Article identification method and device, equipment and medium

Abstract

The invention belongs to the technical field of electric appliances, and particularly relates to an article identification method and device, equipment and a medium. The article identification method is applied to a first intelligent device, and comprises the steps of obtaining a to-be-identified article image, and preliminarily identifying a target article category; based on the target article category, determining a target intelligent device, and sending the article image to the target intelligent device, so that the target intelligent device performs final identification on the article image; and receiving a final identification result returned by the target intelligent equipment, and performing corresponding operation based on the final identification result. When a first intelligent device obtains an image of a to-be-recognized article, the first intelligent device preliminarily recognizes the category of the article, then determines a target intelligent device capable of specifically recognizing the category of the article based on the category of the article, and sends the image of the article to the target intelligent device, so that the target intelligent device finely recognizes the image of the article, and finally, the target intelligent device sends the image of the article to the target intelligent device. And the first intelligent device only needs to perform corresponding operation based on the final identification result returned by the target intelligent device.

Description

Technical Field

[0001] This application belongs to the field of intelligent electrical appliance technology, specifically relating to an item identification method, device, equipment, and medium. Background Technology

[0002] With the advancement of science and technology and the development of artificial intelligence, smart home appliances are becoming increasingly intelligent. Among them, smart home robots are gradually becoming widely used home devices because they can replace users in performing household services and can also be responsible for monitoring daily abnormalities in the home.

[0003] Current home robots are generally equipped with cameras to identify various items in the user's home, such as furniture, home appliances, doors and windows. Because these large items have relatively regular and fixed shapes and clear edges, home robots can identify these items relatively accurately.

[0004] However, when home robots encounter small, irregularly shaped items with indistinct edges, such as overlapping clothing, the difference in camera angles makes it difficult for the home robot to identify detailed features, thus making it difficult to grasp the clothing. Summary of the Invention

[0005] This application provides an item recognition method, apparatus, device, and medium to solve the problem in the prior art that smart home robots, relying solely on cameras, have difficulty accurately recognizing small items with irregular shapes and unclear edges, such as clothing.

[0006] In a first aspect, this application provides an item identification method, comprising: applied to a first smart device, the method comprising:

[0007] Acquire images of the items to be identified and initially identify the category of the target items;

[0008] Based on the target item category, a target smart device is identified, and the item image is sent to the target smart device so that the target smart device can perform final recognition of the item image;

[0009] Receive the final identification result returned by the target smart device, and perform corresponding operations based on the final identification result.

[0010] In one possible design, determining the target smart device based on the target item category includes:

[0011] Determine the first smart device's ability to identify the target item category;

[0012] If the first smart device's ability to recognize the target item category is lower than a preset threshold, then the target smart device is determined based on the target item category.

[0013] In one possible design, prior to acquiring the image of the object to be identified, the method further includes:

[0014] The device receives item identification information shared by multiple second smart devices, wherein the multiple second smart devices are in the same home network as the first smart device, and the item identification information includes: the corresponding shared address, the identifiable item category, and the identification capability of each item category;

[0015] Based on the item recognition information, an item recognition capability table is constructed;

[0016] The step of determining the target smart device based on the target item category includes:

[0017] The target smart device is determined based on the target item type and the item recognition capability table.

[0018] In one possible design, determining the target smart device based on the target item type and the item recognition capability table includes:

[0019] Based on the target item category, at least one third smart device capable of recognizing the target item category is determined from the item recognition capability table;

[0020] The target smart device is the third smart device that has the highest recognition capability for the target item category among at least one of the third smart devices.

[0021] In one possible design, sending the image of the item to the target smart device includes:

[0022] Obtain the shared address corresponding to the target smart device from the item recognition capability table;

[0023] The system connects to the target smart device via the shared address and sends the item image to the target smart device after a successful connection.

[0024] In one possible design, after successfully connecting and sending the image of the item to the target smart device, the method further includes:

[0025] If the final recognition result is not received from the target smart device within a preset time period, the item recognition information of the target smart device for the target item category will be deleted from the item recognition capability table.

[0026] At the same time, the third smart device with the second highest recognition capability is selected as the new target smart device until the final recognition result is obtained.

[0027] In one possible design, the first smart device is a home robot, and the operation based on the final recognition result includes:

[0028] Based on the final recognition result, determine the pixel coordinates of the item to be recognized in the item image;

[0029] The coordinate system of the pixel point is transformed to obtain the three-dimensional coordinates of the object to be identified in the three-dimensional coordinate system, and the object to be identified is grasped based on the three-dimensional coordinates.

[0030] Secondly, this application provides an item recognition device applied to a first smart device, the device comprising:

[0031] The preliminary identification module is used to acquire images of the items to be identified and to initially identify the category of the items.

[0032] The first processing module is used to determine the target smart device based on the target item category, and send the item image to the target smart device so that the target smart device can perform final recognition of the item image;

[0033] The second processing module is used to receive the final recognition result returned by the target smart device and perform corresponding operations based on the final recognition result.

[0034] Thirdly, this application provides an item identification device, including: a processor, and a memory communicatively connected to the processor;

[0035] The memory stores computer-executed instructions;

[0036] The processor executes computer execution instructions stored in the memory to implement the item identification method as described in the first aspect.

[0037] Fourthly, this application provides a computer-readable storage medium storing computer-executable instructions, which, when executed by a computer, are used to implement the article identification method as described in the first aspect.

[0038] The item recognition method, apparatus, device, and medium provided in this application acquire an image of an item to be recognized and preliminarily identify the target item category; based on the target item category, determine a target smart device and send the item image to the target smart device so that the target smart device can perform final recognition of the item image; receive the final recognition result returned by the target smart device and perform corresponding operations based on the final recognition result.

[0039] In the above method, when the first smart device acquires an image of an object to be identified, it first preliminarily identifies the category of the object. Then, based on the category of the object, it determines a target smart device that can specifically identify the category of the object and sends the image of the object to the target smart device so that the target smart device can perform detailed identification of the image of the object. After the target smart device identifies the object, the first smart device obtains the final identification result from the target smart device. Finally, the first smart device performs corresponding operations based on the final identification result. Attached Figure Description

[0040] The accompanying drawings, which are incorporated in and form part of this specification, illustrate embodiments consistent with this application and, together with the description, serve to explain the principles of this application.

[0041] Figure 1 This is a schematic diagram of an application scenario provided by an embodiment of this application;

[0042] Figure 2 A flowchart of an article identification method provided in this application embodiment Figure 1 ;

[0043] Figure 3 A flowchart of an article identification method provided in this application embodiment Figure 2 ;

[0044] Figure 4 A flowchart of an article identification method provided in this application embodiment Figure 3 ;

[0045] Figure 5 This is a schematic diagram of the structure of an item recognition device provided in an embodiment of the present invention;

[0046] Figure 6 This is a hardware schematic diagram of an item recognition device provided in an embodiment of the present invention.

[0047] The accompanying drawings illustrate specific embodiments of this application, which will be described in more detail below. These drawings and descriptions are not intended to limit the scope of the concept in any way, but rather to illustrate the concept of this application to those skilled in the art through reference to particular embodiments. Detailed Implementation

[0048] To make the objectives, technical solutions, and advantages of this application clearer, the technical solutions 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, not all embodiments. Based on the embodiments of this application, all other embodiments obtained by those skilled in the art without creative effort are within the scope of protection of this application.

[0049] The terms "first," "second," "third," "fourth," etc. (if present) in the specification, claims, and accompanying drawings of this invention are used to distinguish similar objects and are not necessarily used to describe a specific order or sequence. It should be understood that such data can be interchanged where appropriate so that embodiments of the invention described herein can be implemented, for example, in orders other than those illustrated or described herein.

[0050] In this application, the terms "exemplary" or "for example" are used to indicate examples, illustrations, or descriptions. Any embodiment or design described as "exemplary" or "for example" in this application should not be construed as being more preferred or advantageous than other embodiments or designs. Specifically, the use of terms such as "exemplary" or "for example" is intended to present the relevant concepts in a specific manner.

[0051] With the development of technology and the improvement of people's living standards, the frequency of use of smart home devices is also increasing. Home robots can effectively patrol and monitor the home environment when people are away, and are increasingly popular among users. Existing smart devices such as home robots are generally equipped with cameras, which take pictures of objects in the home and use image recognition neural network models to identify the objects. The neural network models are trained based on a large number of images of objects in the early stages.

[0052] However, different objects have different shapes and varying degrees of clarity in their boundaries. When multiple objects come into contact with or obstruct each other, it can affect the home robot's ability to recognize objects, thereby affecting the accuracy and intelligence of the home robot's grasping.

[0053] Therefore, this application proposes a method for identifying objects. The method primarily involves first acquiring an image of the object to be identified using a first smart device and initially identifying the target object category. If the first smart device has a low ability to identify the target object category, a target smart device with a higher ability to identify that category is selected, and the object image is sent to the target smart device for final identification. After the target smart device completes its final identification, the first smart device obtains the final identification result from the target smart device and performs corresponding operations based on the final identification result. If the first smart device has a high ability to identify the target object category, it directly performs the final identification of the object image itself and performs corresponding operations based on the final identification result obtained by the first smart device itself, without relying on other smart devices.

[0054] The following is combined Figure 1 The application scenarios of this application will be explained.

[0055] Figure 1 This is a schematic diagram illustrating an application scenario provided by an embodiment of this application. For example... Figure 1As shown, the scenario includes a home robot (including a camera) 101, a smart washing and care device 102, a computer 103, and a smart TV 104. It is assumed that the first smart device is the home robot 101.

[0056] The home robot 101 first acquires an image of the object to be identified and preliminarily identifies the category of the target object; then, based on the category of the target object, it determines the target smart device and sends the object image to the target smart device so that the target smart device can perform the final identification of the object image; finally, the home robot 101 receives the final identification result returned by the target smart device and performs corresponding operations based on the final identification result.

[0057] Assuming the item to be identified is a stack of clothing, after the home robot 101 initially identifies it as clothing, it can first assess its own ability to identify clothing. If the identification ability is not lower than a preset threshold, it can identify the clothing on its own and continue with subsequent operations after the identification is completed.

[0058] If the home robot 101 has a low ability to recognize clothing, especially if it has difficulty recognizing clothing that is stacked together, then a target smart device with a high ability to recognize clothing can be identified in the home network. The target smart device can be used to complete the clothing recognition work, and after the target smart device has completed the recognition, the final recognition result can be obtained from the target smart device, and then the subsequent corresponding operations can be performed.

[0059] Under normal circumstances, the smart laundry and care device 102 has a high recognition capability for clothing. At this time, the home robot 101 can send the image of the clothing to the smart laundry and care device 102, so that the smart laundry and care device 102 can complete the image recognition of the items.

[0060] One of the key functions of a home robot is to grasp objects and place them in the correct and suitable location. When it acts as the primary intelligent device, if it obtains the final recognition results returned by other intelligent devices, it can determine the pixel coordinates of the object to be recognized in the object image based on the final recognition results. It can then perform coordinate system transformation on the pixel coordinates to obtain the three-dimensional coordinates of the object to be recognized in the three-dimensional coordinate system, and grasp the object to be recognized based on the three-dimensional coordinates.

[0061] Based on the cooperation between the aforementioned smart devices, not only can the recognition capabilities of different smart devices in the home environment be fully utilized for different items, but the recognition results of the first smart device for items can also be calibrated to a certain extent.

[0062] The technical solutions of this application and how they solve the aforementioned technical problems are described in detail below with specific embodiments. These specific embodiments may exist independently or in combination with each other. Identical or similar concepts or processes may not be repeated in some embodiments. The embodiments of this application will now be described with reference to the accompanying drawings.

[0063] Figure 2 A flowchart of an article identification method provided in this application embodiment Figure 1 . like Figure 2 As shown, this method is applied to a first smart device, and the method includes:

[0064] S201. Obtain the image of the item to be identified and preliminarily identify the category of the target item.

[0065] In the above scheme, after the first intelligent device acquires the image of the object to be identified, it needs to identify the category of the object to obtain the target object category.

[0066] The first intelligent device can acquire images through a camera, and this embodiment does not limit this; in addition, the intelligent device's identification of item categories is existing technology, and this embodiment will not elaborate on this.

[0067] S202. Based on the target item category, determine the target smart device and send the item image to the target smart device so that the target smart device can perform final recognition of the item image.

[0068] In this step, after determining the category of the item to be identified, the target smart device that can identify the category can be determined based on the item category. After the smart device that can identify the item category is determined, the first smart device can send the item image to the target smart device so that it can be identified.

[0069] S203. Receive the final recognition result returned by the target smart device, and perform corresponding operations based on the final recognition result.

[0070] In the above scheme, after the target smart device completes the identification, it will obtain a final identification result. The target smart device will send the final identification result to the first smart device so that the first smart device can perform subsequent operations based on it.

[0071] In this embodiment of the application, when the first smart device acquires an image of an item to be identified, it first preliminarily identifies the category of the item. Then, based on the category of the item, it determines a target smart device that can specifically identify the category of the item and sends the image of the item to the target smart device so that the target smart device can perform detailed identification of the image of the item. After the target smart device identifies the item, the first smart device obtains the final identification result from the target smart device. Finally, the first smart device performs corresponding operations based on the final identification result.

[0072] Figure 3 A flowchart of an article identification method provided in this application embodiment Figure 2 .like Figure 3 As shown, this method is applied to a first smart device. Based on the previous embodiment, this method further includes determining the recognition capability of the first smart device. The method includes:

[0073] S301. Obtain the image of the item to be identified and preliminarily identify the category of the target item.

[0074] S302. Determine the first intelligent device's ability to identify the category of the target item.

[0075] In the above scheme, the first smart device can also be a smart device with object recognition capability. After the first smart device identifies the object category, it needs to determine whether it can accurately identify the object category, that is, the level of its ability to identify the object category.

[0076] S303. Determine whether the first intelligent device's ability to identify the target item category is lower than a preset threshold.

[0077] In this step, a preset threshold is used as the critical value. If the first smart device's ability to recognize the target item category is lower than the preset threshold, it can be considered that the first smart device has a low ability to recognize the item category and cannot accurately recognize it. If the first smart device's ability to recognize the target item category is not lower than the preset threshold, it can be considered that the first smart device has a high ability to recognize the item category and can accurately recognize it.

[0078] S304. If so, then based on the target item category, determine the target smart device and send the item image to the target smart device so that the target smart device can perform final recognition of the item image.

[0079] In the above scheme, when the first smart device cannot accurately identify the item to be identified, it can only rely on the identification capabilities of other smart devices to perform the identification.

[0080] S305. Receive the final recognition result returned by the target smart device, and perform corresponding operations based on the final recognition result.

[0081] S306. If not, perform final recognition on the object image to obtain the final recognition result, and perform corresponding operations based on the final recognition result.

[0082] In the above scheme, if the first smart device can accurately identify the object to be identified, then there is no need to rely on the help of other smart devices. At this time, the first smart device can perform the final identification of the object image on its own and perform subsequent corresponding operations based on the final identification result.

[0083] For steps that are the same as those in the foregoing embodiments, please refer to the description of the foregoing embodiments, and they will not be repeated here.

[0084] In this embodiment of the application, after the first smart device initially identifies the category of the target item, the recognition ability of the first smart device for that item category is first determined. If its recognition ability is low, other smart devices are used to perform the recognition work; if its recognition ability is high, it can identify the item to be identified by itself.

[0085] Figure 4 A flowchart of an article identification method provided in this application embodiment Figure 3 .like Figure 4 As shown, this method is applied to a first smart device. Based on the aforementioned embodiments, this method further includes the pre-construction and utilization of an item recognition capability table. The method includes:

[0086] S401. Receive item identification information shared by multiple second smart devices, wherein the multiple second smart devices are in the same home network as the first smart device, and the item identification information includes: the corresponding shared address, the identifiable item category, and the identification capability of each item category.

[0087] In the above solution, there are usually multiple smart devices in the same home environment, and the categories of items that different smart devices can recognize will also be different. Therefore, an item recognition capability table can be built in the home environment. Each smart device establishes and maintains its own item recognition capability table, and the item recognition information is shared by smart devices in the home environment.

[0088] Smart devices in the same home environment can share their ability to identify different categories of items with the home network. After receiving the item identification information shared by other smart devices in the home network, the first smart device can establish and maintain its own item identification capability table so that it can use other smart devices in the item identification capability table to help it carry out the identification work in the future.

[0089] S402. Construct an item recognition capability table based on item recognition information.

[0090] In this step, each smart device's identification list can specify the items that other smart devices besides itself can identify, the level of their ability to identify the corresponding items, and the shared address that needs to be connected when using each smart device's identification capabilities. This shared address is also the address where each smart device shares the aforementioned item identification information.

[0091] S403. Obtain the image of the item to be identified and preliminarily identify the category of the target item.

[0092] S404. Based on the target item category, determine at least one third intelligent device that can identify the target item category from the item recognition capability table.

[0093] In the above scheme, after the first smart device identifies the category of the item, it can search its own maintained item recognition capability table to find all the third smart devices that can identify that item category.

[0094] S405. Select the third intelligent device with the highest recognition capability for the target item category among at least one third intelligent device as the target intelligent device.

[0095] In the above scheme, as mentioned above, there may be multiple third smart devices that can identify the same item category, but the recognition capabilities of different smart devices for the same item category may be different. In this embodiment, the third smart device with the highest recognition capability for the target item category is preferred as the target smart device.

[0096] S406. Obtain the shared address corresponding to the target smart device from the item recognition capability table.

[0097] In this step, it is stated that the shared address is both the address where smart devices share item identification information and the shared address that other smart devices need to connect to when they need to use the smart device's identification capability. The shared address is stored in the item identification capability table. After the target smart device is identified, the corresponding shared address can be found in the table.

[0098] S407. Connect to the target smart device via a shared address, and after successful connection, send the object image to the target smart device so that the target smart device can perform final recognition of the object image.

[0099] In the above scheme, after determining the shared address corresponding to the target smart device from the object recognition capability table, the target smart device can be connected through the shared address, and the object image can be sent to the target smart device through the shared address.

[0100] S408: Receive the final recognition result returned by the target smart device, and perform corresponding operations based on the final recognition result.

[0101] In the specific implementation process, if the recognition result of the object image by the target smart device is not received for a long time, a new target smart device needs to be determined to ensure the normal operation of the subsequent work of the first smart device. For example, if the final recognition result returned by the target smart device is not received within a preset time, the object recognition information of the target smart device for the target object category is deleted from the object recognition capability table; at the same time, the third smart device with the second highest recognition capability is selected as the new target smart device until the final recognition result is obtained.

[0102] For steps that are the same as those in the foregoing embodiments, please refer to the description of the foregoing embodiments, and they will not be repeated here.

[0103] In this embodiment, the first smart device constructs and maintains its own item recognition capability table based on the item recognition information shared by multiple second smart devices in the same home network. Once the image of the item to be recognized is obtained and the item category is determined, a suitable target smart device that can recognize the item category can be found from the item recognition capability table, and then the target smart device can be used to perform item recognition.

[0104] In summary, the item recognition method provided in this application first acquires an image of the item to be recognized through a first smart device and preliminarily identifies the target item category. Then, if the first smart device has a low recognition capability for the target item category, a target smart device with a high recognition capability for that target item category is identified, and the item image is sent to the target smart device for final recognition. After the target smart device completes the final recognition, the first smart device obtains the final recognition result from the target smart device and performs corresponding operations based on the final recognition result. If the first smart device has a high recognition capability for the target item category, it directly performs the final recognition of the item image itself and performs corresponding operations based on the final recognition result obtained by the first smart device itself, without relying on other smart devices.

[0105] Figure 5 This is a schematic diagram of the structure of an item recognition device provided in an embodiment of the present invention, as shown below. Figure 5 As shown, the object recognition device is applied to a first smart device. The object recognition device may include various functional modules for implementing the aforementioned object recognition method. Any functional module may be implemented by software / or hardware.

[0106] For example, the item recognition device may include: a preliminary recognition module 501, a first processing module 502, and a second processing module 503;

[0107] The preliminary identification module 501 is used to acquire images of the items to be identified and to initially identify the category of the items.

[0108] The first processing module 502 is used to determine the target smart device based on the target item category and send the item image to the target smart device so that the target smart device can perform final recognition of the item image;

[0109] The second processing module 503 is used to receive the final recognition result returned by the target smart device and perform corresponding operations based on the final recognition result.

[0110] Optionally, the first processing module 502 can also be used to determine the first smart device's ability to identify the target item category; if the first smart device's ability to identify the target item category is lower than a preset threshold, then the target smart device is determined based on the target item category.

[0111] Optionally, the preliminary identification module 501 can also be specifically used for: receiving item identification information shared by multiple second smart devices before acquiring the image of the item to be identified, wherein the multiple second smart devices are in the same home network as the first smart device, and the item identification information includes: the corresponding shared address, the identifiable item category and the identification capability of each item category; and constructing an item identification capability table based on the item identification information.

[0112] Optionally, the first processing module 502 can also be used to determine the target smart device based on the target item type and the item recognition capability table.

[0113] Optionally, the first processing module 502 may also be specifically used to: determine at least one third intelligent device that can identify the target item category from the item recognition capability table based on the target item category; and select the third intelligent device with the highest recognition capability for the target item category among the at least one third intelligent device as the target intelligent device.

[0114] Optionally, the first processing module 502 can also be used to obtain the shared address corresponding to the target smart device from the item recognition capability table; connect to the target smart device through the shared address, and send the item image to the target smart device after successful connection.

[0115] Optionally, the first processing module 502 can also be specifically used to: after successfully connecting and sending the item image to the target smart device, if the final recognition result is not received from the target smart device within a preset time period, delete the item recognition information of the target smart device for the target item category from the item recognition capability table; at the same time, use the third smart device with the second highest recognition capability as the new target smart device until the final recognition result is obtained.

[0116] Optionally, the first intelligent device is a home robot, and the second processing module 503 can also be used to determine the pixel coordinates of the object to be identified in the object image based on the final recognition result; perform coordinate system transformation on the pixel coordinates to obtain the three-dimensional coordinates of the object to be identified in the three-dimensional coordinate system, and grasp the object to be identified based on the three-dimensional coordinates.

[0117] The item recognition device is used to execute the technical solution provided in the aforementioned item recognition method embodiments. Its implementation principle and technical effects are similar to those in the aforementioned method embodiments, and will not be repeated here.

[0118] This application also provides an item identification device, including: at least one processor and a memory;

[0119] The memory stores the instructions that the computer executes;

[0120] At least one processor executes computer execution instructions stored in memory, causing at least one processor to perform an item identification method.

[0121] Figure 6 This is a hardware schematic diagram of an item recognition device provided in an embodiment of the present invention. Figure 6 As shown, the item identification device 60 provided in this embodiment includes at least one processor 601 and a memory 602. The device 60 also includes a communication component 603. The processor 601, memory 602, and communication component 603 are connected via a bus 604.

[0122] In the specific implementation process, at least one processor 601 executes computer execution instructions stored in memory 602, causing at least one processor 601 to execute the above-mentioned item recognition method.

[0123] The specific implementation process of processor 601 can be found in the above method embodiments, and its implementation principle and technical effect are similar. It will not be repeated here.

[0124] In the above Figure 6 In the illustrated embodiments, it should be understood that the processor can be a Central Processing Unit (CPU), or other general-purpose processors, digital signal processors (DSPs), application-specific integrated circuits (ASICs), etc. The general-purpose processor can be a microprocessor or any conventional processor. The steps of the method disclosed in this invention can be directly implemented by a hardware processor, or implemented by a combination of hardware and software modules within the processor.

[0125] The memory may include random access memory (RAM) and may also include non-volatile memory (NVM), such as at least one disk storage device.

[0126] The bus can be an Industry Standard Architecture (ISA) bus, a Peripheral Component Interconnect (PCI) bus, or an Extended Industry Standard Architecture (EISA) bus, etc. Buses can be categorized as address buses, data buses, control buses, etc. For ease of illustration, the buses shown in the accompanying drawings are not limited to a single bus or a single type of bus.

[0127] This application also provides a computer-readable storage medium storing computer-executable instructions, which, when executed by a processor, implement the item identification method described above.

[0128] The aforementioned computer-readable storage medium can be implemented by any type of volatile or non-volatile storage device or a combination thereof, such as static random access memory (SRAM), electrically erasable programmable read-only memory (EEPROM), erasable programmable read-only memory (EPROM), programmable read-only memory (PROM), read-only memory (ROM), magnetic storage, flash memory, magnetic disk, or optical disk. The readable storage medium can be any available medium accessible to a general-purpose or special-purpose computer.

[0129] An exemplary readable storage medium is coupled to a processor, enabling the processor to read information from and write information to the readable storage medium. Of course, the readable storage medium can also be a component of the processor. The processor and the readable storage medium can reside in an Application Specific Integrated Circuit (ASIC). Alternatively, the processor and the readable storage medium can exist as discrete components in the device.

[0130] The division of units described herein is merely a logical functional division. 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 indirect coupling or communication connection through some interfaces, devices, or units, and may be electrical, mechanical, or other forms.

[0131] 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.

[0132] In addition, the functional units in the various embodiments of the present invention 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.

[0133] If the aforementioned functions are implemented as software functional units and sold or used as independent products, they can be stored in a computer-readable storage medium. Based on this understanding, the technical solution of this invention, essentially, or the part that contributes to the prior art, or a portion 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 described in the various embodiments of this invention. 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.

[0134] Those skilled in the art will understand that all or part of the steps of the above-described method embodiments can be implemented by hardware related to program instructions. The aforementioned program can be stored in a computer-readable storage medium. When executed, the program performs the steps of the above-described method embodiments; and the aforementioned storage medium includes various media capable of storing program code, such as ROM, RAM, magnetic disks, or optical disks.

[0135] The technical solutions of this application have been described above with reference to the preferred embodiments shown in the accompanying drawings. However, it is readily understood by those skilled in the art that the scope of protection of this application is obviously not limited to these specific embodiments. The above embodiments are only used to illustrate the technical solutions of this application and are not intended to limit them. 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 or all of the technical features therein. These 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. An item recognition method, characterized in that, Applied to a first smart device, the method includes: Acquire images of the items to be identified and initially identify the category of the target items; Based on the target item category, a target smart device is identified, and the item image is sent to the target smart device so that the target smart device can perform final recognition of the item image; Receive the final identification result returned by the target smart device, and perform corresponding operations based on the final identification result.

2. The method according to claim 1, characterized in that, The step of determining the target smart device based on the target item category includes: Determine the first smart device's ability to identify the target item category; If the first smart device's ability to recognize the target item category is lower than a preset threshold, then the target smart device is determined based on the target item category.

3. The method according to claim 2, characterized in that, Before acquiring the image of the item to be identified, the method further includes: The device receives item identification information shared by multiple second smart devices, wherein the multiple second smart devices are in the same home network as the first smart device, and the item identification information includes: the corresponding shared address, the identifiable item category, and the identification capability of each item category; Based on the item recognition information, an item recognition capability table is constructed; The step of determining the target smart device based on the target item category includes: The target smart device is determined based on the target item type and the item recognition capability table.

4. The method according to claim 3, characterized in that, The step of determining the target smart device based on the target item type and the item recognition capability table includes: Based on the target item category, at least one third smart device capable of recognizing the target item category is determined from the item recognition capability table; The target smart device is the third smart device that has the highest recognition capability for the target item category among at least one of the third smart devices.

5. The method according to claim 4, characterized in that, Sending the image of the item to the target smart device includes: Obtain the shared address corresponding to the target smart device from the item recognition capability table; The system connects to the target smart device via the shared address and sends the item image to the target smart device after a successful connection.

6. The method according to claim 5, characterized in that, After successfully connecting and sending the image of the item to the target smart device, the method further includes: If the final recognition result is not received from the target smart device within a preset time period, the item recognition information of the target smart device for the target item category will be deleted from the item recognition capability table. At the same time, the third smart device with the second highest recognition capability is selected as the new target smart device until the final recognition result is obtained.

7. The method according to claim 6, characterized in that, The first smart device is a home robot, and the operation based on the final recognition result includes: Based on the final recognition result, determine the pixel coordinates of the item to be recognized in the item image; The coordinate system of the pixel point is transformed to obtain the three-dimensional coordinates of the object to be identified in the three-dimensional coordinate system, and the object to be identified is grasped based on the three-dimensional coordinates.

8. An item identification device, characterized in that, Applied to a first intelligent device, the device includes: The preliminary identification module is used to acquire images of the items to be identified and to initially identify the category of the items. The first processing module is used to determine the target smart device based on the target item category, and send the item image to the target smart device so that the target smart device can perform final recognition of the item image; The second processing module is used to receive the final recognition result returned by the target smart device and perform corresponding operations based on the final recognition result.

9. An item recognition device, characterized in that, include: At least one processor and memory; The memory stores computer-executed instructions; The at least one processor executes computer execution instructions stored in the memory, causing the at least one processor to perform the article identification method as described in any one of claims 1 to 7.

10. A computer-readable storage medium having a computer program stored thereon, characterized in that, When executed by a processor, the computer program implements the steps of the article identification method as described in any one of claims 1 to 7.

Images