Brightness adjusting method of night vision camera

Abstract

The invention relates to the technical field of image data processing, in particular to a brightness adjusting method of a night vision camera, and the method comprises the steps: obtaining a target ROI region of each image frame in a video image sequence of the night vision camera; normalizing the product of the gradient mean value of all pixel points in the sub-block of the target ROI and the texture complexity to obtain the complexity feature of the sub-block; taking the optical flow vector of the central point of the sub-block as a reference motion vector of the sub-block, and calculating a cosine similarity entropy value of the optical flow vector of each pixel point and the reference motion vector; according to the mean value and the cosine similarity entropy value of the optical flow vector modulus lengths of all the pixel points in the sub-blocks, obtaining the importance characteristics of the sub-blocks; calculating the weights of the sub-blocks; the brightness value of each sub-block is weighted based on the weight of the sub-block in the target ROI region of the image frame, so that the brightness adjustment of the night vision camera is realized, and the accuracy of the brightness adjustment of the night vision camera is effectively improved.

Description

Technical Field

[0001] The present invention relates to the technical field of image data processing. More specifically, the present invention relates to a method for adjusting the brightness of a night vision camera. Background Art

[0002] A night vision camera is a device that can provide clear surveillance images at night or in low-light environments, usually using infrared light sources. During operation, an infrared night vision camera emits invisible infrared light through infrared light-emitting diodes, irradiates an object, and the reflected light is captured by the camera and converted into an electrical signal to generate a surveillance image. To ensure the quality of the images captured by the camera, it is necessary to adaptively adjust the infrared light brightness according to the ambient light brightness and the brightness of the surveillance image to avoid overexposure or underexposure.

[0003] In the prior art, there have been many studies and applications on night vision cameras. For example, the patent application document with the publication number CN119052656A discloses an infrared lamp brightness dynamic adjustment method, device, electronic device, and computer-readable medium for a wireless camera. This application controls the wireless camera to turn on the infrared lamp on the wireless camera for shooting according to a first preset duty cycle threshold to obtain a scene image; determines the exposure value of the wireless camera when shooting the scene image; and adjusts the brightness of the infrared lamp based on the scene image, the exposure value, and a preset exposure value range.

[0004] The above prior art adjusts the brightness of the infrared lamp through the scene image, the exposure value, and the preset exposure value range. However, when adjusting the brightness of the infrared light source of the camera to collect night-time environment surveillance images, the brightness distribution in the images is not uniform. If the adjustment is directly based on the preset exposure value range, it will result in poor brightness adjustment effect of the night vision camera, thus causing overexposure or underexposure.

[0005] Based on this, how to accurately achieve the brightness adjustment of a night vision camera is an urgent problem to be solved by those skilled in the art. Summary of the Invention

[0006] To solve the above technical problem of how to accurately achieve the brightness adjustment of a night vision camera, the present invention proposes a method for adjusting the brightness of a night vision camera, which includes the following steps: The union of the image frame in the video image sequence of the night vision camera and the ROI region of the previous image frame of this image frame is used as the target ROI region of this image frame; the product of the gradient mean value and the texture complexity of all pixel points in the sub-block of the target ROI region is normalized to obtain the complexity feature of this sub-block; the optical flow vector of the center point of the sub-block is used as the reference motion vector of this sub-block, and the cosine similarity entropy value between the optical flow vector of each pixel point and the reference motion vector is calculated; the importance feature of this sub-block is obtained according to the mean value of the optical flow vector modulus of all pixel points in the sub-block and the cosine similarity entropy value; the weight of the sub-block is obtained according to the complexity feature and the importance feature of the sub-block; the brightness values of each sub-block are weighted based on the weights of the sub-blocks in the target ROI region of the image frame to achieve the brightness adjustment of the night vision camera.

[0007] When adjusting the brightness of the night vision camera, the present invention can realize the brightness adjustment of the night vision camera by obtaining the brightness performance of each sub-block in the ROI region of the image frame of the video image sequence of the night vision camera. In this process, the present invention takes into account that the brightness performances of different sub-blocks in the ROI region are different, so their importance degrees in calculating the image frame brightness are different; based on this, the present invention obtains the contribution degree of the sub-block to the image frame brightness by obtaining the complexity degree and the importance degree of each sub-block in the ROI region, effectively improving the accuracy of the brightness adjustment of the night vision camera.

[0008] According to a brightness adjustment method of a night vision camera provided by the present invention, before using the union of the image frame in the video image sequence of the night vision camera and the ROI region of the previous image frame of this image frame as the target ROI region of this image frame, it further includes: preprocessing the video image captured by the night vision camera to obtain each image frame of the video image sequence; dividing the target ROI region of the image frame into multiple sub-blocks based on a preset sub-block size.

[0009] The present invention takes into account that the edges of the originally captured image frames may be deformed, etc., which may affect subsequent image processing. Therefore, the quality of the image is improved through preprocessing to prepare for subsequent image processing.

[0010] According to a brightness adjustment method of a night vision camera provided by the present invention, the method for obtaining the ROI region of the image frame includes: using a Gaussian mixture model to perform background modeling on the video image sequence, extracting the moving target in the image frame through background subtraction, and using the circumscribed rectangle of the moving target as the ROI region of this image frame.

[0011] According to a brightness adjustment method of a night vision camera provided by the present invention, the method for obtaining the gradient of a pixel point includes: calculating the gradient of the pixel point through a sobel operator.

[0012] A method for adjusting the brightness of a night vision camera according to the present invention, the method for obtaining the texture complexity includes: using the entropy value of each gray level pair in the gray level co-occurrence matrix of the sub-block as the texture complexity of the sub-block.

[0013] The present invention takes into account that the texture complexity in the sub-block is related to the gray level features in the sub-block. Therefore, the entropy value in the gray level co-occurrence matrix is used to measure the complexity of the gray level distribution of the image. When all values in the co-occurrence matrix are equal or the pixel values show the greatest randomness, the entropy value in the co-occurrence matrix reaches the maximum. Based on this, the texture complexity of the sub-block can be accurately obtained.

[0014] A method for adjusting the brightness of a night vision camera according to the present invention, the method for weighting the brightness values of each sub-block based on the weight of the sub-block in the target ROI area of the image frame includes: using the product of the weight of the sub-block in the target ROI area and the brightness value as the weighted value of the sub-block, and using the weighted average value of all sub-blocks in the target ROI area of the image frame as the brightness value of the image frame; Among them, ; is the weight of the i-th sub-block, , are the complexity feature and importance feature of the i-th sub-block respectively, is the exponential function with e as the base.

[0015] A method for adjusting the brightness of a night vision camera according to the present invention, the method for weighting the brightness values of each sub-block based on the weight of the sub-block in the target ROI area of the image frame to achieve the brightness adjustment of the night vision camera includes: obtaining the brightness gain parameter through the ratio of the brightness value of the image frame to the preset brightness value, and adjusting the brightness of the camera based on the brightness gain parameter.

[0016] The present invention adjusts the brightness of the camera by obtaining the brightness gain parameter of the image frame, so that the camera can automatically adjust the gain value according to the brightness change of the collected image frame, thereby ensuring a clear monitoring picture at night.

[0017] A method for adjusting the brightness of a night vision camera according to the present invention, after realizing the brightness adjustment of the night vision camera, it further includes: performing abnormal monitoring on the video image sequence of the night vision camera.

[0018] The present invention can automatically detect and mark abnormal events, timely discover and respond to potential security threats, and reduce security risks.

[0019] The present invention has the following beneficial effects: Based on the above technical solution, when adjusting the brightness of a night vision camera, by obtaining the brightness performance of each sub-block in the ROI region of the image frames of the video image sequence of the night vision camera, the brightness adjustment of the night vision camera can be achieved. In this process, the present invention takes into account that the brightness performances of different sub-blocks in the ROI region are different, so their importance degrees in calculating the brightness of the image frame are different; based on this, the present invention obtains the contribution degree of each sub-block to the image frame brightness by acquiring the complexity and importance degree of each sub-block in the ROI region, effectively improving the accuracy of the brightness adjustment of the night vision camera. BRIEF DESCRIPTION OF THE DRAWINGS

[0020] By referring to the accompanying drawings and reading the following detailed description, the above and other objects, features, and advantages of the exemplary embodiments of the present invention will become readily understood. In the drawings, several embodiments of the present invention are shown in an exemplary rather than restrictive manner, and the same or corresponding reference numerals represent the same or corresponding parts, wherein: Figure 1 It is a schematic flowchart of a method for adjusting the brightness of a night vision camera provided by an embodiment of the present invention. DETAILED DESCRIPTION OF THE EMBODIMENTS

[0021] Next, the technical solutions in the embodiments of the present invention will be clearly and completely described in conjunction with the accompanying drawings in the embodiments of the present invention. Obviously, the described embodiments are some, but not all, of the embodiments of the present invention. All other embodiments obtained by those skilled in the art based on the embodiments of the present invention without creative efforts fall within the protection scope of the present invention.

[0022] Next, the specific embodiments of the present invention will be described in detail in conjunction with the accompanying drawings.

[0023] A night vision camera is a device that can provide clear surveillance images at night or in a dimly lit environment, usually using infrared light sources. During operation, the infrared night vision camera emits invisible infrared light through infrared light-emitting diodes, irradiates an object, and the light is reflected back and captured by the camera and converted into an electrical signal, thereby generating a surveillance image. To ensure the quality of the images captured by the camera, it is necessary to adaptively adjust the infrared light brightness according to the ambient light brightness and the brightness of the surveillance image to avoid overexposure or underexposure.

[0024] However, when adjusting the brightness of the infrared light source of the camera to collect night-time environmental surveillance images, the brightness distribution in the image is not uniform. If the adjustment is directly based on the preset exposure value range, the brightness adjustment effect of the night vision camera will be poor, resulting in overexposure or underexposure.

[0025] Based on this, embodiments of the present invention disclose a method for adjusting the brightness of a night vision camera. By analyzing the image complexity and importance of each sub-block in the image frames captured by the camera, the weight of each sub-block when determining the brightness value of the image frame is obtained, so as to accurately obtain the brightness value required for each image frame, and the accuracy of brightness adjustment of the night vision camera can be effectively improved.

[0026] For details, please refer to Figure 1 as shown in Figure 1 which is a schematic flowchart of a method for adjusting the brightness of a night vision camera provided by an embodiment of the present invention. The method specifically includes the following steps.

[0027] S1: Use the union of the image frame in the video image sequence of the night vision camera and the ROI region of the previous image frame of this image frame as the target ROI region of this image frame.

[0028] Exemplarily, in the embodiments of the present invention, before using the union of the image frame in the video image sequence of the night vision camera and the ROI region of the previous image frame of this image frame as the target ROI region of this image frame, it further includes: preprocessing the video images captured by the night vision camera to obtain each image frame of the video image sequence.

[0029] Among them, the preprocessing can be geometric transformation, image enhancement, etc., which can be specifically set according to actual needs, and the embodiments of the present invention do not limit this too much here.

[0030] It should be noted that the video image sequence captured by the night vision camera contains a lot of content. The image frame contains both the region of interest (ROI) that needs to be concerned and the background region that does not need to be concerned. In order to reduce the interference of the background region and at the same time reduce the data processing volume, when adjusting the brightness of the camera, it is possible to focus only on the ROI region in the image frame.

[0031] It should be further noted that there may be fast-moving objects in the image frame. If it is difficult to identify such targets only through the ROI region of the current image frame, and the characteristics of pixel points in different regions are different. If the ROI region is analyzed as a whole, the characteristics of pixel points in some regions may be blurred.

[0032] Based on this, in the embodiments of the present invention, the union of the ROI regions of the current image frame and its previous image frame is used as the target ROI region of the current image frame, and the target ROI region is divided into multiple sub-blocks, and the pixel point characteristics of each sub-block in the target ROI region are analyzed.

[0033] Exemplarily, in the embodiments of the present invention, a method for obtaining the ROI region of an image frame includes: performing background modeling on a video image sequence using a Gaussian mixture model, extracting moving objects in the image frame through background subtraction, and taking the circumscribed rectangle of the moving object as the ROI region of the image frame.

[0034] Specifically, when performing background modeling on a video image sequence using a Gaussian mixture model, the number of Gaussian distributions required for each pixel point can be preset; for each frame and each pixel point in the video image sequence, compare its pixel value with each Gaussian distribution in the Gaussian mixture model to determine whether it matches a certain distribution; if the pixel value matches a certain Gaussian distribution, update the mean, covariance matrix, and weight of the distribution, and increase the weight to reflect the importance of the distribution for background modeling in the recent period; if the pixel value does not match all Gaussian distributions, select the least important distribution for replacement according to the weight and set a smaller weight; finally, take the Gaussian distribution with a larger weight and a smaller variance as the representative of the background region to obtain a Gaussian mixture model that can be used to identify the foreground region.

[0035] Among them, the number of Gaussian distributions required for each pixel point can be specifically set according to actual needs, and the embodiments of the present invention do not impose too many restrictions here.

[0036] Exemplarily, when extracting moving objects in the image frame through background subtraction, the image frame can be subjected to a difference operation with the background model, and the obtained difference image is recorded as the moving object.

[0037] After obtaining the target ROI region of the image frame based on the above steps, each sub-block in the target ROI region can be analyzed.

[0038] Exemplarily, in the embodiments of the present invention, the target ROI region of the image frame can be divided into multiple sub-blocks based on a preset sub-block size.

[0039] Among them, the sub-block size can be preset to 10×10; the sub-block size can be specifically set according to actual needs, and the embodiments of the present invention do not impose too many restrictions here.

[0040] It should be noted that the features affecting the brightness of the image frame include the image complexity and importance. If the brightness is too low, underexposure will occur, resulting in loss of image details; the higher the brightness, the higher the clarity, but overexposure is likely to occur. After obtaining the sub-blocks of the target ROI regions of each image frame based on the above steps, the following steps can be continued to analyze the image complexity and importance of each sub-block respectively, so as to accurately adjust the brightness of the image frame.

[0041] S2: Normalize the product of the gradient mean and texture complexity of all pixel points in the sub-block of the target ROI region to obtain the complexity feature of the sub-block.

[0042] It should be noted that complex textures in the image frame sub - blocks can interfere with the human eye's perception of sharpness, resulting in the image appearing blurred or difficult to distinguish details visually. The higher the texture complexity, the greater the impact on the sharpness of the image frame. Gradient information is used to measure the rate of change of pixel values in the image. The richer the gradient information in the image frame sub - block, it indicates that there are significant changes in pixel values in different directions, and this area may be clearer visually. The higher the average gradient of the sub - block, it means that the sub - block contains more detail and edge information, and the greater the impact on the sharpness of the image frame.

[0043] Based on this, after obtaining the sub - blocks of the target ROI region in each image frame based on the above steps in the embodiments of the present invention, the complexity of the sub - block can be characterized by the texture complexity degree and the gradient change degree in the sub - block. The higher the texture complexity in the sub - block and the higher the average gradient of all pixel points in the sub - block of the target ROI region, the higher the complexity of the sub - block and the higher the complexity feature.

[0044] Exemplarily, in the embodiments of the present invention, the method for obtaining the gradient of a pixel point includes: calculating the gradient of the pixel point through a sobel operator.

[0045] Among them, the sobel operator is the Sobel operator. The specific steps for obtaining the gradient of a pixel point through the Sobel operator can be realized by existing technologies, and the embodiments of the present invention will not elaborate here.

[0046] It can be understood that the gray - level co - occurrence matrix can extract the texture features in the sub - block and generate a matrix describing the texture features of the image.

[0047] Exemplarily, in the embodiments of the present invention, the method for obtaining the texture complexity includes: taking the entropy value of each gray - level pair in the gray - level co - occurrence matrix of the sub - block as the texture complexity of the sub - block.

[0048] Among them, when obtaining the gray - level co - occurrence matrix of the sub - block, the distance can be set to 1 pixel, the direction can be set to 0°, and the initial gray - level co - occurrence matrix is normalized to obtain the gray - level co - occurrence matrix of the sub - block. The distance and direction can be specifically set according to actual needs; the specific steps for obtaining the gray - level co - occurrence matrix of the sub - block can be realized by existing technologies, and the embodiments of the present invention will not elaborate too much here.

[0049] Exemplarily, in the embodiments of the present invention, when calculating the complexity feature of the sub - block, the following relational expression can be specifically referred to: ; is the complexity feature of the i - th sub - block, is the average gradient of all pixel points in the i - th sub - block, is the texture complexity of the i - th sub - block, is a linear normalization function.

[0050] In the above formula, the greater the average gradient of all pixel points in the i-th sub-block, the more details and edge information may be included in the i-th sub-block, and the greater the impact on the clarity of the image frame.

[0051] The greater the texture complexity of the i-th sub-block, the more complex the pixel gray distribution in the i-th sub-block, and the more complex the texture, the greater the impact on the clarity of the entire region of interest.

[0052] In summary, if the average gradient of all pixel points in the i-th sub-block is greater and the texture complexity is higher, it indicates that the i-th sub-block is more sensitive to brightness adjustment. When adjusting the brightness of the camera's infrared light, more attention needs to be paid to this sub-block to maintain the integrity of image details, and the corresponding complexity feature is also greater.

[0053] Based on the above steps, the complexity features of each sub-block in the target ROI region of the image frame can be obtained. However, the texture features and gradient features in the sub-blocks are static features, and static features are more sensitive to noise in the image frame. If there is noise interference in the image frame collected by the night vision camera, adjusting the brightness only based on the static features of the image frame may identify the noise as gray features or texture features, reducing the accuracy of the camera's brightness adjustment.

[0054] Therefore, the embodiments of the present invention further analyze the important features in the sub-blocks as dynamic features through the following steps, and combine the dynamic features and static features to jointly obtain the weight of each sub-block for the brightness adjustment of the image frame.

[0055] S3: Obtain the important features of the sub-block through the change characteristics of the optical flow vectors of the pixel points in the sub-block.

[0056] It should be noted that in a video image frame, when a moving object changes, calculating the motion components of each pixel point will form a motion vector field, that is, an optical flow field. The optical flow vector is a two-dimensional vector used to describe the motion of each pixel point in the motion vector field. The optical flow vectors of moving objects in the target ROI region usually have high significance. Therefore, the motion information of objects in the image can be reflected by the optical flow vectors of the pixel points in the sub-block. However, in the case of poor image quality or jitter, the optical flow vectors may become unstable.

[0057] Based on this, the embodiments of the present invention can obtain the dynamic features of each sub-block by analyzing the consistency and change speed of the optical flow vectors of the pixel points in the sub-blocks of the target ROI region, so as to characterize the important features of each sub-block.

[0058] By way of example, in an embodiment of the present invention, the optical flow vector of the center point of a sub-block is used as the reference motion vector of the sub-block, and the cosine similarity entropy value of the optical flow vector of each pixel point and the reference motion vector is calculated; the product of the mean normalized value of the modulus of the optical flow vectors of all pixels in the sub-block and the cosine similarity entropy value is used as the importance feature of the sub-block.

[0059] The optical flow vector of the pixel point can be obtained by LK algorithm (Lucas-Kanade algorithm), and the specific steps can be implemented by existing technologies, which will not be described in detail in the embodiment of the present invention.

[0060] It can be understood that the center point of the sub-block is also a pixel point.

[0061] For example, in the embodiment of the present invention, the importance feature of the sub-block is determined, and specifically, the following relationship can be referred to: ; is the importance feature of the ith sub-block, is the cosine similarity entropy value between each pixel in the i-th sub-block and the reference motion vector, is the mean value of the modulus of the optical flow vectors of all pixels in the i-th sub-block, It is an S-shaped growth curve function.

[0062] in, Function used for normalization.

[0063] In the above formula, the cosine similarity entropy value between each pixel in the ith sub-block and the reference motion vector indicates the degree of confusion of the optical flow vector of the pixel in the ith sub-block. The larger the value, the greater the degree of confusion of the optical flow vector of the pixel in the ith sub-block, and the higher the possibility of out-of-focus or blur phenomenon, which leads to a decrease in the clarity of the image frame. Therefore, the importance feature of the ith sub-block in adjusting the clarity of the image frame is higher. Conversely, the smaller the value, the higher the consistency of the optical flow vector of the pixel in the ith sub-block, the more stable the optical flow vector, and other sub-blocks with higher confusion can be given priority when adjusting the clarity of the image frame.

[0064] The mean value of the modulus of the optical flow vectors of all pixels in the ith sub-block represents the speed of the pixels in the block. The larger the value, the faster the pixels in the ith sub-block move, and the more likely motion blur will occur, thus reducing the clarity of the image frame. Therefore, when adjusting the clarity of the image frame, this sub-block needs to be given priority, and the corresponding importance feature is also higher.

[0065] After respectively obtaining the complexity characteristics and importance characteristics of each sub-block based on the above steps, the weight of each sub-block in determining the brightness of the image frame can be obtained, that is, continue to perform the following steps.

[0066] S4: Calculate the weights of each sub-block.

[0067] Exemplarily, in the embodiments of the present invention, to determine the weights of each sub-block, the following relational expression can be specifically referred to: ; is the weight of the i-th sub-block, is the complexity feature of the i-th sub-block, is the importance feature of the i-th sub-block, is the exponential function with base e.

[0068] In the above formula, the higher the complexity feature and importance feature of the i-th sub-block, the higher the degree of influence of the sub-block on the clarity of the image frame, the greater the importance in calculating the brightness of the image frame, and the higher the corresponding weight.

[0069] represents the sum value of the importance degrees of all sub-blocks in the target ROI region. The larger this value is, the higher the importance degree of the target ROI region of the image frame.

[0070] After obtaining the corresponding weights based on the features of each sub-block in the target ROI region through the above steps, the brightness of each sub-block can be weighted based on the weights of each sub-block, so as to accurately obtain the brightness of the target ROI region.

[0071] S5: Weight the brightness values of each sub-block based on the weights of the sub-blocks in the target ROI region of the image frame to achieve the brightness adjustment of the night vision camera.

[0072] Exemplarily, in the embodiments of the present invention, weighting the brightness values of each sub-block based on the weights of the sub-blocks in the target ROI region of the image frame includes: taking the product of the weight of the sub-block in the target ROI region and the brightness value as the weighted value of the sub-block, and taking the weighted average value of all sub-blocks in the target ROI region of the image frame as the brightness value of the image frame.

[0073] Exemplarily, in the embodiments of the present invention, weighting the brightness values of each sub-block based on the weights of the sub-blocks in the target ROI region of the image frame to achieve the brightness adjustment of the night vision camera includes: obtaining a brightness gain parameter through the ratio of the brightness value of the image frame to a preset brightness value, and adjusting the brightness of the camera based on the brightness gain parameter.

[0074] Among them, adjusting the brightness of the camera based on the brightness gain parameter can be achieved through a proportional controller, an integral controller, and a derivative controller. The specific steps can be implemented by existing technologies, and the embodiments of the present invention will not elaborate herein.

[0075] It should be noted that the brightness gain parameter is not the larger the better. Excessive gain will cause an increase in image noise, and too low gain may result in insufficient enhancement of the brightness of the image frame, affecting the result of human eye observation. Therefore, when adjusting the brightness of the night vision camera, the brightness gain parameter threshold can also be set.

[0076] Among them, the brightness gain parameter threshold can be set to ; The brightness gain parameter threshold can be specifically set according to actual needs, and the embodiments of the present invention do not limit it too much here.

[0077] It can be understood that the video image sequence collected by the night vision camera contains important information. In order to ensure the security of the monitoring area of the night vision camera, the video image sequence of the night vision camera can be monitored for anomalies.

[0078] Exemplarily, in the embodiments of the present invention, after realizing the brightness adjustment of the night vision camera, it further includes: monitoring the video image sequence of the night vision camera for anomalies.

[0079] Exemplarily, when monitoring the video image sequence of the night vision camera for anomalies, the video image sequence can be input into a pre-trained anomaly monitoring model to obtain the anomaly monitoring result of the video image sequence of the night vision camera.

[0080] Specifically, when pre-training the anomaly monitoring model, a video data set containing normal and abnormal videos can be collected first, and the anomalies in the video data set can be manually labeled to obtain a labeled video data set; the labeled video data set is input into a neural network model for training to obtain an anomaly monitoring model that can be used for anomaly monitoring.

[0081] Among them, the neural network model can be a convolutional neural network, a recurrent neural network, etc., and can be specifically set according to actual needs.

[0082] Among them, the specific steps of monitoring the video image sequence of the night vision camera for anomalies can be implemented by existing technologies, and the embodiments of the present invention do not elaborate here.

[0083] It can be seen that in the embodiment of the present invention, when adjusting the brightness of the night vision camera, the union of the image frame in the video image sequence of the night vision camera and the ROI region of the previous image frame of the image frame can be used as the target ROI region of the image frame; the product of the gradient mean and the texture complexity of all pixel points in the sub-block of the target ROI region is normalized to obtain the complexity feature of the sub-block; the optical flow vector of the center point of the sub-block is used as the reference motion vector of the sub-block, and the cosine similarity entropy value of the optical flow vector of each pixel point and the reference motion vector is calculated; the importance feature of the sub-block is obtained according to the mean value of the modulus lengths of the optical flow vectors of all pixel points in the sub-block and the cosine similarity entropy value; the weight of the sub-block is obtained according to the complexity feature and the importance feature of the sub-block; the brightness values of each sub-block are weighted based on the weights of the sub-blocks in the target ROI region of the image frame to achieve the brightness adjustment of the night vision camera.

[0084] In this way, the embodiment of the present invention can realize the brightness adjustment of the night vision camera by obtaining the brightness performance of each sub-block in the ROI region of the image frame in the video image sequence of the night vision camera. In this process, the embodiment of the present invention takes into account that the brightness performances of different sub-blocks in the ROI region are different, so their importance degrees in calculating the brightness of the image frame are different; based on this, the embodiment of the present invention obtains the contribution degree of each sub-block to the brightness of the image frame by obtaining the complexity degree and the importance degree of each sub-block in the ROI region, effectively improving the accuracy of the brightness adjustment of the night vision camera.

[0085] The above are only the preferred embodiments of the present invention and are not intended to limit the present invention. Any modifications, equivalent replacements, improvements, etc. made within the principle of the present invention shall be included in the protection scope of the present invention.

Claims

1. A brightness adjustment method for a night vision camera, characterized in that Including: Taking the union of the image frame in the video image sequence of the night vision camera and the ROI region of the previous image frame of this image frame as the target ROI region of this image frame; Normalizing the product of the gradient mean and texture complexity of all pixel points in the sub-block of the target ROI region to obtain the complexity feature of this sub-block; Taking the optical flow vector of the center point of the sub-block as the reference motion vector of this sub-block, and calculating the cosine similarity entropy value between the optical flow vector of each pixel point and the reference motion vector; Obtaining the importance feature of this sub-block according to the mean value of the modulus lengths of the optical flow vectors of all pixel points in the sub-block and the cosine similarity entropy value; Obtaining the weight of the sub-block according to the complexity feature and importance feature of the sub-block; Weighting the brightness values of each sub-block based on the weights of the sub-blocks in the target ROI region of the image frame to achieve brightness adjustment of the night vision camera.

2. The brightness adjustment method of a night vision camera according to claim 1, characterized in that Before taking the union of the image frame in the video image sequence of the night vision camera and the ROI region of the previous image frame of this image frame as the target ROI region of this image frame, it further includes: Preprocessing the video image captured by the night vision camera to obtain each image frame of the video image sequence; dividing the target ROI region of the image frame into multiple sub-blocks based on a preset sub-block size.

3. A brightness adjustment method for a night vision camera according to claim 2, characterized in that, The method for obtaining the ROI region of the image frame includes: Using a Gaussian mixture model to perform background modeling on the video image sequence, extracting moving objects in the image frame through background subtraction, and taking the circumscribed rectangle of the moving object as the ROI region of this image frame.

4. A brightness adjustment method for a night vision camera according to claim 1, characterized in that, The method for obtaining the gradient of a pixel point includes: Calculating the gradient of the pixel point through a sobel operator.

5. A method for adjusting the brightness of a night vision camera according to claim 1, characterized in that, The way to obtain the texture complexity includes: Taking the entropy value of each gray level pair in the gray level co-occurrence matrix of the sub-block as the texture complexity of this sub-block.

6. The brightness adjustment method of a night vision camera according to claim 1, characterized in that, The weighting the brightness values of each sub-block based on the weights of the sub-blocks in the target ROI region of the image frame includes: Taking the product of the weight and the brightness value of the sub-block in the target ROI region as the weighted value of this sub-block, and taking the weighted mean value of all sub-blocks in the target ROI region of the image frame as the brightness value of this image frame; Among them, ; is the weight of the i-th sub-block, , are the complexity feature and importance feature of the i-th sub-block respectively, is the exponential function with base e.

7. A brightness adjustment method for a night vision camera according to claim 6, characterized in that, The weighting the brightness values of each sub-block based on the weights of the sub-blocks in the target ROI region of the image frame to achieve brightness adjustment of the night vision camera includes: Obtaining a brightness gain parameter through the ratio of the brightness value of the image frame to a preset brightness value, and adjusting the brightness of the camera based on the brightness gain parameter.

8. A brightness adjustment method for a night vision camera according to claim 1, characterized in that, After achieving brightness adjustment of the night vision camera, it further includes: Performing anomaly monitoring on the video image sequence of the night vision camera.

Images