Image information extraction method and device

Abstract

The present application relates to the field of image processing, and in particular to a method and device for extracting image information. An image information extraction method, applied to a processor, includes: determining focus pre-configuration information; writing the focus pre-configuration information into a register, wherein the focus pre-configuration information includes the coordinates of the interested frame, the preset PD coordinates of the preset PD points, and the preset flag bits associated with the preset PD points; determining a focus area of ​​interest and several PD points within the focus area of ​​interest in a first image based on the focus pre-configuration information in the register; extracting left and right eye PD information of the several PD points and writing it into a memory, wherein the left and right eye PD information includes the left and right eye flag bits of each PD point, wherein the left and right eye flag bits are used to indicate whether the PD point is a left eye PD point or a right eye PD point, and the memory is used to focus on the focus area of ​​interest based on the PD information of the left eye PD point and the right eye PD point.

Description

Technical field

[0001] The present application relates to the field of image processing, and in particular to a method and device for extracting image information. [Background Technology]

[0002] Phase detection auto focus (PDAF) is an essential feature for terminal devices during image capture. To achieve accurate focus, the terminal device calculates the phase difference between phase detection (PD) points in the image captured by the PDAF sensor.

[0003] During image acquisition, the PDAF sensor can block the light-sensitive area of ​​the PD points, with half of the PD points blocking the left area and the other half blocking the right area, similar to the function of the human eye. Therefore, when imaging the subject, the left and right PD points are required. Focus is achieved by comparing the phase difference between the left and right PD points.

[0004] When the PDAF sensor outputs the PD points on the captured image, it will output the PD points in different forms such as type1, type2, type3, etc. according to actual needs. For PDAF sensors that output type1 / 2 PD points, since the PD information of the PD points is stored in the line blanking or field blanking between the captured image and the next frame image, the memory cannot directly use it to identify the left and right eye PD points. Therefore, the PDAF sensor needs to output all PD points to the memory, and the memory can only distinguish which PD points are the left eye PD points and which PD points are the right eye PD points after calculation. For PDAF sensors that output type3 PD points, although the image can store the PD information of type3 PD points in the captured image, the PD information in the image needs to be calculated by the software in the memory before the left eye PD point and the right eye PD point can be distinguished.

[0005] In the process of calculating the memory, the left eye PD point and the right eye PD point need to be segmented first, and then the information of the left eye PD point and the right eye PD point needs to be processed, which increases the processing steps and reduces the efficiency of software processing. [Summary of the invention]

[0006] In view of this, an embodiment of the present invention provides an image information extraction method and device, which predetermines the focus preconfiguration information and outputs a type 3 image when capturing the image, thereby completing the extraction of the PD information of the left and right eye PD points when capturing the image, so as to directly determine the left and right eye PD points on the image when performing focusing.

[0007] In a first aspect, an embodiment of the present invention provides a method for extracting image information, the method being applied to a processor and comprising:

[0008] Determine focus pre-configuration information;

[0009] Writing the focus preconfiguration information into a register, wherein the focus preconfiguration information includes the coordinates of the interested frame, the preset PD coordinates of the preset PD point, and the preset flag associated with the preset PD point;

[0010] Determining a focus region of interest and a plurality of PD points within the focus region of interest in a first image according to the focus pre-configuration information in the register;

[0011] The left and right eye PD information of the plurality of PD points is extracted and written into a memory, wherein the left and right eye PD information includes left and right eye flags of each of the PD points, and the left and right eye flags are used to indicate whether the PD point is a left eye PD point or a right eye PD point, and the memory is used to focus on the focus area of ​​interest according to the PD information of the left eye PD point and the right eye PD point.

[0012] Optionally, determining focus pre-configuration information includes:

[0013] The focus pre-configuration information is determined in an M-th frame preview image, and a capture time of the M-th frame preview image is before a capture time of the first image.

[0014] Optionally, determining the focus pre-configuration information in the Mth frame preview image includes:

[0015] Determine a focus indication area according to a focus action applied to the M-th frame preview image; determine the coordinates of the frame of interest according to the focus indication area; or

[0016] Identify a target object from the M-th preview image frame, and determine the coordinates of the bounding box of interest based on the target object; or

[0017] The coordinates of the bounding box of interest are determined according to the central area of ​​the M-th preview image.

[0018] Optionally, determining the focus pre-configuration information in the Mth frame preview image further includes:

[0019] Randomly generate a number of sets of preset PD coordinates, where the coordinate positions corresponding to the preset PD coordinates are included in the coordinates of the bounding box of interest;

[0020] Determine the preset flag associated with each preset PD coordinate.

[0021] Optionally, writing the focus pre-configuration information into a register includes:

[0022] Arranging the order of the preset PD points according to the preset PD coordinates;

[0023] The preset PD coordinates and preset flags of each preset PD point are written into the register according to the arrangement order.

[0024] Optionally, arranging the order of the preset PD points according to the preset PD coordinates of the preset PD points includes:

[0025] Determining the horizontal coordinate and the vertical coordinate of each preset PD point in the coordinates of the frame of interest according to the preset PD coordinates of each preset PD point;

[0026] Determine the arrangement value of each preset PD point according to the horizontal coordinate and the vertical coordinate of each preset PD point in the coordinate of the frame of interest and the image block block in the coordinate of the frame of interest;

[0027] The order of the preset PD points is arranged according to the arrangement value of each preset PD point.

[0028] Optionally, determining a focus region of interest and a plurality of PD points within the focus region of interest in the first image according to the focus pre-configuration information in the register includes:

[0029] Mapping the coordinates of the bounding box of interest to the first image to obtain the focused region of interest of the first image;

[0030] The preset PD coordinates are mapped to the focus area of ​​interest to obtain the plurality of PD points, and the PD points are associated with the left and right eye flags of the corresponding preset PD point coordinates.

[0031] Optionally, extracting the left-eye and right-eye PD information of the plurality of PD points and writing them into a memory includes:

[0032] Write the left eye PD information into the first memory partition;

[0033] Write the right eye PD information into the second memory partition.

[0034] In a second aspect, an embodiment of the present invention provides an image information extraction device, comprising:

[0035] A first determining module determines focus pre-configuration information;

[0036] A writing module writes the focus pre-configuration information into a register, wherein the focus pre-configuration information includes the coordinates of the interested frame, the preset PD coordinates of the preset PD point, and the preset flag bit associated with the preset PD point;

[0037] a second determining module, for determining a focus region of interest and a plurality of PD points within the focus region of interest in the first image according to the focus pre-configuration information in the register;

[0038] An extraction module extracts the left and right eye PD information of the plurality of PD points and writes it into a memory, wherein the left and right eye PD information includes the left and right eye flags of each PD point, and the left and right eye flags are used to indicate whether the PD point is a left eye PD point or a right eye PD point. The memory is used to focus on the focus area of ​​interest according to the PD information of the left eye PD point and the right eye PD point.

[0039] In a third aspect, an embodiment of the present invention provides an image information extraction device, comprising:

[0040] at least one processor; and

[0041] at least one memory in communication with the processor, wherein:

[0042] The memory stores program instructions that can be executed by the processor, and the processor calls the program instructions to execute the method as described in any one of the first aspects.

[0043] Through the above solution, the focus pre-configuration information is determined in advance. When acquiring an image through the PDAF sensor, PD information can be directly extracted in the focus area of ​​interest, and the PD information of the left and right eyes can be output in real time. There is no need for redundant PD point splitting calculations, which leaves more time for subsequent focus algorithm processing.

Brief Description of the Drawings

[0044] In order to more clearly illustrate the technical solutions of the embodiments of the present invention, the following briefly introduces the drawings required for use in the embodiments. Obviously, the drawings described below are only some embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying any creative work.

[0045] Figure 1 A flowchart of an image information extraction method provided by an embodiment of the present invention;

[0046] Figure 2 A schematic structural diagram of an image information extraction device provided by an embodiment of the present invention;

[0047] Figure 3 A schematic diagram of a first image provided by an embodiment of the present invention;

[0048] Figure 4 A schematic diagram of focusing on a region of interest provided by an embodiment of the present invention;

[0049] Figure 5A schematic structural diagram of an electronic device provided by an embodiment of the present invention. [Specific implementation method]

[0050] In order to better understand the technical solution of the present invention, the embodiments of the present invention are described in detail below with reference to the accompanying drawings.

[0051] It should be understood that the embodiments described are only a portion of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by persons of ordinary skill in the art without creative work are within the scope of protection of the present invention.

[0052] When the terminal device performs the focusing operation, it needs to determine the left eye PD point and the right eye PD point in a frame of image captured by the PDAF sensor, and calculate the phase difference between the left eye PD point and the right eye PD point to achieve focusing on the preview image.

[0053] When capturing images, the PDAF sensor can output PD points in a variety of different forms. Generally, the PDAF sensor will output PD points in three forms: type1, type2, and type3, depending on actual needs. When the PDAF sensor outputs the PD points on the image in type1 or type2, the sensor cannot directly split the PD points on the image, that is, the sensor cannot directly determine whether the PD points in the same frame of image are left-eye PD points or right-eye PD points when capturing the image. Instead, all PD points on the image need to be input into the memory and split and processed by the program algorithm in the memory before the left-eye PD point and the right-eye PD point can be distinguished and subsequent focusing can be performed. Since the phase difference between the left and right eye PD points also needs to be calculated in the memory, splitting the mixed PD points in the memory to obtain the left and right eye PD points separately will increase the image processing steps, reduce image processing efficiency, and increase the processing speed requirements of the autofocus algorithm itself.

[0054] This embodiment of the present invention predetermines focus preconfiguration information. When the PDAF sensor is used for image acquisition, image acquisition is performed directly based on the preconfiguration information. The acquired image information is simultaneously output as type 3 data, allowing the PD information of the left and right eye PD points to be directly written to the first and second memory partitions of the memory. Subsequent calculations in the memory can directly determine the left and right eye PD points in the same frame based on the PD information, avoiding the redundant step of storing all PD points in memory for separate calculations, thereby improving processing efficiency.

[0055] Since the focusing operation is a continuous process, it is necessary to extract image information from several frames of continuous preview images when performing focusing, that is, determine the left eye PD point and the right eye PD point on each frame of the image, and calculate the phase difference between the left eye PD point and the right eye PD point of each frame of the image to achieve focusing. Among them, the extraction process of each frame of the image is the same as the focus calculation process. The embodiment of the present invention is explained by taking the image of the first frame for image information extraction after determining the pre-configured focus information as an example, and the image of the first frame for left and right eye PD information extraction is determined as the first image. The splitting process and focusing process of several frames of images collected after the first image are the same as those of the first image.

[0056] See also Figure 1 , is a flow chart of an image information extraction method provided by an embodiment of the present invention, wherein the method is applied to a processor, such as Figure 1 As shown, the processing steps of the method include:

[0057] 101. Determine focus pre-configuration information.

[0058] Specifically, when the terminal device enters the shooting mode, it is necessary to focus the preview image in the shooting mode. Before performing the focus, it is necessary to determine the focus pre-configuration information so that when the PDAF sensor collects the first image for performing the focus, it can directly collect it according to the focus pre-configuration information.

[0059] When determining the focus preconfiguration information, it is first necessary to determine the coordinates of the frame of interest, and then generate the threshold PD coordinates of several preset PD points within the range of the coordinates of the frame of interest, as well as the preset flag bits associated with each preset PD point.

[0060] The coordinates of the bounding box of interest are the coordinates of a fixed area selected in the preview image. They are used only to determine the relative position of the preview image and are not related to the actual image content in the preview image. When configuring the coordinates of the bounding box of interest, you can determine them based on the user's focus action or automatically based on a preset algorithm.

[0061] Optionally, when a user focuses on the Mth preview image, the coordinates of the region corresponding to the user's focus action on the preview image are determined, and the coordinates of the bounding box of interest are determined based on the coordinates of the region corresponding to the focus action on the preview image. The coordinates of the bounding box of interest correspond only to a fixed position on the preview image and are unrelated to the image content in the preview image. The image content in the preview image is only used as a reference for the user's focus action, and the coordinates of the bounding box of interest are not determined based on the image content selected by the user. The Mth preview image is captured before the first image.

[0062] Optionally, when no focus action is received from the user, the image recognition model is invoked to identify the preview image of the Mth frame and determine the target object in the preview image. The coordinates of the bounding box of interest are determined based on the relative position of the target object and the preview image. The target image can be the main object or an important object in the preview image, such as a person's face. After image recognition is completed by the image recognition model, the coordinates of the bounding box of interest are determined based on the coordinates of the region where the target object is located in the Mth frame, and the coordinates of the bounding box of interest are determined separately based on the target object.

[0063] Optionally, when no focusing action from the user is received and the image recognition model does not detect the target object, the coordinates of the bounding box of interest are determined at the center position of the preview image.

[0064] After completing the configuration of the coordinates of the frame of interest, several sets of preset PD point coordinates are generated within the range of the coordinates of the frame of interest. Each set of preset PD point coordinates consists of a horizontal coordinate and a vertical coordinate, and are all included in the range identified by the coordinates of the frame of interest.

[0065] After completing the configuration of the preset PD point coordinates, a corresponding preset flag is determined for each set of preset PD point coordinates. The preset flag corresponding to each preset PD point coordinate can be 00 or 01, where 00 indicates that the PDAF sensor collects the left eye PD point when collecting the first image, and 01 indicates that the PDAF sensor collects the right eye PD point when collecting the first image.

[0066] 102. Write the focus pre-configuration information into the register.

[0067] Specifically, the coordinates of the bounding box of interest are written into the register. The order of the preset PD points is arranged according to the preset PD coordinates of each preset PD point, and the preset PD coordinates and preset flags of each preset PD point are written into the register in the arrangement order.

[0068] The horizontal and vertical coordinates of each preset PD point within the coordinate frame of interest are determined, and the image block of the coordinate frame of interest is determined based on the size of the coordinate frame of interest. By calculating the horizontal and vertical coordinates and block of each preset PD point, the arrangement value of each preset PD point can be obtained. The preset PD points are arranged in ascending order according to their arrangement values.

[0069] Optionally, the arrangement value of each preset PD point may be determined by the formula A=col+block*row.

[0070] Where A is the calculated permutation value, col is the ordinate of the preset PD point, row is the abscissa of the preset PD point, and block is the number of image blocks divided by the coordinate frame of interest. The number of image blocks is usually determined by the size of the coordinate frame of interest. Generally, the number of image blocks is one of 8, 16, 32, or 64.

[0071] By writing the preset flags of the preset PD points into the register in the order of the arrangement values ​​from small to large, the position of each preset PD point in the coordinate frame of interest can be calculated.

[0072] In some embodiments, the number of preset PD points can also be determined based on the size of the coordinate frame of interest and the number of image blocks. Since the terminal device is equipped with a limited number of registers, generally 32, and each register can only store the preset flags of two preset PD points, it is necessary to estimate the number of preset PD points and control the number of preset PD points used for calculation to 64 or less.

[0073] 103 : Determine a focus region of interest and a number of PD points within the focus region of interest in the first image according to the focus pre-configuration information in the register.

[0074] Specifically, after the focus pre-configuration information is determined, the PDAF sensor determines the focus area of ​​interest, and a number of PD points and PD information within the focus area of ​​interest in the captured first image according to the focus pre-configuration information in the register.

[0075] The coordinates of the bounding box of interest in the focus pre-configuration information are mapped to the first image to obtain a focus region of interest in the first image where focusing is required.

[0076] Generate several PD points within the focus region of interest. The location of each PD point is determined by the preset PD coordinate information in the focus pre-configuration information. These preset PD coordinate points are mapped to the focus region of interest to generate several PD points. At the same time, the preset flags of each PD point are used to determine its corresponding left and right eye flags.

[0077] When determining the first image, the PDAF sensor captures a Type 3 first image. Unlike Type 1 and Type 2 images, when outputting a Type 3 image, the left and right eye PD points can be directly extracted from the captured first image. In this embodiment of the present invention, when determining the first image, the PDAF sensor captures the first images corresponding to the left and right eye PD points based on the left and right eye flags associated with the preset PD point coordinates in the pre-configured information.

[0078] The determined PD point is a pixel point used to perform focusing of the first image according to the phase difference between the left-eye PD point and the right-eye PD point in the first image.

[0079] like Figure 2 FIG2 is a schematic diagram of a first image provided by an embodiment of the present invention. Figure 2 In the first image captured by the PDAF sensor, the focus region of interest is determined at the corresponding position according to the coordinates of the interested frame in the focus configuration information, that is, the upper left area of ​​the first image is determined as the focus region of interest.

[0080] like Figure 3 As shown, this is an embodiment of the present invention Figure 2 Schematic diagram of the focused region of interest in the first image shown. Figure 3 According to the preset PD point coordinates in the focus configuration information, 6 PD points are generated in the focus area of ​​interest, which are used to perform focusing on the determined focus area of ​​interest.

[0081] 104. Extract the left and right eye PD information of several PD points and write them into the memory.

[0082] Specifically, the left-eye and right-eye PD information is the left-eye and right-eye flags of each PD point in the first image. Since each PD point indicates whether it is a left-eye PD point or a right-eye PD point, the PD information of the left-eye PD point and the right-eye PD point are written into different memory partitions, respectively. The left-eye PD information is written into the first memory partition, and the right-eye PD information is written into the second memory partition, thereby achieving the separation of the left-eye and right-eye PD points in the first memory image.

[0083] When performing focus calculations in the memory, there is no need to separate the left and right eye PD points. Instead, the autofocus algorithm can be directly called to calculate the left and right eye PD points in the first and second memory areas. Generally, the memory can be a double data rate synchronous dynamic random access memory (DDR).

[0084] Optionally, after extracting the left and right eye PD information and writing it into the memory and performing focusing on it in the memory, it is necessary to correct the PD points in the first image to eliminate the PD points in the first image so that the image processing module can perform subsequent image processing on the first image. Since the left and right eyes have been separated, the PD points in the first image can be corrected using two sets of gains for the left and right eyes respectively, thereby improving accuracy. In contrast, if the left and right eye PD points are not separated, the left and right eye PD points are mixed together and can only be corrected using one set of gains, which reduces the accuracy of the correction and may even damage the first image.

[0085] By predetermining the focus pre-configuration information, the embodiment of the present invention can directly extract PD information in the focus area of ​​interest when acquiring an image through the PDAF sensor, and output the PD information of the left and right eyes in real time without the need for redundant PD point splitting calculations, leaving more time for subsequent focusing algorithm processing.

[0086] Corresponding to the above-mentioned image information extraction method, an embodiment of the present invention further provides an image information extraction device. Figure 4 , is a structural diagram of an image information extraction device provided by an embodiment of the present invention. Figure 4 As shown, the apparatus may include: a first determination module 201 , a writing module 202 , a second determination module 203 , and an extraction module 204 .

[0087] A first determining module 201 determines focus pre-configuration information;

[0088] The writing module 202 writes the focus pre-configuration information into a register, where the focus pre-configuration information includes the coordinates of the bounding box of interest, the preset PD coordinates of the preset PD point, and the preset flag associated with the preset PD point;

[0089] A second determining module 203 determines a focus region of interest and a plurality of PD points within the focus region of interest in the first image according to the focus pre-configuration information in the register;

[0090] An extraction module 204 extracts the left-eye and right-eye PD information of the plurality of PD points and writes it into a memory, wherein the left-eye and right-eye PD information include left-eye and right-eye flags of each PD point, and the left-eye and right-eye flags are used to indicate whether the PD point is a left-eye PD point or a right-eye PD point. The memory is used to focus on the focus area of ​​interest based on the PD information of the left-eye PD point and the right-eye PD point.

[0091] Figure 4 The image information extraction device provided in the illustrated embodiment can be used to implement the technical solution of the method embodiment shown in this specification. Its implementation principle and technical effects can be further referred to the relevant description in the method embodiment.

[0092] Figure 5 This is a schematic diagram of the structure of an embodiment of an electronic device in this specification. The electronic device can be implemented as a terminal device that executes the image information extraction method in the embodiment of the present invention. Figure 5 As shown, the electronic device may include at least one processor; and at least one memory communicatively connected to the processing unit, wherein: the memory stores program instructions that can be executed by the processing unit, and the processor calls the program instructions to execute the image information extraction method provided in this embodiment.

[0093] The electronic device can be a device that can conduct intelligent dialogue with the user, and the specific form of the electronic device is not limited in the embodiments of this specification. It can be understood that the electronic device here is the machine mentioned in the method embodiment.

[0094] Figure 5 A block diagram is shown of an exemplary electronic device suitable for implementing embodiments of the present description. Figure 5 The electronic device shown is only an example and should not limit the functions and scope of use of the embodiments of this specification.

[0095] like Figure 5 As shown, the electronic device is implemented as a general-purpose computing device. Components of the electronic device may include, but are not limited to, one or more processors 310, a communication interface 320, a memory 330, and a communication bus 340 connecting different system components (including the memory 330, the communication interface 320, and the processor 310).

[0096] Communication bus 340 represents one or more of several types of bus structures, including a memory bus or memory controller, a peripheral bus, an accelerated graphics port, a processor, or a local bus using any of a variety of bus architectures. Examples of these architectures include, but are not limited to, the Industry Standard Architecture (ISA) bus, the Micro Channel Architecture (MAC) bus, the Enhanced ISA bus, the Video Electronics Standards Association (VESA) local bus, and the Peripheral Component Interconnection (PCI) bus.

[0097] Electronic devices typically include a variety of computer system readable media. These media can be any available media that can be accessed by the electronic device, including volatile and non-volatile media, removable and non-removable media.

[0098] Memory 330 may include computer-readable media in the form of volatile memory, such as random access memory (RAM) and / or cache memory. The electronic device may further include other removable / non-removable, volatile / non-volatile computer system storage media. Memory 330 may include at least one program product having a set (e.g., at least one) of program modules configured to perform the functions of various embodiments of this specification.

[0099] A program / utility having a set (at least one) of program modules may be stored in memory 330. Such program modules include, but are not limited to, an operating system, one or more application programs, other program modules, and program data, each of which, or some combination thereof, may include an implementation of a network environment. The program modules generally implement the functions and / or methods of the embodiments described herein.

[0100] The processor 310 executes various functional applications and data processing by running the programs stored in the memory 330, such as implementing the image information extraction method provided in the embodiments shown in this specification.

[0101] An embodiment of the present specification provides a non-transitory computer-readable storage medium, wherein the non-transitory computer-readable storage medium stores computer instructions, and the computer instructions enable the computer to execute the image information extraction method provided by the embodiment shown in the present specification.

[0102] The above-mentioned non-transitory computer-readable storage medium can adopt any combination of one or more computer-readable media. The computer-readable medium can be a computer-readable signal medium or a computer-readable storage medium. The computer-readable storage medium can be, for example, but not limited to, an electrical, magnetic, optical, electromagnetic, infrared, or semiconductor system, device or device, or any combination thereof. More specific examples (non-exhaustive list) of computer-readable storage media include: an electrical connection with one or more wires, a portable computer disk, a hard disk, a random access memory (RAM), a read-only memory (ReadOnly Memory; hereinafter referred to as: ROM), an erasable programmable read-only memory (Erasable Programmable ReadOnly Memory; hereinafter referred to as: EPROM) or 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 thereof. In this document, a computer-readable storage medium can be any tangible medium containing or storing a program that can be used by an instruction execution system, device or device or used in combination with it.

[0103] A computer-readable signal medium may include a data signal propagated in baseband or as part of a carrier wave, which carries computer-readable program code. Such propagated data signals may take various forms, including but not limited to electromagnetic signals, optical signals, or any suitable combination thereof. A computer-readable signal medium may also be any computer-readable medium other than a computer-readable storage medium that can transmit, propagate, or transport a program for use by or in conjunction with an instruction execution system, apparatus, or device.

[0104] Program code embodied on a computer readable medium may be transmitted using any appropriate medium, including but not limited to wireless, wireline, optical fiber cable, RF, etc., or any suitable combination of the foregoing.

[0105] Computer program code for performing the operations of this specification can be written in one or more programming languages ​​or a combination thereof, including object-oriented programming languages ​​such as Java, Smalltalk, C++, and conventional procedural programming languages ​​such as "C" or similar programming languages. The program code can be executed entirely on the user's computer, partially on the user's computer, as a separate software package, partially on the user's computer and partially on a remote computer, or entirely on a remote computer or server. In cases involving a remote computer, the remote computer can be connected to the user's computer through any type of network, including a local area network (LAN) or a wide area network (WAN), or can be connected to an external computer (for example, through the Internet using an Internet service provider).

[0106] The foregoing description of this specification describes specific embodiments. Other embodiments are within the scope of the appended claims. In some cases, the actions or steps recited in the claims can be performed in an order different from that described in the embodiments and still achieve the desired results. Furthermore, the processes depicted in the accompanying drawings do not necessarily require the specific order shown or the sequential order to achieve the desired results. In certain embodiments, multitasking and parallel processing are also possible or may be advantageous.

[0107] Furthermore, the terms "first" and "second" are used for descriptive purposes only and should not be construed as indicating or implying relative importance or implicitly specifying the number of the technical features being referred to. Thus, a feature specified as "first" or "second" may explicitly or implicitly include at least one such feature. Throughout this specification, "plurality" means at least two, such as two or three, unless otherwise specifically defined.

[0108] Any process or method description in a flowchart or otherwise described herein may be understood to represent a module, segment or portion of code comprising one or more executable instructions for implementing the steps of a custom logical function or process, and the scope of the preferred embodiments of this specification includes alternative implementations in which functions may be performed out of the order shown or discussed, including performing functions in a substantially simultaneous manner or in the reverse order depending on the functions involved, which should be understood by those skilled in the art to which the embodiments of this specification belong.

[0109] The word "if," as used herein, may be interpreted as "at the time of" or "when" or "in response to determining" or "in response to detecting," depending on the context. Similarly, the phrases "if it is determined" or "if (stated condition or event) is detected" may be interpreted as "when it is determined" or "in response to the determination" or "when detecting (stated condition or event)" or "in response to detecting (stated condition or event)," depending on the context.

[0110] It should be noted that the terminals involved in the embodiments of this specification may include but are not limited to personal computers (Personal Computer; hereinafter referred to as: PC), personal digital assistants (Personal Digital Assistant; hereinafter referred to as: PDA), wireless handheld devices, tablet computers (Tablet Computer), mobile phones, MP3 players, MP4 players, etc.

[0111] In the embodiments provided in this specification, it should be understood that the disclosed systems, devices and methods can be implemented in other ways. For example, the device embodiments described above are merely illustrative. For example, the division of the units is merely a logical function division. In actual implementation, there may be other division methods. For example, multiple units or components may be combined or integrated into another system, or some features may be ignored or not executed. Another point is that the mutual coupling or direct coupling or communication connection shown or discussed may be through some interface, indirect coupling or communication connection of the device or unit, which may be electrical, mechanical or other forms.

[0112] In addition, the functional units in the various embodiments of this specification may be integrated into a single processing unit, each unit may exist physically separately, or two or more units may be integrated into a single unit. The aforementioned integrated units may be implemented in the form of hardware or hardware plus software functional units.

[0113] The above-mentioned integrated unit implemented in the form of a software functional unit can be stored in a computer-readable storage medium. The above-mentioned software functional unit stored in a storage medium includes a number of instructions for causing a computer device (which can be a personal computer, server, or network device, etc.) or a processor to perform some steps of the method described in various embodiments of this specification.

[0114] The above description is only a preferred embodiment of this specification and is not intended to limit this specification. Any modifications, equivalent replacements, improvements, etc. made within the spirit and principles of this specification should be included in the scope of protection of this specification.

Claims

1. A method for extracting image information, characterized in that: The method is applied to a processor, and the method includes: Determine focus pre-configuration information; Writing the focus preconfiguration information into a register, wherein the focus preconfiguration information includes the coordinates of the interested frame, the preset PD coordinates of the preset PD point, and the preset flag associated with the preset PD point; Determining a focus region of interest and a plurality of PD points within the focus region of interest in a first image according to the focus pre-configuration information in the register; Extracting left and right eye PD information of the plurality of PD points and writing it into a memory, the left and right eye PD information including left and right eye flags of each PD point, the left and right eye flags being used to indicate whether the PD point is a left eye PD point or a right eye PD point, and the memory being used to focus on the focus area of ​​interest according to the PD information of the left eye PD point and the right eye PD point; The determining, in the first image, a focus region of interest and a plurality of PD points within the focus region of interest according to the focus pre-configuration information in the register includes: Mapping the coordinates of the bounding box of interest to the first image to obtain the focused region of interest of the first image; The preset PD coordinates are mapped to the focus area of ​​interest to obtain the plurality of PD points, and the PD points are associated with the left and right eye flags of the corresponding preset PD point coordinates.

2. The method according to claim 1, characterized in that The determining of the focus pre-configuration information includes: The focus pre-configuration information is determined in an M-th frame preview image, and a capture time of the M-th frame preview image is before a capture time of the first image.

3. The method according to claim 2, characterized in that Determining the focus pre-configuration information in the M-th frame preview image includes: Determine a focus indication area according to a focus action applied to the M-th frame preview image; determine the coordinates of the frame of interest according to the focus indication area; or Identify a target object from the M-th preview image frame, and determine the coordinates of the bounding box of interest based on the target object; or The coordinates of the bounding box of interest are determined according to the central area of ​​the M-th preview image.

4. The method according to claim 2, characterized in that The step of determining the focus pre-configuration information in the preview image of the M frame further includes: Randomly generate a number of sets of preset PD coordinates, where the coordinate positions corresponding to the preset PD coordinates are included in the coordinates of the bounding box of interest; Determine the preset flag associated with each preset PD coordinate.

5. The method according to claim 1, wherein Writing the focus pre-configuration information into a register includes: Arranging the order of the preset PD points according to the preset PD coordinates; The preset PD coordinates and preset flags of each preset PD point are written into the register according to the arrangement order.

6. The method according to claim 5, characterized in that The arranging the order of the preset PD points according to the preset PD coordinates of the preset PD points includes: Determining the horizontal coordinate and the vertical coordinate of each preset PD point in the coordinates of the frame of interest according to the preset PD coordinates of each preset PD point; Determine the arrangement value of each preset PD point according to the horizontal coordinate and the vertical coordinate of each preset PD point in the coordinate of the frame of interest and the image block block in the coordinate of the frame of interest; The order of the preset PD points is arranged according to the arrangement value of each preset PD point.

7. The method according to claim 1, characterized in that The extracting the left and right eye PD information of the plurality of PD points and writing them into the memory includes: Write the left eye PD information into the first memory partition; Write the right eye PD information into the second memory partition.

8. An image information extraction device, characterized in that: include: A first determining module determines focus pre-configuration information; A writing module writes the focus pre-configuration information into a register, wherein the focus pre-configuration information includes the coordinates of the interested frame, the preset PD coordinates of the preset PD point, and the preset flag associated with the preset PD point; a second determining module, for determining a focus region of interest and a plurality of PD points within the focus region of interest in the first image according to the focus pre-configuration information in the register; an extraction module, extracting left-eye and right-eye PD information of the plurality of PD points and writing it into a memory, wherein the left-eye and right-eye PD information includes left-eye and right-eye flags of each PD point, wherein the left-eye and right-eye flags are used to indicate whether the PD point is a left-eye PD point or a right-eye PD point, and the memory is used to perform focusing on the focus area of ​​interest based on the PD information of the left-eye PD point and the right-eye PD point; The determining, in the first image, a focus region of interest and a plurality of PD points within the focus region of interest according to the focus pre-configuration information in the register includes: Mapping the coordinates of the bounding box of interest to the first image to obtain the focused region of interest of the first image; The preset PD coordinates are mapped to the focus area of ​​interest to obtain the plurality of PD points, and the PD points are associated with the left and right eye flags of the corresponding preset PD point coordinates.

9. An image information extraction device, characterized in that: include: at least one processor; as well as at least one memory in communication with the processor, wherein: The memory stores program instructions that can be executed by the processor, and the processor calls the program instructions to execute the method according to any one of claims 1 to 7.

Images