An auto-exposure adjustment non-homologous binocular camera and payment device

Abstract

The application discloses a non-homologous binocular camera for automatically adjusting exposure, which comprises a first camera for shooting a first image of a target object, a second camera for shooting a second image of the target object, wherein the first camera and the second camera are non-homologous cameras, and the first camera and the second camera shoot at the same time; a processor for respectively correcting and aligning the first image and the second image, and respectively detecting the first image and the second image by using different target detection models to confirm a target object type and a target object area, and then adjusting exposure according to the target object area. ir The application adopts different target detection models to respectively detect target objects, automatically determines a target object type, and performs evaluation, and adjusts camera exposure according to image quality. rgb The application adopts different target detection models to respectively detect target objects, automatically determines a target object type, and performs evaluation, and adjusts camera exposure according to image quality.

Description

Technical Field

[0001] This invention relates to the field of depth cameras, specifically to a non-isomorphic binocular camera with automatic exposure adjustment and a payment device. 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.

[0004] In existing target recognition technologies, the target type usually needs to be determined in advance before target object recognition can be performed. For example, common payment devices require users to select the payment type before recognition, which results in many steps and a cumbersome process for users. Summary of the Invention

[0005] Therefore, the present invention addresses the first image I. ir Second image I rgb Different target detection models are used to detect target objects separately, automatically determine the type of target object, and evaluate it. The camera exposure is adjusted according to the image quality. Combining the characteristics of non-homogeneous binocular images, and utilizing the features of target objects, the target object type can be quickly identified and automatically exposed even when the specific target object type is not determined. This reduces the amount of image processing and greatly improves the accuracy of automatic exposure.

[0006] In a first aspect, the present invention provides a non-isomorphic binocular camera with automatic exposure adjustment, characterized in that it comprises the following modules:

[0007] The first camera is used to capture the first image of the target object;

[0008] The second camera is used to capture a second image of the target object; wherein the first camera and the second camera are not from the same source, and the first camera and the second camera capture images simultaneously;

[0009] The processor is used to correct and align the first image and the second image respectively, and to perform detection on the first image and the second image respectively using different target detection models to confirm the target object type and target object region, and then adjust the exposure according to the target object region.

[0010] Optionally, the non-isomorphic binocular camera with automatic exposure adjustment is characterized in that the processor includes:

[0011] The correction module is used to 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 ;

[0012] The detection module is used to detect the first image I. ir and the second image I rgb Different target detection models are used to detect target objects respectively; if a first target object and a second target object are detected in the first image and the second image respectively, the first target object region and the second target object region are obtained respectively, and then the comparison module is executed; 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, the fourth target object module is executed; if no target object is detected, the brightness evaluation module is executed; wherein, the first image and the second image are non-homogeneous images;

[0013] The comparison module is used to compare the areas of the first target object region and the second target object region, mark the one with the larger area as the third target object region, and execute the fourth target object module;

[0014] The fourth target object module is used to determine the third target object region on the image where the target object has been detected, and based on the first image I ir and the second image I rgb The correspondence is used to determine the fourth target object region on the image where no target object was detected;

[0015] The brightness evaluation module is used to evaluate the brightness of the first image I. ir and the second image I rgb The brightness is assessed; if the brightness is abnormal, the exposure gain needs to be reset; if the brightness is normal, no action is taken.

[0016] The image quality module is used to calculate the image quality of the third target object region and the fourth target object region;

[0017] An exposure adjustment module is used to adjust the camera exposure based on the image quality of the third target object region and the fourth target object region.

[0018] Optionally, the aforementioned non-isomorphic binocular camera with automatic exposure adjustment is characterized in that the image quality module includes:

[0019] A brightness calculation unit is used to calculate the average brightness of the third target object region and the fourth target object region;

[0020] A sharpness calculation unit is used to calculate the image sharpness of the third target object region and the fourth target object region;

[0021] The output unit is configured to output an image if both the average brightness and the image sharpness are within a reasonable range; otherwise, it executes the exposure adjustment module.

[0022] Optionally, the non-isomorphic binocular camera with automatic exposure adjustment is characterized in that, in the brightness evaluation module, the first image I... ir and the second image I rgb When evaluating brightness, only a preset range including the image center is evaluated.

[0023] Optionally, the non-same-source binocular camera with automatic exposure adjustment is characterized in that, in the detection module, 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.

[0024] Optionally, the non-isomorphic binocular camera with automatic exposure adjustment is characterized in that, in the brightness evaluation module, 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.

[0025] Optionally, the aforementioned non-isomorphic binocular camera with automatic exposure adjustment is characterized in that the exposure adjustment module includes:

[0026] The brightness adjustment unit is used to increase the exposure time, current value, or gain value if the average brightness of the third target object area and the fourth target object area is too low; and to decrease the exposure time, current value, or gain value if the average brightness of the third target object area and the fourth target object area is too high.

[0027] The sharpness adjustment unit is used to increase the exposure time, increase the current value, or decrease the gain value if the sharpness of the target object is too low.

[0028] Optionally, the aforementioned non-isomorphic binocular camera with automatic exposure adjustment is characterized in that, in the brightness adjustment unit:

[0029] If the average brightness of the third target object area and the fourth target object area is too low, the order of adjustment is exposure time, gain value, and current value.

[0030] If the average brightness of the third target area and the fourth target area is too high, the order of adjustment is current value, gain value, and exposure time.

[0031] Optionally, the aforementioned non-homogeneous binocular camera with automatic exposure adjustment is characterized in that, in the detection module, multiple different target detection models are employed respectively, in the first image I ir and the second image I rgb The tests are performed sequentially without repetition.

[0032] In a second aspect, the present invention provides a payment device, characterized in that it includes a non-isomorphic binocular camera with automatic exposure adjustment as described in any of the preceding claims.

[0033] Compared with the prior art, the present invention has the following beneficial effects:

[0034] 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.

[0035] 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.

[0036] 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.

[0037] 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.

[0038] This invention uses different target detection models to detect the first image and the second image respectively, which can quickly detect the type of target object. It achieves the goal of quickly identifying the target object without pre-specifying the target type, simplifies the steps, and greatly reduces the time required for users to operate. Attached Figure Description

[0039] 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:

[0040] Figure 1 This is a schematic diagram of the structure of a non-isomorphic binocular camera with automatic exposure adjustment according to an embodiment of the present invention;

[0041] Figure 2 This is a schematic diagram of the structure of a processor according to an embodiment of the present invention;

[0042] Figure 3 This is a schematic diagram of the structure of an image quality module according to an embodiment of the present invention;

[0043] Figure 4 This is a schematic diagram of the structure of an exposure adjustment module in an embodiment of the present invention;

[0044] Figure 5 This is a schematic diagram of the structure of a payment device according to an embodiment of the present invention. Detailed Implementation

[0045] 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 various modifications and improvements without departing from the concept of the present invention. These all fall within the scope of protection of the present invention.

[0046] 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.

[0047] 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.

[0048] The present invention provides a non-isomorphic binocular camera with automatic exposure adjustment, which aims to solve the problems existing in the prior art.

[0049] 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.

[0050] Figure 1 This is a schematic diagram of the structure of a non-isomorphic binocular camera with automatic exposure adjustment according to an embodiment of the present invention. Figure 1 As shown, an embodiment of the present invention provides a non-isomorphic binocular camera with automatic exposure adjustment, comprising:

[0051] The first camera 100 is used to capture the first image of the target object;

[0052] The second camera 200 is used to capture a second image of the target object; wherein the first camera and the second camera are non-co-located cameras, and the first camera and the second camera capture images simultaneously;

[0053] The processor 300 is used to correct and align the first image and the second image respectively, and to perform detection on the first image and the second image respectively using different target detection models to confirm the target object type and target object area, and then adjust the exposure according to the target object area.

[0054] Specifically, a non-similar binocular camera refers to a binocular system composed of two cameras using different technical principles. It can simultaneously acquire two types of images and obtain depth data using the parallax principle. 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. In this embodiment, the first camera and the second camera constitute a non-similar binocular system. The acquired first and second images are non-similar images, such as a color image and an infrared image.

[0055] The processor processes the first and second images simultaneously. First, it aligns and corrects the first and second images, then it uses different object detection models to perform detection separately. In this embodiment, the object detection models detect different types of objects, such as two of the following: face, hand, and human pose. Since the first and second images are not from the same source and different detection models are used, the detection results on the first and second images will result in three scenarios: both images detect the target object, only one image detects the target object, and neither image detects the target object. The final target object is determined from the image where two target objects are detected. Then, the image quality is evaluated, and the exposure is adjusted based on this target object region, enabling rapid exposure adjustment.

[0056] Figure 2 This is a schematic diagram of the structure of a processor according to an embodiment of the present invention. Figure 2 As shown in the embodiments of the present invention Figure 2 The schematic diagram of a processor in an embodiment of the present invention includes the following modules.

[0057] The correction module 310 is used to 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 .

[0058] Specifically, the original first image and the original second image are non-originating 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 binocular systems. 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 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 module corrects both types of 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.

[0059] Detection module 320 is used to detect the first image I ir and the second image I rgb Different target detection models are used to detect target objects.

[0060] Specifically, the target objects detected in the first image and the second image are different objects, such as simultaneously recognizing two of the following: a human body, a face, a hand, and a QR code. The target objects detected in the first image and the second image can be set according to specific circumstances. If a first target object and a second target object are detected in the first image and the second image respectively, and a first target object region and a second target object region are obtained respectively, then the comparison module is executed; if only in the first image... ir and the second image I rgb If a target object is detected in one of the images, the fourth target object module is executed; if no target object is detected, the brightness evaluation module is executed; wherein, the first image and the second image are non-homogeneous images.

[0061] In some embodiments, multiple different target detection models are used in the first image I. ir and the second image I rgbThe detection is performed sequentially without repetition. For example, the first image is detected using a human detection model and a face detection model in sequence, while the second image is detected using a palm detection model and a QR code detection model in sequence. Let "first detection model" represent the multiple object detection models used for the first image, and "second detection model" represent the multiple object detection models used for the second image. No two object detection models are the same.

[0062] If multiple objects of the same type are detected in the same image, the one with the largest area in the image is selected as the target object. For example, if there are multiple hands in the first image and multiple faces in the second image, the largest hand in the first image is selected as the target object; similarly, the largest face in the second image is selected as the target object.

[0063] 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.

[0064] The comparison module 330 is used to compare the areas of the first target object region and the second target object region, and mark the one with the larger area as the third target object region.

[0065] Specifically, if two or more target objects of different types are detected on the same image, the target object with the largest area on the image is selected as the final target object. When comparing the areas of different types of target objects on the image, the single target object with the largest area within the same type is used. For example, if the first image contains multiple palms and the second image contains multiple faces, the first image compares the multiple palms to obtain the largest palm, the second image compares the multiple faces to obtain the largest face, and then compares the areas of the largest palm and the largest face to determine the final target object, thus obtaining the third target object region. After this module completes, the fourth target object module is executed.

[0066] The fourth target object module 340 is used to determine a third target object region on the image where the target object has been detected, and based on the first image I ir and the second image I rgb The correspondence is used to determine the fourth target object region on the image where no target object was detected.

[0067] Specifically, since only one target object is detected in the first and second images, this embodiment does not use the same model to detect the target object in the other image in order to quickly obtain the target object in the other image. Instead, it utilizes the alignment between the first and second images to quickly obtain the target object region in the other image, i.e., the fourth target object region. Taking the detection of a target object in the first image as an example, the target object region in the first image is the third target object region. Since the first and second images are aligned, the corresponding fourth target object region in the second image can be obtained based on the third target object region in the first image. Because the brightness of the target object in the fourth target object region has not been detected, it cannot be used directly; further evaluation of the third and fourth target object regions is required. After this module completes, the image quality module is executed.

[0068] Brightness evaluation module 350 is used to evaluate the brightness of the first image I. ir and the second image I rgb The brightness is assessed. If the brightness is abnormal, the exposure gain needs to be reset; if the brightness is normal, no action is taken.

[0069] Specifically, the brightness of the first and second images is evaluated to address situations where no image can be detected in either image. This module 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 be effectively identified, in which case no action is taken, and the current state is maintained.

[0070] 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.

[0071] In some embodiments, the first image I ir and the second image I rgb When 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, then the average brightness value 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.

[0072] 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.

[0073] Image quality module 360 ​​is used to calculate the image quality of the third target object region and the fourth target object region.

[0074] Specifically, considering that in this embodiment, only one of the first and second images obtained target object data, and whether the other image could obtain target object data is unverified, and that the obtained target object data may still have problems such as blurriness leading to issues in subsequent depth processing, it is necessary to evaluate the image quality. This module only evaluates the image quality of the target object region to reduce the amount of data processing, improve the targeting of subsequent modules, and obtain higher quality images. This module evaluates the third and fourth target object regions separately.

[0075] The exposure adjustment module 370 is used to adjust the camera exposure based on the image quality of the third target object region and the fourth target object region.

[0076] Specifically, according to the first image I ir Target Object Region ROI ir Image quality and the second image I rgb Target Object Region ROI rgb The 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.

[0077] Before performing image processing in any module, the first image I is... irand the second image I rgb Compress it.

[0078] This embodiment uses different target detection models to detect non-homogeneous images, and then judges the final target object type and target object region based on the number and area of ​​the target object. Thus, the exposure can be automatically adjusted according to the characteristics of the target object region, so that the target object type can be automatically identified and the exposure can be automatically adjusted without pre-inputting the target object type, which greatly reduces the user's information input time and improves efficiency.

[0079] Figure 3 This is a schematic diagram of the structure of an image quality module according to an embodiment of the present invention. Figure 3 As shown, unlike the previous embodiments, an image quality module in this embodiment of the invention is as follows.

[0080] The brightness calculation unit 361 is used to calculate the average brightness of the third target object region and the fourth target object region.

[0081] Specifically, the average brightness of the target object region is calculated. When calculating the average brightness, values ​​can be taken from all pixels in both the third and fourth target object regions, or a sampling method can be used to take values ​​from only a subset of pixels in both regions. Alternatively, the average brightness can be calculated separately for each of the third and fourth target object regions to obtain their respective average brightness.

[0082] The sharpness calculation unit 362 is used to calculate the image sharpness of the third target object region and the fourth target object region.

[0083] Specifically, image sharpness is represented using the mean gradient. 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.

[0084] The output unit 363 is used to output an image if both the average brightness and the image sharpness are within a reasonable range; otherwise, it executes the exposure adjustment module.

[0085] Specifically, the average brightness and image sharpness are judged. If the values ​​of the target object area in both the first and second images are within a reasonable range, the image is output; otherwise, it is judged as an exposure abnormality and needs to be adjusted, and the exposure adjustment module is executed.

[0086] 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.

[0087] Figure 4 This is a schematic diagram of the structure of an exposure adjustment module according to an embodiment of the present invention. Figure 4 As shown, unlike the previous embodiments, an exposure adjustment module in this embodiment of the invention includes the following units.

[0088] The brightness adjustment unit 371 is used to increase the exposure time, current value, or gain value if the average brightness of the third target object area and the fourth target object area is too low; and to decrease the exposure time, current value, or gain value if the average brightness of the third target object area and the fourth target object area is too high.

[0089] Specifically, if the average brightness of the third and fourth target areas is too low, the adjustment order is exposure time, gain value, and current value. If the average brightness of the third and fourth target areas is too high, the adjustment order is current value, gain value, and exposure time. The different adjustment order for low and high average brightness ensures both adjustment sensitivity and device stability.

[0090] 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.

[0091] The sharpness adjustment unit 372 is used to increase the exposure time, increase the current value, or decrease the gain value if the sharpness of the target object is too low.

[0092] Specifically, the adjustment method is the same as that in the brightness adjustment unit 371, and will not be described again here.

[0093] 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.

[0094] Figure 5 This is a schematic diagram of the structure of a payment device according to an embodiment of the present invention. Figure 5 As shown, in an embodiment of the present invention, a payment device includes a main body 700, a display area 710, a thermal printer 720, a non-isomorphic binocular camera 730 with automatic exposure adjustment, and a scanning area 740.

[0095] The main body 700 is used to fix the components of the device and integrate functions; it serves as a bracket for the payment device. The main body 700 can be configured in different sizes and shapes to suit different application scenarios and needs.

[0096] Display area 710 is used for user interaction. When a user makes a payment using facial recognition or palm recognition, it provides the camera's view so the user can adjust their position and posture for better recognition. Display area 710 can also assist with password input and verification. In standby mode, display area 710 typically displays advertisements, such as promotional videos for shopping malls or stores, featured products, or other advertisements retrieved from the internet.

[0097] The thermal printer 720 is used for printing receipts. In this embodiment, the thermal printer uses a fixed printhead with a heated dot matrix. The printhead has 320 square dots, each 0.25mm × 0.25mm. Using this dot matrix, the printer can place the print dots at any position on the thermal paper. The printing paper can be blank or pre-printed. When using blank paper, the thermal printer prints the entire receipt content one by one, suitable for scenarios requiring detailed printing. When using pre-printed paper, it is suitable for situations with a defined scenario; only the blank areas on the pre-printed paper need to be filled, improving the thermal printer's ticket printing efficiency.

[0098] The auto-adjusting exposure non-similar binocular camera 730 is any of the auto-adjusting exposure non-similar binocular cameras described in the foregoing embodiments. The auto-adjusting exposure non-similar binocular camera 730 includes a first camera 731 and a second camera 732. The auto-adjusting exposure non-similar binocular camera 730 also includes a processor, which can be housed within the auto-adjusting exposure non-similar binocular camera 730 or shared with the payment device. However, to improve data processing capabilities, preferably, the processor is housed separately within the auto-adjusting exposure non-similar binocular camera 730.

[0099] The scanning area 740 is used to scan QR codes. The scanning area 740 is typically used to scan product barcodes and obtain the product's price and quantity, which are then displayed in the display area 710 for user confirmation of the settlement amount. Once the settlement amount is confirmed, the user can either use the automatically adjustable exposure non-isomorphic binocular camera 730 for facial recognition or palm scanning payment, or use the scanning area 740 for QR code payment.

[0100] This embodiment provides a payment device that is user-friendly, offers multiple payment methods, and employs non-homogeneous binocular technology, naturally possessing liveness detection capabilities. It can obtain more information in a shorter time, processing and verifying biometric payments from multiple dimensions, thereby improving the security and convenience of payments.

[0101] 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.

[0102] 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. A non-isomorphic binocular camera with automatic exposure adjustment, characterized in that, include: The first camera is used to capture the first image of the target object; The second camera is used to capture a second image of the target object; wherein the first camera and the second camera are not from the same source, and the first camera and the second camera capture images simultaneously; The processor is used to correct and align the first image and the second image respectively, and to use different target detection models to detect the first image and the second image respectively, to confirm the target object type and target object area, and then to adjust the exposure according to the target object area; The processor includes: The correction module is used to 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 detection module is used to detect the first image. and the second image Different target detection models are used to detect target objects separately; if a first target object and a second target object are detected in the first image and the second image respectively, the first target object region and the second target object region are obtained respectively, and then the comparison module is executed; if only in the first image... and the second image If a target object is detected in one of the images, the fourth target object module is executed; if no target object is detected, the brightness evaluation module is executed; wherein, the first image and the second image These are non-homologous images; The comparison module is used to compare the areas of the first target object region and the second target object region, mark the one with the larger area as the third target object region, and execute the fourth target object module; The fourth target object module is used to, when a first target object and a second target object are detected on the first image and the second image respectively, determine the target object based on the first image. and the second image Based on the correspondence, a fourth target object region is determined on the image where the target object with the larger area was not detected; if only in the first image and the second image When a target object is detected in one of the images, a third target object region is determined in the image where the target object was detected, and based on the first image... and the second image The correspondence is used to determine the fourth target object region on the image where no target object was detected; A brightness evaluation module is used to evaluate the brightness of the first image. and the second image The brightness is assessed; if the brightness is abnormal, the exposure gain needs to be reset; if the brightness is normal, no action is taken. The image quality module is used to calculate the image quality of the third target object region and the fourth target object region; An exposure adjustment module is used to adjust the camera exposure based on the image quality of the third target object region and the fourth target object region.

2. The non-isomorphic binocular camera with automatic exposure adjustment according to claim 1, characterized in that, The image quality module includes: A brightness calculation unit is used to calculate the average brightness of the third target object region and the fourth target object region; A sharpness calculation unit is used to calculate the image sharpness of the third target object region and the fourth target object region; The output unit is configured to output an image if both the average brightness and the image sharpness are within a reasonable range; otherwise, it executes the exposure adjustment module.

3. A non-isomorphic binocular camera with automatic exposure adjustment according to claim 1, characterized in that, In the brightness evaluation module, the first image and the second image When evaluating brightness, only a preset range including the image center is evaluated.

4. A non-isomorphic binocular camera with automatic exposure adjustment according to claim 1, characterized in that, In the detection module, 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. A non-isomorphic binocular camera with automatic exposure adjustment according to claim 1, characterized in that, In the brightness evaluation module, the first image and the second image When evaluating brightness, the first image is used. and the second image Subtract the two images and use the resulting new image for evaluation.

6. A non-isomorphic binocular camera with automatic exposure adjustment according to claim 1, characterized in that, The exposure adjustment module includes: The brightness adjustment unit is used to increase the exposure time, current value, or gain value if the average brightness of the third target object area and the fourth target object area is too low; and to decrease the exposure time, current value, or gain value if the average brightness of the third target object area and the fourth target object area is too high. The sharpness adjustment unit is used to increase the exposure time, increase the current value, or decrease the gain value if the sharpness of the target object is too low.

7. A non-isomorphic binocular camera with automatic exposure adjustment according to claim 6, characterized in that, In the brightness adjustment unit: If the average brightness of the third target object area and the fourth target object area is too low, the order of adjustment is exposure time, gain value, and current value. If the average brightness of the third target area and the fourth target area is too high, the order of adjustment is current value, gain value, and exposure time.

8. A non-isomorphic binocular camera with automatic exposure adjustment according to claim 1, characterized in that, In the detection module, multiple different target detection models are used in the first image. and the second image The tests are performed sequentially without repetition.

9. A payment device, characterized in that, Including a non-homogeneous binocular camera with automatic exposure adjustment as described in any one of claims 1 to 8.

Images