Steel bar binding method, device and equipment and storage medium

Abstract

The invention discloses a reinforcing steel bar binding method, device and equipment and a storage medium, relates to the field of civil construction, is applied to a reinforcing steel bar binding robot, and comprises the steps that first reinforcing steel bar distribution information of a global operation area is determined based on a preset global operation area determination method; determining a region type corresponding to the target image based on a preset image classification method, determining an initial operation region based on the region type by using a region grid search method, and determining all target binding points of the initial operation region based on a preset target detection method; the area type comprises a non-operation area, an operation area boundary, an operation area interior and an operation area corner point; and determining a first position relationship between the initial operation area and the global operation area based on the first steel bar distribution information and all the target binding points, so that the steel bar binding robot moves to the target operation point corresponding to the initial operation area based on the first position relationship to perform steel bar binding. The steel bar binding robot is guided to move to the operation point corresponding to the initial operation area.

Description

Technical Field

[0001] The present invention relates to the field of civil engineering, and particularly relates to a steel bar binding method, device, equipment and storage medium. Background Art

[0002] In recent years, the research on steel bar binding robots has gradually developed. The existing automatic binding research involves aspects such as autonomous navigation and positioning, intersection point recognition, and binding path planning. Binding path planning and binding operation execution are two important steps. However, there is a lack of an automatic initialization method to guide the steel bar binding robot to reach the working point corresponding to the initial working area between these two steps, resulting in the inability to automatically connect these two steps and often requiring manual positioning. Therefore, how to guide the steel bar binding robot to move to the working point corresponding to the initial working area is an urgent problem to be solved at present. Summary of the Invention

[0003] In view of this, the purpose of the present invention is to provide a steel bar binding method, device, equipment and storage medium, which can guide the steel bar binding robot to move to the working point corresponding to the initial working area. The specific scheme is as follows:

[0004] In a first aspect, the present application discloses a steel bar binding method, which is applied to a steel bar binding robot and includes:

[0005] Determine the first steel bar distribution information of the global working area based on a preset global working area determination method; the first steel bar distribution information includes the steel bar intersection point information and steel bar spacing distribution information of the global working area;

[0006] Determine the area type corresponding to the target image based on a preset image classification method, and use the area grid search method to determine the initial working area based on the area type, and determine all target binding points of the initial working area based on a preset target detection method; the target image is an image collected by a target depth camera carried on the steel bar binding robot; the area type includes non-working area, working area boundary, working area interior and working area corner point;

[0007] Determine the first positional relationship between the initial working area and the global working area based on the first steel bar distribution information and all the target binding points, so that the steel bar binding robot can move to the target working point corresponding to the initial working area based on the first positional relationship to perform steel bar binding.

[0008] Optionally, the determining the first steel bar distribution information of the global working area based on a preset global working area determination method includes:

[0009] Establish a target three-dimensional model of the global working area by using a depth camera or a laser scanning device;

[0010] Use the target 3D model for 3D line fitting to determine the first steel bar distribution information of the global working area.

[0011] Optionally, determining the first steel bar distribution information of the global working area based on the preset global working area determination method includes:

[0012] Use a depth camera to capture the global working area to obtain a global depth image corresponding to the global working area;

[0013] Determine the first steel bar distribution information of the global working area based on the global depth image.

[0014] Optionally, determining the first steel bar distribution information of the global working area based on the preset global working area determination method includes:

[0015] Use a preset heuristic rule to determine a target elevation view based on the steel bar layout drawing of the global working area;

[0016] Determine the first steel bar distribution information of the global working area based on the target elevation view.

[0017] Optionally, determining all target tying points of the initial working area based on the preset target detection method includes:

[0018] Filter the target depth image corresponding to the initial working area based on a preset depth threshold to obtain a filtered depth map;

[0019] Use a preset target detection method to detect the filtered depth map to determine all the target tying points of the initial working area.

[0020] Optionally, determining all target tying points of the initial working area based on the preset target detection method includes:

[0021] Determine the first tying point of the initial working area based on a preset target detection method;

[0022] Adjust the robotic arm of the steel bar tying robot based on a second positional relationship to determine all the target tying points of the initial working area;

[0023] Wherein, the second positional relationship is the positional relationship between the first tying point and the camera optical center of the target depth camera.

[0024] Optionally, determining the first positional relationship between the initial working area and the global working area based on the first steel bar distribution information and all the target tying points includes:

[0025] Determine the second steel bar distribution information corresponding to the initial working area based on all the target tying points;

[0026] Determine each target steel bar intersection point corresponding to each target binding point in the global working area based on the first steel bar distribution information and the second steel bar distribution information;

[0027] Determine the first positional relationship between the initial working area and the global working area based on each of the target steel bar intersection points.

[0028] In a second aspect, the present application discloses a steel bar binding device applied to a steel bar binding robot, including:

[0029] A steel bar distribution information determination module for determining first steel bar distribution information of a global working area based on a preset global working area determination method; the first steel bar distribution information includes steel bar intersection point information and steel bar spacing distribution information of the global working area;

[0030] A binding point determination module for determining the area type corresponding to a target image based on a preset image classification method, determining an initial working area based on the area type using an area grid search method, and determining all target binding points of the initial working area based on a preset target detection method; the target image is an image collected by a target depth camera mounted on the steel bar binding robot; the area type includes a non-working area, a working area boundary, an internal working area, and a working area corner point;

[0031] A steel bar binding module for determining the first positional relationship between the initial working area and the global working area based on the first steel bar distribution information and all the target binding points, so that the steel bar binding robot moves to a target working point corresponding to the initial working area based on the first positional relationship to perform steel bar binding.

[0032] In a third aspect, the present application discloses an electronic device, including:

[0033] A memory for storing a computer program;

[0034] A processor for executing the computer program to implement the foregoing steel bar binding method.

[0035] In a fourth aspect, the present application discloses a computer-readable storage medium for storing a computer program, wherein the computer program, when executed by a processor, implements the foregoing steel bar binding method.

[0036] In this application, when the steel bar binding robot binds steel bars, it determines the first steel bar distribution information of the global working area based on a preset global working area determination method; the first steel bar distribution information includes the steel bar intersection information and the steel bar spacing distribution information of the global working area; it determines the area type corresponding to the target image based on a preset image classification method, and uses the area grid search method to determine the initial working area based on the area type, and determines all target binding points in the initial working area based on a preset target detection method; the target image is an image collected by a target depth camera carried on the steel bar binding robot; the area type includes non-working area, working area boundary, inside the working area, and working area corner points; it determines the first position relationship between the initial working area and the global working area based on the first steel bar distribution information and all the target binding points, so that the steel bar binding robot can move to the target working point corresponding to the initial working area based on the first position relationship to bind steel bars. It can be seen that after collecting the target image using the target depth camera in this application, the initial working area can be quickly determined using the preset image classification method and the area grid search method, and then the first position relationship between the initial working area and the global working area is determined using the information of all the target binding points in the initial working area and the first steel bar distribution information of the global working area, so that the steel bar binding robot can move to the working point corresponding to the initial working area based on the first position relationship to bind steel bars. BRIEF DESCRIPTION OF THE DRAWINGS

[0037] In order to more clearly illustrate the technical solutions in the embodiments of the present invention or the prior art, the following will briefly introduce the drawings required for use in the description of the embodiments or the prior art. Obviously, the drawings in the following description are only the embodiments of the present invention. For those of ordinary skill in the art, without creative efforts, other drawings can also be obtained according to the provided drawings.

[0038] Figure 1 It is a flowchart of a steel bar binding method disclosed in this application;

[0039] Figure 2 It is a schematic diagram of the flow of a specific steel bar binding method disclosed in this application;

[0040] Figure 3 It is a schematic diagram of the title of a steel bar layout drawing provided in this application;

[0041] Figure 4 It is a complete digital vector schematic diagram provided in this application;

[0042] Figure 5 It is a schematic diagram of the flow of an initial working area positioning method disclosed in this application;

[0043] Figure 6Schematic diagram of grid search order disclosed in this application;

[0044] Figure 7 Schematic diagram of the process of a label matching method disclosed in this application;

[0045] Figure 8 Schematic diagram of the structure of a steel bar binding device disclosed in this application;

[0046] Figure 9 Structural diagram of an electronic device disclosed in this application. Detailed implementation manners

[0047] Next, the technical solutions in the embodiments of the present invention will be clearly and completely described in conjunction with the accompanying drawings in the embodiments of the present invention. Obviously, the described embodiments are only a part of the embodiments of the present invention, rather than all the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those of ordinary skill in the art without creative efforts shall fall within the protection scope of the present invention.

[0048] Existing research on automatic binding involves aspects such as autonomous navigation and positioning, intersection recognition, and binding path planning. Binding path planning and binding operation execution are two important steps. However, there is a lack of an automatic initialization method to guide the steel bar binding robot to reach the operation points corresponding to the initial operation area between these two steps, resulting in the inability to automatically connect these two steps and often requiring manual positioning. To solve the above technical problems, this application discloses a steel bar binding method that can guide the steel bar binding robot to move to the operation points corresponding to the initial operation area.

[0049] See Figure 1 As shown, an embodiment of the present invention discloses a steel bar binding method applied to a steel bar binding robot, including:

[0050] Step S11: Determine the first steel bar distribution information of the global operation area based on a preset global operation area determination method; the first steel bar distribution information includes the steel bar intersection information and the steel bar spacing distribution information of the global operation area.

[0051] In this embodiment, the process of determining the first steel bar distribution information of the global operation area based on a preset global operation area determination method may specifically include: establishing a target three-dimensional model of the global operation area using a depth camera or a laser scanning device, and then performing three-dimensional straight line fitting on the target three-dimensional model to determine the first steel bar distribution information of the global operation area; or using a depth camera to capture the global operation area to obtain a global depth image corresponding to the global operation area, and determining the first steel bar distribution information of the global operation area based on the global depth image. In addition, as Figure 2As shown in the figure, when determining the first steel bar distribution information of the global working area, a preset heuristic rule can also be used to determine the target elevation view based on the steel bar layout drawing of the global working area, and the first steel bar distribution information of the global working area can be determined based on the target elevation view.

[0052] It should be noted that in this embodiment, the steel bar layout drawing can be a drawing in PDF (Portable Document Format) format. The wide use of PDF format drawings is conducive to the extraction of steel bar information on the surface to be tied. The vector graphic blocks in the PDF format drawings can save a large amount of graphic information (such as layers, bounding boxes, coordinates, line thicknesses, line colors, fills, etc.) and are not affected by the scaling of the drawing. If the drawing is used for printing or cross-platform use, the text in the exported vector drawing is usually converted to outlines to ensure display consistency. The box girder steel bar layout drawing usually has the following characteristics: multiple views are saved at the same time, including elevations, sections, details, etc.; there are overlapping interferences of different legends and markings in each view; there are truncations in the drawing, mainly because the steel bar skeleton is too long to be completely displayed. And the steel bar tying task mainly focuses on the elevation spacing information of the steel bar skeleton. Therefore, for the complex situation of the drawing, the extraction needs to be divided into rough extraction and fine extraction. First, the elevation view is segmented from the layout drawing (i.e., rough extraction), and then the steel bar data on the surface to be tied is extracted from the elevation view (i.e., fine extraction).

[0053] In this embodiment, to achieve the extraction of the steel bar data on the surface to be tied in the steel bar layout drawing, a heuristic rule can be formulated according to the characteristics of the steel bar layout drawing to process the steel bar layout drawing, where the aspect ratio of the text graphics is within a certain range. Therefore, the heuristic rule can be used to screen the elements with the aspect ratio of the circumscribed box of the vector graphic block between 1 / 4 and 4. These elements may be text, such as Figure 3 As shown, the text with a title bottom line below is the title, and the text or digital vectors with the following characteristics can be understood as a group with a complete meaning: the vector spacing of the digital or Chinese character part remains the same and the serial numbers are continuous, and there may be symbols such as "-", "×", "." to connect, such as Figure 4 As shown.

[0054] In a specific implementation, when using heuristic rules to process the steel bar layout drawing, it is necessary to find the position of the facade in the entire drawing and extract the vector blocks belonging to the facade size. Specifically, the filtered elements that may be text are converted into bitmaps while retaining the vector information, and then the converted bitmap is processed by OCR (Optical Character Recognition). According to the pre-established heuristic rules, the location of the title is found, and it is determined whether the title is located above or below the view. Finally, the elevation range in the steel bar layout drawing is determined to segment the elevation, so as to determine the global first steel bar distribution information according to the elevation elements; the first steel bar distribution information includes the steel bar intersection information and steel bar spacing distribution information of the global working area. Among them, the method for determining the title position can be: find the title with the largest y-direction coordinate. If there is no graphic above and there is a graphic below, it can be determined that the title is located above the view. The method for determining the range of the elevation drawing can be: first find the straight line where the title block "elevation" is located and the straight line where the center of the adjacent block below is located, and record them as straight line 1 and straight line 2 respectively, then use the coordinates of the title block "elevation" as a reference, select the x coordinate of the center of the word "elevation" as a reference to draw a vertical line downward, record it as straight line 3, and finally use straight line 3 as a reference, use straight line 4 parallel to straight line 3 to cut the figure on both sides of straight line 3, until straight line 4 just does not intersect with any figure to obtain straight line 5 and straight line 6. At this point, it can be considered that the elevation elements are segmented, and the range of the elevation drawing is the range framed by straight line 1, straight line 2, straight line 5, and straight line 6. After determining the range of the elevation drawing, according to the heuristic rules, the digital size elements in the elevation elements are screened out in the coordinate order, and the numbers connected by the symbol "×" are understood as "spacing × quantity", so as to obtain the first steel bar distribution information.

[0055] Step S12: determine the area type corresponding to the target image based on a preset image classification method, determine the initial working area based on the area type using a regional grid search method, and determine all target binding points in the initial working area based on a preset target detection method; the target image is an image captured by a target depth camera mounted on the steel bar binding robot; the area types include non-working area, working area boundary, working area interior and working area corner points.

[0056] In this embodiment, the target image is an image captured by a target depth camera mounted on the steel bar tying robot, such as Figure 5As shown, the steel bar binding robot will find the boundary of the working area based on the collected target image and determine the position of the initial working area, so as to autonomously adjust to the initial working area subsequently, thus eliminating the step of manually adjusting the pose of the robotic arm. Specifically, when the steel bar binding robot searches for the boundary of the working area to be bound (i.e., the boundary of the working area), it uses a preset image classification method to determine the region type of the target image to obtain the corresponding region type determination result, and obtains a new target image and the corresponding region type determination result based on the region type determination result through a region grid search method (such as grid equal division), thereby determining the initial working area, realizing guiding the robotic arm to quickly approach the boundary of the working area to adjust to the vicinity of the initial working area. The search order of the region grid search method can be the search order as shown in Figure 6 The search order shown, and the region types include non-working area, working area boundary, inside the working area, and corner points of the working area.

[0057] In this embodiment, in order to correspond the target image of the initial working area collected by the steel bar binding robot in real time with the first steel bar distribution information of the global working area, it is necessary to determine all the target binding points of the initial working area based on a preset target detection method. Specifically, it may include: filtering the target depth image corresponding to the initial working area based on a preset depth threshold to obtain a filtered depth map; using the preset target detection method to detect the filtered depth map to determine all the target binding points of the initial working area. Among them, the preset depth threshold can be a depth threshold determined based on the point cloud depth mean value of the target image to exclude the interference of multiple layers of steel bars and complex backgrounds through depth map filtering. In order to more accurately determine each target binding point of the initial working area, the first binding point of the initial working area can be determined first based on the preset target detection method, and then the robotic arm of the steel bar binding robot is adjusted based on the second position relationship to determine all the target binding points of the initial working area, so that the number of binding points in the target image captured by the steel bar binding robot is maximized. Among them, the second position relationship is the position relationship between the first binding point and the camera optical center of the target depth camera.

[0058] Step S13: Determine the first position relationship between the initial working area and the global working area based on the first steel bar distribution information and all the target binding points, so that the steel bar binding robot moves to the target working point corresponding to the initial working area based on the first position relationship to perform steel bar binding.

[0059] In this embodiment, by combining the steel bar spacing information and the target binding points in the initial working area, the initial working area is mapped to the global working area map, and the positions of the initial working area and the target binding points in the entire steel bar framework can be determined. In a specific implementation manner, determining the first positional relationship between the initial working area and the global working area based on the first steel bar distribution information and all the target binding points may specifically include: determining the second steel bar distribution information corresponding to the initial working area based on all the target binding points; determining the target steel bar intersection points corresponding to the target binding points in the global working area based on the first steel bar distribution information and the second steel bar distribution information; and determining the first positional relationship between the initial working area and the global working area based on the target steel bar intersection points. That is to say, after determining the target binding points in the initial working area, the second steel bar distribution information of the initial working area, such as the row and column spacing of the steel bars in the initial working area, can be calculated based on these target binding points. Then, using the first steel bar distribution information of the global working area obtained in the foregoing steps and combining with the second steel bar distribution information, the target steel bar intersection points corresponding to the positions of the target binding points in the global working area in the initial working area can be determined. Specifically, the target binding points in the initial working area can be numbered according to the labeling method as Figure 7 shown, and the steel bar intersection points in the global working area can be numbered. Finally, the label matching between the target binding points in the initial working area and the steel bar intersection points in the global working area is performed to determine the first positional relationship between the initial working area and the global working area, so as to guide and monitor the movement path planning and implementation of the steel bar binding robot. After that, the steel bar binding robot can move to the target working point corresponding to the initial working area based on the first positional relationship and perform the steel bar binding work.

[0060] It can be seen that after the target depth camera is used to collect the target image in this application, the initial working area can be quickly determined by using the preset image classification method and the regional grid search method. Then, the first positional relationship between the initial working area and the global working area is determined by using the information of all the target binding points in the initial working area and the first steel bar distribution information of the global working area, so that the steel bar binding robot can move to the working point corresponding to the initial working area based on the first positional relationship to perform the steel bar binding.

[0061] See Figure 8 shown, this application discloses a steel bar binding device applied to a steel bar binding robot, including:

[0062] A steel bar distribution information determination module 11, configured to determine the first steel bar distribution information of the global working area based on a preset global working area determination method; the first steel bar distribution information includes the steel bar intersection point information and the steel bar spacing distribution information of the global working area;

[0063] The lashing point determination module 12 is configured to determine the region type corresponding to the target image based on a preset image classification method, determine the initial working area based on the region type by using a region grid search method, and determine all target lashing points in the initial working area based on a preset target detection method; the target image is an image collected by a target depth camera mounted on the steel bar lashing robot; the region type includes a non-working area, a working area boundary, an interior of the working area, and a corner of the working area.

[0064] The steel bar lashing module 13 is configured to determine the first positional relationship between the initial working area and the global working area based on the first steel bar distribution information and all the target lashing points, so that the steel bar lashing robot can move to a target working point corresponding to the initial working area based on the first positional relationship to perform steel bar lashing.

[0065] It can be seen that after the target image is collected by using the target depth camera in this application, the initial working area can be quickly determined by using the preset image classification method and the region grid search method, and then the first positional relationship between the initial working area and the global working area is determined by using the information of all the target lashing points in the initial working area and the first steel bar distribution information of the global working area, so that the steel bar lashing robot can move to the working point corresponding to the initial working area based on the first positional relationship to perform steel bar lashing.

[0066] In a specific embodiment, the steel bar distribution information determination module 11 may specifically include:

[0067] The 3D modeling unit is configured to establish a target 3D model of the global working area by using a depth camera or a laser scanning device;

[0068] The first information determination unit is configured to perform 3D straight line fitting by using the target 3D model to determine the first steel bar distribution information of the global working area.

[0069] In a specific embodiment, the steel bar distribution information determination module 11 may specifically include:

[0070] The depth image acquisition unit is configured to capture the global working area by using a depth camera to obtain a global depth image corresponding to the global working area;

[0071] The second information determination unit is configured to determine the first steel bar distribution information of the global working area based on the global depth image.

[0072] In a specific embodiment, the steel bar distribution information determination module 11 may specifically include:

[0073] The elevation view determination unit is configured to determine a target elevation view based on the steel bar layout diagram of the global working area by using a preset heuristic rule;

[0074] A third information determining unit, configured to determine the first steel bar distribution information of the global working area based on the target elevation view.

[0075] In a specific embodiment, the binding point determining module 12 may specifically include:

[0076] A depth image filtering unit, configured to filter the target depth image corresponding to the initial working area based on a preset depth threshold to obtain a filtered depth map;

[0077] A first target binding point determining unit, configured to detect the filtered depth map by using a preset target detection method to determine all the target binding points of the initial working area.

[0078] In a specific embodiment, the binding point determining module 12 may specifically include:

[0079] An initial binding point determining unit, configured to determine the first binding point of the initial working area based on a preset target detection method;

[0080] A second target binding point determining unit, configured to adjust the robotic arm of the steel bar binding robot based on a second positional relationship to determine all the target binding points of the initial working area;

[0081] Wherein, the second positional relationship is the positional relationship between the first binding point and the camera optical center of the target depth camera.

[0082] In a specific embodiment, the steel bar binding module 13 may specifically include:

[0083] An initial working area information determining unit, configured to determine the second steel bar distribution information corresponding to the initial working area based on all the target binding points;

[0084] A steel bar intersection point determining unit, configured to determine the target steel bar intersection points corresponding to the target binding points in the global working area based on the first steel bar distribution information and the second steel bar distribution information;

[0085] A first positional relationship determining unit, configured to determine the first positional relationship between the initial working area and the global working area based on the target steel bar intersection points.

[0086] Furthermore, an embodiment of the present application also discloses an electronic device, Figure 9 It is a structural diagram of an electronic device 20 shown according to an exemplary embodiment, and the content in the figure cannot be considered as any limitation to the scope of use of the present application.

[0087] Figure 9Schematic diagram of the structure of an electronic device 20 provided by an embodiment of the present application. The electronic device 20 may specifically include: at least one processor 21, at least one memory 22, a power supply 23, a communication interface 24, an input / output interface 25, and a communication bus 26. Among them, the memory 22 is used to store a computer program, and the computer program is loaded and executed by the processor 21 to implement the relevant steps in the steel bar binding method disclosed in any of the foregoing embodiments. In addition, the electronic device 20 in this embodiment may specifically be an electronic computer.

[0088] In this embodiment, the power supply 23 is used to provide working voltage for each hardware device on the electronic device 20; the communication interface 24 can create a data transmission channel between the electronic device 20 and external devices, and the communication protocol it follows is any communication protocol applicable to the technical solution of the present application, and no specific limitation is imposed on it here; the input / output interface 25 is used to obtain external input data or output data to the outside, and its specific interface type can be selected according to specific application needs, and no specific limitation is made here.

[0089] In addition, as a carrier for resource storage, the memory 22 may be a read-only memory, a random access memory, a magnetic disk, or an optical disc, etc., and the resources stored thereon may include an operating system 221, a computer program 222, etc., and the storage method may be temporary storage or permanent storage.

[0090] Among them, the operating system 221 is used to manage and control each hardware device and the computer program 222 on the electronic device 20, and it may be Windows Server, Netware, Unix, Linux, etc. In addition to the computer program that can be used to complete the steel bar binding method executed by the electronic device 20 disclosed in any of the foregoing embodiments, the computer program 222 may further include computer programs that can be used to complete other specific tasks.

[0091] Furthermore, the present application also discloses a computer-readable storage medium for storing a computer program; wherein, when the computer program is executed by a processor, the steel bar binding method disclosed above is implemented. For the specific steps of this method, reference may be made to the corresponding content disclosed in the foregoing embodiments, and details will not be repeated here.

[0092] In the present specification, the various embodiments are described in a progressive manner, and the key points of each embodiment are the differences from other embodiments. The same or similar parts among the various embodiments may be referred to each other. For the device disclosed in the embodiments, since it corresponds to the method disclosed in the embodiments, the description is relatively simple, and the relevant parts may be referred to the description of the method part.

[0093] Those skilled in the art may further realize that the units and algorithm steps of each example described in connection with the embodiments disclosed herein can be implemented by electronic hardware, computer software, or a combination of the two. To clearly illustrate the interchangeability of hardware and software, the components and steps of each example have been generally described according to their functions in the above description. Whether these functions are executed in a hardware or software manner depends on the specific application and design constraints of the technical solution. Those skilled in the art can use different methods to implement the described functions for each specific application, but such implementation should not be considered to exceed the scope of this application.

[0094] The steps of the methods or algorithms described in connection with the embodiments disclosed herein can be directly implemented by hardware, software modules executed by a processor, or a combination of the two. The software modules can be placed in a random access memory (RAM), internal memory, read-only memory (ROM), electrically programmable ROM, electrically erasable programmable ROM, registers, hard disk, removable disk, CD-ROM, or any other form of storage medium known in the art.

[0095] Finally, it should also be noted that in this document, relational terms such as "first" and "second" are only used to distinguish one entity or operation from another entity or operation, and do not necessarily require or imply any actual relationship or order between these entities or operations. Moreover, the terms "comprising", "including" or any other variation thereof are intended to cover non-exclusive inclusion, so that a process, method, article or device comprising a series of elements includes not only those elements but also other elements not expressly listed, or elements inherent to such process, method, article or device. Without further limitation, an element defined by the statement "comprising an..." does not exclude the presence of additional identical elements in the process, method, article or device comprising the element.

[0096] The technical solutions provided in this application have been introduced in detail above. Specific examples have been used herein to illustrate the principles and implementation manners of this application. The description of the above embodiments is only used to help understand the method and its core idea of this application; at the same time, for those of ordinary skill in the art, according to the idea of this application, there will be changes in the specific implementation manners and application scopes. In summary, the content of this specification should not be construed as a limitation to this application.

Claims

1. A method for tying steel bars, characterized in that: Applied to steel bar tying robots, including: Determine first steel bar distribution information of the global operation area based on a preset global operation area determination method; the first steel bar distribution information includes steel bar intersection information and steel bar spacing distribution information of the global operation area; Determine the area type corresponding to the target image based on a preset image classification method, determine the initial working area based on the area type using a regional grid search method, and determine all target binding points in the initial working area based on a preset target detection method; the target image is an image captured by a target depth camera mounted on the steel bar binding robot; the area types include non-working area, working area boundary, working area interior and working area corner points; Based on the first steel bar distribution information and all the target binding points, a first positional relationship between the initial operation area and the global operation area is determined so that the steel bar binding robot moves to the target operation point corresponding to the initial operation area based on the first positional relationship to perform steel bar binding.

2. The steel bar binding method according to claim 1, characterized in that: The method of determining the first steel bar distribution information of the global operating area based on a preset global operating area determination method includes: Using a depth camera or laser scanning equipment to establish a target three-dimensional model of the global operating area; The target three-dimensional model is used to perform three-dimensional straight line fitting to determine the first steel bar distribution information of the global operation area.

3. The steel bar binding method according to claim 1, characterized in that: The method of determining the first steel bar distribution information of the global operating area based on a preset global operating area determination method includes: Using a depth camera to photograph the global operating area to obtain a global depth image corresponding to the global operating area; The first steel bar distribution information of the global working area is determined based on the global depth image.

4. The steel bar binding method according to claim 1, characterized in that: The method of determining the first steel bar distribution information of the global operating area based on a preset global operating area determination method includes: Determine a target elevation drawing based on a reinforcement arrangement drawing of the global work area using a preset heuristic rule; The first steel bar distribution information of the global working area is determined based on the target elevation view.

5. The steel bar binding method according to claim 1, characterized in that: The determining of all target lashing points in the initial operation area based on a preset target detection method includes: Filtering the target depth image corresponding to the initial operation area based on a preset depth threshold to obtain a filtered depth map; The filtered depth map is detected using a preset target detection method to determine all the target binding points in the initial operation area.

6. The steel bar binding method according to claim 1, characterized in that: The determining of all target lashing points in the initial operation area based on a preset target detection method includes: Determine the first lashing point of the initial operation area based on a preset target detection method; Adjusting the mechanical arm of the steel bar tying robot based on the second position relationship to determine all the target tying points in the initial operation area; The second positional relationship is the positional relationship between the first binding point and the camera optical center of the target depth camera.

7. The steel bar binding method according to any one of claims 1 to 6, characterized in that: The determining a first positional relationship between the initial operation area and the global operation area based on the first steel bar distribution information and all the target binding points includes: Determine the second steel bar distribution information corresponding to the initial operation area based on all the target binding points; Determine each target steel bar intersection point corresponding to each target binding point in the global operation area based on the first steel bar distribution information and the second steel bar distribution information; A first positional relationship between the initial operation area and the global operation area is determined based on each of the target steel bar intersection points.

8. A steel bar tying device, characterized in that: Applied to steel bar tying robots, including: A reinforcement distribution information determination module, used to determine first reinforcement distribution information of a global operation area based on a preset global operation area determination method; the first reinforcement distribution information includes reinforcement intersection information and reinforcement spacing distribution information of the global operation area; A binding point determination module is used to determine the area type corresponding to the target image based on a preset image classification method, and to determine the initial working area based on the area type using a regional grid search method, and to determine all target binding points in the initial working area based on a preset target detection method; the target image is an image captured by a target depth camera mounted on the steel bar binding robot; the area types include non-working area, working area boundary, working area interior and working area corner point; A rebar tying module is used to determine a first position relationship between the initial operation area and the global operation area based on the first rebar distribution information and all the target tying points, so that the rebar tying robot moves to the target operation point corresponding to the initial operation area based on the first position relationship to perform rebar tying.

9. An electronic device, characterized in that: include: Memory, used to store computer programs; A processor, used to execute the computer program to implement the steel bar binding method according to any one of claims 1 to 7.

10. A computer-readable storage medium, characterized in that: Used to store a computer program, wherein the computer program, when executed by a processor, implements the steel bar binding method according to any one of claims 1 to 7.

Images