A cable image-based model automatic generation device, method and equipment

Abstract

The application discloses a kind of based on cable image model automatic generation device, method and equipment, and the application belongs to electric power facility technical field.The device includes: image acquisition module, for the shooting image of target cable is collected by robot configured with camera;Position acquisition module is used to obtain the position information and attitude information of camera in the shooting image acquisition process;Physical parameter analysis module is used to carry out physical parameter analysis according to the pixel feature of the target cable in the shooting image and the position information and attitude information of the camera, and the physical parameter of the target cable is obtained;Model generation module is used to generate the space model of the target cable according to the physical parameter.The technical scheme, according to the position and attitude information of robot and the shooting image of target cable, the physical parameter of target cable is analyzed, and the space model of target cable can be automatically generated, to improve the work efficiency of cable entry.

Description

Technical Field

[0001] This application belongs to the field of power facility technology, specifically relating to an automatic model generation device, method and equipment based on cable images. Background Technology

[0002] Recording cable geometry, paths, and layouts helps staff understand the spatial location, direction, and intersections of cables more intuitively, facilitating visual analysis. It also allows for the identification and location of specific cables, aiding maintenance personnel in troubleshooting and maintenance operations. In conclusion, recording and storing cable information is crucial for the smooth progress of engineering projects and cable management.

[0003] However, the current manual method of cable entry into the network is not only complex and time-consuming, but also suffers from the difficulty of obtaining precise cable information due to the diverse shapes of cables, such as straight, angled, and coiled types. This impacts subsequent analysis and maintenance based on cable information. Therefore, how to automatically generate spatial models of cables from cable images and improve the efficiency of cable entry is a technical problem that urgently needs to be solved by those skilled in the art. Summary of the Invention

[0004] The purpose of this application is to provide an automatic model generation device, method, and equipment based on cable images. The aim is to enable a robot camera to automatically capture images of a target cable and generate a spatial model of the target cable based on the robot's position and posture information and the captured images, thereby improving the efficiency of cable data entry.

[0005] In a first aspect, embodiments of this application provide an automatic model generation device based on cable images, the device comprising:

[0006] An image acquisition module is used to capture images of the target cable using a robot equipped with a camera;

[0007] The pose acquisition module is used to acquire the position and pose information of the camera during the image acquisition process.

[0008] The physical parameter analysis module is used to analyze the physical parameters of the target cable based on the pixel features of the target cable in the captured image, as well as the position and attitude information of the camera.

[0009] The model generation module is used to generate a spatial model of the target cable based on the physical parameters.

[0010] Secondly, embodiments of this application provide a method for automatically generating models based on cable images, the method comprising:

[0011] Images of the target cable are captured by a robot equipped with a camera.

[0012] Acquire the position and orientation information of the camera during the image acquisition process;

[0013] Based on the pixel features of the target cable in the captured image, as well as the position and orientation information of the camera, physical parameters are analyzed to obtain the physical parameters of the target cable.

[0014] A spatial model of the target cable is generated based on the physical parameters.

[0015] Thirdly, embodiments of this application provide an electronic device including a processor, a memory, and a program or instructions stored in the memory and executable on the processor, wherein the program or instructions, when executed by the processor, implement the steps of the method described in the first aspect.

[0016] Fourthly, embodiments of this application provide a readable storage medium on which a program or instructions are stored, which, when executed by a processor, implement the steps of the method described in the first aspect.

[0017] Fifthly, embodiments of this application provide a chip, the chip including a processor and a communication interface, the communication interface being coupled to the processor, the processor being used to run programs or instructions to implement the method as described in the first aspect.

[0018] In this embodiment, an image acquisition module is used to acquire images of a target cable using a robot equipped with a camera; a pose acquisition module is used to acquire the position and pose information of the camera during the image acquisition process; a physical parameter analysis module is used to perform physical parameter analysis based on the pixel features of the target cable in the captured image, as well as the position and pose information of the camera, to obtain the physical parameters of the target cable; and a model generation module is used to generate a spatial model of the target cable based on the physical parameters. This automatic model generation device based on cable images, by analyzing the physical parameters of the target cable using the robot's position and pose information and the captured image of the target cable, can automatically generate a spatial model of the target cable, improving the efficiency of cable input. Attached Figure Description

[0019] Figure 1 This is a schematic diagram of the structure of the automatic model generation device based on cable images provided in Embodiment 1 of this application;

[0020] Figure 2 This is a schematic diagram of the structure of the automatic model generation device based on cable images provided in Embodiment 2 of this application;

[0021] Figure 3 This is a schematic diagram of the automatic model generation device based on cable images provided in Embodiment 3 of this application;

[0022] Figure 4 This is a flowchart illustrating the automatic model generation method based on cable images provided in Embodiment 4 of this application;

[0023] Figure 5 This is a schematic diagram of the structure of the electronic device provided in Embodiment 5 of this application. Detailed Implementation

[0024] To make the objectives, technical solutions, and advantages of this application clearer, specific embodiments of this application will be described in further detail below with reference to the accompanying drawings. It should be understood that the specific embodiments described herein are merely for explaining this application and not for limiting it. It should also be noted that, for ease of description, only the parts relevant to this application are shown in the drawings, not all of them. Before discussing exemplary embodiments in more detail, it should be mentioned that some exemplary embodiments are described as processes or methods depicted as flowcharts. Although the flowcharts describe operations (or steps) as sequential processes, many of these operations can be performed in parallel, concurrently, or simultaneously. Furthermore, the order of the operations can be rearranged. The process can be terminated when its operation is completed, but may also have additional steps not included in the drawings. The process can correspond to a method, function, procedure, subroutine, subprogram, etc.

[0025] The technical solutions of the embodiments of this application will be clearly described below with reference to the accompanying drawings. Obviously, the described embodiments are only some, not all, of the embodiments of this application. All other embodiments obtained by those skilled in the art based on the embodiments of this application are within the scope of protection of this application.

[0026] The terms "first," "second," etc., used in the specification and claims of this application are used to distinguish similar objects and not to describe a specific order or sequence. It should be understood that such use of data can be interchanged where appropriate so that embodiments of this application can be implemented in orders other than those illustrated or described herein, and the objects distinguished by "first," "second," etc., are generally of the same class and the number of objects is not limited; for example, a first object can be one or more. Furthermore, in the specification and claims, "and / or" indicates at least one of the connected objects, and the character " / " generally indicates that the preceding and following objects are in an "or" relationship.

[0027] The following description, in conjunction with the accompanying drawings, details the automatic model generation apparatus, method, and device based on cable images provided in this application through specific embodiments and application scenarios.

[0028] Example 1

[0029] Figure 1 This is a schematic diagram of the automatic model generation device based on cable images provided in Embodiment 1 of this application. Figure 1 As shown, the specific steps include the following:

[0030] Image acquisition module 110 is used to acquire images of the target cable by a robot equipped with a camera;

[0031] The pose acquisition module 120 is used to acquire the position and pose information of the camera during the image acquisition process.

[0032] The physical parameter analysis module 130 is used to analyze the physical parameters of the target cable based on the pixel features of the target cable in the captured image, as well as the position and attitude information of the camera.

[0033] The model generation module 140 is used to generate a spatial model of the target cable based on the physical parameters.

[0034] This application applies to scenarios where physical parameters are analyzed from images captured by a robot's camera, and a spatial model of the target cable is generated. Specifically, the analysis of physical parameters and the generation of the spatial model can be performed by a smart terminal device, facilitating the scientific management of cables by staff based on the generated cable spatial model.

[0035] Based on the above usage scenarios, it is understood that the executing entity of this application can be the smart terminal device, such as a desktop computer, laptop computer, mobile phone, tablet computer, and interactive multimedia device, etc., without further limitations.

[0036] The image acquisition module 110 may be composed of a computer microprocessor chip, etc., and is used to acquire images of the target cable by a robot equipped with a camera.

[0037] A robot can be a physical entity capable of autonomously performing tasks or jobs. It is designed to perform various tasks and is generally equipped with wheels or tracks to move freely in cabled environments. It can also be equipped with a GPS (Global Positioning System) receiver to obtain the robot's location in real time.

[0038] A cable can be a device used to transport electricity or signals, consisting of one or more conductors, insulation, sheath, and connectors.

[0039] To capture images of the target cable, a robot can be positioned to one side of the cable, perpendicular to it. The robot adjusts the camera's orientation until the target cable is clearly visible in the camera's view, at which point the camera captures the image.

[0040] In computers, images can be represented as arrays of pixels, each pixel containing color and brightness information. A camera is a common image acquisition device used to acquire real-time video or still image data. Cameras convert optical signals into digital image data using optical sensors and image processors. The basic process of a camera acquiring images includes: an optical sensor behind the camera lens converts light entering through the lens into electrical signals; a photosensitive element in the optical sensor detects the intensity and color of the light and converts it into voltage signals; an analog-to-digital converter converts the continuously changing analog voltage signals into digital form for further processing and storage; the image processor processes and enhances the digital signals, including color correction, contrast adjustment, and noise reduction, to improve image quality and clarity; the camera compresses the image data to reduce the space and bandwidth required for storage and transmission; and the processed and compressed image data is output to the computer's microprocessor chip via an interface (such as USB, HDMI, and Ethernet).

[0041] The pose acquisition module 120 may be composed of a computer microprocessor chip or the like, and is used to acquire the position and pose information of the camera during the image acquisition process.

[0042] Location information can be the coordinates of a camera's location mapped onto a cable laying map. A cable laying map can be map data used to represent the cable laying trajectory. Map data can be a digital representation of geospatial information. A planar coordinate system projects the curved surface of the Earth onto a plane for representation on a map. Planar coordinate systems are commonly used for mapping local areas, such as city maps and regional maps. Common planar coordinate systems include the UTM coordinate system and the Gauss-Kruger coordinate system.

[0043] One way to obtain location information is to use the robot's GPS receiver to receive signals from multiple GPS satellites. Each signal contains the time T when it was sent. Then, the distance from the inspection robot to each GPS satellite is calculated based on the difference between time T and the time of reception, thus obtaining the robot's location information.

[0044] The attitude information can include the height and angle of the camera mounted on the robot. The camera angle can include both horizontal and vertical angles. The horizontal angle can be expressed in degrees, with 0 degrees relative to true north and 0-360 degrees clockwise; the vertical angle can also be expressed in degrees, with 0 degrees relative to the direction perpendicular to the ground and 0-360 degrees clockwise.

[0045] Attitude information can be obtained by using a laser rangefinder to measure the distance between the camera and the ground, or by using a gyroscope to measure the camera's angle. A laser rangefinder is a device that uses a laser beam to measure the distance between a target and the rangefinder. It utilizes the characteristics of a laser beam to calculate the target distance by measuring the beam's propagation time or phase difference. A gyroscope is an instrument that uses the law of conservation of angular momentum to measure angular velocity and is commonly used in navigation, attitude control, and robotics.

[0046] The physical parameter analysis module 130 may be composed of a computer microprocessor chip, etc., and is used to analyze the physical parameters of the target cable based on the pixel features of the target cable in the captured image, as well as the position and attitude information of the camera, to obtain the physical parameters of the target cable.

[0047] Pixel features refer to the basic image features used in image processing and analysis. They are descriptions of the attributes, values, or statistical information of each pixel in an image. Common pixel features include grayscale values, color features, texture features, edge features, and scale features.

[0048] Grayscale values ​​can represent the brightness or grayscale level of each pixel in an image. They can be used for tasks such as image enhancement and edge detection. In a grayscale image, each pixel has only one grayscale value, typically within the range of 0 to 255. For color images, color features can be used to describe the color attributes of each pixel. Common color representation methods include the RGB (Red, Green, Blue) color space, the HSV (Hue, Saturation, Lightness) color space, and the Lab color space. Texture features describe the texture attributes of image regions, i.e., the local variation patterns between pixels. Common texture features include the Gray-Level Co-occurrence Matrix (GLCM), Local Binary Pattern (LBP), and Histogram of Oriented Gradients (HOG). Edge features represent the boundaries or edges between different regions in an image. Edge features can be extracted by calculating the gradient between pixels or by using edge detection algorithms (such as Sobel and Canny). Scale features describe the scale of different objects or structures in an image. Common scale features include pixel spacing and the width and height of objects.

[0049] Below is a simple example code demonstrating how to implement an edge detection algorithm using Python and the OpenCV library:

[0050] import cv2

[0051] #Read image

[0052] image=cv2.imread('input.jpg',cv2.IMREAD_GRAYSCALE)

[0053] #Canny Edge Detection

[0054] edges = cv2.Canny(image, 100, 200) # Adjust the threshold parameter to obtain the desired edge effect

[0055] # Display results

[0056] cv2.imshow('Original Image',image)

[0057] cv2.imshow('Edges',edges)

[0058] cv2.waitKey(0)

[0059] cv2.destroyAllWindows()

[0060] The code above uses the `cv2.Canny()` function from the OpenCV library for Canny edge detection. First, the `cv2.imread()` function reads the input image (assuming the image name is 'input.jpg' in this example). Then, the image is converted to grayscale (using the `cv2.IMREAD_GRAYSCALE` parameter) and the Canny edge detection algorithm is applied. Finally, the `cv2.imshow()` function displays the original image and the edge images, `cv2.waitKey(0)` waits for key input, and `cv2.destroyAllWindows()` closes all windows.

[0061] Physical parameters can include the target cable's spatial location information, diameter, direction, and curvature. One method for analyzing these physical parameters is to use the pixel features of the target cable in the captured image, along with the camera's position and orientation information, to deduce at least one of the target cable's spatial location information, diameter, direction, and curvature.

[0062] In this solution, optionally, the physical parameter parsing module is specifically used for:

[0063] Based on the pixel features of the target cable in the captured image, as well as the position and orientation information of the camera, at least one of the following is obtained: spatial position information, diameter, direction, and curvature of the target cable.

[0064] Spatial location information can be the coordinates (x, y, z) of the target cable mapped onto the cable laying map; diameter can be the line segment that intersects the edge of the cross-section of the target cable at the center of the cross-section, measured in centimeters (cm); direction can refer to the laying path or direction of the target cable. Based on the degree of curvature of the target cable, the direction can be divided into straight direction and curved direction. When observing the target cable in the radial direction, the direction of the target cable can be divided into horizontal direction, vertical direction, upward direction, and downward direction; curvature can be a physical quantity used to describe the degree of curvature of the target cable at a certain point, that is, the angle between the tangent of the target cable at that point and a small arc length of the target cable near that point. The greater the curvature, the greater the degree of curvature of the target cable near that point.

[0065] The analysis method can involve inputting the pixel features of the target cable in the captured image, the camera's internal parameters, and the camera's position and orientation information into a neural network model. The neural network model then calculates and provides feedback on the target cable's spatial position, diameter, orientation, and curvature. The camera's internal parameters can include focal length and optical center; the neural network can be a computational model based on the structure and function of biological neurons, processing and analyzing data through connections and information transmission between multiple nodes. Specific nodes can include spatial position information, diameter, orientation, curvature, and pixel features.

[0066] The advantage of this technical solution is that, by analyzing the pixel features of the target cable in the captured image, as well as the camera's position and orientation information, at least one of the target cable's spatial location, diameter, direction, and curvature can be obtained. This provides a data foundation for generating a spatial model of the target cable. Understandably, the more physical parameters obtained through analysis, the higher the accuracy of the generated spatial model of the target cable.

[0067] The model generation module 140 may be composed of a computer microprocessor chip or the like, and is used to generate a spatial model of the target cable based on the physical parameters.

[0068] A spatial model can be a three-dimensional image of the target cable. A three-dimensional image can be a computer-generated image with a sense of depth and realism, and can present the appearance and structural features of a three-dimensional object from different angles.

[0069] The spatial model can be generated automatically by a computer by performing the following steps:

[0070] Open a 3D modeling software, such as Blender, 3ds Max, and Maya;

[0071] Use the tools in the software to create the basic shape of the cable. You can use a cylinder or a tube to represent the main body of the cable and determine the appropriate size based on the diameter of the cable.

[0072] Based on the spatial location information of the cable, the cable model is moved and positioned in 3D modeling software;

[0073] Based on the cable's direction and curvature, the cable's shape can be adjusted in 3D modeling software. Curve tools or deformation tools can be used to simulate the cable's direction and curvature.

[0074] Optionally, in this solution, the device may further include:

[0075] The manual calibration module is used to generate manual calibration information when the captured image includes at least two laid cables, so as to determine the target cable for which a spatial model needs to be generated based on the calibration object of the collected calibration operation.

[0076] Manual calibration information can be a message prompting workers to manually calibrate the target cable. This information can be generated by a pop-up manual calibration window on a smart terminal device's display screen. The window shows images captured by the robot's camera and classification marks for at least two laid cables based on pixel characteristics.

[0077] The calibration process can be completed by the staff selecting the target cable from at least two laid cables and clicking the classification mark of the target cable.

[0078] The advantage of this technical solution is that by identifying the target cable for which a spatial model needs to be generated when the captured image includes at least two laid cables, non-target cables in the captured image can be avoided from interfering with the generation of the spatial model of the target cable, thereby improving the accuracy of the generated spatial model.

[0079] In this application example, an image acquisition module is used to acquire images of the target cable using a robot equipped with a camera; a pose acquisition module is used to acquire the position and pose information of the camera during the image acquisition process; a physical parameter analysis module is used to perform physical parameter analysis based on the pixel features of the target cable in the captured image, as well as the position and pose information of the camera, to obtain the physical parameters of the target cable; and a model generation module is used to generate a spatial model of the target cable based on the physical parameters. This technical solution, by analyzing the physical parameters of the target cable based on the robot's position and pose information and the captured image of the target cable, can automatically generate a spatial model of the target cable, improving the efficiency of cable input.

[0080] Example 2

[0081] Figure 2 This is a schematic diagram of the automatic model generation device based on cable images provided in Embodiment 2 of this application. This solution makes further improvements based on the above embodiments, specifically: the device further includes: an edge position determination module, used to determine the spatial position of the cable on both sides of the currently captured image based on the pixel features of the target cable in the captured image, as well as the position and orientation information of the camera; and a shooting prompt module, used to generate shooting prompt information based on the spatial position of the cable on both sides of the image.

[0082] like Figure 2 As shown, the device includes:

[0083] Image acquisition module 210 is used to acquire images of the target cable by a robot equipped with a camera;

[0084] The pose acquisition module 220 is used to acquire the position and pose information of the camera during the image acquisition process.

[0085] The physical parameter analysis module 230 is used to analyze the physical parameters of the target cable based on the pixel features of the target cable in the captured image, as well as the position and attitude information of the camera.

[0086] Model generation module 240 is used to generate a spatial model of the target cable based on the physical parameters;

[0087] Edge position determination module 250 is used to determine the spatial position of the cable on both sides of the captured image based on the pixel features of the target cable in the captured image, as well as the position and orientation information of the camera.

[0088] The shooting prompt module 260 is used to generate shooting prompt information based on the spatial position of the cables on both sides of the image.

[0089] One method to determine the spatial location of a cable is to obtain the pixel positions of the cable at the edges of the captured image in the pixel coordinate system (i.e., coordinates on the image), convert the pixel positions to coordinates in the camera coordinate system based on the camera's internal parameters, and finally convert the coordinates in the camera coordinate system to coordinates in the cable laying map (i.e., the spatial location of the cable) based on the camera's position and orientation information.

[0090] The shooting prompt message can be a message used to instruct staff to control the robot's camera to capture images. This message can be generated by a smart terminal device displaying a pop-up window showing the camera's captured image, camera posture adjustment control options, robot position adjustment control options, and a shooting prompt icon.

[0091] The shooting prompt message can also be a computer command used to autonomously control the robot's camera to capture images. Another method for generating the shooting prompt message is to use a computer to execute a pre-programmed control system to control both the robot and the camera.

[0092] In particular, the generation cycle of the shooting prompt information can be determined based on the spatial position of the cable on both sides of the current image. The greater the difference in the z-value between the two cable spatial positions, the shorter the generation cycle of the shooting prompt information. By adjusting the robot camera in time, it is possible to prevent the cable from rising or falling too quickly, which would cause the robot camera to fail to capture the cable and thus fail to generate a spatial model of the cable.

[0093] The advantage of this technical solution is that by generating shooting prompts based on the spatial position of the cable on both sides of the image, it can be ensured that the robot camera can always capture the target cable, thereby ensuring the accurate generation of the spatial model of the target cable.

[0094] Optionally, in this solution, the device may further include:

[0095] The shooting position determination module is used to determine the target shooting position when the robot collects the next shooting image based on the cable spatial position of the target cable in the current shooting image;

[0096] The route control module is used to generate a movement route based on the target shooting position and the current shooting position of the robot, and control the robot to move according to the movement route.

[0097] The target shooting position can be the coordinates mapped onto the cable laying map when the robot captures the next image. The target shooting position can be determined by: first, determining the cable's direction based on its spatial location in the current image; second, predicting the cable's spatial location in the next image based on the cable's spatial location at the edges of the current image and its direction; and finally, determining the robot's target shooting position for the next image based on the cable's spatial location in the next image.

[0098] One method for generating the movement route is to connect the current shooting position with the target shooting position when acquiring the next image, using smooth straight lines or curves, based on the direction of the target cable.

[0099] Below is a simple example code for generating a movement route:

[0100]

[0101]

[0102] In this example code, assume the robot's current shooting position is `(current_x, current_y)`, the target shooting position is `(target_x, target_y)`, and the cable's direction information is stored in the variable `cable_direction`. Based on the relative relationship between the robot's current and target shooting positions, the robot's movement direction on the X and Y axes is determined. Then, based on the cable's direction, a movement path is gradually generated until the robot reaches the target position.

[0103] The robot is controlled to move by adjusting its direction and speed according to the movement path, and stopping when it reaches the target shooting position. Furthermore, if the robot cannot fully capture the target cable when it reaches the target shooting position, it can make further position adjustments based on the spatial location of the target cable in the image.

[0104] The advantage of this technical solution is that by determining the target shooting position when the robot collects the next image based on the spatial position of the target cable in the current captured image, it can ensure that the robot can move along the target cable and complete the acquisition of all captured images of the target cable, thereby ensuring the accurate generation of the spatial model of the target cable.

[0105] Example 3

[0106] Figure 3This is a schematic diagram of the automatic model generation device based on cable images provided in Embodiment 1 of this application. This solution makes further improvements based on the above embodiments, specifically: the device further includes: a confidence calculation module, used to determine the confidence of the currently captured image based on the position and posture information of the camera, as well as the current shooting position of the robot and the surrounding environment information of the current shooting position; and a stitching module, used to determine the spatial position of the target cable at the stitching position of the two captured images based on the confidence when stitching the current captured image with the previous and next captured images.

[0107] like Figure 3 As shown, the device includes:

[0108] Image acquisition module 310 is used to acquire images of the target cable by a robot equipped with a camera;

[0109] The pose acquisition module 320 is used to acquire the position and pose information of the camera during the image acquisition process.

[0110] The physical parameter analysis module 330 is used to analyze the physical parameters of the target cable based on the pixel features of the target cable in the captured image, as well as the position and attitude information of the camera.

[0111] Model generation module 340 is used to generate a spatial model of the target cable based on the physical parameters;

[0112] The confidence calculation module 350 is used to determine the confidence of the currently captured image based on the position and posture information of the camera, as well as the current shooting position of the robot and the surrounding environment information of the current shooting position.

[0113] The stitching module 360 ​​is used to determine the cable spatial position of the target cable at the stitching position of the two captured images based on the confidence level when stitching the current captured image with the previous captured image and the next captured image.

[0114] Surrounding environment information can include lighting conditions, obstructions, and terrain at the robot's location. Lighting conditions can affect the brightness and contrast of the images captured by the robot, thus affecting image quality and usability, and further impacting the interpretation of the target cable's physical parameters. Obstacles may exist between the target cable and the robot, preventing the robot's camera from directly capturing the cable, or causing partial obstruction of the cable, thus affecting image integrity and clarity. As the robot moves across different terrains, its position and angle relative to the cable may change, potentially altering the visible portion of the cable and the viewing angle in the captured images. Uneven terrain can affect the stability of the robot's camera; in bumpy or vibrating areas, the camera may be disturbed by the robot's movement, resulting in blurred or shaky images, which may reduce image clarity and readability.

[0115] Confidence level refers to the degree of trust or credibility in a viewpoint, conclusion, or event. Specifically, it can be an evaluation of the accuracy of a currently captured image, expressed as a percentage. Confidence level can be determined by inputting the camera's position and pose information, as well as the robot's current shooting position and surrounding environment information, into a neural network model. The neural network model then provides feedback on the confidence level after comprehensively evaluating these input parameters.

[0116] One method to determine the spatial location of the cable is to multiply the cable spatial location at the splicing location with its corresponding confidence level to obtain the reference spatial location at the splicing location. Then, the sum of the two reference spatial locations is divided by the sum of the two confidence levels, and the result is the final cable spatial location.

[0117] Assuming the cable spatial location at the stitching point of image 1 is (45, 123, 5), and the confidence level of image 1 is 80%, and the cable spatial location at the stitching point of image 2 is (42, 135, 7), and the confidence level of image 2 is 70%, then:

[0118] Reference spatial position at the stitching location of image 1

[0119] = (45×80%, 123×80%, 5×80%)

[0120] =(36, 98.4, 4)

[0121] Reference spatial position at the stitching location of image 2

[0122] = (42×70%, 135×70%, 7×70%)

[0123] =(29.4, 94.5, 4.9)

[0124] Final cable space location at the splicing point

[0125] =[(36+29.4) / (80%+70%), (98.4+94.5) / (80%+70%), (4

[0126] +4.9) / (80%+70%)]

[0127] = (65.4 / 1.5, 192.9 / 1.5, 8.9 / 1.5)

[0128] = (43.6, 128.6, 5.9)

[0129] The advantage of this technical solution is that by determining the confidence level of the currently captured image and determining the spatial position of the target cable at the stitching position of the two captured images based on the confidence level, the error caused by surrounding environmental factors can be reduced, thereby improving the accuracy of the generated spatial model.

[0130] Example 4

[0131] Figure 4 This is a flowchart illustrating the automatic model generation method based on cable images provided in Embodiment 4 of this application. Figure 4 As shown, the specific steps include the following:

[0132] S401. A robot equipped with a camera captures images of the target cable.

[0133] S402. Obtain the position and orientation information of the camera during the image acquisition process;

[0134] S403. Based on the pixel features of the target cable in the captured image, as well as the position and orientation information of the camera, perform physical parameter analysis to obtain the physical parameters of the target cable;

[0135] S404. Generate a spatial model of the target cable based on the physical parameters.

[0136] In this embodiment, a robot equipped with a camera captures images of a target cable; the position and orientation information of the camera are obtained during the image acquisition process; physical parameters of the target cable are analyzed based on the pixel features of the target cable in the captured images, as well as the position and orientation information of the camera, to obtain the physical parameters of the target cable; and a spatial model of the target cable is generated based on the physical parameters. This automatic model generation method based on cable images, by analyzing the physical parameters of the target cable using the robot's position and orientation information and the captured images, can automatically generate a spatial model of the target cable, improving the efficiency of cable data entry.

[0137] The automatic model generation method based on cable images provided in this application corresponds to the automatic model generation device based on cable images provided in the above embodiments. It has the same functional modules and beneficial effects. To avoid repetition, it will not be described again here.

[0138] Example 5

[0139] like Figure 5 As shown, this application embodiment also provides an electronic device 500, including a processor 501, a memory 502, and a program or instructions stored in the memory 502 and executable on the processor 501. When the program or instructions are executed by the processor 501, they implement the various processes of the above-described embodiment of the automatic model generation device based on cable images and achieve the same technical effect. To avoid repetition, they will not be described again here.

[0140] It should be noted that the electronic devices in the embodiments of this application include the mobile electronic devices and non-mobile electronic devices described above.

[0141] Example 6

[0142] This application also provides a readable storage medium storing a program or instructions. When the program or instructions are executed by a processor, they implement the various processes of the above-described embodiment of the automatic model generation device based on cable images and achieve the same technical effect. To avoid repetition, they will not be described again here.

[0143] The processor is the processor in the electronic device described in the above embodiments. The readable storage medium includes computer-readable storage media, such as computer read-only memory (ROM), random access memory (RAM), magnetic disk, or optical disk.

[0144] Example 7

[0145] This application embodiment also provides a chip, which includes a processor and a communication interface. The communication interface is coupled to the processor. The processor is used to run programs or instructions to implement the various processes of the above-described embodiment of the automatic model generation device based on cable images, and can achieve the same technical effect. To avoid repetition, it will not be described again here.

[0146] It should be understood that the chip mentioned in the embodiments of this application may also be referred to as a system-on-a-chip, system chip, chip system, or system-on-a-chip, etc.

[0147] It should be noted that, in this document, the terms "comprising," "including," or any other variations thereof are intended to cover non-exclusive inclusion, such that a process, method, article, or apparatus that comprises a list of elements includes not only those elements but also other elements not expressly listed, or elements inherent to such a process, method, article, or apparatus. Without further limitations, an element defined by the phrase "comprising one..." does not exclude the presence of other identical elements in the process, method, article, or apparatus that includes that element. Furthermore, it should be noted that the scope of the methods and apparatuses in the embodiments of this application is not limited to performing functions in the order shown or discussed, but may also include performing functions substantially simultaneously or in the reverse order, depending on the functions involved. For example, the described methods may be performed in a different order than described, and various steps may be added, omitted, or combined. Additionally, features described with reference to certain examples may be combined in other examples.

[0148] Through the above description of the embodiments, those skilled in the art can clearly understand that the methods of the above embodiments can be implemented by means of software plus necessary general-purpose hardware platforms. Of course, they can also be implemented by hardware, but in many cases the former is a better implementation method. Based on this understanding, the technical solution of this application, in essence, or the part that contributes to the prior art, can be embodied in the form of a computer software product. This computer software product is stored in a storage medium (such as ROM / RAM, magnetic disk, optical disk) and includes several instructions to cause a terminal (which may be a mobile phone, computer, server, or network device, etc.) to execute the methods described in the various embodiments of this application.

[0149] The embodiments of this application have been described above with reference to the accompanying drawings. However, this application is not limited to the specific embodiments described above. The specific embodiments described above are merely illustrative and not restrictive. Those skilled in the art can make many other forms under the guidance of this application without departing from the spirit and scope of the claims, and all of these forms are within the protection scope of this application.

[0150] The above description is merely a preferred embodiment and the technical principles employed in this application. This application is not limited to the specific embodiments described herein, and various obvious changes, readjustments, and substitutions that can be made by those skilled in the art will not depart from the scope of protection of this application. Therefore, although this application has been described in detail through the above embodiments, this application is not limited to the above embodiments, and may include more other equivalent embodiments without departing from the concept of this application, the scope of which is determined by the scope of the claims.

Claims

1. An automatic model generation device based on cable images, characterized in that, The device includes: An image acquisition module is used to capture images of the target cable using a robot equipped with a camera; The pose acquisition module is used to acquire the position and pose information of the camera during the image acquisition process. The physical parameter analysis module is used to analyze the physical parameters of the target cable based on the pixel features of the target cable in the captured image, as well as the position and attitude information of the camera. The model generation module is used to generate a spatial model of the target cable based on the physical parameters. The device further includes: The confidence calculation module is used to determine the confidence of the currently captured image based on the position and posture information of the camera, the current shooting position of the robot, and the surrounding environment information of the current shooting position. The confidence is determined by inputting the position and posture information of the camera, the current shooting position of the robot, and the surrounding environment information of the current shooting position into a neural network model. The neural network model then evaluates the input parameters and provides feedback on the confidence. The stitching module is used to determine the cable spatial position of the target cable at the stitching position of the two captured images based on the confidence level when stitching the current captured image with the previous captured image and the next captured image. The method for determining the cable spatial position is to perform a multiplication operation on the cable spatial position at the stitching position and the corresponding confidence level to obtain the reference spatial position at the stitching position, and then divide the sum of the two reference spatial positions by the sum of the two confidence levels. The result is the final cable spatial position.

2. The automatic model generation device based on cable images according to claim 1, characterized in that, The device further includes: The edge position determination module is used to determine the spatial position of the cable on both sides of the captured image based on the pixel features of the target cable in the captured image, as well as the position and orientation information of the camera. The shooting prompt module is used to generate shooting prompt information based on the spatial position of the cable on both sides of the image.

3. The automatic model generation device based on cable images according to claim 2, characterized in that, The device further includes: The shooting position determination module is used to determine the target shooting position when the robot collects the next shooting image based on the cable spatial position of the target cable in the current shooting image; The route control module is used to generate a movement route based on the target shooting position and the current shooting position of the robot, and control the robot to move according to the movement route.

4. The automatic model generation device based on cable images according to claim 1, characterized in that, The physical parameter analysis module is specifically used for: Based on the pixel features of the target cable in the captured image, as well as the position and orientation information of the camera, at least one of the following is obtained: spatial position information, diameter, direction, and curvature of the target cable.

5. The automatic model generation device based on cable images according to claim 1, characterized in that, The device further includes: The manual calibration module is used to generate manual calibration information when the captured image includes at least two laid cables, so as to determine the target cable for which a spatial model needs to be generated based on the calibration object of the collected calibration operation.

6. A method for automatically generating models based on cable images, characterized in that, The method includes: Images of the target cable are captured by a robot equipped with a camera. Acquire the position and orientation information of the camera during the image acquisition process; Based on the pixel features of the target cable in the captured image, as well as the position and orientation information of the camera, physical parameters are analyzed to obtain the physical parameters of the target cable. Generate a spatial model of the target cable based on the physical parameters; Based on the position and posture information of the camera, as well as the current shooting position of the robot and the surrounding environment information of the current shooting position, the confidence level of the currently captured image is determined; wherein, the confidence level is determined by inputting the position and posture information of the camera, as well as the current shooting position of the robot and the surrounding environment information of the current shooting position into a neural network model, and the neural network model provides feedback on the confidence level after comprehensively evaluating the above input parameters. When stitching the current captured image with the previous and next captured images, the spatial position of the target cable at the stitching position is determined based on the confidence level. The method for determining the cable spatial position is to multiply the cable spatial position at the stitching position with the corresponding confidence level to obtain the reference spatial position at the stitching position, and then divide the sum of the two reference spatial positions by the sum of the two confidence levels. The result is the final cable spatial position.

7. The automatic model generation method based on cable images according to claim 6, characterized in that, After acquiring the camera's position and orientation information during the image capture process, the method further includes: Based on the pixel features of the target cable in the captured image, as well as the position and orientation information of the camera, the spatial position of the cable at both edges of the captured image is determined. A shooting prompt message is generated based on the spatial position of the cable on both sides of the image.

8. The automatic model generation method based on cable images according to claim 7, characterized in that, After determining the spatial positions of the cables at both edges of the currently captured image, the method further includes: Based on the spatial position of the target cable in the current captured image, the target shooting position when the robot captures the next captured image is determined; A movement route is generated based on the target shooting location and the robot's current shooting location, and the robot's movement is controlled according to the movement route.

9. An electronic device, characterized in that, It includes a processor, a memory, and a program or instructions stored in the memory and executable on the processor, wherein the program or instructions, when executed by the processor, implement the steps of the automatic model generation method based on cable images as described in any one of claims 6-8.

Images