Camera supplemental point cloud data storage method and system based on RFID inventory

Abstract

The application discloses a camera supplementing cloud data storage method and system based on RFID article inventory, wherein the method comprises the following steps: S1, historical inventory data of an inventory robot is obtained by analysis, wherein the historical inventory data comprises historical route data and historical access data; S2, the weight of each article is determined based on the historical inventory data; S3, whether a camera needs to be arranged to supplement the inventory is judged based on the weight of each article; and S4, whether the supplementing needs to be adjusted and the position and angle of view of the supplementing need to be adjusted are judged based on the monitoring content of the camera. The application is helpful for comprehensively collecting and uniformly processing inventory article information, positioning the specific position of the inventory article, realizing multi-modal storage in the cloud from data collection, and realizing efficient management and real-time control of a large number of inventory articles through the multi-modal intelligent management in the cloud, so that the intelligent level of the Internet of Things application is improved.

Description

TECHNICAL FIELD

[0001] The present application relates to the field of intelligent management of things, in particular to a camera supplementing point cloud storage data method and system based on RFID inventory of goods. BACKGROUND

[0002] RFID inventory management is a batch inventory through a handheld RFID reader. In practical applications, electronic tags are attached to the surface of the objects to be identified. The reader can contactlessly read and identify the electronic data saved in the electronic tags, thereby achieving the purpose of automatically identifying objects.

[0003] Modern factories and logistics companies use RFID to inventory equipment and other assets. Due to the problems of a large number of types, scattered locations, and complex inventory process scenarios, it is difficult for RFID to obtain specific shape and location information of goods. SUMMARY

[0004] The camera supplementing point cloud storage data method and system based on RFID inventory of goods provided by the present application can improve the intelligence, flexibility and efficiency of inventory management, and can at least solve one of the above technical problems.

[0005] In order to solve the above technical problems, the present application adopts the following technical solutions:

[0006] The camera supplementing point cloud storage data method based on RFID inventory of goods comprises the following steps:

[0007] S1, historical inventory data of an inventory robot is obtained by analysis, wherein the historical inventory data comprises historical route data and historical access data;

[0008] S2, the weight of each item is determined based on the historical inventory data;

[0009] S3, whether a camera needs to be arranged for supplementing points is judged based on the weight of each item;

[0010] S4, whether supplementing points, the position and the angle of view of supplementing points need to be adjusted is judged based on the monitoring content of the camera.

[0011] Further, in S1, the historical route data is the walking route recorded by a sensor or GPS tracking the moving path of the inventory robot in the warehouse at each inventory, and the historical access data is the area which is frequently accessed and the inventory frequency of each item in the area identified according to the historical route data.

[0012] Further, in S2, for any one item, the weight of the item is mainly composed of the weighted sum of three indexes of inventory frequency, item importance and item liquidity:

[0013] W1 = b + γ*P + α*F + β*I (1)

[0014] Wherein, W1 is a weight value, P is a frequency of inventory, F is a frequency of item flow, I is an importance of item, γ, α and β are weight vectors, and b is a bias value set by the system.

[0015] Further, in the S2, the inventory route data and the inventory frequency data in the historical inventory data are combined to identify an item located on an inventory route and having a higher inventory frequency than the average as a key item, the key item obtains a higher weight, and the above linear formula (1) is adjusted according to the following nonlinear formula (2):

[0016] W = α*F p + β*I q (2)

[0017] Wherein, p and q are both indexes, used to adjust the degree of nonlinear influence of the inventory frequency and the importance of the item on the weight.

[0018] Further, in the S3, when the calculated weight exceeds a preset threshold, a new camera is determined to be deployed.

[0019] Further, the S4 further comprises:

[0020] S41, according to the position attribute and the weight information of the item, a target item needing to be displayed in the monitoring video is determined, and the obtained physical coordinates are converted and mapped to visual coordinates recognized by the camera according to the position coordinates of the target item in the monitoring video;

[0021] S42, after determining that various target items needing to be inventoried are displayed at the monitoring end, whether the visual coordinates of the target items are within the display range of the current video channel, and whether the display size and display clarity meet the requirements are judged according to the PTZ value and the field of view angle of the current camera;

[0022] S43, according to the judgment result, the camera of the surrounding environment is installed or supplemented, and the installation and configuration position and the visual angle of the new camera are confirmed, a new monitoring channel is built, the camera is selected and supplemented, and the PTZ value and the field of view angle of the supplemented camera cover a plurality of target items with high weight;

[0023] S44, the RFID electronic tag of the asset to be managed is scanned and acquired, and the platform system is triggered to collect and acquire the video image of the asset through the monitoring camera, and if the appropriate video cannot be collected, the 5G camera supplement operation needs to be performed;

[0024] S45, adopt 5G camera to realize supplementing point according to position information at any time and anywhere, the monitoring video content after supplementing point is analyzed by AI, the target object is obtained, whether in the monitoring video is reasonably displayed to verify the rationality of supplementing point, and the target object is analyzed and associatedly stored by AI.

[0025] Further, in the S4, the distance between the camera and the article is calculated according to the following formula (3):

[0026] (3)

[0027] Wherein, d is the distance between the article and the camera within the effective monitoring distance range of the camera, x / y / z is the three-dimensional coordinates of the article and the existing camera.

[0028] The camera supplementing point cloud storage data system based on RFID article inventory is suitable for the camera supplementing point cloud storage data method based on RFID article inventory, comprising:

[0029] The RFID data acquisition module is used for scanning articles and judging whether supplementing point is needed according to inventory route data and inventory frequency data.

[0030] The video acquisition module is used for adjusting the number of newly added supplementing points and the position and angle of view of supplementing points according to the judgment result of the RFID data acquisition module.

[0031] The AI article identification module is used for identifying the articles scanned by the RFID data acquisition module and the monitoring content of the video acquisition module, and uniformly processing, analyzing and storing the multi-modal data of the articles.

[0032] The video system platform is used for receiving and displaying the video pictures output by the AI article identification module.

[0033] The beneficial effects of the present application are as follows:

[0034] 1. The present application is a camera supplementing point cloud storage data method and system based on RFID article inventory, which is used to solve the problems of unknown quantity, resource waste and complex data processing during asset inventory in factories, logistics companies and the like, and is helpful for comprehensive collection and unified processing of inventory article information, positioning of the specific position of the inventory articles, and realization of multi-modal storage from data collection to the cloud. Through this multi-modal cloud intelligent management, efficient management and real-time control of a large number of inventory articles can be realized, thereby improving the intelligent level of Internet of Things application.

[0035] 2、The management method of the application can increase new video collection points (5G cameras) in real time through 5G network connection, can temporarily change and add or delete monitoring videos according to the importance of RFID inventory checking objects and the liquidity of the objects, and greatly improves the efficiency and flexibility of various object management through cloudization, modularization, intelligentization and dynamicization, and provides stronger function expansion and remote management capability for inventory management, so that object checking, inventory supervision are more intelligent, flexible and efficient, and are suitable for comprehensive inventory checking systems of Internet of Things, and have wide application scenarios and adaptability in industrial, community and commercial building object checking. BRIEF DESCRIPTION OF DRAWINGS

[0036] The accompanying drawings, which are incorporated herein and form a part of the specification, illustrate the embodiments of the present application and, together with the description, further serve to explain the principles of the present application and to enable this present application to be put into practice.

[0037] Figure 1 is a camera point supplement cloud storage data method flowchart based on RFID object checking of an embodiment of the application.

[0038] Figure 2 is a camera point supplement cloud storage data system overall block diagram based on RFID object checking of an embodiment of the application.

[0039] Figure 3 is a structural block diagram of a computer device of an embodiment of the application. DETAILED DESCRIPTION

[0040] The technical solutions in the embodiments of the application will be described clearly and completely below with reference to the drawings in the embodiments of the application. Obviously, the described embodiments are only part of the embodiments of the application, rather than all the embodiments. The embodiments in the present application and the features in the embodiments can be combined with each other without conflict. Based on the embodiments in the present application, all other embodiments obtained by those skilled in the art without creative labor are within the scope of protection of the present application.

[0041] It should be noted that, in addition, the meaning of "and / or" appearing throughout the text includes three parallel solutions. Taking "A and / or B" as an example, it includes A solution, or B solution, or A and B solutions. In addition, "multiple" means more than two.

[0042] Reference Figure 1 The embodiment of the application provides a camera point supplement cloud storage data method based on RFID object checking, which comprises the following steps:

[0043] S1, historical checking data of a checking robot is obtained by analysis, wherein the historical checking data comprises historical route data and historical access data;

[0044] S2, determining the weight of each item based on the historical inventory data;

[0045] S3, determining whether a camera needs to be arranged for supplementing inventory based on the weight of each item;

[0046] S4, determining whether the supplementing inventory and the position and angle of view of the supplementing inventory need to be adjusted based on the monitoring content of the camera.

[0047] The method can increase new video collection points (5G cameras) in real time through 5G network connection, temporarily change, add or delete monitoring videos according to the importance and flow of the RFID inventory, and greatly improve the efficiency and flexibility of the management of various items by gradually optimizing the supplementing inventory, monitoring the supplementing inventory in batches, and automatically monitoring the supplementing inventory, thereby providing stronger function expansion and remote management capability for inventory management, and making the inventory and inventory supervision more intelligent, flexible and efficient.

[0048] In the S1, the historical route data is the moving path of the inventory robot in the warehouse tracked by a sensor or GPS, and the walking route recorded at each inventory, and the historical access data is the identification of which areas are frequently accessed according to the historical route data, and the inventory frequency of each item in the area.

[0049] The area with high access frequency generally stores high-value or high-flow items, and recording the inventory times of each item can reflect the importance of the item, and recording the flow of the item can combine the inventory frequency, item importance and item flow to assign a weight value to the image of each item.

[0050] In the S2, for any one item, the weight of the item is mainly composed of the weighted sum of the three indexes of inventory frequency, item importance and item flow:

[0051] W1=b+γ*P+α*F+β*I (1)

[0052] Wherein, W1 is the weight value, P is the inventory frequency, F is the item flow frequency, I is the item importance, γ, α and β are weight vectors, and b is a bias value set by the system.

[0053] In the above embodiment, the inventory route data and the inventory frequency data in the historical inventory data are combined to identify the key items located on the inventory route and having a higher inventory frequency than the average, the key items obtain a higher weight, and the above linear formula (1) is adjusted according to the following nonlinear formula (2):

[0054] W=α*F p+ β * I q (2)

[0055] Wherein, p and q are both indexes, used to adjust the degree of non-linear influence of inventory frequency and item importance on weight.

[0056] In the embodiment, in S3, when the calculated weight exceeds a preset threshold, it is determined to deploy a new camera.

[0057] In the embodiment, S4 further comprises:

[0058] S41, according to the location attribute of the item and the weight information, determining the target item that needs to be displayed in the monitoring video, and converting and mapping the obtained physical coordinates into visual coordinates recognized by the camera according to the location coordinates of the target item in the monitoring video;

[0059] S42, after determining that the target items need to be inventoried and displayed in the monitoring terminal, judging whether the visual coordinates of the target items are within the display range of the current video channel, and whether the display size and display clarity meet the requirements according to the PTZ value and the field of view angle of the current camera;

[0060] S43, according to the judgment result, installing or supplementing the camera in the surrounding environment, and confirming the installation and configuration position and the visual angle of the new camera, building a new monitoring channel, selecting and supplementing the camera, and the PTZ value and the field of view angle of the supplemented camera covering multiple target items with high weight;

[0061] S44, scanning and acquiring the RFID electronic tag of the asset to be managed, and triggering the platform system to collect and acquire the video image of the asset through the monitoring camera, if the appropriate video cannot be collected, 5G camera supplementing operation is needed;

[0062] S45, using the 5G camera to supplement at any time and anywhere according to the location information, the monitoring video content after supplementing is analyzed by AI to obtain the target item, and the rationality of supplementing is verified by whether the target item is reasonably displayed in the monitoring video, and the target item is analyzed and stored by AI.

[0063] In the above embodiment, the distance between the camera and the item is calculated according to the following formula (3):

[0064] (3)

[0065] Wherein, d is the distance between the item and the camera within the effective monitoring distance range of the camera, and x / y / z is the three-dimensional coordinates of the item and the existing camera.

[0066] Referring to Figure 2The embodiment of the present application also provides a camera supplementing point cloud storage data system based on RFID article inventory, which is suitable for the camera supplementing point cloud storage data method based on RFID article inventory and comprises:

[0067] An RFID data acquisition module is used for scanning articles and judging whether supplementing points are needed according to inventory route data and inventory frequency data;

[0068] A video acquisition module is used for adjusting the number of newly added supplementing points and the positions and angles of view of the supplementing points according to the judgment result of the RFID data acquisition module;

[0069] An AI article identification module is used for identifying the articles scanned by the RFID data acquisition module and the monitoring content of the video acquisition module and performing unified processing, analysis and storage on the multi-modal data of the articles;

[0070] A video system platform is used for receiving and displaying the video pictures output by the AI article identification module.

[0071] The system monitors the scene in the warehouse through the inventory distribution camera of RFID, the inventory time and the position information of the articles, and the linkage of RFID and video monitoring, and performs multi-information and omnidirectional supervision on the assets in real time, so that the whole management process is more intelligent. The AI article identification module analyzes the characteristics of the articles, labels the articles in the video, and stores the multi-modal information such as positioning information, label information and scanning time in the cloud.

[0072] Specifically, the system determines the installation and configuration positions and angles of view of the new cameras according to the RFID requirements, builds a new monitoring channel, selects the cameras and supplements the points, covers the monitoring targets by the PTZ values and the angles of view of the supplementing points, supplements the points by the 5G cameras at any time and anywhere according to the position information, analyzes the video content by the AI analysis module after supplementing the points, performs AI analysis and associated storage on the video objects, realizes the unified processing, storage and analysis of the multi-modal data such as the article names, inventory time, position information and video by real-time monitoring during the inventory of the articles, intelligently analyzes the shapes of the articles, and the whole system operation involves the data acquisition of the equipment, intelligent processing and cloud storage. Through this cloud intelligent management, the efficient management and real-time control of the warehouse materials can be realized, so that the intelligent level of the Internet of Things application is improved, and more accurate decision support is provided.

[0073] The embodiment of the present application also provides a computer readable storage medium which stores a computer program, and the computer program is executed by a processor to make the processor execute the steps of the camera supplementing point cloud storage data method based on RFID article inventory.

[0074] Referring to Figure 3 The embodiment of the present application also provides a computer device, comprising a memory and a processor, the memory stores a computer program, and the computer program is executed by the processor to make the processor execute the steps of the above method.

[0075] The embodiment of the present application also provides a computer program product comprising instructions which, when executed on a computer, cause the computer to carry out the steps of the above method for storing data of a camera point cloud based on RFID inventory.

[0076] It can be understood that the system, device and storage medium provided by the embodiment of the present application correspond to the method provided by the embodiment of the present application, and the explanation, examples and beneficial effects of the related content can refer to the corresponding part in the above method for storing data of a camera point cloud based on RFID inventory.

[0077] It should be noted that all or part of the steps in the embodiments of the present application can be implemented by software, hardware, firmware or any combination thereof. When implemented by hardware, all or part of the steps can be implemented in the form of a purchased standard component or a custom component. When implemented by software, all or part of the steps can be implemented in the form of a computer program product. The computer program product includes one or more computer instructions. When the computer program instructions are loaded and executed on a computer, all or part of the processes or functions described in the embodiments of the present application are generated. The computer can be a general-purpose computer, a special-purpose computer, a computer network or other programmable device. The computer instructions can be stored in a computer readable storage medium or transmitted from one computer readable storage medium to another computer readable storage medium, for example, the computer instructions can be transmitted from one website, computer, server or data center to another website, computer, server or data center through wired (such as coaxial cable, optical fiber, digital subscriber line (DSL)) or wireless (such as infrared, wireless, microwave, etc.) mode. The computer readable storage medium can be any available medium that can be accessed by a computer or a data storage device such as a server, data center, etc. integrated with one or more available media. The available media can be magnetic media (such as floppy disk, hard disk, magnetic tape), optical media (such as DVD), or semiconductor media (such as solid state disk (SSD)) and the like.

[0078] In summary, in order to find out the asset position and video viewing state, the application provides an AI supplement method, which can track and view the video of the goods through the supplement camera, remotely and real-timely view the state and position of the asset inventory, realize the inventory monitoring and viewing of the goods, and supplement the monitoring points through step-by-step optimization, batch monitoring and automatic monitoring. The application not only saves the labor cost investment of on-site measurement and wiring, but also realizes real-time remote monitoring of the inventory process, realizes scanning process supervision and cloud storage real-time evidence storage, improves the intelligence, flexibility and efficiency of asset supervision, and solves the problems of unknown quantity, resource waste and complex data processing in the traditional asset inventory of factories and logistics companies.

[0079] It should be understood that the examples and embodiments described herein are only for illustration and are not intended to limit the application, and those skilled in the art can make various modifications or changes based on it, any modifications, equivalent replacements, improvements, etc. made within the spirit and principles of the application shall be included in the protection scope of the application.

Claims

1. A method for camera fill-in cloud data based on RFID item inventory, characterized in that, The method comprises the following steps: S1, analyzing and obtaining historical inventory data of the inventory robot, the historical inventory data comprising historical route data and historical access data; S2, determining the weight of each item based on the historical inventory data; S3, judging whether a camera needs to be arranged for supplementing inventory based on the weight of each item; S4, judging whether the supplementing inventory and the position and angle of view of the supplementing inventory need to be adjusted based on the monitoring content of the camera; The S4 further comprises: S41, determining target items that need to be displayed in the monitoring video according to the position attribute and weight information of the items, and converting and mapping the obtained physical coordinates into visual coordinates recognized by the camera according to the position coordinates of the target items in the monitoring video; S42, after determining that various target items need to be inventoried and displayed at the monitoring end, judging whether the visual coordinates of the target items are within the display range of the current video channel, and whether the display size and display clarity meet the requirements according to the current camera PTZ value and field of view angle; S43, according to the judgment result, installing or supplementing the camera in the surrounding environment, confirming the installation and configuration position and angle of view of the new camera, building a new monitoring channel, selecting and supplementing the camera, and covering the PTZ value and field of view angle of the supplementing camera with multiple target items with high weight; S44, scanning and obtaining the RFID electronic tag of the asset to be managed, and triggering the platform system to collect and obtain the video image of the asset through the monitoring camera. If appropriate video cannot be collected, 5G camera supplementing operation is needed; S45, using the 5G camera to supplement at any time and anywhere according to the position information, AI analyzing the monitoring video content after supplementing, obtaining the target items, verifying the rationality of the supplementing by whether the target items are reasonably displayed in the monitoring video, and AI analyzing and associatively storing the target items.

2. The RFID-based item inventory camera fill-in cloud data method of claim 1, wherein, In the S1, the historical route data is the moving path of the inventory robot in the warehouse tracked by a sensor or GPS, and the walking route recorded at each inventory time. The historical access data is which areas are frequently accessed and the inventory frequency of each item in the area according to the historical route data.

3. The RFID-based item inventory camera fill-in cloud data method of claim 1, wherein, In the S2, for any one item, the weight of the item is mainly composed of the weighted sum of three indexes of inventory frequency, item importance and item liquidity: W1=b+γ*P+α*F+β*I (1) Wherein, W1 is the weight value, P is the inventory frequency, F is the item flow frequency, I is the item importance, γ, α and β are weight vectors, and b is a bias value set by the system.

4. The RFID-based item inventory camera fill-in cloud data method of claim 3, wherein, In the S2, in combination with the inventory route data and inventory frequency data in the historical inventory data, the items located on the inventory route and with an inventory frequency higher than the average are identified as key items, the key items obtain higher weights, and the above linear formula (1) is adjusted according to the following nonlinear formula (2): W = a * F p + β * I q (2) Wherein, p and q are both indexes for adjusting the nonlinear influence degree of the inventory frequency and the item importance on the weight.

5. The RFID-based item inventory camera fill-in cloud data method of claim 1, wherein, In the S3, when the calculated weight exceeds a preset threshold, a new camera is determined to be deployed.

6. The RFID-based item inventory camera fill-in cloud data method of claim 1, wherein, In the S4, the distance between the camera and the article is calculated according to the following formula (3): （3） Wherein, d is the distance between the article and the camera within the effective monitoring distance range of the camera, x / y / z is the three-dimensional coordinates of the article and the existing camera.

7. A camera fill-in cloud data storage system for RFID item inventory based camera fill-in cloud data storage method as claimed in any one of claims 1 to 6, wherein, Comprise: An RFID data acquisition module, the RFID data acquisition module is used for scanning article, and according to the inventory route data and inventory frequency data, it is judged whether it needs to be supplemented; Video acquisition module, the video acquisition module is used for according to the judgment result of the RFID data acquisition module, adjust the number of newly added supplement and the position and visual angle of supplementing; AI article identification module, the AI article identification module is used for identifying the article scanned by the RFID data acquisition module and the monitoring content of the video acquisition module, and the multi-modal data of the article is uniformly processed, analyzed and stored; Video system platform, the video system platform is used for receiving and displaying the video picture output by the AI article identification module.

Images