Binocular camera quick starting method and system based on parameter mapping

Abstract

The invention relates to a binocular camera quick starting method based on parameter mapping, and the method comprises the steps: obtaining a target scene image through a first camera, carrying out the recognition of the target scene image, judging whether a human face exists or not, responding to the existence of the human face in the target scene image, starting a second camera, obtaining an LV value of the first camera, and starting the second camera according to the LV value. A preset parameter mapping table is searched according to the LV value, a corresponding exposure control parameter is obtained, the second camera carries out shooting based on the exposure control parameter, the first camera is combined to obtain a face image, and face recognition is carried out based on the face image. Through the method and the device, the problem of slow image convergence during face recognition of a binocular camera is solved, the trial and error process of an automatic exposure algorithm is skipped, the pre-stored parameters are directly called, the first frame is correctly exposed, and convergence delay is eliminated; the first camera detects illumination in real time, and the slave cameras synchronously inherit the same parameters, so that inconsistent brightness of left and right images is avoided, and binocular exposure difference is eliminated.

Description

Technical Field

[0001] This application relates to the field of computer vision technology, and in particular to a method and system for rapid startup of a binocular camera. Background Technology

[0002] Cameras are becoming increasingly widely used, especially in access control scenarios. To prevent people from using printed or mobile phone photos to pass through security using facial recognition, dual-lens cameras are often used to prevent these types of attacks. To reduce power consumption, one camera is turned off when no one is around, and it only activates when a face is detected.

[0003] In existing technologies, one RGB camera is typically used by default for face detection. When a face is detected, another infrared camera is activated, and the two cameras work together for face recognition. However, the normal process of activating another camera every time someone enters the frame results in a long startup time and slow image convergence, leading to a decrease in recognition speed. Summary of the Invention

[0004] This application provides a method, system, electronic device, and storage medium for fast startup of a binocular camera based on parameter mapping, in order to at least solve the problem of slow image convergence during face recognition in binocular cameras in related technologies.

[0005] In a first aspect, embodiments of this application provide a method for quickly starting up a binocular camera based on parameter mapping, wherein the binocular camera includes a first camera and a second camera; the method includes: The first camera acquires an image of the target scene, and the image of the target scene is then recognized to determine whether a human face exists. In response to the presence of a human face in the target scene image, the second camera is activated; The LV value of the first camera is obtained, and the corresponding exposure control parameters are obtained by looking up the preset parameter mapping table based on the LV value. The LV value is used to characterize the ambient light intensity, and the parameter mapping table includes the mapping relationship between the LV value of the first camera and the parameters of the second camera. The second camera takes a picture based on the exposure control parameters and, together with the first camera, acquires a face image, and performs face recognition based on the face image.

[0006] In some embodiments, obtaining the LV value of the first camera includes: Obtain the exposure time and gain value of the first camera, and calculate the average brightness of the target scene image; Based on the exposure time and the gain value, the total exposure time is obtained; The LV value is obtained based on the total exposure time and the average brightness.

[0007] In some embodiments, the second camera captures images based on the exposure control parameters and, in conjunction with the first camera, acquires a face image, including: A first face image and a second face image are acquired based on the first camera and the second camera, respectively, and the second face image is obtained according to the exposure control parameters; Determine the brightness of the second face image and determine whether the brightness is within the brightness buffer range. If so, face recognition is performed using the first face image and the second face image. If not, re-capture the face image for brightness assessment. The brightness buffer is determined based on the average brightness corresponding to the exposure control parameters, which are obtained from the parameter mapping table.

[0008] In some embodiments, the method for constructing the parameter mapping table includes: Images are captured using the first camera and the second camera in different scenarios; The LV value of the first camera and the exposure control parameters of the second camera are determined based on the acquired images. The exposure control parameters include camera exposure parameters and exposure time. The parameter mapping table is generated by mapping the LV values ​​to the exposure control parameters one by one.

[0009] In some embodiments, the first camera includes an RGB camera, and the second camera includes an infrared camera.

[0010] In some embodiments, the step of looking up a preset parameter mapping table based on the LV value to obtain the corresponding exposure control parameters includes: The LV value is sent to the driver of the second camera, and the driver looks up the parameter mapping table to obtain the camera exposure parameters and exposure time corresponding to the LV value. The camera exposure parameters and the exposure time are written to the sensor of the second camera via the I2C interface.

[0011] Secondly, embodiments of this application provide a rapid startup system for a binocular camera based on parameter mapping, wherein the binocular camera includes a first camera and a second camera; the system includes: The detection module is used to acquire a target scene image through the first camera, identify the target scene image, and determine whether a human face exists. A startup module is used to activate the second camera in response to the presence of a human face in the target scene image; The lookup module is used to obtain the LV value of the first camera, and look up the corresponding exposure control parameters in a preset parameter mapping table based on the LV value. The LV value is used to characterize the ambient light intensity, and the parameter mapping table includes the mapping relationship between the LV value of the first camera and the parameters of the second camera. The recognition module is used to control the second camera to take pictures based on the exposure control parameters, and in conjunction with the first camera, to acquire a face image and perform face recognition based on the face image.

[0012] In some embodiments, the lookup module includes: The parameter acquisition module is used to acquire the exposure time and gain value of the first camera and calculate the average brightness of the target scene image; An exposure calculation module is used to obtain the total exposure time based on the exposure time and the gain value; The LV value determination module obtains the LV value based on the total exposure time and the average brightness.

[0013] Thirdly, embodiments of this application provide a computer device, including a memory, a processor, and a computer program stored in the memory and executable on the processor. When the processor executes the computer program, it implements the parameter mapping-based binocular camera fast startup method as described in the first aspect above.

[0014] Fourthly, embodiments of this application provide a computer-readable storage medium having a computer program stored thereon, which, when executed by a processor, implements the binocular camera fast startup method based on parameter mapping as described in the first aspect above.

[0015] Compared to related technologies, the binocular camera fast startup method based on parameter mapping provided in this application acquires a target scene image through a first camera, identifies the target scene image to determine if a face exists, and, in response to the presence of a face in the target scene image, activates the second camera, acquires the LV value of the first camera, looks up the corresponding exposure control parameters in a preset parameter mapping table based on the LV value, and then uses the second camera to capture an image based on the exposure control parameters, in conjunction with the first camera to acquire a face image. Face recognition is then performed based on the face image, solving the problem of slow image convergence during binocular camera face recognition. It skips the trial-and-error process of the automatic exposure algorithm, directly calls the pre-stored parameters, and achieves correct exposure in the first frame, eliminating convergence delay. The first camera detects illumination in real time and inherits the same parameters synchronously from the camera, avoiding inconsistent brightness between the left and right images and eliminating binocular exposure differences. Attached Figure Description

[0016] The accompanying drawings, which are included to provide a further understanding of this application and form part of this application, illustrate exemplary embodiments and are used to explain this application, but do not constitute an undue limitation of this application. In the drawings: Figure 1 This is a flowchart of a method for fast startup of a binocular camera based on parameter mapping according to an embodiment of this application; Figure 2 This is a flowchart of a second camera activation method according to an embodiment of this application; Figure 3 This is a structural block diagram of a binocular camera rapid startup system based on parameter mapping according to an embodiment of this application; Figure 4 This is a schematic diagram of the internal structure of an electronic device according to an embodiment of this application. Detailed Implementation

[0017] To make the objectives, technical solutions, and advantages of this application clearer, the application is described and illustrated below with reference to the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are merely illustrative and not intended to limit the scope of this application. All other embodiments obtained by those skilled in the art based on the embodiments provided in this application without inventive effort are within the scope of protection of this application.

[0018] Obviously, the accompanying drawings described below are merely some examples or embodiments of this application. Those skilled in the art can apply this application to other similar scenarios based on these drawings without any inventive effort. Furthermore, it is understood that although the efforts made in this development process may be complex and lengthy, for those skilled in the art related to the content disclosed in this application, any changes to design, manufacturing, or production based on the technical content disclosed in this application are merely conventional technical means and should not be construed as insufficient disclosure of the content of this application.

[0019] In this application, the reference to "embodiment" means that a specific feature, structure, or characteristic described in connection with an embodiment may be included in at least one embodiment of this application. The appearance of this phrase in various places in the specification does not necessarily refer to the same embodiment, nor is it a separate or alternative embodiment that is mutually exclusive with other embodiments. It will be explicitly and implicitly understood by those skilled in the art that the embodiments described in this application may be combined with other embodiments without conflict.

[0020] Unless otherwise defined, the technical or scientific terms used in this application shall have the ordinary meaning understood by one of ordinary skill in the art to which this application pertains. The terms “a,” “an,” “an,” “the,” and similar words used in this application do not indicate quantity limitation and may indicate singular or plural. The terms “comprising,” “including,” “having,” and any variations thereof used in this application are intended to cover non-exclusive inclusion; for example, a process, method, system, product, or device that includes a series of steps or modules (units) is not limited to the listed steps or units, but may also include steps or units not listed, or may include other steps or units inherent to these processes, methods, products, or devices. The terms “connected,” “linked,” “coupled,” and similar words used in this application are not limited to physical or mechanical connections, but may include electrical connections, whether direct or indirect. “Multiple” used in this application refers to two or more. “And / or” describes the relationship between related objects, indicating that three relationships may exist; for example, “A and / or B” can represent: A alone, A and B simultaneously, and B alone. The character " / " generally indicates that the preceding and following objects are in an "or" relationship. The terms "first," "second," and "third" used in this application are merely to distinguish similar objects and do not represent a specific ordering of the objects.

[0021] This embodiment provides a method for quickly starting up a stereo camera based on parameter mapping. The stereo camera includes a first camera and a second camera. Figure 1 This is a flowchart of a method for fast startup of a binocular camera based on parameter mapping according to an embodiment of this application, such as... Figure 1 As shown, the process includes the following steps: Step S101: Acquire the target scene image through the first camera, identify the target scene image, and determine whether a human face exists.

[0022] Preferably, in this embodiment, the first camera of the binocular camera is an RGB camera, and the second camera is an infrared camera.

[0023] RGB+IR binocular cameras for face recognition combine the advantages of visible light and infrared imaging, improving the security, environmental adaptability, and anti-spoofing capabilities of face recognition. Infrared imaging can identify non-biological materials through differences in thermal radiation distribution or material reflectivity; therefore, RGB+IR binocular cameras can resist both 2D attacks (printed photos, mobile phone screens, etc.) and 3D attacks (silicone masks, wax figures, etc.). Furthermore, the image features acquired by the RGB and infrared cameras are complementary, and face models trained using both types of data can significantly reduce the false recognition rate.

[0024] Besides RGB+infrared types, stereo cameras can also be RGB+depth (RGB-D) stereo cameras, thermal infrared (IR) stereo cameras, polarized light stereo cameras, or near-infrared stereo cameras. The specific type of stereo camera can be selected based on the application scenario of face recognition.

[0025] Step S102: In response to the presence of a human face in the target scene image, the second camera is activated.

[0026] If no face is detected, only one camera (e.g., RGB) and a lightweight face detection algorithm are used, significantly reducing power consumption. The second camera (e.g., infrared / depth) is only activated when a face is detected, avoiding continuous high-load computation. Furthermore, the continuous operating time of high-power components in the binocular camera (e.g., infrared emitter, depth sensor) is reduced, lowering the risk of overheating and aging.

[0027] Step S103: Obtain the LV value of the first camera, look up the preset parameter mapping table based on the LV value, and obtain the corresponding exposure control parameters. The LV value is used to characterize the ambient light intensity. The parameter mapping table includes the mapping relationship between the LV value of the first camera and the parameters of the second camera.

[0028] By constructing a parameter mapping table, the exposure control parameters (including camera exposure parameters and exposure time) of the second camera can be quickly determined when the second camera is started. Shooting is then performed using these exposure control parameters, which shortens the time from startup to convergence of the second camera.

[0029] In some embodiments, the method for constructing the parameter mapping table includes: Step S201: Acquire images using the first camera and the second camera in different scenarios.

[0030] Step S202: Determine the LV value of the first camera and the exposure control parameters of the second camera based on the acquired image. The exposure control parameters include camera exposure parameters and exposure time.

[0031] Step S203: Match the LV values ​​with the exposure control parameters one by one to generate a parameter mapping table.

[0032] Collect the light value (LV) of the first camera under different scenarios, as well as the exposure parameters gain, exposure time (time) of the second camera corresponding to each LV value (assuming the brightness of the IR fill light is fixed), and the average brightness mlum of the IR image.

[0033] Data is collected based on commonly used scenarios. For example, the LV value of the first camera at the lobby entrance is LV0 during the day, LV1 with lights on at night, and LV2 with lights off at night; in a normal office area or meeting room, the LV value is LV3 during the day, LV4 with lights on at night, and LV5 with lights off at night; and by the window, the LV value is LV6 during the day, LV7 with lights on at night, and LV8 with lights off at night. These LV values ​​are then compiled into a matrix. The LV matrix is ​​as follows: [LV0 LV1 LV2 LV3 LV4 LV5 LV6 LV7 LV8] While collecting the LV values ​​of RGB, the exposure parameters gain, exposure time time, and average brightness mlum of the second camera image are also collected, resulting in the corresponding arrays gain, time, and mlum matrices: [gain0 gain1 gain2 gain3 gain4 gain5 gain6 gain7 gain8] [time0 time1 time2 time3 time4 time5 time6 time7 time8] [mlum0 mlum1 mlum2 mlum3 mlum4 mlum5 mlum6 mlum7 mlum8] Based on the parameter information collected above, a total matrix rgb2ir is constructed that maps the LV value of the first camera to the gain and time of the second camera.

[0034] The total matrix RGB2IR is stored as a parameter mapping table in the driver of the second camera. To make more precise exposure adjustments, as many values ​​as possible can be collected from the above matrix to achieve the optimal exposure brightness. This is to emphasize the method; more refined adjustment schemes will not be elaborated here.

[0035] In some embodiments, obtaining the LV value of the first camera in step S103 includes: Step S1031: Obtain the exposure time and gain value of the first camera, and calculate the average brightness of the target scene image.

[0036] Step S1032: Based on the exposure time and gain value, obtain the total exposure time.

[0037] Step S1033: Obtain the LV value based on the total exposure time and average brightness.

[0038] The LV value is calculated using the following method in this embodiment: LV = meanluma / exp / 1000 Where meanluma refers to the average brightness of the current image, exp represents the total exposure time, exp=gain*time, the unit is seconds, gain represents the gain value, and time represents the exposure time.

[0039] In some embodiments, step S103 involves looking up a preset parameter mapping table based on the LV value to obtain the corresponding exposure control parameters, including: In step S1034, the LV value is sent to the driver of the second camera. The driver looks up the parameter mapping table to obtain the camera exposure parameters and exposure time corresponding to the LV value.

[0040] Preferably, the parameter mapping table is stored in the driver of the second camera. Alternatively, the parameter mapping table can also be stored in the driver of the first camera. After the first camera looks up the corresponding exposure parameters for the second camera using the parameter mapping table, it directly transmits the exposure parameter values ​​to the second camera. Alternatively, the parameter mapping table can be stored in an external system, and the lookup process can be performed in the external system.

[0041] Step S1035: Write the camera exposure parameters and exposure time into the sensor of the second camera via the I2C interface.

[0042] I2C allows master devices (such as MCUs) to directly modify the exposure control registers inside the sensor, enabling low-latency, high-precision parameter adjustments (such as exposure time accurate to the microsecond level). Furthermore, communication is only conducted via I2C when parameters change; the bus remains idle at other times, making it more power-efficient than protocols with continuous transmission (such as SPI).

[0043] Figure 2 This is a flowchart of a second camera activation method according to an embodiment of this application, such as... Figure 2 As shown, when a face is detected entering the frame by the first camera, the second camera is activated. At the same time, the current LV value of the first camera is calculated and transmitted to the driver of the second camera. The driver looks up the corresponding exposure parameters gain and exposure time time in a table and writes them directly to the sensor of the second camera through the I2C interface.

[0044] In step S104, the second camera takes a picture based on the exposure control parameters and, together with the first camera, acquires a face image, and performs face recognition based on the face image.

[0045] Normally, cameras need to adjust the exposure through multiple iterations (usually 300ms to 1s), while the parameter mapping table can be directly called through pre-stored calibration data, compressing the parameter convergence time to 10 to 50ms, enabling the second camera to respond quickly and improving the efficiency of face recognition.

[0046] The first camera detects lighting in real time and inherits the same parameters synchronously from the second camera to avoid inconsistent brightness between the left and right images and eliminate binocular exposure differences. Furthermore, the mapping table can pre-store parameter combinations for special scenes such as high dynamic range (HDR), backlight, and low light to avoid real-time calculation failures.

[0047] In some embodiments, step S104 specifically includes: Step S1041: Acquire a first face image and a second face image based on the first camera and the second camera respectively. The second face image is obtained according to the exposure control parameters.

[0048] Step S1042: Determine the brightness of the second face image and determine whether the brightness is within the brightness buffer. If yes, perform face recognition using the first and second face images. If no, re-capture the face image and perform brightness determination. The brightness buffer is determined based on the average brightness corresponding to the exposure control parameters, which is obtained from the parameter mapping table.

[0049] To reduce the oscillation caused by the constant switching of brightness, this embodiment sets a buffer zone. If the current brightness of the second camera is within this buffer zone, it is considered stable and no further exposure adjustment is made.

[0050] Preferably, the correspondence between the collected second camera exposure parameters gain, exposure time time, and average brightness mlum of the image is stored in a parameter mapping table. The buffer is determined based on the target brightness target, which is the average brightness mlum of the second camera image collected above. For example, if the current second camera exposure parameters gain and exposure time time are gain2 and time2 respectively, then target = mlum2. The buffer range is set to [target-i, target+i], where the value of i is set based on the actual situation.

[0051] If the current brightness of the second camera is not within the buffer, adjust the parameters and retake the shot until the image brightness falls within the buffer.

[0052] By setting a buffer, the oscillation caused by switching between brightness levels is avoided, and the efficiency of parameter adjustment is improved, so that convergence can be achieved by setting the exposure parameters and exposure time only once.

[0053] By skipping the trial-and-error process of the automatic exposure (AE) algorithm (which typically requires 3-10 frame iterations) and directly calling pre-stored parameters, the first frame achieves correct exposure, eliminating convergence delay. The first camera detects lighting in real time and inherits the same parameters synchronously from the other camera, avoiding inconsistent brightness between the left and right images and eliminating binocular exposure differences. The mapping table can pre-store parameter combinations for special scenes such as high dynamic range (HDR), backlight, and low light, preventing real-time calculation failures.

[0054] It should be noted that the steps shown in the above process or in the flowchart of the accompanying figures can be executed in a computer system such as a set of computer-executable instructions, and although a logical order is shown in the flowchart, in some cases the steps shown or described may be executed in a different order than that shown here.

[0055] This embodiment also provides a rapid startup system for a binocular camera based on parameter mapping. This system is used to implement the above embodiments and preferred embodiments, and details already described will not be repeated. As used below, the terms "module," "unit," "subunit," etc., can refer to a combination of software and / or hardware that performs a predetermined function. Although the apparatus described in the following embodiments is preferably implemented in software, hardware implementation, or a combination of software and hardware, is also possible and contemplated.

[0056] Figure 3 This is a structural block diagram of a binocular camera rapid startup system based on parameter mapping according to an embodiment of this application. The binocular camera includes a first camera and a second camera, such as... Figure 3 As shown, the system includes: Detection module 31 is used to acquire target scene images through the first camera, identify the target scene images, and determine whether a human face exists. Startup module 32 is used to start the second camera in response to the presence of a human face in the target scene image; The lookup module 33 is used to obtain the LV value of the first camera, look up the preset parameter mapping table based on the LV value, and obtain the corresponding exposure control parameters. The LV value is used to characterize the ambient light intensity. The parameter mapping table includes the mapping relationship between the LV value of the first camera and the parameters of the second camera. The recognition module 34 is used to control the second camera to take pictures based on the exposure control parameters, and in conjunction with the first camera, to acquire face images and perform face recognition based on the face images.

[0057] In some embodiments, the lookup module 33 includes: The parameter acquisition module is used to acquire the exposure time and gain value of the first camera and calculate the average brightness of the target scene image; The exposure calculation module is used to obtain the total exposure time based on the exposure time and gain value; The LV value determination module obtains the LV value based on the total exposure time and average brightness.

[0058] In some embodiments, the identification module 34 includes: The image acquisition module is used to acquire a first face image and a second face image based on the first camera and the second camera, respectively. The second face image is obtained according to the exposure control parameters.

[0059] The judgment module is used to determine the brightness of the second face image and whether the brightness is within the brightness buffer. If so, face recognition is performed using the first and second face images. If not, a new face image is captured for brightness judgment. The brightness buffer is determined based on the average brightness corresponding to the exposure control parameters, which is obtained from a parameter mapping table.

[0060] In some embodiments, the system further includes: The data acquisition module is used to acquire images through the first and second cameras in different scenarios.

[0061] The parameter analysis module is used to determine the LV value of the first camera and the exposure control parameters of the second camera based on the acquired images. The exposure control parameters include camera exposure parameters and exposure time.

[0062] The mapping table construction module is used to map LV values ​​to exposure control parameters one-to-one and generate a parameter mapping table.

[0063] In some embodiments, the first camera includes an RGB camera and the second camera includes an infrared camera.

[0064] In some embodiments, the lookup module 33 includes: The parameter lookup module is used to send the LV value to the driver of the second camera. The driver looks up the parameter mapping table to obtain the camera exposure parameters and exposure time corresponding to the LV value.

[0065] The parameter writing module is used to write the camera exposure parameters and exposure time to the sensor of the second camera via the I2C interface.

[0066] The system described above skips the trial-and-error process of the automatic exposure (AE) algorithm (which typically requires 3-10 frame iterations) and directly calls pre-stored parameters, ensuring correct exposure in the first frame and eliminating convergence delay. The first camera detects lighting in real time and inherits the same parameters synchronously from the second camera, avoiding inconsistent brightness between the left and right images and eliminating binocular exposure differences. The mapping table can pre-store parameter combinations for special scenes such as high dynamic range (HDR), backlighting, and low light, preventing real-time calculation failures.

[0067] It should be noted that the above modules can be functional modules or program modules, and can be implemented through software or hardware. For modules implemented through hardware, the above modules can reside in the same processor; or the above modules can be located in different processors in any combination.

[0068] This embodiment also provides an electronic device, including a memory and a processor, wherein the memory stores a computer program and the processor is configured to run the computer program to perform the steps in any of the above method embodiments.

[0069] Optionally, the electronic device may further include a transmission device and an input / output device, wherein the transmission device is connected to the processor and the input / output device is connected to the processor.

[0070] Optionally, in this embodiment, the processor can be configured to perform the following steps via a computer program: S1 acquires an image of the target scene through the first camera, identifies the target scene image, and determines whether a human face exists.

[0071] S2, in response to the presence of a human face in the target scene image, activates the second camera.

[0072] S3. Obtain the LV value of the first camera, look up the preset parameter mapping table based on the LV value, and obtain the corresponding exposure control parameters. The LV value is used to characterize the ambient light intensity. The parameter mapping table includes the mapping relationship between the LV value of the first camera and the parameters of the second camera.

[0073] S4, the second camera takes pictures based on the exposure control parameters, and together with the first camera, acquires a face image, and performs face recognition based on the face image.

[0074] It should be noted that the specific examples in this embodiment can refer to the examples described in the above embodiments and optional implementations, and will not be repeated here.

[0075] In one embodiment, Figure 4 This is a schematic diagram of the internal structure of an electronic device according to an embodiment of this application, such as... Figure 4 As shown, an electronic device is provided, which can be a server, and its internal structure diagram can be as follows. Figure 4As shown, this electronic device includes a processor, memory, network interface, and database connected via a system bus. The processor provides computing and control capabilities. The memory includes a non-volatile storage medium and internal memory. The non-volatile storage medium stores the operating system, computer programs, and database. The internal memory provides an environment for the operation of the operating system and computer programs in the non-volatile storage medium. The database stores data. The network interface communicates with external terminals via a network connection. When executed by the processor, the computer program implements a parameter mapping-based method for rapid startup of a binocular camera.

[0076] Those skilled in the art will understand that Figure 4 The structure shown is merely a block diagram of a portion of the structure related to the present application and does not constitute a limitation on the electronic device to which the present application is applied. The specific electronic device may include more or fewer components than shown in the figure, or combine certain components, or have different component arrangements.

[0077] Those skilled in the art will understand that all or part of the processes in the methods of the above embodiments can be implemented by a computer program instructing related hardware. This computer program can be stored in a non-volatile computer-readable storage medium. When executed, the computer program can include the processes of the embodiments of the above methods. Any references to memory, storage, databases, or other media used in the embodiments provided in this application can include non-volatile and / or volatile memory. Non-volatile memory may include read-only memory (ROM), programmable ROM (PROM), electrically programmable ROM (EPROM), electrically erasable programmable ROM (EEPROM), or flash memory. Volatile memory may include random access memory (RAM) or external cache memory. By way of illustration and not limitation, RAM is available in a variety of forms, such as static RAM (SRAM), dynamic RAM (DRAM), synchronous DRAM (SDRAM), dual data rate SDRAM (DDRSDRAM), enhanced SDRAM (ESDRAM), synchronous link DRAM (SLDRAM), RAMbus direct RAM (RDRAM), direct memory bus dynamic RAM (DRDRAM), and memory bus dynamic RAM (RDRAM), etc.

[0078] Those skilled in the art should understand that the technical features of the above embodiments can be combined in any way. For the sake of brevity, not all possible combinations of the technical features in the above embodiments have been described. However, as long as there is no contradiction in the combination of these technical features, they should be considered to be within the scope of this specification.

[0079] The embodiments described above are merely illustrative of several implementation methods of this application, and while the descriptions are relatively specific and detailed, they should not be construed as limiting the scope of the invention patent. It should be noted that those skilled in the art can make various modifications and improvements without departing from the concept of this application, and these all fall within the protection scope of this application. Therefore, the protection scope of this patent application should be determined by the appended claims.

Claims

1. A method for fast startup of a binocular camera based on parameter mapping, characterized in that, The binocular camera includes a first camera and a second camera; the method includes: The first camera acquires an image of the target scene, and the image of the target scene is then recognized to determine whether a human face exists. In response to the presence of a human face in the target scene image, the second camera is activated; The LV value of the first camera is obtained, and the corresponding exposure control parameters are obtained by looking up the preset parameter mapping table based on the LV value. The LV value is used to characterize the ambient light intensity, and the parameter mapping table includes the mapping relationship between the LV value of the first camera and the parameters of the second camera. The second camera takes a picture based on the exposure control parameters and, together with the first camera, acquires a face image, and performs face recognition based on the face image.

2. The method according to claim 1, characterized in that, The step of obtaining the LV value of the first camera includes: Obtain the exposure time and gain value of the first camera, and calculate the average brightness of the target scene image; Based on the exposure time and the gain value, the total exposure time is obtained; The LV value is obtained based on the total exposure time and the average brightness.

3. The method according to claim 2, characterized in that, The second camera captures images based on the exposure control parameters, and in conjunction with the first camera, acquires facial images including: A first face image and a second face image are acquired based on the first camera and the second camera, respectively, and the second face image is obtained according to the exposure control parameters; Determine the brightness of the second face image and determine whether the brightness is within the brightness buffer range. If so, face recognition is performed using the first face image and the second face image. If not, re-capture the face image for brightness assessment. The brightness buffer is determined based on the average brightness corresponding to the exposure control parameters, which are obtained from the parameter mapping table.

4. The method according to claim 1, characterized in that, The method for constructing the parameter mapping table includes: Images are captured using the first camera and the second camera in different scenarios; The LV value of the first camera and the exposure control parameters of the second camera are determined based on the acquired images. The exposure control parameters include camera exposure parameters and exposure time. The parameter mapping table is generated by mapping the LV values ​​to the exposure control parameters one by one.

5. The method according to claim 1, characterized in that, The first camera includes an RGB camera, and the second camera includes an infrared camera.

6. The method according to claim 1, characterized in that, The step of looking up the preset parameter mapping table based on the LV value to obtain the corresponding exposure control parameters includes: The LV value is sent to the driver of the second camera, and the driver looks up the parameter mapping table to obtain the camera exposure parameters and exposure time corresponding to the LV value. The camera exposure parameters and the exposure time are written to the sensor of the second camera via the I2C interface.

7. A rapid startup system for a binocular camera based on parameter mapping, characterized in that, The binocular camera includes a first camera and a second camera; the system includes: The detection module is used to acquire a target scene image through the first camera, identify the target scene image, and determine whether a human face exists. A startup module is used to activate the second camera in response to the presence of a human face in the target scene image; The lookup module is used to obtain the LV value of the first camera, and look up the corresponding exposure control parameters in a preset parameter mapping table based on the LV value. The LV value is used to characterize the ambient light intensity, and the parameter mapping table includes the mapping relationship between the LV value of the first camera and the parameters of the second camera. The recognition module is used to control the second camera to take pictures based on the exposure control parameters, and in conjunction with the first camera, to acquire a face image and perform face recognition based on the face image.

8. The system according to claim 7, characterized in that, The search module includes: The parameter acquisition module is used to acquire the exposure time and gain value of the first camera and calculate the average brightness of the target scene image; An exposure calculation module is used to obtain the total exposure time based on the exposure time and the gain value; The LV value determination module obtains the LV value based on the total exposure time and the average brightness.

9. An electronic device comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, characterized in that, When the processor executes the computer program, it implements the binocular camera fast startup method based on parameter mapping as described in any one of claims 1 to 6.

10. A storage medium having a computer program stored thereon, characterized in that, When the program is executed by the processor, it implements the fast startup method for a stereo camera based on parameter mapping as described in any one of claims 1 to 6.

Images