Exposure adjusting method and device of moving point sensor and gun ball equipment

Abstract

The invention provides an exposure adjustment method and device of a moving point sensor and gun ball equipment, and relates to the technical field of video surveillance, and the method comprises the steps: determining an overlapping region corresponding to a target prediction region after the moving point sensor rotates along a target direction in a fixed point region of a fixed point sensor, the target prediction area is obtained after a moving point area of the moving point sensor is expanded; based on a current fixed-point parameter corresponding to the fixed-point sensor and a current moving-point parameter corresponding to the moving-point sensor, determining predicted brightness corresponding to the moving-point sensor, the current fixed-point parameter including overlapping area brightness corresponding to the overlapping area; determining an exposure prediction adjustment parameter of the moving point sensor based on the prediction brightness and the actual brightness of the moving point area; and performing exposure adjustment on the moving point sensor based on the exposure prediction adjustment parameter. According to the invention, the exposure prediction adjustment parameters corresponding to the moving point sensor can be accurately predicted, and the problem of image brightness oscillation when the moving point sensor rotates is optimized.

Description

Technical Field

[0001] This invention relates to the field of video surveillance technology, and in particular to an exposure adjustment method, device, and PTZ camera for a moving point sensor. Background Technology

[0002] Currently, the application scenarios for PTZ (PTZ camera) products in the security industry are becoming increasingly widespread. PTZ cameras have two sensors: a stationary sensor and a moving sensor. For example... Figure 1 As shown, the fixed-point sensor has a larger field of view, while the moving-point sensor has a smaller field of view. In addition, the fixed-point sensor can monitor a fixed area, while the moving-point sensor can rotate in directions such as up, down, left, and right, and monitor areas of interest to the user or perform intelligent tracking.

[0003] Because the monitoring area of ​​the PTZ camera is large and the environment is complex, certain scenarios may occur where the ambient brightness of the entire monitoring area is fixed but extremely uneven. Furthermore, since the fixed-point area corresponding to a stationary sensor is fixed, its Auto Exposure (AE) adjustment remains stable. However, for a moving-point sensor, the moving-point area is not fixed. Therefore, during the rotation of the moving-point sensor, the extremely uneven distribution of ambient brightness leads to significant AE adjustment during rotation, frequently causing brightness fluctuations in the image captured by the moving-point sensor. Summary of the Invention

[0004] This invention provides an exposure adjustment method, apparatus, and PTZ camera for a moving point sensor, which solves the problem in the prior art where the uneven distribution of ambient brightness during the rotation of the moving point sensor leads to large AE adjustment and frequent brightness fluctuations in the image captured by the moving point sensor. The invention achieves accurate prediction of the exposure adjustment direction and amplitude corresponding to the moving point sensor, thereby optimizing the image brightness fluctuation problem during the exposure adjustment process of the moving point sensor during rotation and ensuring a smooth transition of image brightness adjustment during rotation.

[0005] This invention provides an exposure adjustment method for a moving point sensor, comprising: In the fixed-point region of the fixed-point sensor, the target overlap region corresponding to the target prediction region after the moving-point sensor rotates along the target direction is determined. The target prediction region is obtained based on the expansion of the moving-point region of the moving-point sensor. Based on the current fixed-point parameters corresponding to the fixed-point sensor and the current moving-point parameters corresponding to the moving-point sensor, the predicted brightness corresponding to the moving-point sensor is determined, wherein the current fixed-point parameters include the brightness of the overlapping region corresponding to the target overlapping region. Based on the predicted brightness and the actual brightness of the moving point region, the exposure prediction adjustment parameters of the moving point sensor are determined; The exposure of the moving point sensor is adjusted based on the exposure prediction adjustment parameters.

[0006] According to the exposure adjustment method for a moving point sensor provided by the present invention, determining the predicted brightness corresponding to the moving point sensor based on the current fixed-point parameters corresponding to the fixed-point sensor and the current moving point parameters corresponding to the moving point sensor includes: Based on a preset brightness prediction function, the current fixed-point parameters, and the current moving-point parameters, the predicted brightness corresponding to the moving-point sensor is determined; the preset brightness prediction function is determined by function fitting based on the historical fixed-point parameters of the fixed-point sensor and the historical moving-point parameters of the moving-point sensor during the initial ambient brightness change process.

[0007] According to the exposure adjustment method of the moving point sensor provided by the present invention, the historical fixed point parameters include: initial historical fixed point parameters, first historical fixed point parameters and second historical fixed point parameters, and the historical moving point parameters include: initial historical moving point parameters, first historical moving point parameters and second historical moving point parameters. The determination of the preset brightness prediction function includes: Determine the initial historical fixed-point parameters of the fixed-point sensor under the initial ambient brightness, and the initial historical moving-point parameters of the moving-point sensor under the initial ambient brightness; Perform a first target operation on the initial ambient brightness, and determine the first historical fixed-point parameters and the first historical moving-point parameters based on the first judgment condition corresponding to the first target operation; A second target operation is performed on the target ambient brightness, and based on the second judgment condition corresponding to the second target operation, the second historical fixed-point parameter and the second historical moving-point parameter are determined, wherein the target ambient brightness is determined based on the initial ambient brightness after the first target operation is performed; The preset brightness prediction function is obtained by performing function fitting on the initial historical fixed-point parameters, the initial historical moving-point parameters, the first historical fixed-point parameters, the first historical moving-point parameters, the second historical fixed-point parameters, and the second historical moving-point parameters.

[0008] According to the exposure adjustment method for a moving point sensor provided by the present invention, the exposure prediction adjustment parameters include the exposure prediction adjustment direction and the exposure prediction adjustment magnitude; The step of determining the exposure prediction adjustment parameters of the moving point sensor based on the predicted brightness and the actual brightness of the moving point region includes: Determine the brightness difference between the predicted brightness and the actual brightness; The exposure prediction adjustment range is determined based on the absolute value of the brightness difference; If the absolute value of the brightness difference is greater than a first preset brightness threshold, the exposure prediction adjustment direction is determined based on the brightness difference.

[0009] According to the exposure adjustment method of the moving point sensor provided by the present invention, determining the exposure prediction adjustment range based on the absolute value of the brightness difference includes: The initial exposure adjustment range is determined based on the absolute value of the brightness difference, the rotation speed of the moving point sensor, and the field of view angle of the target direction. The exposure prediction adjustment range is determined based on the initial exposure adjustment range, the field of view, and the number of predictions for the current frame.

[0010] According to the exposure adjustment method of the moving point sensor provided by the present invention, determining the exposure prediction adjustment direction based on the brightness difference includes: If the brightness difference is greater than the second preset brightness threshold, the exposure prediction adjustment direction is determined to be light suppression, and the second preset brightness threshold is less than the first preset brightness threshold. If the brightness difference is less than or equal to the second preset brightness threshold, the exposure prediction adjustment direction is determined to be brightening.

[0011] According to the exposure adjustment method for a moving point sensor provided by the present invention, the step of adjusting the exposure of the moving point sensor based on the exposure prediction adjustment parameters includes: After the moving point sensor rotates again along the target direction, the first exposure adjustment after exposure prediction is performed on the moving point sensor based on the exposure prediction adjustment direction and the exposure prediction adjustment magnitude. Determine the latest overlap between the adjusted new target prediction region and the fixed-point region; Based on the latest overlap, the exposure feedback adjustment is performed on the moving point sensor.

[0012] According to the exposure adjustment method for a moving point sensor provided by the present invention, the step of adjusting the exposure feedback of the moving point sensor based on the latest overlap condition includes: If the latest overlap indicates that the new target prediction area overlaps with the fixed-point area, the exposure prediction adjustment range is restored to the default exposure adjustment range, and the exposure feedback adjustment of the moving point sensor is performed. If the latest overlap condition indicates that the target prediction area and the fixed point area do not overlap, the exposure feedback adjustment of the moving point sensor is performed based on the correctness of the adjusted exposure direction, or the correctness of the exposure direction adjustment and the position of the moving point. The correctness of the exposure direction adjustment is used to characterize the matching between the actual exposure adjustment direction and the exposure prediction adjustment direction after adjustment; the position of the moving point is used to characterize the overlap between the target area where the moving point sensor is located and the target prediction area after adjustment.

[0013] The present invention also provides an exposure adjustment device for a moving point sensor, comprising: The first determining module is used to determine, within the fixed-point region of the fixed-point sensor, the target overlapping region corresponding to the target prediction region after the moving-point sensor rotates along the target direction, wherein the target prediction region is obtained based on the expansion of the moving-point region of the moving-point sensor. The second determining module is used to determine the predicted brightness corresponding to the moving point sensor based on the current fixed point parameter corresponding to the fixed point sensor and the current moving point parameter corresponding to the moving point sensor. The current fixed point parameter includes the brightness of the overlapping area corresponding to the target overlapping area. The third determining module is used to determine the exposure prediction adjustment parameters of the moving point sensor based on the predicted brightness and the actual brightness of the moving point area; An exposure adjustment module is used to adjust the exposure of the moving point sensor based on the exposure prediction adjustment parameters.

[0014] The present invention also provides a ball-and-shoot device, including a fixed-point sensor and a moving-point sensor, and further including a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor executes the program to implement the exposure adjustment method of the moving-point sensor as described above.

[0015] The present invention provides an exposure adjustment method, device, and PTZ camera for a moving point sensor. In scenarios where the monitoring area has extremely uneven brightness distribution, when the fixed-point area corresponding to the fixed-point sensor overlaps with the target prediction area corresponding to the moving point sensor in the target direction, the overlapping target area is determined in the fixed-point area. Based on the current fixed-point parameters of the fixed-point sensor and the current moving point parameters of the moving point sensor, including the brightness of the overlapping target area, the exposure prediction adjustment parameters of the moving point sensor are accurately predicted. This optimizes the image brightness oscillation problem that occurs during the exposure adjustment process when the moving point sensor rotates, thereby ensuring a smooth transition of image brightness adjustment during the rotation of the moving point sensor and improving the accuracy of pedestrian detection and tracking based on the moving point sensor. Attached Figure Description

[0016] To more clearly illustrate the technical solutions in this invention or the prior art, the drawings used in the description of the embodiments or the prior art will be briefly introduced below. Obviously, the drawings described below are some embodiments of this invention. For those skilled in the art, other drawings can be obtained from these drawings without creative effort.

[0017] Figure 1 This is a schematic diagram of the monitoring field of view provided by existing PTZ (Pocket Camera) technology.

[0018] Figure 2 This is one of the flowcharts illustrating the exposure adjustment method for a moving point sensor provided in this embodiment of the invention.

[0019] Figure 3 This is a schematic diagram of the state of the moving point sensor rotating towards the target direction provided in the embodiment of the present invention.

[0020] Figure 4 This is the second schematic flowchart of the exposure adjustment method for a moving point sensor provided in this embodiment of the invention.

[0021] Figure 5 This is a flowchart illustrating the process of determining a preset brightness prediction function provided in an embodiment of the present invention.

[0022] Figure 6 This is a schematic diagram of the exposure adjustment device for the moving point sensor provided in an embodiment of the present invention.

[0023] Figure 7 This is a schematic diagram of the ball-and-shoot device provided in an embodiment of the present invention. Detailed Implementation

[0024] To make the objectives, technical solutions, and advantages of this invention clearer, the technical solutions of this invention will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some, not all, of the embodiments of this invention. All other embodiments obtained by those skilled in the art based on the embodiments of this invention without creative effort are within the scope of protection of this invention.

[0025] To address the problem in existing technologies where uneven ambient brightness distribution during the rotation of a moving point sensor leads to significant adjustments in the Auto Exposure (AE) setting and frequent brightness fluctuations in the image captured by the sensor, this invention provides a method for adjusting the exposure of a moving point sensor. Figure 2 This is one of the flowcharts illustrating the exposure adjustment method for a moving point sensor provided in this embodiment of the invention, such as... Figure 2As shown, the method includes the following steps 210 to 240.

[0026] Step 210: In the fixed-point region of the fixed-point sensor, determine the target overlap region corresponding to the target prediction region after the moving-point sensor rotates along the target direction. The target prediction region is obtained based on the expansion of the moving-point region of the moving-point sensor.

[0027] Optionally, the monitoring device integrating the moving point sensor and the fixed point sensor in the embodiments of the present invention can be a ball-and-shoot device. The embodiments of the present invention will be described in detail using a ball-and-shoot device as an example.

[0028] It should be noted that a fixed-point sensor can also be called a panoramic lens, while a moving-point sensor can be called a detail lens. Through this dual-lens design of "panoramic + detail," it is possible to simultaneously achieve large-scale panoramic monitoring and precise capture of local details. Both fixed-point and moving-point sensors are photosensitive chips or devices that convert measurement data into useful signals.

[0029] It should be noted that the fixed-point area can be represented by S. f Indicates; the region of the moving point can be represented by S. m This indicates that the target direction is any one of the four predicted directions: up, down, left, and right. The predicted area is the region where the moving point region is expanded according to different predicted directions; that is, each of the four predicted directions (up, down, left, and right) corresponds to an expanded area. The expanded area corresponding to the up direction can be represented by S. m上 Indicates; the corresponding extended area below can be represented by S. m下 Indicates; the corresponding extended region on the left can be represented by S. m左 Indicates; the corresponding extended region on the right can be represented by S. m右 This indicates that the area of ​​each predicted region is the same as the area of ​​the moving point region.

[0030] The target overlap region refers to the overlapping area in the target direction defined within the fixed-point region when the target prediction region and the fixed-point region partially or completely overlap. After determining the target overlap region, the brightness of this overlapping region can be determined. This brightness is the average light intensity of the fixed-point sensor within the overlapping region, which can be represented by Luma. 定 express.

[0031] During the rotation of the moving point sensor along the target direction, if the fixed-point region corresponding to the fixed-point sensor and the moving point region corresponding to the moving point sensor do not overlap, it indicates that the AE adjustment of both the fixed-point and moving point sensors is in a stable state. At this time, all four extended regions may overlap with the fixed-point region, or none may overlap with the fixed-point region, or some extended regions may overlap with the fixed-point region. If the fixed-point region corresponding to the fixed-point sensor and the moving point region corresponding to the moving point sensor overlap, the overlapping areas of all extended regions with the fixed-point regions and the current brightness of each overlapping area can be determined. Then, from all overlapping areas, the target prediction area of ​​the moving point region in the target direction is determined, and then the target overlapping area where the target prediction area overlaps with the fixed-point region is determined in the fixed-point region. Finally, from all the current overlapping area brightness, the brightness of the overlapping area corresponding to the target overlapping area is determined, in order to accurately determine the prediction brightness corresponding to the moving point sensor later.

[0032] Optionally, the PTZ camera can control the moving point sensor to rotate along the target direction, enabling accurate and stable capture of local details within the monitored area. For example, the PTZ camera controls the moving point sensor to rotate along the target direction according to a rotation speed. Here, the rotation speed refers to the rate of rotation, which can be... express.

[0033] Step 220: Based on the current fixed-point parameters corresponding to the fixed-point sensor and the current moving-point parameters corresponding to the moving-point sensor, determine the predicted brightness corresponding to the moving-point sensor. The current fixed-point parameters include the brightness of the overlapping area corresponding to the target overlapping area.

[0034] Specifically, the current fixed-point parameters characterize the performance and state of the fixed-point sensor under specific environmental or conditional conditions. The current moving-point parameters describe the performance and state of the moving-point sensor under specific environmental or conditional conditions. After determining the brightness of the overlapping area, the PTZ camera can determine and record the current fixed-point parameters corresponding to the fixed-point sensor and the current moving-point parameters corresponding to the moving-point sensor. It then calculates the predicted brightness corresponding to the moving-point sensor based on these current fixed-point and moving-point parameters. Because these current fixed-point and moving-point parameters are comprehensive, the accuracy of the final predicted brightness is high.

[0035] It should be noted that since the brightness of the overlapping area is the average light brightness of the fixed-point sensor within the target overlapping area, the brightness of the overlapping area belongs to the current fixed-point parameter corresponding to the fixed-point sensor.

[0036] Further, determining the predicted brightness corresponding to the moving point sensor based on the current fixed-point parameters corresponding to the fixed-point sensor and the current moving point parameters corresponding to the moving point sensor includes: Based on a preset brightness prediction function, the current fixed-point parameters, and the current moving-point parameters, the predicted brightness corresponding to the moving-point sensor is determined; the preset brightness prediction function is determined by function fitting based on the historical fixed-point parameters of the fixed-point sensor and the historical moving-point parameters of the moving-point sensor during the initial ambient brightness change process.

[0037] Specifically, after determining the current fixed-point parameters and the current fixed-point parameters, the current fixed-point parameters and the current fixed-point parameters can be substituted into the preset brightness prediction function to calculate the predicted brightness corresponding to the moving point sensor. Since the current fixed-point parameters and the current moving point parameters are relatively complete, the predicted brightness determined based on the current fixed-point parameters and the current moving point parameters in combination with the preset brightness prediction function is more accurate.

[0038] Furthermore, the current fixed-point parameters include: fixed-point shutter parameters, fixed-point gain parameters, and overlapping region brightness. The fixed-point shutter parameters can be specified using the shutter speed parameter. 定 Indicated; the fixed-point gain parameter can be represented by Gain. 定 This can be represented as: the current moving point parameters, which may include the moving point shutter parameter and the moving point gain parameter. The moving point shutter parameter can be represented as: Shutter. 动 Indicated; the dynamic point gain parameter can be represented by Gain. 动 express.

[0039] In addition, the preset brightness prediction function can be Luma. 预 =F(Shutter) 定 Gain 定 Luma 定 Shutter 动 Gain 动 ) indicates that, among them, Luma 预 This represents the predicted brightness. The initial ambient brightness can be the ambient brightness of the laboratory lights, and can be represented by lux0.

[0040] It should be noted that the timing of determining the current fixed-point parameter and the current moving-point parameter is not limited in the embodiments of the present invention. The current fixed-point parameter can be determined first, and then the current moving-point parameter can be determined. Alternatively, the current moving-point parameter can be determined first, and then the current fixed-point parameter can be determined. Furthermore, the current fixed-point parameter and the current moving-point parameter can be determined simultaneously.

[0041] Furthermore, the historical fixed-point parameters include: initial historical fixed-point parameters, first historical fixed-point parameters, and second historical fixed-point parameters, and the historical moving-point parameters include: initial historical moving-point parameters, first historical moving-point parameters, and second historical moving-point parameters.

[0042] It should be noted that the number of each of the first historical fixed-point parameter, the first historical moving-point parameter, the second historical fixed-point parameter, and the second historical moving-point parameter is at least one, and the number is the same.

[0043] Furthermore, the determination of the preset brightness prediction function includes: Determine the initial historical fixed-point parameters of the fixed-point sensor under the initial ambient brightness, and the initial historical moving-point parameters of the moving-point sensor under the initial ambient brightness; Perform a first target operation on the initial ambient brightness, and determine the first historical fixed-point parameters and the first historical moving-point parameters based on the first judgment condition corresponding to the first target operation; A second target operation is performed on the target ambient brightness, and based on the second judgment condition corresponding to the second target operation, the second historical fixed-point parameter and the second historical moving-point parameter are determined, wherein the target ambient brightness is determined based on the initial ambient brightness after the first target operation is performed; The preset brightness prediction function is obtained by performing function fitting on the initial historical fixed-point parameters, the initial historical moving-point parameters, the first historical fixed-point parameters, the first historical moving-point parameters, the second historical fixed-point parameters, and the second historical moving-point parameters.

[0044] Specifically, after determining the initial historical fixed-point parameters of the fixed-point sensor under the initial ambient brightness and the initial historical moving-point parameters of the moving-point sensor under the initial ambient brightness, the preset brightness prediction function can be obtained by fitting it using either of the following two methods.

[0045] Method 1: During the process of successively performing the first target operation on the initial ambient brightness, determine whether the first ambient brightness corresponding to the i-th first target operation meets the first target judgment condition. If it does, determine the first historical fixed-point parameters of the fixed-point sensor and the first historical moving-point parameters of the moving-point sensor under the first ambient brightness. Continue to successively perform the first target operation until the first ambient brightness corresponding to the (n+1)-th first target operation does not meet the first target judgment condition. At this point, determine that the number of times the first target operation has been performed is n, and the first ambient brightness corresponding to the n-th first target operation is the target ambient brightness, which is determined based on the initial ambient brightness. It should be noted that each time the first target judgment condition is met, the first historical fixed-point parameters and the first historical moving-point parameters are obtained once. At this time, n first historical fixed-point parameters and n first historical moving-point parameters will be obtained.

[0046] During the process of successively performing the second target operation on the target ambient brightness, it is determined whether the current number of times the second target operation is performed meets the second target judgment condition. This second target judgment condition is related to the number of times the first target operation is performed, n. If the second target judgment condition is not met, the second historical fixed-point parameters of the fixed-point sensor and the second historical moving-point parameters of the moving-point sensor under the second ambient brightness corresponding to the current number of second target operations are determined. The second target operation is then performed successively until the number of times the second target operation is performed meets the second target judgment condition. It should be noted that each time the second target judgment condition is not met, the second historical fixed-point parameters and the second historical moving-point parameters are acquired. After performing the second target operation n times, n second historical fixed-point parameters and n second historical moving-point parameters will be acquired.

[0047] Method 2: During the process of successively performing the first target operation on the initial ambient brightness, determine whether the third ambient brightness corresponding to the j-th first target operation meets the first target judgment condition. If it does, determine the first historical fixed-point parameters of the fixed-point sensor and the first historical moving-point parameters of the moving-point sensor under the third ambient brightness. Simultaneously, perform the second target operation on the target ambient brightness, which is the third ambient brightness corresponding to the j-th first target operation, and determine whether the current number of the second target operation meets the second target judgment condition, which is related to the number of executions corresponding to the j-th first target operation. If it does, determine the second historical fixed-point parameters of the fixed-point sensor and the second historical moving-point parameters of the moving-point sensor under the third ambient brightness. Repeat the aforementioned steps, that is, continue to successively perform the first target operation until the third ambient brightness corresponding to the (n+1)-th first target operation does not meet the first target judgment condition, and determine the fourth ambient brightness corresponding to the n-th second target operation, and then determine the second historical fixed-point parameters of the fixed-point sensor and the second historical moving-point parameters of the moving-point sensor under the fourth ambient brightness.

[0048] It should be noted that in Method 2, the first target operation and the second target operation are executed alternately, and each target operation is executed the same number of times. That is, each execution of the first target operation results in one judgment and the acquisition of the first historical fixed-point parameter and the first historical moving-point parameter. Then, the second target operation is executed, and a corresponding judgment is performed, simultaneously acquiring the second historical fixed-point parameter and the second historical moving-point parameter. Ultimately, n first historical fixed-point parameters, n first historical moving-point parameters, n second historical fixed-point parameters, and n second historical moving-point parameters can be obtained.

[0049] It should be noted that, regardless of whether it is method 1 or method 2, if the first target operation is an increase operation and the second target operation is a decrease operation, the first target judgment condition becomes the first judgment condition, and the second target judgment condition becomes the second judgment condition. Conversely, if the first target operation is a decrease operation and the second target operation is an increase operation, the first target judgment condition becomes the second judgment condition, and the second target judgment condition becomes the first judgment condition.

[0050] In addition, the fitting process of the above-mentioned preset brightness prediction function adopts the principle of equal exposure, which can convert the exposure information corresponding to the fixed-point sensor and the moving-point sensor respectively, thereby eliminating the influence caused by the use of different types of sensors or lenses by the fixed-point sensor and the moving-point sensor, and effectively realizing the conversion of exposure information.

[0051] The principle of equal exposure refers to the fact that in the same brightness environment, although the shutter parameters, gain parameters, and average brightness of the captured images of different PTZ cameras are different, the brightness of the current environment can be estimated from these three parameters (i.e., shutter parameters, gain parameters, and average brightness) of the same PTZ camera. Based on this principle, the exposure information of different PTZ cameras can be calibrated in the same ambient brightness, thereby enabling the conversion of exposure information of different PTZ cameras.

[0052] Step 230: Based on the predicted brightness and the actual brightness of the moving point area, determine the exposure prediction adjustment parameters of the moving point sensor.

[0053] Specifically, after determining the predicted brightness and the actual brightness of the moving point area, the exposure prediction adjustment parameters of the moving point sensor in the next frame can be determined more accurately based on the predicted brightness and the actual brightness. The whole process effectively avoids the blindness and uncertainty that may exist in traditional exposure adjustment, making the exposure adjustment more precise, so as to prepare for accurate exposure adjustment of the moving point sensor in the future.

[0054] It should be noted that the actual brightness of the moving point area refers only to the light brightness of the current moving point area corresponding to the moving point sensor.

[0055] Furthermore, the exposure prediction adjustment parameters include the exposure prediction adjustment direction and the exposure prediction adjustment magnitude.

[0056] Among them, the exposure prediction adjustment direction refers to the control direction of the moving point sensor on the trend of image brightness change in the PTZ device when performing AE adjustment, which can be represented by Dir. 预 The exposure prediction adjustment range, also known as the exposure prediction adjustment step size, refers to the step size by which the moving point sensor adjusts the exposure each time. It can be expressed as Step. 预 express.

[0057] It should be noted that the embodiments of the present invention do not limit the timing of determining the exposure prediction adjustment direction and the exposure prediction adjustment magnitude.

[0058] Further, determining the exposure prediction adjustment parameters of the moving point sensor based on the predicted brightness and the actual brightness of the moving point region includes: Determine the brightness difference between the predicted brightness and the actual brightness; The exposure prediction adjustment range is determined based on the absolute value of the brightness difference; If the absolute value of the brightness difference is greater than a first preset brightness threshold, the exposure prediction adjustment direction is determined based on the brightness difference.

[0059] Specifically, after obtaining the predicted brightness and the actual brightness, the predicted brightness is subtracted from the actual brightness to obtain the brightness difference, and then the absolute value of the brightness difference is calculated. Then, based on the absolute value, the exposure prediction adjustment range is calculated, and the relationship between the absolute value and the first preset brightness threshold is determined: if the absolute value is less than or equal to the first preset brightness threshold, it means that the difference between the predicted brightness and the actual brightness is small, and there is no need to adjust the AE of the moving point sensor; if the absolute value is greater than the first preset brightness threshold, it means that the difference between the predicted brightness and the actual brightness is large, and the exposure prediction adjustment direction is calculated based on the above brightness difference, so as to prepare for subsequent exposure adjustment of the moving point sensor.

[0060] It should be noted that the actual brightness can be measured using Luma. m The brightness difference can be represented as Luma. 预 -Luma m The absolute value of the brightness difference can be represented by ∆Luma, ∆Luma = .

[0061] It should be noted that the first preset brightness threshold can be the tolerance precision of the AE brightness adjustment, which can be represented by α. This first preset brightness threshold can be set before the PTZ camera leaves the factory or it can be user-defined; this embodiment of the invention does not limit this.

[0062] Further, determining the exposure prediction adjustment range based on the absolute value of the brightness difference includes: The initial exposure adjustment range is determined based on the absolute value of the brightness difference, the rotation speed of the moving point sensor, and the field of view angle of the target direction. The exposure prediction adjustment range is determined based on the initial exposure adjustment range, the field of view, and the number of predictions for the current frame.

[0063] Specifically, in determining the exposure prediction adjustment range, the absolute value, rotation speed, and field of view are used as the basis, combined with the moving-point AE algorithm, to more comprehensively assess the exposure adjustment requirements, thus obtaining a more accurate initial exposure adjustment range. Then, based on this initial exposure adjustment range, field of view, and the current range prediction count, the exposure prediction adjustment range is calculated, and the accuracy of this exposure prediction adjustment range is also relatively high. The calculation formula for the exposure prediction adjustment range is shown in equation (1), which is:

[0064] in, β represents the conversion coefficient; β represents the field of view, which determines the range of the image captured by the moving point sensor; Step AE This indicates the initial exposure adjustment range; p represents the prediction count for the current frame, which can be a count of the predicted frames. For example, if p=1 when predicting the current frame image, the count starts again from 1 after re-prediction. The larger ∆Luma is... The bigger, The smaller, the better The larger it is.

[0065] It should be noted that the dynamic AE algorithm is a mechanism that automatically adjusts exposure and gain based on the intensity of ambient light to prevent overexposure or underexposure. The dynamic AE algorithm described above, combined with the amplitude formula, can obtain a highly accurate exposure prediction and adjustment amplitude, possessing strong versatility.

[0066] Further, determining the exposure prediction adjustment direction based on the brightness difference includes: If the brightness difference is greater than the second preset brightness threshold, the exposure prediction adjustment direction is determined to be light suppression, and the second preset brightness threshold is less than the first preset brightness threshold. If the brightness difference is less than or equal to the second preset brightness threshold, the exposure prediction adjustment direction is determined to be brightening.

[0067] Specifically, "light reduction" refers to decreasing the brightness or exposure of the data from the moving point sensor to make overly bright areas in the data acquired by the sensor darker or more detailed. "Lightening" refers to increasing the brightness or exposure of the data from the moving point sensor to make darker areas in the data acquired by the sensor brighter or more detailed. In determining the exposure prediction adjustment direction based on the brightness difference, this brightness difference can be compared with a second preset brightness threshold: if the brightness difference is greater than the second preset brightness threshold, it indicates that the predicted brightness is greater than the actual brightness, and in this case, light reduction should be determined as the exposure prediction adjustment direction; if the brightness difference is less than or equal to the second preset brightness threshold, it indicates that the predicted brightness is less than or equal to the actual brightness, and in this case, brightening should be determined as the exposure prediction adjustment direction to ensure the accuracy of the exposure prediction adjustment direction.

[0068] Optionally, the second preset brightness threshold can be set before the PTZ camera leaves the factory or it can be user-defined; this embodiment of the invention does not limit this. Preferably, the value of the second preset brightness threshold is 0.

[0069] Step 240: Adjust the exposure of the moving point sensor based on the exposure prediction adjustment parameters.

[0070] Specifically, after determining the exposure prediction adjustment parameters, the dynamic sensor can be adjusted at least once based on these parameters to optimize the image brightness fluctuation problem that occurs during the exposure adjustment process when the dynamic sensor is rotating.

[0071] Further, the step of adjusting the exposure of the moving point sensor based on the exposure prediction adjustment parameters includes: After the moving point sensor rotates again along the target direction, the first exposure adjustment after exposure prediction is performed on the moving point sensor based on the exposure prediction adjustment direction and the exposure prediction adjustment magnitude. Determine the latest overlap between the adjusted new target prediction region and the fixed-point region; Based on the latest overlap, the exposure feedback adjustment is performed on the moving point sensor.

[0072] Specifically, after determining the exposure prediction adjustment direction and the exposure prediction adjustment magnitude, and with the moving point sensor continuing to rotate along the target direction, the first exposure adjustment after exposure prediction can be performed on the moving point sensor based on the predicted exposure prediction adjustment direction and magnitude for the next frame. This quickly adjusts the exposure of the moving point sensor to near-optimal levels, ensuring that the captured image has moderate brightness and clear details. Simultaneously, to optimize the AE adjustment of the moving point sensor in real time, a new target prediction area and the latest overlap between the new target prediction area and the fixed-point area can be determined in real time. This latest overlap indicates whether the new target prediction area overlaps with the fixed-point area. Subsequently, based on the latest overlap, exposure feedback adjustment can be performed on the moving point sensor to further fine-tune the exposure settings to adapt to different lighting conditions and target motion states, improving the dynamic range and sharpness of the image.

[0073] Furthermore, the exposure feedback adjustment of the moving point sensor based on the latest overlap condition includes: If the latest overlap indicates that the new target prediction area overlaps with the fixed-point area, the exposure prediction adjustment range is restored to the default exposure adjustment range, and the exposure feedback adjustment of the moving point sensor is performed. If the latest overlap condition indicates that the target prediction area and the fixed point area do not overlap, the exposure feedback adjustment of the moving point sensor is performed based on the correctness of the adjusted exposure direction, or the correctness of the exposure direction adjustment and the position of the moving point. The correct exposure direction adjustment status is used to characterize the matching status between the actual exposure adjustment direction and the exposure prediction adjustment direction; the correct rotation status of the moving point is used to characterize the overlap between the target area where the moving point sensor is located and the target prediction area after adjustment.

[0074] Specifically, after the initial exposure adjustment following exposure prediction for the moving point sensor, if the latest overlap condition indicates that the new target prediction area overlaps with the fixed-point area, the exposure adjustment range is restored to the default exposure adjustment range. Then, combined with the exposure adjustment direction, exposure feedback adjustment is performed on the moving point sensor. This ensures that even in complex or uncertain scenes, the exposure settings do not deviate too much, thus maintaining the basic sharpness and recognizability of the image. If the latest overlap condition indicates that the new target prediction area does not overlap with the fixed-point area, the correctness of the adjusted exposure direction is determined; that is, whether the actual exposure adjustment direction matches the exposure prediction adjustment direction during the initial exposure adjustment after exposure prediction. If the actual exposure adjustment direction does not match the exposure prediction adjustment direction, i.e., the correct exposure direction adjustment indicates incorrect adjustment, the exposure prediction adjustment direction and exposure prediction adjustment range are recalculated, and the exposure adjustment is performed again. If the actual exposure adjustment direction matches the exposure prediction adjustment direction, i.e., the exposure direction adjustment is correct, the position of the moving point sensor is determined. Specifically, the overlap between the target area and the target prediction area after adjustment is assessed. If the overlap is greater than or equal to a first preset threshold, the moving point sensor is considered to have rotated to the correct position. In this case, the next frame can be adjusted using the recalculated exposure prediction adjustment parameters for exposure correction. If the overlap is less than the first preset threshold, the moving point sensor is considered not to have rotated to the correct position. In this case, the exposure prediction adjustment parameters calculated in the previous frame can be used for exposure correction. This real-time feedback-based adjustment method can more accurately adapt to target movement and lighting changes, ensuring the accuracy and effectiveness of exposure adjustment.

[0075] Optionally, the first preset threshold can be set based on experience, for example, the first preset threshold can be 90%, 93%, 95%, etc.

[0076] Furthermore, after step 240, the method may further include: upon detecting that the moving point sensor has rotated to a preset position, the PTZ camera controls the moving point sensor to stop rotating. The preset position may be set before the PTZ camera leaves the factory or it may be user-defined; this embodiment of the invention does not limit this.

[0077] During the continuous rotation of the moving point sensor towards the target direction, the target area where the moving point sensor is located can be detected in real time, that is, the current position of the moving point sensor. If the current position does not coincide with the preset position, it means that the moving point sensor has not been rotated to the preset position. At this time, the moving point sensor can continue to rotate towards the target direction until the current position coincides with the preset position. If the current position coincides with the preset position, it means that the moving point sensor has rotated to the preset position. At this time, the moving point sensor can be directly controlled to stop rotating. At the same time, it also means that the AE adjustment of the moving point sensor in the target direction has stabilized, and the entire process of the moving point sensor rotating towards the target direction has ended.

[0078] For example, Figure 3 This is a schematic diagram of the state of the moving point sensor rotating towards the target direction provided in an embodiment of the present invention, as shown below. Figure 3 As shown, the embodiments of the present invention will be further explained with the target direction being to the right as an example.

[0079] When the fixed-point region corresponding to the fixed-point sensor and the moving-point region corresponding to the moving-point sensor are in state 1, the AE adjustment of both the fixed-point sensor and the moving-point sensor is in a stable state. At this time, all four extended regions corresponding to the moving-point region do not overlap with the fixed-point region.

[0080] The moving point sensor starts rotating to the right from state 1. The corresponding extended area to the right is the target prediction area. While the target prediction area and the moving point area are in state 2, the moving point sensor continues to rotate to the right until the fixed point area and the moving point area are in state 3, at which point they overlap. As the moving point sensor continues to rotate, the fixed point area and the moving point area are in state 4. At this point, the overlap between the fixed point area and the moving point area gradually decreases, while the fixed point area and the target prediction area no longer overlap. With the moving point sensor continuing to rotate, it transitions from state 4 to state 5. At this point, all four extended areas corresponding to the fixed point area do not overlap with the fixed point area, and the current position of the moving point sensor coincides with the preset position.

[0081] For example, Figure 4 This is a second schematic flowchart of the exposure adjustment method for a moving point sensor provided in this embodiment of the invention, as shown below. Figure 3 and Figure 4 As shown, the method includes the following steps.

[0082] Step 3.1: Determine that the fixed-point region corresponding to the fixed-point sensor and the moving-point region corresponding to the moving-point sensor are in state 1. At this time, the AE adjustment of both the fixed-point sensor and the moving-point sensor is in a stable state.

[0083] Step 3.2: The moving point sensor begins to rotate to the right according to the rotation speed. If any of the four extended regions corresponding to the moving point sensor overlap with the fixed point region, calculate the area of ​​the current overlapping region between each of the four extended regions and the fixed point region.

[0084] Step 3.3: Use the fixed-point statistical information to calculate the average brightness of the current overlapping area corresponding to the fixed-point area for each of the four extended areas, i.e., the brightness of the current overlapping area. For areas without overlap, there is no need to calculate the brightness of the current overlapping area. The fixed-point statistical information typically refers to statistical data or information collected at a specific location (i.e., the fixed-point area), which describes the position and size of pixels within the fixed-point area.

[0085] Step 3.4: Since the moving point sensor actually rotates to the right, at this point, only the brightness of the overlapping area between the corresponding extended area and the fixed point area on the right needs to be calculated. That is, the brightness of the overlapping area between the target prediction area and the target overlapping area corresponding to the fixed point area. It should be noted that in the actual calculation process, it is necessary to calculate the current overlapping area brightness corresponding to each of the four extended areas and the fixed point area, and then determine which direction's current overlapping area brightness should be used as the overlapping area brightness for the current frame image based on the actual target rotation direction for subsequent processing and use.

[0086] Step 3.5: Record the current fixed-point parameters (Shutter) at this time. 定 Gain 定 Luma 定 ) and current moving point parameters (Shutter) 动 Gain 动 ).

[0087] Step 3.6: Set the current fixed-point parameter (Shutter) 定 Gain 定 Luma 定 ) and current moving point parameters (Shutter) 动 Gain 动 Substitute the values ​​into the preset brightness prediction function to obtain the predicted brightness.

[0088] Step 3.7: Determine the brightness difference Luma based on the predicted brightness and the actual brightness of the moving point area. 预 -Luma m The absolute value of the difference between the brightness and the absolute value of the brightness, ∆Luma. A comparison is made between the absolute value of ∆Luma and the first preset brightness threshold α. If ∆Luma... If α, then proceed to step 3.8; if ∆Luma>α, then proceed to step 3.9.

[0089] Step 3.8: No AE adjustment is required for the moving point sensor.

[0090] Step 3.9: Calculate the brightness difference value Luma. 预 -Luma m Second preset brightness threshold Make a judgment if Luma 预 -Luma m If >0, then light suppression is determined as the exposure prediction adjustment direction; if Luma 预 -Luma m If the value is less than 0, then brightening will be determined as the direction of exposure prediction adjustment.

[0091] Step 3.10: Determine the initial exposure adjustment range based on the absolute value of the brightness difference, the rotation speed of the moving point sensor, and the field of view angle rotating towards the target direction; then determine the exposure prediction adjustment range based on the initial exposure adjustment range, the field of view angle, and the current range prediction count.

[0092] Step 3.11: Perform the first exposure adjustment on the moving point sensor after exposure prediction based on the exposure prediction adjustment direction and exposure prediction adjustment range.

[0093] Step 3.12: The moving point sensor continues to rotate to the right to determine in real time whether the new target prediction area and the fixed point area are in the rightmost target state of state 3, that is, to determine whether the new target prediction area overlaps with the fixed point area: if it is in the target state, then proceed to step 3.13; if it is not in the target state, then restore the exposure prediction adjustment range to the default exposure adjustment range.

[0094] Step 3.13: Determine if the exposure direction adjustment is correct. If the exposure direction adjustment is correct, the adjustment is incorrect. Return to step 3.4 and recalculate the exposure prediction adjustment direction and exposure prediction adjustment range. If the exposure direction adjustment is correct, the adjustment is correct. Then proceed to step 3.14.

[0095] Step 3.14: Determine whether the target area where the moving point sensor is located has rotated to the target prediction area after rotation. If it has rotated to the correct position, repeat step 3.4 to perform the next round of exposure adjustment for the moving point sensor. If it has not rotated to the correct position, use the exposure prediction adjustment direction and exposure prediction adjustment magnitude calculated in the current frame to adjust the exposure of the moving point sensor in the next frame of exposure adjustment.

[0096] Step 3.15: When the moving point sensor is detected to have rotated to the preset position, control the moving point sensor to stop rotating.

[0097] Step 3.16: Adjust the AE of the moving point sensor to a stable state.

[0098] For example, Figure 5This is a flowchart illustrating the process of determining a preset brightness prediction function according to an embodiment of the present invention. Figure 5 As shown, the method includes the following steps.

[0099] Step 4.1: Determine the AE adjustment parameters for the fixed-point sensor and the moving-point sensor of the PTZ camera. Install the PTZ camera in a laboratory environment where the ambient brightness can be adjusted uniformly and linearly. n=0, where n represents the number of times the ambient brightness in the laboratory increases from its lowest level.

[0100] Step 4.2: Adjust the laboratory lights to achieve an initial ambient brightness of 1 lux. min After the AE (Adaptive Acceleration) of the fixed-point sensor and the moving-point sensor has stabilized, record a set of data for each. In this set of data, the initial historical fixed-point parameters of the fixed-point sensor are (Shutter...). fu_0 Gain fu_0 Luma fu_0 The initial historical motion parameters of the motion sensor are (Shutter) mu_0 Gain mu_0 Luma mu_0 ).

[0101] Among them, lux min This represents the lowest brightness of the laboratory environment during the fitting process.

[0102] Shutter fu_0 Gain fu_0 Luma fu_0 These represent the initial historical fixed-point shutter parameters, initial historical fixed-point gain parameters, and initial historical fixed-point average brightness of the fixed-point sensor during the process of increasing brightness in the laboratory environment, at the lowest brightness.

[0103] Shutter mu_0 Gain mu_0 Luma mu_0 These represent the initial historical moving point shutter parameters, initial historical moving point gain parameters, and initial historical moving point average brightness of the moving point sensor during the process of increasing laboratory ambient brightness, respectively, at the lowest brightness.

[0104] Step 4.3, n++, then check if condition 1 is satisfied: lux min +n×∆lux≤lux max If condition 1 is met, the ambient brightness is gradually increased to lux. min +n×∆lux, then, after the AE adjustment stabilizes, record a set of data. In this set of data, the first historical fixed-point parameter of the fixed-point sensor is (Shutter) fu_n Gainfu_n Luma fu_n The first historical motion point parameter of the motion sensor is (Shutter) mu_n Gain mu_n Luma mu_n ).

[0105] Here, ∆lux represents the adjustment range of the laboratory ambient brightness.

[0106] lux max This represents the highest brightness of the laboratory environment during the fitting process.

[0107] Shutter fu_n Gain fu_n Luma fu_n These represent the process of increasing the ambient brightness in the laboratory, where the ambient brightness is in lux. min When +n×∆lux, the first historical fixed-point shutter parameters, the first historical fixed-point gain parameters, and the first historical fixed-point average brightness of the fixed-point sensor.

[0108] Shutter mu_n Gain mu_n Luma mu_n These represent the process of increasing the ambient brightness in the laboratory, where the ambient brightness is in lux. min When +n×∆lux, the first historical moving point shutter parameters, the first historical moving point gain parameters, and the first historical moving point average brightness of the moving point sensor.

[0109] Step 4.4: Repeat the operation in step 1.3 until judgment condition 1 is no longer met, then execute step 4.5. At this time, the historical fixed-point parameters and historical moving-point parameters of the n+1 groups of environmental brightness improvement processes are recorded respectively.

[0110] Step 4.5, n--: Based on the target ambient brightness after the nth increase operation, slowly reduce the laboratory ambient brightness to lux. min +n×∆lux, after the AE adjustment stabilizes, record another set of data. In this set of data, the current historical positioning parameters of the fixed-point sensor are (Shutter) fd_n Gain fd_n Luma fd_n The current historical motion parameters of the motion sensor are (Shutter) md_n Gain md_n Luma md_n ).

[0111] Shutter fd_n Gain fd_n Luma fd_nThese represent the process of decreasing brightness in the laboratory environment, with brightness in lux. min When +n×∆lux, the current historical fixed-point shutter parameters, current historical fixed-point gain parameters, and current historical fixed-point average brightness of the fixed-point sensor.

[0112] Shutter md_n Gain md_n Luma md_n These represent the process of decreasing brightness in the laboratory environment, with brightness in lux. min When +n×∆lux, the current historical moving point shutter parameters, current historical moving point gain parameters, and current historical moving point average brightness of the moving point sensor.

[0113] Step 4.6: Determine if condition 2 is met: Is n equal to 0? If condition 2 is not met, repeat step 4.5 until condition 2 is met; if it is met, proceed to step 4.7.

[0114] Step 4.7: Reduce the ambient brightness of the laboratory environment to lux. min After the AE adjustment stabilizes, record one set of data. In this set of data, the second historical positioning parameter of the positioning sensor is (Shutter). fd_0 Gain fd_0 Luma fd_0 The second historical motion point parameter of the motion point sensor is (Shutter) md_0 Gain md_0 Luma md_0 At this point, we obtain the historical fixed-point parameters and historical moving-point parameters of the n+1 sets of ambient brightness reduction process.

[0115] Step 4.8: Based on the historical fixed-point parameters and historical moving-point parameters during the n+1 sets of ambient brightness enhancement processes, and the historical fixed-point parameters and historical moving-point parameters during the n+1 sets of ambient brightness reduction processes, perform function fitting to obtain the preset brightness prediction function. The preset brightness prediction function obtained by fitting is Luma. 预 =F(Shutter 定 Gain 定 Luma 定 Shutter 动 Gain 动 ).

[0116] The exposure adjustment method for a moving point sensor provided in this invention addresses the scenario where the monitored area has extremely uneven brightness distribution. When the fixed-point area corresponding to the fixed-point sensor overlaps with the target prediction area corresponding to the moving point sensor in the target direction, the method determines the target overlap area within the fixed-point area. Based on the current fixed-point parameters of the fixed-point sensor and the current moving point parameters of the moving point sensor, including the brightness of the overlap area, the method accurately predicts the exposure prediction adjustment parameters of the moving point sensor. This optimizes the image brightness oscillation problem that occurs during the exposure adjustment process when the moving point sensor rotates, thereby ensuring a smooth transition of image brightness adjustment during the rotation of the moving point sensor and improving the accuracy of pedestrian detection and tracking based on the moving point sensor.

[0117] The exposure adjustment device for the moving point sensor provided by the present invention will be described below. The exposure adjustment device for the moving point sensor described below can be referred to in correspondence with the exposure adjustment method for the moving point sensor described above.

[0118] Figure 6 This is a schematic diagram of the exposure adjustment device for the moving point sensor provided in an embodiment of the present invention, as shown below. Figure 6 As shown, the exposure adjustment device 600 of the moving point sensor includes: a first determining module 610, a second determining module 620, a third determining module 630, and an exposure adjustment module 640.

[0119] The first determining module 610 is used to determine, in the fixed-point region of the fixed-point sensor, the target overlapping region corresponding to the target prediction region after the moving-point sensor rotates along the target direction, wherein the target prediction region is obtained based on the expansion of the moving-point region of the moving-point sensor. The second determining module 620 is used to determine the predicted brightness corresponding to the moving point sensor based on the current fixed point parameter corresponding to the fixed point sensor and the current moving point parameter corresponding to the moving point sensor. The current fixed point parameter includes the brightness of the overlapping area corresponding to the target overlapping area. The third determining module 630 is used to determine the exposure prediction adjustment parameters of the moving point sensor based on the predicted brightness and the actual brightness of the moving point area. The exposure adjustment module 640 is used to adjust the exposure of the moving point sensor based on the exposure prediction adjustment parameters.

[0120] The exposure adjustment device for a moving point sensor provided in this embodiment of the invention, in a scenario where the monitoring area has extremely uneven brightness distribution, when the fixed-point area corresponding to the fixed-point sensor overlaps with the target prediction area corresponding to the moving point sensor in the target direction, determines the target overlap area in the fixed-point area. Based on the current fixed-point parameters of the fixed-point sensor and the current moving point parameters of the moving point sensor, including the brightness of the overlap area, the exposure prediction adjustment parameters of the moving point sensor are accurately predicted. This optimizes the image brightness oscillation problem that occurs during the exposure adjustment process when the moving point sensor rotates, thereby ensuring a smooth transition of image brightness adjustment during the rotation of the moving point sensor and improving the accuracy of pedestrian detection and tracking based on the moving point sensor.

[0121] Optionally, the second determining module 620 is specifically used for: Based on a preset brightness prediction function, the current fixed-point parameters, and the current moving-point parameters, the predicted brightness corresponding to the moving-point sensor is determined; the preset brightness prediction function is determined by function fitting based on the historical fixed-point parameters of the fixed-point sensor and the historical moving-point parameters of the moving-point sensor during the initial ambient brightness change process.

[0122] Optionally, the historical fixed-point parameters include: initial historical fixed-point parameters, first historical fixed-point parameters, and second historical fixed-point parameters, and the historical moving-point parameters include: initial historical moving-point parameters, first historical moving-point parameters, and second historical moving-point parameters.

[0123] Optionally, the exposure adjustment device 600 of the moving point sensor also includes a fitting module, which is specifically used for: Determine the initial historical fixed-point parameters of the fixed-point sensor under the initial ambient brightness, and the initial historical moving-point parameters of the moving-point sensor under the initial ambient brightness; Perform a first target operation on the initial ambient brightness, and determine the first historical fixed-point parameters and the first historical moving-point parameters based on the first judgment condition corresponding to the first target operation; A second target operation is performed on the target ambient brightness, and based on the second judgment condition corresponding to the second target operation, the second historical fixed-point parameter and the second historical moving-point parameter are determined, wherein the target ambient brightness is determined based on the initial ambient brightness after the first target operation is performed; The preset brightness prediction function is obtained by performing function fitting on the initial historical fixed-point parameters, the initial historical moving-point parameters, the first historical fixed-point parameters, the first historical moving-point parameters, the second historical fixed-point parameters, and the second historical moving-point parameters.

[0124] Optionally, the exposure prediction adjustment parameters include the exposure prediction adjustment direction and the exposure prediction adjustment magnitude.

[0125] Optionally, the third determining module 630 is specifically used for: Determine the brightness difference between the predicted brightness and the actual brightness; The exposure prediction adjustment range is determined based on the absolute value of the brightness difference; If the absolute value of the brightness difference is greater than a first preset brightness threshold, the exposure prediction adjustment direction is determined based on the brightness difference.

[0126] Optionally, the third determining module 630 is specifically used for: The initial exposure adjustment range is determined based on the absolute value of the brightness difference, the rotation speed of the moving point sensor, and the field of view angle of the target direction. The exposure prediction adjustment range is determined based on the initial exposure adjustment range, the field of view, and the number of predictions for the current frame.

[0127] Optionally, the third determining module 630 is specifically used for: If the brightness difference is greater than the second preset brightness threshold, the exposure prediction adjustment direction is determined to be light suppression, and the second preset brightness threshold is less than the first preset brightness threshold. If the brightness difference is less than or equal to the second preset brightness threshold, the exposure prediction adjustment direction is determined to be brightening.

[0128] Optionally, the exposure adjustment module 640 is specifically used for: After the moving point sensor rotates again along the target direction, the first exposure adjustment after exposure prediction is performed on the moving point sensor based on the exposure prediction adjustment direction and the exposure prediction adjustment magnitude. Determine the latest overlap between the adjusted new target prediction region and the fixed-point region; Based on the latest overlap, the exposure feedback adjustment is performed on the moving point sensor.

[0129] Optionally, the exposure adjustment module 640 is specifically used for: If the latest overlap indicates that the new target prediction area overlaps with the fixed-point area, the exposure prediction adjustment range is restored to the default exposure adjustment range, and the exposure feedback adjustment of the moving point sensor is performed. If the latest overlap condition indicates that the target prediction area and the fixed point area do not overlap, the exposure feedback adjustment of the moving point sensor is performed based on the correctness of the adjusted exposure direction, or the correctness of the exposure direction adjustment and the position of the moving point. The correctness of the exposure direction adjustment is used to characterize the matching between the actual exposure adjustment direction and the exposure prediction adjustment direction after adjustment; the position of the moving point is used to characterize the overlap between the target area where the moving point sensor is located and the target prediction area after adjustment.

[0130] Figure 7 This is a schematic diagram of the structure of the ball-shooting device provided in an embodiment of the present invention, as shown below. Figure 7 The described ball-and-shoot device may include a fixed-point sensor and a moving-point sensor, and may also include: a processor 710, a communication interface 720, a memory 730, and a communication bus 740, wherein the processor 710, the communication interface 720, and the memory 730 communicate with each other via the communication bus 740. The processor 710 can call logic instructions in the memory 730 to execute an exposure adjustment method for the moving-point sensor, the method including: In the fixed-point region of the fixed-point sensor, the target overlap region corresponding to the target prediction region after the moving-point sensor rotates along the target direction is determined. The target prediction region is obtained based on the expansion of the moving-point region of the moving-point sensor. Based on the current fixed-point parameters corresponding to the fixed-point sensor and the current moving-point parameters corresponding to the moving-point sensor, the predicted brightness corresponding to the moving-point sensor is determined, wherein the current fixed-point parameters include the brightness of the overlapping region corresponding to the target overlapping region. Based on the predicted brightness and the actual brightness of the moving point region, the exposure prediction adjustment parameters of the moving point sensor are determined; The exposure of the moving point sensor is adjusted based on the exposure prediction adjustment parameters.

[0131] Furthermore, the logical instructions in the aforementioned memory 730 can be implemented as software functional units and, when sold or used as independent products, can be stored in a computer-readable storage medium. Based on this understanding, the technical solution of the present invention, essentially, or the part that contributes to the prior art, or a part of the technical solution, can be embodied in the form of a software product. This computer software product is stored in a storage medium and includes several instructions to cause a computer device (which may be a personal computer, server, or network device, etc.) to execute all or part of the steps of the methods described in the various embodiments of the present invention. The aforementioned storage medium includes various media capable of storing program code, such as USB flash drives, portable hard drives, read-only memory (ROM), random access memory (RAM), magnetic disks, or optical disks.

[0132] On the other hand, the present invention also provides a computer program product, the computer program product comprising a computer program that can be stored on a non-transitory computer-readable storage medium, wherein when the computer program is executed by a processor, the computer is able to execute the exposure adjustment method for the moving point sensor provided by the above methods, the method comprising: In the fixed-point region of the fixed-point sensor, the target overlap region corresponding to the target prediction region after the moving-point sensor rotates along the target direction is determined. The target prediction region is obtained based on the expansion of the moving-point region of the moving-point sensor. Based on the current fixed-point parameters corresponding to the fixed-point sensor and the current moving-point parameters corresponding to the moving-point sensor, the predicted brightness corresponding to the moving-point sensor is determined, wherein the current fixed-point parameters include the brightness of the overlapping region corresponding to the target overlapping region. Based on the predicted brightness and the actual brightness of the moving point region, the exposure prediction adjustment parameters of the moving point sensor are determined; The exposure of the moving point sensor is adjusted based on the exposure prediction adjustment parameters.

[0133] In another aspect, the present invention also provides a non-transitory computer-readable storage medium having a computer program stored thereon, which, when executed by a processor, implements the exposure adjustment method for the moving point sensor provided by the methods described above, the method comprising: In the fixed-point region of the fixed-point sensor, the target overlap region corresponding to the target prediction region after the moving-point sensor rotates along the target direction is determined. The target prediction region is obtained based on the expansion of the moving-point region of the moving-point sensor. Based on the current fixed-point parameters corresponding to the fixed-point sensor and the current moving-point parameters corresponding to the moving-point sensor, the predicted brightness corresponding to the moving-point sensor is determined, wherein the current fixed-point parameters include the brightness of the overlapping region corresponding to the target overlapping region. Based on the predicted brightness and the actual brightness of the moving point region, the exposure prediction adjustment parameters of the moving point sensor are determined; The exposure of the moving point sensor is adjusted based on the exposure prediction adjustment parameters.

[0134] The device embodiments described above are merely illustrative. The units described as separate components may or may not be physically separate. The components shown as units may or may not be physical units; that is, they may be located in one place or distributed across multiple network units. Some or all of the modules can be selected to achieve the purpose of this embodiment according to actual needs. Those skilled in the art can understand and implement this without any creative effort.

[0135] Through the above description of the embodiments, those skilled in the art can clearly understand that each embodiment can be implemented by means of software plus necessary general-purpose hardware platforms, and of course, it can also be implemented by hardware. Based on this understanding, the above technical solutions, in essence or the part that contributes to the prior art, can be embodied in the form of a software product. This computer software product can be stored in a computer-readable storage medium, such as ROM / RAM, magnetic disk, optical disk, etc., and includes several instructions to cause a computer device (which may be a personal computer, server, or network device, etc.) to execute the methods described in the various embodiments or some parts of the embodiments.

[0136] Finally, it should be noted that the above embodiments are only used to illustrate the technical solutions of the present invention, and not to limit them; although the present invention has been described in detail with reference to the foregoing embodiments, those skilled in the art should understand that modifications can still be made to the technical solutions described in the foregoing embodiments, or equivalent substitutions can be made to some of the technical features; and these modifications or substitutions do not cause the essence of the corresponding technical solutions to deviate from the spirit and scope of the technical solutions of the embodiments of the present invention.

Claims

1. An exposure adjustment method for a moving-point sensor, characterized in that, include: In the fixed-point region of the fixed-point sensor, the target overlap region corresponding to the target prediction region after the moving-point sensor rotates along the target direction is determined. The target prediction region is obtained based on the expansion of the moving-point region of the moving-point sensor. Based on the current fixed-point parameters corresponding to the fixed-point sensor and the current moving-point parameters corresponding to the moving-point sensor, the predicted brightness corresponding to the moving-point sensor is determined, wherein the current fixed-point parameters include the brightness of the overlapping region corresponding to the target overlapping region. Based on the predicted brightness and the actual brightness of the moving point region, the exposure prediction adjustment parameters of the moving point sensor are determined; The exposure of the moving point sensor is adjusted based on the exposure prediction adjustment parameters.

2. The exposure adjustment method for a moving point sensor according to claim 1, characterized in that, The step of determining the predicted brightness corresponding to the moving point sensor based on the current fixed-point parameters corresponding to the fixed-point sensor and the current moving point parameters corresponding to the moving point sensor includes: Based on a preset brightness prediction function, the current fixed-point parameters, and the current moving-point parameters, the predicted brightness corresponding to the moving-point sensor is determined; the preset brightness prediction function is determined by function fitting based on the historical fixed-point parameters of the fixed-point sensor and the historical moving-point parameters of the moving-point sensor during the initial ambient brightness change process.

3. The exposure adjustment method for a moving point sensor according to claim 2, characterized in that, The historical fixed-point parameters include: initial historical fixed-point parameters, first historical fixed-point parameters, and second historical fixed-point parameters; the historical moving-point parameters include: initial historical moving-point parameters, first historical moving-point parameters, and second historical moving-point parameters. The determination of the preset brightness prediction function includes: Determine the initial historical fixed-point parameters of the fixed-point sensor under the initial ambient brightness, and the initial historical moving-point parameters of the moving-point sensor under the initial ambient brightness; Perform a first target operation on the initial ambient brightness, and determine the first historical fixed-point parameters and the first historical moving-point parameters based on the first judgment condition corresponding to the first target operation; A second target operation is performed on the target ambient brightness, and based on the second judgment condition corresponding to the second target operation, the second historical fixed-point parameter and the second historical moving-point parameter are determined, wherein the target ambient brightness is determined based on the initial ambient brightness after the first target operation is performed; The preset brightness prediction function is obtained by performing function fitting on the initial historical fixed-point parameters, the initial historical moving-point parameters, the first historical fixed-point parameters, the first historical moving-point parameters, the second historical fixed-point parameters, and the second historical moving-point parameters.

4. The exposure adjustment method for a moving point sensor according to any one of claims 1-3, characterized in that, The exposure prediction adjustment parameters include the exposure prediction adjustment direction and the exposure prediction adjustment magnitude; The step of determining the exposure prediction adjustment parameters of the moving point sensor based on the predicted brightness and the actual brightness of the moving point region includes: Determine the brightness difference between the predicted brightness and the actual brightness; The exposure prediction adjustment range is determined based on the absolute value of the brightness difference; If the absolute value of the brightness difference is greater than a first preset brightness threshold, the exposure prediction adjustment direction is determined based on the brightness difference.

5. The exposure adjustment method for a moving point sensor according to claim 4, characterized in that, Determining the exposure prediction adjustment range based on the absolute value of the brightness difference includes: The initial exposure adjustment range is determined based on the absolute value of the brightness difference, the rotation speed of the moving point sensor, and the field of view angle of the target direction. The exposure prediction adjustment range is determined based on the initial exposure adjustment range, the field of view, and the number of predictions for the current frame.

6. The exposure adjustment method for a moving point sensor according to claim 4, characterized in that, Determining the exposure prediction adjustment direction based on the brightness difference includes: If the brightness difference is greater than the second preset brightness threshold, the exposure prediction adjustment direction is determined to be light suppression, and the second preset brightness threshold is less than the first preset brightness threshold. If the brightness difference is less than or equal to the second preset brightness threshold, the exposure prediction adjustment direction is determined to be brightening.

7. The exposure adjustment method for a moving point sensor according to claim 4, characterized in that, The exposure adjustment of the moving point sensor based on the exposure prediction adjustment parameters includes: After the moving point sensor rotates again along the target direction, the first exposure adjustment after exposure prediction is performed on the moving point sensor based on the exposure prediction adjustment direction and the exposure prediction adjustment magnitude. Determine the latest overlap between the adjusted new target prediction region and the fixed-point region; Based on the latest overlap, the exposure feedback adjustment is performed on the moving point sensor.

8. The exposure adjustment method for a moving point sensor according to claim 7, characterized in that, The step of adjusting the exposure feedback of the moving point sensor based on the latest overlap condition includes: If the latest overlap indicates that the new target prediction area overlaps with the fixed-point area, the exposure prediction adjustment range is restored to the default exposure adjustment range, and the exposure feedback adjustment of the moving point sensor is performed. If the latest overlap condition indicates that the target prediction area and the fixed point area do not overlap, the exposure feedback adjustment of the moving point sensor is performed based on the correctness of the adjusted exposure direction, or the correctness of the exposure direction adjustment and the position of the moving point. The correctness of the exposure direction adjustment is used to characterize the matching between the actual exposure adjustment direction and the exposure prediction adjustment direction after adjustment; the position of the moving point is used to characterize the overlap between the target area where the moving point sensor is located and the target prediction area after adjustment.

9. An exposure adjustment device for a moving point sensor, characterized in that, include: The first determining module is used to determine, within the fixed-point region of the fixed-point sensor, the target overlapping region corresponding to the target prediction region after the moving-point sensor rotates along the target direction, wherein the target prediction region is obtained based on the expansion of the moving-point region of the moving-point sensor. The second determining module is used to determine the predicted brightness corresponding to the moving point sensor based on the current fixed point parameter corresponding to the fixed point sensor and the current moving point parameter corresponding to the moving point sensor. The current fixed point parameter includes the brightness of the overlapping area corresponding to the target overlapping area. The third determining module is used to determine the exposure prediction adjustment parameters of the moving point sensor based on the predicted brightness and the actual brightness of the moving point area; An exposure adjustment module is used to adjust the exposure of the moving point sensor based on the exposure prediction adjustment parameters.

10. A ball-shooting device, comprising a fixed-point sensor, a moving-point sensor, 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 program, it implements the exposure adjustment method of the moving point sensor as described in any one of claims 1 to 8.

Images