A target object recognition method and device, electronic equipment, and storage medium
Patent Information
- Authority / Receiving Office
- CN · China
- Patent Type
- Applications(China)
- Current Assignee / Owner
- ZHEJIANG UNIVIEW TECH CO LTD
- Filing Date
- 2024-12-12
- Publication Date
- 2026-06-12
Smart Images
Figure CN122200753A_ABST
Abstract
Description
Technical Field
[0001] This invention relates to the field of image processing technology, and in particular to a target object recognition method, apparatus, electronic device, and storage medium. Background Technology
[0002] With the development of computer technology, target object recognition has become increasingly widely used. For example, in the scenario of personnel attendance, facial recognition technology is used to compare real-time facial images with images in a pre-saved facial database to perform personnel sign-in and attendance.
[0003] However, this object recognition method based on comparison and matching has several drawbacks. On the one hand, as the number of object objects stored in the pre-set object database increases, the performance and efficiency of object recognition decrease, and the computational requirements of the device also become higher. On the other hand, if multiple object objects need to be recognized simultaneously, it not only consumes time and reduces efficiency, but in some applicable scenarios, it can also easily cause congestion at the recognition device location. Summary of the Invention
[0004] This invention provides a target object recognition method, apparatus, electronic device, and storage medium to improve the efficiency of target object recognition and reduce the cost of target object recognition.
[0005] In a first aspect, embodiments of the present invention provide a target object recognition method, which is executed by a target object recognition terminal, and the method includes:
[0006] Based on a standard image sent by at least one image acquisition terminal, determine the features of a standard target object that match the standard image;
[0007] The standard target object features are sent to the image acquisition terminal, and the standard target object features are then deleted.
[0008] If it is determined that the image to be identified and the standard target object features sent by the target image acquisition terminal have been received, then the target object is identified based on the image to be identified and the standard target object features, and the target object identification result is sent to the target image acquisition terminal.
[0009] Secondly, embodiments of the present invention also provide a target object recognition method, which is executed by an image acquisition terminal, and the method includes:
[0010] At least one standard image is sent to the target object recognition terminal, and the target object recognition terminal sends standard target object features that match the standard image.
[0011] If a target object recognition command is detected, the image to be recognized is determined, and the image to be recognized and standard target object features are sent to the target object recognition terminal so that the target object recognition terminal can perform target object recognition based on the image to be recognized and the standard target object features.
[0012] Thirdly, embodiments of the present invention also provide a target object recognition device, which is deployed on a target object recognition terminal, and the device includes:
[0013] A standard target object feature determination module is used to determine standard target object features that match the standard image based on a standard image sent by at least one image acquisition terminal.
[0014] A standard target object feature sending module is used to send the standard target object features to the image acquisition terminal and delete the standard target object features;
[0015] The target object recognition module is used to identify the target object based on the image to be recognized and the standard target object features sent by the target image acquisition terminal, and to send the target object recognition result to the target image acquisition terminal if it is determined that the image to be recognized and the standard target object features have been received.
[0016] Fourthly, embodiments of the present invention also provide a target object recognition device, which is deployed in an image acquisition terminal, and the device includes:
[0017] A standard image sending module is used to send at least one standard image to a target object recognition terminal, and to receive standard target object features that match the standard image sent by the target object recognition terminal;
[0018] The module for sending the image to be identified and the standard target object features is used to determine the image to be identified if a target object identification instruction is detected, and to send the image to be identified and the standard target object features to the target object identification terminal so that the target object identification terminal can identify the target object based on the image to be identified and the standard target object features.
[0019] Fifthly, embodiments of the present invention also provide an electronic device, including a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor executes the program to implement the target object identification method as described in any of the embodiments of the present invention.
[0020] In a sixth aspect, embodiments of the present invention also provide a storage medium for storing computer-executable instructions, which, when executed by a computer processor, are used to perform the target object identification method as described in any of the embodiments of the present invention.
[0021] The technical solution of this invention involves a target object recognition terminal receiving a standard image sent by an image acquisition terminal, determining standard target object features matching the standard image, deleting the standard target object features after sending them to the image acquisition terminal, and then performing target object recognition on the image to be recognized and the target object recognition result back to the image acquisition terminal after receiving the image to be recognized and the standard target object features sent by the target image acquisition terminal. This solves the problems of performance and efficiency degradation in existing target object recognition methods that rely on comparison and matching, especially when the number of target objects stored in the target object database increases, and the high time consumption and low efficiency when multiple target objects need to be recognized. By deleting the standard target object features after sending them to the image acquisition terminal, storage space is saved. Target object recognition is performed based on the image to be recognized and the standard target object features sent by the image acquisition terminal, eliminating the need to compare the image to be recognized with all standard target object features in the database, reducing the number of comparisons, improving the efficiency of target object recognition, and lowering the cost of target object recognition.
[0022] It should be understood that the description in this section is not intended to identify key or essential features of the embodiments of the present invention, nor is it intended to limit the scope of the invention. Other features of the invention will become readily apparent from the following description. Attached Figure Description
[0023] To more clearly illustrate the technical solutions in the embodiments of the present invention, the accompanying drawings used in the description of the embodiments will be briefly introduced below. Obviously, the accompanying drawings described below are only some embodiments of the present invention. For those skilled in the art, other drawings can be obtained based on these drawings without creative effort.
[0024] Figure 1 This is a flowchart of a target object recognition method provided in Embodiment 1 of the present invention;
[0025] Figure 2 This is a flowchart of another target object recognition method provided in Embodiment 2 of the present invention;
[0026] Figure 3 This is a schematic diagram of the structure of a target object recognition device provided in Embodiment 3 of the present invention;
[0027] Figure 4 This is a schematic diagram of another target object recognition device provided in Embodiment 4 of the present invention;
[0028] Figure 5 This is a schematic diagram of the structure of an electronic device provided in Embodiment 5 of the present invention. Detailed Implementation
[0029] To enable those skilled in the art to better understand the present invention, the technical solutions of the present invention will be clearly and completely described below with reference to the accompanying drawings of the embodiments of the present invention. Obviously, the described embodiments are only some embodiments of the present invention, and not all embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those skilled in the art without creative effort should fall within the scope of protection of the present invention.
[0030] It should be noted that the terms "first," "second," etc., 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 the embodiments of the invention described herein can be implemented in orders other than those illustrated or described herein. Furthermore, the terms "comprising" and "having," and any variations thereof, are intended to cover non-exclusive inclusion; for example, a process, method, system, product, or device that comprises a series of steps or units is not necessarily limited to those steps or units explicitly listed, but may include other steps or units not explicitly listed or inherent to such processes, methods, products, or devices. In the embodiments of this application, certain software, components, models, and other existing industry solutions may be mentioned. These should be considered exemplary, intended only to illustrate the feasibility of implementing the technical solutions of this application, and do not imply that the applicant has already used or necessarily used such solutions.
[0031] The acquisition, transmission, storage, use, and processing of data in this application all comply with the relevant provisions of national laws and regulations.
[0032] Example 1
[0033] Figure 1 The flowchart of a target object recognition method provided in Embodiment 1 of the present invention is applicable to situations involving target object recognition. The method can be executed by a target object recognition device, which can be implemented in hardware and / or software. The target object recognition device can be configured in a target object recognition terminal, such as an electronic device or a server, and can be used in conjunction with an image acquisition terminal.
[0034] like Figure 1 As shown, the method includes:
[0035] S110. Based on a standard image sent by at least one image acquisition terminal, determine the standard target object features that match the standard image.
[0036] The image acquisition terminal is a terminal device that has established a pre-established communication connection with the target object recognition terminal and has target object recognition permissions. It can be a mobile terminal or other terminal devices capable of capturing and uploading images. This embodiment does not impose any restrictions on this.
[0037] Taking a personnel attendance tracking scenario as an example, the target object recognition terminal can be deployed in the internal network of the attendance location. The image acquisition terminal communicates with the target object recognition terminal by connecting to the wireless network of the attendance location. The communication connection method between the image acquisition terminal and the target object recognition terminal can be flexibly configured according to the application scenario, and this embodiment does not impose any restrictions on it.
[0038] In this embodiment, the target object recognition terminal can receive a standard image sent by at least one image acquisition terminal. For each image acquisition terminal, at least one standard image of the target object can be uploaded. This embodiment does not impose any restrictions on this.
[0039] A standard image is an image of the target object that needs to be identified in the subsequent target object recognition process. The target object can upload the standard image through the image acquisition terminal, or the image acquisition terminal can acquire a standard image of the target object that meets the image requirements.
[0040] Furthermore, after obtaining the image uploaded by the target object or the image captured by the image acquisition terminal, it can be determined whether the image can be used as a standard image. For example, it can be determined whether the position of the target object in the image uploaded by the target object or the image captured by the image acquisition terminal is within a pre-set position range. Another example is whether the number of features obtained by feature extraction from the target object in the image uploaded by the target object or the image captured by the image acquisition terminal is greater than or equal to a preset threshold. Yet another example is whether the quality (brightness, contrast, and sharpness, etc.) of the image uploaded by the target object or the image captured by the image acquisition terminal meets preset image quality requirements. By combining one or more of these conditions, it can be determined whether the image uploaded by the target object or the image captured by the image acquisition terminal can be used as a standard image.
[0041] The target object can be of different types, such as a person or a vehicle. Correspondingly, the standard target object features can also include different content. Taking a human face as an example, standard target object features can include facial contour features, facial features (such as features extracted from the eyes, nose, and mouth), skin texture features, hair features, color features, and expression features. Taking a vehicle as an example, standard target object features can include vehicle type features, vehicle body color features, vehicle body shape features, vehicle logo features, license plate features, size features, and structural features.
[0042] In this embodiment, after receiving a standard image from an image acquisition terminal, the target object recognition terminal extracts features from the standard image to obtain standard target object features. Specifically, the standard image is preprocessed, such as denoising, grayscale conversion, and normalization; target object detection is performed on the preprocessed standard image, such as target object detection based on convolutional neural networks; then, image segmentation is performed on the detected target object, such as based on threshold segmentation algorithms, edge detection algorithms, and watershed algorithms, to obtain the target object image; feature extraction is performed on the target object image, including texture-based feature extraction, shape-based feature extraction, and color-based feature extraction. Texture features can be extracted using local binary algorithms or gray-level co-occurrence matrices; shape features can be obtained using edge detection algorithms or geometric feature analysis; and color features can be determined using color histograms, color matrices, etc. Feature filtering and optimization are performed on the extracted features to obtain the standard target object features.
[0043] In this embodiment, the target object recognition terminal receives a standard image sent by the image acquisition terminal and generates corresponding standard target object features, thereby realizing the registration of the target object of the image acquisition terminal, or data entry.
[0044] S120. Send the standard target object features to the image acquisition terminal and delete the standard target object features.
[0045] In this embodiment, the standard target object features are sent to the image acquisition terminal, which saves the standard target object features, while the standard target object features locally on the target object recognition terminal are deleted.
[0046] The advantages of this setup are twofold. First, the target object recognition terminal does not need to store standard target object features locally, saving significant storage space as the number of target objects to be recognized increases. Second, existing technologies compare the image to be recognized with pre-stored standard target object features in the target object recognition terminal, a 1:N comparison mode where N is the total number of pre-stored standard target object features in the target object recognition terminal. In this embodiment, the standard target object features are deleted from the target object recognition terminal's local storage and instead sent to the terminal device. When target object recognition is needed, the terminal device sends the image to be recognized along with the standard target object features to the target object recognition terminal. This reduces the number of comparisons, even achieving a 1:1 comparison mode, thereby improving target object recognition efficiency. Furthermore, it reduces the difficulty of target object comparison, thus lowering the computing power requirements of the target object recognition terminal and saving hardware costs.
[0047] S130. If it is determined that the image to be identified and the standard target object features sent by the target image acquisition terminal have been received, then the target object is identified based on the image to be identified and the standard target object features, and the target object identification result is sent to the target image acquisition terminal.
[0048] Among them, the target image acquisition terminal is an image acquisition terminal that has previously sent standard images to the target object recognition terminal and received standard target object features from the target object recognition terminal. In other words, the target image acquisition terminal needs to be an image acquisition terminal that has already registered the target object.
[0049] Specifically, a target object identification terminal, upon receiving a standard image from an image acquisition terminal and sending it standard target object characteristics, records the identifier of the image acquisition terminal, such as device fingerprint information, to obtain an image acquisition terminal identification table. Device fingerprint information refers to a set of characteristic data that uniquely identifies the image acquisition terminal device, which may include the processor model, hardware serial number, software information, IMEI (International Mobile Equipment Identity) code, and MAC (Media Access Control Address) address. After receiving data from an image acquisition terminal, the terminal is first authenticated by comparing its device fingerprint information with the pre-stored image acquisition terminal identification table to determine if it has target object identification permissions. If the comparison is successful, it is then designated as the target image acquisition terminal, and target object identification is performed based on the image to be identified and the standard target object characteristics it sends.
[0050] The image to be identified is an image of the target object to be identified, captured and uploaded in real time by the target image acquisition terminal. Furthermore, before uploading the real-time captured image to the target object recognition terminal, the target image acquisition terminal can determine image requirements for the real-time captured image. For example, it can determine whether the position of the target object in the real-time captured image is within a pre-set position range. It can also determine whether the clarity, contrast, and other properties of the real-time captured image meet preset image quality requirements.
[0051] The standard target object feature is generated by the target image acquisition terminal when it first registers the target object, sending a standard image to the target object recognition terminal, and then the target object recognition terminal generates and sends the feature to the target image acquisition terminal based on the standard image.
[0052] In this embodiment, target object recognition is performed based on the image to be recognized and the features of a standard target object. Specifically, feature extraction is performed on the image to be recognized to obtain the features of the target object to be recognized. The feature extraction process has been described in the above embodiments and will not be repeated here. The features of the target object to be recognized and the features of the standard target object are compared. The similarity can be calculated using Euclidean distance, cosine similarity, etc. If the similarity is greater than or equal to a preset similarity threshold, the target object is confirmed to be successfully recognized.
[0053] It should be noted that when the target image acquisition terminal makes a target object recognition request to the target object recognition terminal, the number of images to be recognized is one. However, the number of standard target object features can be one or more.
[0054] In a specific example, taking a personnel attendance scenario, the image acquisition terminal can be a mobile terminal. Each target object uses its own mobile terminal for target object recognition to complete attendance. In this case, the target image acquisition terminal uploads only one image to be recognized and one set of standard target object features.
[0055] In another specific example, still taking the personnel attendance scenario, the image acquisition terminal can be a terminal device set up at multiple entrances / exits or different attendance locations. By setting up multiple image acquisition terminals, each target device is assigned to one of them, thus dispersing the pressure of attendance flow. Each image acquisition terminal can register multiple target objects, and multiple target objects are identified through the same image acquisition terminal. The image acquisition terminal pre-stores multiple standard target object features. At this time, the target image acquisition terminal can either respond to the user interface selection operation, determine the standard target object features to be uploaded, and upload the image to be identified and the standard target object features selected by the target object to be identified to the target object recognition terminal, or upload the image to be identified and the pre-stored multiple standard target object features to the target object recognition terminal. In this case, although a 1:1 comparison effect cannot be achieved, since the number of standard target object features pre-stored by the target image acquisition terminal is definitely less than the total number of standard target object features of all image acquisition terminals, compared with the comparison method in the prior art, it still reduces the number of target object comparisons and improves the efficiency of target object recognition.
[0056] In this embodiment, after the target object recognition terminal sends the target object recognition result to the target image acquisition terminal, it can also delete the image to be recognized, the features of the target object to be recognized, and the standard target object features to free up storage space and improve the operating efficiency of the target object recognition terminal. At the same time, it protects the data security and privacy of the target object to be recognized.
[0057] The technical solution of this embodiment deletes the standard target object features registered during target object registration after they are sent to the image acquisition terminal, saving storage space, ensuring the data security and privacy of the target object, reducing the number of target object comparisons, and improving the target object recognition efficiency. Furthermore, it reduces the difficulty of target object comparison, thereby reducing the computing power requirements of the target object recognition terminal and saving hardware costs. When target recognition of an object is required, the target image acquisition terminal sends the pre-stored standard target object features along with the image to be recognized to the target object recognition terminal for identification. When identifying a large number of target objects, this distributes the pressure on target object recognition and improves the efficiency of target object recognition.
[0058] Furthermore, the method in this embodiment also includes: storing the target object identifier and device fingerprint information sent by the image acquisition terminal accordingly; S130 may further include:
[0059] A1. If it is determined that the image to be identified, standard target object features, target object identifier, and device fingerprint information sent by the target image acquisition terminal have been received, then determine whether the target object identifier and device fingerprint information match.
[0060] A2. If so, then target object identification is performed based on the image to be identified and the features of the standard target object.
[0061] The target object identifier is data that uniquely identifies the target object. The target object identifier can be generated by the target image acquisition terminal when acquiring a standard image of the target object, or it can be uploaded by the target object to the image acquisition terminal. This embodiment does not limit the form or determination method of the target object identifier. Device fingerprint information has been described in the above embodiments and will not be repeated here.
[0062] This embodiment provides an implementation method for adding target object identifiers and device fingerprint information to the data transmitted by the target image acquisition terminal for dual verification.
[0063] Specifically, each image acquisition terminal, while uploading a standard image to the target object recognition terminal, also sends the target object identifier and device fingerprint information to the target object recognition terminal. The target object recognition terminal establishes a link between the target object identifier and the device fingerprint information and stores them accordingly. When the target image acquisition terminal needs to perform target object recognition, it sends the image to be recognized, standard target object features, target object identifier, and device fingerprint information to the target object recognition terminal. The target object recognition terminal first determines whether the target object identifier and device fingerprint information match based on the pre-stored link relationships between each target object identifier and device fingerprint information. The advantage of this setup is that it can determine whether the target object identifier and device fingerprint information are consistent with the data reserved during target object information registration, avoiding interference from unregistered image acquisition devices or target objects in subsequent target object recognition, and improving target object recognition efficiency. When the target object identifier and device fingerprint information sent by the target image acquisition terminal match, feature extraction of the image to be recognized and comparison of the features of the target object to be recognized with the features of the standard target object are then performed. This process has been described in the above embodiments and will not be repeated here.
[0064] Furthermore, S130 may include:
[0065] B1. If it is determined that the image to be identified and the standard target object features sent by the target image acquisition terminal have been received, the image to be identified and the standard target object features are saved to the task processing queue, and a task processing identifier that matches the image to be identified and the standard target object features is determined.
[0066] B2. Send the task processing identifier to the target image acquisition terminal to prompt the target image acquisition terminal to identify the target object.
[0067] This embodiment provides an implementation method for target object recognition based on a task processing queue. It is understood that when there are many target objects requiring simultaneous recognition, the target object recognition terminal may receive images to be recognized and standard target object features from multiple target image acquisition terminals within a short period, or multiple sets of images to be recognized and standard target object features from a single target image acquisition terminal. Since target object recognition requires a certain amount of time, a task processing queue is used to store the sets of images to be recognized and standard target object features to be processed. The target object recognition terminal processes these sets of images and features sequentially according to the order in which they are stored in the task processing queue.
[0068] It should be noted that the task processing queue needs to be persistently stored, for example, in a database.
[0069] The advantages of this setup are that it can improve the target recognition efficiency of the target object recognition terminal, avoid conflicts and competition between the features of each group of images to be recognized and the standard target object, improve the stability of the target object recognition terminal, and facilitate the management of each group of target object recognition tasks, including task submission, queuing, processing, and result storage.
[0070] Meanwhile, when a set of images to be identified and standard target object features are saved to the task processing queue, a task processing identifier is generated for them. This task processing identifier is used to indicate the order of the target object identification task in each group of target object identification tasks.
[0071] Sending the task processing identifier to the target image acquisition terminal has the advantage of notifying the target image acquisition terminal that the target object recognition terminal is performing target object recognition and waiting for the target object recognition result, thus improving the user experience of the target object.
[0072] Furthermore, after obtaining the target object recognition result, different follow-up operations can be performed according to different applicable scenarios. Taking the personnel check-in scenario as an example, if the target object recognition result is successful, the target object recognition terminal determines that the attendance is successful, and can record the current time, the target object identifier, and the attendance success result, and send the above data along with the target object recognition result to the image acquisition terminal; if the target object recognition result is unsuccessful, the unsuccessful target object recognition result is sent to the image acquisition terminal.
[0073] The technical solution of this invention involves a target object recognition terminal receiving a standard image sent by an image acquisition terminal, determining standard target object features matching the standard image, deleting the standard target object features after sending them to the image acquisition terminal, and then performing target object recognition on the image to be recognized and the target object recognition result back to the image acquisition terminal after receiving the image to be recognized and the standard target object features sent by the target image acquisition terminal. This solves the problems of performance and efficiency degradation in existing target object recognition methods that rely on comparison and matching, especially when the number of target objects stored in the target object database increases, and the high time consumption and low efficiency when multiple target objects need to be recognized. By deleting the standard target object features after sending them to the image acquisition terminal, storage space is saved. Target object recognition is performed based on the image to be recognized and the standard target object features sent by the image acquisition terminal, eliminating the need to compare the image to be recognized with all standard target object features in the database, reducing the number of comparisons, improving the efficiency of target object recognition, and lowering the cost of target object recognition.
[0074] Example 2
[0075] Figure 2The flowchart of another target object recognition method is provided for Embodiment 2 of the present invention. This embodiment can be applied to the case of target object recognition. The method can be executed by a target object recognition device, which can be implemented in hardware and / or software. The target object recognition device can be configured in an image acquisition terminal and used in conjunction with the target object recognition terminal.
[0076] like Figure 2 As shown, the method includes:
[0077] S210. Send at least one standard image to the target object recognition terminal, and receive standard target object features that match the standard image sent by the target object recognition terminal.
[0078] In this embodiment, after the image acquisition terminal obtains the standard image of the target object to be registered, it sends the standard image to the target object recognition terminal. The target object recognition terminal extracts features from the standard image and sends the obtained standard target object features to the image acquisition terminal. This process will not be described in detail here.
[0079] The image acquisition terminal acquires a standard image of the target object to be registered. Specifically, this can be done through the user interface of the image acquisition terminal in response to the registration request of the target object, by taking an image. During the image acquisition process, the target object's location range can be displayed through the user interface to ensure that the target object's position in the acquired standard image meets the requirements. After acquiring the image of the target object to be registered, image quality and other verifications can be performed; this process will not be elaborated upon here.
[0080] When the image acquisition device receives the standard target object features that match the standard image sent by the target object recognition terminal, the target object to be registered completes the information registration and is regarded as a registered target object.
[0081] Furthermore, the image acquisition device can acquire standard images of one or more target objects to be registered, and register one or more target objects. Understandably, even if one image acquisition device registers multiple target objects, because all target objects are distributed across multiple image acquisition devices, the number of target object comparisons can be reduced, thus improving the target object recognition efficiency.
[0082] In this embodiment, the image acquisition device saves the standard target object features sent by the target object recognition terminal locally. When the registered target object needs subsequent recognition, the image acquisition device sends the standard target object features along with the real-time acquired image to be recognized to the target object recognition terminal, thus achieving target object recognition. This method of saving and sending standard target object features by the image acquisition device saves storage space in the target object recognition terminal, reduces the number of target object comparisons, and improves target object recognition efficiency. Furthermore, since the target object recognition terminal does not store the standard target object features, but rather the image acquisition device does, this ensures the security and privacy of the target object data, especially when the image acquisition terminal is a mobile terminal of the target object to be recognized.
[0083] Furthermore, this embodiment, while performing S210, also includes: sending the target object identifier and device fingerprint information to the target object recognition terminal; S210 may further include: sending the image to be recognized, standard target object features, target object identifier, and device fingerprint information to the target object recognition terminal, so that the target object recognition terminal can perform target object recognition based on the image to be recognized, standard target object features, target object identifier, and device fingerprint information.
[0084] In this embodiment, when the image acquisition terminal registers a target object, it sends the target object identifier and device fingerprint information to the target object recognition terminal, which stores the target object identifier and device fingerprint information accordingly. When the image acquisition terminal recognizes the target object, it sends the image to be recognized, standard target object features, target object identifier, and device fingerprint information to the target object recognition terminal. The target object recognition terminal performs dual verification based on these four types of data, ensuring the accuracy and security of target object recognition.
[0085] S220. If a target object recognition instruction is detected, the image to be recognized is determined, and the image to be recognized and standard target object features are sent to the target object recognition terminal so that the target object recognition terminal can perform target object recognition based on the image to be recognized and standard target object features.
[0086] The target object recognition instruction is used to instruct the image acquisition terminal to acquire the image to be recognized. Specifically, the target object recognition instruction can be obtained from the user interface of the image acquisition terminal. The target object is identified by clicking the target object recognition button on the user interface, which triggers the target object recognition instruction.
[0087] After detecting a target object recognition command, the image acquisition device acquires an image of the target object to be recognized and verifies the image quality to meet the requirements, thus obtaining the image to be recognized. The image to be recognized, along with pre-stored standard target object features, is then sent to the target object recognition terminal.
[0088] It should be noted that since an image acquisition device can register multiple target objects, it can pre-store multiple standard target object features. When identifying a specific target object, the number of standard target object features sent along with the image to be identified can be one or more.
[0089] Specifically, in response to the user's selection of the target object to be identified through the user interface, the system can select the standard target object feature to be sent from a pre-stored set of standard target object features. Alternatively, all pre-stored standard target object features can be sent directly to the target object identification terminal. Since the number of standard target object features pre-stored by an image acquisition device is always less than the total number of standard target object features, even if an image acquisition device stores multiple standard target object features and sends all of them to the target object identification terminal during target object identification, it can still reduce the number of comparisons and improve the efficiency of target object identification compared to the database-based comparison in existing technologies.
[0090] Furthermore, after S220, it also includes: if it is determined that a task processing identifier sent by the target object recognition terminal has been received, then the task processing identifier is sent to the target object recognition terminal at preset time intervals to query the target object recognition result.
[0091] The above embodiments have provided an implementation method for target object recognition terminals to perform target object recognition based on task processing queues. Based on this, if the image acquisition terminal receives a task processing identifier, it can determine that the target object recognition terminal is currently recognizing the target object. In this embodiment, the target object recognition terminal can be periodically queried according to the task processing identifier until the target object recognition result is received from the target object recognition terminal.
[0092] In another optional embodiment, after receiving the task processing identifier, the system can wait for feedback on the target object recognition result from the target object recognition terminal. If no target object recognition result is received from the target object recognition terminal after a preset time period following the receipt of the task processing identifier, the system can either query the target object recognition result based on the task processing identifier, or indicate a recognition error. In this case, the image to be recognized can be redefined, and subsequent data transmission can proceed.
[0093] The technical solution of this invention involves sending a standard image to a target object recognition terminal via an image acquisition terminal, and receiving standard target object features corresponding to the standard image from the target object recognition terminal. When a target object needs to be identified through the image acquisition terminal, the image to be identified, along with the standard target object features previously sent by the target object recognition terminal, is sent to the target object recognition terminal, enabling the target object recognition terminal to identify the target object in the image to be identified. This solves the problems of decreased performance and efficiency in existing target object recognition methods that rely on comparison and matching, especially when the number of target objects stored in the target object database increases, and the high time consumption and low efficiency when multiple target objects need to be identified. By saving the standard target object features sent by the target object recognition terminal, the storage space of the target object recognition terminal can be saved. Furthermore, by sending the image to be identified along with the standard target object features to the target object recognition terminal when performing target recognition, the number of comparisons of the image to be identified can be reduced, improving the efficiency of target object recognition and reducing the cost of target object recognition.
[0094] Specific application scenario 1
[0095] This invention also provides a specific application scenario in which personnel attendance is achieved based on target object recognition through a target object recognition system. The target object recognition system includes an image acquisition terminal and a target object recognition terminal; in this application scenario, the image acquisition terminal is preferably a mobile terminal. Specifically, this application scenario is divided into two stages: target object registration and target object recognition.
[0096] During the target object registration phase, the target object to be registered enters a standard image and target object identifier through a mobile terminal. The mobile terminal then sends the standard image, target object identifier, and device fingerprint information to the target object recognition terminal.
[0097] The target object recognition terminal performs feature extraction on the standard image to obtain standard target object features, sends these features to the mobile terminal, and deletes the local standard target object features. Simultaneously, it binds the target object identifier and device fingerprint information and stores them accordingly. This completes the registration of the target object.
[0098] During the target object recognition stage, the mobile terminal collects the image of the target object to be recognized, generates an attendance request by combining the image to be recognized, standard target object features, target object identifier, and device fingerprint information, and sends it to the target object recognition terminal.
[0099] After receiving the attendance request, the target object recognition terminal generates a task processing identifier for this target object recognition task and saves the data to the task processing queue. The task processing identifier is then sent back to the mobile terminal.
[0100] After receiving the task processing identifier, the mobile terminal prompts the target object to be identified to be in attendance verification through the user interface.
[0101] The target object recognition terminal sequentially retrieves data corresponding to each target object recognition task from the task processing queue for verification. Specifically, it first checks whether the target object identifier and device fingerprint information are consistent with the binding information during target object registration. If they are, further comparison is performed; otherwise, the attendance result is determined to be a failure. Then, the features of the target object to be recognized extracted from the image to be recognized are compared 1:1 with the standard target object features to obtain the attendance result.
[0102] The target object recognition terminal sends the attendance results to the mobile terminal and deletes the image to be recognized, standard target object features, and device fingerprint information corresponding to this target object recognition task. It only saves the task processing identifier, attendance time, target object identifier, and attendance result of this target object recognition task.
[0103] The mobile terminal will display the attendance results through the user interface.
[0104] In this applicable scenario, the attendance method based on target object recognition stores standard target object features on the mobile terminal, increasing the storage capacity of the target object recognition terminal. The mobile terminal sends the image to be recognized and the standard target object features together to the target object recognition terminal, improving the traditional 1:N comparison mode to a 1:1 comparison mode, significantly improving recognition efficiency. The combination of these two aspects effectively improves attendance efficiency and reduces attendance costs.
[0105] Furthermore, the target object recognition terminal does not store standard target object features and other data; instead, the mobile terminal stores them, which effectively ensures user privacy and security and prevents the leakage of personal information.
[0106] Meanwhile, each user communicates with the target object recognition terminal through their mobile terminal and performs attendance through their own mobile terminal, which is convenient and efficient and avoids congestion at the attendance equipment during peak attendance periods.
[0107] Example 3
[0108] Figure 3 This is a schematic diagram of the structure of a target object recognition device provided in Embodiment 3 of the present invention.
[0109] like Figure 3As shown, the device is deployed on a target object recognition terminal, and the device includes:
[0110] The standard target object feature determination module 310 is used to determine the standard target object features that match the standard image based on a standard image sent by at least one image acquisition terminal.
[0111] The standard target object feature sending module 320 is used to send the standard target object features to the image acquisition terminal and delete the standard target object features;
[0112] The target object recognition module 330 is used to perform target object recognition based on the target object image and standard target object features sent by the target image acquisition terminal if it is determined that the target image acquisition terminal has received the image to be recognized and the standard target object features, and then send the target object recognition result to the target image acquisition terminal.
[0113] The technical solution of this invention involves a target object recognition terminal receiving a standard image sent by an image acquisition terminal, determining standard target object features matching the standard image, deleting the standard target object features after sending them to the image acquisition terminal, and then performing target object recognition on the image to be recognized and the target object recognition result back to the image acquisition terminal after receiving the image to be recognized and the standard target object features sent by the target image acquisition terminal. This solves the problems of performance and efficiency degradation in existing target object recognition methods that rely on comparison and matching, especially when the number of target objects stored in the target object database increases, and the high time consumption and low efficiency when multiple target objects need to be recognized. By deleting the standard target object features after sending them to the image acquisition terminal, storage space is saved. Target object recognition is performed based on the image to be recognized and the standard target object features sent by the image acquisition terminal, eliminating the need to compare the image to be recognized with all standard target object features in the database, reducing the number of comparisons, improving the efficiency of target object recognition, and lowering the cost of target object recognition.
[0114] Optionally, based on the above embodiments, the device may further include:
[0115] The target object identifier and device fingerprint information storage module is used to store the target object identifier and device fingerprint information sent by the image acquisition terminal accordingly;
[0116] Target object recognition module 330 includes:
[0117] The target object identifier and device fingerprint information judgment unit is used to determine whether the target object identifier and device fingerprint information match if it is determined that the image to be identified, standard target object features, target object identifier and device fingerprint information sent by the target image acquisition terminal are received.
[0118] The target object recognition unit is used to recognize the target object based on the image to be recognized and the standard target object features.
[0119] Based on the above embodiments, optionally, the target object recognition module 330 includes:
[0120] The task processing identifier determination unit is used to save the image to be identified and the standard target object features sent by the target image acquisition terminal to the task processing queue if it is determined that the image to be identified and the standard target object features are received, and to determine the task processing identifier that matches the image to be identified and the standard target object features.
[0121] The task processing identifier sending unit is used to send the task processing identifier to the target image acquisition terminal to prompt the target image acquisition terminal to identify the target object.
[0122] The target object recognition device provided in the embodiments of the present invention can execute the target object recognition method provided in any embodiment of the present invention, and has the corresponding functional modules and beneficial effects of the method execution.
[0123] Example 4
[0124] Figure 4 This is a schematic diagram of the structure of a target object recognition device provided in Embodiment 4 of the present invention.
[0125] like Figure 4 As shown, the device is deployed on a target object recognition terminal, and the device includes:
[0126] The standard image sending module 410 is used to send at least one standard image to the target object recognition terminal and receive standard target object features that match the standard image sent by the target object recognition terminal.
[0127] The image to be identified and standard target object feature sending module 420 is used to determine the image to be identified if a target object identification instruction is detected, and send the image to be identified and standard target object features to the target object identification terminal so that the target object identification terminal can identify the target object based on the image to be identified and standard target object features.
[0128] The technical solution of this invention involves sending a standard image to a target object recognition terminal via an image acquisition terminal, and receiving standard target object features corresponding to the standard image from the target object recognition terminal. When a target object needs to be identified through the image acquisition terminal, the image to be identified, along with the standard target object features previously sent by the target object recognition terminal, is sent to the target object recognition terminal, enabling the target object recognition terminal to identify the target object in the image to be identified. This solves the problems of decreased performance and efficiency in existing target object recognition methods that rely on comparison and matching, especially when the number of target objects stored in the target object database increases, and the high time consumption and low efficiency when multiple target objects need to be identified. By saving the standard target object features sent by the target object recognition terminal, the storage space of the target object recognition terminal can be saved. Furthermore, by sending the image to be identified along with the standard target object features to the target object recognition terminal when performing target recognition, the number of comparisons of the image to be identified can be reduced, improving the efficiency of target object recognition and reducing the cost of target object recognition.
[0129] Optionally, based on the above embodiments, the device may further include:
[0130] The target object identification and device fingerprint information sending module is used to send the target object identification and device fingerprint information to the target object identification terminal;
[0131] The image to be identified and the standard target object feature transmission module 420 includes:
[0132] The target object identification and device fingerprint information sending unit is used to send the image to be identified, standard target object features, target object identification, and device fingerprint information to the target object identification terminal, so that the target object identification terminal can identify the target object based on the image to be identified, standard target object features, target object identification, and device fingerprint information.
[0133] Optionally, based on the above embodiments, the device may further include:
[0134] The target object recognition result query module is used to send the task processing identifier to the target object recognition terminal at preset time intervals if it is determined that the task processing identifier sent by the target object recognition terminal has been received, so as to query the target object recognition result.
[0135] The target object recognition device provided in the embodiments of the present invention can execute the target object recognition method provided in any embodiment of the present invention, and has the corresponding functional modules and beneficial effects of the method execution.
[0136] Example 5
[0137] Figure 5 A schematic diagram of an electronic device 10 that can be used to implement embodiments of the present invention is shown. The electronic device is intended to represent various forms of digital computers, such as laptop computers, desktop computers, workstations, personal digital assistants, servers, blade servers, mainframe computers, and other suitable computers. The electronic device can also represent various forms of mobile devices, such as personal digital processors, cellular phones, smartphones, wearable devices (e.g., helmets, glasses, watches, etc.), and other similar computing devices. The components shown herein, their connections and relationships, and their functions are merely illustrative and are not intended to limit the implementation of the invention described and / or claimed herein.
[0138] like Figure 5 As shown, the electronic device 10 includes at least one processor 11 and a memory, such as a read-only memory (ROM) 12 or a random access memory (RAM) 13, communicatively connected to the at least one processor 11. The memory stores computer programs executable by the at least one processor. The processor 11 can perform various appropriate actions and processes based on the computer program stored in the ROM 12 or loaded from storage unit 18 into the RAM 13. The RAM 13 may also store various programs and data required for the operation of the electronic device 10. The processor 11, ROM 12, and RAM 13 are interconnected via a bus 14. An input / output (I / O) interface 15 is also connected to the bus 14.
[0139] Multiple components in electronic device 10 are connected to I / O interface 15, including: input unit 16, such as keyboard, mouse, etc.; output unit 17, such as various types of displays, speakers, etc.; storage unit 18, such as disk, optical disk, etc.; and communication unit 19, such as network card, modem, wireless transceiver, etc. Communication unit 19 allows electronic device 10 to exchange information / data with other devices through computer networks such as the Internet and / or various telecommunications networks.
[0140] Processor 11 can be a variety of general-purpose and / or special-purpose processing components with processing and computing capabilities. Some examples of processor 11 include, but are not limited to, a central processing unit (CPU), a graphics processing unit (GPU), various special-purpose artificial intelligence (AI) computing chips, various processors running machine learning model algorithms, a digital signal processor (DSP), and any suitable processor, controller, microcontroller, etc. Processor 11 performs the various methods and processes described above, such as target object recognition methods.
[0141] In some embodiments, the target object identification method may be implemented as a computer program tangibly contained in a computer-readable storage medium, such as storage unit 18. In some embodiments, part or all of the computer program may be loaded and / or installed on electronic device 10 via ROM 12 and / or communication unit 19. When the computer program is loaded into RAM 13 and executed by processor 11, one or more steps of the target object identification method described above may be performed. Alternatively, in other embodiments, processor 11 may be configured to perform the target object identification method by any other suitable means (e.g., by means of firmware).
[0142] Various embodiments of the systems and techniques described above herein can be implemented in digital electronic circuit systems, integrated circuit systems, field-programmable gate arrays (FPGAs), application-specific integrated circuits (ASICs), application-specific standard products (ASSPs), systems-on-a-chip (SoCs), payload-programmable logic devices (CPLDs), computer hardware, firmware, software, and / or combinations thereof. These various embodiments may include implementations in one or more computer programs that can be executed and / or interpreted on a programmable system including at least one programmable processor, which may be a dedicated or general-purpose programmable processor, capable of receiving data and instructions from a storage system, at least one input device, and at least one output device, and transmitting data and instructions to the storage system, the at least one input device, and the at least one output device.
[0143] Computer programs used to implement the methods of the present invention may be written in any combination of one or more programming languages. These computer programs may be provided to a processor of a general-purpose computer, a special-purpose computer, or other programmable data processing device, such that when executed by the processor, the computer programs cause the functions / operations specified in the flowcharts and / or block diagrams to be performed. The computer programs may be executed entirely on a machine, partially on a machine, or as a standalone software package, partially on a machine and partially on a remote machine, or entirely on a remote machine or server.
[0144] In the context of this invention, a computer-readable storage medium can be a tangible medium that may contain or store a computer program for use by or in conjunction with an instruction execution system, apparatus, or device. A computer-readable storage medium may include, but is not limited to, electronic, magnetic, optical, electromagnetic, infrared, or semiconductor systems, apparatus, or devices, or any suitable combination thereof. Alternatively, a computer-readable storage medium may be a machine-readable signal medium. More specific examples of machine-readable storage media include electrical connections based on one or more wires, portable computer disks, hard disks, random access memory (RAM), read-only memory (ROM), erasable programmable read-only memory (EPROM or flash memory), optical fibers, portable compact disk read-only memory (CD-ROM), optical storage devices, magnetic storage devices, or any suitable combination thereof.
[0145] To provide interaction with a user, the systems and techniques described herein can be implemented on an electronic device having: a display device (e.g., a CRT (cathode ray tube) or LCD (liquid crystal display) monitor) for displaying information to the user; and a keyboard and pointing device (e.g., a mouse or trackball) through which the user provides input to the electronic device. Other types of devices can also be used to provide interaction with the user; for example, feedback provided to the user can be any form of sensory feedback (e.g., visual feedback, auditory feedback, or tactile feedback); and input from the user can be received in any form (including sound input, voice input, or tactile input).
[0146] The systems and technologies described herein can be implemented in computing systems that include backend components (e.g., as data servers), or computing systems that include middleware components (e.g., application servers), or computing systems that include frontend components (e.g., user computers with graphical user interfaces or web browsers through which users can interact with implementations of the systems and technologies described herein), or any combination of such backend, middleware, or frontend components. The components of the system can be interconnected via digital data communication of any form or medium (e.g., communication networks). Examples of communication networks include local area networks (LANs), wide area networks (WANs), blockchain networks, and the Internet.
[0147] A computing system can include clients and servers. Clients and servers are generally located far apart and typically interact through communication networks. The client-server relationship is created by computer programs running on the respective computers and having a client-server relationship with each other. The server can be a cloud server, also known as a cloud computing server or cloud host, which is a hosting product within the cloud computing service system to address the shortcomings of traditional physical hosts and VPS services, such as high management difficulty and weak business scalability.
[0148] It should be understood that the various forms of processes shown above can be used, with steps reordered, added, or deleted. For example, the steps described in this invention can be executed in parallel, sequentially, or in different orders, as long as the desired result of the technical solution of this invention can be achieved, and this is not limited herein.
[0149] The specific embodiments described above do not constitute a limitation on the scope of protection of this invention. Those skilled in the art should understand that various modifications, combinations, sub-combinations, and substitutions can be made according to design requirements and other factors. Any modifications, equivalent substitutions, and improvements made within the spirit and principles of this invention should be included within the scope of protection of this invention.
Claims
1. A method for identifying a target object, characterized in that, The method is executed by a target object recognition terminal, and the method includes: Based on a standard image sent by at least one image acquisition terminal, determine the features of a standard target object that match the standard image; The standard target object features are sent to the image acquisition terminal, and the standard target object features are then deleted. If it is determined that the image to be identified and the standard target object features sent by the target image acquisition terminal have been received, then the target object is identified based on the image to be identified and the standard target object features, and the target object identification result is sent to the target image acquisition terminal.
2. The method according to claim 1, characterized in that, The method further includes: The target object identifier and device fingerprint information sent by the image acquisition terminal are stored accordingly; If it is determined that the image to be identified and the standard target object features sent by the target image acquisition terminal have been received, then target object identification is performed based on the image to be identified and the standard target object features, including: If it is determined that the image to be identified, standard target object features, target object identifier, and device fingerprint information sent by the target image acquisition terminal have been received, then it is determined whether the target object identifier and device fingerprint information match. If so, target object identification is performed based on the image to be identified and the features of the standard target object.
3. The method according to claim 1, characterized in that, If it is determined that the image to be identified and the standard target object features sent by the target image acquisition terminal have been received, then target object identification is performed based on the image to be identified and the standard target object features, including: If it is determined that the image to be identified and the standard target object features sent by the target image acquisition terminal have been received, the image to be identified and the standard target object features are saved to the task processing queue, and a task processing identifier that matches the image to be identified and the standard target object features is determined. The task processing identifier is sent to the target image acquisition terminal to prompt the target image acquisition terminal to identify the target object.
4. A method for identifying a target object, characterized in that, The method is executed by an image acquisition terminal, and the method includes: At least one standard image is sent to the target object recognition terminal, and the target object recognition terminal sends standard target object features that match the standard image. If a target object recognition command is detected, the image to be recognized is determined, and the image to be recognized and standard target object features are sent to the target object recognition terminal so that the target object recognition terminal can perform target object recognition based on the image to be recognized and the standard target object features.
5. The method according to claim 4, characterized in that, The method further includes: Send the target object identifier and device fingerprint information to the target object recognition terminal; The image to be identified and standard target object features are sent to the target object recognition terminal, so that the target object recognition terminal can perform target object recognition based on the image to be identified and the standard target object features, including: The image to be identified, standard target object features, target object identifier, and device fingerprint information are sent to the target object identification terminal so that the target object identification terminal can identify the target object based on the image to be identified, standard target object features, target object identifier, and device fingerprint information.
6. The method according to claim 4, characterized in that, After sending the image to be identified and the standard target object features to the target object recognition terminal, the process also includes: If it is confirmed that a task processing identifier has been received from the target object recognition terminal, the task processing identifier will be sent to the target object recognition terminal at preset time intervals to query the target object recognition results.
7. A target object recognition device, characterized in that, The device is deployed on a target object recognition terminal, and the device includes: A standard target object feature determination module is used to determine standard target object features that match the standard image based on a standard image sent by at least one image acquisition terminal. A standard target object feature sending module is used to send the standard target object features to the image acquisition terminal and delete the standard target object features; The target object recognition module is used to identify the target object based on the image to be recognized and the standard target object features sent by the target image acquisition terminal, and to send the target object recognition result to the target image acquisition terminal if it is determined that the image to be recognized and the standard target object features have been received.
8. A target object recognition device, characterized in that, The device is deployed in an image acquisition terminal, and the device includes: A standard image sending module is used to send at least one standard image to a target object recognition terminal, and to receive standard target object features that match the standard image sent by the target object recognition terminal; The module for sending the image to be identified and the standard target object features is used to determine the image to be identified if a target object identification instruction is detected, and to send the image to be identified and the standard target object features to the target object identification terminal so that the target object identification terminal can identify the target object based on the image to be identified and the standard target object features.
9. An electronic device comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, characterized in that, When the processor executes the program, it implements the target object recognition method as described in any one of claims 1-7.
10. A storage medium for storing computer-executable instructions, characterized in that, The computer-executable instructions, when executed by a computer processor, are used to perform the target object recognition method as described in any one of claims 1-7.