Pallet height identification method, device and electronic equipment

Abstract

The present application relates to a method for identifying the height of a pallet, wherein the method comprises: obtaining point cloud information of the pallet and the height of the pile, filtering the point cloud information to obtain a discrete point cloud; performing a coarse matching of the pallet and the height of the pile according to the discrete point cloud to obtain a matching score, and determining the position with the highest coarse matching score as the updated reference position; performing a fine matching of the pallet and the height of the pile according to the updated reference position to determine the position and height of the pallet. The present application effectively reduces noise and error and improves the accuracy of recognition by filtering the point cloud data. By combining a coarse matching algorithm with a fine matching algorithm and adopting the same recognition logic for the identification of the pallet and the height of the pile, the matching logic is optimized, and matching results that meet the conditions can be quickly screened out during the identification process, thereby improving the recognition speed and accuracy, and having high reliability and stability.

Description

Technical Field

[0001] The present application relates to the field of automated control, and in particular to a method, device, and electronic device for identifying the height of a pallet. Background Art

[0002] With the rapid development of automated control, AGVs (Automated Guided Vehicles) are increasingly used in the logistics industry. They can move and transport goods according to instructions or planned paths, enabling automated transportation. However, when performing logistics tasks, AGVs need to accurately understand the location and posture of goods. In particular, the ability to identify three-dimensional pallets and stack heights plays a vital role in improving logistics efficiency and safety.

[0003] Existing solutions mainly rely on lidar or visual sensors to obtain three-dimensional information of pallets and materials. However, these methods have the problem of low recognition accuracy in the process of identifying pallets and stack heights. Summary of the Invention

[0004] The embodiments of the present application provide a method, device, and electronic device for identifying the height of a pallet, so as to at least solve the problem of low accuracy in identifying the height of a pallet and a pile in the related art.

[0005] In a first aspect, an embodiment of the present application provides a method for identifying the height of a pallet, comprising:

[0006] Obtaining point cloud information of the pallet and the stack height, and filtering the point cloud information to obtain a discrete point cloud;

[0007] Performing a rough match between the pallet and the stack height according to the discrete point cloud to obtain a matching score, and determining the position with the highest rough matching score as the updated reference position;

[0008] The pallet and the stack height are finely matched according to the updated reference position to determine the posture of the pallet and the position and height of the stack height.

[0009] In one embodiment, performing a rough match on the pallet and the stack height according to the discrete point cloud to obtain a matching score, and determining the position with the highest rough matching score as the updated reference position includes:

[0010] According to a preset initial reference position of the pallet or the pile height, a point cloud in the discrete point cloud whose distance to the preset initial reference position is less than or equal to a first preset distance is determined as a first point cloud;

[0011] Obtaining a current baseline based on the first point cloud fitting;

[0012] Partitioning the discrete point cloud according to a first preset step size, and fitting the discrete point cloud of each partition to obtain a coarse matching baseline;

[0013] The current reference line is matched with the coarse matching reference line of each partition, and the coarse matching reference line with the highest matching score is determined as the updated reference position.

[0014] In one embodiment, obtaining a current baseline based on the first point cloud fitting includes:

[0015] Fitting a first reference line according to the first point cloud;

[0016] resampling the point cloud based on the first reference line and the second preset distance, and fitting a second reference line according to the resampled point cloud;

[0017] The resampled point cloud is projected onto the second reference line to obtain a current reference line.

[0018] In one embodiment, the fine matching of the pallet and the stack height according to the updated reference position to determine the posture of the pallet and the position and height of the stack includes:

[0019] determining a second point cloud according to the updated reference position and a first preset threshold, wherein the second point cloud is used for fine matching;

[0020] Partitioning the second point cloud according to a second preset step size, and fitting the second point cloud of each partition to obtain a fine matching baseline;

[0021] Matching the current baseline with the fine matching baseline of each partition to obtain a matching value and a posture or a position and height of the pallet;

[0022] In response to the matching value satisfying a preset condition, the position and height information of the pallet corresponding to the matching value satisfying the preset condition or the stack position is used as a recognition result.

[0023] In one embodiment, in response to the matching value satisfying a preset condition, taking the pallet posture corresponding to the matching value satisfying the preset condition as the recognition result includes:

[0024] In response to the matching value being greater than or equal to the second preset threshold, it is determined that the match is successful, an intermediate value of all successful matching examples is determined, and the posture information of the pallet corresponding to the intermediate value is used as the recognition result.

[0025] In one embodiment, in response to the matching value satisfying a preset condition, taking the position and height information of the pile height corresponding to the matching value satisfying the preset condition as the recognition result includes:

[0026] In response to the matching value being greater than or equal to a second preset threshold, determining that the match is successful;

[0027] In response to the number of consecutive successful matches reaching a third preset threshold, the position and height of the stack corresponding to the first consecutive successful match are determined as the recognition result.

[0028] In one embodiment, the filtering process based on the point cloud information to obtain a discrete point cloud includes:

[0029] Converting the point cloud information into point cloud data in a target coordinate system;

[0030] Performing a first filtering process on the point cloud data according to a preset selected area to obtain a filtered point cloud;

[0031] A normal vector of the filtered point cloud is determined, and a second filtering process is performed on the filtered point cloud based on the normal vector to obtain the discrete point cloud.

[0032] In a second aspect, an embodiment of the present application provides a pallet height identification device, comprising:

[0033] An acquisition module is used to obtain point cloud information of the pallet and the pile height, and filter the point cloud information to obtain a discrete point cloud;

[0034] An updating module, configured to perform a rough match between the pallet and the stack height according to the discrete point cloud to obtain a matching score, and determine a position with the highest rough matching score as an updated reference position;

[0035] A determination module is used to perform fine matching of the pallet and the stack height according to the updated reference position, and determine the posture of the pallet and the position and height of the stack height.

[0036] In a third aspect, an embodiment of the present application provides an electronic device comprising: a memory, a processor, and a computer program stored on the memory and executable on the processor, wherein when the processor executes the computer program, the pallet height identification method provided in the first aspect is implemented.

[0037] In a fourth aspect, an embodiment of the present application provides a computer-readable storage medium having a computer program stored thereon, characterized in that when the program is executed by a processor, the pallet height identification method provided in the first aspect is implemented.

[0038] The pallet height identification method provided in the embodiment of the present application has at least the following technical effects.

[0039] The pallet height recognition method provided in this application effectively reduces noise and errors by filtering point cloud data, thereby improving recognition accuracy. It employs a combination of coarse and fine matching algorithms, employing the same recognition logic for pallet and stack height recognition. This optimized matching logic allows for rapid screening of matching results that meet the criteria during the recognition process, improving recognition speed and accuracy. It also boasts high reliability and stability, enabling accurate and rapid recognition and operation of high-level three-dimensional cargo pick-and-place operations in the AGV industry.

[0040] The details of one or more embodiments of the present application are set forth in the following drawings and description to make other features, objects, and advantages of the present application more readily apparent. BRIEF DESCRIPTION OF THE DRAWINGS

[0041] The drawings described herein are used to provide a further understanding of the present application and constitute a part of the present application. The illustrative embodiments of the present application and their descriptions are used to explain the present application and do not constitute an improper limitation on the present application. In the drawings:

[0042] Figure 1 is a flow chart of a method for identifying the height of a pallet according to an exemplary embodiment;

[0043] Figure 2 is a flowchart illustrating a point cloud filtering process according to an exemplary embodiment;

[0044] Figure 3 is a flowchart showing updating a reference position according to an exemplary embodiment;

[0045] Figure 4 is a flow chart showing a method of obtaining a current baseline according to an exemplary embodiment;

[0046] Figure 5 is a flow chart illustrating a method for determining a posture, position, and height of a pallet according to an exemplary embodiment;

[0047] Figure 6 It is a flow chart for determining the position and height results of the pile height;

[0048] Figure 7 is a block diagram of a pallet height identification device according to an embodiment of the present application;

[0049] Figure 8 A schematic diagram of the structure of an electronic device provided in an embodiment of the present application. DETAILED DESCRIPTION

[0050] In order to make the purpose, technical solutions and advantages of this application more clearly understood, the present application is described and illustrated below in conjunction with the accompanying drawings and examples. It should be understood that the specific embodiments described herein are merely used to explain this application and are not intended to limit this application. Based on the embodiments provided in this application, all other embodiments obtained by those of ordinary skill in the art without making any creative efforts are within the scope of protection of this application.

[0051] Obviously, the drawings described below are merely examples or embodiments of the present application. Those skilled in the art can, without inventive effort, apply the present application to other similar scenarios based on these drawings. Furthermore, it is also understood that, although the effort involved in such a development process may be complex and lengthy, for those skilled in the art related to the content disclosed in this application, changes in design, manufacturing, or production based on the technical content disclosed in this application are merely conventional technical means and should not be construed as an insufficiency of the content disclosed in this application.

[0052] References to "embodiments" in this application mean that a particular feature, structure, or characteristic described in connection with the embodiment may be included in at least one embodiment of the application. The appearance of this phrase in various places in the specification does not necessarily refer to the same embodiment, nor does it refer to independent or alternative embodiments that are mutually exclusive of other embodiments. It is understood, both explicitly and implicitly, by those skilled in the art that the embodiments described in this application may be combined with other embodiments unless there is a conflict.

[0053] Unless otherwise defined, the technical or scientific terms used in this application should have the ordinary meaning understood by a person of ordinary skill in the technical field to which this application belongs. The words "one", "a", "the" and the like used in this application do not indicate a limit on quantity and may indicate the singular or plural. The terms "include", "comprise", "have" and any variations thereof used in this application are intended to cover non-exclusive inclusions; for example, a process, method, system, product or device that includes a series of steps or modules (units) is not limited to the listed steps or units, but may also include steps or units that are not listed, or may also include other steps or units that are inherent to these processes, methods, products or devices. The words "connect", "connected", "coupled" and the like used in this application are not limited to physical or mechanical connections, but may include electrical connections, whether direct or indirect. The word "multiple" used in this application refers to two or more. "And / or" describes the association relationship of associated objects, indicating that three relationships can exist. For example, "A and / or B" can mean: A exists alone, A and B exist at the same time, and B exists alone. The character " / " generally indicates that the objects before and after are in an "or" relationship. The terms "first", "second", "third", etc. involved in this application are only used to distinguish similar objects and do not represent a specific order for the objects.

[0054] Based on the above situation, embodiments of the present application provide a method, device, and electronic device for identifying the height of a pallet.

[0055] In a first aspect, an embodiment of the present application provides a method for identifying the height of a pallet.

[0056] Figure 1 FIG. 1 is a flow chart of a method for identifying the height of a pallet according to an exemplary embodiment. Figure 1 As shown, the method includes:

[0057] Step S101: Obtain point cloud information of the pallet and the stack height, and perform filtering based on the point cloud information to obtain a discrete point cloud. Optionally, the point cloud information is collected and uploaded by a Time of Flight (TOF) camera mounted on an Automated Guided Vehicle (AGV).

[0058] In one example, Figure 2 FIG. 1 is a flowchart of a point cloud filtering process according to an exemplary embodiment. Figure 2 As shown, in step S101, filtering is performed based on the point cloud information to obtain a discrete point cloud, which specifically includes:

[0059] Step S1011: converting the point cloud information into point cloud data in the target coordinate system.

[0060] Among them, the reference coordinate system of the point cloud information obtained by the TOF camera is the camera. Through the external parameters of the TOF camera (the relative position of the TOF camera with respect to the vehicle control center), the point cloud information is converted to the vehicle control center for description.

[0061] Step S1012 : performing a first filtering process on the point cloud data according to the preset selected area to obtain a filtered point cloud.

[0062] The filtered point cloud is the point cloud within a preset selection area. Optionally, a region of interest (ROI) selection method can be used to determine the preset selection area. The ROI selection area can be set based on actual conditions and needs. In the AGV industry, a range of 20% of the pallet's outer dimensions is generally selected. Using the ROI selection area, background noise and other points unrelated to the identified object are filtered to obtain valid point cloud data, which helps improve the accuracy of subsequent pallet height recognition.

[0063] Step S1013 : determining the normal vector of the filtered point cloud, and performing a second filtering process on the filtered point cloud based on the normal vector to obtain a discrete point cloud.

[0064] The second filtering step removes noise and outliers from the point cloud. If the difference between the normal vector of a point in the filtered point cloud and the normal vectors of surrounding points is greater than or equal to a fourth preset threshold, the point is determined to be a noise point or outlier and filtered out to obtain a discrete point cloud. This method removes noise and outliers caused by lighting, occlusion, and other factors, further reducing interference from environmental factors and facilitating the acquisition of more accurate point cloud data, thereby improving the accuracy of pallet height recognition.

[0065] In this embodiment, the TOF camera acquires point cloud information about the pallet and its height, effectively identifying objects of varying shapes and heights, thereby improving the versatility of the pallet height recognition method. Steps S1012 and S1013 employ techniques such as normal vector filtering and discrete point removal to effectively reduce noise and errors, improving the quality and accuracy of the point cloud data and, consequently, enhancing recognition accuracy.

[0066] Continue to refer to Figure 1 , execute step S102 after step S101.

[0067] Step S102 : performing a rough match between the pallet and the stack height according to the discrete point cloud to obtain a matching score, and determining the position with the highest rough matching score as an updated reference position.

[0068] Among them, the updated reference position obtained by coarse matching narrows the matching range, greatly reduces the matching time, and provides the main position basis for subsequent fine matching, effectively improving the efficiency and accuracy of pallet and pile height recognition.

[0069] In one example, Figure 3 is a flow chart showing updating a reference position according to an exemplary embodiment. Figure 3 As shown, step S102 specifically includes:

[0070] In step S1021 , based on a preset initial reference position of the pallet or the stack height, a point cloud in the discrete point cloud whose distance to the preset initial reference position is less than or equal to a first preset distance is determined as a first point cloud.

[0071] Optionally, the preset reference position of the pallet or pile is a prior value of the pallet or pile height, which is obtained based on the point cloud data and resolution of the pallet or pile. The resolution is determined by the accuracy of the current TOF camera, and a resolution of 5 mm is typically used. The first point cloud is a point cloud near the height of the target object. The first preset distance is set according to actual conditions, such as 5 cm, 8 cm, or 10 cm.

[0072] Step S1022: Obtain a current baseline based on the first point cloud fitting.

[0073] In one example, the current reference line is obtained based on the first point cloud fitting. Figure 4 is a flow chart showing a method of obtaining a current baseline according to an exemplary embodiment. Figure 4 As shown, step S1022 specifically includes:

[0074] Step S401, fitting a first reference line according to the first point cloud;

[0075] Step S402 resamples the point cloud based on the first baseline and a second preset distance, and fits the second baseline to the resampled point cloud. The first preset distance can be set based on actual conditions, such as 2 cm, 3 cm, or 4 cm. This method allows for a more accurate current baseline, thereby improving the accuracy of pallet and stack height recognition.

[0076] Step S403: Project the resampled point cloud onto the second baseline to obtain the current baseline.

[0077] In this embodiment, the point cloud near the height of the target object is resampled in step S402, and the resampled current baseline is obtained in step S403. In this embodiment of the application, a more accurate current baseline is obtained by resampling the point cloud, which is conducive to improving the recognition accuracy of the pallet and the pile height.

[0078] Step S1023 : partitioning the discrete point cloud according to a first preset step size, and fitting the discrete point cloud of each partition to obtain a coarse matching baseline.

[0079] Optionally, the first step length is set based on actual conditions, such as 10 cm, 12 cm, or 15 cm. In step S1023, the discrete point cloud is divided into at least two partitions along the height direction according to the first step length, and at least two vertically aligned coarse matching reference lines are fitted. The smaller the first step length, the more coarse matching reference lines are fitted, and the more accurate the pose and height information subsequently determined based on the coarse matching reference lines.

[0080] Step S1024 : Match the current reference line with the coarse matching reference line of each partition, and determine the coarse matching reference line with the highest matching score as the updated reference position.

[0081] A pallet is typically a frame-like structure formed by multiple solid edges, with both solid and hollow areas. The current baseline and the coarse matching baseline are determined based on the actual application scenario of the pallet's height. The current baseline and the coarse matching baseline for each partition each correspond to an index, which records whether the current point belongs to a solid or hollow area of the pallet. Optionally, if the current point is in / corresponds to a hollow area, the index is marked as 0; if the current point is in / corresponds to a solid area, the index is marked as 1.

[0082] In this embodiment, through steps S1021 and S1022, a point cloud near the height of the target object is obtained and the current baseline is fitted to it. Through step S1023, a coarse matching baseline is obtained. Through step S1024, a coarse matching of the pallet or pile height is performed. This allows for rapid positioning near the actual height of the target object, reduces matching time, and provides a positional basis for subsequent fine matching, which is beneficial to improving the efficiency and accuracy of pallet and pile height recognition.

[0083] Continue to refer to Figure 1 , execute step S103 after step S102.

[0084] Step S103 : performing fine matching of the pallet and the stack height according to the updated reference position to determine the posture of the pallet and the position and height of the stack height.

[0085] The pallet's position information refers to its position relative to the vehicle's control center, including its location and orientation. The position information for the pallet and its stack height represents its spatial coordinates relative to the vehicle's control center. These coordinates can be expressed in units such as meters and millimeters, depending on the application requirements and the selected coordinate system.

[0086] In one example, Figure 5FIG. 1 is a flow chart showing a method for determining the posture, position, and height of a pallet according to an exemplary embodiment. Figure 5 As shown, step S103 specifically includes:

[0087] In step S1031, a second point cloud is determined based on the updated reference position and the first preset threshold value, and the second point cloud is used for fine matching. The first preset distance can be set according to actual conditions, such as 5 cm, 8 cm, or 10 cm.

[0088] Step S1032 : partition the second point cloud according to a second preset step size, and fit the second point cloud in each partition to obtain a fine matching baseline.

[0089] The second step size can be set based on actual conditions, for example, 1cm, 1.5cm, or 2cm. The discrete point cloud is divided into at least two partitions along the height direction according to the second step size, and then at least two vertically aligned fine matching reference lines are fitted. The smaller the second step size, the more fine matching reference lines are fitted, and the more accurate the recognition results of the pallet and stack height. For example, in the scenario of fitting fine matching reference lines, a fine matching reference line is fitted every 1cm within the ±5cm range of the updated reference position.

[0090] Step S1033 : Match the current baseline with the fine matching baseline of each partition to obtain a matching value and the posture or position and height of the pallet.

[0091] The current baseline used in the fine match is the same as the current baseline used in the coarse match. Each fine match baseline corresponds to an index that records whether the current point is solid or hollow. Optionally, if the current point is hollow, it is marked as 0; if the current point is solid, it is marked as 1.

[0092] Step S1034 : In response to the matching value satisfying a preset condition, the position and height information of the pallet corresponding to the matching value satisfying the condition or the stack position is used as a recognition result.

[0093] In this embodiment, based on the coarse matching results, a fine matching range is determined in step S1031, and fine matching is performed using a smaller step size in steps S1032 and S1033, effectively improving the efficiency and accuracy of pallet and pile height recognition. Furthermore, the use of the same matching logic for pallet and pile height recognition offers high reliability and stability, effectively avoiding false positives and missed positives.

[0094] There are multiple implementations of step S1034, which will be described in detail below.

[0095] In the first method, step S1034 specifically includes: in response to the matching value being greater than or equal to the second preset threshold, determining that the match is successful, determining the median value of all successful matching examples, and using the posture information of the stack corresponding to the median value as the recognition result.

[0096] The second preset threshold can be set based on actual conditions; the median of all successfully matched examples is the median of the successfully matched examples. The pallet's position information refers to the pallet's position relative to the vehicle's control center, including its position and orientation relative to the vehicle's control center.

[0097] In this embodiment, by filtering unsuccessful matching examples through a second preset threshold and taking the median of successful matching examples, the matching of pallets of different heights and sizes can be adaptively adapted, while improving the accuracy and robustness of three-dimensional pallet recognition.

[0098] The second way, Figure 6 It is a flow chart to determine the position and height of the pile, such as Figure 6 As shown, step S1034 specifically includes:

[0099] Step S601: In response to the matching value being greater than or equal to the second preset threshold, it is determined that the match is successful.

[0100] Step S602: In response to the number of consecutive successful matches reaching a third preset threshold, the position and height of the stack corresponding to the first consecutive successful match are determined as the recognition result.

[0101] The stack height matching process utilizes a top-down sliding window method. The sliding window size and third preset threshold are set based on actual conditions. In this embodiment, the third threshold is set to 4, and the sliding window size is 5. If four consecutive matches are successful, the position and height corresponding to the first successful match are used as the result. This ensures that the correct stack height is detected, not an incorrect match. The stack height position information represents its spatial coordinates relative to the vehicle's control center.

[0102] In this embodiment, unsuccessful matching examples are filtered out by the second preset threshold in step S601, and four consecutive successful matches are performed in step S602 to ensure successful matching, avoid false matching, and improve the accuracy of fine matching.

[0103] In summary, the pallet height recognition method provided in this application filters point cloud data through methods such as ROI selection, normal vector calculation and discrete point filtering, effectively reducing noise and errors, which is conducive to improving recognition accuracy. By resampling the point cloud, a more accurate current baseline is obtained, which is conducive to improving the recognition accuracy of pallets and pile heights. By combining the coarse matching algorithm and the fine matching algorithm, the same recognition logic and different step lengths are used to recognize pallets and pile heights, and the recognition logic is optimized. During the recognition process, matching results that meet the conditions can be quickly and accurately screened out, thereby improving recognition speed and accuracy, and having high reliability and stability, thereby realizing accurate and rapid recognition and operation of high-level pick-and-place operations of three-dimensional goods.

[0104] Second aspect

[0105] An embodiment of the present application provides a device for identifying the height of a pallet. Figure 7 1 is a block diagram of a device for identifying the height of a pallet according to an embodiment of the present application. The device for identifying the height of a pallet includes an acquisition module 110 , an update module 120 , and a determination module 130 .

[0106] The acquisition module 110 is used to acquire point cloud information of the pallet and the stack height, and perform filtering processing based on the point cloud information to obtain a discrete point cloud.

[0107] The updating module 120 is configured to perform a rough match between the pallet and the stack height according to the discrete point cloud to obtain a matching score, and determine the position with the highest rough matching score as the updated reference position.

[0108] The determination module 130 is used to perform fine matching of the pallet and the stack height according to the updated reference position, and determine the posture of the pallet and the position and height of the stack height.

[0109] In one example, the acquisition module 110 includes:

[0110] Conversion unit: converts point cloud information into point cloud data in the target coordinate system;

[0111] Filtering unit: performs the first filtering process on the point cloud data according to the preset selection area to obtain the filtered point cloud;

[0112] Secondary filtering unit: determines the normal vector of the filtered point cloud, and performs a second filtering process on the filtered point cloud based on the normal vector to obtain a discrete point cloud.

[0113] In one example, the update module 120 includes:

[0114] A point cloud determining unit: determining, based on a preset initial reference position of the pallet or the pile height, a point cloud in the discrete point cloud whose distance to the preset initial reference position is less than or equal to a first preset distance as a first point cloud;

[0115] Fit current baseline unit: obtain the current baseline based on the first point cloud fitting;

[0116] Fitting a coarse matching baseline unit: partitioning the discrete point cloud according to a first preset step size, and fitting the discrete point cloud of each partition to obtain a coarse matching baseline;

[0117] Update unit: matches the current baseline with the coarse matching baseline of each partition, and determines the coarse matching baseline with the highest matching score as the updated baseline position.

[0118] In one example, the updating module 120 includes:

[0119] Fitting subunit: fitting a first baseline according to the first point cloud;

[0120] Refitting subunit: resamples the point cloud based on the first reference line and the second preset distance, and fits the second reference line according to the resampled point cloud;

[0121] Get subunit: Project the resampled point cloud to the second baseline and get the current baseline.

[0122] In one example, the determination module 130 includes:

[0123] Point cloud determination unit: determining a second point cloud according to the updated reference position and a first preset threshold, wherein the second point cloud is used for fine matching;

[0124] Fitting unit: partitioning the second point cloud according to a second preset step size, and fitting the second point cloud of each partition to obtain a fine matching baseline;

[0125] Acquisition unit: matches the current baseline with the fine matching baseline of each partition, obtains the matching value and the position and height of the pallet or the stack height;

[0126] Recognition unit: In response to the matching value meeting the preset condition, the position and height information of the pallet corresponding to the matching value meeting the preset condition is used as the recognition result.

[0127] In one example, the recognition unit in the determination module 130 specifically includes: in response to the matching value being greater than or equal to the second preset threshold, judging that the match is successful, determining the median value of all successful matching samples, and using the posture information of the stack corresponding to the median value as the recognition result.

[0128] In one example, the identification unit in the determination module 130 includes:

[0129] A judgment subunit: in response to the matching value being greater than or equal to the second preset threshold, judging that the match is successful;

[0130] Determining subunit: In response to the number of consecutive successful matches reaching a third preset threshold, determining the position and height of the pile corresponding to the first consecutive successful match as the recognition result.

[0131] In summary, the pallet stack height recognition device provided by the present application filters the point cloud data through the acquisition module, effectively reducing noise and errors and improving the recognition accuracy. By updating the module, a coarse matching method is used to quickly confirm the approximate range of the pallet and the stack height. By determining the module, based on the coarse matching results, a fine matching method is used to quickly and accurately identify the posture of the pallet and the position and height of the stack. In the process of identifying the pallet and the stack height, the present application can quickly screen out matching results that meet the conditions, improve the recognition speed and accuracy, and has high reliability and stability, realizing accurate and rapid recognition and operation of high-level pick-up and placement operations of three-dimensional goods.

[0132] The third aspect

[0133] An embodiment of the present application provides an electronic device, Figure 8 This is a structural diagram of an electronic device provided in an embodiment of the present application. The electronic device includes a memory, a processor, and a computer program stored in the memory and executable on the processor. When the processor executes the program, the AR interaction method provided in the first aspect is implemented. Figure 8 The electronic device 60 shown is only an example and should not limit the functions and scope of use of the embodiments of the present application.

[0134] The electronic device 60 may be a general-purpose computing device, such as a server device. Components of the electronic device 60 may include, but are not limited to, the at least one processor 61, the at least one memory 62, and a bus 63 connecting different system components (including the memory 62 and the processor 61).

[0135] The bus 63 includes a data bus, an address bus, and a control bus.

[0136] The memory 62 may include a volatile memory, such as a random access memory (RAM) 621 and / or a cache memory 622 , and may further include a read-only memory (ROM) 623 .

[0137] The memory 62 may also include a program / utility 625 having a set (at least one) of program modules 624, such program modules 624 including but not limited to: an operating system, one or more application programs, other program modules, and program data, each of which or some combination may include an implementation of a network environment.

[0138] The processor 61 executes various functional applications and data processing by running the computer programs stored in the memory 62, such as the pallet and stack height identification method of the first aspect of the present application.

[0139] The electronic device 60 can also communicate with one or more external devices 64 (e.g., a keyboard, pointing device, etc.). This communication can occur via an input / output (I / O) interface 65. Furthermore, the model-generating device 60 can also communicate with one or more networks (e.g., a local area network (LAN), a wide area network (WAN), and / or a public network, such as the Internet) via a network adapter 66. As shown, the network adapter 66 communicates with other modules of the model-generating device 60 via a bus 63. It should be understood that, although not shown, other hardware and / or software modules can be used in conjunction with the model-generating device 60, including but not limited to microcode, device drivers, redundant processors, external disk drive arrays, RAID (RAID) systems, tape drives, and data backup storage systems.

[0140] It should be noted that although several units / modules or sub-units / modules of the electronic device are mentioned in the detailed description above, this division is merely exemplary and not mandatory. In fact, according to embodiments of the present invention, the features and functions of two or more units / modules described above may be embodied in a single unit / module. Conversely, the features and functions of a single unit / module described above may be further divided and embodied by multiple units / modules.

[0141] The fourth aspect

[0142] An embodiment of the present application provides a computer-readable storage medium having a program stored thereon. When the program is executed by a processor, the method for identifying the pallet height provided in the first aspect is implemented.

[0143] The readable storage medium may include, but is not limited to, a portable disk, a hard disk, a random access memory, a read-only memory, an erasable programmable read-only memory, an optical storage device, a magnetic storage device, or any suitable combination thereof.

[0144] In a possible embodiment, the present invention can also be implemented in the form of a program product, which includes program code. When the program product is run on a terminal device, the program code is used to enable the terminal device to execute the steps of the pallet height identification method provided in the first aspect.

[0145] The program code for executing the present invention may be written in any combination of one or more programming languages, and may be executed entirely on the user device, partially on the user device, as an independent software package, partially on the user device and partially on a remote device, or entirely on the remote device.

[0146] The technical features of the above-mentioned embodiments can be combined arbitrarily. In order to make the description concise, not all possible combinations of the technical features in the above-mentioned 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.

[0147] The above-described embodiments merely represent several implementation methods of the present application. While the descriptions are relatively specific and detailed, they should not be construed as limiting the scope of the present invention. It should be noted that a person skilled in the art could make various modifications and improvements without departing from the spirit of the present application, all of which fall within the scope of protection of the present application. Therefore, the scope of protection of the present patent application shall be determined by the appended claims.

Claims

1. A method for identifying the height of a pallet, characterized in that: include: Obtaining point cloud information of the pallet and the stack height, and filtering the point cloud information to obtain a discrete point cloud; According to the discrete point cloud, the pallet and the stack height are roughly matched to obtain a matching score, and the position with the highest rough matching score is determined as the updated reference position, including: According to a preset initial reference position of the pallet or pile height, a point cloud in the discrete point cloud whose distance to the preset initial reference position is less than or equal to a first preset distance is determined as a first point cloud, a current baseline is obtained based on fitting of the first point cloud, the discrete point cloud is partitioned according to a first preset step size, and a coarse matching baseline is obtained by fitting the discrete point cloud of each partition, the current baseline is matched with the coarse matching baseline of each partition, and the coarse matching baseline with the highest matching score is determined as the updated reference position; The pallet and the stack height are finely matched according to the updated reference position to determine the posture of the pallet and the position and height of the stack height.

2. The pallet height identification method according to claim 1, characterized in that: The obtaining of a current baseline based on the first point cloud fitting includes: Fitting a first reference line according to the first point cloud; resampling the point cloud based on the first reference line and the second preset distance, and fitting a second reference line according to the resampled point cloud; The resampled point cloud is projected onto the second reference line to obtain a current reference line.

3. The pallet height identification method according to claim 2, characterized in that: The step of finely matching the pallet and the stack height according to the updated reference position to determine the pallet's posture and the position and height of the stack includes: determining a second point cloud according to the updated reference position and a first preset threshold, wherein the second point cloud is used for fine matching; Partitioning the second point cloud according to a second preset step size, and fitting the second point cloud of each partition to obtain a fine matching baseline; Matching the current baseline with the fine matching baseline of each partition to obtain a matching value and a posture or a position and height of the pallet; In response to the matching value satisfying a preset condition, the position and height information of the pallet corresponding to the matching value satisfying the preset condition or the stack position is used as a recognition result.

4. The pallet height recognition method according to claim 3, characterized in that: In response to the matching value satisfying a preset condition, taking the pallet posture corresponding to the matching value satisfying the preset condition as a recognition result, including: In response to the matching value being greater than or equal to the second preset threshold, it is determined that the match is successful, an intermediate value of all successful matching examples is determined, and the posture information of the pallet corresponding to the intermediate value is used as the recognition result.

5. The pallet height identification method according to claim 3, characterized in that: In response to the matching value satisfying the preset condition, taking the position and height information of the pile height corresponding to the matching value satisfying the preset condition as the recognition result, including: In response to the matching value being greater than or equal to a second preset threshold, determining that the match is successful; In response to the number of consecutive successful matches reaching a third preset threshold, the position and height of the stack corresponding to the first consecutive successful match are determined as the recognition result.

6. The pallet height recognition method according to claim 1, characterized in that: The filtering process based on the point cloud information to obtain a discrete point cloud includes: Converting the point cloud information into point cloud data in a target coordinate system; Performing a first filtering process on the point cloud data according to a preset selected area to obtain a filtered point cloud; A normal vector of the filtered point cloud is determined, and a second filtering process is performed on the filtered point cloud based on the normal vector to obtain the discrete point cloud.

7. A pallet height identification device, characterized in that: include: An acquisition module is used to obtain point cloud information of the pallet and the pile height, and filter the point cloud information to obtain a discrete point cloud; An updating module is configured to perform a rough match between the pallet and the stack height according to the discrete point cloud to obtain a matching score, and determine the position with the highest rough matching score as the updated reference position, including: According to a preset initial reference position of the pallet or pile height, a point cloud in the discrete point cloud whose distance to the preset initial reference position is less than or equal to a first preset distance is determined as a first point cloud, a current baseline is obtained based on fitting of the first point cloud, the discrete point cloud is partitioned according to a first preset step size, and a coarse matching baseline is obtained by fitting the discrete point cloud of each partition, the current baseline is matched with the coarse matching baseline of each partition, and the coarse matching baseline with the highest matching score is determined as the updated reference position; A determination module is used to perform fine matching of the pallet and the stack height according to the updated reference position, and determine the posture of the pallet and the position and height of the stack height.

8. An electronic device, characterized in that: include Memory, processor, and A computer program stored in the memory and executable on the processor, wherein when the processor executes the computer program, the method for identifying the pallet height according to any one of claims 1 to 6 is implemented.

9. A computer-readable storage medium having a computer program stored thereon, characterized in that: When the program is executed by a processor, the pallet height recognition method according to any one of claims 1 to 6 is implemented.

Images