Point cloud-based lifting hook positioning method and device, equipment and medium

Abstract

The invention discloses a lifting hook positioning method, device and equipment based on point cloud and a medium, and relates to the technical field of engineering machinery. The lifting hook positioning method comprises the steps that initial lifting rope point clouds of a plurality of lifting ropes of a lifting hook are obtained and preprocessed, and first lifting rope point clouds are obtained; performing interpolation processing on the first lifting rope point cloud to obtain a second lifting rope point cloud; performing point cloud segmentation for the plurality of lifting ropes based on the second lifting rope point cloud; performing straight line fitting according to a point cloud segmentation result to obtain direction vectors of one or more lifting ropes; and determining the position of the lifting hook according to the obtained direction vector and the size information of the corresponding lifting rope and the lifting hook. According to the embodiment of the invention, the problem that the lifting rope point cloud is sparse under the scenes of fast illumination change, long lifting hook distance and the like is solved through point cloud interpolation, and the spatial position of the lifting hook is obtained by calculating the direction vector of the lifting rope, so that the required calculation resources are few, the precision is high, and the real-time performance is strong.

Description

Technical Field

[0001] This application relates to the technical field of construction machinery, and specifically relates to a hook positioning method, device, equipment and medium based on point cloud. Background Art

[0002] During the hoisting operation, whether it is an empty hook or a load, manual judgment of the hook position is required, and then the machine operator is commanded to operate. In the complex environment of the construction site, there are a large number of obstacles around the hook. The vision of manual workers is limited, and there is also a situation where communication is not timely, resulting in safety accidents. Moreover, the labor cost is gradually increasing. Therefore, a method capable of obtaining the accurate spatial position of the hook is needed to replace manual observation. However, currently, most of the methods for hook positioning are based on visual detection, and are not applicable in scenarios such as rapid light change and long hook distance due to the inherent properties of the camera.

[0003] In this regard, some hook positioning methods based on point cloud segmentation have also emerged in the prior art, but these methods have at least the following defects:

[0004] First, for different hooks, a large amount of point cloud data needs to be collected each time, and the universality is poor. Moreover, the point cloud obtained in scenarios such as rapid light change and long hook distance is quite sparse, and the hook cannot be accurately positioned.

[0005] Second, usually, deep learning algorithms and other methods are used to train and segment the hook point cloud data, but only specific types of hooks can be recognized, and it cannot be directly adapted to different types of construction machinery. Moreover, the segmentation process requires manual selection, and the steps are relatively cumbersome.

[0006] Third, when segmenting the hook point cloud, it depends on the minimum bounding box of the cable point cloud to judge the cable direction. In the case of uneven cable point cloud or incomplete local data, direction deviation may occur. Moreover, when the hook is far away, the sparsity of the hook point cloud will cause a large difference between the length and width of the hook point cloud and the actual length and width, resulting in a high segmentation error rate.

[0007] Therefore, the embodiments of this application provide a new hook positioning solution. Summary of the Invention

[0008] The purpose of the embodiments of this application is to provide a hook positioning method, device, equipment and medium based on point cloud, so as to solve at least partially the above technical problems.

[0009] To achieve the above object, a first aspect of the present application provides a hook positioning method based on point cloud, including: acquiring and preprocessing the initial point cloud of multiple suspension ropes of the hook to obtain the first suspension rope point cloud; performing interpolation processing on the first suspension rope point cloud to obtain the second suspension rope point cloud; performing point cloud segmentation on the second suspension rope point cloud for the multiple suspension ropes; performing linear fitting according to the point cloud segmentation result to obtain the direction vectors of one or more suspension ropes; and determining the position of the hook according to the obtained direction vectors and the dimension information of the corresponding suspension ropes and the hook.

[0010] In an embodiment of the present application, acquiring the initial point cloud of the suspension rope includes: scanning the multiple suspension ropes in real time through a point cloud acquisition device to obtain the corresponding suspension rope point cloud data, and taking the suspension rope point cloud data scanned within a preset period as the initial point cloud of the suspension rope. Wherein, the sensing range of the point cloud acquisition device covers at least the multiple suspension ropes and the hook.

[0011] In an embodiment of the present application, preprocessing the initial point cloud data includes: performing filtering processing on the initial point cloud of the suspension rope, and retaining the point cloud of the suspension rope within a set range as the first point cloud of the suspension rope, where the set range is determined based on the farthest point of the suspension rope scanned by the point cloud acquisition device.

[0012] In an embodiment of the present application, performing interpolation processing on the first point cloud of the suspension rope includes: for the first point cloud of the suspension rope, performing nearest neighbor search based on a KD tree, and inserting a point cloud between each point cloud and its nearest neighbor point.

[0013] In an embodiment of the present application, the point cloud segmentation for the multiple suspension ropes based on the second point cloud of the suspension rope includes: extracting the edge point cloud of the second point cloud of the suspension rope to obtain the third point cloud of the suspension rope retaining the edge feature; filtering the third point cloud of the suspension rope based on the point cloud intensity, and retaining the point cloud of the suspension rope with the point cloud intensity less than a set value as the fourth point cloud of the suspension rope; projecting the fourth point cloud of the suspension rope corresponding to each suspension rope respectively to obtain the corresponding planar point cloud; and performing clustering segmentation on the planar point cloud to obtain the final point cloud segmentation result.

[0014] In an embodiment of the present application, extracting the edge point cloud of the second point cloud of the suspension rope includes: traversing all the point clouds in the second point cloud of the suspension rope to find the neighborhood of each point cloud and performing tangent plane projection towards the neighborhood; according to the projection result, connecting each point cloud with the corresponding projected point cloud in its neighborhood pairwise to obtain the angle value of the corresponding connection line; and for all the obtained angle values, screening out the edge point cloud according to the comparison result with a set angle threshold.

[0015] In the embodiments of the present application, determining the position of the hook includes: calculating the end coordinates of the suspension rope according to the obtained direction vector, the length of the corresponding suspension rope, and the starting point coordinates; and determining the position of the hook according to the end coordinates of the suspension rope and the size of the hook.

[0016] The second aspect of the present application provides a hook positioning device based on point cloud, including: a memory configured to store instructions; and a processor configured to call the instructions from the memory and capable of implementing any of the above hook positioning methods when executing the instructions.

[0017] The third aspect of the present application provides a hook positioning device based on point cloud, including: any of the above hook positioning devices; and a point cloud acquisition device for acquiring and providing point cloud data to the hook positioning device. Among them, the point cloud acquisition device has a sensing range that at least covers multiple suspension ropes and the hook.

[0018] The fourth aspect of the present application provides a machine-readable storage medium, on which instructions are stored for causing a machine to execute any of the above hook positioning methods.

[0019] Through the above technical solutions, the embodiments of the present application solve the problem that the suspension rope point cloud is relatively sparse in scenarios such as fast-changing illumination and long distance of the hook through point cloud interpolation, and obtain the spatial position of the hook by calculating the direction vector of the suspension rope, resulting in less computing resources required, high precision, and strong real-time performance.

[0020] Other features and advantages of the embodiments of the present application will be described in detail in the subsequent specific implementation section. Description of the Drawings

[0021] The drawings are used to provide a further understanding of the embodiments of the present application, and constitute a part of the specification, and are used to explain the embodiments of the present application together with the following specific implementation, but do not constitute a limitation to the embodiments of the present application. In the drawings:

[0022] Figure 1 Schematically shows a flowchart of a hook positioning method based on point cloud according to an embodiment of the present application;

[0023] Figure 2 Is a schematic diagram of the installation position of the tower crane lidar in the example of the embodiment of the present application;

[0024] Figure 3 Is a schematic diagram of the first suspension rope point cloud of four steel wire suspension ropes obtained in the example of the embodiment of the present application;

[0025] Figure 4 Is a flowchart of point cloud segmentation in the embodiment of the present application;

[0026] Figure 5 It is a schematic diagram of separate projection in the examples of the embodiments of the present application;

[0027] Figure 6 It is the point cloud effect diagram after separate projection in the examples of the embodiments of the present application;

[0028] Figure 7 It is the segmentation effect diagram of the steel wire suspension rope in the examples of the embodiments of the present application; and

[0029] Figure 8 Schematically shows the structural block diagram of a hook positioning device based on point cloud according to an embodiment of the present application. Detailed implementation manners

[0030] To make the objectives, technical solutions and advantages of the embodiments of the present application clearer, the technical solutions in the embodiments of the present application will be clearly and completely described below with reference to the accompanying drawings in the embodiments of the present application. It should be understood that the specific implementation manners described herein are only used to illustrate and explain the embodiments of the present application, and are not used to limit the embodiments of the present application. All other embodiments obtained by those of ordinary skill in the art based on the embodiments in the present application without creative efforts belong to the scope protected by the present application.

[0031] It should be noted that the acquisition, transmission, storage, use, processing, etc. of data in the technical solutions of the present application all comply with the relevant provisions of national laws and regulations. In the embodiments of the present application, some industry-existing solutions such as certain software, components, models, etc. may be mentioned, and they should be regarded as exemplary. The purpose is only to illustrate the feasibility in the implementation of the technical solutions of the present application, but it does not mean that the applicant has already or necessarily used this solution.

[0032] It should be noted that if there are directional indications (such as up, down, left, right, front, back...) involved in the embodiments of the present application, then the directional indications are only used to explain the relative positional relationship and movement conditions between components in a certain specific posture (as shown in the drawings). If the specific posture changes, the directional indications will also change accordingly.

[0033] In addition, if the embodiments of the present application involve descriptions such as "first" and "second", the descriptions of "first", "second", etc. are only for descriptive purposes and should not be construed as indicating or implying their relative importance or implicitly specifying the quantity of the indicated technical features. Thus, the features defined with "first" and "second" may explicitly or implicitly include at least one such feature. In addition, the technical solutions between various embodiments may be combined with each other, but it must be based on the fact that those of ordinary skill in the art can implement them. When the combination of technical solutions is contradictory or cannot be implemented, it should be considered that such a combination of technical solutions does not exist and is not within the scope of protection required by the present application.

[0034] Figure 1 Schematically shows a flowchart of a hook positioning method based on point cloud according to an embodiment of the present application. As Figure 1 shown, the embodiment of the present application provides a hook positioning method based on point cloud, and this method may include the following steps S100 - S500.

[0035] Step 100, obtain and preprocess the initial rope point clouds of multiple ropes of the hook to obtain the first rope point cloud.

[0036] In a preferred embodiment, obtaining the initial rope point cloud includes: real - time scanning the multiple ropes through a point cloud acquisition device to obtain corresponding rope point cloud data, and taking the rope point cloud data scanned within a preset period as the initial rope point cloud. Wherein, the sensing range of the point cloud acquisition device covers at least the multiple ropes and the hook. Taking a tower crane as an example, the point cloud acquisition device is vertically installed downward on the luffing trolley of the tower crane and is relatively fixed in position with respect to the multiple ropes. The following examples will continue to take "the point cloud acquisition device is vertically installed downward on the luffing trolley of the tower crane" as an example, but it should be noted that for different working machines, such as crawler cranes, tyre cranes, port cranes, etc., the installation position of the point cloud acquisition device can be different. For example, for a crawler crane or a tyre crane, the point cloud acquisition device can be installed on its boom head.

[0037] In a preferred embodiment, preprocessing the initial point cloud data includes: performing filtering processing on the initial rope point cloud, and retaining the rope point cloud within a set range as the first rope point cloud, where the set range is determined based on the farthest point of the rope scanned by the point cloud acquisition device.

[0038] The execution of step S100 will be specifically described below through an example. In this example, taking the point cloud acquisition device as a lidar as an example, and Figure 2 is a schematic diagram of the installation position of the tower crane lidar in the example of the embodiment of the present application. As Figure 2As shown in the figure, a laser radar is installed vertically downward on the tower crane's luffing trolley. The sensing range of the laser radar is shown in the red cone in the figure. The sensing area covers the wire rope, the hook and the surrounding environment. The wire rope is relatively fixed relative to the installation position of the laser radar. Figure 2 Installation position diagram, install the laser radar on the variable-length trolley, record the relative position coordinates of the laser radar and the wire rope during installation, and set the laser radar's coordinate system with the X-axis in front, perpendicular to the ground, and the Z-axis on the right, in accordance with the right-hand rule.

[0039] In this example, after installing the laser radar, first set the laser radar scanning mode to non-repetitive scanning to start the point cloud scanning of the wire rope. In addition, in order to take into account both the integrity of the point cloud data and the real-time detection, the point cloud scanned with a preset period t is generally used as a frame of point cloud data (which can be called a processing frame), that is, the initial rope point cloud. Then, according to the characteristics of the laser radar, a frame of point cloud data is filtered, such as performing a straight-through filtering in the X-axis direction. Through straight-through filtering, the portion containing clear wire rope point clouds is selected, and the remaining point clouds are removed. For example, the point cloud within the range R (that is, the set range above) is retained, where Figure 2 As shown in the figure, R is the distance from the center of the laser radar to the farthest point of the wire rope that it can scan, and the range R is an empirical value obtained based on historical scanning of the wire rope. Similarly, the Y-axis and Z-axis directions are filtered to obtain a point cloud that only retains the point cloud within the shaking range of the wire rope, that is, the first rope point cloud is obtained.

[0040] It should be noted that in other examples, binocular cameras or the like can be used as point cloud acquisition devices, and other types of lifting ropes besides steel wire ropes can be used.

[0041] Step S200: interpolating the first suspension rope point cloud to obtain a second suspension rope point cloud.

[0042] In a preferred embodiment, the interpolation process includes: for the first suspension rope point cloud, performing a nearest neighbor search based on a KD tree, and inserting a point cloud between each point cloud and its nearest neighbor point.

[0043] Successor to Figure 2 For example, Figure 3 This is a schematic diagram of the first rope point cloud of the four wire ropes obtained in the example of the embodiment of the present application. During the operation of the crane, the wire rope, hook and load will shake due to inertia. Especially on large lifting equipment, the farther the distance, the faster the end speed. The non-repetitive scanning laser radar has a denser point cloud than the repetitive laser radar, but in this case it is still impossible to obtain an ideal wire rope point cloud, such as Figure 3As shown, there will be obvious breakpoints in the point cloud of the same steel wire suspension rope, and the point cloud is very sparse, similar to the characteristics of noise points, which affects judgment and results in incorrect identification results of the suspension rope.

[0044] Therefore, for Figure 3 , interpolation is performed on the point cloud of the steel wire suspension rope, and the nearest neighbor search is carried out based on the KD tree. A point cloud is inserted between the original point cloud and the nearest neighbor point, and this step is executed for all point clouds to obtain the second suspension rope point cloud.

[0045] Step S300, perform point cloud segmentation for the multiple suspension ropes based on the second suspension rope point cloud.

[0046] In a preferred embodiment, as Figure 4 shown, the point cloud segmentation corresponding to this step S300 may include the following steps S310 - S340.

[0047] Step S310, extract the edge point cloud from the second suspension rope point cloud to obtain the third suspension rope point cloud that retains the edge features.

[0048] If there is a non - steel - wire suspension rope point cloud in the selected scanning space, after the above interpolation processing, the number of non - steel - wire suspension rope point clouds will also increase, interfering with the final calculation. Therefore, this step S310 extracts the edge point cloud (or boundary point cloud) from the interpolated point cloud.

[0049] Further, in the example, based on the angle method for edge feature detection and edge point cloud extraction, it may include: traversing all the point clouds in the second suspension rope point cloud to find the neighborhood of each point cloud and performing a tangent plane projection towards the neighborhood; according to the projection result, connecting each point cloud with the corresponding projected point cloud in its neighborhood pairwise to obtain the angle value of the corresponding connection; for all the obtained angle values, based on the comparison result with the set angle threshold, filter out the edge point cloud. For example, find the maximum value of the angle. The larger the value, the more likely the point is an edge point, and then set the angle threshold to distinguish between edge points and non - edge points.

[0050] Step S320, filter the third suspension rope point cloud based on the point cloud intensity, and retain the suspension rope point cloud with a point cloud intensity less than the set value as the fourth suspension rope point cloud.

[0051] In the example, the steel wire suspension rope is straightened under the action of gravity. Therefore, after edge detection, the point cloud of the steel wire suspension rope can be completely retained, and noise can be further removed based on this. The reflectivity of the steel wire suspension rope is relatively low, so it can be filtered according to the intensity of the point cloud. For example, only retain the point cloud with an intensity less than f as the fourth suspension rope point cloud, where the point cloud with an intensity less than f can be understood as the point cloud of the part with a reflection intensity of the steel wire suspension rope.

[0052] Step S330: Project the fourth sling point clouds corresponding to each sling rope respectively to obtain the corresponding planar point clouds.

[0053] Continuing with the above example, after the above processing, it can be considered that only the complete steel wire sling point clouds are retained. Now, according to the relative positions of the steel wire slings and the lidar, the point clouds are projected onto, for example, the YOZ plane. The relative positions of the 4 steel wire slings and the lidar in the example are fixed. The steel wires on the left and right sides of the lidar can be projected separately, as Figure 5 shown. The points of the same steel wire sling on the same side are closer. Better separation results can be obtained through separate projection. It should be noted that here, 4 steel wire slings are taken as an example, but it is also applicable to scenarios corresponding to other numbers of sling ropes. For example, for two sling ropes, separate projection is also required because the lidar is installed at the middle position between the starting points of the two steel wire slings, and the steel wire slings are still on different half-axes.

[0054] Step S340: Perform clustering segmentation on the planar point clouds to obtain the final point cloud segmentation result.

[0055] For example, perform clustering segmentation on the projected point clouds based on the DBScan method. Continuing with the above example, the initial point clouds have no categories. As Figure 3 shown, if no projection is performed, the distances between the end point clouds of each steel wire sling are close, which may cause multiple steel wire slings to be misclassified as 1 or be segmented into 5 during clustering segmentation. After performing separate projection as Figure 5 shown, the point cloud effect is as Figure 6 shown. The distances between the 4 steel wire ropes are large, and they can be correctly classified. According to the clustering segmentation result of the projection, the final segmentation effect of the original steel wire sling is as Figure 7 shown. It can be easily seen that the end point clouds with similar points in blue and dark green can be correctly segmented into 2 steel wire ropes.

[0056] After completing the above point cloud segmentation, return to Figure 1 Continue to introduce other steps of the hook positioning method according to the embodiments of the present application.

[0057] Step S400: Perform linear fitting according to the point cloud segmentation result to obtain the direction vectors of one or more sling ropes.

[0058] Continuing from the above example, for the 4 classified steel wire ropes, based on the random consistency sampling method, straight line fitting is performed for each type of point cloud, and the direction vectors of the 4 straight lines can be obtained respectively. When the coordinates of a point and the direction vector of the straight line on which it is located are known, the coordinates of another point can be obtained according to the length of the straight line. It should also be noted that after the direction vector is normalized, the angle between it and the XYZ coordinate axis is the rope runout, so the embodiment of the present application can be understood as taking the rope runout into account to locate the hook.

[0059] Step S500, determining the position of the hook according to the obtained direction vector and the size information of the corresponding lifting rope and the lifting hook.

[0060] In a preferred embodiment, step S500 may include: calculating the end coordinates of the suspension rope according to the obtained direction vector and the length and starting point coordinates of the corresponding suspension rope; and determining the position of the suspension hook according to the end coordinates of the suspension rope and the size of the hook.

[0061] In the above example, the direction vectors of the four wire ropes are different, and the coordinates of the starting point in the laser radar coordinate system are also different. The starting point and the direction vector are one-to-one corresponding. When the starting point is selected, the direction vector of the wire rope needs to be fixedly calculated to obtain the hook position.

[0062] Therefore, following the above example, firstly, the relative order of the four wire ropes is obtained according to the relative position of the center point of the cluster, that is, the direction vector order of the four ropes. Figure 6 As shown, assuming that after the four steel wire ropes are clustered, the coordinates of their cluster center points on the blue coordinate axis are 5, 2, -2, -5 (light green, dark green, blue, purple), then the relative order of the steel wire ropes can be determined based on this value. In this example, the steel wire rope corresponding to the maximum value is always taken for subsequent calculations, that is, the steel wire rope on the far left. Because according to the display of the point cloud, the point cloud of the leftmost steel wire rope is the most complete, and the point cloud is clearer when the shaking is larger. However, it should be noted that the selection of the steel wire rope used for calculation is based on a comprehensive selection based on the radar installation location and actual conditions, and multiple steel wire ropes can also be selected, and the embodiments of the present application are not limited to this.

[0063] Furthermore, suppose the direction vector of the leftmost wire rope after linear fitting is The starting point of the wire rope has a coordinate of A(x a ,y a ,z a ), combined with the wire rope length L obtained from the tower crane operating data, the wire rope end coordinate B (x b ,yb , z b ):

[0064]

[0065] After obtaining the coordinates of the end of the wire rope sling, the actual spatial position of the hook can be further obtained according to the hook size.

[0066] In summary, on the one hand, the embodiment of the present application solves the problem that the wire rope sling point cloud is relatively sparse in scenarios such as fast-changing illumination and far distance of the hook through point cloud interpolation, and is not restricted by environmental factors such as the distance of the hook and the scene light. On the other hand, the spatial position of the hook is obtained by calculating the direction vector of the wire rope sling, which requires less computing resources, has high precision, and strong real-time performance. Combining the above examples, the embodiment of the present application specifically includes the following advantages:

[0067] (1) In the example, only one lidar is installed under the luffing trolley of the tower crane, and the sensing range is conical, which can completely cover the hook, the load, the wire rope sling and the surrounding environment. At the same time, the lidar can also be used for obstacle detection. Therefore, the hook spatial position detection and subsequent obstacle recognition can share the same sensor, and the cost is relatively low.

[0068] (2) In the example, by detecting the wire rope sling and combining the working condition data of the tower crane, the actual spatial position of the hook can be quickly estimated, and subsequent obstacle collision prevention detection can be carried out according to this position, with strong real-time performance and wide adaptability.

[0069] (3) In the example, there is no need to adopt existing point cloud segmentation methods such as deep learning, model matching, and minimum bounding box, and there is no need to implement corresponding data collection and training. Only traditional point cloud processing and line fitting are required, which requires less computing resources, is not restricted by the distance of the hook, and has strong universality. For example, when the tower crane performs operations such as "winding around a column", the spatial position of the hook can be transmitted back to the operator in real time.

[0070] (4) In the example, point cloud filtering is carried out by using the point cloud intensity information and the physical characteristics of the wire rope sling, which can effectively reduce the interference of airborne noise on the detection result and has good robustness.

[0071] Figure 8 Schematically shows a structural block diagram of a hook positioning device based on point cloud according to an embodiment of the present application. As Figure 8 shown, the embodiment of the present application provides a hook positioning device, which may include: a memory configured to store instructions; and a processor configured to call instructions from the memory and be able to implement the hook positioning method of the above embodiment when executing the instructions.

[0072] In the example, the hook positioning device is, for example, a controller integrated in the tower crane console or a remote controller. Therefore, the operator of the tower crane console or the remote supervisor can know the spatial position of the hook in real time.

[0073] An embodiment of the present application further provides a hook positioning device based on point cloud, which may include: the hook positioning device of the above embodiment; and a point cloud acquisition device for acquiring and providing point cloud data to the hook positioning device. Among them, the point cloud acquisition device is, for example, vertically installed downward on the luffing trolley of the tower crane, and is relatively fixed in position with respect to multiple suspension ropes, and has a sensing range that at least covers the multiple suspension ropes and the hook. In the example, the point cloud acquisition device is, for example, a lidar or a binocular camera.

[0074] An embodiment of the present application further provides a machine-readable storage medium, on which instructions are stored, and the instructions are used to cause the machine to execute the above hook positioning method.

[0075] An embodiment of the present application further provides a working machine, including the above hook positioning device. The working machine is, for example, various types of cranes (tower cranes, crawler cranes, rubber-tired cranes, port cranes, etc.), elevators, forklifts, monorail systems, etc.

[0076] Those skilled in the art should understand that the embodiments of the present application may provide a method, a system or a computer program product. Therefore, the present application may take the form of a complete hardware embodiment, a complete software embodiment, or an embodiment combining software and hardware aspects. Moreover, the present application may take the form of a computer program product implemented on one or more computer-usable storage media (including but not limited to disk storage, CD-ROM, optical storage, etc.) containing computer-usable program code.

[0077] The present application is described with reference to the flowcharts and / or block diagrams of methods, devices (systems), and computer program products according to the embodiments of the present application. It should be understood that each flow and / or block in the flowchart and / or block diagram, and the combination of flows and / or blocks in the flowchart and / or block diagram, can be implemented by computer program instructions. These computer program instructions can be provided to the processor of a general-purpose computer, a special-purpose computer, an embedded processor, or other programmable data processing devices to generate a machine, so that the instructions executed by the processor of the computer or other programmable data processing devices generate a device for realizing the functions specified in Figure 1 one process or multiple processes and / or blocks Figure 1 one block or multiple blocks.

[0078] These computer program instructions can also be stored in a computer-readable memory that can direct a computer or other programmable data processing apparatus to operate in a particular manner, such that the instructions stored in the computer-readable memory produce an article of manufacture including an instruction means that implements the function specified in one process Figure 1 one process or a plurality of processes and / or blocks Figure 1 in one block or a plurality of blocks.

[0079] These computer program instructions can also be loaded onto a computer or other programmable data processing apparatus, such that a series of operational steps are performed on the computer or other programmable apparatus to produce a computer-implemented process, whereby the instructions executed on the computer or other programmable apparatus provide steps for implementing the function specified in one process Figure 1 one process or a plurality of processes and / or blocks Figure 1 in one block or a plurality of blocks.

[0080] In a typical configuration, a computing device includes one or more processors (CPUs), an input / output interface, a network interface, and memory.

[0081] The memory may include non-permanent memory in the computer-readable medium, in the form of random access memory (RAM) and / or non-volatile memory such as read-only memory (ROM) or flash memory (flash RAM). The memory is an example of a computer-readable medium.

[0082] Computer-readable media includes both permanent and non-permanent, removable and non-removable media implemented by any method or technology for storage of information such as computer-readable instructions, data structures, program modules or other data. Examples of computer storage media include, but are not limited to, phase change memory (PRAM), static random access memory (SRAM), dynamic random access memory (DRAM), other types of random access memory (RAM), read-only memory (ROM), electrically erasable programmable read-only memory (EEPROM), flash memory or other memory technologies, compact disc read-only memory (CD-ROM), digital versatile discs (DVD) or other optical storage, magnetic cassettes, magnetic disk storage or other magnetic storage devices or any other non-transmission media that can be used to store information accessible by a computing device. As defined herein, computer-readable media does not include transitory media such as modulated data signals and carrier waves.

[0083] It should also be noted that the term "comprising", "including" or any other variant thereof is intended to cover non-exclusive inclusion, such that a process, method, commodity 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, commodity 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, commodity or device comprising the element.

[0084] The above are only embodiments of the present application and are not intended to limit the present application. For those skilled in the art, various changes and modifications can be made to the present application. Any modification, equivalent replacement, improvement, etc. made within the spirit and principle of the present application shall be included within the scope of the claims of the present application.

Claims

1. A hook positioning method based on point cloud, characterized in that: include: Acquire and pre-process initial suspension rope point clouds of the plurality of suspension ropes of the suspension hook to obtain a first suspension rope point cloud; Performing interpolation processing on the first suspension rope point cloud to obtain a second suspension rope point cloud; performing point cloud segmentation for the plurality of suspension ropes based on the second suspension rope point cloud; Perform straight line fitting according to the point cloud segmentation result to obtain the direction vector of one or more suspension ropes; as well as The position of the hook is determined according to the obtained direction vector and the size information of the corresponding lifting rope and the lifting hook.

2. The method for positioning the hook according to claim 1, characterized in that: Acquiring the initial suspension rope point cloud includes: Scanning the plurality of suspension ropes in real time by a point cloud acquisition device to obtain corresponding suspension rope point cloud data, and using the suspension rope point cloud data obtained by scanning within a preset period as the initial suspension rope point cloud; Wherein, the sensing range of the point cloud acquisition device at least covers the multiple suspension ropes and the suspension hook.

3. The method for positioning the hook according to claim 2, characterized in that: Preprocessing the initial point cloud data includes: The initial suspension rope point cloud is filtered, and the suspension rope point cloud within a set range is retained as a first suspension rope point cloud, wherein the set range is determined based on the farthest point of the suspension rope scanned by the point cloud acquisition device.

4. The method for positioning the hook according to claim 1, characterized in that: The interpolation processing of the first suspension rope point cloud includes: For the first suspension rope point cloud, a nearest neighbor search is performed based on the KD tree, and a point cloud is inserted between each point cloud and its nearest neighbor point.

5. The method for positioning the hook according to claim 1, characterized in that: The performing point cloud segmentation on the plurality of suspension ropes based on the second suspension rope point cloud comprises: Performing edge point cloud extraction on the second suspension rope point cloud to obtain a third suspension rope point cloud retaining edge features; filtering the third suspension rope point cloud based on point cloud strength, and retaining the suspension rope point cloud with a point cloud strength less than a set value as the fourth suspension rope point cloud; Projecting the fourth suspension rope point clouds corresponding to each suspension rope respectively to obtain corresponding plane point clouds; and The plane point cloud is clustered and segmented to obtain a final point cloud segmentation result.

6. The method for positioning the hook according to claim 5, characterized in that: The extracting edge point cloud from the second suspension rope point cloud comprises: Traversing all point clouds in the second suspension rope point cloud to find a neighborhood of each point cloud and performing a tangent plane projection on the neighborhood; According to the projection results, each point cloud is connected with the corresponding projected point cloud in its neighborhood to obtain the angle value of the corresponding connection line; and For all the obtained angle values, the edge point cloud is filtered out according to the comparison results between them and the set angle threshold.

7. The method for positioning a hook according to claim 1, characterized in that: Determining the position of the hook comprises: Calculating the end coordinates of the suspension rope according to the obtained direction vector and the length and starting point coordinates of the corresponding suspension rope; and The position of the hook is determined according to the end coordinates of the lifting rope and the size of the lifting hook.

8. A hook positioning device based on point cloud, characterized in that: include: a memory configured to store instructions; as well as A processor is configured to call the instructions from the memory and implement the hook positioning method according to any one of claims 1 to 7 when executing the instructions.

9. A hook positioning device based on point cloud, characterized in that: include: The hook positioning device according to claim 8; as well as A point cloud acquisition device, used for acquiring and providing point cloud data to the hook positioning device; Wherein, the point cloud acquisition device has a sensing range that at least covers multiple suspension ropes and the suspension hook.

10. A machine-readable storage medium, characterized in that: The machine-readable storage medium stores instructions for causing a machine to execute the hook positioning method according to any one of claims 1 to 7.

Images