Paper roll identification method, device, computer equipment and storage medium
By using laser beam scanning on industrial handling vehicles to acquire point cloud data and combining Kalman filtering algorithm, the accuracy of paper roll identification and positioning is solved, the handling efficiency and accuracy are improved, and efficient automated handling is achieved.
Patent Information
- Application Number
- CN202411117686.2
- Authority / Receiving Office
- CN · China
- Patent Type
- Patents(China)
- Current Assignee / Owner
- Filing Date
- 2024-08-15
- Publication Date
- 2024-11-12
- Estimated Expiration
- 2044-08-15
Smart Images

Figure CN118628576B_ABST
Abstract
Description
Technical Field
[0001] The present application relates to the technical field of industrial handling vehicles. Specifically, the present application relates to a paper roll identification method, device, computer equipment, storage medium and computer program product. Background Art
[0002] Industrial handling vehicles, also known as industrial vehicles, are used for short-distance cargo handling, loading and unloading, and stacking operations. Such vehicles are widely used in ports, stations, airports, freight yards, factory workshops, warehouses, and distribution centers. There are many types of vehicles, such as forklifts, single bucket loaders, chassis vehicles, etc., to meet different operational needs.
[0003] In the business scenario of using industrial handling vehicles to automatically transport paper rolls, it is crucial to accurately grasp the properties and location information of the target paper roll, which is the prerequisite for starting an efficient handling process. However, under the existing technology, usually only a relatively rough location information of the target paper roll can be provided. Although the basic handling function can be realized by carrying out the handling operation based on this information, it may not meet the requirements of high-precision and high-efficiency operations.
[0004] Therefore, given the approximate location of the paper roll, how to enable the industrial transport vehicle to accurately identify the information of the paper roll to be transported has become a technical problem that needs to be solved urgently by those skilled in the art. Summary of the invention
[0005] Based on this, it is necessary to provide a paper roll identification method, device, computer equipment, storage medium and computer program product to address the above technical problems.
[0006] In a first aspect, the present application provides a paper roll identification method. The method comprises:
[0007] Acquire initial point cloud data; wherein the initial point cloud data is data obtained by scanning the paper roll to be identified by a laser beam on an industrial transport vehicle;
[0008] According to the initial position information of the paper roll to be identified, the initial point cloud data is screened to obtain target point cloud data;
[0009] Fitting is performed according to the target point cloud data to obtain at least one initial axis position of the paper roll to be identified and a radius of the paper roll to be identified;
[0010] According to the initial position information of the paper roll to be identified, the initial axis position of the at least one paper roll to be identified is screened to obtain the target axis position of the paper roll to be identified.
[0011] In one embodiment, the method further comprises:
[0012] When t k When a new target axis position of the paper roll to be identified is obtained at any time, an initial odometer data set of the industrial transport vehicle is obtained;
[0013] According to the first timestamp t of the initial point cloud data corresponding to the new target axis position m and a second timestamp of the initial odometer data set, searching the initial odometer data set for a location at the first timestamp t m The two second timestamps before and after t n-1 and t n The corresponding two first odometer data o n-1 and n ;
[0014] In the two first odometer data o n-1 and n Perform linear interpolation to obtain the first timestamp t m The corresponding second odometer data o m , and according to the second odometer data o m Updating the initial odometer data set to obtain a target odometer data set;
[0015] In the target odometer data set, the third timestamp of the initial point cloud data corresponding to the previous target axis position of the paper roll to be identified and the first timestamp of the initial point cloud data corresponding to the new target axis position are searched. m The third odometer data between;
[0016] The new target axis center position of the paper roll to be identified is updated according to the third odometer data to obtain the updated axis center position of the paper roll to be identified.
[0017] In one embodiment, after the new target axis position of the paper roll to be identified is updated according to the third odometer data to obtain the updated axis position of the paper roll to be identified, the method further includes:
[0018] In the target odometer data set, search for a timestamp greater than or equal to the first timestamp t m The fourth odometer data;
[0019] Prediction is performed based on the fourth odometer data to obtain the precise axis position of the paper roll to be identified.
[0020] In one embodiment, updating the target axis position of the paper roll to be identified according to the third odometer data to obtain the updated axis position of the paper roll to be identified includes:
[0021] According to the third odometer data, t n-1 The target axis position of the paper roll to be identified corresponding to the time t n-1 The state covariance matrix corresponding to the time is predicted to obtain the target axis position predicted by the paper roll to be identified;
[0022] The predicted target axis center position of the paper roll to be identified is used to replace the new target axis center position of the paper roll to be identified, so as to achieve the update of the target axis center position.
[0023] In one embodiment, the initial point cloud data is screened according to the initial position information of the paper roll to be identified to obtain target point cloud data, including:
[0024] Converting the initial point cloud data into a vehicle coordinate system to obtain converted point cloud data; wherein the vehicle coordinate system is a coordinate system constructed based on the industrial transport vehicle;
[0025] Converting the initial position information of the paper roll to be identified into the vehicle coordinate system to obtain converted position information;
[0026] In the vehicle coordinate system, the converted point cloud data is screened according to the converted position information to obtain target point cloud data.
[0027] In one of the embodiments, in the vehicle coordinate system, the converted point cloud data is filtered according to the converted position information to obtain target point cloud data, including:
[0028] In the vehicle coordinate system, extracting the x-coordinate and the y-coordinate in the converted position information;
[0029] In the vehicle coordinate system, constructing a first target area according to the x-coordinate, the y-coordinate, the pre-stored paper roll radius and the first preset threshold;
[0030] In the converted point cloud data, point cloud data outside the first target area is screened out, and point cloud data within the first target area is retained to obtain target point cloud data.
[0031] In one embodiment, the initial axis position of the at least one paper roll to be identified is screened according to the initial position information of the paper roll to be identified to obtain the target axis position of the paper roll to be identified, including:
[0032] constructing a second target area according to the initial position information of the paper roll to be identified and a second preset threshold;
[0033] Among the initial axis center positions of the at least one paper roll to be identified, the initial axis center positions outside the second target area are screened out, and the initial axis center positions within the second target area are retained to obtain the target axis center position of the paper roll to be identified.
[0034] In a second aspect, the present application provides a paper roll identification device. The device comprises:
[0035] A point cloud acquisition module, used to acquire initial point cloud data; wherein the initial point cloud data is data obtained by scanning the paper roll to be identified by a laser beam on an industrial transport vehicle;
[0036] A point cloud screening module, used for screening the initial point cloud data according to the initial position information of the paper roll to be identified, to obtain target point cloud data;
[0037] A point cloud fitting module, used for performing fitting according to the target point cloud data to obtain at least one initial axis position of the paper roll to be identified and a radius of the paper roll to be identified;
[0038] The position screening module is used to screen the initial axis center position of the at least one paper roll to be identified according to the initial position information of the paper roll to be identified, so as to obtain the target axis center position of the paper roll to be identified.
[0039] In a third aspect, the present application further provides a computer device. The computer device includes a memory and a processor, the memory stores a computer program, and the processor implements the following steps when executing the computer program:
[0040] Acquire initial point cloud data; wherein the initial point cloud data is data obtained by scanning the paper roll to be identified by a laser beam on an industrial transport vehicle;
[0041] According to the initial position information of the paper roll to be identified, the initial point cloud data is screened to obtain target point cloud data;
[0042] Fitting is performed according to the target point cloud data to obtain at least one initial axis position of the paper roll to be identified and a radius of the paper roll to be identified;
[0043] According to the initial position information of the paper roll to be identified, the initial axis position of the at least one paper roll to be identified is screened to obtain the target axis position of the paper roll to be identified.
[0044] In a fourth aspect, the present application further provides a computer-readable storage medium. The computer-readable storage medium stores a computer program, and when the computer program is executed by a processor, the following steps are implemented:
[0045] Acquire initial point cloud data; wherein the initial point cloud data is data obtained by scanning the paper roll to be identified by a laser beam on an industrial transport vehicle;
[0046] According to the initial position information of the paper roll to be identified, the initial point cloud data is screened to obtain target point cloud data;
[0047] Fitting is performed according to the target point cloud data to obtain at least one initial axis position of the paper roll to be identified and a radius of the paper roll to be identified;
[0048] According to the initial position information of the paper roll to be identified, the initial axis position of the at least one paper roll to be identified is screened to obtain the target axis position of the paper roll to be identified.
[0049] In a fifth aspect, the present application further provides a computer program product. The computer program product includes a computer program, and when the computer program is executed by a processor, the following steps are implemented:
[0050] Acquire initial point cloud data; wherein the initial point cloud data is data obtained by scanning the paper roll to be identified by a laser beam on an industrial transport vehicle;
[0051] According to the initial position information of the paper roll to be identified, the initial point cloud data is screened to obtain target point cloud data;
[0052] Fitting is performed according to the target point cloud data to obtain at least one initial axis position of the paper roll to be identified and a radius of the paper roll to be identified;
[0053] According to the initial position information of the paper roll to be identified, the initial axis position of the at least one paper roll to be identified is screened to obtain the target axis position of the paper roll to be identified.
[0054] The paper roll identification method, device, computer equipment, computer readable storage medium and computer program product described above firstly scan the paper roll to be identified by a laser beam on an industrial transport vehicle to obtain initial point cloud data. These point cloud data provide the three-dimensional shape and position information of the paper roll, which is the basis for subsequent identification and processing. Then, according to the initial position information of the paper roll to be identified, the initial point cloud data is screened to obtain the target point cloud data. This step is based on the given approximate position of the paper roll, and the most relevant and representative point cloud data for the paper roll to be identified is extracted from a large amount of point cloud data to reduce the complexity of subsequent processing and improve accuracy. Then, the target point cloud data is used for fitting to obtain the initial axis position of at least one paper roll to be identified and the radius of the paper roll. In this step, the initial axis position and radius of the paper roll are calculated from the point cloud data by a fitting algorithm. Finally, according to the initial position information of the paper roll to be identified, the initial axis position obtained by fitting is screened again to obtain the target axis position of the paper roll to be identified. This step can ensure that the target axis position finally obtained matches the approximate position of the paper roll to improve the accuracy and reliability of identification. It can be seen that the present application realizes accurate identification and positioning of the paper roll to be identified by combining the initial position information of the test paper to be identified and the point cloud data obtained by laser scanning, and by screening and fitting the point cloud data. That is, it solves the problem that industrial handling vehicles can accurately obtain paper roll information under the premise of a given approximate position of the paper roll, thereby providing strong support for automated handling operations. BRIEF DESCRIPTION OF THE DRAWINGS
[0055] Figure 1 A schematic diagram of a process flow of a paper roll identification method in one embodiment;
[0056] Figure 2 is a two-dimensional point cloud image before filtering in one embodiment;
[0057] Figure 3 is a filtered two-dimensional point cloud image in one embodiment;
[0058] Figure 4 is a structural block diagram of a paper roll identification device in one embodiment;
[0059] Figure 5 FIG. 4 is a diagram showing the internal structure of a computer device in one embodiment. DETAILED DESCRIPTION
[0060] In order to make the purpose, technical solution and advantages of the present application more clearly understood, the present application is further described in detail below in conjunction with the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are only used to explain the present application and are not used to limit the present application.
[0061] In one embodiment, a paper roll identification method is provided. Figure 1As shown, the method includes the following steps S102-S108:
[0062] Step S102, obtaining initial point cloud data.
[0063] The initial point cloud data is derived from an industrial transport vehicle scanning the paper roll to be identified by a laser beam. The industrial transport vehicle can be used for transporting paper rolls, and may include a forklift, a single bucket loader, a chassis vehicle, etc. The generation of the laser beam can be achieved by a single-line laser radar or a multi-line laser radar. Optionally, the timestamps of the initial point cloud data are the same, that is, the identification result of the paper roll is obtained based on the point cloud data with the same timestamp.
[0064] Step S104 , screening the initial point cloud data according to the initial position information of the paper roll to be identified to obtain target point cloud data.
[0065] The initial position information of the paper roll to be identified is given in advance and can be issued by an upper-level task scheduling system.
[0066] Specifically, the initial point cloud data is transformed into a vehicle coordinate system based on an industrial transport vehicle to obtain the transformed point cloud data. In addition, the initial position information of the paper roll to be identified is also transformed into the vehicle coordinate system to obtain the transformed position information. Subsequently, in the vehicle coordinate system, the transformed point cloud data is screened according to the transformed position information to obtain the target point cloud data.
[0067] Further, the converted position information is a three-dimensional coordinate. In the vehicle coordinate system, an x coordinate and a y coordinate are extracted from the converted position information. Subsequently, in the vehicle coordinate system, a first target area is constructed based on the x coordinate, the y coordinate, the pre-stored paper roll radius, and the first preset threshold. Finally, in the converted point cloud data, the point cloud data not in the first target area is filtered out, and the point cloud data in the first target area is retained, thereby obtaining the target point cloud data. Optionally, the first preset threshold can be set based on actual needs.
[0068] Step S106, performing fitting according to the target point cloud data to obtain at least one initial axis position of the paper roll to be identified and the radius of the paper roll to be identified.
[0069] Specifically, the target point cloud data is fitted by using a random sampling consistency algorithm and a two-point method or a three-point method to obtain at least one initial axis position of the paper roll to be identified and the radius of the paper roll to be identified. Optionally, the initial axis position is a two-dimensional coordinate, representing the x and y values of the axis of the paper roll.
[0070] Step S108, screening the initial axis position of at least one paper roll to be identified according to the initial position information of the paper roll to be identified, and obtaining the target axis position of the paper roll to be identified.
[0071] Specifically, the second target area is constructed according to the initial position information of the paper roll to be identified and the second preset threshold. Then, among the initial axis positions of at least one paper roll to be identified, the initial axis positions that are not in the second target area are screened out, and the initial axis positions in the second target area are retained, thereby obtaining the target axis position of the paper roll to be identified. Optionally, the second preset threshold can be set based on actual needs.
[0072] In the above paper roll identification method, first, the paper roll to be identified is scanned by a laser beam on an industrial transport vehicle to obtain initial point cloud data. These point cloud data provide the three-dimensional shape and position information of the paper roll, which is the basis for subsequent identification and processing. Then, according to the initial position information of the paper roll to be identified, the initial point cloud data is screened to obtain the target point cloud data. This step is based on the given approximate position of the paper roll, and the most relevant and representative point cloud data for the paper roll to be identified is extracted from a large amount of point cloud data to reduce the complexity of subsequent processing and improve accuracy. Then, the target point cloud data is used for fitting to obtain at least one initial axis position of the paper roll to be identified and the radius of the paper roll. In this step, the initial axis position and radius of the paper roll are calculated from the point cloud data by a fitting algorithm. Finally, according to the initial position information of the paper roll to be identified, the initial axis position obtained by fitting is screened again to obtain the target axis position of the paper roll to be identified. This step can ensure that the target axis position finally obtained matches the approximate position of the paper roll to improve the accuracy and reliability of identification. It can be seen that this method combines the initial position information of the test paper to be identified with the point cloud data obtained by laser scanning, and performs screening, fitting and other processing on the point cloud data to achieve accurate identification and positioning of the paper roll to be identified. In other words, it solves the problem of industrial handling vehicles being able to accurately obtain paper roll information given the approximate position of the paper roll, thereby providing strong support for automated handling operations.
[0073] During the movement of industrial transport vehicles, due to the fluctuation of point cloud data, the paper roll recognition results often fluctuate greatly, and the output frequency of the recognition results is relatively low. In order to improve the frequency and stability of the recognition results, the odometer data is combined and optimized using the extended Kalman filter algorithm. Based on the invention concept, in one embodiment, the method also includes the following steps S111-S115:
[0074] Step S111, when t k When a new target axis position of the paper roll to be identified is obtained at any time, an initial odometer data set of the industrial transport vehicle is obtained.
[0075] Specifically, during the paper roll recognition / fitting process of the industrial handling vehicle, the odometer in the industrial handling vehicle will synchronously collect the odometer data of the vehicle. Since the paper roll recognition process takes a long time, the odometer will accumulate multiple data points between two consecutive recognition results. To ensure data integrity and the accuracy of subsequent analysis, all collected odometer data will be saved to form a corresponding data set.
[0076] When t k When the new target axis position of the paper roll is identified, the initial odometer data set of the industrial handling vehicle is read from the database. Optionally, this initial odometer data set can be a complete odometer data record in the database, or a partial odometer data can be selected.
[0077] Step S112: according to the first timestamp t of the initial point cloud data corresponding to the new target axis position m and the second timestamp of the initial odometer dataset, find the first timestamp t in the initial odometer dataset m The two second timestamps before and after t n-1 and t n The corresponding two first odometer data o n-1 and n .
[0078] The initial point cloud data corresponding to the target axis position refers to the target axis position of the corresponding paper roll generated by using the initial point cloud data.
[0079] Specifically, the first timestamp t of the initial point cloud data corresponding to the newly identified target axis position is m , compare with the second timestamp of the initial odometer data set, and find the two second timestamps t closest to the first timestamp. n-1 and t n , and determine the first odometer data o corresponding to them n-1 and n .
[0080] Step S113, between the two first odometer data o n-1 and n Perform linear interpolation to obtain the first timestamp t m The corresponding second odometer data o m , and according to the second odometer data o m The initial odometer dataset is updated to obtain the target odometer dataset.
[0081] Specifically, linear interpolation is used to calculate the time corresponding to the first timestamp t m The corresponding second odometer data o mThen, based on the second odometer data o m , the initial odometer dataset is updated to obtain the target odometer dataset.
[0082] Step S114, searching the target odometer data set for the third timestamp of the initial point cloud data corresponding to the previous target axis position of the paper roll to be identified and the first timestamp of the initial point cloud data corresponding to the new target axis position. m The third odometer data between.
[0083] Specifically, in the target odometer data set, the data from the third timestamp of the initial point cloud data corresponding to the previous target axis position to the first timestamp of the initial point cloud data corresponding to the new target axis position is filtered. m All odometer data between are determined as the third odometer data.
[0084] Step S115 , updating the target axis center position of the paper roll to be identified according to the third odometer data, and obtaining an updated axis center position of the paper roll to be identified.
[0085] Specifically, based on the extended Kalman filter algorithm, firstly according to the third odometer data, t n-1 The state vector u corresponding to the moment n-1 (i.e. the target axis position of the paper roll to be identified) and t n-1 The state covariance matrix ∑ corresponding to the moment n-1 Make a prediction and get t m The state vector u corresponding to the moment m (i.e., the target axis position predicted by the paper roll to be identified) and the state covariance matrix ∑ m Then, the target axis position u predicted by the paper roll to be identified is used m and the state covariance matrix ∑ m , replace t m The state vector (i.e., the new target axis position of the paper roll to be identified) and the state covariance matrix originally corresponding to the time instant are used to update the target axis position of the paper roll to be identified.
[0086] Since there is a delay in the laser radar when acquiring point cloud data, and there is also a delay in the processing of point cloud fitting paper roll, the fitted paper roll axis position is already the position from some time ago. In addition, since the processing cycle of point cloud fitting paper roll is relatively long, the movement of the vehicle during this period will generate multiple frames of odometer data. In order to compensate for this time lag and improve the accuracy of positioning, on the basis of the traditional extended Kalman filter, multiple odometer data predictions are used, combined with a delayed update of the extended Kalman filter with a single fitting result update, to obtain a more accurate paper roll axis position. Based on the inventive concept, in one embodiment, the method also includes the following steps S122-S124:
[0087] Step S122, searching the target odometer data set for a timestamp greater than or equal to the first timestamp t m The fourth odometer data;
[0088] Step S124, predicting based on the fourth odometer data to obtain the precise axis position of the paper roll to be identified.
[0089] Specifically, based on the updated axis position of the paper roll to be identified obtained in step S115, the timestamp is greater than or equal to the first timestamp t m The fourth odometer data, t i ≥t m Odometer data, t i Represents the latest timestamp in the target odometer data set. The fourth odometer data, t i-1 The state vector u corresponding to the moment i-1 and t i-1 The state covariance matrix ∑ corresponding to the moment i-1 After a series of processing, it can be predicted that t i The state vector u corresponding to the moment i and the state covariance matrix ∑ i The state vector u i This is the more accurate axis position of the paper roll to be identified. It is applied to industrial handling vehicles to further improve positioning accuracy and reliability.
[0090] In a specific example, taking a forklift as an example, the implementation process of this application is described in detail as follows:
[0091] Step a: Use a single-line laser radar installed on a forklift to scan the paper roll to be identified and obtain its two-dimensional point cloud data.
[0092] Step b: converting the collected two-dimensional point cloud data into the coordinate system of the forklift.
[0093] Step c: converting the initial world coordinate position of the paper roll to be identified into the coordinate system of the forklift to ensure data consistency.
[0094] Step d, based on the initial world coordinate position information converted in step c, the two-dimensional point cloud obtained in step a is screened and filtered to remove irrelevant point cloud data. The two-dimensional point cloud before filtering is as follows Figure 2 As shown in Figure 3 shown.
[0095] Step e: Use the random sampling consistency algorithm combined with the two-point method (or three-point method) to fit the axis position of the paper roll to be identified and the radius information of the paper roll.
[0096] Step f, comparing and analyzing the paper roll axis center position obtained by fitting in step e with the initial world coordinate position of the paper roll, and selecting the paper roll axis center position data that meets the requirements.
[0097] Step g: considering that the paper roll fitting process is time-consuming, multiple odometer data will be accumulated between two consecutive paper roll fitting results. To ensure data integrity, all collected odometer data are stored.
[0098] Step h, when a new paper roll fitting result is generated, compare the original timestamp of the point cloud of the new result with the timestamp of the stored odometer data, find the odometer data of the two timestamps closest to the original timestamp of the point cloud, and use the linear interpolation method to calculate the odometer data corresponding to the original timestamp of the point cloud.
[0099] Step i, starting from the point cloud timestamp corresponding to the last paper roll fitting result to the point cloud timestamp corresponding to the new paper roll fitting result, all odometer data within this time period are used to predict the extended Kalman filter of the paper roll fitting result.
[0100] Step j: combining the new paper roll fitting result with the prediction result in step i, and using the extended Kalman filter algorithm to update the axis position of the paper roll.
[0101] Step k, based on the updated result of step j, using the odometer data with a time stamp later than the point cloud time stamp corresponding to the new paper roll fitting result, further predict the change of the axis position of the paper roll.
[0102] Step 1, finally outputting the paper roll axis data with higher frequency and more accurate value in step k for use in forklift operation or other related applications.
[0103] In this embodiment, a single-line laser radar is used to scan the paper roll, and the obtained two-dimensional point cloud is projected onto the plane where the forklift is located. The initial world coordinate position of the paper roll is used to filter the points in the two-dimensional point cloud, and then the random sampling consistency algorithm and the two-point method (three-point method) are used to fit the axis position and radius of the paper roll. The fitted axis position of the paper roll is then compared with the initial world coordinate position of the paper roll to screen out the axis position of the paper roll that meets the requirements. Then, the extended Kalman filter algorithm is used to fuse the axis position of the paper roll fitted by the point cloud and the data of the odometer to output a higher frequency, smaller fluctuation range, and more stable axis position of the paper roll.
[0104] It should be understood that, although the various steps in the flowcharts involved in the above-mentioned embodiments are displayed in sequence according to the indication of the arrows, these steps are not necessarily executed in sequence according to the order indicated by the arrows. Unless there is a clear explanation in this article, the execution of these steps does not have a strict order restriction, and these steps can be executed in other orders. Moreover, at least a part of the steps in the flowcharts involved in the above-mentioned embodiments can include multiple steps or multiple stages, and these steps or stages are not necessarily executed at the same time, but can be executed at different times, and the execution order of these steps or stages is not necessarily to be carried out in sequence, but can be executed in turn or alternately with other steps or at least a part of the steps or stages in other steps.
[0105] Based on the same inventive concept, the embodiment of the present application also provides a paper roll identification device for implementing the paper roll identification method involved above. The implementation scheme for solving the problem provided by the device is similar to the implementation scheme recorded in the above method, so the specific limitations in one or more embodiments of the paper roll identification device provided below can refer to the limitations of the paper roll identification method above, and will not be repeated here.
[0106] In one embodiment, Figure 4 As shown, a paper roll identification device is provided. The device comprises:
[0107] The point cloud acquisition module 202 is used to acquire initial point cloud data; wherein the initial point cloud data is data obtained by scanning the paper roll to be identified by a laser beam on an industrial transport vehicle;
[0108] The point cloud screening module 204 is used to screen the initial point cloud data according to the initial position information of the paper roll to be identified, and obtain the target point cloud data;
[0109] The point cloud fitting module 206 is used to perform fitting according to the target point cloud data to obtain at least one initial axis position of the paper roll to be identified and the radius of the paper roll to be identified;
[0110] The position screening module 208 is used to screen the initial axis position of at least one paper roll to be identified according to the initial position information of the paper roll to be identified, so as to obtain the target axis position of the paper roll to be identified.
[0111] In the above-mentioned paper roll identification device, first, the paper roll to be identified is scanned by a laser beam on an industrial transport vehicle to obtain initial point cloud data. These point cloud data provide the three-dimensional shape and position information of the paper roll, which is the basis for subsequent identification and processing. Then, according to the initial position information of the paper roll to be identified, the initial point cloud data is screened to obtain the target point cloud data. This step is based on the given approximate position of the paper roll, and the most relevant and representative point cloud data for the paper roll to be identified is extracted from a large amount of point cloud data to reduce the complexity of subsequent processing and improve accuracy. Then, the target point cloud data is used for fitting to obtain at least one initial axis position of the paper roll to be identified and the radius of the paper roll. In this step, the initial axis position and radius of the paper roll are calculated from the point cloud data by a fitting algorithm. Finally, according to the initial position information of the paper roll to be identified, the initial axis position obtained by fitting is screened again to obtain the target axis position of the paper roll to be identified. This step can ensure that the target axis position finally obtained matches the approximate position of the paper roll to improve the accuracy and reliability of identification. It can be seen that the device combines the initial position information of the test paper to be identified with the point cloud data obtained by laser scanning, and processes the point cloud data by screening and fitting, thereby achieving accurate identification and positioning of the paper roll to be identified. In other words, it solves the problem of industrial handling vehicles being able to accurately obtain paper roll information given the approximate position of the paper roll, thereby providing strong support for automated handling operations.
[0112] It should be noted that the paper roll identification device provided in the above embodiment only uses the division of the above functional modules as an example to illustrate when realizing the corresponding functions. In actual applications, the above functions can be assigned to different functional modules as needed, that is, the internal structure of the device is divided into different functional modules to complete all or part of the functions described above. In addition, the paper roll identification device provided in the above embodiment and the paper roll identification method embodiment belong to the same concept, and the specific implementation process is detailed in the method embodiment, which will not be repeated here.
[0113] According to one aspect of the present application, an embodiment of the present invention further provides a computer program product, the computer program product comprising a computer program, the computer program comprising a program code for executing the method shown in the flowchart. In such an embodiment, the computer program can be downloaded and installed from a network through a communication part. When the computer program is executed by a processor, the paper roll identification method provided in the embodiment of the present application is executed.
[0114] In addition, an embodiment of the present invention further provides a computer device, which includes a processor and a memory, wherein the memory stores a computer program, and the processor can execute the computer program stored in the memory. When the computer program is executed by the processor, the paper roll identification method provided in any of the above embodiments can be implemented.
[0115] For example, Figure 5 A computer device provided by an embodiment of the present invention is shown. The device includes a bus 1110 , a processor 1120 , a transceiver 1130 , a bus interface 1140 , a memory 1150 , and a user interface 1160 .
[0116] In the embodiment of the present invention, the device further includes: a computer program stored in the memory 1150 and executable on the processor 1120, and when the computer program is executed by the processor 1120, each process of the above-mentioned paper roll identification method embodiment is implemented.
[0117] The transceiver 1130 is configured to receive and send data under the control of the processor 1120 .
[0118] In an embodiment of the present invention, a bus architecture (represented by bus 1110 ) may include any number of interconnected buses and bridges, and bus 1110 connects various circuits including one or more processors represented by processor 1120 and a memory represented by memory 1150 .
[0119] Bus 1110 represents one or more of any of several types of bus structures, including a memory bus and memory controller, a peripheral bus, an Accelerate Graphical Port (AGP), a processor, or a local bus using any of a variety of bus architectures. By way of example and not limitation, such architectures include: Industry Standard Architecture (ISA) bus, Micro Channel Architecture (MCA) bus, Enhanced ISA (EISA) bus, Video Electronics Standards Association (VESA), Peripheral Component Interconnect (PCI) bus.
[0120] The processor 1120 may be an integrated circuit chip with signal processing capabilities. In the implementation process, each step of the above method embodiment may be completed by an integrated logic circuit of hardware in the processor or an instruction in the form of software. The above processors include: a general processor, a central processing unit (CPU), a network processor (NP), a digital signal processor (DSP), an application specific integrated circuit (ASIC), a field programmable gate array (FPGA), a complex programmable logic device (CPLD), a programmable logic array (PLA), a microcontroller unit (MCU) or other programmable logic devices, discrete gates, transistor logic devices, discrete hardware components. The methods, steps and logic block diagrams disclosed in the embodiments of the present invention may be implemented or executed. For example, the processor may be a single-core processor or a multi-core processor, and the processor may be integrated into a single chip or located on multiple different chips.
[0121] Processor 1120 can be a microprocessor or any conventional processor. The method steps disclosed in the embodiment of the present invention can be directly executed by a hardware decoding processor, or by a combination of hardware and software modules in the decoding processor. The software module can be located in a readable storage medium known in the art, such as a random access memory (RAM), a flash memory (FlashMemory), a read-only memory (ROM), a programmable read-only memory (PROM), an erasable programmable read-only memory (EPROM), a register, etc. The readable storage medium is located in the memory, and the processor reads the information in the memory and completes the steps of the above method in combination with its hardware.
[0122] The bus 1110 may also connect various other circuits such as peripheral devices, voltage regulators or power management circuits, and the bus interface 1140 provides an interface between the bus 1110 and the transceiver 1130, which are well known in the art. Therefore, the embodiments of the present invention will not be further described.
[0123] The transceiver 1130 may be one element or multiple elements, such as multiple receivers and transmitters, and provides a unit for communicating with various other devices on a transmission medium. For example, the transceiver 1130 receives external data from other devices, and the transceiver 1130 is used to send data processed by the processor 1120 to other devices. Depending on the nature of the computer system, a user interface 1160 may also be provided, such as a touch screen, a physical keyboard, a display, a mouse, a speaker, a microphone, a trackball, a joystick, and a stylus.
[0124] It should be understood that in an embodiment of the present invention, the memory 1150 may further include a memory remotely arranged relative to the processor 1120, and these remotely arranged memories may be connected to the server through a network. One or more parts of the above-mentioned network may be an ad hoc network, an intranet, an extranet, a virtual private network (VPN), a local area network (LAN), a wireless local area network (WLAN), a wide area network (WAN), a wireless wide area network (WWAN), a metropolitan area network (MAN), the Internet, a public switched telephone network (PSTN), a plain old telephone service network (POTS), a cellular telephone network, a wireless network, a wireless fidelity (Wi-Fi) network, and a combination of two or more of the above-mentioned networks. For example, the cellular telephone network and the wireless network can be a Global System for Mobile Communications (GSM) system, a Code Division Multiple Access (CDMA) system, a Worldwide Interoperability for Microwave Access (WiMAX) system, a General Packet Radio Service (GPRS) system, a Wideband Code Division Multiple Access (WCDMA) system, a Long Term Evolution (LTE) system, a LTE Frequency Division Duplex (FDD) system, a LTE Time Division Duplex (TDD) system, an Advanced Long Term Evolution (LTE-A) system, a Universal Mobile Telecommunications (UMTS) system, an Enhanced Mobile Broadband (eMBB) system, a Massive Machine Type of Communication (mMTC) system, an Ultra Reliable Low Latency Communications (uRLLC) system, etc.
[0125] It should be understood that the memory 1150 in the embodiment of the present invention may be a volatile memory or a non-volatile memory, or may include both a volatile memory and a non-volatile memory. Among them, the non-volatile memory includes: a read-only memory (ROM), a programmable read-only memory (PROM), an erasable programmable read-only memory (EPROM), an electrically erasable programmable read-only memory (EEPROM), or a flash memory.
[0126] Volatile memory includes: Random Access Memory (RAM), which is used as an external cache. By way of example but not limitation, many forms of RAM are available, such as: Static RAM (SRAM), Dynamic RAM (DRAM), Synchronous DRAM (SDRAM), Double Data Rate SDRAM (DDRSDRAM), Enhanced SDRAM (ESDRAM), Synchronous Link DRAM (SLDRAM) and Direct Rambus RAM (DRRAM). The memory 1150 described in the embodiments of the present invention includes but is not limited to the above and any other suitable types of memory.
[0127] In the embodiment of the present invention, the memory 1150 stores the following elements of the operating system 1151 and the application program 1152: executable modules, data structures, or subsets thereof, or extended sets thereof.
[0128] Specifically, the operating system 1151 includes various system programs, such as a framework layer, a core library layer, a driver layer, etc., which are used to implement various basic services and process hardware-based tasks. The application 1152 includes various applications, such as a media player (Media Player) and a browser (Browser), which are used to implement various application services. The program for implementing the method of the embodiment of the present invention may be included in the application 1152. The application 1152 includes applets, objects, components, logic, data structures, and other computer system executable instructions that perform specific tasks or implement specific abstract data types.
[0129] In addition, an embodiment of the present invention further provides a computer-readable storage medium on which a computer program is stored. When the computer program is executed by a processor, the various processes of the above-mentioned paper roll identification method embodiment are implemented and the same technical effect can be achieved. To avoid repetition, it will not be repeated here.
[0130] Computer readable storage media include: permanent and non-permanent, removable and non-removable media, which are tangible devices that can retain and store instructions for use by instruction execution devices. Computer readable storage media include: electronic storage devices, magnetic storage devices, optical storage devices, electromagnetic storage devices, semiconductor storage devices, and any suitable combination of the above. Computer readable storage media include: 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), non-volatile random access memory (NVRAM), electrically erasable programmable read-only memory (EEPROM), flash memory or other memory technology, compact disk read-only memory (CD-ROM), digital versatile disk (DVD) or other optical storage, magnetic cassette storage, magnetic tape disk storage or other magnetic storage devices, memory sticks, mechanical encoding devices (such as punched cards or raised structures in grooves with instructions recorded thereon) or any other non-transmission medium that can be used to store information that can be accessed by a computing device. As defined in the embodiments of the present invention, computer-readable storage media do not include temporary signals themselves, such as radio waves or other freely propagating electromagnetic waves, electromagnetic waves propagating through waveguides or other transmission media (such as light pulses passing through fiber optic cables), or electrical signals transmitted through wires.
[0131] In the description of the embodiments of the present invention, those skilled in the art should know that the embodiments of the present invention can be implemented as methods, devices, equipment and storage media. Therefore, the embodiments of the present invention can be specifically implemented in the following forms: complete hardware, complete software (including firmware, resident software, microcode, etc.), a combination of hardware and software. In addition, in some embodiments, the embodiments of the present invention can also be implemented in the form of a computer program product in one or more computer-readable storage media, and the computer-readable storage medium contains computer program code.
[0132] The above-mentioned computer-readable storage medium may adopt any combination of one or more computer-readable storage media. Computer-readable storage media include: electrical, magnetic, optical, electromagnetic, infrared or semiconductor systems, devices or devices, or any combination of the above. More specific examples of computer-readable storage media include: portable computer disks, hard disks, random access memories (RAM), read-only memories (ROM), erasable programmable read-only memories (EPROM), flash memories, optical fibers, compact disk read-only memories (CD-ROM), optical storage devices, magnetic storage devices or any combination of the above. In an embodiment of the present invention, a computer-readable storage medium may be any tangible medium containing or storing a program, which may be used by or in combination with an instruction execution system, device, or device.
[0133] The computer program code contained in the above-mentioned computer-readable storage medium can be transmitted by any appropriate medium, including: wireless, wire, optical cable, radio frequency (RF) or any suitable combination thereof.
[0134] The computer program code for performing the operation of the embodiment of the present invention can be written in assembly instructions, instruction set architecture (ISA) instructions, machine instructions, machine-related instructions, microcode, firmware instructions, state setting data, integrated circuit configuration data, or in one or more programming languages or a combination thereof, wherein the programming language includes an object-oriented programming language, such as Java, Smalltalk, C++, and also includes a conventional procedural programming language, such as C language or a similar programming language. The computer program code can be executed entirely on the user's computer, partially on the user's computer, as an independent software package, partially on the user's computer, partially on a remote computer, and completely on a remote computer or server. In the case of a remote computer, the remote computer can be connected to the user's computer or to an external computer through any type of network, including a local area network (LAN) or a wide area network (WAN).
[0135] It should be understood that each box in the flowchart and / or block diagram and the combination of boxes in the flowchart and / or block diagram can be implemented by computer-readable program instructions. These computer-readable program instructions can be provided to a processor of a general-purpose computer, a special-purpose computer or other programmable data processing device to produce a machine, and these computer-readable program instructions are executed by a computer or other programmable data processing device to produce a device that implements the functions / operations specified by the boxes in the flowchart and / or block diagram.
[0136] These computer-readable program instructions may also be stored in a computer-readable storage medium that enables a computer or other programmable data processing device to work in a specific manner. In this way, the instructions stored in the computer-readable storage medium produce an instruction device product including functions / operations specified in the blocks in the flowchart and / or block diagram.
[0137] Computer-readable program instructions may also be loaded onto a computer, other programmable data processing apparatus, or other device, so that a series of operational steps are performed on the computer, other programmable data processing apparatus, or other device to produce a computer-implemented process, thereby enabling the instructions executed on the computer or other programmable data processing apparatus to provide a process for implementing the functions / operations specified in the blocks in the flowchart and / or block diagram.
[0138] The above is only a specific implementation of the embodiment of the present invention, but the protection area of the embodiment of the present invention is not limited thereto. Any technician familiar with the technical field can easily think of changes or replacements within the technical area disclosed in the embodiment of the present invention, which should be included in the protection area of the embodiment of the present invention. Therefore, the protection area of the embodiment of the present invention should be based on the protection area of the claims.
Claims
1. A paper roll identification method, characterized in that: The method comprises: Acquire initial point cloud data; wherein the initial point cloud data is data obtained by scanning the paper roll to be identified by a laser beam on an industrial transport vehicle; According to the initial position information of the paper roll to be identified, the initial point cloud data is screened to obtain target point cloud data; Fitting is performed according to the target point cloud data to obtain at least one initial axis position of the paper roll to be identified and a radius of the paper roll to be identified; Screening the initial axis position of at least one paper roll to be identified according to the initial position information of the paper roll to be identified to obtain the target axis position of the paper roll to be identified; The method further comprises: When t k When a new target axis position of the paper roll to be identified is obtained at any time, an initial odometer data set of the industrial transport vehicle is obtained; According to the first timestamp t of the initial point cloud data corresponding to the new target axis position m and a second timestamp of the initial odometer data set, searching the initial odometer data set for a location at the first timestamp t m The two second timestamps before and after t n-1 and t n The corresponding two first odometer data o n-1 and n ; In the two first odometer data o n-1 and n Perform linear interpolation to obtain the first timestamp t m The corresponding second odometer data o m , and according to the second odometer data o m Updating the initial odometer data set to obtain a target odometer data set; In the target odometer data set, the third timestamp of the initial point cloud data corresponding to the previous target axis position of the paper roll to be identified and the first timestamp of the initial point cloud data corresponding to the new target axis position are searched. m The third odometer data between; The new target axis center position of the paper roll to be identified is updated according to the third odometer data to obtain the updated axis center position of the paper roll to be identified.
2. The method according to claim 1, characterized in that After the new target axis position of the paper roll to be identified is updated according to the third odometer data to obtain the updated axis position of the paper roll to be identified, the method further includes: In the target odometer data set, search for a timestamp greater than or equal to the first timestamp t m The fourth odometer data; Prediction is performed based on the fourth odometer data to obtain the precise axis position of the paper roll to be identified.
3. The method according to claim 1 or 2, characterized in that: The target axis center position of the paper roll to be identified is updated according to the third odometer data to obtain the updated axis center position of the paper roll to be identified, including: According to the third odometer data, t n-1 The target axis position of the paper roll to be identified corresponding to the time t n-1 The state covariance matrix corresponding to the time is predicted to obtain the target axis position predicted by the paper roll to be identified; The predicted target axis center position of the paper roll to be identified is used to replace the new target axis center position of the paper roll to be identified, so as to achieve the update of the target axis center position.
4. The method according to claim 1, characterized in that: According to the initial position information of the paper roll to be identified, the initial point cloud data is screened to obtain target point cloud data, including: Converting the initial point cloud data into a vehicle coordinate system to obtain converted point cloud data; wherein the vehicle coordinate system is a coordinate system constructed based on the industrial transport vehicle; Converting the initial position information of the paper roll to be identified into the vehicle coordinate system to obtain converted position information; In the vehicle coordinate system, the converted point cloud data is screened according to the converted position information to obtain target point cloud data.
5. The method according to claim 4, characterized in that The method of filtering the converted point cloud data in the vehicle coordinate system according to the converted position information to obtain target point cloud data includes: In the vehicle coordinate system, extracting the x-coordinate and the y-coordinate in the converted position information; In the vehicle coordinate system, constructing a first target area according to the x-coordinate, the y-coordinate, the pre-stored paper roll radius and the first preset threshold; In the converted point cloud data, point cloud data outside the first target area is screened out, and point cloud data within the first target area is retained to obtain target point cloud data.
6. The method according to claim 1, characterized in that The step of screening the initial axis position of at least one paper roll to be identified according to the initial position information of the paper roll to be identified to obtain the target axis position of the paper roll to be identified includes: constructing a second target area according to the initial position information of the paper roll to be identified and a second preset threshold; Among the initial axis center positions of the at least one paper roll to be identified, the initial axis center positions outside the second target area are screened out, and the initial axis center positions within the second target area are retained to obtain the target axis center position of the paper roll to be identified.
7. A paper roll identification device, characterized in that: The device comprises: A point cloud acquisition module, used to acquire initial point cloud data; wherein the initial point cloud data is data obtained by scanning the paper roll to be identified by a laser beam on an industrial transport vehicle; A point cloud screening module, used for screening the initial point cloud data according to the initial position information of the paper roll to be identified, to obtain target point cloud data; A point cloud fitting module, used for performing fitting according to the target point cloud data to obtain at least one initial axis position of the paper roll to be identified and a radius of the paper roll to be identified; A position screening module, used for screening the initial axis position of at least one paper roll to be identified according to the initial position information of the paper roll to be identified, so as to obtain the target axis position of the paper roll to be identified; The device also includes: Data acquisition module, used when t k When a new target axis position of the paper roll to be identified is obtained at any time, an initial odometer data set of the industrial transport vehicle is obtained; The first data search module is used to find the first timestamp t of the initial point cloud data corresponding to the new target axis position. m and a second timestamp of the initial odometer data set, searching the initial odometer data set for a location at the first timestamp t m The two second timestamps before and after t n-1 and t n The corresponding two first odometer data o n-1 and n ; A data updating module is used to update the two first odometer data o n-1 and n Perform linear interpolation to obtain the first timestamp t m The corresponding second odometer data o m , and according to the second odometer data o m Updating the initial odometer data set to obtain a target odometer data set; The second data search module is used to search the target odometer data set for the third timestamp of the initial point cloud data corresponding to the previous target axis position of the paper roll to be identified and the first timestamp of the initial point cloud data corresponding to the new target axis position. m The third odometer data between; The position refinement module is used to update the new target axis position of the paper roll to be identified according to the third odometer data to obtain the updated axis position of the paper roll to be identified.
8. A computer device comprising a memory and a processor, wherein the memory stores a computer program, wherein: When the processor executes the computer program, the steps of the method according to any one of claims 1 to 6 are implemented.
9. A computer-readable storage medium having a computer program stored thereon, characterized in that: When the computer program is executed by a processor, the steps of the method according to any one of claims 1 to 6 are implemented.
