Item location method based on identification code and related device

Abstract

The application provides an object positioning method based on an identification code and related devices. An object is provided with an identification code, which includes a positioning code and a content code. The object positioning method based on the identification code includes: identifying the positioning code and the content code in a first image, the first image being obtained by an image acquisition device shooting the identification code on the object; in response to a failed identification of the positioning code and a successful identification of the content code, determining a rough pose of the object based on the identification result of the content code; adjusting the pose of the image acquisition device according to the rough pose to obtain a second image, the second image being obtained by the adjusted image acquisition device shooting the identification code on the object; and in response to a successful identification of the positioning code in the second image, determining an accurate pose of the object based on the identification result of the positioning code. The application can improve the accuracy of the pose determination of the object.

Description

Technical Field

[0001] This application relates to the field of item positioning technology, and in particular to item positioning methods and related devices based on identification codes. Background Technology

[0002] Item location technology is profoundly changing our lives by giving items "location awareness." It is widely used in many fields, including logistics and supply chain management.

[0003] During the long-term research and development process, the inventors of this application discovered that current methods for locating objects still have certain limitations, which also affect the accuracy of object location to some extent. Summary of the Invention

[0004] This application provides a method and related apparatus for locating items based on identification codes, so as to improve the accuracy of item location determination.

[0005] To address the aforementioned objectives, this application provides a method for locating an item based on an identification code. The item is provided with the identification code, which includes a location code and a content code. The method for locating an item based on the identification code includes: The location code and the content code in the first image are identified. The first image is obtained by taking a picture of the identification code on the item using an image acquisition device. In response to the failure of the location code recognition and the success of the content code recognition, the approximate pose of the item is determined based on the recognition result of the content code; The pose of the image acquisition device is adjusted according to the rough pose to obtain a second image, which is obtained by the adjusted image acquisition device capturing the identification code on the item. In response to the successful recognition of the positioning code in the second image, the precise pose of the item is determined based on the recognition result of the positioning code.

[0006] To address the aforementioned problems, this application provides an electronic device, which includes a processor; the processor is used to execute instructions to implement the steps of the above-described method.

[0007] To address the aforementioned problems, this application provides a computer storage medium storing instruction / program data, which, when executed, implements the steps of the method described above.

[0008] The method of this application is as follows: First, the positioning code and content code in the first image are identified; then, in response to the failure of positioning code recognition and the success of content code recognition, a coarse pose of the item is determined based on the recognition result of the content code; next, the pose of the image acquisition device is adjusted according to the coarse pose so that the image acquisition device is suitable for capturing the positioning code and content code under the relatively adjusted pose of the item / content code, and a second image captured by the image acquisition device of the identification code can be obtained, thus improving the image quality of the positioning code and content code in the second image; then, in response to the successful recognition of the positioning code in the second image, the precise pose of the item is determined based on the recognition result of the positioning code. This can improve the success rate of positioning code recognition and the accuracy of the positioning code's position information by utilizing the high-quality second image of the identification code, thereby improving the accuracy of the item's pose determination. Attached Figure Description

[0009] To more clearly illustrate the technical solutions in the embodiments of this application, the accompanying drawings that can be used in the description of the embodiments will be briefly introduced below. Obviously, the accompanying drawings described below are only some embodiments of this application. For those skilled in the art, other drawings can be obtained based on these drawings without creative effort.

[0010] Figure 1 This is a flowchart illustrating an implementation method of the item location method based on identification codes in this application; Figure 2 This is a schematic diagram of the identification code in the item location method based on the identification code of this application; Figure 3 This is a flowchart illustrating an implementation method of the item location method based on identification codes in this application; Figure 4 This is a flowchart illustrating an implementation method of the item location method based on identification codes in this application; Figure 5 This is a schematic diagram of the structure of one embodiment of the electronic device of this application; Figure 6 This is a schematic diagram of one embodiment of the computer storage medium of this application. Detailed Implementation

[0011] To enable those skilled in the art to better understand the technical solution of this application, the item positioning method and related apparatus based on identification codes provided in this application will be further described in detail below with reference to the accompanying drawings and specific embodiments.

[0012] The terms "first," "second," and "third" used in this application are for descriptive purposes only and should not be construed as indicating or implying relative importance or implicitly specifying the number of technical features indicated. Therefore, a feature defined as "first," "second," or "third" may explicitly or implicitly include at least one of that feature. In the description of this application, "multiple" means at least two, such as two, three, etc., unless otherwise explicitly specified.

[0013] In this document, the term "implementation" means that a specific feature, structure, or characteristic described in connection with an implementation may be included in at least one implementation of this application. The appearance of this phrase in various places in the specification does not necessarily refer to the same implementation, nor is it a separate or alternative implementation mutually exclusive with other implementations. It will be explicitly and implicitly understood by those skilled in the art that, without conflict, the implementations described herein may be combined with other implementations.

[0014] like Figure 1 As shown, Figure 1 This is a flowchart illustrating one embodiment of the item location method based on identification codes according to this application. The item in this application is equipped with an identification code, which includes a location code and a content code. The entity executing the item location method of this application is not limited; for example, it can be an image acquisition device, or a main device that installs the aforementioned image acquisition device. Specific examples of the main device could be a CTU (Cargo Transport Unit), or a server. The item location method based on identification codes of this application may include the following steps.

[0015] S11: Identify the location code and content code in the first image.

[0016] The location code and content code in the first image can be identified first, so that the item can be located based on the identification results of the location code and content code in the first image. The first image is obtained by the image acquisition device taking a picture of the identification code on the item.

[0017] Specifically, the location code in the first image can be identified to determine its position information. The position information of the location code can be its pose relative to the image acquisition device.

[0018] In the process of recognizing the positioning code, the corner coordinates of the positioning code can be determined by detecting the positioning code in the first image. Then, the pose of the positioning code relative to the image acquisition device can be calculated by using the corner coordinates of the positioning code, the size information of the positioning code, and the intrinsic parameters of the image acquisition device.

[0019] In one implementation, only one location code can be set on the item.

[0020] In another implementation, at least two location codes can be set on the item, replacing a single location code. This increases the redundancy of the location code recognition and avoids the situation where a single location code cannot be recognized due to dirt or glare. Furthermore, by recognizing at least two location codes, the location information of each code can be obtained, allowing for a more precise determination of the item's location.

[0021] Alternatively, this application may use an ArUco code or a QR code, etc., without any particular restriction.

[0022] Preferably, the positioning code is square in shape. Of course, in other embodiments, the positioning code can also be other shapes such as triangle.

[0023] The content code in the first image can be identified to determine the location information and / or recording information of the content code.

[0024] The content code can record relevant information about the item; for example, when the item is a material bin or other goods, the content code on the item can record information about the items inside the goods and the goods' transit information; or, when the item is a storage location, the content code on the item can record the storage records of the goods in the storage location. For example, the information recorded in the content code may include basic identification information of the item, production and supply chain information, network and digital resources, and / or internal management and anti-counterfeiting information.

[0025] The process of identifying the content code to determine its recorded information may include: preprocessing the image to improve its quality, where preprocessing methods may include operations such as grayscale conversion, binarization, and / or filtering; detecting and parsing the content code, for example, using a dedicated library to check the code's position and decode its data, and further processing the acquired decoded data to obtain the recorded information.

[0026] Similar to location codes, the location information of content codes can be the pose of the content code on an item relative to the image acquisition device.

[0027] In the process of recognizing the content code, the corner coordinates of the content code can be determined by detecting the content code in the first image. Then, the pose of the content code relative to the image acquisition device can be calculated by using the corner coordinates of the content code, the size information of the content code, and the intrinsic parameters of the image acquisition device.

[0028] The content code can be a matrix QR code or a stacked / row-column QR code, etc., without any particular restriction. For example, the content code can be a Data Matrix code. Another example is an Aztec code.

[0029] Preferably, the content code is square in shape. Of course, in other embodiments, the content code can also be other shapes such as triangles.

[0030] In a scenario, such as Figure 2 As shown, two location codes and one content code are set on the item. To improve the accuracy of item positioning, the center of the two location codes can be the same as the center of the content code. Specifically, the content code can be placed between the two location codes. Alternatively, the two location codes and the content code can be placed adjacent to each other.

[0031] For the content code, the content code can be directly identified during the code recognition process in step S11 to determine the location information and recording information of the content code.

[0032] In other embodiments, the content code can also be identified during the code identification process in step S11, determining only the recording information of the content code. In this embodiment, if the location information of the location code is not obtained by identifying the location code, the content code can be identified again to determine the location information of the content code.

[0033] Optionally, the location code and content code can be identified separately using two threads. Alternatively, the location code and content code can be identified sequentially using only a single thread.

[0034] S12: In response to the failure of the positioning code recognition and the success of the content code recognition, determine the approximate pose of the item based on the recognition result of the content code.

[0035] After recognizing the location code and content code in the first image, the item can be located based on the recognition results. Specifically, if the location code recognition fails but the content code recognition succeeds, the item's approximate pose can be determined based on the content code recognition result. This allows the image acquisition device to be adjusted based on the approximate pose to re-acquire a better image, which can then be used to determine a more accurate pose of the item.

[0036] In this context, "location code recognition failure" means that the location information of the location code was not identified and analyzed. "Content code recognition success" means that the location information and record information of the content code were successfully identified and analyzed.

[0037] The coarse pose of an object can be its pose relative to the image acquisition device. Alternatively, in one application scenario, the image acquisition device is mounted on an actuator, and the coarse pose of the object is its pose relative to the actuator. Or, the coarse pose of the object can be its pose in the real world. Or, the coarse pose of the object can be the pose of the content code relative to the image acquisition device; that is, the position information of the content code can be directly used as the coarse pose of the object. Or, the coarse pose of the object can be the pose of the content code relative to the actuator.

[0038] If the coarse pose of the object is the pose of the object relative to the actuator, determining the coarse pose of the object based on the recognition result of the content code may include: using the pasting position of the content code on the object and the extrinsic parameters of the image acquisition device on the actuator to convert the position information of the content code in order to calculate the coarse pose of the object.

[0039] The formula for calculating the coarse pose of an object can be: ; in, It is the approximate position of the object; These are the extrinsic parameters of the image acquisition device in its execution structure; It is the location where the content code is pasted on the item; It is the location information of the content code.

[0040] If the coarse pose of an object is the pose of the object relative to the image acquisition device, determining the coarse pose of the object based on the recognition result of the content code may include: using the position of the content code pasted on the object to convert the position information of the content code in order to calculate the coarse pose of the object.

[0041] The formula for calculating the coarse pose of an object can be: ; in, It is the approximate position of the object; It is the location where the content code is pasted on the item; It is the location information of the content code.

[0042] If the coarse pose of an object can be the object's pose in the real world, determining the coarse pose of an object based on the recognition result of the content code can include: using the pasting position of the content code on the object and the pose of the image acquisition device in the real world to convert the position information of the content code in order to calculate the coarse pose of the object.

[0043] If the coarse pose of an object can be the pose of the content code relative to the actuator, determining the coarse pose of the object based on the recognition result of the content code can include: using the extrinsic parameters of the image acquisition device on the actuator to convert the position information of the content code in order to calculate the coarse pose of the object.

[0044] S13: Adjust the pose of the image acquisition device according to the rough pose to obtain a second image.

[0045] After determining the approximate pose of the item based on the content code recognition result, the pose of the image acquisition device can be adjusted according to the approximate pose to obtain a second image. The second image is obtained by taking a picture of the identification code on the item with the adjusted image acquisition device, so that more accurate location information of the item can be obtained based on the second image.

[0046] Specifically, the pose of the image acquisition device can be adjusted based on a rough pose so that the adjusted pose of the image acquisition device relative to the item / content code is suitable for capturing the positioning code and content code.

[0047] In one implementation, the coarse pose of the item is the pose of the content code relative to the image acquisition device. A first preset pose can be set. The first preset pose can be the pose of the content code relative to the image acquisition device when the image acquisition device is suitable for capturing the positioning code and the content code. The first preset pose can be determined by comparing the quality of positioning codes and content codes captured by multiple image acquisition devices, or it can be determined by other methods. Then, the adjusted pose of the image acquisition device can be calculated from the first preset pose and the coarse pose, so that the pose of the content code relative to the adjusted image acquisition device is the first preset pose.

[0048] In another implementation, the coarse pose of the item can be the pose of the content code relative to the actuator. A second preset pose can be set, which can be the pose of the content code relative to the actuator when the image acquisition device is suitable for capturing the positioning code and the content code. The second preset pose can be determined by comparing the quality of the positioning code and the content code captured by the image acquisition device at multiple actuator positions, or it can be determined by other methods. Then, the adjustment pose of the actuator can be calculated using the second preset pose and the coarse pose, so that the pose of the content code relative to the adjusted actuator is the second preset pose.

[0049] In another implementation, the coarse pose of the object can be the pose of the object relative to the image acquisition device. A third preset pose can be set, which can be the pose of the object relative to the image acquisition device when the image acquisition device is suitable for capturing the positioning code and content code. The third preset pose can be determined by comparing the quality of the positioning code and content code captured by multiple image acquisition devices, or it can be determined by other methods. Then, the adjusted pose of the image acquisition device can be calculated using the third preset pose and the coarse pose, so that the pose of the object relative to the adjusted image acquisition device is the third preset pose.

[0050] In another implementation, the coarse pose of the object can be the pose of the object relative to the actuator. A fourth preset pose can be set. The fourth preset pose can be the pose of the object relative to the actuator when the image acquisition device is suitable for capturing the positioning code and content code. The fourth preset pose can be determined by comparing the quality of the positioning code and content code captured by the image acquisition device at multiple actuator positions. Of course, the fourth preset pose can also be determined by other methods. Then, the adjusted pose of the actuator can be calculated by the fourth preset pose and the coarse pose, so that the pose of the object relative to the adjusted actuator is the fourth preset pose.

[0051] In another implementation, the coarse pose of the object can be its pose in the real world. A first preset pose can be set, which can be the pose of the content code relative to the image acquisition device when the image acquisition device is suitable for capturing the positioning code and the content code. The first preset pose can be determined by comparing the quality of positioning codes and content codes captured by multiple image acquisition devices, or it can be determined by other methods. Then, the adjusted pose of the image acquisition device can be calculated using the first preset pose, the coarse pose, and the pose of the image acquisition device in the real world, so that the pose of the content code relative to the adjusted image acquisition device is the first preset pose.

[0052] S14: In response to successful recognition of the positioning code in the second image, the precise pose of the item is determined based on the recognition result of the positioning code.

[0053] After adjusting the pose of the image acquisition device based on the coarse pose to obtain the second image, the precise pose of the object can be determined based on the recognition result of the positioning code in the second image, so as to obtain more accurate location information of the object based on the second image.

[0054] Successful identification of the location code means that the location information of the location code has been identified and analyzed.

[0055] The precise pose of an object can be its pose relative to the image acquisition device. In one application scenario, the image acquisition device is mounted on an actuator, and the precise pose of the object is its pose relative to the actuator. Alternatively, the precise pose of the object can be its pose in the real world.

[0056] If the precise pose of an object is the pose of the object relative to the actuator, determining the precise pose of the object based on the recognition result of the positioning code can include: using the position of the positioning code on the object and the external parameters of the image acquisition device on the actuator to convert the position information of the positioning code in order to calculate the precise pose of the object.

[0057] The formula for calculating the precise pose of an object can be: ; in, It is the precise pose of the object; These are the extrinsic parameters of the image acquisition device in its execution structure; It refers to the location where the positioning code is affixed to the item; It is the location information of the positioning code.

[0058] If the precise pose of an object is the pose of the object relative to the image acquisition device, determining the precise pose of the object based on the recognition result of the positioning code can include: using the position of the positioning code on the object to convert the position information of the positioning code in order to calculate the precise pose of the object.

[0059] The formula for calculating the precise pose of an object can be: ; in, It is the precise pose of the object; It refers to the location where the positioning code is affixed to the item; It is the location information of the positioning code.

[0060] If the precise pose of an object can be its pose in the real world, determining the precise pose of an object based on the recognition result of the positioning code can include: using the position of the positioning code pasted on the object and the current pose of the image acquisition device in the real world to convert the position information of the positioning code in order to calculate the precise pose of the object.

[0061] In this implementation, the location code and content code in the first image are first identified. Then, in response to the failure of location code recognition and the success of content code recognition, a coarse pose of the item is determined based on the content code recognition result. Next, the pose of the image acquisition device is adjusted according to the coarse pose so that the image acquisition device is suitable for capturing the location code and content code under the adjusted pose of the item / content code, and a second image of the identification code captured by the adjusted image acquisition device can be obtained. This improves the image quality of the location code and content code in the second image. Then, in response to the successful recognition of the location code in the second image, the precise pose of the item is determined based on the location code recognition result. This improves the success rate of location code recognition and the accuracy of the location code's position information by utilizing the high-quality second image of the identification code, thereby improving the accuracy of the item's pose determination.

[0062] Furthermore, this application also provides a second embodiment of an item location method based on an identification code, such as... Figure 3 and Figure 4 As shown, the item location method based on identification code in this embodiment may include the following steps: S201: Identify the location code and content code in the first image.

[0063] Please refer to step S11 for the specific details of the steps; no restrictions will be imposed here.

[0064] After recognizing the location code and content code in the first image, several situations may occur.

[0065] The first scenario is that the location code in the first image is successfully recognized. In this case, step S206 can be initiated to determine the precise pose of the item based on the recognition result of the location code in the first image.

[0066] Based on the two recognition scenarios of the content code, the first scenario has two sub-scenarios. The first sub-scenarios is that both the location code and the content code in the first image are successfully recognized. In this sub-scenarios, the precise pose of the item is determined based on the recognition result of the location code in the first image, and the information of the item is determined based on the content code in the first image.

[0067] The second sub-case is that the location code in the first image is successfully recognized, but the content code is not recognized. In this sub-case, the precise pose of the item is determined based on the recognition result of the location code in the first image, and the error of the content code recognition failure is reported.

[0068] The second scenario is that both the location code and the content code in the first image fail to be recognized. In this case, you can proceed to step S207, report the error that both the location code and the content code failed to be recognized, and end the item location process.

[0069] The third scenario is that the location code in the first image fails to be recognized, but the content code is recognized successfully. In this case, we can proceed to step S202 to determine the approximate pose of the item based on the recognition result of the content code.

[0070] The above content code recognition failure means that the record information of the content code was not successfully analyzed.

[0071] S202: Determine the approximate pose of the item based on the recognition result of the content code.

[0072] Please refer to step S12 for the specific details of the steps; no restrictions will be imposed here.

[0073] S203: Adjust the pose of the image acquisition device according to the rough pose to obtain a second image, and add the first value to the number of recognition adjustments.

[0074] The details of the pose adjustment of the image acquisition device can be referred to in step S13, and there are no restrictions here.

[0075] After adjusting the image acquisition device, the number of recognition adjustments can be increased by a first value to determine if the number of attempts has exceeded the limit. If the number of attempts exceeds the limit (i.e., the number of recognition adjustments is greater than a second value), proceed to step S207 to end the item positioning process. If the number of attempts does not exceed the limit (i.e., the number of recognition adjustments is less than or equal to the second value), proceed to step S204 to identify the positioning code and content code in the second image. The initial number of recognition adjustments can be a fixed value such as 0 or 1, without restriction. The first and second values ​​can be set according to actual conditions, without restriction. For example, the first value can be set to a non-zero positive number such as 1 or 2, and the second value can be set to a value greater than the first value, such as 3.

[0076] S204: Identify the location code and content code in the second image.

[0077] For specific details on the identification of the location code and content code, please refer to step S11, which is not limited here.

[0078] After recognizing the location code and content code in the second image, several situations may occur.

[0079] The first scenario is that the location code in the second image is successfully recognized. In this case, we can proceed to step S206 to determine the precise pose of the item based on the recognition result of the location code in the second image.

[0080] Based on the two recognition scenarios of the content code, the first scenario has two sub-scenarios. The first sub-scenarios is that both the location code and the content code in the second image are successfully recognized. In this sub-scenarios, the precise pose of the item is determined based on the recognition result of the location code in the second image, and the information of the item is determined based on the content code in the second image.

[0081] The second sub-case is that the location code in the second image is successfully recognized, but the content code is not recognized. In this sub-case, the precise pose of the item is determined based on the recognition result of the location code in the second image, and the error of the content code recognition failure is reported.

[0082] The second scenario is that both the location code and the content code in the second image fail to be recognized. In this case, you can proceed to step S207, report the error that both the location code and the content code failed to be recognized, and end the item location process.

[0083] The third scenario is that the location code in the second image fails to be recognized, but the content code is recognized successfully. In this case, step S205 can be initiated to re-determine the approximate pose of the item based on the recognition result of the content code in the second image.

[0084] If the content code of the first image is successfully recognized, the information of the item can be determined directly based on the content code recognition result of the first image. That is, the recorded information of the content code of the first image can be directly used as the information of the item, so that the information of the item can be determined without relying on the content code in the second image.

[0085] S205: Based on the recognition result of the content code in the second image, redetermine the coarse pose of the item.

[0086] Please refer to step S12 for the specific details of the steps; no restrictions will be imposed here.

[0087] After redetermining the coarse pose of the item based on the recognition result of the content code in the second image, the process can return to step S203 to perform the step of adjusting the pose of the image acquisition device according to the coarse pose to obtain the second image, and incrementing the recognition adjustment number by one.

[0088] S206: Determine the precise pose of the item based on the identification result of the positioning code.

[0089] Please refer to step S14 for the specific details of the steps; no restrictions are imposed here.

[0090] S207: End the item location process.

[0091] The above-mentioned item positioning method based on identification codes can be applied to goods retrieval and placement scenarios. The item is the goods or the storage location corresponding to the goods. The image acquisition device is installed on the execution mechanism. The precise pose of the item is the pose of the item relative to the execution mechanism. In the goods retrieval and placement scenario, the execution mechanism can move and retrieve goods from the storage location based on the precise pose of the item.

[0092] When the item is the goods, after determining the precise position of the item based on the above-described item positioning method, the actuator can be controlled to pick up the item based on the precise position of the goods.

[0093] When the item is the storage location, after determining the precise position of the item based on the above item positioning method, the actuator can be controlled to place the goods in the storage location or retrieve the goods from the storage location based on the precise position of the storage location.

[0094] In a specific example, the above-mentioned item positioning method based on identification codes is applied to the visual docking method of bins and shelves based on fusion decoding. It is applicable to the picking and placing operations of square material boxes in multi-layer shelf areas, and can be mainly used for the operation process of more vehicle types such as CTU equipment. Its main idea is to integrate ARUCO positioning codes and DATAMATRIX data codes to meet the multiple requirements of high-precision positioning and highly complex data. It can simultaneously realize shelf and bin pose calculation and information decoding, and simultaneously complete the functional requirements of inventory and accurate picking and placing.

[0095] Compared to barcode and ordinary QR code-based bin handling solutions, the technical solution of this application can accurately calculate the relative pose between the actuator and the item, achieving high-precision visual docking with an accuracy of approximately ±4mm and ±0.5°. Furthermore, compared to RFID-based bin handling solutions, this application's technical solution can decode richer inventory information through customized content codes, enabling location maintenance and status updates for multi-level shelving warehouses. This application also designs a fusion visual code and corresponding identification docking scheme, achieving a technical solution that integrates inventory information, positioning information, and shelving & location information, and is compatible with the simultaneous recognition of multiple barcodes in the field of view, improving recognition efficiency. This application can also address the functional requirement of picking up and placing specific bins on designated shelves in bin handling scenarios, decoding the corresponding inventory information and providing it to the robot scheduling system. Additionally, in dense shelving scenarios, the reduced operating space of the gripping mechanism leads to increased execution accuracy requirements; this application provides a high-precision docking and picking identification scheme to ensure accurate recognition feedback when picking up and placing bins and docking with shelves. In addition, this application can also distinguish between bin codes and shelf codes by positioning code values, and realize the simultaneous recognition of multiple fusion codes in the field of view.

[0096] Of course, the item location method based on the identifier code can be applied to scenarios such as real-world item location or environmental mapping.

[0097] Please see Figure 5 , Figure 5 This is a schematic diagram of one embodiment of the electronic device of this application. The electronic device 10 includes a processor 12, which executes instructions to implement the above-described item positioning method based on identification codes. For detailed implementation processes, please refer to the description of the above embodiment; further details will not be repeated here.

[0098] Processor 12 can also be referred to as a CPU (Central Processing Unit). Processor 12 may be an integrated circuit chip with signal processing capabilities. Processor 12 may also be a general-purpose processor, a digital signal processor (DSP), an application-specific integrated circuit (ASIC), a field-programmable gate array (FPGA), or other programmable logic devices, discrete gate or transistor logic devices, or discrete hardware components. A general-purpose processor may be a microprocessor, or processor 12 may be any conventional processor.

[0099] The electronic device 10 may further include a memory 11 for storing instructions and data required for the processor 12 to run.

[0100] The processor 12 is used to execute instructions to implement the method provided by any embodiment and any non-conflicting combination of the item location method based on the identification code of this application.

[0101] Please see Figure 6 , Figure 6 This is a schematic diagram of the structure of a computer-readable storage medium in an embodiment of this application. The computer-readable storage medium 20 in this embodiment stores instruction / program data 21. When executed, this instruction / program data 21 implements the method provided by any embodiment of the item location method based on identification codes and any non-conflicting combination thereof. The instruction / program data 21 can be formed into a program file and stored in the storage medium 20 as a software product, so that a computer device (which may be a personal computer, server, or network device, etc.) or processor can execute all or part of the steps of the methods in various embodiments of this application. The aforementioned storage medium 20 includes various media capable of storing program code, such as a USB flash drive, portable hard drive, read-only memory (ROM), random access memory (RAM), magnetic disk, or optical disk, or terminal devices such as computers, servers, mobile phones, and tablets.

[0102] In the several 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 functional 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, or indirect coupling or communication connection between apparatuses or units, and may be electrical, mechanical, or other forms.

[0103] Furthermore, the functional units in the various 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 functional unit.

[0104] The above are merely embodiments of this application and do not limit the scope of this patent application. Any equivalent structural or procedural changes made using the content of this application's specification and drawings, or direct or indirect applications in other related technical fields, are similarly included within the scope of patent protection of this application.

Claims

1. A method for locating items based on identification codes, characterized in that, The item is provided with the identification code, which includes a location code and a content code; the method includes: The location code and the content code in the first image are identified. The first image is obtained by taking a picture of the identification code on the item using an image acquisition device. In response to the failure of the location code recognition and the success of the content code recognition, the approximate pose of the item is determined based on the recognition result of the content code; The pose of the image acquisition device is adjusted according to the rough pose to obtain a second image, which is obtained by the adjusted image acquisition device capturing the identification code on the item. In response to the successful recognition of the positioning code in the second image, the precise pose of the item is determined based on the recognition result of the positioning code.

2. The item positioning method according to claim 1, characterized in that, The step of adjusting the pose of the image acquisition device according to the coarse pose to obtain a second image includes: The pose of the image acquisition device is adjusted according to the rough pose to obtain a second image, and the number of recognition adjustments is added to a first value; The step of adjusting the pose of the image acquisition device based on the coarse pose to obtain the second image includes: In response to the recognition adjustment number being less than or equal to a second value, the location code and the content code in the second image are recognized; In response to the failure to recognize the positioning code in the second image and the success of the recognition of the content code, the coarse pose of the item is re-determined based on the recognition result of the content code in the second image; Based on the re-determined coarse pose, the process returns to adjusting the pose of the image acquisition device according to the coarse pose to obtain a second image, and increments the recognition adjustment count by one.

3. The item positioning method according to claim 2, characterized in that, The process of identifying the location code and the content code in the second image then includes: In response to the successful recognition of both the location code and the content code in the second image, the precise pose of the item is determined based on the recognition result of the location code in the second image, and the information of the item is determined based on the content code in the second image. In response to the successful recognition of the location code in the second image and the failure to recognize the content code, the precise pose of the item is determined based on the recognition result of the location code in the second image, and the error of the content code recognition failure is reported. If both the location code and the content code in the second image fail to be recognized, an error indicating that both the location code and the content code have failed to be recognized is reported, and the location process for the item is terminated.

4. The item positioning method according to claim 2, characterized in that, The step of adjusting the pose of the image acquisition device based on the coarse pose to obtain the second image includes: If the number of identification adjustments exceeds the second value, the positioning process for the item is terminated.

5. The article positioning method according to claim 1, characterized in that, The process of identifying the location code and the content code in the first image then includes: In response to the successful recognition of both the location code and the content code in the first image, the precise pose of the item is determined based on the recognition result of the location code in the first image, and the information of the item is determined based on the content code in the first image. In response to the successful recognition of the location code in the first image and the failure to recognize the content code, the precise pose of the item is determined based on the recognition result of the location code in the first image, and the error of the failure to recognize the content code is reported. If both the location code and the content code in the first image fail to be recognized, an error indicating that both the location code and the content code have failed to be recognized is reported, and the location process for the item is terminated.

6. The item positioning method according to claim 1, characterized in that, Identifying the location code and content code in the image includes: The location code and content code in the image are identified by dual threads, wherein the image is either the first image or the second image.

7. The article positioning method according to claim 1, characterized in that, The item positioning method is applied in a goods retrieval and placement scenario, where the item is the goods or the corresponding storage location, the image acquisition device is mounted on the execution mechanism, and the precise pose of the item is the pose of the item relative to the execution mechanism; the method further includes: When the item is the goods, the actuator is controlled to pick up the item based on the precise position of the goods; When the item is in the storage location, the actuator is controlled to place the item in the storage location or retrieve the item from the storage location based on the precise orientation of the storage location.

8. The article positioning method according to claim 1, characterized in that, Determining the precise pose of the item based on the identification result of the positioning code includes: The position of the positioning code relative to the image acquisition device is calculated based on the recognition result of the positioning code; Based on the pose of the positioning code relative to the image acquisition device, the affixing position of the positioning code on the item, and the external parameters of the image acquisition device on the actuator, the precise pose of the item is calculated.

9. An electronic device, characterized in that, The electronic device includes a processor; the processor is configured to execute instructions to implement the steps of the method as described in any one of claims 1-8.

10. A computer-readable storage medium having a program stored thereon, characterized in that, When the program is executed by a processor, it implements the steps of the method according to any one of claims 1-8.

Images