Method and apparatus for determining robot pose information, and computer device

Abstract

The application relates to a robot pose information determination method and device and a computer device. In an embodiment, feature point recognition is performed on an original image around the robot, a large-area pure color region in the original image can be recognized, a preset image feature can be added to a corresponding region of the pure color region in the original image to obtain an intermediate image, and the intermediate image is input into a pose calculation model to obtain the pose information of the robot. In this way, the pure color region such as a wall in the original image also has a certain number of feature points in a manner of recognizing the pure color region and adding the image feature, the success rate of feature point extraction is increased, the accuracy of pose positioning is improved, and the problem of poor applicability of robot pose positioning is solved.

Description

Technical Field

[0001] This disclosure relates to the field of positioning and mapping, and in particular to a method, apparatus and computer equipment for determining robot pose information. Background Technology

[0002] Today, intelligent robots are developing rapidly and their applications are becoming increasingly widespread. Robotic vacuum cleaners, material handling robots, and other similar devices can already replace humans in certain scenarios. These robots rely on real-time positioning and mapping technologies to move and perform tasks in different environments.

[0003] Robot localization and mobility systems in related technologies cannot function without pose calculation. Taking the currently popular SLAM (Simultaneous Localization and Mapping) method as an example, the robot uses visual sensors to acquire images of the surrounding environment and selects feature points in different images. Based on the changes in feature points and device parameters, the robot infers its own pose information to complete localization. Furthermore, it can build a map based on its own localization.

[0004] However, in practical applications, robots often encounter large, solid-colored areas such as walls and floors. In these situations, the robot's pose localization often deviates from the actual environment, leading to inaccurate localization results, incorrect movement paths, and in severe cases, even accidents. This greatly limits the application of robots. Summary of the Invention

[0005] Based on this, and to address the aforementioned technical problems, a method, apparatus, computer device, computer-readable storage medium, and computer program product for determining robot pose information are provided. The technical solution of this disclosure is as follows:

[0006] According to one aspect of the present disclosure, a method for determining robot pose information is provided, comprising:

[0007] Acquire the original image within the robot's preset range;

[0008] The original image is subjected to feature point recognition according to a preset image detection algorithm to obtain a solid color region whose area reaches a preset area threshold or whose area ratio reaches a preset first ratio; wherein, the number of feature points per unit area in the solid color region is less than the preset first threshold.

[0009] A preset graphic feature is added to the region corresponding to the solid color region in the original image to obtain an intermediate image;

[0010] The intermediate image is input into a preset pose calculation model, and the pose information of the robot is obtained by outputting the pose calculation model.

[0011] In one embodiment, the step of performing feature point recognition on the original image according to a preset image detection algorithm to obtain pure color regions with an area reaching a preset area threshold or an area ratio reaching a preset first ratio includes:

[0012] Edge detection is performed on the original image to obtain a textured image with feature points;

[0013] The texture image is subjected to image opening operation by a preset algorithm to filter out areas where feature points exceed the first threshold, thereby obtaining the first area to be processed.

[0014] Calculate whether the ratio of the area of ​​the first region to be processed to the area of ​​the original image reaches the preset first ratio; if it does, treat the first region to be processed as a solid color region.

[0015] In one embodiment, before performing image opening operation on the texture image using a preset algorithm, the method further includes:

[0016] The texture image is inverted.

[0017] In one embodiment, adding a preset graphic feature to the region corresponding to the solid color region in the original image to obtain an intermediate image includes:

[0018] Add a preset triangle pattern and / or grid lines to the area corresponding to the solid color area in the original image;

[0019] The preset triangular pattern and / or the grid lines are overlaid onto the area in the original image corresponding to the solid color area to obtain an intermediate image.

[0020] In one embodiment, the preset area threshold ranges from 500 to 1000 pixels;

[0021] and / or;

[0022] The preset first ratio ranges from 1% to 10%.

[0023] According to another aspect of the embodiments of this disclosure, a device for determining robot pose information is provided, comprising:

[0024] The image acquisition module is used to acquire raw images within a preset range of the robot;

[0025] The image recognition module is used to identify feature points in the original image according to a preset image detection algorithm, and to obtain a solid color region whose area reaches a preset area threshold or whose area ratio reaches a preset first ratio; wherein the number of feature points per unit area in the solid color region is less than the preset first threshold.

[0026] The feature addition module is used to add preset graphic features to the regions corresponding to the solid color regions in the original image to obtain an intermediate image;

[0027] The pose calculation module is used to input the intermediate image into a preset pose calculation model, and output the pose information of the robot through the pose calculation model.

[0028] According to another aspect of the present disclosure, an operation and maintenance management system is also provided, including a central control system and an inspection robot; the inspection robot is provided with a memory and a processor, the memory stores a computer program, and the processor executes the computer program to implement the steps of the above-described method.

[0029] According to another aspect of the present disclosure, a computer device is also provided, including a memory and a processor, wherein the memory stores a computer program, and the processor executes the computer program to implement the steps of the above-described method.

[0030] According to another aspect of the present disclosure, a computer-readable storage medium is also provided, on which a computer program is stored, which, when executed by a processor, implements the steps of the above-described method.

[0031] According to another aspect of the present disclosure, a computer program product is also provided, including a computer program that, when executed by a processor, implements the steps of the above-described method.

[0032] In the technical solution provided by this disclosure, feature point recognition is performed on the original image surrounding the robot to identify solid-color areas that occupy a large area in the original image. Preset graphic features are then added to the corresponding areas in the original image based on these solid-color areas to obtain an intermediate image. This intermediate image is then input into a pose calculation model to obtain the robot's pose information. In this way, by identifying solid-color areas and adding image features, even solid-color areas such as walls in the original image can have a certain number of feature points, increasing the success rate of feature point extraction, improving the accuracy of pose localization, and solving the problem of poor applicability of robot pose localization.

[0033] It should be understood that the above general description and the following detailed description are exemplary and explanatory only, and are not intended to limit this disclosure. Attached Figure Description

[0034] To more clearly illustrate the technical solutions in the embodiments or related technologies of this specification, the drawings used in the description of the embodiments or related technologies will be briefly introduced below. Obviously, the drawings described below are only some embodiments recorded in this specification. For those skilled in the art, other drawings can be obtained based on these drawings without creative effort.

[0035] Figure 1 This is a flowchart illustrating a method for determining robot pose information in one embodiment;

[0036] Figure 2 This is a schematic diagram of the process for obtaining a solid color region in one embodiment;

[0037] Figure 3 This is a flowchart illustrating the process of adding graphic features to an original image in one embodiment;

[0038] Figure 4 This is an example of an original image of the robot in front of it, captured by a camera.

[0039] Figure 5 This is a textured image obtained by performing edge detection on the original image in one embodiment;

[0040] Figure 6 This is an example of an inverted image obtained by inverting the texture image;

[0041] Figure 7 In one embodiment, an opening operation is performed on an image to obtain an image of the first region to be processed.

[0042] Figure 8 This is a schematic diagram of a grid feature obtained by adding crosshairs to a solid color area in one embodiment;

[0043] Figure 9 This is a schematic diagram of an intermediate image obtained by adding grid lines to the original image in one embodiment;

[0044] Figure 10 This is a schematic diagram of a device for determining robot pose information in one embodiment;

[0045] Figure 11 This is a schematic diagram of the internal structure of a computer device in one embodiment. Detailed Implementation

[0046] To enable those skilled in the art to better understand the technical solutions of this disclosure, the technical solutions in the embodiments of this disclosure will be clearly and completely described below with reference to the accompanying drawings.

[0047] It should be noted that the terms "first," "second," etc., in the specification, claims, and accompanying drawings of this disclosure are used to distinguish similar objects and are not necessarily used to describe a specific order or sequence. It should be understood that such data can be interchanged where appropriate so that the embodiments of this disclosure described herein can be implemented in orders other than those illustrated or described herein. The embodiments described in the following exemplary embodiments do not represent all embodiments consistent with this disclosure. Rather, they are merely examples of apparatuses and methods consistent with some aspects of this disclosure as detailed in the appended claims. The terms "comprising," "including," or any other variations thereof are intended to cover a non-exclusive inclusion, such that a process, method, product, 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, product, or apparatus. Without further limitation, the presence of other identical or equivalent elements in a process, method, product, or apparatus that includes said elements is not excluded. For example, the use of terms such as "first," "second," etc., is to denote names and does not indicate any specific order.

[0048] The terms “vertical,” “horizontal,” “left,” “right,” “up,” “down,” “front,” “back,” “circumferential,” “direction of travel,” and similar expressions used herein are based on the orientation or positional relationship shown in the accompanying drawings and are used only for the convenience of describing the invention and simplifying the description, and are not intended to indicate or imply that the device or element referred to must have a specific orientation, or be constructed and operated in a specific orientation, and therefore should not be construed as a limitation of the invention.

[0049] Unless otherwise defined, the technical and scientific terms used herein have the same meaning as commonly understood by one of ordinary skill in the art to which this invention pertains. The terminology used herein in the specification of this invention is for the purpose of describing particular embodiments only and is not intended to limit the invention. The terms “and / or,” “and / or,” and “at least one of” as used herein include any and all combinations of one or more of the associated listed items. It should be noted that the connections, links, etc., described in this disclosure can be direct connections via interfaces or pins between devices, connections via leads, or wireless connections (communication connections).

[0050] In robot localization systems, visual odometry (VO) is a module that processes robot position information. It can determine the robot's relative position based on images acquired by visual sensors such as cameras, measure the robot's pose in real time, and create a local map. After obtaining the pose information, pose optimization can be performed by combining it with methods such as loop closure detection in some common approaches. Then, a map related to the robot's surrounding environment can be constructed through algorithms or models.

[0051] This vision-based pose determination method requires using feature extraction algorithms such as SIFT or ORB to extract feature points from images. SIFT, short for Scale-Invariant Feature Transform, is a computer vision (CV) algorithm used to detect and describe local features in images. It finds extrema in scale space (the LoG pyramid approximated by the DoG difference between Gaussian images) and extracts their position, scale, and rotation invariants. In the SIFT algorithm, the description and detection of local image features helps in object identification. SIFT features are based on points of interest in the local appearance of objects and are independent of image size and rotation. They also have a high tolerance for lighting, noise, and slight changes in viewpoint. Based on these characteristics, they are highly salient and relatively easy to extract, making it easy to identify objects in large feature databases with few false positives. SIFT feature description also has a high detection rate for partially occluded objects; sometimes only three or more SIFT object features are sufficient to calculate position and orientation. With current computer hardware speeds and small feature databases, recognition speeds can approach real-time computation. SIFT features contain a large amount of information, making them suitable for fast and accurate matching in massive databases. ORB, short for Oriented Fast and Rotated Brief, can be used to quickly create feature vectors from keypoints in an image. These feature vectors can be used to identify objects in the image. Fast and Brief are the feature detection algorithm and the vector creation algorithm, respectively. ORB first identifies special regions in the image, called keypoints. Keypoints are small, prominent areas in the image, such as corners, or those with pixel values ​​that rapidly change from light to dark. Then, ORB calculates a corresponding feature vector for each keypoint. The feature vectors created by the ORB algorithm contain only 1s and 0s, called binary feature vectors. The order of 1s and 0s varies depending on the specific keypoint and its surrounding pixel region. This vector represents the intensity pattern around the keypoint, so multiple feature vectors can be used to identify larger areas, or even specific objects in the image. ORB is characterized by its extremely high speed and is to some extent unaffected by noise and image transformations, such as rotation and scaling.

[0052] However, whether it is SIFT or ORB, or other feature point extraction algorithms, these algorithms have a high accuracy rate in pose localization when applied to theoretical models, but in the actual operation of robots, when the robot encounters large solid-color areas such as walls and the ground, localization errors often occur, which greatly limits the application environment of the robot.

[0053] Through in-depth analysis and research, the applicant discovered that the cause of the above problems lies in the fact that pose localization methods in related technologies require extracting feature points from areas of dense texture in images. However, in the actual working environment of robots, large areas of solid color, such as walls and floors, often appear. These solid color areas have sparse textures, making it difficult to effectively extract feature points. Ultimately, this results in unsatisfactory efficiency and accuracy of pose localization. Related technologies have not provided a good solution to the problems encountered in the robot pose localization process.

[0054] To address the aforementioned problems, according to one aspect of an embodiment of this disclosure, such as Figure 1 As shown, a method for determining robot pose information is provided, including:

[0055] Step S202: Obtain the original image within the preset range of the robot.

[0056] Specifically, raw images of the robot's surroundings can be acquired using visual sensors such as cameras. For example, cameras can be placed on the robot's head or other parts, and the cameras can be controlled to take pictures in a specified direction to obtain raw images.

[0057] Step S204: Based on a preset image detection algorithm, feature point recognition is performed on the original image to obtain a solid color region whose area reaches a preset area threshold or whose area ratio reaches a preset first ratio; wherein, the number of feature points per unit area in the solid color region is less than the preset first threshold.

[0058] The preset image detection algorithm can be the ORB algorithm, or an image processing algorithm such as the SIFT algorithm that can extract feature points or edge points. The preset area threshold can be any value not less than 500 pixels. The area ratio can be the ratio of the area of ​​the solid color region to the area of ​​the original image. The preset first ratio can be not less than 1%.

[0059] Specifically, image detection algorithms can be used to perform feature detection on the original image, identify feature points present in the image, and statistically analyze regions with sparse feature point distribution. The algorithm searches for regions whose area reaches a preset area threshold or whose area ratio reaches a preset first ratio, and whose feature points per unit area are less than the preset first threshold. If such a region exists, it is designated as the solid color region. For example, a rectangle not smaller than the preset area threshold can be randomly selected in the original image, and the number of feature points within each selected region can be calculated. The solid color region is then determined based on the relationship between the number of feature points per unit area and the first threshold. In some other implementations, regions with dense feature points can be removed using methods such as opening operations before selecting sparsely distributed regions as the solid color region.

[0060] Step S206: Add preset graphic features to the region corresponding to the solid color region in the original image to obtain an intermediate image.

[0061] The preset graphic features can be patterns that include points and / or lines.

[0062] Specifically, graphic features can be added to the locations corresponding to solid-color regions in the original image using image processing software or algorithms. For example, algorithms can be used to generate graphic features adapted to the size of the solid-color regions, and then these features can be added to the corresponding locations in the original image to obtain an intermediate image. Optionally, the added pattern can be smaller than or equal to the solid-color region. This ensures that the number of feature points per unit area in the solid-color region exceeds a preset first threshold. Furthermore, in some other implementations, the number of added feature points can exceed the preset first threshold by several times, such as two or three times. This increases the success rate of feature point extraction and improves the accuracy of pose localization. On the other hand, it avoids adding too many feature points while ensuring localization accuracy. In some other implementations, mask operations can also be used to combine the pattern with graphic features with the original image to obtain an intermediate image where the solid-color region is the graphic feature.

[0063] Step S208: Input the intermediate image into a preset pose calculation model, and output the pose information of the robot through the pose calculation model.

[0064] The preset pose calculation model can be a SLAM (Simultaneous Localization and Mapping) model based on the ORB algorithm. This pose calculation model can extract feature points from the input image, obtain the positional changes of these feature points based on at least two input images, and, combined with pre-stored known parameters such as camera intrinsic and extrinsic parameters, determine and output the robot's pose information.

[0065] Specifically, the obtained intermediate image can be input into a trained pose calculation model. The model extracts features from the input intermediate image, calculates the robot's pose based on the feature points, and outputs the pose information. The pose calculation model can be trained based on SLAM principles combined with the ORB algorithm. In some other embodiments, the pose calculation model can also use the SIFT algorithm.

[0066] In the technical solution provided by this disclosure, feature point recognition is performed on the original image surrounding the robot to identify solid-color areas that occupy a large area in the original image. Preset graphic features are then added to the corresponding areas in the original image based on these solid-color areas to obtain an intermediate image. This intermediate image is then input into a pose calculation model to obtain the robot's pose information. In this way, by identifying solid-color areas and adding image features, even solid-color areas such as walls in the original image can have a certain number of feature points, increasing the success rate of feature point extraction, improving the accuracy of pose localization, and solving the problem of poor applicability of robot pose localization.

[0067] In one embodiment, such as Figure 2 As shown, the step of performing feature point recognition on the original image according to a preset image detection algorithm to obtain pure color regions with an area reaching a preset area threshold or an area ratio reaching a preset first ratio includes:

[0068] Step S2042: Perform edge detection on the original image to obtain a texture image with feature points.

[0069] Specifically, edge detection algorithms such as ORB can be used to detect the original image, obtain edge feature point information of the original image, and obtain a texture image with feature points.

[0070] Step S2044: Perform image opening operation on the texture image using a preset algorithm to filter out regions where feature points exceed the first threshold, thereby obtaining the first region to be processed.

[0071] Opening is an image processing technique that performs erosion followed by dilation on a grayscale image to remove noise while preserving its original shape. The first threshold can be used to represent the number of feature points within a preset area.

[0072] Specifically, a preset image algorithm can be used to perform an opening operation on the texture image to filter out regions where feature points are clustered, retaining a first region with sparse feature points. In some other embodiments, the algorithm parameters can be adjusted according to a preset first threshold to filter out regions in the texture image where the number of feature points within a certain area exceeds the first threshold, thus obtaining the first region to be processed.

[0073] Step S2046: Calculate whether the ratio between the area of ​​the first region to be processed and the area of ​​the original image reaches the preset first ratio; if it does, treat the first region to be processed as a solid color region.

[0074] The preset first ratio can be set according to the parameters of the pose calculation model; for example, the first ratio can be 1%. The solid color region can be used to represent a region in the image with a high area ratio and few feature points.

[0075] Specifically, the area of ​​the first region to be processed obtained after the opening operation in step S2044 can be calculated, and the ratio of this area to the total area of ​​the original image can be calculated. The calculated ratio is then compared with a preset first ratio. If the ratio is greater than or equal to the first ratio, the first region to be processed can be considered a solid color region. In some other embodiments, a certain area threshold can be set according to the pose calculation model, and the area of ​​the first region to be processed can be compared with the area threshold. If the area of ​​the first region to be processed exceeds the area threshold, the first region to be processed is considered a solid color region.

[0076] In the above embodiments, edge detection and opening operations can remove small areas with dense feature points in the original image, resulting in solid-color areas with sparse feature points and an area ratio reaching a certain threshold, which provides a foundation for solving the problem of difficulty in effectively extracting image feature points.

[0077] In one embodiment, before performing image opening operation on the texture image using a preset algorithm, the method further includes:

[0078] The texture image is inverted.

[0079] Specifically, an image containing feature point information can be inverted to make the texture features containing the feature points darker, resulting in an inverted image. This inverted image can then be used to perform image opening operations to obtain a first region to be processed.

[0080] In the above embodiments, before performing the opening operation, the texture image can be inverted to make the texture features in the image darker. This allows for more effective removal of small areas with dense feature points during the opening operation, improving the algorithm's processing efficiency.

[0081] In one embodiment, such as Figure 3 As shown, the step of adding preset graphic features to the region corresponding to the solid color region in the original image to obtain an intermediate image includes:

[0082] Step S2062: Add a preset triangle pattern and / or grid lines to the area in the original image corresponding to the solid color area.

[0083] Specifically, after obtaining the solid color region from the original image, an algorithm can be used to add a pattern containing several triangles and / or grid lines to the solid color region, so that the solid color region has triangular and / or grid features.

[0084] Step S2064: Cover the area in the original image corresponding to the solid color area with the preset triangle pattern and / or the grid lines to obtain an intermediate image.

[0085] Specifically, the triangular patterns and / or grid lines in the solid color area can be overlaid onto the corresponding areas in the original image to obtain an intermediate image.

[0086] In the above embodiments, adding graphic features to the solid color areas in the original image using triangles and / or grid lines can provide more effective feature points for feature extraction algorithms such as ORB. Moreover, feature points extracted from triangles and / or grid lines are easier to calculate pose, enabling faster acquisition of robot pose information and meeting the real-time requirements of robot pose localization.

[0087] In one embodiment, the preset area threshold ranges from 500 to 1000 pixels;

[0088] and / or;

[0089] The preset first ratio ranges from 1% to 10%.

[0090] Specifically, the preset area threshold can be any value between 500 pixels and 1000 pixels. The preset first ratio can be any value between 1% and 10%.

[0091] In the above embodiments, setting a ratio of 500 pixels and / or 1% as a constraint for selecting solid color regions can avoid selecting small areas sufficient to provide feature points as solid color regions, thus reducing the processing burden on the algorithm. Furthermore, depending on the needs of the pose calculation task, the preset area threshold can be increased to 1000 pixels or the first ratio can be increased to 10%, which can be applied to scenarios with many single areas such as walls, improving pose calculation efficiency.

[0092] To further demonstrate the beneficial effects of this plan, the following is an explanation of a specific implementation process:

[0093] Figure 4 This is a raw image of the robot's front obtained by a camera in one embodiment, such as... Figure 4 As shown, the partition in the image has a large area of ​​uniform color, which is not conducive to feature point extraction during the robot's pose localization process. After acquiring the original image, edge detection algorithms can be used to obtain the image's edge texture features, such as... Figure 5 As shown, the image contains several edge points that can represent image features, and the lower half of the image contains a large area of ​​solid color. Figure 5 Inverting colors can produce results such as Figure 6 The inverted color image shown is in Figure 6In this image, edge points are dark. After obtaining the inverted image, a preset algorithm can be used to... Figure 6 Perform an opening operation to remove small areas with densely packed edge points, resulting in: Figure 7 The first region to be processed is shown. The area of ​​this first region exceeds a preset area threshold of 500 pixels. This region is treated as a solid color region, and a crosshair grid is added to it as a feature. Specifically, the bounding rectangle of the solid color region can be calculated, and the rectangular region can be divided into a grid using crosshairs. Grid lines extending beyond the rectangular region are then removed, resulting in the following: Figure 8 The mesh feature shown. Finally, it can be... Figure 8 The grid lines in the image overlap the corresponding areas in the original image, resulting in: Figure 9 The intermediate image shown has a grid feature. Figure 9 As input to the pose calculation model, the pose information output by the model can be obtained.

[0094] In the above embodiments, by performing operations such as edge detection, opening operations, and feature addition, preset grid lines can be added to large areas of a single color in the original image, so that the area also has sufficient graphic features to effectively extract image feature points, thereby improving the efficiency of pose localization.

[0095] It should be understood that although the steps in the flowcharts of the embodiments described above are shown sequentially according to the arrows, these steps are not necessarily executed in the order indicated by the arrows. Unless explicitly stated herein, there is no strict order restriction on the execution of these steps, and they can be executed in other orders. Moreover, at least some steps in the flowcharts of the embodiments described above may include multiple steps or multiple stages. These steps or stages are not necessarily completed at the same time, but can be executed at different times. The execution order of these steps or stages is not necessarily sequential, but can be performed alternately or in turn with other steps or at least some of the steps or stages of other steps.

[0096] According to another aspect of the embodiments of this disclosure, such as Figure 10 As shown, a device for determining robot pose information is also provided, comprising:

[0097] Image acquisition module 302 is used to acquire original images within a preset range of the robot;

[0098] Image recognition module 304 is used to perform feature point recognition on the original image according to a preset image detection algorithm, and obtain a solid color region whose area reaches a preset area threshold or whose area ratio reaches a preset first ratio; wherein, the number of feature points per unit area in the solid color region is less than the preset first threshold.

[0099] The feature addition module 306 is used to add preset graphic features to the region corresponding to the solid color region in the original image to obtain an intermediate image;

[0100] The pose calculation module 308 is used to input the intermediate image into a preset pose calculation model, and output the pose information of the robot through the pose calculation model.

[0101] In one embodiment, the image recognition module 304 includes:

[0102] An edge detection unit is used to perform edge detection on the original image to obtain a textured image with feature points;

[0103] An opening operation unit is used to perform an image opening operation on the texture image using a preset algorithm, filtering out regions where feature points exceed the first threshold to obtain a first region to be processed.

[0104] An area comparison unit is used to calculate whether the ratio of the area of ​​the first region to be processed to the area of ​​the original image reaches the preset first ratio; if it does, the first region to be processed is treated as a solid color region.

[0105] In one embodiment, the image recognition module 304 further includes:

[0106] The inversion unit is used to invert the colors of the texture image.

[0107] In one embodiment, the feature addition module 306 includes:

[0108] A feature generation unit is used to add a preset triangle pattern and / or grid lines to the region in the original image corresponding to the solid color region;

[0109] The feature addition unit is used to overlay the preset triangle pattern and / or the grid lines onto the area in the original image corresponding to the solid color area to obtain an intermediate image.

[0110] For specific limitations regarding the aforementioned determining device, please refer to the limitations of the aforementioned determining method above, which will not be repeated here. According to the aforementioned determining method, the determining device can be supplemented with a first module, a second module, etc., to implement the steps in the corresponding method embodiments. Each module in the aforementioned determining device can be implemented entirely or partially through software, hardware, or a combination thereof. Each module can be embedded in or independent of the processor in a computer device in hardware form, or stored in the memory of a computer device in software form, so that the processor can call and execute the operations corresponding to each module.

[0111] According to another aspect of the present disclosure, an operation and maintenance management system is provided, which includes at least a central control system and an inspection robot; the inspection robot is provided with a memory and a processor, the memory stores a computer program, and the processor executes the computer program to implement the steps in the above-described method embodiments.

[0112] The central control system can be applied to the server side, and the central control system can communicate with the inspection robot.

[0113] Specifically, a corresponding central control system can be developed based on operation and maintenance management needs. This system can control the inspection robot to move within a designated area and perform corresponding maintenance operations based on the maintenance tasks. These operations can include maintaining the normal operation of equipment or systems, or inspecting or maintaining them. For example, a maintenance task might be to check whether the power indicator light on a specific processing device is lit correctly. The central control system can plan an inspection route based on the location of the processing device, control the inspection robot to move to the vicinity of the device along the route, and photograph the power indicator light before uploading it to the central control system. The central control system then determines the status of the power indicator light. The inspection robot can achieve pose localization by executing the steps described in the above method embodiments through a processor, and move according to the positioning information and the inspection route.

[0114] Optionally, the central control system can also be used in electronic device terminals with processing functions, such as computers and smartphones.

[0115] In the above embodiments, under the control of the central control system, the inspection robot can move according to the instructions and inspection route issued by the central control system, and use the pose information determination method to move to the designated location in a timely manner and complete the corresponding maintenance tasks. In this way, by confirming the robot's own position through more accurate pose information, it can make timely adjustments according to the movement route, which can not only avoid route errors during movement, but also reach the target location more quickly to perform maintenance tasks, thereby improving the work efficiency of the maintenance system.

[0116] According to another aspect of the embodiments of this disclosure, a computer device is provided, which may be a terminal, and its internal structure diagram may be as follows: Figure 11As shown. The computer device includes a processor, memory, communication interface, display screen, and input devices connected via a system bus. The processor provides computing and control capabilities. The memory includes non-volatile storage media and internal memory. The non-volatile storage media stores the operating system and computer programs. The internal memory provides an environment for the operation of the operating system and computer programs stored in the non-volatile storage media. The communication interface is used for wired or wireless communication with external terminals; wireless communication can be achieved through Wi-Fi, carrier networks, NFC (Near Field Communication), or other technologies. When the computer program is executed by the processor, it implements the aforementioned determined method. The display screen can be an LCD screen or an e-ink screen. The input devices can be a touch layer covering the display screen, buttons, a trackball, or a touchpad mounted on the computer device casing, or an external keyboard, touchpad, or mouse.

[0117] Those skilled in the art will understand that Figure 11 The structure shown is merely a block diagram of a portion of the structure related to the present application and does not constitute a limitation on the computer device to which the present application is applied. Specific computer devices may include more or fewer components than those shown in the figure, or combine certain components, or have different component arrangements.

[0118] In one embodiment, a computer device is also provided, including a memory and a processor, wherein the memory stores a computer program, and the processor executes the computer program to implement the steps in the above method embodiments.

[0119] According to another aspect of the present disclosure, a computer program product is provided, including a computer program that, when executed by a processor, implements the steps in the above-described method embodiments.

[0120] Those skilled in the art will understand that all or part of the processes in the above embodiments can be implemented by a computer program instructing related hardware. The computer program can be stored in a non-volatile computer-readable storage medium, and when executed, it can include the processes of the embodiments described above. Any references to memory, storage, databases, or other media used in the embodiments provided in this application can include at least one of non-volatile and volatile memory. Non-volatile memory can include read-only memory (ROM), magnetic tape, floppy disk, flash memory, or optical storage, etc. Volatile memory can include random access memory (RAM) or external cache memory. By way of illustration and not limitation, RAM can be in various forms, such as static random access memory (SRAM) or dynamic random access memory (DRAM), etc. The databases involved in the embodiments provided in this application can include at least one relational database and non-relational database. Non-relational databases can include blockchain-based distributed databases, etc., and are not limited thereto. The processors involved in the various embodiments provided in this application may be general-purpose processors, central processing units, graphics processors, digital signal processors, programmable logic devices, quantum computing-based data processing logic devices, etc., and are not limited thereto.

[0121] The technical features of the above embodiments can be combined in any way. For the sake of brevity, not all possible combinations of the technical features in the above embodiments are described. However, as long as there is no contradiction in the combination of these technical features, they should be considered to be within the scope of this specification.

[0122] The embodiments described above are merely illustrative of several implementations of this application, and while the descriptions are specific and detailed, they should not be construed as limiting the scope of this application. It should be noted that those skilled in the art, upon considering the specification and practicing the invention disclosed herein, will readily conceive of other embodiments of this disclosure. This disclosure is intended to cover any variations, uses, or adaptations of this disclosure that follow the general principles of this disclosure and include common knowledge or customary techniques in the art not disclosed herein. The specification and embodiments are to be considered exemplary only, and the true scope and spirit of this disclosure are indicated by the claims.

[0123] It should be understood that this disclosure is not limited to the precise structures already described and shown in the accompanying drawings, and various modifications and changes can be made without departing from its scope.

Claims

1. A method for determining robot pose information, characterized in that, include: Acquire the original image within the robot's preset range; The original image is subjected to feature point recognition according to a preset image detection algorithm to obtain a solid color region whose area reaches a preset area threshold or whose area ratio reaches a preset first ratio; wherein, the number of feature points per unit area in the solid color region is less than the preset first threshold. Adding preset graphic features to the region corresponding to the solid color region in the original image to obtain an intermediate image includes: generating graphic features adapted to the size of the solid color region using an algorithm, adding the graphic features to the corresponding position in the original image to obtain an intermediate image; The method further includes: The intermediate image is input into a preset pose calculation model, and the pose information of the robot is obtained by outputting the pose calculation model.

2. The method according to claim 1, characterized in that, The step of performing feature point recognition on the original image according to a preset image detection algorithm to obtain pure color regions with an area reaching a preset area threshold or an area ratio reaching a preset first ratio includes: Edge detection is performed on the original image to obtain a textured image with feature points; The texture image is subjected to image opening operation by a preset algorithm to filter out areas where feature points exceed the first threshold, thereby obtaining the first area to be processed. Calculate whether the ratio of the area of ​​the first region to be processed to the area of ​​the original image reaches the preset first ratio; if it does, treat the first region to be processed as a solid color region.

3. The method according to claim 2, characterized in that, Before performing image opening operation on the texture image using a preset algorithm, the method further includes: The texture image is inverted.

4. The method according to claim 1, characterized in that, Adding preset graphic features to the regions corresponding to the solid color regions in the original image to obtain an intermediate image includes: Add a preset triangle pattern and / or grid lines to the area corresponding to the solid color area in the original image; The preset triangular pattern and / or the grid lines are overlaid onto the area in the original image corresponding to the solid color area to obtain an intermediate image.

5. The method according to claim 1, characterized in that, The preset area threshold value ranges from 500 to 1000 pixels; and / or; The preset first ratio ranges from 1% to 10%.

6. A device for determining robot pose information, characterized in that, include: The image acquisition module is used to acquire raw images within a preset range of the robot; The image recognition module is used to identify feature points in the original image according to a preset image detection algorithm, and to obtain a solid color region whose area reaches a preset area threshold or whose area ratio reaches a preset first ratio; wherein the number of feature points per unit area in the solid color region is less than the preset first threshold. The feature addition module is used to add preset graphic features to the region corresponding to the solid color region in the original image to obtain an intermediate image. The feature addition module is also used to generate graphic features adapted to the size of the solid color region using an algorithm, and add the graphic features to the corresponding position in the original image to obtain an intermediate image. The pose calculation module is used to input the intermediate image into a preset pose calculation model, and output the pose information of the robot through the pose calculation model.

7. An operation and maintenance management system, characterized in that, It includes a central control system and an inspection robot; the inspection robot is equipped with a memory and a processor, the memory stores a computer program, and the processor executes the computer program to implement the steps of the method according to any one of claims 1 to 5.

8. A computer device comprising a memory and a processor, wherein the memory stores a computer program, characterized in that, When the processor executes the computer program, it implements the steps of the method according to any one of claims 1 to 5.

9. A computer-readable storage medium having a computer program stored thereon, characterized in that, When the computer program is executed by a processor, it implements the steps of the method according to any one of claims 1 to 5.

10. A computer program product, comprising a computer program, characterized in that, When the computer program is executed by a processor, it implements the steps of the method according to any one of claims 1 to 5.

Images