A method and device for constructing a model of a bulk cargo yard
By constructing two-dimensional, three-dimensional, and four-dimensional models of bulk cargo yards and utilizing information technology and artificial intelligence, the problems of untimely and inaccurate data in bulk cargo yards have been solved, achieving visualization of yard data and improving operational efficiency.
Patent Information
- Authority / Receiving Office
- CN · China
- Patent Type
- Patents(China)
- Current Assignee / Owner
- BEIJING DAOPOWER
- Filing Date
- 2023-04-13
- Publication Date
- 2026-07-21
AI Technical Summary
Existing bulk cargo yard management methods rely on manual inspections, which leads to untimely and inaccurate data, affecting operational efficiency, especially when there are insufficient yard tally staff or in bad weather.
By acquiring raw data from bulk cargo yards, two-dimensional, three-dimensional, and four-dimensional models are constructed. Information technology is used to replace manual inspections, generating visualized yard data. Artificial intelligence algorithms are then combined to classify cargo stacks and predict operational plans.
It enables timely and accurate display of bulk cargo yard data, improves data transmission and operational efficiency, optimizes yard utilization and cargo turnover, and reduces human error and weather impact.
Smart Images
Figure CN116415319B_ABST
Abstract
Description
Technical Field
[0001] This application relates to the field of Internet technology, and in particular to a method and apparatus for modeling bulk cargo yards. Background Technology
[0002] Bulk cargo yards are the main distribution centers for bulk cargo in ports. They are used to store goods and load and unload them, which can shorten the dwell time of vehicles and ships in the port, improve the turnover efficiency of goods, and improve the quality of goods transportation.
[0003] Currently, the management method for bulk cargo yards involves yard tallies manually inspecting the yards to obtain paper-based yard data. This data is then used to ensure the efficient and stable operation of various tasks within the yard. However, when there are insufficient yard tallies, inaccurate stack information, untimely data provision, or inclement weather preventing yard tallies from conducting inspections, the yard data cannot be transmitted to the operators in a timely manner, thus affecting the efficiency of subsequent operations. Summary of the Invention
[0004] In view of this, this application provides a method and apparatus for modeling bulk cargo yards, with the aim of displaying the yard data of bulk cargo yards in a timely and accurate manner.
[0005] The first aspect of this application provides a method for modeling bulk cargo yards, the method comprising:
[0006] Obtain raw data of the bulk cargo yard, including geospatial physical data of the bulk cargo yard, business information of the storage locations, business information of the goods, three-dimensional point cloud data of the stacks, and the production operation time cycle of the bulk cargo yard, wherein the stacks are distributed on storage locations in the bulk cargo yard.
[0007] Two-dimensional yard data is constructed based on the geospatial physical data of the bulk cargo yard, the business information of the cargo location, and the business information of the cargo.
[0008] A point cloud model of the stack is generated based on the three-dimensional point cloud data of the stack.
[0009] The point cloud model is superimposed on the two-dimensional stockpile data to obtain three-dimensional stockpile data;
[0010] Based on the production operation time cycle of the bulk cargo yard and the three-dimensional yard data, a four-dimensional yard model of the bulk cargo yard is constructed.
[0011] Optionally, generating the point cloud model of the stack based on the three-dimensional point cloud data of the stack includes:
[0012] The three-dimensional point cloud data is scanned in a pre-constructed planar coordinate system according to the preset point cloud sampling interval to obtain three-dimensional point cloud data with a point cloud interval smaller than the point cloud sampling interval.
[0013] The point cloud model is obtained by clustering the three-dimensional point cloud data whose point cloud interval is smaller than the point cloud sampling interval.
[0014] Optionally, the step of overlaying the point cloud model onto the two-dimensional stockpile data to obtain three-dimensional stockpile data includes:
[0015] Obtain the first feature points of the stack from the point cloud model;
[0016] The goods are classified according to the first feature points of the goods stack and the preset goods stack classification model to obtain the first classification result of the goods stack;
[0017] Based on the first classification result of the stack, the point cloud model is superimposed onto the two-dimensional stacking data using a stacking layout algorithm to obtain the three-dimensional stacking data.
[0018] Optionally, the method further includes:
[0019] When the first classification result of the stack cannot be obtained based on the first feature point and the stack classification model, the point cloud model is split according to the preset basic category model to obtain a point cloud sub-model.
[0020] Obtain the second feature points of the stack from the point cloud sub-model;
[0021] Based on the second feature points of the stack and the stack classification model, the stack is classified to obtain the second classification result of the stack.
[0022] Based on the second classification result of the cargo stack, the point cloud sub-model is superimposed onto the two-dimensional storage yard data using the storage yard layout algorithm to obtain the three-dimensional storage yard data.
[0023] Optionally, the step of overlaying the point cloud model onto the two-dimensional stockpile data using a stockpile layout algorithm includes:
[0024] The point cloud model is structurally adjusted according to the preset stacking standard to obtain the stacking model;
[0025] The stack model is simplified into individual polygons to obtain a two-dimensional graphic of the stack.
[0026] The location of the stack of goods in the bulk cargo yard is determined based on the two-dimensional graph and the rectangular clustering algorithm.
[0027] The position of the stack of goods in the two-dimensional storage yard data is obtained based on the position of the stack of goods in the bulk cargo yard.
[0028] The point cloud model of the stack is superimposed onto the corresponding position of the stack in the two-dimensional stockyard data.
[0029] Optionally, the method further includes:
[0030] The bulk cargo yard is diagnosed based on the four-dimensional yard model and the preset analysis rules to obtain the diagnosis results of the bulk cargo yard. The preset analysis rules include the principle of stacking similar items together, the principle of space utilization, the principle of turnover speed, the principle of cargo flow to the nearest location, and the principle of environmental protection.
[0031] Optionally, the method further includes:
[0032] The four-dimensional storage yard model is used to predict the completion time of the piling plan and / or the completion time of the stacking plan of the bulk cargo storage yard within a preset time period, thereby obtaining the prediction result of the bulk cargo storage yard.
[0033] Another aspect of this application provides a model building apparatus for bulk cargo yards, the apparatus comprising: an acquisition module, a data processing module, and a model building module;
[0034] The acquisition module is used to acquire the raw data of the bulk cargo yard. The raw data includes the geospatial physical data of the bulk cargo yard, the business information of the storage locations, the business information of the goods, the three-dimensional point cloud data of the stacks, and the production operation time cycle of the bulk cargo yard. The stacks are distributed on the storage locations in the bulk cargo yard.
[0035] The data processing module is used to construct two-dimensional yard data based on the geospatial physical data of the bulk cargo yard, the business information of the cargo location, and the business information of the cargo.
[0036] The model building module is used to generate a point cloud model of the stack based on the three-dimensional point cloud data of the stack.
[0037] The data processing module is also used to overlay the point cloud model onto the two-dimensional stockpile data to obtain three-dimensional stockpile data;
[0038] The model building module is also used to build a four-dimensional storage yard model of the bulk cargo storage yard based on the production operation time cycle of the bulk cargo storage yard and the three-dimensional storage yard data.
[0039] Optionally, the model building module is specifically used to scan the three-dimensional point cloud data in a pre-built planar coordinate system according to a preset point cloud sampling interval, so as to obtain three-dimensional point cloud data with a point cloud interval smaller than the point cloud sampling interval.
[0040] The model building module is also used to cluster the three-dimensional point cloud data whose point cloud interval is smaller than the point cloud sampling interval to obtain the point cloud model.
[0041] Optionally, the data processing module is further configured to obtain the first feature points of the stack from the point cloud model;
[0042] The data processing module is also used to classify the stack of goods based on the first feature points of the stack and the preset stack classification model, and obtain the first classification result of the stack of goods.
[0043] The data processing module is further configured to, based on the first classification result of the stack, superimpose the point cloud model onto the two-dimensional stack data using a stack layout algorithm to obtain the three-dimensional stack data.
[0044] Optionally, when the first classification result of the pallet cannot be obtained based on the first feature point and the artificial intelligence algorithm, the data processing module is further configured to split the point cloud model according to the preset basic category model to obtain point cloud sub-models.
[0045] The data processing module is also used to obtain the second feature points of the stack from the point cloud sub-model;
[0046] The data processing module is also used to classify the stack of goods based on the second feature points of the stack and the stack classification model, and obtain the second classification result of the stack of goods.
[0047] The data processing module is further configured to, based on the second classification result of the cargo stack, superimpose the point cloud sub-model onto the two-dimensional storage yard data using the storage yard layout algorithm to obtain the three-dimensional storage yard data.
[0048] Optionally, the data processing module is further configured to adjust the structure of the point cloud model according to a preset stacking standard to obtain a stacking model;
[0049] The data processing module is also used to simplify the stack model into individual polygons to obtain a two-dimensional graphic of the stack.
[0050] The data processing module is also used to determine the location of the stack of goods in the bulk cargo yard based on the two-dimensional graphics and the rectangular clustering algorithm;
[0051] The data processing module is also used to obtain the position of the stack in the two-dimensional storage yard data based on the position of the stack in the bulk cargo yard;
[0052] The data processing module is also used to overlay the point cloud model of the stack onto the corresponding position of the stack in the two-dimensional stockyard data.
[0053] Optionally, the data processing module is further configured to diagnose the bulk cargo yard based on the four-dimensional yard model and preset analysis rules, and obtain the diagnostic results of the bulk cargo yard. The preset analysis rules include the principle of stacking similar items together, the principle of space utilization, the principle of turnover speed, the principle of cargo flow to the nearest location, and the principle of environmental protection.
[0054] Optionally, the data processing module is further configured to predict the completion time of the re-stacking plan and / or the completion time of the stacking plan of the bulk cargo yard within a preset time period using the four-dimensional yard model, and obtain the prediction result of the bulk cargo yard.
[0055] This application discloses a model construction method and apparatus for a bulk cargo yard. The method includes: acquiring raw data of the bulk cargo yard, including geospatial physical data of the bulk cargo yard, business information of storage locations, business information of goods, three-dimensional point cloud data of stacks of goods, and the production operation time cycle of the bulk cargo yard, wherein the stacks of goods are distributed on storage locations in the bulk cargo yard; constructing two-dimensional yard data based on the geospatial physical data of the bulk cargo yard, the business information of storage locations, and the business information of goods; generating a point cloud model of the stacks of goods based on the three-dimensional point cloud data of the stacks of goods; superimposing the point cloud model onto the two-dimensional yard data to obtain three-dimensional yard data; and constructing a four-dimensional yard model of the bulk cargo yard based on the production operation time cycle and the three-dimensional yard data. The method provided in this application enables timely and accurate display of the yard data of the bulk cargo yard, providing a visual representation of the bulk cargo yard. Attached Figure Description
[0056] Figure 1 A flowchart illustrating a method for constructing a bulk cargo yard model, provided in an embodiment of this application;
[0057] Figure 2 This is a schematic diagram of the structure of a bulk cargo storage yard provided in an embodiment of this application;
[0058] Figure 3 A flowchart illustrating an artificial intelligence process for recognizing pallets, provided as an embodiment of this application;
[0059] Figure 4 This application provides a schematic diagram of the structure of a stack of goods whose classification type cannot be identified.
[0060] Figure 5 A schematic diagram of the structure of a point cloud sub-model of a disassembled stack of goods provided in an embodiment of this application;
[0061] Figure 6A schematic diagram of the structure of another split stack of goods point cloud sub-model provided in this application embodiment;
[0062] Figure 7 A schematic flowchart of a stockyard layout algorithm provided in an embodiment of this application;
[0063] Figure 8 A schematic diagram of a model building device for a bulk cargo yard provided in an embodiment of this application;
[0064] Figure 9 A schematic flowchart illustrating a spatial positioning process provided in an embodiment of this application;
[0065] Figure 10 This application provides a four-dimensional data transfer dependency diagram for a storage yard. Detailed Implementation
[0066] The technical solutions of the embodiments of this application will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some embodiments of this application, and not all embodiments. Based on the embodiments of this application, all other embodiments obtained by those of ordinary skill in the art without creative effort are within the scope of protection of this application.
[0067] The following is combined with Figure 1 This paper introduces a method for constructing a bulk cargo yard model according to an embodiment of the present application, which can be implemented through steps S101-S105.
[0068] S101: Obtain raw data from the bulk cargo yard.
[0069] Specifically, the raw data of the bulk cargo yard is obtained, including: the geospatial physical data of the bulk cargo yard, the business information of the storage locations, the business information of the cargo, the three-dimensional point cloud data of the stacks, and the production operation time cycle of the bulk cargo yard.
[0070] The acquired raw data can be used to construct a four-dimensional model of a bulk cargo yard.
[0071] like Figure 2 The structure diagram of the bulk cargo yard shows that the bulk cargo yard includes a storage area consisting of multiple zones, each zone consisting of multiple storage locations, with stacks of goods distributed on the storage locations within the bulk cargo yard.
[0072] Furthermore, in this embodiment, information technology is used to acquire raw data from bulk cargo yards, solving the problem of inconsistent skill levels among yard tally clerks and avoiding inaccurate yard data caused by human error. Moreover, by replacing manual inspections with information technology to acquire data, the data transmission time is shortened, and the transmission efficiency of yard data is improved.
[0073] S102: Construct two-dimensional yard data based on the geospatial physical data of the bulk cargo yard, the business information of the cargo locations, and the business information of the cargo.
[0074] Specifically, the geospatial physical data of the bulk cargo yard is processed according to a preset ratio, and each cargo location is marked according to its business information to obtain two-dimensional yard data. The geospatial physical data of the bulk cargo yard includes basic spatial physical information such as the length and width of the yard, the length and width of the area, the length and width of the cargo location, the coordinate point set of the bulk cargo yard, and the start and end meters. The business information of the cargo location is used to identify the type of goods stored in that location, such as coal, ore, or commodities.
[0075] In two-dimensional yard data, the rationality of a cargo's stacking location can be determined based on its business attributes, the spatial and physical attributes of the bulk cargo yard, and the business attributes of the storage location. Data such as the space occupied by the cargo and the starting and ending meters of the storage location can be calculated, providing data support for subsequent storage capacity analysis, yard health diagnosis, and yard site planning based on the four-dimensional yard model. Two-dimensional yard data serves as the foundation for spatial positioning in three-dimensional yard data, enabling accurate positioning of the 3D point cloud model of the auxiliary cargo stacks.
[0076] S103: Generate a point cloud model of the stack based on the 3D point cloud data of the stack.
[0077] Specifically, after acquiring the three-dimensional point cloud data of the stack, the three-dimensional point cloud data of the stack is scanned along the x-axis and y-axis of the pre-constructed planar coordinate system according to the preset point cloud sampling interval, so as to obtain three-dimensional point cloud data with a point cloud interval smaller than the preset point cloud sampling interval.
[0078] The point cloud data with point cloud intervals smaller than the preset point cloud sampling interval will be obtained to obtain the point cloud model of the stack.
[0079] The point cloud model of the stack can accurately display the irregular shape of the stack.
[0080] Understandably, point cloud data of cargo stacks can be obtained by scanning the stacks with laser scanners installed in bulk cargo yards.
[0081] S104: Overlay the point cloud model onto the two-dimensional stockpile data to obtain the three-dimensional stockpile data.
[0082] Specifically, after generating the point cloud model of the stack, the first feature point of the stack is obtained from the point cloud model.
[0083] The stack is classified based on its first feature point and a pre-defined stack classification model to obtain the classification result. The classification results include basic category models such as cone, frustum, cylinder, square pyramid, square frustum, and square prism.
[0084] Based on the classification results of the stacks, the point cloud model of the stacks is superimposed onto the two-dimensional yard data using a yard layout algorithm to obtain visualized three-dimensional yard data.
[0085] by Figure 3 Taking the artificial intelligence recognition process of the pallet as an example, the pallet classification model used in this embodiment can perform feature fusion based on the first feature point of the pallet after extracting the first feature point of the pallet, and perform classification comparison based on the feature to obtain the classification result of the pallet.
[0086] Understandably, the pallet classification model is an artificial intelligence matching model trained using deep learning algorithms. Taking the object detection algorithm (YouOnlyLookOnce, YOLO) based on Convolutional Neural Network (CNN) as an example, it uses train2017 from the COCO (Common Objects in Context) dataset as a pre-training set and can achieve a transmission frame rate of 78 frames per second on a Tesla V100 GPU.
[0087] In one possible embodiment, when the classification result of the stack cannot be obtained using the first feature point of the stack and the preset stack classification model, the point cloud model is split according to the preset basic category model to obtain a recognizable point cloud sub-model. Figure 4 For example, Figure 4 The types of pallets in the data cannot be directly matched to generate reasonable classification results, which can... Figure 4 The point cloud model of the stack of goods in the middle is decomposed into, for example, Figure 5 , 6 The point cloud sub-model shown.
[0088] The second feature points of the stack are obtained from the point cloud sub-model, and the stack is classified according to the second feature points and the stack classification model to obtain the classification result of the stack.
[0089] After obtaining the classification results of the cargo stacks, the point cloud sub-model is superimposed onto the two-dimensional storage yard data through the storage yard layout algorithm to obtain the three-dimensional storage yard data of the bulk cargo storage yard.
[0090] By splitting the unrecognizable point cloud model into multiple recognizable basic category models, it is possible to ensure the identification of all types of cargo stacks. The point cloud model of the identified cargo stack is then superimposed onto the two-dimensional storage yard data of the bulk cargo yard to obtain the three-dimensional storage yard data of the bulk cargo yard.
[0091] S105: Construct a four-dimensional model of the bulk cargo yard based on the production operation time cycle and three-dimensional yard data.
[0092] Specifically, based on the three-dimensional data of the bulk cargo yard, the production operation time cycle within the bulk cargo yard is overlaid to establish a four-dimensional model of the bulk cargo yard.
[0093] The production operation time cycle within a bulk cargo yard consists of the estimated task duration, planned task start time, planned task end time, and operation interval duration. The time occupancy relationship of each piece of equipment or each storage location is shown below:
[0094] (Estimated duration of task 1 = Scheduled end time of task 1 - Scheduled start time of task 1) + task interval duration + (Estimated duration of task 2 = Scheduled end time of task 2 - Scheduled start time of task 2)...
[0095] The task route in a production cycle consists of the start point, the path, and the end point, and their relationship is shown below:
[0096] Task route = Start point of task / equipment + Transportation route of task / equipment + End point of task / equipment.
[0097] It is understandable that the equipment used in the bulk cargo yard for the operation cycle includes stacker cranes, reclaimers, ship loaders, ship unloaders, belt conveyors, etc., and there is no limitation in this case.
[0098] The four-dimensional model of a bulk cargo yard, by incorporating the production operation time cycle within the yard, can provide real-time feedback on the distribution of stacks of cargo at each location and the real-time operational status of the yard. Yard handlers can use this data—including train or ship task information, personnel allocation information, and equipment information—to develop pre-operation plans for equipment within the bulk cargo yard.
[0099] like Figure 10 As shown in the data transfer dependency relationship of the four-dimensional yard, it is possible to perform yard capacity analysis based on the four-dimensional yard model, perform yard health diagnosis based on the yard capacity, perform site planning based on the diagnosis report after the yard health diagnosis, perform route planning based on the yard planning, and perform real-time scheduling of stacks based on the route planning.
[0100] In one possible embodiment, the four-dimensional model of the bulk cargo yard superimposed artificial intelligence learning technology and data mining technology can accumulate and analyze historical data of the bulk cargo yard, and make predictions on the cargo stack information of the bulk cargo yard within a preset time period to obtain the prediction results of the bulk cargo yard.
[0101] The four-dimensional model of the bulk cargo yard, due to its visualization features, can take into account the occupation of equipment and geographical space within the bulk cargo yard by multiple parallel operation cycles in space and time, eliminate equipment downtime, verify the rationality of the pre-planned operation within the bulk cargo yard, and ensure the maximization of the daily throughput of the bulk cargo yard.
[0102] In the four-dimensional storage yard model of bulk cargo yards, it is possible to predict stack information. The model can display the stack on the corresponding storage location model at the completion time of each stacking plan and hide the stack at the completion time of each reclaiming plan, enabling the four-dimensional storage yard model to provide timely feedback on the stack status.
[0103] By using a four-dimensional yard model to predict the future condition of the yard and conduct a visual simulation, the accuracy is higher than that of yard tally clerks who rely on experience to predict the future condition of the yard. This improves the work efficiency of yard tally clerks, shortens the time of the pre-operation process in the bulk cargo yard, and thus improves the work efficiency of the operation cycle.
[0104] Understandably, the data used by the four-dimensional yard model of bulk cargo yard to predict stack information comes partly from the stacking and retrieval completion times of the yard tally clerks' pre-planned operations, and partly from the task time cycle prediction values automatically learned from historical data of bulk cargo yards, predicting the stacking and retrieval completion times of tasks.
[0105] Based on the visualized current and future forecast data of the bulk cargo yard using a 4D yard model, yard tally clerks can efficiently complete tasks such as site planning, work route planning, and real-time scheduling, improving yard utilization and cargo turnover rate, thereby increasing work efficiency within the bulk cargo yard and enhancing its economic benefits. Because the 4D yard model can replace yard tally clerks for pre-planning, it lowers the entry barrier for yard tally clerks.
[0106] In one possible embodiment, the storage space of the bulk cargo yard can be analyzed based on a four-dimensional yard model to calculate the storage capacity of the bulk cargo yard.
[0107] A four-dimensional yard model for bulk cargo yards can obtain cargo information from received train or ship unloading plans and calculate the expected yard space and area occupied by the cargo based on cargo weight, density, and angle of repose. Cargo information includes cargo name, owner, weight, density, angle of repose, and moisture content.
[0108] The four-dimensional storage model of a bulk cargo yard can calculate the remaining physical space within the bulk cargo yard based on the two-dimensional storage data contained in the four-dimensional storage model and the existing three-dimensional point cloud model of the cargo stacks, thus preventing the received goods from exceeding the storage capacity of the bulk cargo yard.
[0109] The four-dimensional yard model of bulk cargo yard can provide feedback to yard tally staff on insufficient storage capacity when there is insufficient storage space.
[0110] In one possible embodiment, the bulk cargo yard can be diagnosed based on a four-dimensional yard model and preset analysis rules to obtain diagnostic results. These diagnostic results can then be used to issue early warnings for non-compliant stacks of cargo within the current yard.
[0111] The preset analysis data includes principles such as similar items being stacked together, space utilization, turnover speed, proximity of goods flow, and environmental protection.
[0112] The principle of grouping similar goods together means that the same type of goods should be stacked together without affecting the quality of the goods, so as to save yard space. The four-dimensional yard model of bulk cargo yard can automatically retrieve stacks of the same type of goods, the same owner, and the same freight forwarding company in the yard, and remind the yard tally staff of bulk cargo yard to group them together.
[0113] The space utilization principle is used to determine whether the stacking height of cargo piles in the storage yard is being used reasonably. The space utilization rate is calculated by comparing the stacking height with the preset safe stacking height. When the space utilization rate is lower than the preset threshold, it alerts the yard handlers that the space utilization is insufficient and suggests reasonable stacking. Taking coal as an example, if the safe stacking height for coal is set at 15 meters and the stacking height of the coal pile is 5 meters, the calculated space utilization rate for this pile is 1 / 3, indicating that the space utilization of this pile is insufficient.
[0114] The principle of high turnover speed is to set a storage time for stacks of goods. If there are stacks of goods that exceed the set storage time, an alarm will be promptly issued to the yard tally clerk of the bulk cargo yard.
[0115] The principle of proximity in cargo flow aims to place the cargo stacks close to the means of transport they are transported to. Cargo flow types include trains, ships, and trucks. Taking train flow as an example, if the stack of cargo is far from the train's loading terminal, a notification is sent to the yard clerk in the bulk cargo yard, allowing them to adjust the stacking location.
[0116] In order to avoid dust pollution during severe weather, environmental protection principles are followed, and the yard tally clerks of bulk cargo yards are reminded to spray or cover the cargo locations that are closer to residential areas.
[0117] The bulk cargo yard model construction method provided in this application can display the yard data in a timely and accurate manner, and provide a visual representation of the bulk cargo yard. It can also perform prediction and health diagnosis based on the bulk cargo yard model, thereby improving the utilization rate of storage space within the bulk cargo yard and increasing the daily throughput of the bulk cargo yard.
[0118] The following is combined with Figure 7 This application introduces a yard layout algorithm, which can be implemented through steps S701-S705.
[0119] S701: Adjust the structure of the point cloud model according to the preset stacking standard to obtain the stacking model.
[0120] Specifically, the point cloud model of the stack is automatically structurally adjusted according to the preset stack standard, so that the adjusted stack model can be superimposed on the two-dimensional storage yard data.
[0121] S702: Simplify the stack model into individual polygons to obtain a two-dimensional graphic of the stack.
[0122] Specifically, the stack model is simplified and abstracted into individual units to obtain a two-dimensional model of the stack. This allows the shape of the stack to be displayed in the two-dimensional storage yard data of the bulk cargo yard.
[0123] S703: Determine the location of the stack in the bulk cargo yard based on two-dimensional graphics and rectangular clustering algorithm.
[0124] Specifically, such as Figure 9 The spatial positioning process shown uses a rectangular clustering algorithm to determine the location of the stack in the bulk cargo yard. This allows us to determine the spatial location of the stack in the bulk cargo yard, which is convenient for subsequent determination of the stack's location in the two-dimensional yard data.
[0125] S704: Obtain the corresponding position of the stack in the two-dimensional storage yard data based on the position of the stack in the bulk cargo yard.
[0126] Specifically, the position of the stack in the two-dimensional yard data is determined based on the spatial location of the stack in the bulk cargo yard. After locating the position of the stack in the two-dimensional yard data, the stack model can be superimposed onto the corresponding position in the two-dimensional yard data.
[0127] S705: Overlay the point cloud model of the stack onto the corresponding position of the stack in the two-dimensional yard data.
[0128] Specifically, based on the corresponding position of the stack in the two-dimensional storage yard data, the point cloud model of the stack is superimposed onto the two-dimensional storage yard data to obtain the three-dimensional storage yard data of the bulk cargo storage yard.
[0129] The storage yard layout algorithm provided in this application embodiment can overlay a three-dimensional point cloud model of a stack of goods onto two-dimensional storage yard data to obtain three-dimensional storage yard data for bulk cargo storage yards.
[0130] The following is combined with Figure 8 This application introduces a model building device for bulk cargo yards, comprising: an acquisition module 801, a data processing module 802, and a model building module 803.
[0131] The acquisition module 801 is used to acquire the raw data of the bulk cargo yard. The raw data includes the geospatial physical data of the bulk cargo yard, the business information of the storage locations, the business information of the goods, the three-dimensional point cloud data of the stacks, and the production operation time cycle of the bulk cargo yard. The stacks are distributed on the storage locations in the bulk cargo yard.
[0132] The data processing module 802 is used to construct two-dimensional yard data based on the geospatial physical data of the bulk cargo yard, the business information of the cargo locations, and the business information of the cargo.
[0133] The model building module 803 is used to generate a point cloud model of the stack based on the 3D point cloud data of the stack.
[0134] The data processing module 802 is also used to overlay the point cloud model onto the two-dimensional stockpile data to obtain three-dimensional stockpile data.
[0135] The model building module 803 is also used to build a four-dimensional storage yard model of the bulk cargo storage yard based on the production operation time cycle and three-dimensional storage yard data.
[0136] Specifically, the model building module 803 is used to scan three-dimensional point cloud data in a pre-built planar coordinate system according to a preset point cloud sampling interval, so as to obtain three-dimensional point cloud data with a point cloud interval smaller than the point cloud sampling interval.
[0137] The model building module 803 is also used to cluster 3D point cloud data with point cloud intervals smaller than point cloud sampling intervals to obtain point cloud models.
[0138] Specifically, the data processing module 802 is also used to obtain the first feature points of the stack from the point cloud model.
[0139] The data processing module 802 is also used to classify the stack of goods based on the first feature points of the stack and the preset stack classification model, and obtain the first classification result of the stack of goods.
[0140] The data processing module 802 is also used to overlay the point cloud model onto the two-dimensional storage yard data based on the first classification result of the stack, using a storage yard layout algorithm to obtain three-dimensional storage yard data.
[0141] Specifically, when the first classification result of the pallet cannot be obtained based on the first feature point and the artificial intelligence algorithm, the data processing module 802 is also used to split the point cloud model according to the preset basic category model to obtain the point cloud sub-model.
[0142] The data processing module 802 is also used to obtain the second feature points of the stack from the point cloud sub-model.
[0143] The data processing module 802 is also used to classify the stack of goods based on the second feature points of the stack and the stack classification model, and obtain the second classification result of the stack of goods.
[0144] The data processing module 802 is also used to overlay the point cloud sub-model onto the two-dimensional storage yard data based on the second classification result of the stack, using a storage yard layout algorithm to obtain three-dimensional storage yard data.
[0145] Specifically, the data processing module 802 is also used to adjust the structure of the point cloud model according to the preset stacking standard to obtain the stacking model.
[0146] The data processing module 802 is also used to simplify the stack model into individual polygons to obtain a two-dimensional graphic of the stack.
[0147] The data processing module 802 is also used to determine the location of the stack in the bulk cargo yard based on two-dimensional graphics and a rectangular clustering algorithm.
[0148] The data processing module 802 is also used to obtain the corresponding position of the stack in the two-dimensional stacking yard data based on the position of the stack in the bulk cargo yard.
[0149] The data processing module 802 is also used to overlay the point cloud model of the stack onto the corresponding position of the stack in the two-dimensional yard data.
[0150] Specifically, the data processing module 802 is also used to diagnose the bulk cargo yard based on the four-dimensional yard model and preset analysis rules to obtain the diagnosis results of the bulk cargo yard. The preset analysis rules include the principle of stacking similar items together, the principle of space utilization, the principle of turnover speed, the principle of cargo flow to the nearest location, and the principle of environmental protection.
[0151] Specifically, the data processing module 802 is also used to predict the completion time of the piling plan and / or the completion time of the stacking plan of the bulk cargo yard within a preset time period using a four-dimensional yard model, so as to obtain the prediction results of the bulk cargo yard.
[0152] The bulk cargo yard model building device provided in this application embodiment can display the yard data of the bulk cargo yard in a timely and accurate manner, and provide a visual representation of the bulk cargo yard.
[0153] The terms “first,” “second,” “third,” “fourth,” etc. (if present) in the specification, claims, and accompanying drawings of this application are used to distinguish similar objects and are not necessarily used to describe a particular order or sequence. It should be understood that such data can be interchanged where appropriate so that the embodiments described herein can be implemented in a sequence other than that illustrated or described herein. Furthermore, the terms “comprising” and “having,” and any variations thereof, are intended to cover a non-exclusive inclusion; for example, a process, method, system, product, or apparatus that comprises a series of steps or units is not necessarily limited to those steps or units explicitly listed, but may include other steps or units not explicitly listed or inherent to such processes, methods, products, or apparatus.
[0154] Those skilled in the art will clearly understand that, for the sake of convenience and brevity, the specific working processes of the systems, devices, and units described above can be referred to the corresponding processes in the foregoing method embodiments, and will not be repeated here.
[0155] In the embodiments provided in this application, it should be understood that the disclosed systems, apparatuses, and methods can be implemented in other ways. For example, the apparatus embodiments described above are merely illustrative; for instance, the division of units is only a logical business division, and in actual implementation, there may be other division methods. For example, multiple units or components may be combined or integrated into another system, or some features may be ignored or not executed. Furthermore, the coupling or direct coupling or communication connection shown or discussed may be through some interfaces, indirect coupling or communication connection between apparatuses or units, and may be electrical, mechanical, or other forms.
[0156] The units described as separate components may or may not be physically separate. The components shown as units may or may not be physical units; that is, they may be located in one place or distributed across multiple network units. Some or all of the units can be selected to achieve the purpose of this embodiment according to actual needs.
[0157] Furthermore, the various business units in the embodiments of this application can be integrated into one processing unit, or each unit can exist physically separately, or two or more units can be integrated into one unit. The integrated unit can be implemented in hardware or as a software business unit.
[0158] If the integrated unit is implemented as a software business unit and sold or used as an independent product, it can be stored in a computer-readable storage medium. Based on this understanding, the technical solution of this application, in essence, or the part that contributes to the prior art, or all or part of the technical solution, can be embodied in the form of a software product. This computer software product is stored in a storage medium and includes several instructions to cause a computer device (which may be a personal computer, server, or network device, etc.) to execute all or part of the steps of the methods of the various embodiments of this application. The aforementioned storage medium includes various media capable of storing program code, such as USB flash drives, portable hard drives, read-only memory (ROM), random access memory (RAM), magnetic disks, or optical disks.
[0159] Those skilled in the art will recognize that, in one or more of the examples above, the services described in this invention can be implemented using hardware, software, firmware, or any combination thereof. When implemented in software, these services can be stored in a computer-readable medium or transmitted as one or more instructions or code on a computer-readable medium. Computer-readable media include computer storage media and communication media, wherein communication media include any medium that facilitates the transmission of computer programs from one place to another. Storage media can be any available medium accessible to general-purpose or special-purpose computers.
[0160] The above specific embodiments further illustrate the purpose, technical solution, and beneficial effects of the present invention. It should be understood that the above are merely specific embodiments of the present invention.
[0161] The above embodiments are only used to illustrate the technical solutions of this application, and are not intended to limit it. Although this application has been described in detail with reference to the foregoing embodiments, those skilled in the art should understand that modifications can still be made to the technical solutions described in the foregoing embodiments, or equivalent substitutions can be made to some of the technical features. Such modifications or substitutions do not cause the essence of the corresponding technical solutions to deviate from the scope of the technical solutions of the embodiments of this application.
Claims
1. A method for constructing a model of a bulk cargo yard, characterized in that, The method includes: Obtain raw data of the bulk cargo yard, including geospatial physical data of the bulk cargo yard, business information of the storage locations, business information of the goods, three-dimensional point cloud data of the stacks, and the production operation time cycle of the bulk cargo yard, wherein the stacks are distributed on storage locations in the bulk cargo yard. Two-dimensional yard data is constructed based on the geospatial physical data of the bulk cargo yard, the business information of the cargo location, and the business information of the cargo. A point cloud model of the stack is generated based on the three-dimensional point cloud data of the stack. The point cloud model is superimposed on the two-dimensional stockpile data to obtain three-dimensional stockpile data; Based on the production operation time cycle of the bulk cargo yard and the three-dimensional yard data, a four-dimensional yard model of the bulk cargo yard is constructed.
2. The method according to claim 1, characterized in that, The step of generating a point cloud model of the stack based on the three-dimensional point cloud data of the stack includes: The three-dimensional point cloud data is scanned in a pre-constructed planar coordinate system according to the preset point cloud sampling interval to obtain three-dimensional point cloud data with a point cloud interval smaller than the point cloud sampling interval. The point cloud model is obtained by clustering the three-dimensional point cloud data whose point cloud interval is smaller than the point cloud sampling interval.
3. The method according to claim 1, characterized in that, The step of overlaying the point cloud model onto the two-dimensional stockpile data to obtain three-dimensional stockpile data includes: Obtain the first feature points of the stack from the point cloud model; The goods are classified according to the first feature points of the goods stack and the preset goods stack classification model to obtain the first classification result of the goods stack; Based on the first classification result of the stack, the point cloud model is superimposed onto the two-dimensional stacking data using a stacking layout algorithm to obtain the three-dimensional stacking data.
4. The method according to claim 3, characterized in that, The method further includes: When the first classification result of the stack cannot be obtained based on the first feature point and the stack classification model, the point cloud model is split according to the preset basic category model to obtain a point cloud sub-model. Obtain the second feature points of the stack from the point cloud sub-model; Based on the second feature points of the stack and the stack classification model, the stack is classified to obtain the second classification result of the stack. Based on the second classification result of the cargo stack, the point cloud sub-model is superimposed onto the two-dimensional storage yard data using the storage yard layout algorithm to obtain the three-dimensional storage yard data.
5. The method according to claim 3, characterized in that, The step of overlaying the point cloud model onto the two-dimensional stockpile data using a stockpile layout algorithm includes: The point cloud model is structurally adjusted according to the preset stacking standard to obtain the stacking model; The stack model is simplified into individual polygons to obtain a two-dimensional graphic of the stack. The location of the stack of goods in the bulk cargo yard is determined based on the two-dimensional graph and the rectangular clustering algorithm. The position of the stack of goods in the two-dimensional storage yard data is obtained based on the position of the stack of goods in the bulk cargo yard. The point cloud model of the stack is superimposed onto the corresponding position of the stack in the two-dimensional stockyard data.
6. The method according to claim 1, characterized in that, The method further includes: The bulk cargo yard is diagnosed based on the four-dimensional yard model and the preset analysis rules to obtain the diagnosis results of the bulk cargo yard. The preset analysis rules include the principle of stacking similar items together, the principle of space utilization, the principle of turnover speed, the principle of cargo flow to the nearest location, and the principle of environmental protection.
7. The method according to claim 1, characterized in that, The method further includes: The four-dimensional storage yard model is used to predict the completion time of the piling plan and / or the completion time of the stacking plan of the bulk cargo storage yard within a preset time period, thereby obtaining the prediction result of the bulk cargo storage yard.
8. A model building device for bulk cargo yards, characterized in that, The device includes: an acquisition module, a data processing module, and a model building module; The acquisition module is used to acquire the raw data of the bulk cargo yard. The raw data includes the geospatial physical data of the bulk cargo yard, the business information of the storage locations, the business information of the goods, the three-dimensional point cloud data of the stacks, and the production operation time cycle of the bulk cargo yard. The stacks are distributed on the storage locations in the bulk cargo yard. The data processing module is used to construct two-dimensional yard data based on the geospatial physical data of the bulk cargo yard, the business information of the cargo location, and the business information of the cargo. The model building module is used to generate a point cloud model of the stack based on the three-dimensional point cloud data of the stack. The data processing module is also used to overlay the point cloud model onto the two-dimensional stockpile data to obtain three-dimensional stockpile data; The model building module is also used to build a four-dimensional storage yard model of the bulk cargo storage yard based on the production operation time cycle of the bulk cargo storage yard and the three-dimensional storage yard data.
9. The apparatus according to claim 8, characterized in that, The model building module is specifically used to scan the three-dimensional point cloud data in a pre-built planar coordinate system according to a preset point cloud sampling interval, so as to obtain three-dimensional point cloud data with a point cloud interval smaller than the point cloud sampling interval. The model building module is also used to cluster the three-dimensional point cloud data whose point cloud interval is smaller than the point cloud sampling interval to obtain the point cloud model.
10. The apparatus according to claim 8, characterized in that, The data processing module is also used to obtain the first feature points of the stack from the point cloud model; The data processing module is also used to classify the stack of goods based on the first feature points of the stack and the preset stack classification model, and obtain the first classification result of the stack of goods. The data processing module is further configured to, based on the first classification result of the stack, superimpose the point cloud model onto the two-dimensional stack data using a stack layout algorithm to obtain the three-dimensional stack data.