Photographing control method, electronic device, product, medium and photographing system

Abstract

The present application provides a photographing control method, an electronic device, a product, a medium and a photographing system. The method comprises: acquiring predicted distribution data (S11); and on the basis of target area information in the predicted distribution data, controlling a photographing device to photograph a target area (S12), wherein the target area is an area, predicted by the predicted distribution data, where the number density of detected objects in a monitoring area exceeds a preset threshold.

Description

Photographing control method, electronic device, product, medium and photographing system

[0001] Cross-reference to related applications

[0002] The present application claims priority to the Chinese patent application No. 202411230154.X, filed on September 3, 2024, and entitled "Photographing control method, electronic device, product, medium and photographing system", the content of which is incorporated herein by reference in its entirety. TECHNICAL FIELD

[0003] The present application relates to the field of control, and in particular, to a photographing control method, an electronic device, a product, a medium and a photographing system. BACKGROUND

[0004] With the development of technology, the monitoring industry has also entered a period of rapid development, and it is mainly applied to city safety, public place monitoring, commercial and home security scenes, etc. In most scenes, a conventional multi-camera cluster is usually used. Each camera in the monitoring system is deployed in each area to monitor the shooting area at different angles. However, due to the number of cameras, focal length, angle, etc., the monitored area cannot be fully and effectively covered. Moreover, due to the poor linkage between each camera, the possibility of missing the required monitoring data in the monitoring process is high. SUMMARY

[0005] The present application mainly aims to provide a photographing control method, an electronic device, a product, a medium and a photographing system.

[0006] The present application provides a photographing control method. The method comprises: acquiring prediction distribution data; controlling a photographing device to photograph a target region according to target region information in the prediction distribution data; wherein the target region is a region in which the number density of detected objects in a monitoring region exceeds a preset threshold value, which is predicted by the prediction distribution data.

[0007] The present application provides an electronic device. The electronic device comprises a memory and a processor, the memory is used to store program data, and the program data can be executed by the processor to realize the above photographing control method.

[0008] The present application provides a computer program product. The computer program product stores program data, which can be executed by a processor to realize the above photographing control method.

[0009] The present application provides a computer readable storage medium. The computer program product stores program data, which can be executed by a processor to realize the above photographing control method.

[0010] The application provides a photographing system. The photographing system comprises a photographing device for photographing a monitoring area; and an electronic device as described in the second technical solution, which is in communication connection with the photographing device to implement the photographing control method. BRIEF DESCRIPTION OF DRAWINGS

[0011] In order to more clearly illustrate the technical solutions in the embodiments of the present application, the drawings needed to be used in the embodiments will be briefly introduced. Obviously, the drawings in the following description are only some embodiments of the present application, and other drawings can be obtained by those skilled in the art without any creative effort.

[0012] Fig. 1 is a flowchart of a first embodiment of the photographing control method of the present application;

[0013] Fig. 2 is a flowchart of a second embodiment of the photographing control method of the present application;

[0014] Fig. 3 is a flowchart of a third embodiment of the photographing control method of the present application;

[0015] Fig. 4 is a flowchart of a fourth embodiment of the photographing control method of the present application;

[0016] Fig. 5 is a flowchart of a fifth embodiment of the photographing control method of the present application;

[0017] Fig. 6 is a flowchart of a sixth embodiment of the photographing control method of the present application;

[0018] Fig. 7 is a structural diagram of an embodiment of the electronic device of the present application;

[0019] Fig. 8 is a structural diagram of an embodiment of the computer program product of the present application;

[0020] Fig. 9 is a structural diagram of an embodiment of the computer readable storage medium of the present application;

[0021] Fig. 10 is a structural diagram of an embodiment of the photographing system of the present application. DETAILED DESCRIPTION

[0022] The technical solutions in the embodiments of the present application will be described clearly and completely below with reference to the drawings in the embodiments of the present application. Obviously, the described embodiments are only some embodiments of the present application, rather than all the embodiments. Based on the embodiments in the present application, all other embodiments obtained by those skilled in the art without any creative effort fall within the scope of protection of the present application.

[0023] The terms "first", "second", etc. in this application are used to distinguish different objects and are not intended to describe a particular order. In addition, the terms "include" and "have" and any variations thereof are intended to cover non-exclusive inclusion. For example, a process, method, system, product or device that includes a series of steps or units is not limited to the listed steps or units, but can optionally include steps or units not listed, or can optionally include other steps or units inherent to the process, method, product or device.

[0024] Reference herein to "embodiments" means that a particular feature, structure, or characteristic described in connection with an embodiment can be included in at least one embodiment of the application. The appearance of the phrase in various places in the specification does not necessarily all refer to the same embodiment, nor is it necessarily mutually exclusive of other embodiments. It is expressly understood that the embodiments described herein can be combined with each other.

[0025] In some scenarios, due to the area to be monitored is too large, the range that a single monitoring device can monitor cannot completely cover the area to be monitored, so multiple monitoring devices are usually used to make the range that they can monitor together cover the area to be monitored. Since a single monitoring device can only monitor part of the range that it can monitor at a time, there will also be a time when the monitoring device cannot fully cover the area to be monitored. Therefore, how to control the monitoring device to make it miss as little key monitoring data as possible to improve monitoring efficiency, the present application proposes the following embodiments.

[0026] Referring to FIG. 1, FIG. 1 is a flowchart of a first embodiment of a photographing control method of the present application. The photographing control method includes but is not limited to the following steps.

[0027] S11: Obtain prediction distribution data.

[0028] In an embodiment, the prediction distribution data is obtained by using prediction time and historical distribution data. The prediction time can be the current time or a future time that has not yet arrived. The historical distribution data is the distribution data of the detected object in the monitoring area obtained by the object detection device before the current time.

[0029] The distribution data is related data that can reflect the distribution of the detected object in the monitoring area. Its specific form can be various, which can be graphical data, list data, etc.

[0030] S12: Control the photographing device to photograph the target area according to the target area information in the prediction distribution data.

[0031] The target region is a region in the monitoring region in which the number density of detected objects predicted by the prediction distribution data exceeds a preset threshold.

[0032] In an embodiment, the monitoring region is divided into a plurality of regions. The target region is obtained from the plurality of regions. The target region is a region in the plurality of regions in which the number density of detected objects exceeds a preset threshold.

[0033] In an embodiment, the number density is the number of detected objects appearing in a region within a time range of a time period. For example, the monitoring region A is divided into a plurality of regions B, C, D, and so on. Within a certain time period, the number of detected objects appearing in region B is 10, the number of detected objects appearing in region C is 20, and the number of detected objects appearing in region D is 50. Thus, the number density of region B in the time period is 10, the number density of region C in the time period is 20, and the number density of region D in the time period is 50.

[0034] If the target region information exists in the prediction distribution data, the target region can be determined according to the target region information, so that the shooting device shoots the target region at the prediction time for obtaining the prediction distribution data. The shooting range of the shooting device is limited according to the target region, so that the shooting device can shoot the target region in which the detected objects are more likely to appear at the prediction time, and the possibility of missing important monitoring data is reduced. Moreover, because the adjustment is performed according to the prediction distribution data, compared with the adjustment based on the currently obtained distribution data, the timing of the adjustment based on the prediction distribution data is more advanced, and the possibility of missing important monitoring data is further reduced.

[0035] In the embodiment, one shooting device can only shoot part of the monitoring region at the same time.

[0036] In some embodiments, the number of shooting devices is multiple, and the shooting of the multiple shooting devices at the same time can cover the entire monitoring region.

[0037] In some embodiments, the number of shooting devices is multiple, and the shooting of the multiple shooting devices at the same time can only cover part of the monitoring region, but the complete shooting regions of the multiple shooting devices combined together can cover the entire monitoring region. The complete shooting region is the entire region that can be shot by one shooting device.

[0038] In the embodiment, the prediction distribution data is acquired, when the target region information is included in the prediction distribution data, the target region corresponding to the target region information is photographed according to the target region information, and through prediction, the photographing device can adjust the photographed coordinate range to the target region where more detection objects are likely to appear in advance, so as to reduce the possibility of missing important photographing data and improve the photographing efficiency.

[0039] Referring to FIG. 2, FIG. 2 is a flowchart of a second embodiment of the photographing control method. The method is a further extension of step S12. It includes but is not limited to the following steps.

[0040] S21: determining the target region coordinate range according to the target region information.

[0041] S22: adjusting the photographing region coordinate range of the photographing device according to the target region coordinate range, and obtaining the photographing parameter corresponding to the adjusted photographing region coordinate range.

[0042] S23: controlling the photographing device to photograph the target region according to the photographing parameter.

[0043] The target region information is a representation of the target region, and can be used to derive various related information of the target region. For example, if the prediction distribution data distinguishes each region in the monitoring region by a serial number, the target region information can be the corresponding serial number, and the coordinate range of the target region can be obtained through the relationship between the serial number and the region coordinate range. If the prediction distribution data distinguishes each region in the monitoring region by a single coordinate, the target region information can be the corresponding coordinate, and the coordinate range of the target region can also be obtained through the relationship between the coordinate and the region coordinate range.

[0044] The target region coordinate range of the target region can be determined through the target region information. After obtaining the target region coordinate range of the target region, the photographing region coordinate range of the photographing device is related to the photographing parameter of the photographing device, and the corresponding photographing parameter can be derived from the photographing region coordinate range. Therefore, after adjusting the photographing region coordinate range according to the target region coordinate range, the corresponding photographing parameter of the photographing device can be obtained according to the adjusted region coordinate range. The photographing region coordinate range is adjusted according to the target region coordinate range, so that the photographing region coordinate range completely covers the target region coordinate range or partially covers the target region coordinate range. The obtained target region coordinate range and the photographing region coordinate range are established in the same coordinate system, which can be a world coordinate system in the real world or a virtual coordinate system preset in a model.

[0045] The shooting parameters can include shooting angle, shooting focal length, shooting height, shooting center coordinate, etc. Generally, since the shooting height is fixed, the shooting angle and the shooting focal length can be determined according to the shooting region coordinate range.

[0046] In an embodiment, in the process of determining the shooting parameters, the shooting parameters can be obtained by minimizing the difference between the target region coordinate range and the shooting region coordinate range. According to the method, the shooting device can shoot the target region as accurately and clearly as possible.

[0047] In a specific embodiment, the shooting region coordinate range of the shooting device under specific shooting parameters can be regarded as a rectangular region [Bi1, Bi2, Bi3, Bi4] with four vertices. The shooting parameters can include angle θi, focal length fi, and height d. The coordinate range can be calculated by the following formula:

[0048] Where (xi, yi) is the coordinate of the center of the shooting range of the shooting device Bi, the angle θi can be used to calculate the coordinate of the center, the angle θi is the rotation angle of the shooting device relative to the reference position, d is the distance from the shooting device Bi to the ground, and lj and mj are the relative displacements calculated according to the direction and angle of view of the shooting device.

[0049] In the same coordinate system, the shooting region coordinate range is adjusted by the target region coordinate range, so that the shooting region coordinate range can completely cover the target region coordinate range, or partially cover the target region coordinate range. Further minimizing the error between the shooting region coordinate range and the target region coordinate range, thereby obtaining the final adjusted shooting region coordinate range, and obtaining the shooting parameters according to the shooting region coordinate range.

[0050] In the above embodiment, the target region information in the prediction distribution data can not contain the actual coordinates of the target region in the real world, but can be replaced by coordinates in a new coordinate system constructed in the prediction process or other information, in order to save the calculation consumption of the prediction step. If the prediction model is used to obtain the prediction distribution data, the actual coordinates in the historical distribution data can also be replaced by coordinates in a new coordinate system constructed in the prediction model or other information when the historical distribution data is input into the prediction model for training, thereby saving the calculation resources. When the target region information in the prediction distribution data is obtained, the coordinates of the target region in the actual coordinate system can be obtained according to the conversion relationship between the actual coordinate system and the new coordinate system in the prediction model.

[0051] Referring to FIG. 3, FIG. 3 is a flow diagram of a third embodiment of the photographing control method. The method is a further extension of steps S22 and S23. It includes but is not limited to the following steps.

[0052] S31: Adjust the photographing region coordinate range of at least one photographing device according to the at least one target region coordinate range.

[0053] S32: Determine at least one set of photographing parameters according to the adjusted photographing region coordinate range of the at least one photographing device.

[0054] Each set of photographing parameters corresponds to one photographing device.

[0055] S33: Control the corresponding photographing device to photograph the at least one target region coordinate range according to the at least one set of photographing parameters.

[0056] Optionally, the number of photographing devices can be one or more. The number of photographing devices includes two or more.

[0057] When the number of photographing devices is at least one and the number of obtained target region coordinate ranges is at least one, adjusting the photographing region coordinate range of the at least one photographing device according to the at least one target coordinate range can obtain at least one adjusted photographing region coordinate range. Further, at least one set of corresponding photographing parameters can be obtained according to the at least one adjusted photographing region coordinate range. Then, the corresponding photographing device is controlled according to the obtained photographing parameters.

[0058] Referring to FIG. 4, FIG. 4 is a flow diagram of a fourth embodiment of the photographing control method. The method is a further extension of step S31. It includes but is not limited to the following steps.

[0059] S41: For any target region coordinate range, in response to the target region coordinate range not being covered by the photographing region coordinate range of the photographing device, determine the nearest target photographing device according to the target region coordinate range.

[0060] S42: Adjust the photographing region coordinate range of the nearest photographing device.

[0061] When the target region coordinate range is obtained, the photographing parameters of all photographing devices corresponding to the distribution of the target region coordinate range have not been determined. Therefore, the photographing parameters of each photographing device need to be determined according to the target region coordinate range.

[0062] In the process of determining the shooting parameters according to the target region coordinate range, the shooting parameters are determined according to the ranges one by one in sequence. The sequence can be determined randomly. For any selected target region coordinate range, it is first determined whether it has been completely covered by the shooting region coordinate range of the shooting device. If it has been completely covered by the shooting region coordinate range, there is no need to determine the shooting parameters, and the corresponding shooting device can continue to shoot it according to the existing shooting region coordinate range that completely covers it. This is because when the prediction time comes, the shooting region coordinate range of the shooting device at the previous time may directly completely cover the obtained target region coordinate range, so there is no need to adjust the shooting device.

[0063] If the target region coordinate range is not completely covered by the shooting region coordinate range of the shooting device, the nearest target shooting device is determined. The target shooting device is a shooting device that does not completely cover other target region ranges. It is taken as an adjustment object so that its shooting region coordinate range can completely cover the target region coordinate range. The shooting device that is nearest to the target region coordinate range and does not shoot other target region ranges is selected, which can make the shooting of the target region coordinate range as clear and clear as possible.

[0064] In an embodiment, after the shooting region coordinate range of at least one shooting device is adjusted according to at least one target region coordinate range, at least one set of shooting parameters is determined according to the adjusted shooting region coordinate range of at least one shooting device, and in response to the fact that there are still shooting devices that do not cover the target region ranges, the preset shooting parameters corresponding to the shooting devices that do not cover the target region ranges are obtained, and the preset shooting parameters are determined as the shooting parameters, or the preset shooting region coordinate range corresponding to the shooting devices that do not cover the target region ranges is obtained, and the shooting parameters are obtained according to the preset shooting region coordinate range. In the process of determining the shooting parameters, there may be a situation that the number of target region coordinate ranges is too large, or the number of shooting devices is too large, or there are still target region coordinate ranges that have not been completely covered, but the remaining shooting devices cannot cover the target region coordinate ranges.

[0065] After the shooting region coordinate range is adjusted according to the target region coordinate range, the shooting parameters of the shooting devices are obtained, and when all the target region coordinate ranges are completely covered by the shooting region coordinate ranges, there are still some shooting devices that do not cover the target region coordinate ranges. The preset shooting parameters or the preset shooting region coordinate ranges corresponding to the shooting devices are obtained. At this time, the shooting capacity of the shooting devices is still sufficient to completely cover the target region coordinate range, so that the remaining shooting devices are used to shoot the default region set in advance. The preset shooting parameter is a shooting parameter set in advance, which corresponds to a region set in advance. The preset shooting region coordinate range is a region set in advance. Each shooting device can set a preset shooting parameter or a preset shooting region coordinate range. After the preset shooting parameter is obtained, the preset shooting parameter is used as the shooting parameter of the shooting device for adjustment and control. Or, the corresponding shooting parameter is obtained according to the preset shooting region coordinate range, and then the shooting parameter is used as the shooting parameter of the shooting device for adjustment and control.

[0066] In an embodiment, after the shooting region coordinate range is adjusted according to the target region coordinate range, the shooting parameters of the shooting devices are obtained, and there are still some target region coordinate ranges that are not completely covered by the shooting region coordinate ranges. This may be due to the insufficient number of shooting devices, all the shooting devices have determined the shooting parameters, or the remaining shooting devices that have not determined the shooting parameters cannot cover the target region coordinate range. At this time, the corresponding shooting parameters and shooting devices cannot be determined according to the target region coordinate ranges that are not completely covered, and a corresponding prompt can be given to prompt the user whether to adjust the existing shooting parameter scheme that has been determined.

[0067] In the above embodiment, a neural network model can be used to obtain the prediction distribution data. In the above embodiment, a prediction time can be obtained, the prediction time is input into the trained distribution prediction model, and prediction distribution data of the detection object in the monitoring region at the prediction time is generated. The trained distribution prediction model is trained based on historical distribution data of the detection object in the monitoring region and the corresponding time. The historical distribution data includes the number density of the detection object in the monitoring region.

[0068] Referring to FIG. 5, FIG. 5 is a flowchart of a fifth embodiment of the shooting control method of the present application. The method is a further extension of obtaining prediction distribution data. It includes but is not limited to the following steps.

[0069] S51: Obtain a prediction time.

[0070] S52: Input the prediction time into the trained distribution prediction model to obtain the prediction distribution data.

[0071] Referring to FIG. 6, FIG. 6 is a flowchart of a sixth embodiment of the device control method of the present application. The method is a further extension of the training process of the prediction distribution model in the obtaining prediction distribution data. It includes but is not limited to the following steps.

[0072] S61: obtaining historical distribution data of the detection object in the monitoring area and the corresponding time.

[0073] S62: classifying the time to obtain at least one time period.

[0074] S63: obtaining prediction distribution data based on at least one time period and the historical distribution data corresponding to the time period.

[0075] The historical distribution data includes the number density of the detection object in the monitoring area. The historical distribution data and the corresponding time are determined. The time is classified according to a pre-set time classification method to obtain at least one time period. The obtained time period and the corresponding historical distribution data are input into the distribution prediction model to perform training.

[0076] In an embodiment, classifying the time can include classifying the time according to date type and / or time period type.

[0077] Classifying according to date type, such as dividing the time into working days, holidays, shopping days, etc. Classifying according to time period type, such as dividing the time of a day according to a pre-set time period. For example, dividing the time of a day into 0-1, 1-2, etc.

[0078] In an embodiment, obtaining prediction distribution data based on at least one time period and the historical distribution data corresponding to the time period includes: inputting at least one time period and the historical distribution data corresponding to the time period into the corresponding distribution prediction model according to the time classification type of the time period to perform training. In order to make the prediction distribution data obtained by the prediction distribution model more accurate, different prediction distribution models are used to realize the prediction of the prediction distribution data of different time classification types. For example, a certain prediction distribution model only predicts the prediction distribution data of working days, a certain prediction distribution model only predicts the prediction distribution data from 3 pm to 4 pm, etc.

[0079] The device control method of the present application will be described in more detail below with reference to a specific embodiment.

[0080] In one scenario, an object in a monitoring area is monitored by a shooting system. The shooting system includes a main field of view camera device and multiple secondary camera devices. The shooting system can further include a server background for processing related data. The main field of view camera device corresponds to the object detection device described above, and is used to obtain distribution data. The secondary camera device corresponds to the multiple shooting devices described above.

[0081] Generally, the main field of view camera device is arranged above the monitoring area, vertically downward, so that its shooting field of view can accommodate the entire monitoring area. The secondary camera is arranged at each edge point of the monitoring area.

[0082] The main field of view camera device inputs the collected video data of the monitoring area to the server background for calculation, and processes the collected video data by using a detection and recognition algorithm to obtain the corresponding position of each object in the monitoring area at each time. If the computing resources are sufficient, the data processing can also be directly performed by the main field of view camera device.

[0083] Radar devices or infrared sensor devices can also be used to replace the main field of view camera device to obtain the position information of the object. Generally, due to the limited measurement range of a single radar device or infrared sensor device, it cannot completely cover the monitoring area, so multiple devices are generally needed. When using radar devices or infrared sensor devices, the radar devices or infrared sensor devices can be correspondingly arranged at positions corresponding to the secondary camera devices, or can be arranged at other positions, as long as the data collection range can cover the entire monitoring area. The corresponding arrangement of the radar devices or infrared sensor devices with the secondary camera devices is for the convenience of arrangement. When using radar devices, the radar devices are used to collect real-time distance, angle, speed and other information of the object. The position of each radar device and the collected distance, angle, speed and other information are used to calculate the global coordinates (with the position of the radar device as the origin) of each object. The calculation formula can be: x=d·cos(θ) y=d·sin(θ)

[0084] Wherein, d is the distance, θ is the azimuth angle, and (x, y) is the position coordinate of the object relative to the radar device.

[0085] Then, the data obtained by each radar is fused to eliminate the repeatedly detected data. The fusion of the data can adopt weighted average or filtering processing method. The processing process of the weighted average method is relatively simple, and the processing process of the filtering algorithm is relatively complex. The processing method can be selected according to the actual situation. The data acquisition process of the infrared sensor device is similar to that of the radar device, which will not be repeated here.

[0086] After obtaining the data, the data is detected and recognized to obtain the detection box position and corresponding time stamp of each object.

[0087] According to the date and time period, the date is classified into working days, holidays, shopping days, etc. to form a set D = {d1, d2, …, dn}, and a day is divided into T minutes to form a time period set Y = {y1, y2, …, ym}.

[0088] After time division, the data of the area to be monitored is spatially divided and the density is calculated. For example, the area to be monitored can be divided by 3*3 meters, and each sub-area is represented by the center coordinates to obtain a center coordinate set C = {c1, c2, …, ck}. Then, according to the date classification d and time period division y, the density of objects in each sub-area is calculated, that is, the number of objects falling into the sub-area within the time period. The sub-areas with density exceeding the preset threshold are grouped into a high-density region coordinate set Chigh.

[0089] The time and density data of the historical time period are counted to form a data set. For example, the data of the last sixty days is recorded to form a data set (D, Y, Chigh). The data is used to train the distribution prediction model.

[0090] During training, the data set can be divided according to the date classification, which is used as the training data of different distribution prediction models. In this way, the distribution prediction model can make more accurate predictions for the data corresponding to the date classification.

[0091] During model network construction, Transformer or LSTM model can be used to construct the spatio-temporal dependency. LSTM (Long Short Term Memory) is a variant of recurrent neural network (RNN) suitable for processing time series data. It can capture time dependence and perform better than traditional RNN in handling long-term dependence problems. Transformer can effectively capture long-term dependence and time series features. Transformer model is composed of attention mechanism, which is particularly suitable for processing long-distance dependence and time series data, and is also suitable for time series prediction tasks. The loss function can use mean square error, etc., and the optimization can use Adam optimizer, etc. During the training of the model, the related parameters in the model are adjusted by using back propagation.

[0092] The trained distribution prediction model can obtain the corresponding object density distribution data according to the target time.

[0093] In adjusting the sub-shooting devices using the obtained distribution data, the actual coordinates of the sub-shooting devices in the world coordinate system {B1, B2, …, Bn} can be obtained first. Then, the shooting range of each sub-shooting device under a specific shooting parameter (which can include the angle θi, the focal length fi, and the height d) can be regarded as a rectangular region [Bi1, Bi2, Bi3, Bi4] with four vertices. The coordinates of this region can be calculated by the following formula:

[0094] where (xi, yi) is the coordinate of the center of the shooting range of the sub-shooting device Bi in the world coordinate system, the angle θi can be used to calculate the coordinate of the center, the angle θi is the rotation angle of the shooting device relative to the reference position, d is the distance from the sub-shooting device Bi to the ground, and lj and mj are the relative displacements calculated according to the direction and angle of view of the shooting device.

[0095] In the predicted distribution data obtained based on the target time, the high-density region coordinates (usually, in order to facilitate calculation, the actual coordinates in the world coordinate system are not used in the prediction model, and therefore the above-mentioned center coordinate set and the high-density region coordinates used are both new coordinate systems in the model) are determined, the high-density region coordinates are projected, and the projection is performed to the world coordinate system to obtain the actual coordinates of the predicted high-density region in the world coordinate system. The high-density region and the coordinates of the shooting range of the sub-shooting device are matched and optimized so that the shooting range can include the high-density region, thereby obtaining the required shooting range and determining the shooting parameter required by the sub-shooting device. Thus, the sub-shooting device can be adjusted according to the shooting parameter at the target time.

[0096] In addition, the following strategies can also be performed when controlling the sub-shooting devices:

[0097] Region monitoring judgment: if the predicted high-density region of the monitoring region has been covered by other sub-shooting devices, the next high-density region is searched. In determining the shooting parameter of the sub-shooting device according to the high-density region, the sub-shooting device closest to the target time and not yet determined to have the shooting parameter is preferentially selected.

[0098] Default strategy: if all high-density regions have been covered or are unavailable, the remaining sub-shooting devices can set a default monitoring region, such as a doorway or other low-density region, to monitor the default monitoring region at the target time.

[0099] Sleep strategy: for the monitoring regions that are not high-density regions, the shooting devices can be set to a sleep state / reduce the quality of the uploaded monitoring video to save energy and resources and storage space.

[0100] Manual strategy / abnormality processing: when an emergency or abnormal crowd density change occurs, a monitoring point is manually set by observing the real-time monitored heat map, an instruction is sent to the secondary shooting device to adjust parameters such as angle and focal length.

[0101] As shown in FIG. 7, FIG. 7 is a structural schematic diagram of an embodiment of the electronic device.

[0102] The electronic device includes a processor 110 and a memory 120.

[0103] The processor 110 controls the operation of the electronic device, and the processor 110 can also be referred to as a CPU (Central Processing Unit). The processor 110 can be an integrated circuit chip with signal sequence processing capability. The processor 110 can also be a general-purpose processor, a digital signal sequence processor (DSP), an application-specific integrated circuit (ASIC), a field programmable gate array (FPGA), or other programmable logic devices, discrete gates or transistor logic devices, discrete hardware components. The general-purpose processor can be a microprocessor or the processor can also be any conventional processor.

[0104] The memory 120 stores instructions and program data required for the operation of the processor 110.

[0105] The processor 110 is configured to execute instructions to implement the method provided by any embodiment and possible combination of the photographing control method.

[0106] As shown in FIG. 8, FIG. 8 is a structural schematic diagram of an embodiment of the computer program product.

[0107] An embodiment of the computer program product includes a memory 210, and the memory 210 stores program data, which, when executed, implements the method provided by any embodiment and possible combination of the photographing control method.

[0108] The memory 210 can include a U disk, a mobile hard disk, a read-only memory (ROM), a random access memory (RAM), a magnetic disk or an optical disk, and other media that can store program instructions, or it can also be a server that stores the program instructions, which can send the stored program instructions to other devices for running, or it can also run the stored program instructions by itself.

[0109] As shown in FIG. 9, FIG. 9 is a structural schematic diagram of an embodiment of the computer readable storage medium.

[0110] An embodiment of the computer readable storage medium of the present application comprises a memory 310, which stores program data, which, when executed, implements the method provided by any embodiment and possible combination of the photographing control method of the present application.

[0111] The memory 310 can comprise a U disk, a mobile hard disk, a read-only memory (ROM), a random access memory (RAM), a magnetic disk or an optical disk, etc., which can store program instructions, or can be a server storing the program instructions, which can send the stored program instructions to other devices for running, or can run the stored program instructions itself.

[0112] As shown in FIG. 10, FIG. 10 is a structural schematic diagram of an embodiment of the photographing system of the present application.

[0113] The photographing system comprises an electronic device 410 and a photographing device 420. The photographing device 420 is used for photographing a target region, and the electronic device 410 is the device described in the embodiment of the electronic device of the present application.

[0114] The electronic device 410 and the photographing device 420 are communicatively connected to implement the method provided by any embodiment and possible combination of the photographing control method of the present application.

[0115] In an embodiment, the photographing system can further comprise an object detection device, which is used for identifying and detecting an object. The object detection device can be a camera device, a radar device, an infrared sensor device, etc. Further, the object detection device also has a certain data processing capability, and can obtain distribution data of the detected object in the monitoring region according to the identification and detection result, which will be used as historical distribution data for training the distribution prediction model, so as to obtain the predicted distribution data.

[0116] When the electronic device 410 is a server or other device with strong computing capability, the photographing system can send the distribution data of the detected object to the electronic device 410 by the object detection device, for implementing the above-mentioned device control method.

[0117] When the electronic device 410 itself has the object detection function and strong computing capability, the additional object detection device is not needed.

[0118] In summary, the present application obtains the predicted distribution data, and when the target region information is included in the predicted distribution data, controls the photographing device to photograph the target region corresponding to the target region information according to the target region information, so that the photographing device can adjust the coordinate range of photographing to the target region where more detected objects are likely to appear in advance, thereby reducing the possibility of missing important photographing data and improving the photographing efficiency.

[0119] In several embodiments provided in the present application, it should be understood that the disclosed methods and devices can be implemented in other manners. For example, the above described device embodiments are merely illustrative, and the division of the modules or units can be different, for example, the division of the modules or units can be combined or integrated into another system, or some features can be ignored or not executed. In this way, the internal structure of the device is not limited to the above.

[0120] The units described as separate components may or may not be physically separate, and the components shown as units may or may not be physical units, that is, they can be located in one place, or they can be distributed on multiple network units. Some or all of the units can be selected according to actual needs to achieve the purpose of the present embodiment.

[0121] In addition, each functional unit in each embodiment of the present application can be integrated into a processing unit, or each unit can be physically present separately, or two or more units can be integrated into one unit. The integrated unit can be realized in the form of hardware or in the form of a software functional unit.

[0122] The integrated unit in the above other embodiments, if realized in the form of a software functional unit and sold or used as an independent product, can be stored in a computer readable storage medium. Based on this understanding, the technical solutions of the present application essentially or the part that contributes to the prior art or the whole or part of the technical solutions can be embodied in the form of a software product. The computer software product is stored in a storage medium, and includes a number of instructions for causing a computer device (which can be a personal computer, a server, or a network device, etc.) or a processor to execute all or part of the steps of the methods described in the various embodiments of the present application. The aforementioned storage medium includes: a U disk, a mobile hard disk, a read-only memory (ROM, Read-Only Memory), a random access memory (RAM, Random Access Memory), a magnetic disk or an optical disk, and various media that can store program codes.

[0123] The above is merely an embodiment of the present application, and does not limit the patent scope of the present application, and any equivalent structure or equivalent process transformation using the content of the present application specification and drawings, or direct or indirect application in other related technical fields, are also included in the patent protection scope of the present application.

Claims

1. A photographing control method, wherein, The method comprises: acquiring prediction distribution data; controlling a photographing device to photograph a target region according to target region information in the prediction distribution data; wherein the target region is a region in which the number density of detected objects in a monitoring region exceeds a preset threshold value, as predicted by the prediction distribution data.

2. The photographing control method according to claim 1, wherein The step of controlling the photographing device to photograph the target region according to the target region information in the prediction distribution data comprises: determining a target region coordinate range according to the target region information; adjusting a photographing region coordinate range of the photographing device according to the target region coordinate range to obtain photographing parameters corresponding to the adjusted photographing region coordinate range; controlling the photographing device to photograph the target region according to the photographing parameters.

3. The photographing control method according to claim 2, wherein The number of target region coordinate ranges is at least one, and the number of photographing devices is at least one. The step of adjusting the photographing region coordinate range of the photographing device according to the target region coordinate range to obtain photographing parameters corresponding to the adjusted photographing region coordinate range comprises: adjusting the photographing region coordinate range of at least one photographing device according to at least one target region coordinate range; determining at least one set of photographing parameters according to the adjusted photographing region coordinate range of at least one photographing device, each set of photographing parameters corresponding to one photographing device; The step of controlling the photographing device to photograph the target region according to the photographing parameters comprises: controlling the corresponding photographing device to photograph at least one target region coordinate range according to at least one set of photographing parameters.

4. The photographing control method according to claim 3, wherein The step of adjusting the photographing region coordinate range of at least one photographing device according to at least one target region coordinate range comprises: for any target region coordinate range, in response to the target region coordinate range not being completely covered by the photographing region coordinate range of the photographing device, determining the closest target photographing device according to the target region range, the target photographing device being a photographing device that does not completely cover other target region ranges; adjusting the photographing region coordinate range of the closest photographing device.

5. The photographing control method according to claim 3, wherein After the step of determining at least one set of photographing parameters according to the adjusted photographing region coordinate range of at least one photographing device, the method comprises: in response to there still being photographing devices that do not cover the target region range, acquiring preset photographing parameters corresponding to the photographing devices that do not cover the target region range, and determining the preset photographing parameters as the photographing parameters, or acquiring a preset photographing region coordinate range corresponding to the photographing devices that do not cover the target region range, and obtaining the photographing parameters according to the preset photographing region coordinate range.

6. The photographing control method according to claim 1, wherein The step of acquiring prediction distribution data comprises: acquiring a prediction time; inputting the prediction time into a trained distribution prediction model to obtain the prediction distribution data, the trained distribution prediction model being trained based on historical distribution data of the detected objects in the monitoring region and corresponding times, the historical distribution data including the number density.

7. The photographing control method according to claim 6, wherein The training of the distribution prediction model comprises: obtaining historical distribution data of the detection object in the monitoring area and a corresponding time, the historical distribution data including the number density; classifying the time to obtain at least one time period; inputting the at least one time period and the historical distribution data of the corresponding time period into the distribution prediction model for training.

8. The photographing control method according to claim 7, wherein The inputting the at least one time period and the historical distribution data of the corresponding time period into the distribution prediction model for training includes: inputting the at least one time period and the historical distribution data of the corresponding time period into the corresponding distribution prediction model according to the time classification type of the time period for training.

9. The photographing control method according to claim 8, wherein The inputting the prediction time into the trained distribution prediction model to obtain the prediction distribution data includes: obtaining a time classification type of the prediction time; inputting the prediction time into the distribution prediction model corresponding to the time classification type of the prediction time to obtain the prediction distribution data.

10. The photographing control method according to claim 8, wherein The number density is the number of the detection object appearing in the target area within the time range of the time period.

11. An electronic device, comprising: The electronic device includes a memory and a processor, the memory is used to store program data, and the program data can be executed by the processor to realize the photographing control method in any one of claims 1-10.

12. A computer program product, wherein, The memory stores program data, which can be executed by the processor to realize the photographing control method in any one of claims 1-10.

13. A computer readable storage medium, wherein, The memory stores program data, which can be executed by the processor to realize the photographing control method in any one of claims 1-10.

14. A photographing system, wherein, including: a photographing device for photographing a monitoring area; The electronic device according to claim 11 is in communication connection with the photographing device to realize the photographing control method in any one of claims 1-10.

15. The photographing system according to claim 14, wherein Further including an object detection device for identifying a detection object.

Images