A focusing control method, device, equipment and medium based on image signal

Abstract

The present application relates to the technical field of shooting lenses, and to a focusing control method, device, equipment and medium based on image signals. Distributed images are collected through multiple lenses of a camera device; the distributed images are fused based on the feature information in the distributed images to generate a panoramic image; the corresponding image area in the panoramic image is detected according to the preset points of interest of each lens, and the feature quality corresponding to the image area is evaluated; the initial step size of the focal length adjustment of each lens is determined according to the feature quality, and the iterative step size of the focal length adjustment of each lens is determined according to the initial step size of the adjacent lens; the focus position of each lens is adjusted based on the initial step size and the iterative step size. The present application can accurately determine the image area that needs to be optimized, and through the combined use of the initial step size and the iterative step size, gradually approach the optimal focus position, further improve the image quality and clarity of the areas corresponding to these points of interest, and realize coordinated and unified focus adjustment under multiple lenses.

Description

Technical Field

[0001] The present application relates to the technical field of photographic lenses, and in particular to a focusing control method, device, equipment and medium based on image signals. Background Art

[0002] In imaging systems, whether in photography, videography, automated production, real-time monitoring or machine vision, the focus alignment of the optical lens is a key factor in determining the final image quality. Autofocus technology enables the imaging system to quickly and accurately obtain clear images by automatically adjusting the lens position or focal length, greatly improving the efficiency and performance of the imaging system.

[0003] However, when dealing with a camera device equipped with multiple lenses, it is often impossible to achieve coordinated and unified focus adjustment of the multiple lenses. It is easy for adjustment of one lens to affect the shooting effects of other lenses, resulting in low efficiency and accuracy of multi-lens focus adjustment. Summary of the invention

[0004] The embodiments of the present application provide a focus control method, device, equipment and medium based on an image signal, which can solve the problem of low efficiency and accuracy of multi-lens focus adjustment at least to a certain extent.

[0005] Other features and advantages of the present application will become apparent from the following detailed description, or may be learned in part by the practice of the present application.

[0006] According to one aspect of the present application, a focusing control method based on image signals is provided, comprising: acquiring distributed images through multiple lenses of a camera device; fusing the distributed images based on feature information in the distributed images to generate a panoramic image; detecting image areas corresponding to each point of interest in the panoramic image according to points of interest preset in each lens, and evaluating feature quality corresponding to the image area; determining an initial step size for adjusting the focal length of each lens according to the feature quality, and determining an iterative step size for adjusting the focal length of each lens according to the initial step size of adjacent lenses; and adjusting the focus position of each lens based on the initial step size and the iterative step size.

[0007] In the present application, based on the aforementioned scheme, before collecting distributed images through multiple lenses of the camera device, it also includes: obtaining ambient lighting parameters and brightness parameters within the lens field of view; adjusting the exposure time and gain value of each lens according to the ambient lighting parameters and the brightness parameters.

[0008] In the present application, based on the aforementioned scheme, the distributed images are fused based on the feature information in the distributed images to generate a panoramic image, including: using a deep learning model to extract feature points in the distributed images to obtain a set of feature vectors; performing feature matching on the sampled feature vectors by randomly sampling the feature vector set to obtain a matching vector group; and performing feature fusion based on the feature information corresponding to the vector group to generate a panoramic image.

[0009] In the present application, based on the aforementioned scheme, the image area corresponding to each interest point in the panoramic image is detected according to the interest points preset by each lens, and the feature quality corresponding to the image area is evaluated, including: detecting the image area corresponding to each interest point in the panoramic image through a target detection network, and outputting a set of bounding boxes corresponding to each image area; based on the set of bounding boxes corresponding to the image area, evaluating the feature quality corresponding to the image area in each dimension.

[0010] In the present application, based on the aforementioned scheme, the initial step size of the focal length adjustment of each lens is determined according to the feature quality, and the iterative step size of the focal length adjustment of each lens is determined according to the initial step size of the adjacent lens, including: determining a focusing function based on the feature quality corresponding to the image area in each dimension; determining the initial step size of the focal length adjustment of each lens according to the focusing function; determining the iterative step size of each subsequent adjustment of the focal length adjustment of each lens according to the overlap of the shooting ranges between adjacent lenses and the initial step size.

[0011] In the present application, based on the aforementioned scheme, the focusing position of each lens is adjusted based on the initial step size and the iterative step size, including: adjusting the focusing position of each lens based on the initial step size, and then continuing to adjust based on the iterative step size.

[0012] In the present application, based on the above-mentioned solution, after adjusting the focus position of each lens based on the initial step size and the iteration step size, the method further includes: recording the focus information of each lens during each adjustment.

[0013] According to one aspect of the present application, there is provided a focus control device based on an image signal, comprising:

[0014] A collection unit, used for collecting distributed images through multiple lenses of a camera device;

[0015] A fusion unit, configured to fuse the distributed images based on feature information in the distributed images to generate a panoramic image;

[0016] A quality unit, configured to detect, based on the interest points preset by each lens, an image area corresponding to each interest point in the panoramic image, and evaluate a feature quality corresponding to the image area;

[0017] A step length unit, used to determine an initial step length of focal length adjustment of each lens according to the characteristic quality, and determine an iterative step length of focal length adjustment of each lens according to the initial step length of an adjacent lens;

[0018] An adjusting unit is used to adjust the focus position of each lens based on the initial step size and the iteration step size.

[0019] In the present application, based on the aforementioned scheme, before collecting distributed images through multiple lenses of the camera device, it also includes: obtaining ambient lighting parameters and brightness parameters within the lens field of view; adjusting the exposure time and gain value of each lens according to the ambient lighting parameters and the brightness parameters.

[0020] In the present application, based on the aforementioned scheme, the distributed images are fused based on the feature information in the distributed images to generate a panoramic image, including: using a deep learning model to extract feature points in the distributed images to obtain a set of feature vectors; performing feature matching on the sampled feature vectors by randomly sampling the feature vector set to obtain a matching vector group; and performing feature fusion based on the feature information corresponding to the vector group to generate a panoramic image.

[0021] In the present application, based on the aforementioned scheme, the image area corresponding to each interest point in the panoramic image is detected according to the interest points preset by each lens, and the feature quality corresponding to the image area is evaluated, including: detecting the image area corresponding to each interest point in the panoramic image through a target detection network, and outputting a set of bounding boxes corresponding to each image area; based on the set of bounding boxes corresponding to the image area, evaluating the feature quality corresponding to the image area in each dimension.

[0022] In the present application, based on the aforementioned scheme, the initial step size of the focal length adjustment of each lens is determined according to the feature quality, and the iterative step size of the focal length adjustment of each lens is determined according to the initial step size of the adjacent lens, including: determining a focusing function based on the feature quality corresponding to the image area in each dimension; determining the initial step size of the focal length adjustment of each lens according to the focusing function; and determining the iterative step size of each subsequent adjustment according to the overlap of the shooting ranges between adjacent lenses and the initial step size.

[0023] In the present application, based on the aforementioned scheme, the focusing position of each lens is adjusted based on the initial step size and the iterative step size, including: adjusting the focusing position of each lens based on the initial step size, and then continuing to adjust based on the iterative step size.

[0024] In the present application, based on the above-mentioned solution, after adjusting the focus position of each lens based on the initial step size and the iteration step size, the method further includes: recording the focus information of each lens during each adjustment.

[0025] According to one aspect of the present application, a computer-readable medium is provided, on which a computer program is stored. When the computer program is executed by a processor, the focusing control method based on the image signal as described in the above embodiment is implemented.

[0026] According to one aspect of the present application, an electronic device is provided, comprising: one or more processors; a storage device for storing one or more programs, wherein when the one or more programs are executed by the one or more processors, the one or more processors implement a focusing control method based on an image signal as described in the above-mentioned embodiments.

[0027] According to one aspect of the present application, a computer program product or a computer program is provided, the computer program product or the computer program comprising computer instructions, the computer instructions being stored in a computer-readable storage medium. A processor of a computer device reads the computer instructions from the computer-readable storage medium, and the processor executes the computer instructions, so that the computer device executes the image signal-based focus control method provided in the above-mentioned various optional implementations.

[0028] The technical solution of the present application is to collect distributed images through multiple lenses of a camera device; based on the feature information in the distributed images, the distributed images are fused to generate a panoramic image; according to the interest points preset by each lens, the image area corresponding to each interest point in the panoramic image is detected, and the feature quality corresponding to the image area is evaluated; according to the feature quality, the initial step length of the focal length adjustment of each lens is determined, and according to the initial step length of the adjacent lens, the iterative step length of the focal length adjustment of each lens is determined; based on the initial step length and the iterative step length, the focus position of each lens is adjusted. By collecting distributed images through multiple lenses and fusing them into a panoramic image, the integrity and field of view of the image are improved. By detecting the image area corresponding to each interest point in the panoramic image and its feature quality, the image area that needs to be optimized can be accurately determined. By combining the initial step length and the iterative step length, the optimal focus position can be gradually approached, and the image quality and clarity of the areas corresponding to these interest points can be further improved, realizing the coordinated and unified focus adjustment under multiple lenses.

[0029] It should be understood that the foregoing general description and the following detailed description are exemplary and explanatory only and are not restrictive of the present application. BRIEF DESCRIPTION OF THE DRAWINGS

[0030] The drawings herein are incorporated into the specification and constitute a part of the specification, illustrate embodiments consistent with the present application, and together with the specification are used to explain the principles of the present application. Obviously, the drawings described below are only some embodiments of the present application, and for ordinary technicians in this field, other drawings can be obtained based on these drawings without creative work.

[0031] Figure 1 The flowchart of a focusing control method based on an image signal in one embodiment of the present application is schematically shown.

[0032] Figure 2 The flowchart for determining the initial step size and the iteration step size in one embodiment of the present application is schematically shown.

[0033] Figure 3 A schematic diagram of a focus control device based on an image signal in an embodiment of the present application is schematically shown.

[0034] Figure 4 A schematic diagram of the structure of a computer system suitable for implementing an electronic device of an embodiment of the present application is shown. DETAILED DESCRIPTION

[0035] Example embodiments will now be described more fully with reference to the accompanying drawings. However, example embodiments can be implemented in a variety of forms and should not be construed as limited to the examples set forth herein; rather, these embodiments are provided so that this application will be more comprehensive and complete and fully convey the concept of the example embodiments to those skilled in the art.

[0036] In addition, described feature, structure or characteristic can be combined in one or more embodiments in any suitable manner. In the following description, many specific details are provided to provide a full understanding of the embodiments of the present application. However, those skilled in the art will appreciate that the technical scheme of the present application can be put into practice without one or more of the specific details, or other methods, components, devices, steps, etc. can be adopted. In other cases, known methods, devices, realizations or operations are not shown or described in detail to avoid blurring the various aspects of the present application.

[0037] The block diagrams shown in the accompanying drawings are merely functional entities and do not necessarily correspond to physically independent entities. That is, these functional entities may be implemented in software form, or in one or more hardware modules or integrated circuits, or in different networks and / or processor devices and / or microcontroller devices.

[0038] The flowcharts shown in the accompanying drawings are only exemplary and do not necessarily include all the contents and operations / steps, nor must they be executed in the order described. For example, some operations / steps can be decomposed, and some operations / steps can be combined or partially combined, so the actual execution order may change according to actual conditions.

[0039] The implementation details of the technical solution of this application are described in detail below:

[0040] Figure 1 FIG. 1 is a flow chart of a focusing control method based on an image signal according to an embodiment of the present application. Figure 1 As shown, the focus control method based on the image signal at least includes steps S110 to S150, which are described in detail as follows:

[0041] In step S110, distributed images are collected by using multiple lenses of a camera device.

[0042] In one embodiment of the present application, before collecting distributed images through multiple lenses of a camera device, the method further includes:

[0043] Get the ambient lighting parameters and the brightness parameters within the lens field of view;

[0044] The exposure time and gain value of each lens are adjusted according to the ambient light parameter and the brightness parameter.

[0045] In one embodiment of the present application, the camera device is equipped with multiple lenses, each of which is responsible for capturing images of different areas or angles. The camera device is used in application scenarios such as environmental monitoring in large scenes and production environment monitoring of precision instruments.

[0046] Optionally, the lens configuration on the camera device in this embodiment takes into account factors such as field of view overlap, resolution, focal length, etc. to ensure the integrity and accuracy of the distributed image.

[0047] Multiple light sensors are installed around or inside the camera device to monitor the ambient light parameters in real time. These light sensors have high sensitivity, wide spectral response and fast response time to accurately capture light changes. A central processor and image processing unit that communicate with each other are installed inside the camera device. The central processor is responsible for overall control and logical judgment, while the image processing unit accelerates the execution of image processing algorithms. The central processor regularly obtains ambient light parameters such as light intensity and color temperature from the light sensor network. These ambient light parameters are transmitted to the central processor through a digital interface and processed by the central processor. The image processing unit analyzes the preview image of each lens and calculates brightness parameters such as average brightness and brightness distribution within the lens field of view. These brightness parameters reflect the actual lighting conditions within the lens field of view.

[0048] The central processor fuses the ambient light parameters and brightness parameters. Based on the fused ambient light parameters and brightness parameters, the central processor calculates the optimal exposure time for each lens. The exposure time is adjusted by adjusting the shutter speed or electronic shutter of the camera device. After the exposure time is determined, the central processor further calculates the gain value of each lens. The gain value is adjusted by adjusting the amplifier gain value or digital gain value of the camera device. The gain value should be adjusted to ensure that the dynamic range of the image signal is maximized while avoiding excessive noise or image distortion.

[0049] Before collecting distributed images, the exposure time and gain value of each lens are adjusted according to the ambient lighting parameters and the brightness parameters in the lens field of view to ensure that high-quality images can be collected under different lighting conditions, providing a good foundation for subsequent image fusion and focal length adjustment. By real-time monitoring of ambient lighting parameters and brightness parameters in the lens field of view, and dynamically adjusting lens parameters based on these parameters, intelligent adaptive adjustment of image acquisition conditions is achieved. This adjustment method has higher flexibility and accuracy than traditional manual adjustment or preset fixed parameter methods.

[0050] In step S120, the distributed images are fused based on the feature information in the distributed images to generate a panoramic image.

[0051] In one embodiment of the present application, based on feature information in the distributed images, the distributed images are fused to generate a panoramic image, including:

[0052] Extract feature points from the distributed image using a deep learning model to obtain a feature vector set;

[0053] By randomly sampling the feature vector set, feature matching is performed on the sampled feature vectors to obtain a matching vector group;

[0054] Based on the feature information corresponding to the vector group, feature fusion is performed to generate a panoramic image.

[0055] In an embodiment of the present application, the feature information includes feature points in a distributed image, image edges, and other information. In this embodiment, a deep learning model can be used to extract feature points of a distributed image to obtain a feature vector set consisting of vectors corresponding to a plurality of feature points. The feature vector set is randomly sampled, and feature matching is performed on a set of feature vectors obtained by sampling to obtain a matching vector set.

[0056] Specifically, a set of feature vectors is randomly sampled from the feature vector set, and feature matching is performed on the sampled feature vectors to find similar feature vectors in the feature vector set. In the feature matching process, for two feature vectors and , calculate the matching parameters for:

[0057]

[0058] Where exp represents the natural exponential function, represents the Euclidean distance, and σ represents the preset matching factor.

[0059] Afterwards, the matching parameters between different feature vectors are compared, and the vectors whose matching parameters are greater than the set threshold are determined as the matching vector group. After obtaining the matching vector group, the distributed image is feature fused based on the features corresponding to the vector group to generate a panoramic image. Specifically, the target features corresponding to the vector groups in the distributed image are determined, and then the target features are weighted averaged or linearly combined, and the remaining features other than the target features are also adaptively adjusted and linearly combined to generate a panoramic image.

[0060] In the above process, distributed images are collected by multiple lenses of the camera device, and the feature information in these images is fused to generate a panoramic image. This process can fully utilize the viewing angle advantages of multiple lenses, reduce image blind spots, and improve image integrity and clarity.

[0061] In step S130, according to the interest points preset in each lens, the image area corresponding to each interest point in the panoramic image is detected, and the feature quality corresponding to the image area is evaluated.

[0062] In one embodiment of the present application, according to the interest points preset by each lens, detecting the image area corresponding to each interest point in the panoramic image, and evaluating the feature quality corresponding to the image area, includes:

[0063] Detect the image area corresponding to each point of interest in the panoramic image through the object detection network, and output the set of bounding boxes corresponding to each image area;

[0064] Based on a set of bounding boxes corresponding to the image region, the feature quality corresponding to the image region in each dimension is evaluated.

[0065] In one embodiment of the present application, an image area corresponding to each point of interest in a panoramic image is detected through a target detection network, and a bounding box set corresponding to each image area is output, wherein the bounding box set includes coordinates corresponding to the four corners of the rectangular area.

[0066] Based on the bounding box set corresponding to the image area, the feature quality corresponding to each dimension of the image area is evaluated, wherein each dimension may include a clarity dimension, a contrast dimension, a saturation dimension, and the like.

[0067] Exemplarily, the first parameter for measuring the contrast of an image region is for:

[0068]

[0069] in, N Represents the image area P The number of pixels within Represents the mean value of the pixel values ​​in the image area. Represents the image at coordinates The pixel value at .

[0070] Exemplary, second parameter for measuring the saturation of an image region for:

[0071]

[0072] in, is a function that converts pixel value to saturation.

[0073] In step S140, the initial step length of the focal length adjustment of each lens is determined according to the characteristic quality, and the iterative step length of the focal length adjustment of each lens is determined according to the initial step length of the adjacent lens.

[0074] like Figure 2 As shown, in one embodiment of the present application, determining the initial step length of the focal length adjustment of each lens according to the characteristic quality, and determining the iterative step length of the focal length adjustment of each lens according to the initial step length of the adjacent lens, includes:

[0075] S210, determining a focusing function of each lens based on the feature quality corresponding to each dimension of the image area;

[0076] S220, determining an initial step length of focal length adjustment of each lens according to the focusing function;

[0077] S230: Determine the iterative step length of each subsequent adjustment of the focal length of each lens according to the overlap of the shooting ranges of adjacent lenses and in combination with the initial step length.

[0078] In one embodiment of the present application, it is assumed that n feature dimensions, the feature quality of each dimension can be expressed as ,in f represents the focal length, i Indicates the identifier corresponding to each dimension, and each dimension corresponds to a weight In this embodiment, the focusing function for:

[0079]

[0080] here, The focal length corresponding to the maximum value f This is the optimal focal length we are looking for. In other words, is the formula for calculating the optimal focal length.

[0081] The current focal length is , initial step length for:

[0082]

[0083] in, represents the step size factor determined based on historical data, is a focal length change. The initial step length calculated in this embodiment is used to represent the corresponding change parameter when each lens is adjusted initially for the first time, and the iteration step length is used to represent the step length when the lens is adjusted iteratively after the first adjustment. In practical applications, the initial step length is at least greater than the iteration step length. N times, of which N Greater than 10 to improve the efficiency and accuracy of focusing of each lens.

[0084] During the iteration process, the overlap of shooting ranges between adjacent shots needs to be considered.

[0085] Below is the lens g Take the lens as an example g The focus adjustment method of the other lenses is the same.

[0086] Hypothetical lens g have m adjacent shots, and adjacent shots j With lens g The overlap of the shooting range is , j≤m In this embodiment, an overlap function is defined: , which indicates the focal length f Lower camera g The average overlap with all neighboring shots.

[0087] Then, the overlap function With initial step length Combined to determine the iteration step size for each adjustment for:

[0088]

[0089] in, Indicates the number of adjustments. Indicates The focal length at the time of the first adjustment, is a decay factor that controls the decay speed of the iteration step size as the overlap increases. According to the above calculation, the higher the overlap, the faster the step size decays.

[0090] In one embodiment of the present application, the best focus position can be gradually approached by combining the initial step size and the iterative step size. The initial step size is used to quickly approach the focus area, while the iterative step size is used to make fine adjustments in the area, thereby improving the focusing efficiency and accuracy.

[0091] In step S150, the focus position of each lens is adjusted based on the initial step size and the iteration step size.

[0092] In one embodiment of the present application, adjusting the focus position of each lens based on the initial step size and the iteration step size includes: adjusting the focus position of each lens based on the initial step size, and then continuing to adjust based on the iteration step size.

[0093] In one embodiment of the present application, a user triggers a focus adjustment command through a user interface or a preset script. The adjustment unit receives the command and generates a corresponding control signal according to the command type (such as manual adjustment, automatic focus, etc.). and initial step length , calculate the focal length after the initial adjustment + . Send instructions to the lens system to adjust the focal length to . Capture an image using the adjusted focal length and evaluate the image quality.

[0094] Set an iteration counter and start the iteration process. Calculate the step size of this iteration based on the current focal length, the quality evaluation result of the previous iteration, and the calculation method of the iteration step size. . Calculate the focal length for the next iteration The system then sends a command to the lens system to make adjustments. It then captures an image using the new focal length and evaluates the image quality.

[0095] Check whether the iteration termination condition is met, which includes reaching the maximum number of iterations, the image quality index reaching the preset threshold, or the focal length adjustment amount being less than the minimum step length threshold, etc. If the condition is met, the iteration is terminated; otherwise, the iteration counter is increased and the iteration steps are repeated.

[0096] Through the above steps, a computer-controlled lens focus position adjustment system based on the initial step size and the iterative step size is realized. The focus adjustment step size is determined based on the feature quality, and the focus position of each lens can be adjusted in a targeted manner, and the optimal focal length of each lens can be automatically and efficiently found, and high-quality images can be captured, thereby further improving the image quality and clarity of the areas corresponding to these points of interest.

[0097] In one embodiment of the present application, the processed focus information is recorded and stored in the data storage module, and each record should contain key information such as timestamp, lens identification, focus parameters, etc. An index mechanism is established to facilitate the subsequent rapid query of focus information records based on conditions such as lens identification and time range.

[0098] Optionally, the user interface provides a viewing function for focus information records, allowing users to filter and view records according to different conditions. Users can export focus information records as files for further analysis or processing in other software. By recording focus information after adjusting the focus position of each lens, it can provide a reference for subsequent focus operations and further optimize the focus strategy, and also help the system self-learning and optimization.

[0099] The technical solution of the present application is to collect distributed images through multiple lenses of a camera device; based on the feature information in the distributed images, the distributed images are fused to generate a panoramic image; according to the interest points preset by each lens, the image area corresponding to each interest point in the panoramic image is detected, and the feature quality corresponding to the image area is evaluated; according to the feature quality, the initial step length of the focal length adjustment of each lens is determined, and according to the initial step length of the adjacent lens, the iterative step length of the focal length adjustment of each lens is determined; based on the initial step length and the iterative step length, the focus position of each lens is adjusted. By collecting distributed images through multiple lenses and fusing them into a panoramic image, the integrity and field of view of the image are improved. By detecting the image area corresponding to each interest point in the panoramic image and its feature quality, the image area that needs to be optimized can be accurately determined. By combining the initial step length and the iterative step length, the optimal focus position can be gradually approached, and the image quality and clarity of the areas corresponding to these interest points can be further improved, realizing the coordinated and unified focus adjustment under multiple lenses.

[0100] The following describes an embodiment of the device of the present application, which can be used to execute the focusing control method based on image signals in the above-mentioned embodiment of the present application. It can be understood that the device can be a computer program (including program code) running in a computer device, for example, the device is an application software; the device can be used to execute the corresponding steps in the method provided in the embodiment of the present application. For details not disclosed in the embodiment of the device of the present application, please refer to the embodiment of the focusing control method based on image signals in the above-mentioned embodiment of the present application.

[0101] Figure 3 A block diagram of a focus control device based on an image signal according to an embodiment of the present application is shown.

[0102] Reference Figure 3 As shown, a focus control device based on an image signal according to an embodiment of the present application includes:

[0103] A collection unit 310, configured to collect distributed images through multiple lenses of a camera device;

[0104] A fusion unit 320, configured to fuse the distributed images based on feature information in the distributed images to generate a panoramic image;

[0105] The quality unit 330 is used to detect the image area corresponding to each interest point in the panoramic image according to the interest points preset by each lens, and evaluate the feature quality corresponding to the image area;

[0106] A step length unit 340, configured to determine an initial step length of focal length adjustment of each lens according to the characteristic quality, and determine an iterative step length of focal length adjustment of each lens according to the initial step length of an adjacent lens;

[0107] The adjusting unit 350 is used to adjust the focus position of each lens based on the initial step size and the iteration step size.

[0108] In the present application, based on the aforementioned scheme, before collecting distributed images through multiple lenses of the camera device, it also includes: obtaining ambient lighting parameters and brightness parameters within the lens field of view; adjusting the exposure time and gain value of each lens according to the ambient lighting parameters and the brightness parameters.

[0109] In the present application, based on the aforementioned scheme, the distributed images are fused based on the feature information in the distributed images to generate a panoramic image, including: using a deep learning model to extract feature points in the distributed images to obtain a set of feature vectors; performing feature matching on the sampled feature vectors by randomly sampling the feature vector set to obtain a matching vector group; and performing feature fusion based on the feature information corresponding to the vector group to generate a panoramic image.

[0110] In the present application, based on the aforementioned scheme, the image area corresponding to each interest point in the panoramic image is detected according to the interest points preset by each lens, and the feature quality corresponding to the image area is evaluated, including: detecting the image area corresponding to each interest point in the panoramic image through a target detection network, and outputting a set of bounding boxes corresponding to each image area; based on the set of bounding boxes corresponding to the image area, evaluating the feature quality corresponding to the image area in each dimension.

[0111] In the present application, based on the aforementioned scheme, the initial step size of the focal length adjustment of each lens is determined according to the feature quality, and the iterative step size of the focal length adjustment of each lens is determined according to the initial step size of the adjacent lens, including: determining a focusing function based on the feature quality corresponding to the image area in each dimension; determining the initial step size of the focal length adjustment of each lens according to the focusing function; and determining the iterative step size of each subsequent adjustment according to the overlap of the shooting ranges between adjacent lenses and the initial step size.

[0112] In the present application, based on the aforementioned scheme, the focusing position of each lens is adjusted based on the initial step size and the iterative step size, including: adjusting the focusing position of each lens based on the initial step size, and then continuing to adjust based on the iterative step size.

[0113] In the present application, based on the above-mentioned solution, after adjusting the focus position of each lens based on the initial step size and the iteration step size, the method further includes: recording the focus information of each lens during each adjustment.

[0114] The technical solution of the present application is to collect distributed images through multiple lenses of a camera device; based on the feature information in the distributed images, the distributed images are fused to generate a panoramic image; according to the interest points preset by each lens, the image area corresponding to each interest point in the panoramic image is detected, and the feature quality corresponding to the image area is evaluated; according to the feature quality, the initial step length of the focal length adjustment of each lens is determined, and according to the initial step length of the adjacent lens, the iterative step length of the focal length adjustment of each lens is determined; based on the initial step length and the iterative step length, the focus position of each lens is adjusted. By collecting distributed images through multiple lenses and fusing them into a panoramic image, the integrity and field of view of the image are improved. By detecting the image area corresponding to each interest point in the panoramic image and its feature quality, the image area that needs to be optimized can be accurately determined. By combining the initial step length and the iterative step length, the optimal focus position can be gradually approached, and the image quality and clarity of the areas corresponding to these interest points can be further improved, realizing the coordinated and unified focus adjustment under multiple lenses.

[0115] Figure 4 A schematic diagram of the structure of a computer system suitable for implementing an electronic device of an embodiment of the present application is shown.

[0116] It should be noted that the computer system of the electronic device in this embodiment is only an example and should not bring any limitation to the functions and scope of use of the embodiments of the present application.

[0117] In this embodiment, the computer system includes a central processing unit 401, which can perform various appropriate actions and processes according to the program stored in the read-only memory 402 or the program loaded from the storage part 408 to the random access memory 403, such as executing the method described in the above embodiment. Various programs and data required for system operation are also stored in the random access memory 403. The central processing unit 401, the read-only memory 402 and the random access memory 403 are connected to each other through a bus 404. The input / output interface 405 is also connected to the bus 404.

[0118] The following components are connected to the input / output interface 405: an input section 406 including a keyboard, a mouse, etc.; an output section 407 including a cathode ray tube (CRT), a liquid crystal display (LCD), etc., and a speaker; a storage section 408 including a hard disk, etc.; and a communication section 409 including a network interface card such as a LAN (Local Area Network) card, a modem, etc. The communication section 409 performs communication processing via a network such as the Internet. A drive 410 is also connected to the input / output interface 405 as needed. A removable medium 411, such as a magnetic disk, an optical disk, a magneto-optical disk, a semiconductor memory, etc., is installed on the drive 410 as needed so that a computer program read therefrom is installed into the storage section 408 as needed.

[0119] In particular, according to an embodiment of the present application, the process described above with reference to the flowchart can be implemented as a computer software program. For example, an embodiment of the present application includes a computer program product, which includes a computer program carried on a computer-readable medium, and the computer program includes a computer program for executing the method shown in the flowchart. In such an embodiment, the computer program can be downloaded and installed from a network through the communication part 409, and / or installed from a removable medium 411. When the computer program is executed by the central processing unit 401, various functions defined in the system of the present application are executed.

[0120] It should be noted that the computer-readable medium shown in the embodiment of the present application may be a computer-readable signal medium or a computer-readable storage medium or any combination of the above two. The computer-readable storage medium may be, for example, but not limited to, an electrical, magnetic, optical, electromagnetic, infrared, or semiconductor system, device or device, or any combination of the above. More specific examples of computer-readable storage media may include, but are not limited to: an electrical connection with one or more wires, a portable computer disk, a hard disk, a random access memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM), a flash memory, an optical fiber, a portable compact disk read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination of the above. In the present application, a computer-readable storage medium may be any tangible medium containing or storing a program, which may be used by or in combination with an instruction execution system, device or device. In the present application, a computer-readable signal medium may include a data signal propagated in a baseband or as part of a carrier wave, which carries a computer-readable computer program. Such propagated data signals may take a variety of forms, including but not limited to electromagnetic signals, optical signals, or any suitable combination of the above. Computer-readable signal media may also be any computer-readable medium other than computer-readable storage media, which may send, propagate, or transmit programs for use by or in conjunction with an instruction execution system, apparatus, or device. The computer program contained on the computer-readable medium may be transmitted using any appropriate medium, including but not limited to: wireless, wired, etc., or any suitable combination of the above.

[0121] The flowchart and block diagram in the accompanying drawings illustrate the possible architecture, functions and operations of the system, method and computer program product according to various embodiments of the present application. Wherein, each box in the flowchart or block diagram can represent a module, a program segment, or a part of the code, and the above-mentioned module, program segment, or a part of the code contains one or more executable instructions for realizing the specified logical function. It should also be noted that in some alternative implementations, the functions marked in the box can also occur in a different order from the order marked in the accompanying drawings. For example, two boxes represented in succession can actually be executed substantially in parallel, and they can sometimes be executed in the opposite order, depending on the functions involved. It should also be noted that each box in the block diagram or flowchart, and the combination of boxes in the block diagram or flowchart can be implemented with a dedicated hardware-based system that performs a specified function or operation, or can be implemented with a combination of dedicated hardware and computer instructions.

[0122] The units involved in the embodiments described in this application may be implemented by software or hardware, and the units described may also be set in a processor. The names of these units do not, in some cases, constitute limitations on the units themselves.

[0123] According to one aspect of the present application, a computer program product or a computer program is provided, the computer program product or the computer program comprising computer instructions, the computer instructions being stored in a computer-readable storage medium. A processor of a computer device reads the computer instructions from the computer-readable storage medium, and the processor executes the computer instructions, so that the computer device executes the methods provided in the above-mentioned various optional implementations.

[0124] As another aspect, the present application also provides a computer-readable medium, which may be included in the electronic device described in the above embodiment; or may exist independently without being assembled into the electronic device. The above computer-readable medium carries one or more programs, and when the above one or more programs are executed by an electronic device, the electronic device implements the method described in the above embodiment.

[0125] It should be noted that, although several modules or units of the equipment for action execution are mentioned in the above detailed description, this division is not mandatory. In fact, according to the embodiments of the present application, the features and functions of two or more modules or units described above can be embodied in one module or unit. On the contrary, the features and functions of one module or unit described above can be further divided into being embodied by multiple modules or units.

[0126] Through the description of the above implementation methods, it is easy for those skilled in the art to understand that the example implementation methods described here can be implemented by software, or by combining software with necessary hardware. Therefore, the technical solution according to the implementation method of the present application can be embodied in the form of a software product, which can be stored in a non-volatile storage medium (which can be a CD-ROM, a USB flash drive, a mobile hard disk, etc.) or on a network, including several instructions to enable a computing device (which can be a personal computer, a server, a touch terminal, or a network device, etc.) to execute the method according to the implementation method of the present application.

[0127] Those skilled in the art will readily appreciate other embodiments of the present application after considering the specification and practicing the embodiments disclosed herein. The present application is intended to cover any variations, uses or adaptations of the present application, which follow the general principles of the present application and include common knowledge or customary technical means in the art that are not disclosed in the present application.

[0128] It should be understood that the present application is not limited to the precise structures that have been described above and shown in the drawings, and that various modifications and changes may be made without departing from the scope thereof. The scope of the present application is limited only by the appended claims.

Claims

1. A focusing control method based on an image signal, characterized in that: include: Collect distributed images through multiple lenses of a camera device; Based on feature information in the distributed images, the distributed images are fused to generate a panoramic image; According to the interest points preset by each lens, detecting the image area corresponding to each interest point in the panoramic image, and evaluating the feature quality corresponding to the image area; Determining an initial step length of focal length adjustment of each lens according to the characteristic quality, and determining an iterative step length of focal length adjustment of each lens according to the initial step length of an adjacent lens; Based on the initial step size and the iteration step size, the focus position of each lens is adjusted.

2. The focusing control method based on image signals according to claim 1, characterized in that: Before collecting distributed images through multiple lenses of a camera device, the method further includes: Get the ambient lighting parameters and the brightness parameters within the lens field of view; The exposure time and gain value of each lens are adjusted according to the ambient light parameter and the brightness parameter.

3. The focusing control method based on image signals according to claim 1, characterized in that: Based on the feature information in the distributed images, the distributed images are fused to generate a panoramic image, including: Extract feature points from the distributed image using a deep learning model to obtain a feature vector set; By randomly sampling the feature vector set, feature matching is performed on the sampled feature vectors to obtain a matching vector group; Based on the feature information corresponding to the vector group, feature fusion is performed to generate a panoramic image.

4. The focusing control method based on image signals according to claim 1, characterized in that: According to the interest points preset by each lens, detecting the image area corresponding to each interest point in the panoramic image, and evaluating the feature quality corresponding to the image area, including: Detect the image area corresponding to each point of interest in the panoramic image through the object detection network, and output the set of bounding boxes corresponding to each image area; Based on a set of bounding boxes corresponding to the image region, the feature quality corresponding to the image region in each dimension is evaluated, wherein the dimensions include a clarity dimension, a contrast dimension, and a saturation dimension.

5. The focusing control method based on image signals according to claim 4, characterized in that: Determining the initial step length of focal length adjustment of each lens according to the characteristic quality, and determining the iterative step length of focal length adjustment of each lens according to the initial step length of the adjacent lens, including: Determining a focusing function based on the feature quality corresponding to each dimension of the image area; Determining the initial step length of the focal length adjustment of each lens according to the focusing function; According to the overlapping degree of the shooting ranges between adjacent lenses and in combination with the initial step length, the iterative step length of each subsequent adjustment of the focal length of each lens is determined.

6. The focusing control method based on image signals according to claim 1, characterized in that: Based on the initial step size and the iteration step size, adjusting the focus position of each lens includes: The focus position of each lens is adjusted based on the initial step size, and then the adjustment is continued based on the iteration step size.

7. The focusing control method based on image signals according to claim 1, characterized in that: After adjusting the focus position of each lens based on the initial step size and the iteration step size, the method further includes: Record the focus information of each lens at each adjustment.

8. A focusing control device based on an image signal, characterized in that: include: A collection unit, used for collecting distributed images through multiple lenses of a camera device; A fusion unit, configured to fuse the distributed images based on feature information in the distributed images to generate a panoramic image; A quality unit, configured to detect, based on the interest points preset by each lens, an image area corresponding to each interest point in the panoramic image, and evaluate a feature quality corresponding to the image area; A step length unit, used to determine an initial step length of focal length adjustment of each lens according to the characteristic quality, and determine an iterative step length of focal length adjustment of each lens according to the initial step length of an adjacent lens; An adjusting unit is used to adjust the focus position of each lens based on the initial step size and the iteration step size.

9. A computer readable medium having a computer program stored thereon, characterized in that: When the computer program is executed by a processor, the focus control method based on an image signal according to any one of claims 1 to 7 is implemented.

10. An electronic device, characterized in that: include: one or more processors; A storage device for storing one or more programs, which, when executed by the one or more processors, enables the one or more processors to implement the focus control method based on image signals as described in any one of claims 1 to 7.

Images