Method and device for acquiring image, electronic equipment and computer program product

Abstract

The embodiment of the invention relates to a method and device for collecting images, electronic equipment and a computer program product. The method includes acquiring camera information and device information, and determining a driver for a camera for installation on a device based on the camera information and the device information. According to the method, based on input of a user on a user interface, an acquisition strategy related to image acquisition is configured. In addition, the method also includes acquiring images for the AI model by controlling cameras of different brands, models, and types with a device based on the acquisition strategy. Therefore, according to the embodiment of the invention, a user can select a camera and a matched lens suitable for application through the graphical user interface without mastering complex programming skills, and meanwhile, parameter adjustment and control are carried out on the selected camera through the graphical user interface, so that the threshold of data acquisition is reduced, and the user experience is improved. And the efficiency and reliability of image acquisition are improved, and data support is provided for labeling, training and deployment of the AI model.

Description

Technical Field

[0001] The present application relates to the field of computer technology, and more particularly to a method, device, electronic device and computer program product for acquiring images. Background Art

[0002] With the development of industrial automation and intelligence, the importance of artificial intelligence (AI) models is becoming increasingly prominent, becoming a key technology to promote innovation and development in various industries. For example, machine vision models play an important role in efficiently processing and analyzing image data, realizing core functions such as accurate detection, recognition and positioning, and are widely used in many fields.

[0003] Data collection is an indispensable part of AI model construction, and its importance is reflected in many aspects. By collecting a large amount of diverse data, artificial intelligence models can obtain sufficient training materials, laying the foundation for subsequent learning and optimization. Whether it is image processing, speech recognition, or text analysis, data collection runs through the entire development process and affects the performance and applicability of the model. Summary of the invention

[0004] Embodiments of the present disclosure provide a method, an apparatus, an electronic device, and a computer program product for acquiring an image.

[0005] According to a first aspect of the present disclosure, a method for capturing images is provided. The method includes obtaining camera information of a camera and device information of a device to which the camera is connected. The method also includes determining a driver for the camera to be installed on the device based on the camera information and the device information. The method also includes configuring, after installing the driver, a capture strategy related to the captured image based on user input on a user interface, the capture strategy being related to the application scenario of the AI ​​model for which the captured image is used. In addition, the method also includes capturing images for the AI ​​model by controlling the camera using a device based on the capture strategy.

[0006] According to a second aspect of the present disclosure, a device for capturing images is provided. The device includes an information acquisition module configured to obtain camera information of a camera and device information of a device to which the camera is connected. The device also includes a driver determination module configured to determine a driver for the camera to be installed on the device based on the camera information and the device information. The device also includes a policy configuration module configured to configure, after installing the driver, a capture strategy related to the captured image based on user input on a user interface, wherein the capture strategy is related to the application scenario of the artificial intelligence (AI) model for which the captured image is used. In addition, the device also includes an image capture module configured to capture images for the AI ​​model by controlling the camera using a device based on the capture strategy.

[0007] According to a third aspect of the present disclosure, an electronic device is provided, comprising a processor and a memory coupled to the processor, wherein the memory has instructions stored therein, and when the instructions are executed by the processor, the electronic device executes the method according to the first aspect.

[0008] In a fourth aspect of the present disclosure, a computer readable storage medium is provided. The computer program product is tangibly stored on a non-transitory computer readable medium and includes computer executable instructions, which when executed cause a computer to perform the steps of the method of the first aspect of the present disclosure.

[0009] The purpose of this Summary is to introduce a selection of concepts in a simplified form that are further described in the Detailed Description below. This Summary is not intended to identify key features or essential features of the claimed subject matter, nor is it intended to limit the scope of the claimed subject matter. BRIEF DESCRIPTION OF THE DRAWINGS

[0010] The above and other features, advantages and aspects of the embodiments of the present disclosure will become more apparent with reference to the following detailed description in conjunction with the accompanying drawings. In the accompanying drawings, the same or similar reference numerals represent the same or similar elements, wherein:

[0011] Figure 1 A schematic diagram showing an example environment in which devices and / or methods according to embodiments of the present disclosure may be implemented;

[0012] Figure 2 A flow chart of a method for collecting data according to an embodiment of the present disclosure is shown;

[0013] Figure 3A A schematic diagram showing the architecture of an intelligent image acquisition system according to an embodiment of the present disclosure;

[0014] Figure 3B A schematic diagram showing a process of camera matching and recommendation according to an embodiment of the present disclosure is shown;

[0015] Figure 4 A schematic diagram showing a process of module interaction according to an embodiment of the present disclosure;

[0016] Figure 5 A schematic diagram showing device connections according to an embodiment of the present disclosure;

[0017] Figure 6 A block diagram showing a device for acquiring an image according to an embodiment of the present disclosure; and

[0018] Figure 7 A block diagram of an electronic device according to an embodiment of the present disclosure is shown.

[0019] Throughout the drawings, the same or similar reference numbers denote the same or similar elements. DETAILED DESCRIPTION

[0020] It is understandable that before using the technical solutions disclosed in the embodiments of the present disclosure, the type, scope of use, usage scenarios, etc. of the personal information (such as voice) involved in the present disclosure should be informed to the user and the user's authorization should be obtained in an appropriate manner in accordance with relevant laws and regulations.

[0021] Embodiments of the present disclosure will be described in more detail below with reference to the accompanying drawings. Although certain embodiments of the present disclosure are shown in the accompanying drawings, it should be understood that the present disclosure can be implemented in various forms and should not be construed as being limited to the embodiments described herein, which are instead provided for a more thorough and complete understanding of the present disclosure. It should be understood that the drawings and embodiments of the present disclosure are only for exemplary purposes and are not intended to limit the scope of protection of the present disclosure.

[0022] In the description of the embodiments of the present disclosure, the term "including" and similar terms should be understood as open inclusion, that is, "including but not limited to". The term "based on" should be understood as "based at least in part on". The term "one embodiment" or "the embodiment" should be understood as "at least one embodiment". The terms "first", "second", etc. may refer to different or the same objects, unless explicitly stated. Other explicit and implicit definitions may also be included below.

[0023] As mentioned earlier, data collection is crucial in the training and application of artificial intelligence models. For example, when training machine vision models, it is essential to collect high-quality and diverse image data. In the related art, when collecting image data for machine vision models, users need to program the image acquisition hardware device (e.g., camera) used. This usually involves calling specific driver software interfaces to configure camera parameters (such as shutter speed, white balance, resolution, etc.), and designing acquisition processes (such as single acquisition or continuous acquisition). This process not only has high requirements on the user's programming ability and hardware knowledge, but also requires a lot of time for program development and testing, which increases the complexity and cost of the operation.

[0024] To this end, the embodiment of the present disclosure proposes a solution for capturing images. The system first determines the camera selection range based on the user's answers to the camera selection question through the "question-based case generation module" by asking questions. Then the user determines the camera model to be used in the end. After the user receives the camera hardware, the system first obtains the camera information and the device information connected to the camera, and based on the above information, determines the camera driver for installation on the device, and then configures the acquisition strategy related to the image acquisition based on the user input on the user interface, and finally uses the device to control the camera to complete the image acquisition based on the acquisition strategy.

[0025] Therefore, through the embodiments of the present disclosure, it is possible to realize automatic identification and calling of cameras of different brands and models, and users can adjust and control the parameters of cameras of different brands and models through a graphical user interface without having to master complex programming skills. This method simplifies the operational process of image data acquisition, allowing users to flexibly complete tasks such as dynamic adjustment of camera parameters, real-time control of single or continuous acquisition, local storage of image data, and data upload after acquisition. The solution of the present disclosure not only lowers the threshold for data acquisition, but also improves the efficiency and reliability of image acquisition, providing high-quality data support for the annotation, training and deployment of artificial intelligence models.

[0026] Figure 1 Schematic diagram of an example environment in which the device and / or method according to an embodiment of the present disclosure may be implemented. Figure 1 As shown, the example environment 100 may include a device 110, which may be a user terminal, a mobile device, a computer, etc., or a computing system, a single server, a distributed server, or a cloud-based server. An image acquisition system 112 may be deployed on the device 110, which may obtain camera information 116 of the camera 114 and device information 118 of the device 110 to which the camera 114 is connected. For example, the camera information 116 may include the brand and model of the camera. The device information 118 may include the operating system type, operating system version, hardware configuration (such as processor type, memory size), etc. of the device 110. In some embodiments, the image acquisition system 112 may also be deployed on other devices, such as a remote server, and communicate with the device 110 through a network to achieve remote configuration.

[0027] The image acquisition system 112 can determine the driver 120 for the camera 114 to be installed on the device 110 based on the camera information 116 and the device information 118. For example, the system can filter out the driver version compatible with the current device environment by analyzing the camera brand, model, and the operating system type and version of the device. Subsequently, the system can automatically download, install and load the driver so that the device 110 can correctly call the function of the camera 114 and realize the dynamic configuration and control of its parameters. If the operating system does not meet the requirements, the system can recommend to the user and ask whether to install a suitable system image. If the user chooses to install the system image, the deployment system can automatically download, install and deploy a suitable operating system and corresponding driver and other supporting software versions according to the current hardware information, so as to achieve the purpose of being able to use the device to correctly call the camera and realize the dynamic configuration and control of its parameters. For example, when the operating system of the device 110 is Windows 7, and the driver required by the camera 114 only supports Windows 10, the system will detect that the operating system of the device cannot meet the operating requirements of the camera driver. At this time, the system can prompt the user to install a compatible target operating system image (such as Windows 10) through the user interface, and provide relevant driver support at the same time. In this way, even if the current operating system cannot meet the requirements, the driver installation and deployment can still be completed by replacing the operating system.

[0028] After installing the driver 120, the image acquisition system 112 can configure an acquisition strategy 126 related to the acquired image based on the input of the user 122 on the user interface 124, and the acquisition strategy is related to the application scenario of the AI ​​model for which the acquired image is used. For example, the acquisition strategy may include acquisition parameters and acquisition processes, and the user can intuitively set the acquisition parameters through the visualization tools of the user interface 124, such as adjusting the resolution, frame rate, exposure time and other parameters. The acquisition process refers to the specific operation sequence for performing the image acquisition task, such as camera initialization, acquisition mode selection, real-time monitoring and adjustment, and data storage and processing.

[0029] The acquisition strategy varies according to the specific application scenario of the AI ​​model. For example, in the application of visual inspection of product defects on the production line, the acquisition strategy needs to support a continuous acquisition mode with a high frame rate, while optimizing the resolution to ensure that the acquired image can clearly display the detailed defects on the surface of the product. In unmanned driving applications, the acquisition strategy may require the synchronous acquisition of multi-view images and adjust the camera parameters in combination with dynamic lighting conditions to capture comprehensive environmental perception data. These application scenarios have different requirements for image quality, acquisition speed, and data storage. The image acquisition system 112 ensures that these diverse needs are met by flexibly configuring the acquisition strategy.

[0030] The image acquisition system 112 can acquire images for the AI ​​model by controlling the camera 114 using the device 110 based on the acquisition strategy 126. The acquired image data can be uploaded to the annotation platform as required to generate high-quality annotation data for training the AI ​​model. In addition, these image data can also be directly applied to the trained AI model for reasoning and real-time decision-making, thereby supporting the realization of a variety of practical application scenarios.

[0031] It should be understood that the architecture and functions in the example environment 100 are described for exemplary purposes only and do not imply any limitation on the scope of the present disclosure. Embodiments of the present disclosure may also be applied to other environments with different structures and / or functions.

[0032] The following will combine Figures 2 to 7 The process according to the embodiment of the present disclosure is described in detail. For ease of understanding, the specific data mentioned in the following description are exemplary and are not intended to limit the scope of protection of the present disclosure. It is understood that the embodiments described below may also include additional actions not shown and / or the actions shown may be omitted, and the scope of the present disclosure is not limited in this respect.

[0033] Figure 2 FIG. 2 is a flow chart of a method 200 for collecting data according to an embodiment of the present disclosure. At block 202, camera information of a camera and device information of a device to which the camera is connected may be obtained. For example, referring to Figure 1 , the image acquisition system 112 may obtain the camera information 116 of the camera 114 and the device information 118 of the device 110 to which the camera is connected. At block 204, a driver for the camera to be installed on the device may be determined based on the camera information and the device information. Figure 1 The image acquisition system 112 may determine a driver 120 for the camera 114 to be installed on the device 110 based on the camera information 116 and the device information 118 .

[0034] At block 206, after the driver is installed, based on the user input on the user interface, a collection strategy related to the collected image may be configured, the collection strategy being related to the application scenario of the artificial intelligence AI model for which the collected image is used. Figure 1 , the image acquisition system 112 can configure an acquisition strategy 126 related to the acquired image based on the input of the user 122 on the user interface 124 after installing the driver 120, and the acquisition strategy 126 is related to the application scenario of the artificial intelligence AI model for which the acquired image is used. At box 208, the image for the AI ​​model can be acquired by using the device to control the camera based on the acquisition strategy. For example, referring to Figure 1The image acquisition system 112 can acquire images for the AI ​​model by controlling the camera 114 using the device 110 based on the acquisition strategy 126.

[0035] Therefore, according to the method 200 of the embodiment of the present disclosure, it is possible to realize automatic identification and calling of cameras of different brands and models, and users can adjust and control the parameters of the camera through a graphical user interface without having to master complex programming skills. This method enables users to easily collect image data, such as dynamic adjustment of camera parameters, real-time control of continuous or single acquisition, local storage of image data, and data upload function after acquisition. The solution of the present disclosure not only lowers the threshold for data acquisition, but also improves the efficiency and reliability of image acquisition, and provides high-quality data support for the annotation, training and deployment of artificial intelligence models.

[0036] Figure 3A FIG. 3 is a schematic diagram showing an architecture 300 of an intelligent image acquisition system according to an embodiment of the present disclosure. Figure 3A As shown, the intelligent image acquisition system 302 may include a demand analysis module 304, a hardware recommendation module 306, a UI control interface 308, a camera driver library 310, a hardware compatibility information library 312, and an image synchronization module 314. The demand analysis module 304 can also be called a question-based case generation module, and its main function is to inquire about the user's application requirements through interactive questioning, and recommend suitable image acquisition hardware devices to the user accordingly. Specifically, this module helps users quickly complete hardware selection by asking users questions related to application scenarios, combining the user's actual needs, the hardware requirements installed, and the project budget. This question-based interactive design not only lowers the user's usage threshold, but also provides personalized hardware recommendations based on the needs of different usage scenarios.

[0037] The demand analysis module 304 guides the user to two branch processes based on whether the user needs to use the deep learning model provided by the platform. For users who need to use the deep learning model provided by the platform, the demand analysis module 304 can screen out image acquisition hardware devices compatible with the platform and the deployed hardware based on the deployment hardware platform parameters supported by the platform (such as PC, cloud computing, embedded system, etc.) and the type of deep learning model (such as image recognition, object detection or image segmentation), to ensure that the selected device can meet the subsequent deployment requirements. In addition, after preliminarily screening out the supported image data acquisition sensor types, the demand analysis module 304 will continue to ask the user for other demand parameters through a series of follow-up questions, such as image color type (color / grayscale, etc.), minimum target recognition object (used to determine the minimum resolution parameter of the sensor), target recognition object motion state (moving / fixed, such as the maximum moving speed needs to be determined in the moving state), data acquisition minimum frame rate, sensor working distance, etc. as reference indicators for image sensor selection.

[0038] For users who do not need to use the deep learning model provided by the platform, the demand analysis module 304 will directly use the user's application requirements (such as the color type of the image, the minimum recognition size of the target object, the motion state of the object, the minimum frame rate of data acquisition, and the working distance of the sensor, etc.) as screening criteria to screen camera devices that meet these technical indicators and the hardware platform required for deployment (such as PC, cloud computing or embedded system, etc.).

[0039] After completing the screening of technical indicators, the intelligent image acquisition system 302 will prompt the user to enter the budget range of the project, and the hardware recommendation module 306 will optimize the screening results in combination with the budget, and finally recommend hardware devices with balanced performance and cost to the user. In this way, the efficiency and accuracy of hardware selection are improved, while ensuring that the recommendation results can not only meet the user's functional requirements, but also have reasonable costs, thereby optimizing the user experience and providing reliable support for subsequent image acquisition work.

[0040] The UI control interface 308 can provide users with a graphical human-computer interaction interface, which is convenient for users to intuitively set and operate various parameters and functions related to image acquisition. The UI control interface 308 is mainly used to set the acquisition parameters that the camera supports adjustment, including but not limited to shutter speed, exposure time, resolution, frame rate, color type, and other parameters related to the acquired image. In addition, the user can select and adjust the image acquisition process through this interface, such as single acquisition or continuous acquisition, dynamically adjust the acquisition parameters, or perform a series of operations in combination with different scene requirements, such as saving the acquired image to a specified location, transferring it to the AI ​​model service for processing (such as image segmentation), or directly calling the AI ​​model to process the image, etc., thereby meeting the acquisition requirements of different application scenarios. Acquisition parameters and acquisition processes can be collectively referred to as acquisition strategies.

[0041] In addition to the parameter setting function, the UI control interface 308 also supports the storage and management of captured images. Through this module, users can save the captured images to a local storage device, and can upload the stored images to a matching annotation platform through built-in functions, which is convenient for subsequent data annotation and deep learning model training. Through the UI control interface 308, users can complete the camera control and image acquisition tasks without having a complex technical background. Its intuitive operating interface and flexible functional design greatly reduce the use threshold of the system, making the image acquisition process more convenient and efficient, while ensuring the adaptability of the system in a variety of application scenarios.

[0042] The camera driver library 310 in the intelligent image acquisition system 302 can provide adaptive driver support for the camera to ensure that cameras of different brands, models and interface types can operate normally in multiple operating system environments. The camera driver library 310 can be dynamically adjusted according to the camera types supported by the system, and stores all supported camera drivers and related codes required to call the camera. Through this module, automatic recognition and driver adaptation of the connected camera connected to the device can be achieved, so that the user can directly operate the camera through the UI control interface 308 to complete the image acquisition task.

[0043] The camera driver library 310 is adapted to the driver requirements of different operating systems (such as Windows, Linux, macOS, and embedded systems, etc.). Driver versions that support various mainstream operating systems are pre-installed in the driver library. By automatically detecting the operating system type and camera type of the current device, the adapted driver is selected and called. This ensures the compatibility of the intelligent image acquisition system 302 in a multi-platform environment, allowing it to be flexibly applied to different hardware configurations and operating system environments. In addition, the camera driver library 310 has dynamic expansion capabilities and can support new camera types and models. For example, when a new camera is added to the system, the driver library can support the newly added camera by updating or expanding it, thereby enhancing the adaptability and expansion capabilities of the system.

[0044] Since different cameras require specific drivers under different operating system environments, when the system detects the user's camera, it can obtain information such as the camera's brand, model, interface type, and the device's motherboard type, acquisition card configuration, and operating system information. Based on the above information, the driver library 310 can filter out drivers that are compatible with the current hardware and operating system environment, and recommend the most suitable driver to the user through the user interface 308. After the user confirms the recommended driver, the system will automatically complete the download, installation, and call of the driver, so that the camera can operate normally and operate through the UI control interface 308. If the operating system does not meet the deployment requirements, the system can prompt the user to update the appropriate version of the operating system. If the user agrees to update the operating system, the UI can guide the user to complete the installation of the appropriate version of the operating system. If the system cannot automatically identify the specific model of the camera, the camera driver library 310 will prompt the user to manually select the camera model and install the corresponding driver according to the user's selection, thereby achieving support for unrecognized cameras. With the support of the camera driver library 310, the intelligent image acquisition system 302 can realize automatic recognition and calling of cameras of different brands and models, provide users with efficient camera access and operation experience, significantly reduce the technical threshold of hardware compatibility, and enable users to easily connect the camera to the device and complete high-quality image acquisition.

[0045] The hardware compatibility information library 312 can be used to store and manage information related to the hardware deployment platform supported by the system. It contains detailed system information of all system compatible hardware platforms, including but not limited to PC models (and corresponding CPU, GPU and motherboard information), embedded system motherboard models, embedded processor information, operating system versions, and software environment configurations required for deploying deep learning models. The hardware compatibility information library 312 works in collaboration with other modules (such as the demand analysis module 304 and the hardware recommendation module 306) to support users in selecting suitable hardware deployment platforms based on specific application requirements and hardware conditions. For example, when a user specifies the use of a specific deep learning model, the system can query the hardware compatibility information library 312 to retrieve the hardware platform that meets the model operation requirements, and provide the user with the best hardware selection in combination with the budget and other technical indicators entered by the user.

[0046] In addition, the intelligent image acquisition system 302 also includes an image synchronization module 314. The main function of the image synchronization module 314 is to synchronously upload and manage the acquired image data, so that the user can quickly connect with the annotation platform after the image acquisition is completed. For example, the image synchronization module 314 can provide a one-key synchronization function through the UI interface, and the user can log in to his personal account in the system and select the image data to be synchronized. During the image upload process, the user can quickly select all images to be uploaded through the one-key select all function. After confirming the image data, the user can upload the selected image data to the matching annotation platform through one-key operation.

[0047] In addition, the system can mark the upload status of the image and display it separately in the interface, so that users can distinguish between uploaded and unuploaded images, and select images to be uploaded individually or in batches. When uploading images, the system can automatically identify uploaded images. If the user selects an image that has been uploaded, the system will confirm with the user whether it needs to be uploaded again. If the user selects "no need to upload repeatedly", the system will not upload duplicate images to ensure efficient management and storage of image data. On the other hand, if the user selects "repeated upload", the system can upload all user-selected images, including duplicate and / or non-duplicate images, after confirming with the user again. In this process, the system can prompt the user through the user interface that using the same image for model training may lead to a decrease in the model training effect, and it is only recommended to upload repeatedly in specific circumstances such as debug or data transformation. In addition, the system can support the total count function of the collected images. For example, the total number of images that the user has collected can be counted and displayed in real time for the user to view. In addition, in the scenario of multiple collections and batch uploads, the system can display the number of uploaded images, so that users can intuitively understand the upload progress and data synchronization.

[0048] Figure 3BA schematic diagram of a camera matching and recommendation process 300B according to an embodiment of the present disclosure is shown. At box 322, the user logs in to the demand analysis module. As mentioned above, the demand analysis module is also called a question-based case generation module, which mainly helps users quickly select cameras suitable for project applications by asking users application-related questions, combining user application scenarios, hardware requirements, etc. At box 324, the demand analysis module can prompt the user to select a parameter-based hardware recommendation method or a scene-based hardware recommendation method through the UI interface. For example, the system can provide "select camera kits and supporting deployment hardware based on application scenario parameters and budget", or "directly recommend camera kits and deployment hardware by the system based on the usage scenario category". If the user selects a scenario-based recommendation at box 324, the process proceeds to box 326 to prompt the user to select a usage scenario. The scene categories preset by the system may include but are not limited to: factory automation, medical and life sciences, retail, security, transportation, logistics, agriculture, sports, education and others. At box 328, if the user selects a preset scenario, proceed to box 330, and directly recommend the corresponding hardware equipment to the customer based on one or more successful case configurations and corresponding costs in similar fields built into the system, so that the user can compare and choose. For example, the system can store hardware combinations used in different cases, so that if the user selects the corresponding usage scenario, one or more stored hardware combinations and corresponding costs can be quickly recommended. Return to box 328, if the user's application field is selected as "other", proceed to box 332, and prompt the user to describe the scenario to be used through the UI interface. For example, the "Application Case Description" option provided by the UI interface can allow the user to simply explain his or her application field and needs, and then access the background expert system at box 334 for analysis, and then obtain a suitable hardware combination. In addition, even if the user selects a preset scenario, after completing the recommendation, the user can still be prompted at box 336 through the UI interface whether to make an expert recommendation.

[0049] Returning to box 324, if the user selects "Select camera kit and supporting deployment hardware according to application scenario parameters and budget", the system proceeds to box 338, and the system guides the user to answer questions according to the prompts of the UI interface. The system guides the user to enter more detailed information, such as spectral range, working distance, minimum size of the target object, motion state (fixed or moving), maximum moving speed of the target object, etc., based on the usage scenario selected or described by the user, combined with specific technical requirements and camera parameter requirements. In some embodiments, the user can also be asked through the UI interface whether the distance of the target object relative to the camera changes during use, so that the lens recommendation can be made after the camera equipment is determined.

[0050] At box 340, the system can recommend camera devices based on the user's response and provide a recommendation explanation. For example, based on the application scenario selected by the user and the specific technical indicator requirements entered, combined with the camera performance parameters, cost budget constraints, and system compatibility requirements, qualified camera devices can be recommended, and recommendation results can be generated and displayed to the user through a graphical user interface. In some embodiments, a detailed recommendation explanation can be provided at the same time to help the user understand the basis for the recommendation and make a choice. For example, the recommendation explanation can include the reason for the recommendation, the camera features section, the applicable scenario description section, and alternatives. In addition, in some embodiments, if there is no suitable recommended device, feedback information can be displayed in the user interface. For example, the user is prompted that "there is currently no recommended device", and the user is advised to adjust the required parameters, such as resolution, frame rate, etc., to expand the range of choices.

[0051] For example, in the reason for recommendation section, you can explain how the recommended camera meets the application scenarios and technical requirements specified by the user, and specifically explain the matching of the camera in key parameters such as resolution, frame rate, spectral range, and interface type. In the camera features section, you can list the main technical parameters and advantages of the recommended camera in detail. In the applicable scenario description section, you can explain which specific application scenarios the recommended camera is suitable for, such as defect detection in industrial inspection scenarios, high-precision image capture in medical imaging scenarios, etc., to ensure that users can make judgments based on actual needs. In addition, in order to meet the diverse needs of users, the system can also provide possible alternatives. For example, camera devices with similar performance parameters but lower cost or functions that are more suitable for other specific scenarios can be recommended, so that users can choose camera devices that better match their own situations.

[0052] At box 342, it can be determined through the UI interface whether the user has a camera that meets the requirements. For example, the UI interface can be used to guide the user to answer whether he already has a camera device in the recommended list that meets the use requirements of the case. If the user already has a camera device that meets the requirements, proceed to box 344. If the user does not have a camera device that meets the requirements, proceed to box 346. At box 346, the user can be prompted to enter a cost budget and filter camera devices. For example, the UI interface can be used to guide the user to enter a cost budget range for the project so that the system can further filter the optional camera devices based on the budget constraints. After the screening is completed, the screening results can be displayed to the user through the UI interface, including detailed information on the recommended equipment and corresponding budget specifications.

[0053] In some embodiments, after determining the camera, the system can further recommend lens solutions that match the selected camera to meet the user's specific application needs. For example, in the demand analysis module, the system automatically screens and recommends suitable lenses based on the user's answers to the scene and technical parameters, combined with the camera model and application requirements. The recommended lens solutions may include fixed focal length lenses, zoom lenses, autofocus lenses, or integrated cameras, and provide the best choice based on the technical requirements of the application scenario. In some embodiments, the camera lens can be screened based on the cost budget entered by the user. In some embodiments, a recommendation description for the recommended lens can be displayed in the user interface.

[0054] Figure 4 A schematic diagram of a process 400 of module interaction according to an embodiment of the present disclosure is shown. The demand analysis module 402 is deployed in an online interactive interface. Users can log in to the demand analysis module 402 and gradually input their application requirements through questions prompted by the system, such as image acquisition scenarios, hardware deployment environments, and functional requirements. The system can automatically match and recommend hardware and software devices suitable for the user's application based on the answers provided by the user, combined with the data call hierarchy and logic.

[0055] For example, the demand analysis module 402 can search and match suitable image acquisition cameras, hardware deployment platforms, and deep learning models based on user needs. The matching recommendation results are based on the hardware compatibility information library and camera driver library preset in the system to ensure that the recommended devices can meet the user's technical requirements and are compatible with the subsequent deployment environment. In some embodiments, the demand analysis module 402 can support users to select recommended software and hardware modules through online inquiry, and can further implement online procurement services. This not only simplifies the user's selection process, but also improves the efficiency of hardware and software matching, allowing users to complete the full process of demand analysis, equipment selection, and procurement within a unified platform.

[0056] For users who use the deep learning model provided by the platform, they can proceed to box 404, where the demand analysis module 402 will screen out suitable deployment platforms 406 based on the user's application requirements and the hardware deployment parameters supported by the platform, including but not limited to PC, cloud computing, embedded systems, etc., and the model type 408 may include but is not limited to image recognition, object detection, and image segmentation. In addition, the system can include specific parameters such as image color type 410 (for example, color, grayscale, or black and white), target recognition object size 412, target object motion state 414, frame rate 416, and working distance 418 according to the image acquisition related requirements specified by the user. In addition, the hardware recommendation module 438 can recommend cameras and deployment platforms that meet the user's needs based on the camera cost 420 and the deployment platform cost 422.

[0057] For users who do not use the deep learning model provided by the platform, they can proceed to box 424, where the requirements analysis module 402 allows users to define hardware parameters according to their own needs. For example, users can specify information such as image color type 426, target recognition object size 428, target object motion state 430, frame rate 432, working distance 434 and budget 436. The system will perform camera matching based on the data entered by the user. The hardware recommendation module 438 screens the matching results to ensure that the recommended equipment can meet the user's technical requirements and meet the user's cost budget.

[0058] The UI control interface 442 is a graphical human-computer interaction interface, through which the user can flexibly adjust image acquisition-related strategies, such as adjusting the acquisition process, including but not limited to continuous shooting 446 (i.e., video) or single shooting 448. In addition, the camera parameter adjustment 450 can also be controlled, such as adjusting the exposure time, resolution, frame rate and other camera parameters. In some embodiments, other extended functions can also be set through the UI control interface 442. For example, real-time adjustment of acquisition settings and storage of image data, and the collected images are transmitted to the corresponding annotation platform for subsequent processing through the integrated upload function.

[0059] In some embodiments, the intelligent image acquisition system can adopt a Web-based architecture design to provide users with cross-platform access and operation support. For example, users can directly access the system through the browser of a variety of terminal devices (including but not limited to PCs, tablets, smart phones, etc.) to conveniently complete image acquisition tasks. In some embodiments, the intelligent image acquisition system has developed native applications for mainstream operating systems such as Windows, MacOS, Linux, iOS, and Android to meet the needs of different operating environments and achieve cross-platform compatibility.

[0060] Figure 5A schematic diagram 500 of device connection according to an embodiment of the present disclosure is shown. During the image acquisition process, the camera 502 and the hardware platform 504 (e.g., PC) can be connected wired or wirelessly through a variety of connection methods. For example, it may include but is not limited to a wired connection through a USB interface 506, a wired connection through an Ethernet (LAN) interface 508, or a wireless connection through Wi-Fi 510. Supporting multiple connection methods can adapt to the needs of different scenarios. The wired connection provides high transmission rate and stability, and the wireless connection meets the needs of high mobility and flexible deployment. Through the UI control interface deployed on the hardware platform 504, the user can call, operate and adjust parameters of the camera 502. For example, the user can set parameters such as resolution, frame rate, exposure time, etc. of image acquisition, and select an acquisition mode (such as single acquisition or continuous acquisition). The collected image data is processed in the foreground, and the relevant data can be stored in the background for further AI processing and analysis.

[0061] Figure 6 FIG. 6 is a block diagram of an apparatus 600 for collecting images according to some embodiments of the present disclosure. Figure 6 As shown, the device 600 includes an information acquisition module 602, which is configured to obtain camera information of the camera and device information of the device to which the camera is connected. The device 600 also includes a driver determination module 604, which is configured to determine a driver for the camera to be installed on the device based on the camera information and the device information. The device 600 also includes a policy configuration module 606, which is configured to configure an acquisition strategy related to the acquired image based on the user input on the user interface after the driver is installed. The acquisition strategy is related to the application scenario of the AI ​​model for which the acquired image is used. In addition, the device 600 also includes an image acquisition module 608, which is configured to acquire images for the AI ​​model by controlling the camera using the device based on the acquisition strategy.

[0062] Figure 7 A block diagram of an electronic device 700 is shown in accordance with certain embodiments of the present disclosure. Figure 7 FIG. 1 is a block diagram of an electronic device 700 according to some embodiments of the present disclosure. The device 700 may be a device or apparatus described in an embodiment of the present disclosure. Figure 7As shown, the device 700 includes a central processing unit (CPU) and / or a graphics processing unit (GPU) 701, which can perform various appropriate actions and processes according to computer program instructions stored in a read-only memory (ROM) 702 or computer program instructions loaded from a storage unit 708 to a random access memory (RAM) 703. In the RAM 703, various programs and data required for the operation of the device 700 can also be stored. The CPU / GPU 701, the ROM 702, and the RAM 703 are connected to each other via a bus 704. An input / output (I / O) interface 705 is also connected to the bus 704. Although not shown in FIG. Figure 7 As shown in FIG. 7 , device 700 may further include a coprocessor.

[0063] A number of components in the device 700 are connected to the I / O interface 705, including: an input unit 706, such as a keyboard, a mouse, etc.; an output unit 707, such as various types of displays, speakers, etc.; a storage unit 708, such as a disk, an optical disk, etc.; and a communication unit 709, such as a network card, a modem, a wireless communication transceiver, etc. The communication unit 709 allows the device 700 to exchange information / data with other devices through a computer network such as the Internet and / or various telecommunication networks.

[0064] The various methods or processes described above may be performed by the CPU / GPU 701. For example, in some embodiments, the methods may be implemented as a computer software program, which is tangibly contained in a machine-readable medium, such as a storage unit 708. In some embodiments, part or all of the computer program may be loaded and / or installed on the device 700 via the ROM 702 and / or the communication unit 709. When the computer program is loaded into the RAM 703 and executed by the CPU / GPU 701, one or more steps or actions in the methods or processes described above may be performed.

[0065] In some embodiments, the methods and processes described above may be implemented as a computer program product. The computer program product may include a computer-readable storage medium carrying computer-readable program instructions for executing various aspects of the present disclosure.

[0066] Computer readable storage medium can be a tangible device that can hold and store instructions used by an instruction execution device. Computer readable storage medium can be, for example, but not limited to, an electrical storage device, a magnetic storage device, an optical storage device, an electromagnetic storage device, a semiconductor storage device, or any suitable combination thereof. More specific examples (non-exhaustive list) of computer readable storage medium include: a portable computer disk, a hard disk, a random access memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or flash memory), a static random access memory (SRAM), a portable compact disk read-only memory (CD-ROM), a digital versatile disk (DVD), a memory stick, a floppy disk, a mechanical encoding device, for example, a punch card or a convex structure in a groove on which instructions are stored, and any suitable combination thereof. The computer readable storage medium used here is not interpreted as a transient signal itself, such as a radio wave or other freely propagating electromagnetic wave, an electromagnetic wave propagated by a waveguide or other transmission medium (for example, a light pulse by an optical fiber cable), or an electrical signal transmitted by a wire.

[0067] The computer-readable program instructions described herein can be downloaded from a computer-readable storage medium to each computing / processing device, or downloaded to an external computer or external storage device via a network, such as the Internet, a local area network, a wide area network, and / or a wireless network. The network can include copper transmission cables, optical fiber transmissions, wireless transmissions, routers, firewalls, switches, gateway computers, and / or edge servers. The network adapter card or network interface in each computing / processing device receives the computer-readable program instructions from the network and forwards the computer-readable program instructions for storage in the computer-readable storage medium in each computing / processing device.

[0068] The computer program instructions for performing the disclosed operation may be assembler instructions, instruction set architecture (ISA) instructions, machine instructions, machine-related instructions, microcode, firmware instructions, state setting data, or source code or object code written in any combination of one or more programming languages, programming languages ​​including object-oriented programming languages, and conventional procedural programming languages. Computer-readable program instructions may be executed completely on a user's computer, partially on a user's computer, executed as an independent software package, partially on a user's computer, partially on a remote computer, or completely on a remote computer or server. In the case of a remote computer, the remote computer may be connected to the user's computer via any type of network, including a local area network (LAN) or a wide area network (WAN), or may be connected to an external computer (e.g., utilizing an Internet service provider to connect via the Internet). In certain embodiments, by utilizing the state information of a computer-readable program instruction to customize an electronic circuit, such as a programmable logic circuit, a field programmable gate array (FPGA), or a programmable logic array (PLA), the electronic circuit may execute a computer-readable program instruction, thereby realizing various aspects of the present disclosure.

[0069] These computer-readable program instructions can be provided to a processing unit of a general-purpose computer, a special-purpose computer, or other programmable data processing device, thereby producing a machine, so that when these instructions are executed by the processing unit of the computer or other programmable data processing device, a device that implements the functions / actions specified in one or more boxes in the flowchart and / or block diagram is generated. These computer-readable program instructions can also be stored in a computer-readable storage medium, and these instructions cause the computer, programmable data processing device, and / or other equipment to work in a specific manner, so that the computer-readable medium storing the instructions includes a manufactured product, which includes instructions for implementing various aspects of the functions / actions specified in one or more boxes in the flowchart and / or block diagram.

[0070] Computer-readable program instructions may also be loaded onto a computer, other programmable data processing apparatus, or other device so that a series of operating steps are performed on the computer, other programmable data processing apparatus, or other device to produce a computer-implemented process, thereby causing the instructions executed on the computer, other programmable data processing apparatus, or other device to implement the functions / actions specified in one or more boxes in the flowchart and / or block diagram.

[0071] The flow chart and block diagram in the accompanying drawings show the possible architecture, function and operation of the equipment, method and computer program product according to multiple embodiments of the present disclosure. In this regard, each frame in the flow chart or block diagram can represent a part of a module, program segment or instruction, and a part of the module, program segment or instruction includes one or more executable instructions for realizing the specified logical function. In some alternative implementations, the function marked in the frame can also occur in a sequence different from that marked in the accompanying drawings. For example, two continuous frames can actually be executed substantially in parallel, and they can also be executed in the opposite order sometimes, depending on the functions involved. It should also be noted that each frame in the block diagram and / or flow chart, and the combination of frames in the block diagram and / or flow chart can be implemented with a dedicated hardware-based system that performs a specified function or action, or can be implemented with a combination of dedicated hardware and computer instructions.

[0072] The embodiments of the present disclosure have been described above, and the above description is exemplary, not exhaustive, and is not limited to the disclosed embodiments. Many modifications and changes will be apparent to those of ordinary skill in the art without departing from the scope and spirit of the described embodiments. The choice of terms used herein is intended to best explain the principles of the embodiments, practical applications, or technical improvements to the technology in the market, or to enable other persons of ordinary skill in the art to understand the embodiments disclosed herein.

Claims

1. A method for collecting images: Obtaining camera information of a camera and device information of a device to which the camera is connected; Based on the camera information and the device information, determining a driver for the camera to be installed on the device; After the driver is installed, based on the user input on the user interface, a collection strategy related to the collected image is configured, wherein the collection strategy is related to the application scenario of the artificial intelligence AI model in which the collected image is used; as well as Based on the acquisition strategy, the image for the AI ​​model is acquired by controlling the camera using the device. 2 . The method according to claim 1 , wherein the camera information comprises at least a camera brand and a camera model of the camera, and the device information comprises at least operating system information of the device.

3. The method according to claim 2, wherein obtaining the camera information and the device information comprises: In response to a camera brand and a camera model of the camera being identified, determining the identified camera brand and the camera model as the camera information; or In response to a camera brand and a camera model of the camera not being identified, the camera information is determined based on a selection from the user.

4. The method of claim 2, wherein determining the driver for the camera to install on the device comprises: Based on the camera brand, the camera model and the operating system information, determining one or more drivers in a driver library for display in the user interface; as well as In response to the user's confirmation of a target driver among the one or more drivers, the target driver is determined as the driver to be installed.

5. The method according to claim 2, further comprising: In response to determining that the operating system of the device cannot support the operation of the camera, recommending to the user through the user interface and asking whether to install a target operating system image; as well as In response to the user confirming to install the target operating system image, the target operating system image and a corresponding driver are automatically downloaded and installed on the device. The method according to claim 1 , wherein the acquisition strategy comprises at least one of an acquisition parameter and an acquisition process.

7. The method according to claim 6, wherein configuring the acquisition strategy related to acquiring images comprises: Based on the acquisition parameters and / or acquisition process input by the user on the user interface, the device is used to call corresponding driver software to configure the camera.

8. The method according to claim 7, wherein the acquisition parameters include at least one of the following: shutter speed, aperture, white balance, resolution, color type, frame rate, working distance, or acquisition mode.

9. The method according to claim 1, further comprising: storing the acquired images; as well as The collected images are uploaded to the corresponding annotation platform.

10. The method according to claim 1, further comprising: Providing a deep learning platform including a deep learning model related to image processing, wherein the deep learning model includes at least one or more of an image recognition model, an object detection model, and / or an image segmentation model; Acquiring application information related to the use of the acquired image from the user, the application information including one or more of the following: a required image color type, a minimum target object size, a target object motion state, a minimum frame rate for data acquisition, or a camera working distance; In response to the user determining to use the deep learning platform, recommending one or more cameras to the user based on parameter information of a deployment hardware platform supported by the deep learning platform and the application information; or In response to the user not needing to use the deep learning platform, recommending one or more cameras to the user based on the application information.

11. The method according to claim 10, wherein the parameter information of the deployment hardware platform supported by the deep learning platform includes one or more of the following: central processing unit information, graphics processing unit information, motherboard information, embedded system motherboard model, embedded processor information, operating system version, or software environment information required for the deployment model.

12. The method according to claim 1, further comprising: The camera is connected to the device through a predetermined connection method, wherein the predetermined connection method includes one of a wired connection and a wireless connection.

13. The method of claim 1, wherein the user interface is based on a web design and the user interface is accessed through a browser on the device.

14. The method according to claim 1, wherein the user interface is designed based on a native application of a target operating system, and the target operating system comprises one or more of Windows, MacOS, Linux, iOS and Android.

15. The method according to claim 1, further comprising: Based on the user's selection, determining a target image to be uploaded from the collected images; as well as The target image is synchronized to a server.

16. The method according to claim 14, further comprising at least one of the following: Select all images to be uploaded based on the one-click select all function selected by the user; During the image uploading process, marking the uploaded image on the user interface, and prompting the user whether to repeatedly upload the marked uploaded image; Displaying the number of images collected and the number of images uploaded on the user interface; or In response to multiple acquisitions and multiple uploads, the total number of uploaded images on the server is displayed on the user interface.

17. The method according to claim 1, further comprising: Prompting the user to determine an application scenario through the user interface; as well as In response to the determined application scenario being a preset application scenario, a recommendation result for the user is generated based on historical recommendation cases related to the determined application scenario.

18. The method according to claim 17, further comprising: In response to the determined application scenario not belonging to the preset application scenario, prompting the user to provide input information through the user interface, wherein the input information is related to the application scenario, camera parameters, and whether the distance of the target object relative to the camera changes during the application process; generating a recommendation result for the user based at least on the input information, and In response to the recommendation result including at least one recommended camera, displaying an explanation for the recommendation result on the user interface, the explanation including at least one of a reason for recommendation, camera features, applicable scenarios, and alternative cameras; or In response to the recommendation result being empty, feedback information is displayed on the user interface.

19. The method according to claim 18, further comprising: In response to the user not having the recommended camera, prompting the user through the user interface to provide input information related to a usage budget; as well as Based on the input information, filter the target camera in the recommendation results; or In response to the user having the recommended camera, the camera information of the camera is acquired.

20. The method according to claim 19, further comprising: Based on the change in the distance of the target object relative to the camera in the input information, generating a recommended lens corresponding to the camera; as well as The recommendation description of the recommended lens is displayed on the user interface.

21. A device for collecting images, comprising: An information acquisition module, configured to acquire camera information of a camera and device information of a device connected to the camera; A driver determination module, configured to determine a driver program for the camera to be installed on the device based on the camera information and the device information; A policy configuration module is configured to configure, after the driver is installed, a collection policy related to the collected image based on a user input on a user interface, wherein the collection policy is related to an application scenario of an artificial intelligence (AI) model for which the collected image is used; as well as The image acquisition module is configured to acquire images for the AI ​​model by controlling the camera using the device based on the acquisition strategy.

22. An electronic device comprising: processor; as well as A memory coupled to the processor, the memory having instructions stored therein, wherein when the instructions are executed by the processor, the electronic device executes the method according to any one of claims 1 to 20.

23. A computer program product tangibly stored on a non-transitory computer readable medium and comprising computer executable instructions for performing the method according to any one of claims 1 to 20.

Images