An automatic exposure method, device and storage medium based on a non-homologous binocular camera

Abstract

An automatic exposure method based on a non-homologous binocular camera, comprising: step S1: performing distortion correction on original first and second images, and then performing polar correction to obtain corrected first and second images I ir and I rgb ; step S2: detecting target objects in the first and second images I ir and I rgb respectively; step S3: determining a target object region ROI1 on the image in which the target object is detected, and determining a target object region ROI2 on the image in which the target object is not detected according to the correspondence between the first and second images I ir and I rgb , and then adjusting exposure according to the target object region ROI2 on the image in which the target object is not detected; step S4: evaluating the brightness of the first and second images I ir and I rgb ; step S5: calculating the image quality of the target object regions ROI ir and ROI rgb ; and step S6: adjusting the camera exposure.

Description

Technical Field

[0001] This invention relates to the field of depth cameras, and more specifically, to an automatic exposure method, apparatus, and storage medium based on a non-isomorphic binocular camera. Background Technology

[0002] Binocular vision is one of the mainstream technologies for obtaining depth data. Utilizing the principle of parallax, it calculates depth information from two images, combining the intrinsic and extrinsic parameters of the depth camera. The depth data obtained through binocular vision can be used for 3D reconstruction, making depth cameras valuable in fields such as biometrics.

[0003] In existing technologies, binocular imaging is typically used to obtain better target object information and perform matching. Non-binocular imaging, on the other hand, produces two different images, resulting in differences in clarity, feature extraction, and other aspects. When automatically adjusting the exposure of non-binocular cameras, a generic automatic exposure adjustment strategy is used without considering the specific characteristics of the non-binocular imaging and the target object, leading to unclear target objects or inefficient automatic exposure. Summary of the Invention

[0004] Therefore, the present invention addresses the first image I. ir Second image I rgb The system detects and evaluates target objects separately, and adjusts camera exposure based on image quality. This invention combines the characteristics of non-homogeneous binocular images, utilizes target object features, is applicable to different target objects, reduces image processing load, and significantly improves the accuracy of automatic exposure.

[0005] In a first aspect, the present invention provides an automatic exposure method based on a non-homogeneous binocular camera, characterized by comprising the following steps:

[0006] Step S1: Perform distortion correction on the original first image and the original second image respectively, and then perform epipolar correction to obtain the corrected first image I. ir and the corrected second image I rgb ;

[0007] Step S2: For the first image I ir and the second image I rgb Detect the target object separately; if in the first image I ir and the second image I rgb If the target object is detected in both images, then the first image I is obtained respectively. ir Target Object Region ROI ir and the second image I rgb Target Object Region ROIrgb Execute step S5; if only in the first image I ir and the second image I rgb If a target object is detected in one of the images, then step S3 is executed; if no target object is detected, then step S4 is executed; wherein, the first image I ir and the second image I rgb These are non-homologous images;

[0008] Step S3: Determine the target object region ROI1 on the image where the target object has been detected, and based on the first image I... ir and the second image I rgb Based on the correspondence, the target object region ROI2 on the image where no target object was detected is determined, and then the exposure is adjusted according to the target object region ROI2 on the image where no target object was detected.

[0009] Step S4: For the first image I ir and the second image I rgb The brightness is evaluated; if the brightness is abnormal, the exposure gain needs to be reset; if the brightness is normal, no action is taken.

[0010] Step S5: Calculate the ROI of the target object region. ir and the target object region ROI rgb Image quality;

[0011] Step S6: Adjust the camera exposure.

[0012] Optionally, the automatic exposure method based on a non-homogeneous binocular camera is characterized in that step S5 includes:

[0013] Step S51: Calculate the ROI of the target object region. ir and the target object region ROI rgb Average brightness;

[0014] Step S52: Calculate the ROI of the target object region. ir and the target object region ROI rgb Image clarity;

[0015] Step S53: If the average brightness and the image sharpness are both within a reasonable range, then output the image; otherwise, proceed to step S6.

[0016] Optionally, the automatic exposure method based on a non-homogeneous binocular camera is characterized in that, in step S4, the first image I... ir and the second image I rgbWhen evaluating brightness, only a preset range including the image center is evaluated.

[0017] Optionally, the automatic exposure method based on a non-homogeneous binocular camera is characterized in that, in step S2, if a target object is detected, the area of ​​the target object is judged; if the area of ​​the target object is less than a threshold, it is judged that no target object has been detected.

[0018] Optionally, the automatic exposure method based on a non-homogeneous binocular camera is characterized in that, in step S4, the first image I... ir and the second image I rgb When evaluating brightness, the first image I ir and the second image I rgb Subtract the two images and use the resulting new image for evaluation.

[0019] Optionally, the automatic exposure method based on a non-synthetic binocular camera is characterized in that step S6 includes:

[0020] Step S61: If the average brightness of the target area is too low, increase the exposure time, current value, or gain value; if the average brightness of the target area is too high, decrease the exposure time, current value, or gain value.

[0021] Step S62: If the sharpness of the target object is low, increase the exposure time, increase the current value, or decrease the gain value.

[0022] Optionally, the automatic exposure method based on a non-homogeneous binocular camera is characterized in that, in step S61:

[0023] If the target object region ROI ir and the target object region ROI rgb If the average brightness is too low, the order of adjustment is exposure time, gain value, and current value.

[0024] If the target object region ROI ir and the target object region ROI rgb If the average brightness is too high, the order of adjustment is current value, gain value, and exposure time.

[0025] Optionally, the automatic exposure method based on a non-homogeneous binocular camera is characterized in that, before processing the image in any step, the first image I is... ir and the second image I rgb Compress it.

[0026] Secondly, the present invention provides an automatic exposure device based on a non-homogeneous binocular camera, characterized in that it comprises:

[0027] processor;

[0028] A memory module that stores executable instructions of the processor;

[0029] The processor is configured to perform the steps of the automatic exposure method based on a non-homogeneous binocular camera as described above by executing the executable instructions.

[0030] Thirdly, the present invention provides a computer-readable storage medium for storing a program, characterized in that, when the program is executed, it implements the steps of the automatic exposure method based on a non-homogeneous binocular camera as described in any of the preceding claims.

[0031] Compared with the prior art, the present invention has the following beneficial effects:

[0032] This invention employs non-homogeneous binocular technology, which, compared to homogeneous binoculars, can acquire more types of data information, obtaining more data in a single acquisition, thus improving data acquisition efficiency and reducing the number of acquisitions. Furthermore, cross-verification of multiple data sources can enhance the accuracy of biometric identification.

[0033] This invention performs separate detections on the first and second images and classifies the different detection results, thus adapting to more situations and improving its adaptability to different target objects. Furthermore, it allows for targeted processing schemes for different target objects, enhancing the processing effect.

[0034] This invention identifies target areas with high efficiency, enabling rapid autofocus and automatic exposure, meeting the fast response requirements of practical applications. Furthermore, the rapid automatic exposure makes it easier to achieve accurate focus and exposure, improving image quality and satisfying the demands of commercial applications.

[0035] This invention evaluates both the first and second images, resulting in accurate focusing, clearer final images, guaranteed image quality, better acquisition of image information, and accurate processing results. Attached Figure Description

[0036] To more clearly illustrate the technical solutions in the embodiments of the present invention or the prior art, the drawings used in the description of the embodiments or the prior art will be briefly introduced below. Obviously, the drawings described below are merely embodiments of the present invention. For those skilled in the art, other drawings can be obtained based on the provided drawings without creative effort. Other features, objects, and advantages of the present invention will become more apparent by reading the following detailed description of non-limiting embodiments with reference to the accompanying drawings:

[0037] Figure 1 This is a flowchart illustrating the steps of an automatic exposure method based on a non-isomorphic binocular camera in an embodiment of the present invention.

[0038] Figure 2 This is a flowchart illustrating the steps for calculating the image quality of a target object region in an embodiment of the present invention.

[0039] Figure 3 This is a flowchart illustrating a step for adjusting camera exposure in an embodiment of the present invention;

[0040] Figure 4 This is a schematic diagram of the structure of an automatic exposure device based on a non-homogeneous binocular camera in an embodiment of the present invention;

[0041] Figure 5 This is a schematic diagram of a computer-readable storage medium according to an embodiment of the present invention. Detailed Implementation

[0042] The present invention will now be described in detail with reference to specific embodiments. These embodiments will help those skilled in the art to further understand the present invention, but do not limit the invention in any way. It should be noted that those skilled in the art can make several modifications and improvements without departing from the concept of the present invention. These all fall within the protection scope of the present invention.

[0043] The terms “first,” “second,” “third,” “fourth,” etc. (if present) in the specification, claims, and accompanying drawings of this invention are used to distinguish similar objects and are not necessarily used to describe a particular order or sequence. It should be understood that such data can be interchanged where appropriate so that embodiments of the invention described herein can be implemented, for example, in orders other than those illustrated or described herein. Furthermore, the terms “comprising” and “having,” and any variations thereof, are intended to cover a non-exclusive inclusion; for example, a process, method, system, product, or apparatus that comprises a series of steps or units is not necessarily limited to those steps or units explicitly listed, but may include other steps or units not explicitly listed or inherent to such processes, methods, products, or apparatus.

[0044] The technical solution of the present invention will be described in detail below with reference to specific embodiments. These specific embodiments can be combined with each other, and the same or similar concepts or processes may not be described again in some embodiments.

[0045] The present invention provides an automatic exposure method based on a non-homogeneous binocular camera, which aims to solve the problems existing in the prior art.

[0046] The technical solutions of the present invention and how they solve the above-mentioned technical problems will be described in detail below with specific embodiments. These specific embodiments can be combined with each other, and the same or similar concepts or processes may not be repeated in some embodiments. The embodiments of the present invention will now be described with reference to the accompanying drawings.

[0047] Non-similar binocular cameras refer to binocular systems composed of two cameras using different technical principles. They can simultaneously acquire two types of images and obtain depth data using the principle of parallax. For example, a binocular system composed of an RGB camera and an infrared camera is a non-similar binocular system. The two images acquired by a non-similar binocular camera are non-similar images.

[0048] Figure 1 This is a flowchart illustrating the steps of an automatic exposure method based on a non-homogeneous binocular camera according to an embodiment of the present invention. Figure 1 As shown, an automatic exposure method based on a non-homogeneous binocular camera in an embodiment of the present invention includes the following steps.

[0049] Step S1: Perform distortion correction on the original first image and the original second image respectively, and then perform epipolar correction to obtain the corrected first image I. ir and the corrected second image I rgb .

[0050] In this step, the original first image and the original second image are non-homogeneous images, meaning they were obtained using different techniques. Distortion correction is performed on the original first image, followed by epipolar correction, to obtain the corrected first image I. ir The original second image is distorted and then epipolarized to obtain the corrected second image I. rgbSince distortion is caused by the lens imaging principle, distortion correction for the original first and second images needs to be performed according to the parameters of each acquisition device. Epipolar correction is a correction for the binocular system. It involves rotating the two cameras and redefining a new image plane so that the epipolar pairs are collinear and parallel to a coordinate axis (usually the horizontal axis) of the image plane. This operation simultaneously establishes a new stereo image pair. After correction, the same matching point pair is located in the same row in both views, meaning they only differ in their horizontal coordinates (or column coordinates), a difference called parallax. However, since the images used are the first and second images, the content they capture differs, making it impossible to directly solve for parallax using existing techniques. This step corrects both images to make the data more accurate, thereby making subsequent matching more accurate. It should be noted that the original first and second images used in this embodiment are usually acquired by a calibrated binocular system, where one camera is the first camera and the other is the second camera. The first camera is used to acquire the first image, and the second camera is used to acquire the second image, with both cameras simultaneously acquiring the target image. For example, the first camera is a near-infrared camera, and the first image is a near-infrared image; the second camera is a color camera, and the second image is a color image.

[0051] Step S2: For the first image I ir and the second image I rgb Detect the target objects separately.

[0052] In this step, the same object detection model is used for detection in both the first and second images, meaning the detected target object is the same object, such as simultaneously recognizing a human body, face, or hand. If the target object is detected in both the first and second images, then the first image I is obtained. ir Target Object Region ROI ir and the second image I rgb Target Object Region ROI rgb Execute step S5; if a target object is detected in only one of the first image and the second image, then execute step S3; if no target object is detected, then execute step S4; wherein, the first image I ir and the second image I rgb These are non-homologous images.

[0053] In some embodiments, if a target object is detected, the area of ​​the target object is determined. If the area of ​​the target object is less than a threshold, it is determined that no target object has been detected.

[0054] Step S3: Determine the target object region ROI1 on the image where the target object has been detected, and based on the first image I... ir and the second image I rgb Based on the correspondence, the target object region ROI2 on the image where no target object was detected is determined, and the exposure is adjusted according to the target object region ROI2 on the image where no target object was detected.

[0055] In this step, since only one target object is detected in the first and second images, the exposure needs to be adjusted based on the other image. Let's take the detection of the target object in the first image as an example. The target object region in the first image is ROI1. Since the first and second images are aligned, the corresponding target object region ROI2 in the second image can be obtained from ROI1 in the first image. Due to abnormal brightness in the second image, the target object cannot be detected, but ROI2 in the second image can be used to evaluate the exposure effect, thus allowing for exposure adjustment. This step utilizes data from a clear image to determine the target object region in a blurry image, enabling more precise exposure adjustment.

[0056] Step S4: For the first image I ir and the second image I rgb The brightness is evaluated. If the brightness is abnormal, the exposure gain needs to be reset; if the brightness is normal, no action is taken.

[0057] In this step, the brightness of the first and second images is evaluated, in case no image is detected in either image. This step evaluates the overall brightness of the first and second images; if the brightness is too high, the gain is reduced; if the brightness is too low, the gain is increased. If the brightness is normal, it indicates that there is no target object or the target object is too far away to achieve effective recognition; in this case, no action is taken, and the current state is maintained.

[0058] In some embodiments, the first image I ir and the second image I rgb When evaluating brightness, only a preset range, including the image center, is assessed. In specific application scenarios, such as facial recognition authentication, the target is usually located in the center of the image. Therefore, evaluating only the image center and its surrounding area can achieve very good results and save computational resources.

[0059] In some embodiments, the first image I ir and the second image I rgbWhen evaluating brightness, only a preset number of points are considered. Multiple points, typically no fewer than five, are preset in the central region of the image, and the image brightness is evaluated by averaging the brightness of these points. For example, if six points are preset, denoted as a1, a2, a3, a4, a5, and a6, the average brightness (a0) of these six points is used to evaluate the image brightness. If a0 is greater than a preset range, the brightness is considered too high; if a0 is less than the preset range, the brightness is considered too low.

[0060] In some embodiments, the first image I ir and the second image I rgb When evaluating brightness, the first image I ir and the second image I rgb The two images are subtracted, and the resulting new image is used for evaluation. Since the first and second images are not from the same source and acquire different signals, in some applications, a new image can be obtained by subtracting the first and second images. This new image is more sensitive to certain information, improving accuracy. For example, when photographing a hand, the infrared image captures the veins, while the color image captures the combined effect of the palm lines and veins. Subtracting the two makes the palm lines clearer and easier to distinguish. Alternatively, the color image can be converted to grayscale before subtracting from the infrared image, resulting in stronger data comparison.

[0061] Step S5: Calculate the ROI of the target object region. ir and the target object region ROI rgb Image quality.

[0062] In this step, although both the first and second images contain target object data, the target object may still have issues such as blurriness, which could lead to problems in subsequent depth processing. Therefore, image quality evaluation is necessary. This step only evaluates the image quality of the target object region to reduce data processing volume, improve the focus of subsequent steps, and obtain higher quality images. This step evaluates the image quality of the first image I... ir Target Object Region ROI ir Second image I rgb Target Object Region ROI rgb An assessment will be conducted.

[0063] Step S6: Adjust the camera exposure.

[0064] In this step, based on the first image I ir Target Object Region ROI ir Image quality and the second image I rgb Target Object Region ROI rgbThe camera exposure is adjusted to improve image quality. During adjustment, one or more of the exposure time, current value, or gain value are adjusted. If both the first and second images are overexposed, the exposure is reduced. If both the first and second images are underexposed, the exposure is increased. If the exposure states of the first and second images are inconsistent, the exposure is adjusted using the image with the abnormal state.

[0065] Before performing any step of image processing, the first image I is... ir and the second image I rgb Compress it.

[0066] This embodiment employs non-homogeneous binocular technology, which can improve performance in various biometric scenarios. For example, in facial recognition, eye information can be obtained simultaneously with face recognition for liveness detection; in palm recognition, palm vein features can be obtained simultaneously with palm print recognition for liveness detection. This embodiment utilizes the characteristics of non-homogeneous images to perform targeted processing on different types of images, adjusting exposure based on the image quality of the target area, ensuring that both the first and second images quickly reach optimal exposure, thereby obtaining clearer, higher-quality images.

[0067] Figure 2 This is a flowchart illustrating the steps for calculating the image quality of a target object region in an embodiment of the present invention. Figure 2 As shown, unlike the previous embodiments, a method for calculating the image quality of a target object region in this embodiment of the invention includes the following steps.

[0068] Step S51: Calculate the ROI of the target object region. ir and the target object region ROI rgb The average brightness.

[0069] In this step, the average brightness of the target object region is calculated. This calculation of the average brightness can be performed on the target object region (ROI). ir and target object region ROI rgb All pixel values ​​can be obtained using a sampling method, focusing only on the target object region (ROI). ir and target object region ROI rgb Values ​​are taken from a subset of pixels. When calculating average brightness, the ROI (Region of Interest) of the target object is considered. ir and target object region ROI rgb Calculate the average brightness of each separately.

[0070] Step S52: Calculate the ROI of the target object region. ir and the target object region ROI rgb Image clarity.

[0071] In this step, the mean gradient is used to represent image sharpness. The mean gradient refers to the significant difference in gray levels near the boundaries or shadows of an image, i.e., a large rate of gray level change. The mean gradient reflects the rate of change in the contrast of minute details in the image, that is, the rate of density change in multiple dimensions of the image, characterizing the relative sharpness of the image. When calculating image sharpness, the sharpness is calculated separately for the first and second images to obtain their respective image sharpness.

[0072] Step S53: If the average brightness and the image sharpness are both within a reasonable range, then output the image; otherwise, proceed to step S6.

[0073] In this step, the average brightness and image sharpness are judged. If the values ​​of the target object area in the first image and the second image are both within a reasonable range, the image is output; otherwise, it is judged as an exposure abnormality and needs to be adjusted, and step S6 is executed.

[0074] This embodiment evaluates image quality from two dimensions: average brightness and image sharpness. This allows for a better assessment of whether the image is in optimal exposure. By adjusting the exposure, optimal exposure can be quickly achieved, resulting in a clear and usable image and ensuring image quality.

[0075] Figure 3 This is a flowchart illustrating a step in adjusting camera exposure according to an embodiment of the present invention. Figure 3 As shown, unlike the previous embodiments, a method for adjusting camera exposure in this embodiment of the invention includes the following steps.

[0076] Step S61: If the average brightness of the target area is too low, increase the exposure time, current value, or gain value; if the average brightness of the target area is too high, decrease the exposure time, current value, or gain value.

[0077] In this step, if the target object region ROI ir and the target object region ROI rgb If the average brightness is too low, the order of adjustment is exposure time, gain value, and current value. If the target object region (ROI) is... ir and the target object region ROI rgb If the average brightness is too high, the adjustment order is: current value, gain value, and exposure time. The adjustment order is different when the average brightness is too low compared to when it is too high, ensuring both sensitivity and equipment stability.

[0078] During adjustment, if adjusting the first-order parameters to their maximum or minimum still fails to achieve the expected average brightness of the target area, then the second-order parameters are adjusted. If adjusting the second-order parameters to their maximum or minimum still fails to achieve the expected average brightness of the target area, then the third-order parameters are adjusted. For example, if the average brightness is too low, the exposure time is increased first. If increasing the exposure time to its maximum still fails to achieve the expected average brightness of the target area, the gain value is increased. If increasing the gain value to its maximum still fails to achieve the expected average brightness of the target area, the current value is increased.

[0079] Step S62: If the sharpness of the target object is low, increase the exposure time, increase the current value, or decrease the gain value.

[0080] The adjustment method in this step is the same as in the previous step, so it will not be repeated here.

[0081] This embodiment refines the adjustment method, considers the impact of different parameter adjustments, and adopts different sequences in different situations, making the parameter adjustment more effective and stable. While ensuring smooth adjustment, it is also easier to ensure image quality.

[0082] This invention also provides an automatic exposure device based on a non-isomorphic binocular camera, including a processor and a memory storing executable instructions for the processor. The processor is configured to execute steps of an automatic exposure method based on a non-isomorphic binocular camera by executing the executable instructions.

[0083] As described above, in this embodiment, a depth camera of a binocular system consisting of a first camera and a second camera is used to acquire a first image and a second image. The two different types of images are automatically exposed using the method described in the previous embodiment, overcoming the differences between the different types of images and achieving the purpose of accurate automatic exposure.

[0084] Those skilled in the art will understand that various aspects of the present invention can be implemented as systems, methods, or program products. Therefore, various aspects of the present invention can be specifically implemented in the following forms: a completely hardware implementation, a completely software implementation (including firmware, microcode, etc.), or a combination of hardware and software aspects, collectively referred to herein as a "circuit," "module," or "platform."

[0085] Figure 4 This is a schematic diagram of an automatic exposure device based on a non-homogeneous binocular camera according to an embodiment of the present invention. The following refers to... Figure 4 To describe an electronic device 600 according to this embodiment of the present invention. Figure 4The electronic device 600 shown is merely an example and should not impose any limitations on the functionality and scope of use of the embodiments of the present invention.

[0086] like Figure 4 As shown, the electronic device 600 is presented in the form of a general-purpose computing device. The components of the electronic device 600 may include, but are not limited to: at least one processing unit 610, at least one storage unit 620, a bus 630 connecting different platform components (including storage unit 620 and processing unit 610), a display unit 640, etc.

[0087] The storage unit stores program code, which can be executed by the processing unit 610 to perform the steps described in the section on automatic exposure methods based on non-homogeneous binocular cameras described in this specification, including the various exemplary embodiments of the invention. For example, the processing unit 610 can perform actions such as... Figure 1 The steps are shown in the figure.

[0088] Storage unit 620 may include a readable medium in the form of a volatile storage unit, such as random access memory (RAM) 6201 and / or cache memory 6202, and may further include a read-only memory (ROM) 6203.

[0089] Storage unit 620 may also include a program / utility 6204 having a set (at least one) program module 6205, such program module 6205 including but not limited to: operating system, one or more application programs, other program modules and program data, each or some combination of these examples may include an implementation of a network environment.

[0090] Bus 630 can represent one or more of several types of bus structures, including a memory cell bus or memory cell controller, a peripheral bus, a graphics acceleration port, a processing unit, or a local bus using any of the various bus structures.

[0091] Electronic device 600 can also communicate with one or more external devices 700 (e.g., keyboard, pointing device, Bluetooth device, etc.), and with one or more devices that enable a user to interact with electronic device 600, and / or with any device that enables electronic device 600 to communicate with one or more other computing devices (e.g., router, modem, etc.). This communication can be performed via input / output (I / O) interface 650. Furthermore, electronic device 600 can also communicate with one or more networks (e.g., local area network (LAN), wide area network (WAN), and / or public networks, such as the Internet) via network adapter 660. Network adapter 660 can communicate with other modules of electronic device 600 via bus 630. It should be understood that, although... Figure 4 As not shown in the diagram, other hardware and / or software modules may be used in conjunction with the electronic device 600, including but not limited to: microcode, device drivers, redundant processing units, external disk drive arrays, RAID systems, tape drives, and data backup storage platforms.

[0092] This invention also provides a computer-readable storage medium for storing a program that, when executed, implements the steps of an automatic exposure method based on a non-homogeneous binocular camera. In some possible implementations, various aspects of the invention can also be implemented as a program product comprising program code that, when run on a terminal device, causes the terminal device to perform the steps described in the above-described automatic exposure method based on a non-homogeneous binocular camera section of this specification, according to various exemplary embodiments of the invention.

[0093] As shown above, when the program of the computer-readable storage medium of this embodiment is executed, it acquires a first image and a second image by using the depth camera of a binocular system composed of a first camera and a second camera, and automatically exposes the two different types of images by means of the method in the foregoing embodiment, thereby overcoming the differences between the different types of images and achieving the purpose of stable and fast automatic exposure.

[0094] Figure 5 This is a schematic diagram of the structure of a computer-readable storage medium according to an embodiment of the present invention. (Reference) Figure 5 As shown, a program product 800 for implementing the above-described method according to an embodiment of the present invention is described. This product may employ a portable compact disc read-only memory (CD-ROM) and include program code, and may run on a terminal device, such as a personal computer. However, the program product of the present invention is not limited thereto. In this document, the readable storage medium may be any tangible medium containing or storing a program that may be used by or in conjunction with an instruction execution system, apparatus, or device.

[0095] The program product may employ any combination of one or more readable media. A readable medium may be a readable signal medium or a readable storage medium. A readable storage medium may be, for example, but not limited to, an electrical, magnetic, optical, electromagnetic, infrared, or semiconductor system, apparatus, or device, or any combination thereof. More specific examples (a non-exhaustive list) of readable storage media include: electrical connections having one or more wires, portable disks, hard disks, random access memory (RAM), read-only memory (ROM), erasable programmable read-only memory (EPROM or flash memory), optical fiber, portable compact disk read-only memory (CD-ROM), optical storage devices, magnetic storage devices, or any suitable combination thereof.

[0096] Computer-readable storage media may include data signals propagated in baseband or as part of a carrier wave, carrying 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 readable storage medium may also be any readable medium other than a readable storage medium that can transmit, propagate, or transfer a program for use by or in connection with an instruction execution system, apparatus, or device. The program code contained on the readable storage medium may be transmitted using any suitable medium, including but not limited to wireless, wired, optical fiber, RF, etc., or any suitable combination thereof.

[0097] Program code for performing the operations of this invention can be written in any combination of one or more programming languages, including object-oriented programming languages ​​such as Java and C++, and conventional procedural programming languages ​​such as C or similar languages. The program code can execute entirely on the user's computing device, partially on the user's computing device, as a standalone software package, partially on the user's computing device and partially on a remote computing device, or entirely on a remote computing device or server. In cases involving remote computing devices, the remote computing device can be connected to the user's computing device via any type of network, including a local area network (LAN) or a wide area network (WAN), or it can be connected to an external computing device (e.g., via the Internet using an Internet service provider).

[0098] In this embodiment of the invention, a first image and a second image are acquired by a depth camera of a binocular system consisting of a first camera and a second camera. The two different types of images are automatically exposed using the method described in the foregoing embodiment, overcoming the differences between the different types of images and achieving the purpose of stable and fast automatic exposure.

[0099] The various embodiments described in this specification are presented in a progressive manner, with each embodiment focusing on its differences from other embodiments. Similar or identical parts between embodiments can be referred to interchangeably. The above description of the disclosed embodiments enables those skilled in the art to make or use the invention. Various modifications to these embodiments will be readily apparent to those skilled in the art, and the general principles defined herein may be implemented in other embodiments without departing from the spirit or scope of the invention. Therefore, the invention is not to be limited to the embodiments shown herein, but is to be accorded the widest scope consistent with the principles and novel features disclosed herein.

[0100] The specific embodiments of the present invention have been described above. It should be understood that the present invention is not limited to the specific embodiments described above, and those skilled in the art can make various modifications or variations within the scope of the claims, which do not affect the essence of the present invention.

Claims

1. An automatic exposure method based on a non-isomorphic binocular camera, characterized in that, Includes the following steps: Step S1: Perform distortion correction on the original first image and the original second image respectively, and then perform epipolar correction to obtain the corrected first image. and the corrected second image The first image is a near-infrared image, and the second image is a color image. The epipolar correction is achieved by rotating the two cameras and redefining a new image plane, so that the epipolar pairs are collinear and parallel to a certain coordinate axis of the image plane, so that the same matching point pair is located in the same row of the two views, thereby establishing a pixel-level correspondence between the first image and the second image. Step S2: For the first image and the second image Detect the target object separately; if in the first image and the second image If the target object is detected in both images, then the first image is obtained respectively. target object area and the second image target object area Execute step S5; if only in the first image and the second image If a target object is detected in one of the images, then step S3 is executed; if no target object is detected, then step S4 is executed; wherein, the first image and the second image These are non-homologous images; Step S3: Determine the target object region on the image where the target object has been detected. And according to the first image and the second image The pixel-level correspondence is used to determine the target object region in the image where the target object was not detected. Then, based on the target object region in the image where no target object was detected... Adjust the exposure; Step S4: For the first image and the second image The brightness is evaluated. If the brightness is abnormal, the exposure gain needs to be reset. If the brightness is normal, no operation is performed. When evaluating the brightness, the first image and the second image are subtracted, and the resulting new image is used for brightness evaluation. Step S5: Calculate the target object region and the target object region Image quality; Step S6: Adjust the camera exposure.

2. The automatic exposure method based on a non-homogeneous binocular camera according to claim 1, characterized in that, Step S5 includes: Step S51: Calculate the target object region and the target object region Average brightness; Step S52: Calculate the target object region and the target object region Image clarity; Step S53: If the average brightness and the image sharpness are both within a reasonable range, then output the image; otherwise, proceed to step S6.

3. The automatic exposure method based on a non-homogeneous binocular camera according to claim 1, characterized in that, In step S4, the first image and the second image When evaluating brightness, only a preset range including the image center is evaluated.

4. The automatic exposure method based on a non-homogeneous binocular camera according to claim 1, characterized in that, In step S2, if a target object is detected, the area of ​​the target object is judged. If the area of ​​the target object is less than a threshold, it is judged that no target object has been detected.

5. The automatic exposure method based on a non-homogeneous binocular camera according to claim 1, characterized in that, Step S6 includes: Step S61: If the average brightness of the target area is too low, increase the exposure time, current value, or gain value; if the average brightness of the target area is too high, decrease the exposure time, current value, or gain value. Step S62: If the sharpness of the target object is low, increase the exposure time, increase the current value, or decrease the gain value.

6. The automatic exposure method based on a non-homogeneous binocular camera according to claim 5, characterized in that, In step S61: If the target object area and the target object region If the average brightness is too low, the order of adjustment is exposure time, gain value, and current value. If the target object area and the target object region If the average brightness is too high, the order of adjustment is current value, gain value, and exposure time.

7. The automatic exposure method based on a non-homogeneous binocular camera according to claim 1, characterized in that, Before performing any step of image processing, the first image is... and the second image Compress it.

8. An automatic exposure device based on a non-isomorphic binocular camera, characterized in that, include: processor; A memory module that stores executable instructions of the processor; The processor is configured to perform the steps of the automatic exposure method based on a non-homogeneous binocular camera as described in any one of claims 1 to 7 by executing the executable instructions.

9. A computer-readable storage medium for storing a program, characterized in that, When the program is executed, it implements the steps of the automatic exposure method based on a non-homogeneous binocular camera as described in any one of claims 1 to 7.

Images