Image acquisition method, device, apparatus and computer readable storage medium

Abstract

Embodiments of the present application disclose an image acquisition method, device, equipment and computer readable storage medium. The method acquires original image data of a target object through an image acquisition module. After the original image data is acquired, the application scenario corresponding to the original image data is determined by detecting the image content in the original image data. Next, the target acquisition parameter matched with the application scenario is determined. The image acquisition module is controlled to acquire the image of the target object based on the target acquisition parameter, and target image data is obtained. In the image acquisition process, the acquisition parameter of the image acquisition module is adaptively adjusted. The target acquisition parameter obtained by the adjustment is matched with the application scenario. The image acquisition module acquires the image based on the target acquisition parameter matched with the application scenario. Furthermore, the image recognition is performed based on the target image data, which can improve the accuracy of the image recognition result.

Description

Technical Field

[0001] This application relates to the field of computer technology, and in particular to an image acquisition method, apparatus, device, and computer-readable storage medium. Background Technology

[0002] With the continuous development of smart terminal technology, the use of electronic devices (such as smartphones and tablets) is becoming more and more widespread. For example, gesture detection and facial recognition functions have been widely used in daily life, allowing users to complete human-computer interaction without touching electronic devices, thus improving the user experience.

[0003] In practical applications, electronic devices use image acquisition and image recognition to identify user gestures and faces. Typically, after the frame rate and resolution of the image acquisition module are successfully set, it acquires images using the pre-defined parameters. The recognition processing module then processes the acquired image data. However, images acquired using the pre-defined parameters may not meet the requirements of the recognition process, thus affecting the accuracy of image recognition. Summary of the Invention

[0004] This application provides an image acquisition method, apparatus, device, and computer-readable storage medium. By detecting the image content in the original image data, determining the application scenario, acquiring images based on target acquisition parameters matching the application scenario, and then performing image recognition based on the target image data, the accuracy of image recognition results can be improved.

[0005] The technical solution of this application embodiment is implemented as follows:

[0006] In a first aspect, embodiments of this application provide an image acquisition method, the method comprising: acquiring raw image data of a target object through an image acquisition module; determining an application scenario corresponding to the raw image data by detecting image content in the raw image data, the application scenario representing a scenario for recognizing and processing the target object; determining target acquisition parameters matching the application scenario; and controlling the image acquisition module to acquire images of the target object based on the target acquisition parameters to obtain target image data.

[0007] Secondly, embodiments of this application provide an image acquisition device, the device comprising: acquiring raw image data of a target object through an image acquisition module; determining an application scenario corresponding to the raw image data by detecting image content in the raw image data, the application scenario representing a scenario for recognizing and processing the target object; determining target acquisition parameters matching the application scenario; and controlling the image acquisition module to acquire images of the target object based on the target acquisition parameters to obtain target image data.

[0008] Thirdly, embodiments of this application provide an image acquisition device, the device including a memory for storing executable instructions and a processor for executing the executable instructions stored in the memory to implement the above-described image acquisition method.

[0009] Fourthly, embodiments of this application provide a computer-readable storage medium storing executable instructions thereon, which, when executed by a processor, implement the above-described image acquisition method.

[0010] This application provides an image acquisition method, apparatus, device, and computer-readable storage medium. In this embodiment, an image acquisition module first acquires raw image data of a target object. After acquiring the raw image data, the application scenario corresponding to the raw image data is determined by detecting the image content in the raw image data. This application scenario represents the scenario in which the target object is identified and processed. Next, target acquisition parameters matching the application scenario are determined. The image acquisition module is then controlled to acquire images of the target object based on the target acquisition parameters to obtain target image data. This application adaptively adjusts the acquisition parameters of the image acquisition module during the image acquisition process, ensuring that the adjusted target acquisition parameters match the application scenario. The image acquisition module performs image acquisition based on the target acquisition parameters matching the application scenario, and then performs image recognition based on the target image data, thereby improving the accuracy of the image recognition results. Attached Figure Description

[0011] Figure 1 A flowchart illustrating the steps of an image acquisition method provided in this application embodiment;

[0012] Figure 2 A flowchart illustrating the steps of another image acquisition method provided in this application embodiment;

[0013] Figure 3 A schematic diagram illustrating the depth information of a target object provided in an embodiment of this application;

[0014] Figure 4 A flowchart illustrating the steps of another image acquisition method provided in this application embodiment;

[0015] Figure 5 This is a schematic diagram of the structure of the front end of an image processing system provided in an embodiment of this application;

[0016] Figure 6 A flowchart illustrating the steps of another image acquisition method provided in this application embodiment;

[0017] Figure 7 This is a schematic diagram of the structure of an image acquisition device provided in an embodiment of this application;

[0018] Figure 8 This is a schematic diagram of the structure of an image acquisition device provided in an embodiment of this application. Detailed Implementation

[0019] The technical solutions of the embodiments of this application will be clearly and completely described below with reference to the accompanying drawings. It should be understood that some embodiments described herein are merely used to explain the technical solutions of this application and are not intended to limit the technical scope of this application.

[0020] To better understand the image acquisition method provided in the embodiments of this application, the relevant technologies will be explained before introducing the technical solutions of the embodiments of this application.

[0021] In related technologies, directly outputting images at high resolution or high frame rate would affect system power consumption and slow down system recognition and processing capabilities. Therefore, the frame rate and resolution of the image acquisition module are set to low frame rate and low resolution by default. During the shooting process, after the image is displayed, the user can actively adjust the frame rate and resolution of the image acquisition module in the application (App) to suit different application scenarios. Subsequent image acquisition will then be performed at a fixed frame rate and resolution. In other words, the frame rate and resolution remain constant during image acquisition in any application scenario. For general application scenarios, the frame rate and resolution settings in related technologies are sufficient. However, for applications such as gesture detection and eye recognition, the recognition efficiency and accuracy of the shooting function are significantly affected by changes in frame rate and resolution.

[0022] For example, in a gesture detection scenario, it's necessary to recognize hand gestures, and then a subsequent recognition processing module processes the image data acquired by the image acquisition device. Taking eye recognition as an example, the accuracy and detail of the image directly affect the accuracy of the recognition result. Directly outputting images at high resolution or high frame rate will affect the speed and efficiency of the recognition process, and also the accuracy of the recognition result. Therefore, there is an urgent need to provide an image acquisition method that strikes a balance between the accuracy of the recognition result and system power consumption, facilitating improved accuracy while maintaining low power consumption.

[0023] This application provides an image acquisition method, such as... Figure 1 As shown, Figure 1 This application provides a flowchart of an image acquisition method, which includes the following steps:

[0024] Step S101: Acquire the original image data of the target object through the image acquisition module.

[0025] In the embodiments of this application, the image acquisition module may include, but is not limited to, a mobile phone camera, a camera, an optical sensor, and an Alawys on sensor (AON sensor), where sensor may refer to a low-power image sensor configured for application scene recognition.

[0026] In the embodiments of this application, the target object may include, but is not limited to, animals, human bodies, human faces, human eyes, human lips, human eyeballs, and human hands.

[0027] For example, taking the AON sensor as an image acquisition module, the AON sensor acquires data from the target object, obtaining raw image data. This raw image data represents the original image data obtained by the sensor from converting the captured light source signal into a digital signal; this raw image data has not undergone subsequent compensation or other processing.

[0028] Step S102: Determine the application scenario corresponding to the original image data by detecting the image content in the original image data.

[0029] Among them, the application scenario represents the scenario in which the target object is identified and processed.

[0030] In this embodiment, the image content detection module can be used to detect the image content in the original image data, thereby determining the application scenario based on the image content detection results.

[0031] The recognition processing includes, but is not limited to, human body recognition, human face recognition, human eye recognition, human eyeball recognition, human hand recognition, human gesture detection, and preset action detection, where human gesture detection refers to non-contact gesture recognition or gesture recognition without contact.

[0032] Image content can reflect the user's shooting intention, and can also be understood as the shooting function mode used by the user. The application scenario is determined based on the image content detection results, which improves the accuracy of the application scenario.

[0033] In some embodiments, a user-preset scene mode can also be obtained, and the application scenario can be determined based on the pre-set scene mode. That is, before the image acquisition module begins capturing the target object, the user can pre-select the shooting function mode on the app, such as face recognition, gesture detection, and eye recognition. In other words, the scene mode is pre-set before shooting, and the application scenario is determined based on the pre-set scene mode. This method of directly obtaining the application scenario through the user-preset scene mode improves the efficiency of obtaining the application scenario.

[0034] Step S103: Determine the target acquisition parameters that match the application scenario.

[0035] Target acquisition parameters are used to acquire images of the target object. The application scenario corresponds to these parameters. For example, in a face recognition scenario, the resolution is set to 1080P, meaning 1280 pixels per horizontal row and 1080 pixels per column, for a total of 1280 x 1080 pixels. This product is the resolution. In a gesture detection scenario, the frame rate is set to 50 FPS. It's important to note that Frames Per Second (FPS) represents the number of frames transmitted per second, which can be understood as the number of frames in an animation or video. FPS measures the amount of information used to store and display dynamic video; the higher the frame rate, the smoother the displayed motion.

[0036] For example, taking frame rate and resolution as acquisition parameters, directly outputting images at high resolution or high frame rate will affect system power consumption, leading to problems such as overheating of the smart terminal and slower system recognition and processing capabilities. Therefore, the default acquisition parameters of the image acquisition module are set to low frame rate and low resolution. However, if image acquisition is consistently performed at low frame rate and low resolution, the accuracy and detail of the image will affect the accuracy of target object recognition. Therefore, in this embodiment, after determining the application scenario, a target acquisition parameter matching the application scenario is also determined. The acquisition parameters of the image acquisition module are adjusted to the target acquisition parameters, so that the subsequent image acquisition module performs image acquisition on the target object based on the target acquisition parameters, thereby improving the accuracy of the acquisition results.

[0037] Step S104: Control the image acquisition module to acquire images of the target object based on the target acquisition parameters, and obtain target image data.

[0038] Because the target acquisition parameters match the application scenario, the image acquisition module controls the acquisition of images of the target object based on these parameters. The acquisition results are closely related to the application scenario. These results are used for subsequent recognition processing within the application scenario. The acquisition results can be target image data, and then image recognition is performed based on this target image data, improving the accuracy of the image recognition results.

[0039] In this embodiment, the acquisition parameters of the image acquisition module are adaptively adjusted during the image acquisition process, and the adjusted target acquisition parameters are matched with the application scenario. The image acquisition module performs image acquisition based on the target acquisition parameters matched with the application scenario, and then performs image recognition based on the target image data, which can improve the accuracy of the image recognition results.

[0040] In some embodiments, step S102 can be implemented through steps S1021 and S1022. For example... Figure 2 As shown, Figure 2A flowchart illustrating the steps of another image acquisition method provided in this application embodiment.

[0041] Step S1021: Obtain image feature points and / or motion parameters of image feature points by detecting image content in the original image data.

[0042] In this embodiment, image feature points are used to characterize the feature information of feature points in the image content; the motion parameters of image feature points are used to characterize the motion information of feature points in the image content within a preset time period. The image feature points may include, but are not limited to, preset location regions, representative location regions, preset location points, and representative location points of the target object.

[0043] For example, in a face recognition scenario, image feature points can represent, but are not limited to, the feature information of the face contour, the tip of the nose, and the ears. In a gesture detection scenario, image feature points can represent, but are not limited to, the feature information of the fingers, wrists, and fingertips, and the motion parameters of the image feature points can represent, but are not limited to, the motion information of the fingers, wrists, and fingertips within a preset time period.

[0044] Step S1022: Match the image feature points and / or motion parameters of the image feature points with a preset application scenario to obtain the application scenario corresponding to the original image data.

[0045] In the embodiments of this application, the preset application scenarios can be appropriately set by those skilled in the art according to actual needs. For example, face recognition scenarios, eye recognition scenarios, gesture detection scenarios, and specific action detection scenarios, as long as the preset application scenario can be matched with image feature points and / or motion parameters of image feature points to determine the application scenario corresponding to the original image data. The preset application scenario includes preset image feature points and / or preset motion parameters of image feature points, which can be determined by analyzing the motion parameters of image feature points and / or image feature points corresponding to a large amount of experimental data.

[0046] When performing application scenario matching, the application scenario corresponding to the maximum similarity between image feature points and preset image feature points can be determined as the application scenario corresponding to the original image data. Alternatively, the application scenario corresponding to the maximum similarity between motion parameters of image feature points and preset motion parameters can be determined as the application scenario corresponding to the original image data. Another approach is to calculate a first similarity between image feature points and preset image feature points, and a second similarity between the motion parameters of image feature points and preset motion parameters, and then comprehensively consider both similarities by adding weights to obtain a comprehensive similarity score. The application scenario corresponding to the maximum comprehensive similarity score is determined as the application scenario corresponding to the original image data; however, this embodiment does not limit this approach.

[0047] This application embodiment obtains image feature points and / or motion parameters of image feature points by detecting image content in the original image data. Then, based on the image feature points and / or motion parameters of image feature points, it matches them with a preset application scenario to obtain the application scenario, thereby improving the accuracy of the application scenario.

[0048] In some embodiments, the target acquisition parameters in step S103 include at least one of the following: frame rate, resolution, focal length, and image bit width information.

[0049] In this embodiment, frame rate represents the number of images played per second in a video; a higher frame rate results in smoother video playback. Resolution characterizes the number of pixels a display can show; a higher resolution produces a more detailed image. Focal length characterizes the lens focal length, which is the distance from the lens's rear principal point to its focal point. Image bit width information represents the number of bits of image data that can be transmitted within one clock cycle; a larger bit width means a larger amount of image data can be transmitted instantaneously, which can be understood as the amount of image data that memory or video memory can transmit at once.

[0050] The target acquisition parameters in this application embodiment include at least one of frame rate, resolution, focal length, and image bit width information. When the acquisition parameters used by the image acquisition module are adjusted to the target acquisition parameters, one of the target acquisition parameters can be adjusted, or two or more of the target acquisition parameters can be adjusted at the same time, which improves the diversity of target acquisition parameter adjustment methods.

[0051] In some embodiments, step S103 can be implemented through the following two examples.

[0052] Example 1: Based on the first mapping relationship, the acquisition parameters that match the application scenario are determined, and the target acquisition parameters are obtained. The first mapping relationship represents the correspondence between the application scenario and the acquisition parameters.

[0053] In the embodiments of this application, there is a correspondence between the application scenarios and the acquisition parameters. For example, in the face recognition scenario, the resolution in the acquisition parameters is 720P; in the eye recognition scenario, the resolution in the acquisition parameters is 1080P; and in the gesture detection scenario, the frame rate in the acquisition parameters is 50FPS.

[0054] After determining the application scenario corresponding to the original image data, one possible approach is to adaptively adjust the acquisition parameters of the image acquisition module according to the acquisition parameters of the application scenario. For example, appropriately increasing the resolution and appropriately decreasing the frame rate can adjust the acquisition parameters of the image acquisition module to match the application scenario. For instance, in an eye recognition scenario where the resolution in the acquisition parameters is 1080P, the resolution of the image acquisition module's acquisition parameters can be increased to 720P. Another possible approach is to use the acquisition parameters of the application scenario as the target acquisition parameters of the image acquisition module. For instance, in a face recognition scenario where the resolution in the acquisition parameters is 720P, the resolution of the target acquisition parameters of the image acquisition module can be set to 720P.

[0055] In some embodiments, the first mapping relationship in Example 1 above includes the following two cases.

[0056] The first scenario: If the application scenario is for recognizing the actions of a target object, then the target acquisition parameters include the first frame rate, which is higher than the second frame rate used to acquire the original image data.

[0057] The second scenario: If the application scenario is for identifying target objects or identifying local details of target objects, then the target acquisition parameters include a first resolution, which is higher than the second resolution used to acquire the original image data.

[0058] The image acquisition module acquires raw image data from the target object based on initial acquisition parameters. Taking the initial acquisition parameters, including frame rate and resolution, as an example, to reduce system power consumption and improve system processing capabilities, the default initial acquisition parameters are set to low frame rate and low resolution. After determining the application scenario based on the image content in the raw image data, the initial acquisition parameters can be adaptively adjusted according to different application scenarios. That is, the second frame rate and the second resolution in the initial acquisition parameters are low. If the application scenario is for recognizing the action of the target object, the second frame rate is adjusted to the first frame rate, which is greater than the second frame rate. In this case, the resolution can be adjusted or not; simply increasing the frame rate is sufficient. This application embodiment does not impose any restrictions on this. If the application scenario is for recognizing the target object or recognizing local details of the target object, the second resolution is adjusted to the first resolution, which is greater than the second resolution. In this case, the frame rate can be adjusted or not; simply increasing the resolution is sufficient. This application embodiment does not impose any restrictions on this.

[0059] For example, taking the acquisition parameters including frame rate and resolution as an example, the adjustment strategies for frame rate and resolution can be adjusted differently according to different scenarios. The application scenario for recognizing the action of a target object in this embodiment can be understood as a detection scenario requiring pose transformation, such as gesture detection and action detection scenarios. For application scenarios for recognizing the action of a target object, the frame rate is adjusted first to ensure that more effective image data frames are available per unit time for the recognition processing module to analyze and recognize. The application scenario for recognizing a target object or recognizing local details of a target object in this embodiment can be understood as a scenario that relies on the accuracy of image information. For example, face recognition and eye recognition scenarios. For application scenarios for recognizing a target object or recognizing local details of a target object, the resolution is increased first to improve the accuracy of recognition through more detailed information.

[0060] It should be noted that in the embodiments of this application, "first" and "second" are used to distinguish different objects, rather than to describe a specific order, such as first mapping relationship, second mapping relationship, first frame rate, second frame rate, first resolution, and second resolution.

[0061] Example 2: Based on the second mapping relationship, the adjustment range of the acquisition parameters matching the application scenario is determined, thus obtaining the adjustment range of the target acquisition parameters. The second mapping relationship represents the correspondence between the application scenario and the adjustment range of the acquisition parameters. Based on the depth information of the target object in the original image data, the target acquisition parameters are determined within the adjustment range of the target acquisition parameters.

[0062] In this application embodiment, there is a corresponding relationship between the application scenario and the adjustment range of the acquisition parameters. For example, in application scenarios involving the identification of target objects or local details of target objects, the resolution adjustment range in the acquisition parameters is 720P-1080P. That is, when the application scenario is a face recognition or eye recognition scenario, setting the resolution in the target acquisition parameters between 720P and 1080P allows for the acquisition of more detailed information, thereby improving the accuracy of recognition. In application scenarios involving the identification of target object actions, the frame rate adjustment range in the acquisition parameters is 40FPS-60FPS. That is, when the application scenario is a gesture detection or action detection scenario, setting the frame rate in the target acquisition parameters between 40FPS and 60FPS allows for the acquisition of more effective image data frames per unit time, which the recognition processing module can then use to analyze and identify the actions.

[0063] The depth information of the target object represents the distance between the target object and the camera. For example... Figure 3 As shown, Figure 3 This is a schematic diagram illustrating the depth information of a target object provided in an embodiment of this application. Figure 3 The depth information of the target object can be represented as the focusing distance between the focal plane and the image plane.

[0064] In this embodiment, the adjustment range of the target acquisition parameters is first determined, and then the target acquisition parameters are determined within the adjustment range based on the depth information of the target object in the original image data. This not only considers the application scenario but also the depth information of the target object, thus improving the matching degree between the target acquisition parameters and the application scenario.

[0065] In some embodiments, step S104 can be implemented as follows: An adjustment time point is determined based on the expected number of image frames required for target object recognition processing in the application scenario, or the time required to complete the target object recognition processing in the application scenario. At the adjustment time point, the image acquisition module is controlled to acquire images of the target object based on the target acquisition parameters to obtain target image data.

[0066] In this embodiment, the selection of the adjustment time point can be determined based on various factors, including but not limited to: the expected number of image frames required for target object recognition processing, and the duration required to complete the target object recognition processing in the application scenario. For example, based on the number of image frames required for accurate detail recognition, the required number of image frames to be acquired within a specific time period is determined, and the time point before that period is determined as the adjustment time point. Similarly, based on the rate of change of the action posture obtained during parameter adjustment, the required time period for detecting the corresponding working posture is determined, meaning the frame rate needs to be adjusted before that time period, and the time point before that period is determined as the adjustment time point.

[0067] For example, gesture detection typically takes about 0.5 seconds, or 500 milliseconds, to complete the entire gesture detection process. This requires the recognition processing module to complete the recognition within 500 milliseconds. If the image acquisition module's frame rate is 30 FPS (30 frames per second), then recognition needs to be completed within 15 frames. Therefore, for gesture detection scenarios, the frame rate of the image acquisition module needs to be increased when the image feature points representing the gesture appear in 3 frames. For example, increasing the frame rate to 50 FPS would mean that the image acquisition module takes 150 milliseconds to acquire 15 frames, allowing the recognition processing module to meet the requirement of completing recognition within 500 milliseconds. In this example, considering that the initial frame rate of the image acquisition module is low, and 3 frames already take a long time, the number of image frames corresponding to the image feature points is set to 3 frames. When the image acquisition module acquires 3 frames, the frame rate of the image acquisition module is increased from 30 FPS to 50 FPS.

[0068] After adjusting the acquisition parameters of the image acquisition module through the above steps S101-S104 and determining the target acquisition parameters of the image acquisition module, this embodiment of the application further adjusts the acquisition parameters a second time based on the target image data.

[0069] In some embodiments, after step S104 in any of the above embodiments, the image acquisition method provided in this application further includes steps S105-S109. For example... Figure 4 As shown, Figure 4 A flowchart illustrating the steps of another image acquisition method provided in this application embodiment.

[0070] Step S105: Detect local information of image content in target image data, and obtain local image feature points and / or motion parameters of local image feature points.

[0071] In the embodiments of this application, local information represents information about local parts or details of a target object. For example, if the target object is a human face, the local parts of the target object include, but are not limited to, eyebrows, eyeballs, pupils, and sclera. If the target object is a human hand, the local parts of the target object include, but are not limited to, fingertips and finger joints.

[0072] Step S106: Determine the target application scenario corresponding to the target image data based on the local image feature points and / or the motion parameters of the local image feature points.

[0073] Among them, the target application scenario represents the scenario in which the local details of the target object are identified and processed, which can be understood as the scenario in which the local parts of the target object are accurately identified.

[0074] The implementation method of the target application scenario is determined through steps S105 and S106, which is consistent with the implementation method of the application scenario determined through steps S1021 and S1022 above, and will not be repeated here.

[0075] Step S107: If the target acquisition parameters do not match the acquisition parameters corresponding to the target application scenario, then determine the intermediate acquisition parameters that match the target application scenario.

[0076] Steps S105 and S106 involve analyzing the image feature points and / or motion parameters of the target image data obtained after the first adjustment of the acquisition parameters. Based on the determined application scenario, the target application scenario is further determined. If the target acquisition parameters do not match the acquisition parameters corresponding to the target application scenario, the acquisition parameters are adjusted a second time. The method for the second adjustment is the same as the method for the first adjustment, and will not be described again here. For example, the acquisition parameters of the image acquisition module are adjusted first to adapt to the face recognition scenario, and then the acquisition parameters of the image acquisition module are adjusted second to adapt to the eye recognition scenario.

[0077] Step S108: Control the image acquisition module to acquire images of the target object based on intermediate acquisition parameters to obtain intermediate image data.

[0078] The implementation of step S108 is the same as that of step S104, and will not be repeated here.

[0079] It is understood that after obtaining the intermediate image data in step S108, this embodiment of the application may continue to perform the analysis in steps S105 and S106 above on the intermediate image data to further determine new application scenarios. If the acquisition parameters of the image acquisition module do not match the new application scenario, the acquisition parameters will be adjusted again to match the new application scenario.

[0080] Step S109: If the target acquisition parameters match the acquisition parameters corresponding to the target application scenario, then proceed to step S104.

[0081] If the target acquisition parameters match the acquisition parameters corresponding to the target application scenario, there is no need to adjust the acquisition parameters a second time. The image acquisition module can simply acquire images of the target object based on the target acquisition parameters.

[0082] This application embodiment obtains local image feature points and / or motion parameters of local image feature points by detecting local information of image content in target image data. Then, based on the local image feature points and / or motion parameters, the target application scenario corresponding to the target image data is determined. If the target acquisition parameters do not match the acquisition parameters corresponding to the target application scenario, intermediate acquisition parameters that match the target application scenario are determined, thereby controlling the image acquisition module to acquire images of the target object based on the intermediate acquisition parameters to obtain intermediate image data. Through a multi-level adjustment strategy, the problem of excessive power consumption or mismatch with the application scenario caused by excessively large adjustments to the acquisition parameters at one time is avoided. The acquisition parameters increase or decrease along a stepped curve, thereby finding a balance between image recognition effect and system power consumption, and improving the accuracy of image recognition while maintaining low power consumption.

[0083] In some embodiments, after step S104 or step S109 in any of the above embodiments, the image acquisition method provided in this application further includes the following step: Determining the operating parameters of the recognition processing module based on the target acquisition parameters. The recognition processing module performs recognition processing on the target object in the target image data according to the operating parameters.

[0084] In this embodiment, the image acquisition module first acquires images of the target object based on target acquisition parameters, obtaining target image data. Then, the working parameters of the recognition processing module are determined according to the target acquisition parameters. The recognition processing module then performs recognition processing on the target object in the target image data according to the working parameters. Only after the recognition processing module completes its recognition processing is the image output, and the user can then see the displayed image. That is, in this embodiment, the image acquisition method is completed before the image is displayed.

[0085] Taking frame rate and resolution as examples of acquisition parameters, to reduce system power consumption and improve system processing capabilities, the default initial acquisition parameters are set to low frame rate and low resolution. The initial operating parameters of the recognition processing module correspond to the initial acquisition parameters of the image acquisition module, and the initial operating parameters of the recognition processing module are matched with low frame rate and low resolution. Therefore, after adjusting the acquisition parameters of the image acquisition module, it is necessary to determine the operating parameters of the recognition processing module based on the target acquisition parameters, and synchronize the adjusted frame rate and resolution to the recognition processing module to ensure that the settings of the entire link are synchronized, so that the adjusted data stream can flow and be processed normally.

[0086] For example, taking an AON sensor as the image acquisition module, with acquisition parameters including frame rate and resolution, the AON sensor does not display images to the user but instead sends the acquired raw image data to the recognition processing module for recognition processing. Therefore, the adjustment of the AON sensor's frame rate and resolution depends on the frame rate and resolution set when the AON sensor is started. However, related technologies often use a fixed frame rate and resolution for image acquisition. The image acquisition module acquires images at low frame rates or low resolutions, and the recognition processing module performs recognition processing on these low-frame-rate or low-resolution images, increasing overall system power consumption and reducing the accuracy of image recognition processing. In this embodiment, the image acquisition module acquires images at a frame rate or resolution matching the application scenario, and the recognition processing module performs recognition processing on images matching the application scenario, improving the accuracy of image recognition processing while maintaining low power consumption.

[0087] In some embodiments, the present application embodiments can not only improve the efficiency of image recognition processing by adjusting the acquisition parameters of the image acquisition module and then having the recognition processing module identify the target object in the target image data according to the working parameters corresponding to the target acquisition parameters, but also by adjusting the processing procedure of the target image data to achieve the same technical effect. For example, when the recognition processing module reads data frames of the target image data, adjusting the interval between reading data frames, such as every 3 frames, every 2 frames, or frame-by-frame reading, can reduce the pressure on image data processing, reduce system power consumption, and improve the efficiency of image recognition processing.

[0088] The following will describe an exemplary application of the embodiments of this application in a real-world application scenario. For example... Figure 5 As shown, Figure 5 This is a schematic diagram of the front end of an image processing system provided in an embodiment of this application.

[0089] For example, the following explanation will be based on the image acquisition module being an AON sensor and the acquisition parameters including frame rate and resolution.

[0090] Figure 5 The front end of the image processing system includes an AON sensor, an image content detection module, and a frame rate and resolution control module. The AON sensor acquires raw image data of the target object based on a default low frame rate and low resolution. Figure 5 In Chinese, RAW images represent raw image data. RAW images are the original image data captured by the image sensor and converted into digital signals.

[0091] The image content detection module performs preliminary detection on the acquired RAW images to initially determine if any application scenarios require identification. This detection process can be achieved by detecting image feature points and / or their motion parameters. When preset image feature points and / or their motion parameters are detected, an application scenario requiring identification is identified. The image content detection module performs image content detection and analysis on the RAW images using Neural-network Processing Units (NPUs). NPUs are computational processors for neural networks (NNs) capable of rapidly processing input information.

[0092] The image content detection module sends the image content detection results to the frame rate and resolution control module. These results are used to determine the application scenario. Figure 5 This example illustrates how the frame rate and resolution control module determines the application scenario based on image content detection results. The frame rate and resolution control module determines a suitable frame rate and resolution based on the image content detection results and a preset frame rate and resolution adjustment strategy. It then adjusts the frame rate and resolution of the AON sensor to the appropriate values ​​and synchronizes the entire data link based on the adjusted frame rate and resolution, for example, synchronizing the operating parameters of the recognition processing module.

[0093] It should be noted that, in this embodiment of the application, the application scenario can be determined by the image content detection module based on the image content detection result, or by the frame rate and resolution control module based on the image content detection result. This embodiment of the application does not limit the application scenario in this way.

[0094] The frame rate and resolution adjustment strategies described above can be tailored to different application scenarios. For example, in scenarios requiring pose change detection (e.g., gesture detection or action detection), the frame rate is prioritized to ensure more effective image data frames are available for analysis and recognition per unit time. In application scenarios where image information accuracy is paramount (e.g., for scenarios requiring eye recognition), the resolution is prioritized to ensure greater accuracy through more detailed eye information.

[0095] Then, the AON sensor acquires images based on the adjusted frame rate and resolution to obtain target image data. The frame rate and resolution control module, when adjusting according to preset frame rates and resolutions, can execute frame rate and resolution decisions based on an adjustment strategy. In this embodiment, for Figure 5 The frame rate and resolution adjustment strategy can also be based on the AON sensor's adjustment results to determine the configuration file. This means there's a mapping relationship between the application scenario and the AON sensor's acquisition parameters. When adjustments to the acquisition parameters are needed, the target acquisition parameters can be determined by querying the configuration file. Alternatively, the configuration file can be set to allow for adjustments to the acquisition parameters based on the application scenario, and then combined with other relevant parameters using an interpolation-like process to determine the target acquisition parameters. For example, in a portrait scene, the target acquisition parameters can be calculated within the allowable adjustment range of the configuration file, combined with the depth information of the portrait's location. Here, depth information can be understood as the distance between the target object and the lens, as described above. Figure 3 As shown, it will not be elaborated further here.

[0096] In this embodiment, the image content detection module at the system front end performs preliminary application scenario identification on the raw image data output by the AON sensor, obtaining a judgment result for the application scenario. It is understood that the frame rate and resolution decision module can also determine the application scenario based on the image content detection result. Then, the frame rate and resolution decision module adjusts the frame rate and resolution based on the application scenario judgment result, enabling the system to achieve accurate application scenario identification while maintaining low power consumption. This embodiment does not require user intervention; the front-end image content detection module directly judges the application scenario, and then the frame rate and resolution decision module adjusts the frame rate and resolution based on the judgment result. Therefore, this embodiment is invisible to the user, is automatically completed, and improves the user experience.

[0097] Combination Figure 5The provided image processing system front-end, in this application embodiment, offers a method for configuring and adjusting an AON sensor based on image detection. The adjusted acquisition parameters may include frame rate and / or resolution, used to improve the accuracy of image recognition processing while maintaining low power consumption. Figure 6 As shown, Figure 6 The flowchart of another image acquisition method provided in the embodiments of this application includes steps S601-S609. Figure 6 The example below uses adjusting the frame rate and resolution. It can be understood that when adjusting the acquisition parameters, you can also adjust only the frame rate or resolution.

[0098] Step S601: The AON Sensor collects raw image data and sends the raw image data to the image content detection module for image content detection processing.

[0099] It should be noted that before step S601, this embodiment of the application turns on the AON sensor and starts the Pre-ISP (Image Signal Processing) module at the front end of the image processing system. The Pre-ISP module represents the front-end image signal processor.

[0100] Step S602: The image content detection module performs image content detection.

[0101] The image content detection module detects image feature points and / or motion parameters of image feature points based on the original image data, and obtains threshold information for frame rate and resolution adjustment. Figure 6 In this context, the motion parameters of image feature points are set to a threshold of 1.

[0102] In step S602, relevant adjustment strategies can be automatically activated based on the image content detection results, or the user can set the shooting scene mode in advance, such as gesture recognition function mode or eye recognition function mode, and determine the adjustment strategy based on the scene mode.

[0103] Step S603: Based on the obtained threshold information, adjust the frame rate and resolution using the combined adjustment strategy.

[0104] Step S603 can be a multi-level adjustment, which can be achieved through steps S6031-S6034.

[0105] Step S6031: Determine whether the image content detected by the image content detection module reaches the threshold 1.

[0106] Step S6032: If the image content detected by the image content detection module reaches the threshold 1, then the frame rate and resolution are adjusted for the first time according to the adjustment strategy.

[0107] The AON sensor uses the initially adjusted frame rate and resolution to acquire image data, and the image content detection module detects the adjusted image content based on the target image data.

[0108] Step S6033: Determine whether the adjusted image content detected by the image content detection module reaches the threshold 2.

[0109] Step S6034: If the adjusted image content detected by the image content detection module reaches the threshold 2, then the frame rate and resolution are adjusted a second time according to the adjustment strategy.

[0110] Through multi-level adjustments in steps S6031-S6034, more accurate identification and processing of application scenarios can continue.

[0111] For example, the image content recognition module identifies and analyzes image feature points and / or motion parameters of image feature points in the original image data. When the change of image feature points and / or motion parameters of image feature points reaches a threshold of 1, the frame rate and resolution are increased by one level, for example, the frame rate is increased from 15FPS to 30FPS. Then, the scene to be identified is identified more accurately and timely, so that the system can perform subsequent control operations, such as screen lighting or camera wake-up. This application embodiment does not limit this.

[0112] In some embodiments, the image content detection module identifies the image content (e.g., face recognition, gesture detection). When certain conditions are met (e.g., face is recognized, different gestures are recognized, and gesture changes between frames are recognized), the frame rate and resolution are adjusted to output the target image data with an appropriate frame rate and resolution. Then, image recognition is performed based on the target image data, which improves the accuracy of the image recognition results.

[0113] Step S604: Use the adjusted frame rate and resolution to acquire images, and synchronize the working parameters corresponding to the adjusted frame rate and resolution to the corresponding recognition and processing modules to ensure that the settings of the entire link are synchronized.

[0114] Step S605: Based on the adjusted frame rate and resolution configuration, continue to preview or capture the image.

[0115] After adjusting the frame rate and resolution, the image acquisition module and the recognition processing module are simultaneously adjusted to the same processing mode. That is, the frame rate and resolution are synchronized to the output of the AON sensor and the input of the subsequent recognition processing module. The AON sensor acquires target image data based on high resolution and high frame rate, and the recognition processing module performs recognition processing based on the target image data to obtain more accurate recognition results, which are then used by the subsequent system to perform corresponding operations, such as screen wake-up and camera opening.

[0116] It should be noted that the selection of threshold 1 and threshold 2 can be based on a variety of factors. For example, based on the number of image frames required for accurate identification of the target object in the application scenario, and the rate of change of the action posture obtained when the acquisition parameters are adjusted, the frame rate and resolution need to be adjusted at what time, and then the corresponding threshold 1 and threshold 2 are determined. The thresholds are used as the judgment conditions on which the adjustment time point is determined.

[0117] This application adjusts the acquisition parameters (frame rate and resolution) of the AON sensor based on image feature points and / or their motion parameters. Simultaneously, leveraging the characteristics of the underlying processing, the operating parameters of the recognition processing module are synchronized according to the adjusted frame rate and resolution, ensuring the normal flow and processing of data in the system after adjustment. For example, different frame rate and resolution adjustment strategies are adopted based on the characteristics of the image recognition content in the application scenario. For instance, for portrait recognition scenarios (face recognition, eye recognition), a low frame rate and high resolution can be set. For gesture detection scenarios, a high frame rate is set to match rapid gesture changes, and a low resolution is set to reduce system power consumption. This application can also adaptively adjust, for example, the frame rate and resolution, based on the self-feedback parameters of the image acquisition module and the image content detection module.

[0118] In some embodiments, the accuracy of image recognition processing can also be achieved through the following examples.

[0119] Example 1: Adjusting the frame rate and resolution can not only adjust the acquisition parameters of the AON sensor, but also the processing strategy for the image data stream. For example, when the recognition processing module reads the data frames of the target image data, the interval between reading the data frames can be adjusted (interval of 3 frames, interval of 2 frames, and frame-by-frame reading), thereby reducing the pressure on image data processing and reducing system power consumption.

[0120] Example 2: Adjusting the acquisition parameters is not limited to frame rate and resolution. The amount of image data can also be adjusted by modifying the image bit width and target image depth information, thereby reducing the processing load on the algorithm and saving system power. Therefore, there are more options and corresponding adjustment strategies for related configurations, allowing for a balance between overall system recognition and processing performance and power consumption, ultimately reducing system power consumption and improving the accuracy of image recognition.

[0121] Based on the image acquisition method of the above embodiments, this application also provides an image acquisition device, such as... Figure 7 As shown, Figure 7 This is a schematic diagram of an image acquisition device provided in an embodiment of this application. The image acquisition device 70 includes: a first acquisition unit 701, used to acquire raw image data of a target object through an image acquisition module; a first determination unit 702, used to determine the application scenario corresponding to the raw image data by detecting the image content in the raw image data, wherein the application scenario represents a scenario for recognizing and processing the target object; a second determination unit 703, used to determine target acquisition parameters matching the application scenario; and a second acquisition unit 704, used to control the image acquisition module to acquire images of the target object based on the target acquisition parameters to obtain target image data.

[0122] In this embodiment of the application, the first determining unit 702 is further configured to obtain image feature points and / or motion parameters of the image feature points by detecting image content in the original image data; and to match the image feature points and / or motion parameters of the image feature points with a preset application scenario to obtain the application scenario corresponding to the original image data.

[0123] In this embodiment of the application, the target acquisition parameters include at least one of the following: frame rate, resolution, focal length, and image bit width information.

[0124] In this embodiment of the application, the second determining unit 703 is further configured to determine the acquisition parameters matching the application scenario according to the first mapping relationship, and obtain the target acquisition parameters, wherein the first mapping relationship characterizes the correspondence between the application scenario and the acquisition parameters.

[0125] In this embodiment of the application, the first mapping relationship includes: if the application scenario is an application scenario for recognizing the action of the target object, then the target acquisition parameters include a first frame rate, which is higher than the second frame rate used to acquire the original image data; if the application scenario is an application scenario for recognizing the target object or recognizing local details of the target object, then the target acquisition parameters include a first resolution, which is higher than the second resolution used to acquire the original image data.

[0126] In this embodiment of the application, the second determining unit 703 is further configured to determine the adjustment range of the acquisition parameters matching the application scenario according to the second mapping relationship, thereby obtaining the adjustment range of the target acquisition parameters, wherein the second mapping relationship characterizes the correspondence between the application scenario and the adjustment range of the acquisition parameters; and to determine the target acquisition parameters within the adjustment range of the target acquisition parameters based on the depth information of the target object in the original image data.

[0127] In this embodiment of the application, the second acquisition unit 704 is further configured to determine an adjustment time point based on the expected number of image frames required for the identification processing of the target object in the application scenario, or the time required to complete the identification processing of the target object in the application scenario; at the adjustment time point, control the image acquisition module to acquire images of the target object based on the target acquisition parameters to obtain target image data.

[0128] In this embodiment, the first determining unit 702 is further configured to detect local information of the image content in the target image data, obtain local image feature points and / or motion parameters of the local image feature points; determine the target application scenario corresponding to the target image data based on the local image feature points and / or the motion parameters of the local image feature points, wherein the target application scenario represents a scenario for recognizing and processing local details of the target object; the second acquisition unit 704 is further configured to determine intermediate acquisition parameters that match the target application scenario if the target acquisition parameters do not match the acquisition parameters corresponding to the target application scenario; and control the image acquisition module to acquire images of the target object based on the intermediate acquisition parameters to obtain intermediate image data.

[0129] In this embodiment of the application, the image acquisition device 70 further includes an identification unit, which is used to determine the operating parameters of the identification processing module according to the target acquisition parameters; the identification processing module performs identification processing on the target object in the target image data according to the operating parameters.

[0130] It should be noted that the image acquisition device provided in the above embodiments is only illustrated by the division of the above-described program modules when performing image processing. In practical applications, the above processing can be assigned to different program modules as needed, that is, the internal structure of the device can be divided into different program modules to complete all or part of the processing described above. Furthermore, the image acquisition device and image acquisition method embodiments provided in the above embodiments belong to the same concept, and their specific implementation process and beneficial effects are detailed in the method embodiments, and will not be repeated here. For technical details not disclosed in the device embodiments, please refer to the description of the method embodiments of this application for understanding.

[0131] In the embodiments of this application, Figure 8 This is a schematic diagram of the composition structure of the image acquisition device proposed in the embodiments of this application, as shown below. Figure 8 As shown, the image acquisition device 80 proposed in the embodiments of this application may further include a processor 801 and a memory 802 storing executable instructions of the processor 801. In some embodiments of this application, the image acquisition device 80 may further include a communication interface 803 and a bus 804 for connecting the processor 801, the memory 802 and the communication interface 803.

[0132] In the embodiments of this application, the processor 801 can be at least one of the following: Application-Specific Integrated Circuit (ASIC), Digital Signal Processor (DSP), Digital Signal Processing Device (DSPD), Programmable Logic Device (PLD), Field Programmable Gate Array (FPGA), Central Processing Unit (CPU), Controller, Microcontroller, and Microprocessor. It is understood that for different devices, the electronic device used to implement the above-mentioned processor function can also be other types, and this application embodiment does not specifically limit this. The image acquisition device 80 may also include a memory 802, which can be connected to the processor 801. The memory 802 is used to store executable program code, which includes computer operation instructions. The memory 802 may include high-speed RAM memory and may also include non-volatile memory, such as at least two disk drives.

[0133] In the embodiments of this application, bus 804 is used to connect communication interface 803, processor 801 and memory 802 and the mutual communication between these devices.

[0134] In embodiments of this application, memory 802 is used to store instructions and data.

[0135] In the embodiments of this application, the processor 801 is configured to acquire raw image data of a target object through an image acquisition module; determine the application scenario corresponding to the raw image data by detecting the image content in the raw image data, wherein the application scenario represents a scenario for recognizing and processing the target object; determine target acquisition parameters that match the application scenario; and control the image acquisition module to acquire images of the target object based on the target acquisition parameters to obtain target image data.

[0136] In practical applications, the aforementioned memory 802 can be volatile memory, such as random-access memory (RAM); or non-volatile memory, such as read-only memory (ROM), flash memory, hard disk drive (HDD), or solid-state drive (SSD); or a combination of the above types of memory, and provide instructions and data to the processor 801.

[0137] Furthermore, in this embodiment, the functional modules can be integrated into one processing unit, or each unit can exist physically separately, or two or more units can be integrated into one unit. The integrated unit can be implemented in hardware or as a software functional module.

[0138] If the integrated unit is implemented as a software functional module and is not sold or used as an independent product, it can be stored in a computer-readable storage medium. Based on this understanding, the technical solution of this embodiment, in essence, or the part that contributes to the prior art, or all or part of the technical solution, can be embodied in the form of a software product. This computer software product is stored in a storage medium and includes several instructions to cause a computer device (which may be a personal computer, server, or network device, etc.) or processor to execute all or part of the steps of the method of this embodiment. The aforementioned storage medium includes various media capable of storing program code, such as USB flash drives, portable hard drives, read-only memory (ROM), random access memory (RAM), magnetic disks, or optical disks.

[0139] This application provides a computer-readable storage medium having a program stored thereon, which, when executed by a processor, implements the image acquisition method as described in any of the above embodiments.

[0140] For example, the program instructions corresponding to an image acquisition method in this embodiment can be stored on a storage medium such as an optical disc, hard disk, or USB flash drive. When the program instructions corresponding to an image acquisition method in the storage medium are read or executed by an electronic device, the image acquisition method described in any of the above embodiments can be implemented.

[0141] Those skilled in the art will understand that embodiments of this application can be provided as methods, systems, or computer program products. Therefore, this application can take the form of hardware embodiments, software embodiments, or embodiments combining software and hardware aspects. Furthermore, this application can take the form of a computer program product implemented on one or more computer-usable storage media (including, but not limited to, disk storage and optical storage) containing computer-usable program code.

[0142] This application is described with reference to schematic and / or block diagrams of implementations of methods, apparatus (systems), and computer program products according to embodiments of this application. It should be understood that each block of the schematic and / or block diagrams can be implemented by computer program instructions, and combinations of blocks in the schematic and / or block diagrams can be implemented. These computer program instructions can be provided to a processor of a general-purpose computer, special-purpose computer, embedded processor, or other programmable data processing apparatus to produce a machine, such that the instructions, which execute via the processor of the computer or other programmable data processing apparatus, create a machine for implementing the schematic and / or block diagrams. Figure 1 One or more processes and / or boxes Figure 1 A device that provides the functions specified in one or more boxes.

[0143] These computer program instructions may also be stored in a computer-readable storage medium that can direct a computer or other programmable data processing device to function in a particular manner, such that the instructions stored in the computer-readable storage medium produce an article of manufacture including instruction means, which are implemented in the implementation flow diagram. Figure 1 One or more processes and / or boxes Figure 1 The function specified in one or more boxes.

[0144] These computer program instructions may also be loaded onto a computer or other programmable data processing equipment to cause a series of operational steps to be performed on the computer or other programmable equipment to produce a computer-implemented process, thereby providing instructions that execute on the computer or other programmable equipment for implementing the process. Figure 1 One or more processes and / or boxes Figure 1 The steps of the function specified in one or more boxes.

[0145] The above description is merely a preferred embodiment of this application and is not intended to limit the scope of protection of this application.

Claims

1. An image acquisition method, characterized in that, The method includes: The original image data of the target object is acquired through the image acquisition module; By detecting the image content in the original image data, image feature points and / or motion parameters of the image feature points are obtained; based on the image feature points and / or motion parameters of the image feature points, a preset application scenario is matched to obtain the application scenario corresponding to the original image data; the preset application scenarios include face recognition scenarios, eye recognition scenarios, gesture detection scenarios, and specific action detection scenarios; the application scenario represents the scenario in which the target object is identified and processed. Determine the target acquisition parameters that match the application scenario; The image acquisition module is controlled to acquire images of the target object based on the target acquisition parameters, thereby obtaining target image data; The determination of the target acquisition parameters matching the application scenario includes: Based on the first mapping relationship, the acquisition parameters that match the application scenario are determined to obtain the target acquisition parameters. The first mapping relationship represents the correspondence between the application scenario and the acquisition parameters. The first mapping relationship includes: If the application scenario is for recognizing the action of the target object, then the target acquisition parameters include a first frame rate, which is higher than the second frame rate used to acquire the original image data; If the application scenario is for identifying the target object or identifying local details of the target object, then the target acquisition parameters include a first resolution, which is higher than the second resolution used to acquire the original image data.

2. The method according to claim 1, characterized in that, The target acquisition parameters include at least one of the following: frame rate, resolution, focal length, and image bit width information.

3. The method according to claim 1 or 2, characterized in that, The determination of the target acquisition parameters matching the application scenario includes: Based on the second mapping relationship, the adjustment range of the acquisition parameters that match the application scenario is determined, and the adjustment range of the target acquisition parameters is obtained. The second mapping relationship represents the correspondence between the application scenario and the adjustment range of the acquisition parameters. The target acquisition parameters are determined within the adjustment range of the target acquisition parameters based on the depth information of the target object in the original image data.

4. The method according to claim 1, characterized in that, The image acquisition module is controlled to acquire images of the target object based on the target acquisition parameters to obtain target image data, including: The adjustment time point is determined based on the expected number of image frames required to identify the target object in the application scenario, or the time required to complete the identification process of the target object in the application scenario. At the adjusted time point, the image acquisition module is controlled to acquire images of the target object based on the target acquisition parameters, thereby obtaining target image data.

5. The method according to claim 1 or 2, characterized in that, The method further includes: Detect local information of image content in the target image data to obtain local image feature points and / or motion parameters of local image feature points; Based on the local image feature points and / or the motion parameters of the local image feature points, the target application scenario corresponding to the target image data is determined, and the target application scenario represents the scenario of recognizing and processing the local details of the target object; If the target acquisition parameters do not match the acquisition parameters corresponding to the target application scenario, then an intermediate acquisition parameter that matches the target application scenario is determined. The image acquisition module is controlled to acquire images of the target object based on the intermediate acquisition parameters, thereby obtaining intermediate image data.

6. The method according to claim 1 or 2, characterized in that, The method further includes: The operating parameters of the identification and processing module are determined based on the target acquisition parameters. The recognition processing module is used to perform recognition processing on the target object in the target image data according to the working parameters.

7. An image acquisition device, characterized in that, The device includes: The first acquisition unit is used to acquire the original image data of the target object through the image acquisition module; The first determining unit is configured to obtain image feature points and / or motion parameters of the image feature points by detecting image content in the original image data; and to match the image feature points and / or motion parameters of the image feature points with a preset application scenario to obtain an application scenario corresponding to the original image data; the preset application scenario includes a face recognition scenario, an eye recognition scenario, a gesture detection scenario, and a specific action detection scenario; the application scenario represents a scenario in which the target object is identified and processed. The second determining unit is configured to determine acquisition parameters matching the application scenario based on a first mapping relationship, thereby obtaining target acquisition parameters. The first mapping relationship characterizes the correspondence between the application scenario and the acquisition parameters. The first mapping relationship includes: if the application scenario is for recognizing the action of the target object, then the target acquisition parameters include a first frame rate, which is higher than a second frame rate used for acquiring the original image data; if the application scenario is for recognizing the target object or recognizing local details of the target object, then the target acquisition parameters include a first resolution, which is higher than a second resolution used for acquiring the original image data. The second acquisition unit is used to control the image acquisition module to acquire images of the target object based on the target acquisition parameters, and obtain target image data.

8. An image acquisition device, characterized in that, Including memory and processor; The memory stores computer programs that can run on a processor; When the processor executes the program, it implements the steps of the method according to any one of claims 1 to 6.

9. A computer-readable storage medium, characterized in that, It stores executable instructions that, when executed by a processor, implement the method described in any one of claims 1 to 6.

Images