi-limb robot with the operator's equipment and the background computer to the same network, and can realize real-time transmission of the video taken by the camera; the command controller and the driving controller can communicate through the serial port, and the command controller can control the multi-limb robot according to the instructions issued by the operator and send driving related instructions to the driving controller; the driving controller can communicate and control the driving of the multi-limb robot through the CAN port.

[0095] The multi-limbed robot according to the embodiments of the present invention measures water depth by collecting images and inclination angles of the forelimbs of the multi-limbed robot, performing image preprocessing on the images of the forelimbs, locating the water surface line, identifying the values ​​of the scales above the water surface line, calculating the scale values ​​on the water surface line, and calculating the water depth at the location of the forelimbs based on the scale values ​​and the inclination angles. The robot can efficiently and accurately measure the water depth at the location of the forelimbs of the multi-limbed robot with low measurement cost, can instantly judge the safety situation based on its own wading depth, avoid malfunctions of key parts of the robot due to encountering water, and achieve safe and sustainable water depth measurement.

[0096] In the description of the present invention, the terms "first" and "second" are used for descriptive purposes only and should not be understood as indicating or implying relative importance or implicitly indicating the number of the indicated technical features. Therefore, the features defined as "first" and "second" may explicitly or implicitly include one or more of the features. "Multiple" means two or more, unless otherwise clearly and specifically defined.

[0097] In the present invention, unless otherwise clearly specified and limited, the terms "installed", "connected", "connected", "fixed" and the like should be understood in a broad sense, for example, it can be a fixed connection, a detachable connection, or an integral connection; it can be a mechanical connection or an electrical connection; it can be a direct connection or an indirect connection through an intermediate medium, it can be the internal connection of two elements or the interaction relationship between two elements. For ordinary technicians in this field, the specific meanings of the above terms in the present invention can be understood according to specific circumstances.

[0098] In the present invention, unless otherwise clearly specified and limited, a first feature being "above" or "below" a second feature may mean that the first and second features are in direct contact, or the first and second features are in indirect contact through an intermediate medium. Moreover, a first feature being "above", "above" or "above" a second feature may mean that the first feature is directly above or obliquely above the second feature, or simply means that the first feature is higher in level than the second feature. A first feature being "below", "below" or "below" a second feature may mean that the first feature is directly below or obliquely below the second feature, or simply means that the first feature is lower in level than the second feature.

[0099] In the description of this specification, the description with reference to the terms "one embodiment", "some embodiments", "example", "specific example", or "some examples" etc. means that the specific features, structures, materials or characteristics described in conjunction with the embodiment or example are included in at least one embodiment or example of the present invention. In this specification, the schematic representations of the above terms do not necessarily refer to the same embodiment or example. Moreover, the specific features, structures, materials or characteristics described may be combined in any one or more embodiments or examples in a suitable manner. In addition, those skilled in the art may combine and combine the different embodiments or examples described in this specification and the features of the different embodiments or examples, unless they are contradictory.

[0100] Any process or method description in a flowchart or otherwise described herein may be understood to represent a module, segment or portion of code that includes one or more executable instructions for implementing the steps of a specific logical function or process, and the scope of the preferred embodiments of the present invention includes alternative implementations in which functions may not be performed in the order shown or discussed, including performing functions in a substantially simultaneous manner or in the reverse order depending on the functions involved, which should be understood by those skilled in the art to which the embodiments of the present invention belong.

[0101] The logic and / or steps represented in the flowchart or otherwise described herein, for example, can be considered as an ordered list of executable instructions for implementing logical functions, and can be embodied in any computer-readable medium for use by an instruction execution system, device or apparatus (such as a computer-based system, a system including a processor, or other system that can fetch instructions from an instruction execution system, device or apparatus and execute instructions), or in combination with these instruction execution systems, devices or apparatuses. For the purposes of this specification, a "computer-readable medium" can be any device that can contain, store, communicate, propagate or transmit a program for use by an instruction execution system, device or apparatus, or in combination with these instruction execution systems, devices or apparatuses. More specific examples of computer-readable media (a non-exhaustive list) include the following: an electrical connection with one or more wires (electronic devices), a portable computer disk box (magnetic device), a random access memory (RAM), a read-only memory (ROM), an erasable and programmable read-only memory (EPROM or flash memory), a fiber optic device, and a portable compact disk read-only memory (CDROM). In addition, the computer-readable medium may even be paper or other suitable medium on which the program is printed, since the program may be obtained electronically, for example, by optically scanning the paper or other medium and then editing, interpreting or processing in other suitable ways if necessary, and then stored in a computer memory.

[0102] It should be understood that the various parts of the present invention can be implemented by hardware, software, firmware or a combination thereof. In the above-mentioned embodiments, a plurality of steps or methods can be implemented by software or firmware stored in a memory and executed by a suitable instruction execution system. For example, if implemented by hardware, as in another embodiment, it can be implemented by any one of the following technologies known in the art or their combination: a discrete logic circuit having a logic gate circuit for implementing a logic function for a data signal, a dedicated integrated circuit having a suitable combination of logic gate circuits, a programmable gate array (PGA), a field programmable gate array (FPGA), etc.

[0103] A person skilled in the art may understand that all or part of the steps in the method for implementing the above-mentioned embodiment may be completed by instructing related hardware through a program, and the program may be stored in a computer-readable storage medium, which, when executed, includes one or a combination of the steps of the method embodiment.

[0104] In addition, each functional unit in each embodiment of the present invention may be integrated into a processing module, or each unit may exist physically separately, or two or more units may be integrated into one module. The above-mentioned integrated module may be implemented in the form of hardware or in the form of a software functional module. If the integrated module is implemented in the form of a software functional module and sold or used as an independent product, it may also be stored in a computer-readable storage medium.

[0105] Although the embodiments of the present invention have been shown and described above, it is to be understood that the above embodiments are exemplary and are not to be construed as limitations of the present invention. A person skilled in the art may change, modify, replace and vary the above embodiments within the scope of the present invention.

Claims

1. A water depth measurement method, characterized in that: The following steps are involved: S1, collecting images of forelimbs of a multi-limb robot and the tilt angle of the forelimbs, wherein the forelimbs of the multi-limb robot are marked with scales; S2, performing image preprocessing on the collected image of the forelimb; S3, locating the water surface line according to the image of the forelimb after image preprocessing, and obtaining a scale graphic above the water surface line in the image; S4, identifying the value of the scale above the water surface line in the image according to the graphic of the scale above the water surface line; S5, obtaining the scale value on the water surface line by fitting calculation according to the scale value above the water surface line in the image; S6, calculating the water depth at the location of the forelimb according to the inclination angle of the forelimb and the scale value.

2. The water depth measurement method according to claim 1, characterized in that: Step S2 specifically includes: Binarizing the collected image of the forelimb to obtain a binary image of a first contrast; Performing dilation and erosion operations on the binary image of the first contrast to obtain a binary image of a second contrast, wherein the second contrast is higher than the first contrast.

3. The water depth measurement method according to claim 1, characterized in that: In step S3, the water surface line is located by using connected domain processing.

4. The water depth measurement method according to claim 2, characterized in that: In step S4, the improved VGG16 model is used to identify the numerical value of the scale above the water surface line in the image.

5. A water depth measuring device, characterized in that: include: A collection module, the collection module is used to collect images of the forelimbs of the multi-limb robot and the tilt angle of the forelimbs, wherein the forelimbs of the multi-limb robot are marked with scales; A preprocessing module, the preprocessing module is used to perform image preprocessing on the collected image of the forelimb; A positioning module, the positioning module is used to locate the water surface line according to the image of the forelimb after image preprocessing, and obtain a scale figure above the water surface line in the image; A recognition module, the recognition module is used to recognize the value of the scale above the water surface line in the image according to the graphic of the scale above the water surface line; A first calculation module, the first calculation module is used to obtain the scale value on the water surface line through fitting calculation according to the value of the scale above the water surface line in the image; The second calculation module is used to calculate the water depth at the location of the forelimb according to the inclination angle of the forelimb and the scale value.

6. The water depth measuring device according to claim 5, characterized in that: The preprocessing module specifically includes: A binarization submodule, the binarization submodule is used to perform binarization processing on the collected image of the forelimb to obtain a binary image of a first contrast; The expansion and corrosion submodule is used to perform expansion and corrosion operations on the binary image to obtain a binary image with a second contrast, wherein the second contrast is higher than the first contrast.

7. The water depth measuring device according to claim 5, characterized in that: The positioning module uses connected domain processing to locate the water surface line.

8. The water depth measuring device according to claim 1, characterized in that: The recognition module uses an improved VGG16 model to recognize the numerical value of the scale above the water surface line in the image.

9. A multi-limbed robot, characterized in that: include: trunk; A forelimb, wherein the forelimb is coupled to the trunk and has a scale marked thereon; A hind limb, wherein the hind limb is coupled to the trunk, and the hind limb is provided with a camera, and the shooting range of the camera includes the scale marked on the forelimb; The water depth measuring device according to any one of claims 5-8, wherein the water depth measuring device is used to measure the water depth at the location of the forelimbs of the multi-limbed robot.

10. The multi-limbed robot according to claim 9, characterized in that: The forelimbs and the hindlimbs both include legs and feet, the scales are marked on the legs of the forelimbs, the legs are made of rigid materials, and the feet are made of flexible materials.

Images