An image quality control method, device, medium and equipment of a multi-view camera

Abstract

The application discloses a kind of multi-view camera's image quality control method, device, medium and equipment.The method comprises: according to the detected moving object, at least multi-view camera is divided into first type camera and second type camera;Image quality of first type camera collected containing first type moving object is compared with first quality threshold;And, image quality of second type camera collected containing second type moving object is compared with second quality threshold;If there is the result of comparison does not comply with preset standard, then it is not adjusted according to the image quality adjustment rule corresponding to the type of moving object to the camera that does not comply with preset standard;If it is detected to comply with preset standard after adjustment, the image collected by first type camera and second type camera is spliced, and integrated image is obtained.The technical scheme can realize different processing mode for different moving object in picture, increase multi-view camera mixed line applicability.

Description

Technical Field

[0001] This application relates to the field of Internet technology, and in particular to an image quality control method, apparatus, medium and device for multi-view cameras. Background Technology

[0002] With societal development, video surveillance has become an indispensable part of life, playing a significant role in all aspects of society. Currently, although there are many optimization methods for monocular cameras in low-light mixed-scene scenarios, these methods are all based on adjusting parameters globally and then performing post-processing to ensure the mixed-scene effect. The optimized mixed-scene effect cannot reach the optimal level, and the latency is large. The optimization methods are not flexible enough and cannot adjust parameters separately for different monitored subjects, thus failing to achieve the goal of using different processing methods for different monitored subjects in the scene. Summary of the Invention

[0003] This application provides an image quality control method, apparatus, medium, and device for a multi-view camera. It can intelligently adjust parameters to optimize the effect based on the image quality of moving objects in different channels of the multi-view camera, thereby enabling different processing methods to be used for different moving objects in the picture and increasing the applicability of the multi-view camera in mixed scenes.

[0004] In a first aspect, embodiments of this application provide an image quality control method for a multi-view camera, the method comprising:

[0005] Based on the detected moving objects, multi-view cameras are divided into at least two categories: Category I cameras and Category II cameras.

[0006] The image quality of the first type of moving object captured by the first type of camera is compared with a first quality threshold; and the image quality of the second type of moving object captured by the second type of camera is compared with a second quality threshold.

[0007] If any comparison result does not meet the preset standard, the camera that does not meet the preset standard will be adjusted according to the image quality adjustment rules corresponding to the type of moving object;

[0008] If the adjustment is found to meet the preset standard, the images captured by the first type of camera and the second type of camera are stitched together to obtain an integrated image.

[0009] Optionally, the first type of moving object is a pedestrian, and the second type of moving object is a vehicle;

[0010] If any comparison result does not meet the preset standard, then the cameras that do not meet the preset standard will be adjusted according to the image quality adjustment rules corresponding to the type of moving object, including:

[0011] If the quality of the pedestrian images captured by the first type of camera does not meet the first quality threshold, the image quality of the first type of camera is adjusted based on the gain value of the pedestrian images.

[0012] or,

[0013] If the quality of the vehicle image captured by the second type of camera does not meet the second quality threshold, the image quality of the second type of camera is adjusted based on the vehicle image brightness information.

[0014] Optionally, the image quality of the first type of camera is adjusted based on the gain value of the pedestrian image, including:

[0015] Obtain the current gain value of the pedestrian image;

[0016] If the current gain value is greater than the preset gain value, then the supplementary lighting device of the first type of camera is turned on;

[0017] The pedestrian images are re-acquired through the first type of camera, and it is determined whether the quality of the pedestrian images meets the first quality threshold.

[0018] If the conditions are met, the output will be based on the pedestrian image after the supplementary lighting device is turned on;

[0019] If the condition is not met, the ISP image parameters of the first type of camera are adjusted until the pedestrian images re-acquired by the first type of camera meet the first quality threshold.

[0020] Optionally, the pedestrian image quality includes face image quality and body image quality;

[0021] The quality of the face image is determined based on at least one of the brightness, sharpness, and noise of the face in the pedestrian image;

[0022] The quality of the human body image is determined based on at least one of the brightness, sharpness, and noise of the human body in the pedestrian image.

[0023] Optionally, the image quality of the second type of camera is adjusted based on vehicle image brightness information, including:

[0024] Obtain the highest brightness value of bright blocks in the vehicle image;

[0025] If the highest brightness value exceeds the preset brightness value, then the brightness value of the bright block is suppressed so that the brightness value of the bright block is lower than the preset brightness value.

[0026] Adjust the ISP image parameters of the second type of camera until the vehicle images re-acquired by the second type of camera meet the second quality threshold.

[0027] Optionally, the vehicle image quality includes vehicle body image quality and license plate image quality;

[0028] The quality of the vehicle image is determined based on at least one of the brightness, sharpness, and noise of the vehicle in the image.

[0029] The quality of the license plate image is determined based on at least one of the following: the brightness, sharpness, and noise of the license plate in the image.

[0030] Optionally, the second type of camera has at least one channel;

[0031] Virtualize at least one of the second-type cameras to obtain virtual route images for each of the second-type cameras;

[0032] Accordingly, the brightness value of the bright blocks is suppressed based on the virtual route image, so that the brightness value of the bright blocks is lower than the preset brightness value; and the ISP image parameters of the second type of camera are adjusted until the vehicle image re-acquired by the second type of camera meets the second quality threshold, so as to obtain a vehicle image that meets the second quality threshold.

[0033] Vehicle headlight and license plate images are cropped from the virtual route image and fused with the real route image from the second type of camera.

[0034] Secondly, embodiments of this application provide an image quality control device for a multi-view camera, the device comprising:

[0035] The camera classification module is used to classify multi-camera systems into at least a first category and a second category based on detected moving objects.

[0036] The image quality comparison module is used to compare the image quality of the image containing the first type of moving object captured by the first type of camera with a first quality threshold; and to compare the image quality of the image containing the second type of moving object captured by the second type of camera with a second quality threshold.

[0037] The image adjustment module is used to adjust the camera that does not meet the preset standard according to the image quality adjustment rules corresponding to the type of moving object if the comparison result does not meet the preset standard.

[0038] The image acquisition module is used to stitch together the images captured by the first type of camera and the second type of camera to obtain an integrated image if the image is detected to be adjusted to meet a preset standard.

[0039] Thirdly, embodiments of this application provide a computer-readable storage medium having a computer program stored thereon, which, when executed by a processor, implements the image quality control method for a multi-view camera as described in embodiments of this application.

[0040] Fourthly, embodiments of this application provide an electronic 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 image quality control method for a multi-view camera as described in embodiments of this application.

[0041] The technical solution provided in this application categorizes multi-camera systems into at least a first type of camera and a second type of camera based on detected moving objects. It compares the image quality of images containing the first type of moving object captured by the first type of camera with a first quality threshold, and compares the image quality of images containing the second type of moving object captured by the second type of camera with a second quality threshold. If any comparison result does not meet a preset standard, the camera that does not meet the preset standard is adjusted according to an image quality adjustment rule corresponding to the type of moving object. If the adjustment is detected to meet the preset standard, the images captured by the first type of camera and the second type of camera are stitched together to obtain an integrated image. This technical solution can intelligently adjust parameters to optimize the effect based on the image quality of moving objects in different channels of the multi-camera system, enabling different processing methods to be used for different moving objects in the image, thus increasing the applicability of multi-camera systems in mixed-scene scenarios. Attached Figure Description

[0042] Figure 1 This is a flowchart of the image quality control method for a multi-view camera provided in Embodiment 1 of this application;

[0043] Figure 2 This is a flowchart of the image quality control method for a multi-view camera provided in Embodiment 2 of the present invention;

[0044] Figure 3 This is a structural block diagram of an image quality control device for a multi-view camera provided in Embodiment 3 of the present invention;

[0045] Figure 4 This is a schematic diagram of the structure of an electronic device provided in Embodiment 5 of this application. Detailed Implementation

[0046] The present application will now be described in further detail with reference to the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are merely illustrative of the application and not intended to limit it. Furthermore, it should be noted that, for ease of description, the accompanying drawings show only the parts relevant to the present application, not the entire structure.

[0047] Before discussing the exemplary embodiments in more detail, it should be noted that some exemplary embodiments are described as processes or methods depicted as flowcharts. Although the flowcharts describe the steps as sequential processes, many of these steps can be performed in parallel, concurrently, or simultaneously. Furthermore, the order of the steps can be rearranged. The process can be terminated when its operation is complete, but may also have additional steps not included in the figures. The process can correspond to a method, function, procedure, subroutine, subroutine, etc.

[0048] Example 1

[0049] Figure 1 This is a flowchart of an image quality control method for a multi-view camera provided in Embodiment 1 of this application. This embodiment is applicable to scenarios where moving objects are detected. The method can be executed by the image quality control device for the multi-view camera provided in this embodiment. The device can be implemented in software and / or hardware and can be integrated into an electronic device.

[0050] like Figure 1 As shown, the image quality control method for the multi-view camera includes:

[0051] S110, based on the detected moving objects, the multi-camera system is divided into at least a first-class camera and a second-class camera.

[0052] This solution can be implemented by multi-view cameras to monitor mixed traffic scenarios on roads. The main monitoring subject is moving objects. Multi-view cameras can process images in different channels according to the different moving objects. They can also process images based on whether the image quality of the moving objects meets the standards. When the standards are not met, the image quality parameters can be adjusted according to the different types of moving objects, thereby increasing the applicability of multi-view cameras in mixed traffic scenarios.

[0053] The moving object can be a pedestrian or a vehicle. In this embodiment, the multi-camera system is divided into at least a first type of camera and a second type of camera based on the moving object. When the moving object in the current frame monitored by the multi-camera system is a pedestrian, the camera monitoring the pedestrian is designated as the first type of camera; when the moving object in the current frame monitored by the multi-camera system is a vehicle, the camera monitoring the vehicle is designated as the second type of camera. For example, if there are currently n cameras detecting vehicles, with m cameras used to detect pedestrians (as the first type of camera) and nm cameras used to detect vehicles (as the second type of camera), then nm cameras are used to detect vehicles.

[0054] In this embodiment, the monitoring subject in the current mixed scene may be multiple objects. The multi-view camera needs to confirm whether there are moving objects in the picture. The multi-view camera's intelligent recognition function determines whether there are moving objects in the current picture. If there are no moving objects, the picture is not processed and the multi-view merging processing mode is in effect. If moving objects are detected in the picture, the multi-view camera detects the moving objects and classifies them into at least a first-class camera and a second-class camera based on their different categories. The multi-view camera can determine which type of camera the moving object belongs to and perform channel processing accordingly. If no moving objects are detected in the picture within a preset time, it will automatically switch to the multi-view merging processing mode. That is, the images from each channel of the multi-view camera are first stitched together and then the entire image is processed by ISP, which ensures the overall effect of the entire multi-view image. The preset time can be 2 seconds or 5 seconds, etc.

[0055] S120, compare the image quality of the image containing the first type of moving object captured by the first type of camera with a first quality threshold; and compare the image quality of the image containing the second type of moving object captured by the second type of camera with a second quality threshold.

[0056] The first type of moving object can be a pedestrian. The image quality of the first type of moving object can be the same as the image quality of a pedestrian, and can be represented using R... 行人 The image quality R of pedestrians is indicated. 行人 It can be determined by face quality R 人脸 and human body mass R 人体 The composition includes the quality of faces and bodies, which can include brightness, sharpness, and noise quality, and each quality factor is weighted. The first quality threshold can be represented by RT, which can be a pre-set threshold or set according to actual needs. The second type of moving object can be a vehicle. The image quality of the second type of moving object can be the image quality of a vehicle, which can be represented by W. 车 The image quality of the vehicle (W) is indicated. 车 It can be determined by the vehicle's mass W 车身 And license plate quality W 车牌 The composition includes factors such as brightness, clarity, and noise quality of the vehicle body and license plate, and weights can be assigned to each of these factors. The second quality threshold can be represented by W. T This can be a pre-set threshold, or it can be set according to actual needs. In this embodiment, the image quality is compared with the corresponding quality threshold for judgment.

[0057] For example, in this embodiment, the N-camera device automatically segments the monitored subjects in the image based on the characteristics of road monitoring. The middle M-channel is used to monitor vehicles and capture license plates, while the surrounding NM-channels are used to monitor non-motorized vehicles and pedestrians. There is also an additional M-channel, a virtual channel in the middle, used to suppress vehicle lights at night. The total bitrate is N+M channels. The multi-camera intelligently detects which channel contains a moving object in the current live feed and then processes each channel separately. If the live feed is in the middle M-channel, it means the moving object is in the motorized vehicle lane, so the monitoring is performed on the motorized vehicle lane, and the monitored subjects are moving vehicles and license plates. Otherwise, it means the moving object is in the non-motorized vehicle lane, so the monitoring is performed on the non-motorized vehicle and pedestrian lane, and the monitored subjects are pedestrians.

[0058] For example, when the moving object is a pedestrian, the pedestrian image quality value R 行人 It satisfies the following relationship:

[0059] R 行人 =k1R 人脸 +k2R 人体 ;

[0060] Here, k1 and k2 are weight values, and they must satisfy k1 + k2 = 1.

[0061] R 人脸 / 人体 =ρ1·L 人脸 / 人体 +ρ2·B 人脸 / 人体 +ρ3·S 人脸 / 人体 ;

[0062] Among them, L 人脸 / 人体 B 人脸 / 人体 Sface / Sbody represents the brightness, sharpness, and noise of the face / body, respectively. ρ1, ρ2, and ρ3 are weight values, and they must satisfy ρ1 + ρ2 + ρ3 = 1.

[0063] For example, when the moving object is a vehicle, the vehicle image quality value W 车 It satisfies the following relationship:

[0064] W 车 =k3W 车身 +k4W 车牌 ;

[0065] Here, k3 and k4 are weight values, and they must satisfy k3 + k4 = 1.

[0066] W 车身 / 车牌 =ε1·L 车身 / 车牌 +ε2·B 车身 / 车牌 +ε3·S 车身 / 车牌 ;

[0067] Among them, ε1, ε2, and ε3 are weight values, and they need to satisfy ε1+ε2+ε3=1.

[0068] Furthermore, the quality of a moving object can be evaluated in other ways; the above function model is for reference only.

[0069] In this embodiment, the multi-view camera can measure the image quality R of pedestrians captured by the first type of camera. 行人 With the first quality threshold R T Compare them. If the comparison result is R... 行人 ≥R T If the pedestrian image quality meets the quality threshold, that is, meets the preset standard, then the multi-view camera does not perform any processing, the multi-view merging parameter remains effective, and the current image can be directly output; if the comparison result R 行人 <R T This indicates that the pedestrian image quality does not meet the quality threshold, that is, it does not meet the preset standard. Additionally, the multi-view camera assesses the vehicle image quality W acquired by the second type of camera. 车 With the second quality threshold W T Compare them. If the comparison result is W... 车 ≥W T If the image quality meets the quality threshold, i.e., the preset standard, then the multi-view camera does not perform any processing and the multi-view merging parameter remains in effect; if the comparison result W... 车 <W T If the image quality does not meet the quality threshold, it means that the image does not meet the preset standard.

[0070] S130, if any comparison result does not meet the preset standard, then the camera that does not meet the preset standard shall be adjusted according to the image quality adjustment rule corresponding to the type of moving object.

[0071] The preset standard can be pre-set. In this embodiment, the preset standard can be R. 行人 ≥R T And W 车 ≥W T The types of moving objects include pedestrians and vehicles. The image quality adjustment rules can be set separately for pedestrians or vehicles. In this embodiment, the multi-camera system sets a quality threshold, using image quality greater than or equal to the threshold as a preset standard. When a camera's comparison result does not meet the preset standard, the image quality is adjusted according to the image quality adjustment rules corresponding to the category of that moving object. For example, when the first moving object is a pedestrian, its comparison result is R. 行人 <R T If the comparison result does not meet the preset standard, then the first type of camera will be adjusted according to the image quality adjustment rules corresponding to pedestrians.

[0072] S140, if the adjustment is detected to meet the preset standard, the images captured by the first type of camera and the second type of camera are stitched together to obtain an integrated image.

[0073] The integrated image can be obtained by stitching together images captured by a multi-view camera from a first-type camera and a second-type camera. In this embodiment, when the multi-view camera detects that the image quality has been adjusted to meet a preset standard, it stitches together the optimized channel images captured by the first-type camera (detecting pedestrians) and the second-type camera (detecting vehicles) to obtain the integrated image.

[0074] The technical solution provided in this application categorizes multi-camera systems into at least a first type of camera and a second type of camera based on detected moving objects. It compares the image quality of images containing the first type of moving object captured by the first type of camera with a first quality threshold, and compares the image quality of images containing the second type of moving object captured by the second type of camera with a second quality threshold. If any comparison result does not meet a preset standard, the camera that does not meet the preset standard is adjusted according to an image quality adjustment rule corresponding to the type of moving object. If the adjustment is detected to meet the preset standard, the images captured by the first type of camera and the second type of camera are stitched together to obtain an integrated image. Through these methods, this technical solution can intelligently adjust parameters to optimize the effect based on the image quality of moving objects in different channels of the multi-camera system, enabling different processing methods to be used for different moving objects in the scene, thus increasing the applicability of multi-camera systems in mixed-scene scenarios.

[0075] Example 2

[0076] Figure 2 This is a flowchart of the image quality control of a multi-camera system in Embodiment 2 of the present invention. This embodiment is based on the above embodiment and optimized. Specifically, the optimization is as follows: the first type of moving object is a pedestrian, and the second type of moving object is a vehicle; if there is a comparison result that does not meet the preset standard, the camera that does not meet the preset standard is adjusted according to the image quality adjustment rule corresponding to the type of moving object, including: if the pedestrian image quality acquired by the first type of camera does not meet the first quality threshold, the image quality of the first type of camera is adjusted based on the gain value of the pedestrian image; or, if the vehicle image quality acquired by the second type of camera does not meet the second quality threshold, the image quality of the second type of camera is adjusted based on the brightness information of the vehicle image.

[0077] like Figure 2 As shown, the method in this embodiment specifically includes the following steps:

[0078] S210, based on the detected moving objects, the multi-view cameras are divided into at least a first category of cameras and a second category of cameras;

[0079] S220, compare the image quality of the image containing the first type of moving object captured by the first type of camera with a first quality threshold; and compare the image quality of the image containing the second type of moving object captured by the second type of camera with a second quality threshold;

[0080] The first type of moving object is pedestrians, and the second type of moving object is vehicles;

[0081] S230, if the quality of the pedestrian image acquired by the first type of camera does not meet the first quality threshold, the image quality of the first type of camera is adjusted based on the gain value of the pedestrian image;

[0082] or,

[0083] If the quality of the vehicle image captured by the second type of camera does not meet the second quality threshold, the image quality of the second type of camera is adjusted based on the vehicle image brightness information.

[0084] The gain value of the pedestrian image can be obtained by using AE statistics to obtain the gain value Gi of the current pedestrian image. The brightness information of the vehicle image can be obtained by using AE statistics to obtain the brightness information L of the current vehicle image. m The AE statistics may include information such as automatic exposure, exposure information, and the average brightness value of the image.

[0085] In this embodiment, when the quality of the pedestrian image captured by the first type of camera that detects pedestrians does not meet the first quality threshold, that is, when it does not meet R... 行人 ≥R T In this case, the system first determines whether to turn on the supplementary lighting by judging the gain value, and then adjusts the pedestrian image quality by adjusting the ISP parameters to ensure that the pedestrian image quality meets the first quality threshold. Alternatively, when it is detected that the vehicle image quality captured by the second type of camera does not meet the second quality threshold, that is, when W is not met... 车 ≥W T At that time, the vehicle image quality is adjusted by adjusting the vehicle image brightness information so that the vehicle image quality meets the second quality threshold.

[0086] S240, if the adjustment is detected to meet the preset standard, the images captured by the first type of camera and the second type of camera are stitched together to obtain an integrated image.

[0087] In this implementation, different processing methods are used for different moving objects in the picture based on the image quality of moving objects in different channels of the multi-camera, so as to ensure the best mixed-line effect and increase the applicability of multi-camera mixed-line.

[0088] In this embodiment, optionally, adjusting the image quality of the first type of camera based on the gain value of the pedestrian image includes: obtaining the current gain value of the pedestrian image; if the current gain value is greater than a preset gain value, then turning on the supplementary lighting device of the first type of camera; re-acquiring the pedestrian image through the first type of camera, and determining whether the quality of the pedestrian image meets a first quality threshold; if it meets the threshold, then outputting the pedestrian image after turning on the supplementary lighting device; if it does not meet the threshold, then adjusting the ISP image parameters of the first type of camera until the pedestrian image re-acquired through the first type of camera meets the first quality threshold.

[0089] The current gain value can be obtained from the gain value G of the current pedestrian image through AE statistics. i The preset gain value can be a pre-set threshold, which can be represented by G. R The aforementioned supplementary lighting device can be a supplementary light. The ISP (Image Signal Processor) parameters, also known as image processing parameters, primarily perform post-processing on the signal output from the front-end image sensor. Its main functions include linear correction, noise removal, bad pixel removal, interpolation, white balance, and automatic exposure control. The ISP is essential for accurately reproducing scene details under various optical conditions, and its technology largely determines the camera's image quality. Furthermore, it comes in at least two forms: standalone and integrated.

[0090] In this embodiment, when R 行人 <R T If the pedestrian image quality is below standard, the current gain value G of the pedestrian image is obtained through AE statistics. i ; By using the gain threshold G R Compare and determine whether the current lighting is sufficient, such as G. i >G R If the current gain is too high and the ambient light is insufficient, the supplementary lighting device of the first type of camera will be activated to improve the image quality. Otherwise, if the ambient light is sufficient, the supplementary lighting device is not required. After activating the supplementary lighting device of the first type of camera, pedestrian images are re-acquired through the first type of camera, and it is determined whether the pedestrian images meet the first quality threshold R. T If the conditions are met, the pedestrian image acquired after turning on the supplementary lighting will be output. If the first quality threshold R is not met... TThen, the ISP image parameters of the current channel are dynamically adjusted to improve the image quality of moving objects until the pedestrian images re-acquired by the first type of camera meet the first quality threshold R. T Then, the optimized pedestrian images are output.

[0091] This solution optimizes pedestrian image quality by adjusting the lighting settings and intelligently adjusting ISP parameters, thus ensuring the quality of pedestrian images.

[0092] In this embodiment, optionally, the pedestrian image quality includes face image quality and body image quality; the face image quality is determined based on at least one of the brightness, sharpness, and noise of the face in the pedestrian image; the body image quality is determined based on at least one of the brightness, sharpness, and noise of the body in the pedestrian image.

[0093] In this embodiment, the quality of face images and human body images is determined based on multiple factors, thereby determining the quality of pedestrian images and further ensuring the quality of human body images.

[0094] In this embodiment, optionally, adjusting the image quality of the second type of camera based on vehicle image brightness information includes: obtaining the highest brightness value of a bright spot in the vehicle image; if the highest brightness value exceeds a preset brightness value, suppressing the brightness value of the bright spot so that the brightness value of the bright spot is lower than the preset brightness value; adjusting the ISP image parameters of the second type of camera until the vehicle image re-acquired by the second type of camera meets the second quality threshold.

[0095] The highest brightness value can be obtained by the second type of camera dividing the vehicle image and acquiring the highest brightness value L in the image through AE information. m The preset brightness value can be a pre-set threshold, such as L. y This indicates that the brightness suppression may be to suppress vehicle headlights. The ISP (Image Signal Processor) image parameters are also image processing parameters.

[0096] For example, at night, vehicle headlights can make license plates illegible. In this case, the second type of camera uses virtual M-channel intelligence to determine whether there is strong light in the current channel, and then obtains the brightness L of the brightest block in the image through AE information. m If L m Exceeding the set upper limit of the brightness threshold L y If strong light is detected in the image, the headlights are first suppressed until the brightness of the brightest area L is reached. m ≤L yThe ISP image parameters are dynamically adjusted until the vehicle images re-acquired by the second type of camera meet the second quality threshold, thus obtaining the best license plate and headlight effects. Then, the normal M-road motor vehicle image quality W is calculated. 车 If the highest block brightness value L m The preset brightness threshold limit L has not been exceeded. y If the image quality is negative, then it is assumed that there is no strong light in the image. In this case, the image quality W of the motor vehicle is also judged. 车 If the standard is not met, the ISP parameters are dynamically adjusted to ensure the overall effect of the vehicle; otherwise, the current vehicle image is output directly.

[0097] This solution optimizes vehicle image quality by suppressing headlight adjustment methods and intelligently adjusting ISP parameters.

[0098] In this embodiment, optionally, the vehicle image quality includes the vehicle body image quality and the license plate image quality; the vehicle body image quality is determined based on at least one of the brightness, sharpness, and noise of the vehicle body in the vehicle body image; the license plate image quality is determined based on at least one of the brightness, sharpness, and noise of the license plate in the license plate image.

[0099] In this embodiment, the vehicle image quality is determined by considering multiple factors to determine the vehicle body image quality and license plate image quality, thereby further ensuring the effectiveness of the vehicle image quality.

[0100] In this embodiment, optionally, the second type of camera is at least one channel; the at least one channel of the second type of camera is virtualized to obtain virtual route images of each channel of the second type of camera; correspondingly, the brightness value of the bright blocks is suppressed based on the virtual route images, so that the brightness value of the bright blocks is lower than a preset brightness value; and the ISP image parameters of the second type of camera are adjusted until the vehicle images re-acquired by the second type of camera meet the second quality threshold, so as to obtain vehicle images that meet the second quality threshold; the headlight images and license plate images are cropped from the virtual route images and fused with the real route images of the second type of camera.

[0101] The virtual route image can be a vehicle image obtained from a virtual route with M channels of the second cameras as the middle channel, used to suppress vehicle headlights at night. The real route image from the second type of camera can be a real route image of the same scene as the virtual route image.

[0102] In this embodiment, when the vehicle image quality value W 车 With vehicle mass threshold W T When making comparisons, if W 车 ≥W TThis indicates that the overall image quality of the moving vehicle meets the requirements. The headlights and license plates are cropped from the images obtained from the virtual M-path image (images with suppressed headlights and optimized clear license plates) and merged into the normally exposed image, thus achieving the goal of optimizing the headlights and license plates of the moving object; if W 车 <W T The second type of camera uses virtual M-channel intelligent detection to determine whether there is strong light in the current channel, and then obtains the brightness L of the brightest block in the image through AE information. m If L m Exceeding the set upper limit of the brightness threshold L y If strong light is detected in the image, the headlights are first suppressed until the brightness of the brightest area L is reached. m ≤L y The system dynamically adjusts ISP parameters to ensure the overall effect of moving vehicles meets the standard until the vehicle images captured by the second type of camera meet the second quality threshold. Similarly, the headlight and license plate images are cropped from the images of suppressed headlights and optimized clear license plates obtained from the virtual M-road images. Then, the virtual route images are merged into the real route images of the same scene. The images from the first type of camera and the second type of camera are stitched together to output the final image, thereby obtaining the best image effect for both the monitored subject and the overall image quality under the current ambient illumination.

[0103] This solution uses this setting to suppress vehicle headlights in low-light environments, obtain clear license plates, and then merge the suppressed headlights and clear license plates into a normally exposed image, thereby achieving the goal of optimizing moving vehicles in low-light environments.

[0104] Example 3

[0105] Figure 3 This is a structural block diagram of an image quality control device for a multi-view camera provided in Embodiment 3 of the present invention. This device can execute the image quality control method for a multi-view camera provided in any embodiment of the present invention, and possesses the corresponding functional modules and beneficial effects for executing the method. For example... Figure 3 As shown, the device may include:

[0106] The camera classification module 310 is used to classify multi-cameras into at least a first category of cameras and a second category of cameras based on the detected moving objects.

[0107] The image quality comparison module 320 is used to compare the image quality of the first type of camera containing a first type of moving object with a first quality threshold; and to compare the image quality of the second type of camera containing a second type of moving object with a second quality threshold.

[0108] The image adjustment module 330 is used to adjust the camera that does not meet the preset standard according to the image quality adjustment rules corresponding to the type of moving object if there is a comparison result that does not meet the preset standard.

[0109] The image acquisition module 340 is used to stitch together the images acquired by the first type of camera and the second type of camera to obtain an integrated image if it detects that the adjustment has been made to meet the preset standard.

[0110] This technical solution, through the above methods, can intelligently adjust parameters to optimize the effect based on the image quality of moving objects in different channels of a multi-camera system, thereby enabling different processing methods to be used for different moving objects in the image and increasing the applicability of multi-camera systems in mixed-mode operation.

[0111] The first type of moving object is pedestrians, and the second type of moving object is vehicles;

[0112] Furthermore, the image adjustment module 330 includes:

[0113] A pedestrian image adjustment unit is used to adjust the image quality of the first type of camera based on the gain value of the pedestrian image if the quality of the pedestrian image acquired by the first type of camera does not meet the first quality threshold.

[0114] or,

[0115] The vehicle image adjustment unit is used to adjust the image quality of the second type of camera based on the vehicle image brightness information if the quality of the vehicle image acquired by the second type of camera does not meet the second quality threshold.

[0116] Furthermore, the pedestrian image adjustment unit is specifically used for:

[0117] Obtain the current gain value of the pedestrian image;

[0118] If the current gain value is greater than the preset gain value, then the supplementary lighting device of the first type of camera is turned on;

[0119] The pedestrian images are re-acquired through the first type of camera, and it is determined whether the quality of the pedestrian images meets the first quality threshold.

[0120] If the conditions are met, the output will be based on the pedestrian image after the supplementary lighting device is turned on;

[0121] If the condition is not met, the ISP image parameters of the first type of camera are adjusted until the pedestrian images re-acquired by the first type of camera meet the first quality threshold.

[0122] Furthermore, the pedestrian image quality includes face image quality and body image quality; the face image quality is determined based on at least one of the brightness, sharpness, and noise of the face in the pedestrian image; the body image quality is determined based on at least one of the brightness, sharpness, and noise of the body in the pedestrian image.

[0123] Furthermore, the vehicle image adjustment unit is specifically used for:

[0124] Obtain the highest brightness value of bright blocks in the vehicle image;

[0125] If the highest brightness value exceeds the preset brightness value, then the brightness value of the bright block is suppressed so that the brightness value of the bright block is lower than the preset brightness value.

[0126] Adjust the ISP image parameters of the second type of camera until the vehicle images re-acquired by the second type of camera meet the second quality threshold.

[0127] Furthermore, the vehicle image quality includes the vehicle body image quality and the license plate image quality; the vehicle body image quality is determined based on at least one of the brightness, sharpness, and noise of the vehicle body in the vehicle body image; the license plate image quality is determined based on at least one of the brightness, sharpness, and noise of the license plate in the license plate image.

[0128] Furthermore, the second type of camera is at least one channel; the at least one channel of the second type of camera is virtualized to obtain virtual route images of each channel of the second type of camera; correspondingly, the brightness value of the bright blocks is suppressed based on the virtual route images, so that the brightness value of the bright blocks is lower than a preset brightness value; and the ISP image parameters of the second type of camera are adjusted until the vehicle images re-acquired by the second type of camera meet the second quality threshold, so as to obtain vehicle images that meet the second quality threshold; the headlight images and license plate images are cropped from the virtual route images and fused with the real route images of the second type of camera.

[0129] The above-mentioned product can perform the image quality control method for multi-view cameras provided in the embodiments of this application, and has the corresponding functional modules and beneficial effects of performing the method.

[0130] Example 4

[0131] Embodiment 4 of the present invention provides a computer-readable storage medium storing a computer program thereon, which, when executed by a processor, implements the image quality control method for a multi-view camera as provided in all embodiments of the present application:

[0132] Based on the detected moving objects, multi-view cameras are divided into at least two categories: Category I cameras and Category II cameras.

[0133] The image quality of the first type of moving object captured by the first type of camera is compared with a first quality threshold; and the image quality of the second type of moving object captured by the second type of camera is compared with a second quality threshold.

[0134] If any comparison result does not meet the preset standard, the camera that does not meet the preset standard will be adjusted according to the image quality adjustment rules corresponding to the type of moving object;

[0135] If the adjustment is found to meet the preset standard, the images captured by the first type of camera and the second type of camera are stitched together to obtain an integrated image.

[0136] Any combination of one or more computer-readable media may be used. A computer-readable medium can be a computer-readable signal medium or a computer-readable storage medium. A computer-readable storage medium can 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 computer-readable storage media include: an electrical connection having one or more wires, a portable computer disk, a hard disk, 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 device, magnetic storage device, or any suitable combination thereof. In this document, a computer-readable storage medium can be any tangible medium that contains or stores a program that can be used by or in connection with an instruction execution system, apparatus, or device.

[0137] Computer-readable signal media may include data signals propagated in baseband or as part of a carrier wave, carrying computer-readable program code. Such propagated data signals may take various forms, including—but not limited to—electromagnetic signals, optical signals, or any suitable combination thereof. Computer-readable signal media may also be any computer-readable medium other than computer-readable storage media, capable of transmitting, propagating, or transmitting programs for use by or in connection with an instruction execution system, apparatus, or device.

[0138] The program code contained on a computer-readable medium may be transmitted using any suitable medium, including—but not limited to—wireless, wire, optical fiber, RF, etc., or any suitable combination thereof.

[0139] Computer program code for performing the operations of this invention can be written in one or more programming languages ​​or a combination thereof, including object-oriented programming languages ​​such as Java, Smalltalk, and C++, as well as conventional procedural programming languages ​​such as "C" or similar programming languages. The program code can be executed entirely on the user's computer, partially on the user's computer, as a standalone software package, partially on the user's computer and partially on a remote computer, or entirely on a remote computer or server. In cases involving remote computers, the remote computer can be connected to the user's computer via any type of network—including a local area network (LAN) or a wide area network (WAN)—or can be connected to an external computer (e.g., via the Internet using an Internet service provider).

[0140] Example 5

[0141] Embodiment 5 of this application provides an electronic device. Figure 4 This is a schematic diagram of the structure of an electronic device provided in Embodiment Six of this application. Figure 4 As shown, this embodiment provides an electronic device 400, which includes: one or more processors 420; and a storage device 410 for storing one or more programs. When the one or more programs are executed by the one or more processors 420, the one or more processors 420 implement the image quality control method for a multi-view camera provided in this application embodiment. The method includes:

[0142] Based on the detected moving objects, multi-view cameras are divided into at least two categories: Category I cameras and Category II cameras.

[0143] The image quality of the first type of moving object captured by the first type of camera is compared with a first quality threshold; and the image quality of the second type of moving object captured by the second type of camera is compared with a second quality threshold.

[0144] If any comparison result does not meet the preset standard, the camera that does not meet the preset standard will be adjusted according to the image quality adjustment rules corresponding to the type of moving object;

[0145] If the adjustment is found to meet the preset standard, the images captured by the first type of camera and the second type of camera are stitched together to obtain an integrated image.

[0146] Of course, those skilled in the art will understand that the processor 420 also implements the technical solution of the image quality control method for multi-view cameras provided in any embodiment of this application.

[0147] Figure 4The electronic device 400 shown is merely an example and should not impose any limitations on the functionality and scope of use of the embodiments of this application.

[0148] like Figure 4 As shown, the electronic device 400 includes a processor 420, a storage device 410, an input device 430, and an output device 440; the number of processors 420 in the electronic device can be one or more. Figure 4 Taking a processor 420 as an example; the processor 420, storage device 410, input device 430, and output device 440 in the electronic device can be connected via a bus or other means. Figure 4 For example, China and Israel are connected via bus 450.

[0149] Storage device 410, as a computer-readable storage medium, can be used to store software programs, computer-executable programs, and module units, such as the program instructions corresponding to the image quality control method of the multi-view camera in the embodiments of this application.

[0150] Storage device 410 may primarily include a program storage area and a data storage area. The program storage area may store the operating system and at least one application program required for a given function; the data storage area may store data created based on terminal usage. Furthermore, storage device 410 may include high-speed random access memory and non-volatile memory, such as at least one disk storage device, flash memory, or other non-volatile solid-state storage device. In some instances, storage device 410 may further include memory remotely located relative to processor 420, which can be connected via a network. Examples of such networks include, but are not limited to, the Internet, intranets, local area networks, mobile communication networks, and combinations thereof.

[0151] Input device 430 can be used to receive input digital, character, or voice information, and to generate key signal inputs related to user settings and function control of the electronic device. Output device 440 may include electronic devices such as a display screen and a speaker.

[0152] The electronic device provided in this application embodiment can intelligently adjust parameters to optimize the effect based on the image quality of moving objects in different channels of a multi-view camera, thereby enabling different processing methods to be used for different moving objects in the picture and increasing the applicability of multi-view cameras in mixed scenes.

[0153] The image quality control device, medium, and electronic equipment for multi-view cameras provided in the above embodiments can execute the image quality control method for multi-view cameras provided in any embodiment of this application, and have the corresponding functional modules and beneficial effects for executing the method. Technical details not described in detail in the above embodiments can be found in the image quality control method for multi-view cameras provided in any embodiment of this application.

[0154] Note that the above description is merely a preferred embodiment of the present invention and the technical principles employed. Those skilled in the art will understand that the present invention is not limited to the specific embodiments described herein, and various obvious changes, readjustments, and substitutions can be made without departing from the scope of protection of the present invention. Therefore, although the present invention has been described in detail through the above embodiments, the present invention is not limited to the above embodiments, and may include many other equivalent embodiments without departing from the concept of the present invention, the scope of which is determined by the scope of the appended claims.

Claims

1. An image quality control method for a multi-view camera, characterized in that, include: Based on the detected moving objects, multi-view cameras are divided into at least two categories: Category I cameras and Category II cameras. The image quality containing the first type of moving object captured by the first type of camera is compared with a first quality threshold; In addition, the image quality of the second type of moving object captured by the second type of camera is compared with a second quality threshold; If any comparison result does not meet the preset standard, the camera that does not meet the preset standard will be adjusted according to the image quality adjustment rules corresponding to the type of moving object; If the adjustment is found to meet the preset standard, the images captured by the first type of camera and the second type of camera are stitched together to obtain an integrated image; The first type of moving object is pedestrians, and the second type of moving object is vehicles; If any comparison result does not meet the preset standard, then the cameras that do not meet the preset standard will be adjusted according to the image quality adjustment rules corresponding to the type of moving object, including: If the quality of the pedestrian images captured by the first type of camera does not meet the first quality threshold, the image quality of the first type of camera is adjusted based on the gain value of the pedestrian images. If the quality of the vehicle image captured by the second type of camera does not meet the second quality threshold, the image quality of the second type of camera is adjusted based on the vehicle image brightness information. Adjusting the image quality of the second type of camera based on vehicle image brightness information includes: Obtain the highest brightness value of bright blocks in the vehicle image; If the highest brightness value exceeds the preset brightness value, then the brightness value of the bright block is suppressed so that the brightness value of the bright block is lower than the preset brightness value. Adjust the ISP image parameters of the second type of camera until the vehicle images re-acquired by the second type of camera meet the second quality threshold; The second type of camera has at least one channel; Virtualize at least one of the second-type cameras to obtain virtual route images for each of the second-type cameras; Accordingly, the brightness value of the bright blocks is suppressed based on the virtual route image, so that the brightness value of the bright blocks is lower than the preset brightness value; and the ISP image parameters of the second type of camera are adjusted until the vehicle image re-acquired by the second type of camera meets the second quality threshold, so as to obtain a vehicle image that meets the second quality threshold. Vehicle headlight and license plate images are cropped from the virtual route image and fused with the real route image from the second type of camera.

2. The method according to claim 1, characterized in that, Adjusting the image quality of the first type of camera based on the gain value of the pedestrian image includes: Obtain the current gain value of the pedestrian image; If the current gain value is greater than the preset gain value, then the supplementary lighting device of the first type of camera is turned on; The pedestrian images are re-acquired through the first type of camera, and it is determined whether the quality of the pedestrian images meets the first quality threshold. If the conditions are met, the output will be based on the pedestrian image after the supplementary lighting device is turned on; If the condition is not met, the ISP image parameters of the first type of camera are adjusted until the pedestrian images re-acquired by the first type of camera meet the first quality threshold.

3. The method according to claim 1, characterized in that, The pedestrian image quality includes face image quality and body image quality; The quality of the face image is determined based on at least one of the brightness, sharpness, and noise of the face in the pedestrian image; The quality of the human body image is determined based on at least one of the brightness, sharpness, and noise of the human body in the pedestrian image.

4. The method according to claim 1, characterized in that, The vehicle image quality includes the vehicle body image quality and the license plate image quality; The quality of the vehicle image is determined based on at least one of the brightness, sharpness, and noise of the vehicle in the image. The quality of the license plate image is determined based on at least one of the following: the brightness, sharpness, and noise of the license plate in the image.

5. An image quality control device for a multi-view camera, characterized in that, include: The camera classification module is used to classify multi-camera systems into at least a first category and a second category based on detected moving objects. The image quality comparison module is used to compare the image quality of the first type of moving object captured by the first type of camera with a first quality threshold. In addition, the image quality of the second type of moving object captured by the second type of camera is compared with a second quality threshold; The image adjustment module is used to adjust the camera that does not meet the preset standard according to the image quality adjustment rules corresponding to the type of moving object if the comparison result does not meet the preset standard. The image acquisition module is used to stitch together the images captured by the first type of camera and the second type of camera to obtain an integrated image if the adjustment is detected to meet the preset standard. The image adjustment module includes: A pedestrian image adjustment unit is used to adjust the image quality of the first type of camera based on the gain value of the pedestrian image if the quality of the pedestrian image acquired by the first type of camera does not meet the first quality threshold. The vehicle image adjustment unit is used to adjust the image quality of the second type of camera based on the vehicle image brightness information if the quality of the vehicle image acquired by the second type of camera does not meet the second quality threshold. The vehicle image adjustment unit is specifically used for: Obtain the highest brightness value of bright blocks in the vehicle image; If the highest brightness value exceeds the preset brightness value, then the brightness value of the bright block is suppressed so that the brightness value of the bright block is lower than the preset brightness value. Adjust the ISP image parameters of the second type of camera until the vehicle images re-acquired by the second type of camera meet the second quality threshold; The second type of camera consists of at least one channel; the at least one channel of the second type of camera is virtualized to obtain virtual route images for each channel of the second type of camera; correspondingly, the brightness value of the bright blocks is suppressed based on the virtual route images, so that the brightness value of the bright blocks is lower than a preset brightness value; and the ISP image parameters of the second type of camera are adjusted until the vehicle images re-acquired by the second type of camera meet the second quality threshold, so as to obtain vehicle images that meet the second quality threshold; the headlight images and license plate images are cropped from the virtual route images and fused with the real route images of the second type of camera.

6. A computer-readable storage medium having a computer program stored thereon, characterized in that, When executed by the processor, the program implements the image quality control method for a multi-view camera as described in any one of claims 1-4.

7. 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 image quality control method for a multi-view camera as described in any one of claims 1-4.

Images