Optical positioning configuration method and device, electronic equipment, computer storage medium and computer program product

Abstract

The embodiment of the invention provides an optical positioning configuration method and device, electronic equipment, a computer storage medium and a computer program product. The optical positioning configuration method comprises the steps that the simulation position of at least one object in an optical positioning field is determined, and a camera array used for executing optical positioning in the optical positioning field is arranged in the optical positioning field; performing space matching on the simulation pose parameters of the camera array and the optical positioning field, and determining a shielding orientation relation between a collection view field of the camera array in the optical positioning field and the simulation position of the at least one object according to a matching result; adjusting simulation pose parameters of the camera array according to the shielding azimuth relation, so that the proportion of a view blind area, shielded by the at least one object, of the collection view of the camera array is smaller than a preset threshold value; and performing parameter configuration on the camera array according to the adjusted simulation pose parameters.

Description

Technical Field

[0001] Embodiments of the present invention relate to the field of computer technology, and in particular, to an optical positioning configuration method, apparatus, electronic device, computer storage medium, and computer program product. Background Art

[0002] Generally speaking, optical positioning configuration refers to using a relatively fixed site space as an optical positioning site, and through optical positioning devices such as cameras and related technical means, accurately configuring a camera array according to objects in the optical positioning site, so as to accurately perform operations such as positioning, tracking, and measurement on positioning targets in the optical positioning scene subsequently.

[0003] In the traditional configuration process, professionals analyze the object distribution in the optical positioning site and the positioning of the cameras, systematically adjust the acquisition field of view of the cameras, and after the adjustment is completed, use professional positioning components to move in the optical positioning site, and repeatedly check the adjusted acquisition field of view of the cameras through observation. However, the traditional method has problems of low efficiency and poor accuracy in the manual configuration process. Summary of the Invention

[0004] In view of this, embodiments of the present invention provide an optical positioning configuration method, apparatus, electronic device, computer storage medium, and computer program product to solve the above problems.

[0005] According to a first aspect of the embodiments of the present invention, there is provided an optical positioning configuration method, including: determining a simulated position of at least one object in an optical positioning site, where a camera array for performing optical positioning in the optical positioning site is arranged in the optical positioning site; performing spatial matching between simulated pose parameters of the camera array and the optical positioning site, and determining an occlusion azimuth relationship between an acquisition field of view of the camera array in the optical positioning site and the simulated positions of the at least one object according to a matching result; adjusting the simulated pose parameters of the camera array according to the occlusion azimuth relationship, so that a proportion of a field of view blind area where the acquisition field of view of the camera array is occluded by the at least one object is less than a preset threshold; and performing parameter configuration on the camera array according to the adjusted simulated pose parameters.

[0006] According to a second aspect of the embodiments of the present invention, an optical positioning configuration device is provided, including: a determination module, which determines the simulated positions of at least one object in an optical positioning field, where a camera array for performing optical positioning in the optical positioning field is arranged in the optical positioning field; a matching module, which performs spatial matching on the simulated pose parameters of the camera array and the optical positioning field, and determines an occlusion azimuth relationship between the acquisition field of view of the camera array in the optical positioning field and the simulated positions of the at least one object according to the matching result; an adjustment module, which adjusts the simulated pose parameters of the camera array according to the occlusion azimuth relationship, so that the proportion of the field of view blind area of the acquisition field of view of the camera array occluded by the at least one object is less than a preset threshold; a configuration module, which configures the parameters of the camera array according to the adjusted simulated pose parameters.

[0007] According to a third aspect of the embodiments of the present invention, an electronic device is provided, including: a processor, a memory, a communication interface, and a communication bus. The processor, the memory, and the communication interface complete communication with each other through the communication bus; the memory is used to store at least one executable instruction, and the executable instruction causes the processor to execute the method described in the first aspect.

[0008] According to a fourth aspect of the embodiments of the present invention, a computer storage medium is provided, on which a computer program is stored. When the program is executed by a processor, the method described in the first aspect is implemented.

[0009] According to a fifth aspect of the embodiments of the present invention, a computer program product is provided, including computer instructions. When the computer instructions are executed by a processor, the method described in the first aspect is implemented.

[0010] In the solution of the embodiments of the present invention, through simulation data processing, spatial matching can be performed on the simulated pose parameters of the camera array and the optical positioning field. Furthermore, according to the matching result, the occlusion azimuth relationship between the acquisition field of view of the camera array in the optical positioning field and the simulated positions of at least one object can be determined, accurately determining the complex azimuth relationship affecting the field of view blind area of the camera array's acquisition field of view. In addition, according to the occlusion azimuth relationship, the simulated pose parameters of the camera array are adjusted so that the proportion of the field of view blind area of the acquisition field of view of the camera array occluded by at least one object is less than a preset threshold. The simulated pose parameters of the camera array are adjusted through the precise quantitative relationship between the field of view blind area ratio and the simulated pose parameters of the camera array. Therefore, according to the adjusted simulated pose parameters, the parameters of the camera array are configured, enabling the configured camera array to accurately perform optical positioning on the target in the optical positioning field. Since the above data processing is performed via simulation data processing, while ensuring the accuracy of parameter configuration, the efficiency of the parameter configuration process is also improved. Brief Description of the Drawings

[0011] In order to more clearly illustrate the technical solutions in the embodiments of the present invention or the prior art, the following will briefly introduce the drawings required for the description of the embodiments or the prior art. Obviously, the drawings in the following description are only some embodiments described in the embodiments of the present invention. For those of ordinary skill in the art, other drawings can also be obtained based on these drawings.

[0012] Figure 1 Spatial layout diagram of an optical positioning site according to some examples.

[0013] Figure 2 Flowchart of steps of an optical positioning configuration method according to some embodiments of the present invention.

[0014] Figure 3 According to Figure 2 Schematic diagram of the relationship between spatial sampling points and the blind area of the camera's field of view according to the embodiments.

[0015] Figure 4 According to Figure 2 Flowchart of steps of an optical positioning configuration method according to some examples of the embodiments.

[0016] Figure 5 Block diagram of the structure of an optical positioning configuration device according to other embodiments of the present invention.

[0017] Figure 6 Schematic diagram of the structure of an electronic device according to other embodiments of the present invention. Detailed Description of the Embodiments

[0018] In order to enable those skilled in the art to better understand the technical solutions in the embodiments of the present invention, the following will clearly and completely describe the technical solutions in the embodiments of the present invention in conjunction with the drawings in the embodiments of the present invention. Obviously, the described embodiments are only a part of the embodiments of the present invention, rather than all of the embodiments. Based on the embodiments in the embodiments of the present invention, all other embodiments obtained by those of ordinary skill in the art should fall within the scope of protection of the embodiments of the present invention.

[0019] The following further illustrates the specific implementation of the embodiments of the present invention in conjunction with the drawings of the embodiments of the present invention.

[0020] Figure 1 Spatial layout diagram of an optical positioning site according to some examples. Figure 1The spatial layout of the optical positioning site 100 includes a camera array 10. When the optical positioning site 100 is an indoor site, the camera array 10 can be arranged on the surrounding walls or ceiling of the indoor site. When the optical positioning site 100 is an outdoor site, the camera array 10 can be arranged on a camera array support in the outdoor site. As Figure 1 shown, the camera array 10 includes cameras 11, 12, 13, 14, and 15. The cameras in the camera array 10 can be arranged at uniform intervals. Alternatively, they can also be arranged at non-uniform intervals. The area before the dotted line drawn from each camera represents the acquisition field of view of that camera.

[0021] Furthermore, in the optical positioning site 100, there may be objects such as object 20 that block the acquisition field of view of the cameras. There may be spatial positions in the optical positioning site 100 that cannot be acquired by any camera or cannot be acquired by a sufficient number of cameras, which may affect operations such as positioning, tracking, and measurement of positioning targets in the optical positioning scenario. In Figure 1 the example, object 20 can include objects 21, 22, 23, and 24. For example, object 21 is within the acquisition fields of view of cameras 11 and 12, object 22 is within the acquisition field of view of camera 14, object 23 is within the acquisition fields of view of cameras 14 and 15, and object 24 is within the acquisition field of view of camera 15. By professionals analyzing the distribution of objects 20 in the optical positioning site 100 and the positioning of the camera array 10, the acquisition fields of view of the cameras in the camera array 10 can be systematically adjusted. However, there are problems such as low efficiency and poor configuration accuracy in the manual configuration process. For this reason, the various embodiments of the present invention can improve both the accuracy of parameter configuration and the efficiency of the parameter configuration process.

[0022] Specifically, Figure 2 is a flowchart of the steps of an optical positioning configuration method according to some embodiments of the present invention. Figure 2 The optical positioning configuration method is executed by an electronic device with three-dimensional data processing capabilities such as a three-dimensional simulation platform. The optical positioning configuration method includes:

[0023] S210: Determine the simulation position of at least one object in the optical positioning site, where a camera array for performing optical positioning in the optical positioning site is arranged in the optical positioning site.

[0024] It should be understood that the camera array can be arranged at any position in the optical positioning site. Camera arrays arranged in different ways have different acquisition fields of view. The camera array captures images of positioning targets in the optical positioning site within its acquisition field of view to achieve optical positioning.

[0025] It should also be understood that at least one object can be identified in the optical positioning field, and the simulated position of at least one object can be determined. At least one object may block the acquisition field of view of the camera array. The simulated position of the object can be determined through a three-dimensional data processing environment such as a three-dimensional simulation platform, and the parameters of the camera array can be configured according to the simulated position. The simulated position can be the position in the coordinate system of the optical positioning scenario.

[0026] S220: Perform spatial matching between the simulated pose parameters of the camera array and the optical positioning field, and determine the occlusion azimuth relationship between the acquisition field of view of the camera array in the optical positioning field and the simulated positions of at least one object according to the matching result.

[0027] It should be understood that the objects in the text include but are not limited to physical objects existing in the optical positioning field. In virtual shooting or video special effects scenarios, physical objects include but are not limited to props or physical models, etc. In addition, the simulated pose parameters of the camera array include the position of the camera (e.g., translation vector) and the direction (e.g., rotation matrix), and these pose parameters define the position and orientation in the coordinate system of the camera. In addition, performing spatial matching between the simulated pose parameters of the camera array and the optical positioning field means mapping the position and orientation in the coordinate system of the camera array to the coordinate system of the optical positioning scenario, which is consistent with the coordinate system of the simulated position of the object, so that the occlusion azimuth relationship indicating whether an object blocks the acquisition field of view of the camera can be checked according to the matching result, resulting in a blind area in the field of view of the camera array.

[0028] S230: Adjust the simulated pose parameters of the camera array according to the occlusion azimuth relationship, so that the proportion of the blind area in the acquisition field of view of the camera array blocked by at least one object is less than a preset threshold.

[0029] It should be understood that when adjusting the simulated pose parameters, the simulated pose parameters of the camera array can be adjusted according to the occlusion azimuth relationship to reduce or eliminate the field of view blind area. For example, the debugging operations include, but are not limited to, changing the position parameter in the external parameters of the moving camera, changing the orientation parameter in the external parameters of the camera, or adjusting the internal parameters of the camera (such as the focal length), etc. In addition, the field of view blind area ratio can accurately quantify and characterize the state of the field of view blind area of the optical positioning site. The field of view blind area ratio can indicate the ratio of the area of the field of view blind area that cannot be captured by the camera array to the area of the optical positioning site. For example, if the field of view blind area ratio is less than a preset threshold (such as 10% or 5%, etc.), it can be considered that the optical positioning site has no field of view blind area. That is, the field of view blind area can be reduced or eliminated by reducing the field of view blind area ratio. For example, the field of view blind area ratio of the acquisition field of view of the adjusted camera array blocked by at least one object can be calculated first. If this ratio is greater than the preset threshold, the pose parameters of the camera need to be further adjusted until the field of view blind area ratio is less than the preset threshold. The following text introduces a method for calculating the field of view blind area ratio based on sampling points. Those skilled in the art should understand that the field of view blind area ratio can also be calculated based on other methods as long as it can reflect the ratio of the area of the field of view blind area that cannot be captured by the camera array to the area of the optical positioning site.

[0030] S240: Configure the parameters of the camera array according to the adjusted simulated pose parameters.

[0031] It should be understood that when configuring the parameters of the camera array with the adjusted simulated pose parameters, the position parameters (such as the translation vector) and orientation parameters (such as the rotation matrix) of each camera indicated by the adjusted simulated pose parameters can be used to configure the external parameters of the corresponding camera while keeping the internal parameters of each camera.

[0032] In the solution of the embodiment of the present invention, through simulation data processing, the spatial matching between the simulated pose parameters of the camera array and the optical positioning site can be performed. Furthermore, according to the matching result, the occlusion azimuth relationship between the acquisition field of view of the camera array in the optical positioning site and the simulated positions of at least one object can be determined, and the complex azimuth relationship affecting the acquisition field of view blind area of the camera array can be accurately determined. In addition, according to the occlusion azimuth relationship, the simulated pose parameters of the camera array are adjusted so that the field of view blind area ratio of the acquisition field of view of the camera array blocked by at least one object is less than the preset threshold. The simulated pose parameters of the camera array are adjusted through the precise quantitative relationship between the field of view blind area ratio and the simulated pose parameters of the camera array. Therefore, the parameters of the camera array are configured according to the adjusted simulated pose parameters, so that the configured camera array can accurately perform optical positioning on the target in the optical positioning site. Since the above data processing is performed through simulation data processing, the efficiency of the configuration process is improved while ensuring the accuracy of parameter configuration.

[0033] In some embodiments, the attitude parameters of each camera in the camera array can be obtained. Based on the layout orientation of the camera array in the optical positioning scenario, a spatial matching relationship is established among the positions of each camera, multiple sampling points in the space of the optical positioning scenario, and at least one object that may cause occlusion. For example, a common coordinate system (such as the world coordinate system) is established based on the optical positioning scenario, and the attitude parameters of each camera are mapped to the common coordinate system, thereby establishing the orientation relationship between the attitude of the camera and each object and each sampling point in the optical positioning scenario, so as to accurately determine the field-of-view blind areas of each camera for each sampling point.

[0034] To determine the position of at least one object that may cause occlusion in the optical positioning scenario, three-dimensional image data of the optical positioning site can be collected, and the three-dimensional image data can be preprocessed to identify the position of at least one object that may cause occlusion in the optical positioning site.

[0035] In some examples, three-dimensional image data of the optical positioning site can be obtained, and a surface mesh representation can be performed on the three-dimensional image data. That is to say, the optical positioning site has relatively complex position features and shape features, and the three-dimensional image data can more reliably reflect these position features and shape features, avoiding large errors in parameter configuration caused by the loss of feature information. Then, feature recognition is performed on the surface mesh representation to obtain at least one object in the optical positioning site, and the recognized position of the at least one object is marked as the simulation position. That is to say, performing a surface mesh representation on the three-dimensional image data is beneficial to improving the data processing efficiency while retaining the position features and shape features of the optical positioning site. That is to say, by performing feature recognition on the surface mesh representation, at least one object that may occlude the field-of-view blind area of the camera array can be efficiently recognized.

[0036] It should be understood that the above spatial matching process can be executed in a three-dimensional data processing environment such as a three-dimensional simulation platform by importing the attitude parameters of each camera in the camera array and the simulation positions of at least one object. The process of determining the simulation positions of at least one object in the optical positioning scenario can be carried out in a three-dimensional data processing environment such as a three-dimensional simulation platform, or the positions of at least one object in the optical positioning scenario can be obtained through preprocessing, and after marking the simulation positions of at least one object in the optical positioning site, they can be imported into a three-dimensional data processing environment such as a three-dimensional simulation platform.

[0037] Furthermore, in some other embodiments, to accurately determine the field-of-view blind areas of each camera for each sampling point in the simulation environment, after spatially sampling the optical positioning scenario, according to the spatial matching relationship, it can be determined one by one whether each sampling point is in the field-of-view blind area of each camera.

[0038] In order to adjust the simulated pose parameters of the camera array according to the occlusion azimuth relationship, so that the proportion of the field-of-view blind area of the acquisition field-of-view of the camera array occluded by at least one object is less than a preset threshold, the occlusion azimuth relationship indicating the proportion of the field-of-view blind area of the acquisition field-of-view of the camera array occluded by the at least one object can be determined. And when the proportion of the field-of-view blind area of the camera array is greater than the preset threshold, while maintaining the position parameters of each camera in the camera array, the orientation parameters of at least some cameras are adjusted to adjust the occlusion azimuth relationship. Then, when the proportion of the field-of-view blind area of the camera array is less than the preset threshold after the orientation parameters of at least some cameras are adjusted, the adjusted simulated pose parameters are output.

[0039] That is to say, adjusting the orientation parameters while maintaining the position parameters of each camera in the camera array is conducive to accurately determining the internal factors affecting the proportion of the field-of-view blind area when adjusting the orientation parameters, so as to achieve the target of the proportion of the field-of-view blind area with as few cameras as possible. When the occlusion azimuth relationship indicates that the proportion of the field-of-view blind area of the acquisition field-of-view of the camera array is less than the preset threshold, it means that the target of the proportion of the field-of-view blind area is achieved only by adjusting the orientation parameters. Therefore, the adjusted simulated pose parameters can be directly output to configure the parameters of the camera array. Those skilled in the art should understand that the simulated pose parameters of the camera array can also be adjusted by other means, such as adjusting the position parameters and orientation parameters simultaneously. In addition, for the case where the proportion of the field-of-view blind area is equal to the preset threshold, it can be regarded as having achieved the adjustment target as needed, or having met the requirement of the proportion of the field-of-view blind area, or regarded as needing further adjustment.

[0040] Specifically, as the occlusion azimuth relationship indicating the proportion of the field-of-view blind area of the acquisition field-of-view of the camera array occluded by at least one object, the spatial position of the optical positioning site can be sampled to obtain a plurality of sampling points. Then, according to the occlusion azimuth relationship, it is determined whether each sampling point is in the field-of-view blind area of the camera array. Then, the ratio between the number of sampling points in the field-of-view blind area of the camera array among the plurality of sampling points and the number of the plurality of sampling points is determined as the proportion of the field-of-view blind area of the acquisition field-of-view of the camera array.

[0041] That is to say, the proportion of the field-of-view blind area depends on the proportion of the sampling points in the field-of-view blind area of the camera array. Sampling the spatial position of the optical positioning site with a given sampling accuracy can improve the calculation efficiency of the proportion of the field-of-view blind area to a certain extent. Generally speaking, as the sampling accuracy becomes higher, the obtained proportion of the field-of-view blind area can represent a more accurate field-of-view blind area situation. As the sampling accuracy becomes lower, the calculation efficiency of the proportion of the field-of-view blind area will be more significantly improved.

[0042] Next, an exemplary description will be given of determining whether each sampling point is in the field-of-view blind area of the camera array. In some examples, if a sampling point is blocked within the acquisition fields of view of more than a preset number of cameras, it is determined that the sampling point is in the field-of-view blind area of the camera array. Generally speaking, the preset number here can be a value or a range of values preset according to experience. For example, the lower limit value of the preset number can be zero. In this case, if there is a sampling point blocked within the acquisition field of view of any camera, it can be considered that the sampling point is in the field-of-view blind area of the camera array. For another example, the upper limit value of the preset number can be the difference between the total number of cameras in the camera array and 1. In this case, only when the sampling point is blocked within the acquisition fields of view of all cameras, it is considered that the sampling point is in the field-of-view blind area of the camera array. For another example, the preset number can be a value between the above-mentioned lower limit value and upper limit value. The smaller the preset number, the stricter the condition for determining that the sampling point is in the field-of-view blind area of the camera array, and the higher the reliability of the camera array after parameter configuration for performing optical positioning on the target in the optical positioning field; on the contrary, the larger the preset number, the looser the condition for determining that the sampling point is in the field-of-view blind area of the camera array, the lower the requirement for the number of cameras in the camera array, and the lower the cost of performing optical positioning on the target in the optical positioning field.

[0043] Further, in some other examples, when determining whether each sampling point is blocked within the acquisition field of view of each camera in the camera array, the purpose is to determine whether the sampling point is visible within the acquisition field of view of the camera. Specifically, each camera has a certain acquisition viewing angle for given internal parameters. The acquisition field of view can be a conical space defined by the acquisition viewing angle. If a sampling point is not within the acquisition viewing angle of the camera, then the sampling point is not within the acquisition field of view of the camera and is invisible; if a sampling point is within the acquisition viewing angle of the camera, but the sampling point is blocked by at least one object, resulting in the sampling point not being captured and acquired within the acquisition field of view of the camera, then the sampling point is not within the acquisition field of view of the camera and is invisible.

[0044] It should be understood that according to the spatial matching result between the camera array and the optical positioning field, the spatial position relationship between the sampling point, the camera with the acquisition viewing angle, and at least one object can be determined when the sampling point is within the acquisition viewing angle of the camera, and based on the above-mentioned spatial position relationship, it can be determined whether the sampling point is blocked by at least one object. For example, the virtual connection line between the sampling point and at least one object passes through a camera, and the sampling point is blocked by at least one object. For another example, when the virtual connection line between the sampling point and the camera passes through the simulation position of at least one object, the sampling point is blocked by at least one object.

[0045] Without loss of generality, as an example of determining whether each sampling point is occluded within the acquisition field of view of each camera in the camera array, it can be first determined whether each sampling point is within the acquisition field of view of each camera in the camera array. If a sampling point is within the acquisition field of view of a camera and the virtual connection line between the sampling point and the camera passes through the simulated positions of at least one object, it is determined that the sampling point is occluded within the acquisition field of view of the camera. Alternatively, in addition to the field of view blind spots caused by object occlusion, the field of view blind spots outside the acquisition field of view of the camera itself can also be considered. Therefore, if a sampling point is not within the acquisition field of view of a camera, it can be directly determined that the sampling point is occluded within the acquisition field of view of the camera.

[0046] Alternatively, when adjusting the simulated pose parameters of the camera array according to the occlusion orientation relationship, if the proportion of the field of view blind spots in the camera array is greater than a preset threshold after the orientation parameters of at least some cameras are adjusted, at least one camera can also be added to the camera array and the camera array can be updated.

[0047] Among them, the condition for adding a camera can be that the adjustment of the pose parameters of the current camera array has reached the condition for ending the adjustment, that is, for the current number of cameras, the requirement for the proportion of the field of view blind spots cannot be achieved by adjusting the pose parameters. The condition for ending the adjustment can be set as needed. For example, the pose parameters of at least some cameras in the current camera array have been adjusted a preset number of times and in a preset manner, but the proportion of the field of view blind spots is still greater than the preset threshold. Specifically, at least one camera can be added at the remaining positions of the camera array so that a scattered distribution is formed between at least one camera and each of the cameras already set in the camera array, so as to make the proportion of the field of view blind spots greater than the preset threshold by adding as few cameras as possible. For example, at least one camera can be added to the camera array based on the initial position information and the initial attitude information. Exemplarily, the initial position information of at least one camera can indicate that the sum of the squares of the distances between the positions of at least one camera and the positions of each of the cameras already set is the largest, and the initial attitude information of at least one camera can indicate the random orientation parameters of at least one camera.

[0048] That is to say, when the occlusion orientation relationship indicates that the proportion of the field of view blind spots in the acquisition field of view of the camera array is greater than the preset threshold, it indicates that the goal of the proportion of the field of view blind spots cannot be achieved only by adjusting the orientation parameters, and the number of cameras in the camera array needs to be increased to further reduce the proportion of the field of view blind spots.

[0049] Further, when adjusting the simulated pose parameters of the camera array according to the occlusion orientation relationship, if it is determined that the field of view blind area ratio of the camera array is greater than a preset threshold, the orientation parameters of at least some cameras can be adjusted while keeping the position parameters of the cameras in the camera array unchanged, and the change of the field of view blind area ratio of the camera array can be determined after the adjustment.

[0050] In some examples, as a specific implementation of adjusting the orientation parameters of at least some cameras, currently selected cameras (for example, randomly select 10 cameras) can be first selected from the cameras in the camera array, and the orientation parameters of the currently selected cameras can be adjusted. Then, it is determined whether the field of view blind area ratio decreases after the orientation parameters of the currently selected cameras are adjusted. If the field of view blind area ratio of the camera array decreases, while keeping the orientation parameters of the currently selected cameras unchanged, some cameras in the remaining cameras (for example, randomly select another 10 cameras) are used as the updated currently selected cameras to adjust the orientation parameters of the updated currently selected cameras. That is, when the change of the field of view blind area ratio of the camera array is a decrease, the value of the field of view blind area ratio is in the convergence stage during the adjustment of the camera orientation parameters of the camera array, and retaining it is beneficial to optimizing the camera orientation parameters.

[0051] Alternatively, if the field of view blind area ratio of the camera array increases after the orientation parameters of the currently selected cameras are adjusted, the orientation parameters of the currently selected cameras are restored to before the adjustment, and some cameras in the remaining cameras are used as the updated currently selected cameras to adjust the orientation parameters of the updated currently selected cameras. That is, when the change of the field of view blind area ratio of the camera array is an increase, the value of the field of view blind area ratio is not in the convergence stage during the adjustment of the camera orientation parameters of the camera array, and abandoning the adjustment result is beneficial to avoiding deteriorating the camera orientation parameters.

[0052] That is to say, when reducing the field of view blind area by adjusting the orientation parameters of each camera, there is a problem of how to optimize the orientation parameters of each camera. Currently selected cameras are sequentially selected from each camera, and some cameras in the remaining cameras are used as the updated currently selected cameras when the field of view blind area ratio decreases, which can iteratively adjust the orientation parameters, improving the marginal effect of the orientation parameters on the field of view blind area. That is, when the field of view blind area ratio converges to a relatively small value, the optimal configuration of the orientation parameters of each camera is achieved.

[0053] Furthermore, when adjusting the orientation parameters of the current partial camera, various methods can be adopted as needed until the condition for ending the adjustment is met. For example, a single adjustment can be performed on the current partial camera using a preset orientation angle, or multiple iterative adjustments can be performed on the current partial camera. Correspondingly, when performing multiple iterative adjustments on the current partial camera, before each adjustment of the current partial camera, a preset angle step is added to the orientation angle of the previous adjustment, and then the current adjustment of the current partial camera is performed. It should be understood that the preset angle step is used as the vector reference for multiple iterative adjustments, and the value of the preset angle step can be a value preset according to experience or a random value, and the direction of the preset angle step can be any preset direction or random direction in the coordinate system of the external parameters of the camera.

[0054] Without loss of generality, in multiple adjustments of the orientation parameters of the current partial camera with a preset angle step, if the proportion of the field-of-view blind area decreases after the current adjustment of the orientation parameters of the current partial camera, the next adjustment of the orientation parameters of the current partial camera is performed until the condition for ending the adjustment is met (for example, the adjustment for the current partial camera reaches a preset number of times, or the proportion of the field-of-view blind area is lower than a threshold), and the orientation parameters of the current partial camera can be maintained. If the proportion of the field-of-view blind area does not decrease after the current adjustment of the orientation parameters of the current partial camera, it can be regarded that the condition for ending the iteration has been reached, and the orientation parameters of the current partial camera can be restored to before the current adjustment. Those skilled in the art should understand that the method for adjusting the orientation parameters of the current partial camera and the condition for ending the adjustment are not limited to the above.

[0055] That is to say, during the iteration of different partial cameras, adjusting the orientation parameters with a preset angle step can further improve the convergence accuracy of the field-of-view blind area and further optimize the orientation parameter configuration of each camera in the camera array.

[0056] Those skilled in the art should understand that the method for adjusting the simulated pose parameters of the camera array is not limited to the above method. For example, for all or part of the selected cameras in the camera array, they can be adjusted as a whole in a preset adjustment method. The adjustment method is, for example, but not limited to randomly changing the orientation parameters of each camera, or changing the orientation parameters of each camera with a preset angle step and a preset direction, etc., until the condition for stopping the adjustment is met.

[0057] Specifically, as Figure 3An optically positioned field after spatial sampling is shown, obtaining multiple sampling points formed by each dotted grid. Among them, sampling point A, sampling point B, and sampling point C are exemplary sampling points among all the sampling points. For camera 310 in the camera array, the area between the two dotted lines drawn from camera 310 represents the acquisition field of view of camera 310, and the viewing angle of the acquisition field of view of camera 310 is determined by the internal parameters of camera 310. In Figure 3 the example, object 321 is within the acquisition field of view of camera 310, and object 322 is not within the acquisition field of view of camera 310.

[0058] That is to say, when determining whether a sampling point is within the acquisition field of view of a camera, it is not necessary to consider the simulated positions of at least one object. Since the camera itself has internal parameters and external parameters, and the internal parameters and external parameters indicate the acquisition viewing angle of the camera, for sampling points that do not meet the internal parameters and external parameters, even if the sampling points are not blocked by objects, they will not appear in the acquisition field of view of the camera.

[0059] For sampling points that meet the internal parameters and external parameters, it is possible to further confirm whether the sampling points are blocked by objects. Therefore, when determining whether a sampling point is within the acquisition field of view of a camera, the virtual connection line between the sampling point and the camera is determined to judge whether the sampling point is blocked in the acquisition field of view of the camera, and it is reliably determined whether the sampling point has an impact on the field of view blind area.

[0060] For example, in Figure 3 the example, the virtual connection line between sampling point A and camera 310 passes through object 321, and sampling point A has an impact on the field of view blind area of camera 310, and thus has an impact on the field of view blind area of the camera array. Another example is that the virtual connection line between sampling point B and camera 310 does not pass through object 321, and sampling point B has no impact on the field of view blind area of camera 310, and thus has no impact on the field of view blind area of the camera array. Another example is that sampling point C is not within the acquisition field of view of camera 310 and has no impact on the field of view blind area of camera 310. In addition, sampling point C may be within the acquisition field of view of a camera outside camera 310 in the camera array and may have an impact on the field of view blind area of the camera array, which depends on whether the connection between sampling point C and other cameras passes through object 322.

[0061] Alternatively, for sampling points that do not meet the internal parameters and external parameters, even if the sampling points are not blocked by objects, they will not appear in the acquisition field of view of the camera. In this case, if a sampling point is not within the acquisition field of view of a camera, it is determined that the sampling point is blocked in the acquisition field of view of the camera.

[0062] Next, it will be described in combination with Figure 4 description Figure 2It is the optical positioning configuration process for some examples of the embodiments. Figure 4 The optical positioning configuration process includes:

[0063] Step S410: Obtain the three-dimensional image data of the optical positioning site, and perform surface mesh representation on the three-dimensional image data, and continue to execute step S420. For example, a camera array or other three-dimensional scanning device can be used to obtain the three-dimensional image data of the optical positioning site, and the three-dimensional image data includes but is not limited to point cloud data, depth image data, etc. For another example, when converting the three-dimensional image data into surface mesh representation, the point cloud data can be fitted into a mesh grid such as a triangular grid or a polygon grid to form a continuous surface model.

[0064] Step S420: Perform feature recognition on the surface mesh representation, mark the simulated positions of at least one object, and continue to execute step S450. For example, the specific features identified in the surface mesh representation include but are not limited to the edges, corner points or specific marker points of the object. In addition, the position of the object can be determined according to the identified specific features, and in the three-dimensional data processing environment, the positions of the specific features are marked as simulated positions.

[0065] Step S430: Sample the spatial positions of the optical positioning site to obtain a plurality of sampling points, and continue to execute step S440. For example, a mathematical model of the optical positioning site (for example, including the size, contour shape, etc. of the site) can be created, and a plurality of sampling points are uniformly or randomly selected in the optical positioning site to improve the data processing efficiency while effectively evaluating the field of view coverage and occlusion conditions of the camera array. As an example of uniformly selecting a plurality of sampling points, a three-dimensional grid can be divided in the simulation space of the optical positioning site, and spatial sampling is performed to make the boundary points of each three-dimensional grid become sampling points.

[0066] Step S440: Determine the sampling points occluded in the acquisition field of view of each camera, and continue to execute step S450. For example, for each sampling point, check whether the sampling point is occluded in the acquisition field of view of each camera to obtain the occlusion azimuth relationship. Specifically, ray tracing or geometric analysis can be used to determine which sampling points are occluded by the object.

[0067] Step S450: Determine that the sampling point occluded within the acquisition fields of view of more than a preset number of cameras is in the blind area of the field of view of the camera array, and continue to execute Step S460. For example, if a sampling point is occluded within the acquisition fields of view of more than a preset number of cameras, then determine that the sampling point is in the blind area of the field of view of the camera array. The preset number can be determined according to specific application requirements and site layout. For example, the preset number of cameras is one camera or two cameras. Also, for example, if a sampling point does not appear within the acquisition fields of view of more than a preset number of cameras, then the sampling point is also in the blind area of the field of view of the camera array.

[0068] Step S460: Determine whether the blind area ratio of the acquisition field of view of the camera array is less than a preset threshold? If yes, then execute Step S480; if no, then execute Step S470. In Step S470, multiple iterative adjustments can be performed on the current partial cameras. Before each adjustment of the current partial cameras, a preset angular step is added to the orientation angle of the previous adjustment, and then the current adjustment is performed on the current partial cameras.

[0069] Step S470: Adjust the orientation parameters of at least some cameras, and determine whether the blind area ratio of the camera array is less than the preset threshold after the camera orientation parameters are adjusted? If yes, then continue to execute Step S480; if no, then continue to execute Step S490. That is, in Step S470, while keeping the position parameters of each camera in the camera array, the orientation parameters of at least some cameras can be adjusted to adjust the occlusion azimuth relationship, and determine whether the blind area ratio of the camera array is less than the preset threshold after the orientation parameters of at least some cameras are adjusted.

[0070] Step S480: Output the adjusted simulation pose parameters. For example, the orientation parameters that make the blind area ratio less than the preset threshold can be output corresponding to the camera identifiers, so as to configure the corresponding cameras with the adjusted orientation parameters. Alternatively, the adjusted orientation parameters of the cameras can also be associated and stored with the camera identifiers.

[0071] Step S490: Add and arrange at least one camera in the camera array, and continue to execute Step S440. In Step S490, if the blind area ratio is still greater than the preset threshold, consider adding at least one camera (for example, an example of one camera) in the camera array to improve the field of view coverage and reduce the blind area. It should be understood that the initial position information and initial attitude information of the at least one camera added and arranged can be as described above.

[0072] Next, it will be combined with Figure 5 Describe the optical positioning configuration device according to some other embodiments of the present invention. Figure 5 the optical positioning configuration device of Figure 2corresponding to the optical positioning configuration method, including:

[0073] A determination module 510 determines the simulated positions of at least one object in the optical positioning field, where a camera array for performing optical positioning in the optical positioning field is arranged in the optical positioning field;

[0074] A matching module 520 performs spatial matching between the simulated pose parameters of the camera array and the optical positioning field, and determines the occlusion azimuth relationship between the acquisition field of view of the camera array in the optical positioning field and the simulated positions of the at least one object according to the matching result;

[0075] An adjustment module 530 adjusts the simulated pose parameters of the camera array according to the occlusion azimuth relationship, so that the proportion of the field of view blind area of the acquisition field of view of the camera array occluded by the at least one object is less than a preset threshold;

[0076] A configuration module 540 configures the parameters of the camera array according to the adjusted simulated pose parameters.

[0077] In the solution of the embodiment of the present invention, through simulation data processing, spatial matching can be performed between the simulated pose parameters of the camera array and the optical positioning field. Furthermore, according to the matching result, the occlusion azimuth relationship between the acquisition field of view of the camera array in the optical positioning field and the simulated positions of at least one object can be determined, accurately determining the complex azimuth relationship affecting the acquisition field of view blind area of the camera array. In addition, according to the occlusion azimuth relationship, the simulated pose parameters of the camera array are adjusted so that the proportion of the field of view blind area of the acquisition field of view of the camera array occluded by at least one object is less than a preset threshold. The simulated pose parameters of the camera array are adjusted through the precise quantitative relationship between the field of view blind area ratio and the simulated pose parameters of the camera array. Therefore, according to the adjusted simulated pose parameters, the parameters of the camera array are configured, so that the configured camera array can accurately perform optical positioning on the target in the optical positioning field. Since the above data processing is performed via simulation data processing, the efficiency of the configuration process is improved while ensuring the accuracy of parameter configuration.

[0078] For example, in video special effects production, it is necessary to integrate virtual characters with real scenes and actors for shooting, add physical models to virtual characters for actor performance interaction, and the physical models of virtual characters will be replaced by virtual characters in special effects later, but during the shooting process, it is necessary to continuously perform optical positioning on the models of virtual characters. Since the actions and positions of actors need to match those of virtual characters when actors perform in the optical positioning venue. For example, when an actor makes a movement to avoid an attack by a virtual character, the optical positioning needs to accurately capture the position of the virtual character model so that the attack action of the virtual character can reasonably target the actor. Due to the occlusion of objects such as props or physical models in the optical positioning venue, the camera array for shooting may not be able to completely capture the full-body actions of the virtual character model. For example, when the virtual character model moves in the optical positioning venue, part of it may be occluded by some props or physical models, resulting in the inability to accurately restore the complete posture of the virtual object during special effects production. Therefore, after configuring the parameters of the camera array for shooting, the visual blind area of the camera array for shooting can be significantly reduced.

[0079] Specifically, taking the optical positioning venue as the real scene, the camera array for shooting that matches the space of the optical positioning venue tracks and locates moving targets such as virtual character models, and accurately determines the position information and posture information of the moving targets in the real scene. In addition, through the coordinate system of the optical positioning scene, the position parameters and posture parameters of the virtual character are determined, and the position and trajectory of the moving target in the real scene are also accurately determined, so as to accurately present the dynamic interaction relationship and static position relationship between the actor and the virtual character in the video special effects, and realistically integrate the virtual character into the shooting picture of the camera array. By using the optical positioning configuration method of the embodiment of the present invention, through simulation data processing, the spatial matching relationship between the camera array and the optical positioning venue, and the occlusion azimuth relationship between the acquisition field of view of the camera array and the objects in the venue (for example, props or physical models, including but not limited to natural props such as trees and rocks, and artificial props for enhancing the scene atmosphere) are determined. According to these relationships, the simulated pose parameters of the camera array are adjusted, so that the proportion of the occluded visual blind area is reduced, so that the complete actions of the virtual object during movement can be completely captured, and the problem of the visual blind area is solved.

[0080] In addition, during the traditional optical positioning configuration process, it is necessary to repeatedly adjust the position and attitude of the camera array on-site and determine the optimal configuration scheme through actual shooting tests. This process is time-consuming and laborious, and it is difficult to guarantee the accuracy. Because the on-site environment is complex, it is necessary to retest after each adjustment, and it is easily affected by various interference factors. By using the simulation data processing method of the embodiment of the present invention, the simulated pose parameters of the camera array can be quickly and accurately adjusted in a virtual environment. The influence of various objects in the site on the camera's field of view is simulated through simulation data, and an optimized camera configuration scheme is determined in advance. Then, according to the adjusted simulated pose parameters, the actual camera array is configured with parameters. This not only ensures the accuracy of the parameter configuration but also greatly improves the efficiency of the configuration process, saving a large amount of time and labor costs.

[0081] In some other embodiments, the adjustment module is specifically configured to: determine the occlusion azimuth relationship indicating the proportion of the field-of-view blind area where the acquisition field of view of the camera array is occluded by the at least one object; when the proportion of the field-of-view blind area of the camera array is greater than a preset threshold, while maintaining the position parameters of each camera in the camera array, adjust the orientation parameters of at least some of the cameras to adjust the occlusion azimuth relationship; when the proportion of the field-of-view blind area of the camera array is less than the preset threshold after the orientation parameters of at least some of the cameras are adjusted, output the adjusted simulated pose parameters.

[0082] In some other embodiments, the adjustment module is further configured to: when the proportion of the field-of-view blind area of the camera array is greater than the preset threshold after the orientation parameters of at least some of the cameras are adjusted, add at least one camera to the camera array and update the camera array.

[0083] In some other embodiments, the adjustment module is specifically configured to: determine the proportion of the field-of-view blind area where the acquisition field of view of the camera array is occluded by the at least one object; while maintaining the position parameters of each camera in the camera array, adjust the orientation parameters of the current part of the cameras in each camera; if the proportion of the field-of-view blind area decreases after the orientation parameters of the current part of the cameras are adjusted, while maintaining the orientation parameters of the current part of the cameras, and taking some of the remaining cameras as the updated current part of the cameras to adjust the orientation parameters of the updated current part of the cameras.

[0084] In some other embodiments, the adjustment module is specifically configured to: if the proportion of the field-of-view blind area increases after the orientation parameters of the current part of the cameras are adjusted, restore the orientation parameters of the current part of the cameras to before the adjustment, and take some of the remaining cameras as the updated current part of the cameras to adjust the orientation parameters of the updated current part of the cameras.

[0085] In some other embodiments, the adjustment module is specifically configured to: in multiple adjustments of the orientation parameter of the current partial camera with a preset angular step, if the field-of-view blind area ratio decreases after the current adjustment of the orientation parameter of the current partial camera, perform the next adjustment of the orientation parameter of the current partial camera; if the field-of-view blind area ratio does not decrease after the current adjustment of the orientation parameter of the current partial camera, restore the orientation parameter of the current partial camera to before the current adjustment.

[0086] In some other embodiments, the adjustment module is specifically configured to: sample the spatial position of the optical positioning site to obtain a plurality of sampling points; determine whether each sampling point is in the field-of-view blind area of the camera array according to the occlusion azimuth relationship; determine the ratio between the number of sampling points in the field-of-view blind area of the camera array among the plurality of sampling points and the number of the plurality of sampling points as the field-of-view blind area ratio of the acquisition field of view of the camera array.

[0087] In some other embodiments, the adjustment module is specifically configured to: determine whether each sampling point is occluded within the acquisition field of view of each camera in the camera array; if a sampling point is occluded within the acquisition field of view of more than a preset number of cameras, determine that the sampling point is in the field-of-view blind area of the camera array.

[0088] In some other embodiments, the adjustment module is specifically configured to: determine whether each sampling point is within the acquisition field of view of each camera in the camera array; if a sampling point is within the acquisition field of view of a camera and the virtual connection line between the sampling point and the camera passes through the simulation position of at least one object, determine that the sampling point is occluded in the acquisition field of view of the camera; if a sampling point is not within the acquisition field of view of a camera, directly determine that the sampling point is occluded in the acquisition field of view of the camera.

[0089] In some other embodiments, the determination module is specifically configured to: obtain the three-dimensional image data of the optical positioning site, and perform a surface mesh representation on the three-dimensional image data; perform feature recognition on the surface mesh representation to obtain at least one object in the optical positioning site; mark the recognition position of the at least one object as the simulation position.

[0090] It should be understood that for the specific implementation of each module in the optical positioning configuration device, reference may be made to the corresponding descriptions of the corresponding steps in the embodiments of the optical positioning configuration method, and there are corresponding beneficial effects, which will not be elaborated here. Those skilled in the art can clearly understand that for the convenience and conciseness of description, the specific working processes of the above optical positioning configuration device and modules can refer to the corresponding process descriptions in the embodiments of the optical positioning configuration method, which will not be repeated here.

[0091] Refer to Figure 6, showing a schematic structural diagram of an electronic device according to another embodiment of the present invention. The specific embodiments of the present invention do not limit the specific implementation of the electronic device.

[0092] As Figure 6 shown, the electronic device may include: a processor 602 for executing a program 610, a communications interface 604, a memory 606, and a communication bus 608.

[0093] The processor, the communications interface, and the memory communicate with each other through the communication bus.

[0094] The communications interface is used to communicate with other electronic devices or servers.

[0095] The processor is used to execute the program, and specifically may execute the relevant steps in the above method embodiments.

[0096] Specifically, the program may include program code, and the program code includes computer operation instructions.

[0097] The processor may be a CPU, or a specific integrated circuit ASIC (Application Specific Integrated Circuit), or one or more integrated circuits configured to implement the embodiments of the present invention. One or more processors included in the intelligent device may be of the same type of processor, such as one or more CPUs; or may be of different types of processors, such as one or more CPUs and one or more ASICs.

[0098] The memory is used to store the program. The memory may include high-speed RAM memory, and may also include non-volatile memory, such as at least one disk memory.

[0099] The program may include multiple computer instructions, and specifically, the program may cause the processor to execute the optical positioning configuration method described in any one of the foregoing multiple method embodiments through the multiple computer instructions.

[0100] For the specific implementation of each step in the program, reference may be made to the corresponding descriptions in the corresponding steps, modules, or units in the above method embodiments, and there are corresponding beneficial effects, which will not be elaborated here. Those skilled in the art can clearly understand that for the convenience and brevity of description, the specific working processes of the above-described devices, equipment, or modules may refer to the corresponding process descriptions in the foregoing method embodiments, and will not be elaborated here.

[0101] An embodiment of the present invention further provides a computer storage medium, on which a computer program is stored, and when the program is executed by a processor, it implements the method described in any one of the foregoing multiple method embodiments. The computer storage medium includes but is not limited to: Compact Disc Read-Only Memory (CD-ROM), Random Access Memory (RAM), floppy disk, hard disk, magneto-optical disk, etc.

[0102] An embodiment of the present invention further provides a computer program product, including computer instructions, and the computer instructions direct a computing device to execute the optical positioning configuration method in the above-mentioned multiple method embodiments.

[0103] In addition, it should be noted that the information related to users (including but not limited to user device information, user personal information, etc.) and data (including but not limited to sample data for training a model, data for analysis, stored data, displayed data, etc.) involved in the embodiments of the present invention are all information and data that have been authorized by the user or fully authorized by all parties, and the collection, use, and processing of relevant data need to comply with relevant regulations and standards, and corresponding operation entrances are provided for the user to select authorization or rejection.

[0104] It should be pointed out that according to the needs of implementation, each component / step described in the embodiments of the present invention can be split into more components / steps, or two or more components / steps or partial operations of components / steps can be combined into new components / steps to achieve the purpose of the embodiments of the present invention.

[0105] The method according to an embodiment of the present invention can be implemented in hardware, firmware, or be implemented as software or computer code that can be stored in a recording medium (such as a CD-ROM, RAM, floppy disk, hard disk, or magneto-optical disk), or be implemented as computer code originally stored in a remote recording medium or a non-transitory machine-readable medium and downloaded through a network and to be stored in a local recording medium, so that the method described herein can be stored in such a software process on a recording medium using a general-purpose computer, a dedicated processor, or programmable or dedicated hardware (such as an Application Specific Integrated Circuit (ASIC) or a Field Programmable Gate Array (FPGA)). It can be understood that a computer, a processor, a microprocessor controller, or programmable hardware includes a storage component (such as a Random Access Memory (RAM), a Read-Only Memory (ROM), a flash memory, etc.) that can store or receive software or computer code, and when the software or computer code is accessed and executed by the computer, the processor, or the hardware, the method described herein is implemented. In addition, when a general-purpose computer accesses the code for implementing the method shown herein, the execution of the code converts the general-purpose computer into a dedicated computer for executing the method shown herein.

[0106] Those of ordinary skill in the art can realize that the units and method steps of each example described in combination with the embodiments disclosed herein can be implemented by electronic hardware, or a combination of computer software and electronic hardware. Whether these functions are executed in a hardware or software manner depends on the specific application and design constraints of the technical solution. A professional technician can use different methods to implement the described functions for each specific application, but such an implementation should not be considered to exceed the scope of the embodiments of the present invention.

[0107] The above embodiments are only used to illustrate the embodiments of the present invention, rather than to limit the embodiments of the present invention. Those of ordinary skill in the relevant technical field can make various changes and modifications without departing from the spirit and scope of the embodiments of the present invention. Therefore, all equivalent technical solutions also belong to the scope of the embodiments of the present invention. The patent protection scope of the embodiments of the present invention shall be defined by the claims.

Claims

1. An optical positioning configuration method, comprising: Determining a simulated position of at least one object in an optical positioning site, wherein a camera array for performing optical positioning in the optical positioning site is arranged in the optical positioning site; Spatially matching the simulated pose parameters of the camera array with the optical positioning site, and determining the occlusion orientation relationship between the acquisition field of view of the camera array in the optical positioning site and the simulated position of the at least one object according to the matching result; According to the occlusion orientation relationship, the simulation posture parameters of the camera array are adjusted so that the proportion of the blind area of ​​the camera array's acquisition field of view blocked by the at least one object is less than a preset threshold; The camera array is configured with parameters according to the adjusted simulation posture parameters.

2. The method according to claim 1, wherein: According to the occlusion orientation relationship, adjusting the simulation posture parameters of the camera array so that the proportion of the blind area of ​​the camera array's acquisition field of view blocked by the at least one object is less than a preset threshold, including: Determining an occlusion orientation relationship indicates a ratio of a blind area of ​​a camera array's acquisition field of view that is blocked by the at least one object; When the blind area ratio of the camera array is greater than a preset threshold, while maintaining the position parameters of each camera in the camera array, adjusting the orientation parameters of at least some cameras to adjust the occlusion orientation relationship; When the blind area ratio of the camera array is less than the preset threshold after the orientation parameters of at least some cameras are adjusted, the adjusted simulation posture parameters are output.

3. The method according to claim 2, wherein: According to the occlusion orientation relationship, the simulation posture parameters of the camera array are adjusted so that the proportion of the blind area of ​​the camera array's acquisition field of view blocked by the at least one object is less than a preset threshold, and further comprising: When the blind area ratio of the camera array is greater than the preset threshold after the orientation parameters of at least some of the cameras are adjusted, at least one camera is added to the camera array to update the camera array.

4. The method according to claim 2, wherein: While maintaining the position parameters of each camera in the camera array, adjusting the orientation parameters of at least some of the cameras includes: While maintaining the position parameters of each camera in the camera array, adjusting the orientation parameters of a current portion of the cameras in each camera; If the blind area ratio of the field of view decreases after the orientation parameters of the current partial cameras are adjusted, while maintaining the orientation parameters of the current partial cameras, some cameras among the remaining cameras are used as updated current partial cameras to adjust the orientation parameters of the updated current partial cameras.

5. The method according to claim 4, wherein: While maintaining the position parameters of each camera in the camera array, adjusting the orientation parameters of at least some of the cameras, further comprising: If the blind area ratio of the field of view increases after the orientation parameters of the current partial cameras are adjusted, the orientation parameters of the current partial cameras are restored to before the adjustment, and some cameras among the remaining cameras are used as updated current partial cameras to adjust the orientation parameters of the updated current partial cameras.

6. The method according to claim 4, wherein: Adjust the orientation parameters of the current part of the cameras, including: In multiple adjustments of the orientation parameters of the current portion of the camera with a preset angle step, if the blind spot ratio of the current portion of the camera decreases after the orientation parameters of the current portion of the camera are adjusted for the current time, the next adjustment of the orientation parameters of the current portion of the camera is performed; if the blind spot ratio of the current portion of the camera does not decrease after the orientation parameters of the current portion of the camera are adjusted for the current time, the orientation parameters of the current portion of the camera are restored to the level before the current adjustment.

7. The method according to claim 2, wherein: Determining the occlusion orientation relationship indicates the ratio of the blind area of ​​the camera array's acquisition field of view blocked by the at least one object, including: Sampling the spatial position of the optical positioning site to obtain a plurality of sampling points; Determine whether each sampling point is in a blind spot of the camera array according to the occlusion orientation relationship; The ratio between the number of sampling points in the blind area of ​​the field of view of the camera array and the number of the plurality of sampling points is determined as the blind area ratio of the acquisition field of view of the camera array.

8. The method according to claim 7, wherein: Determining whether each sampling point is in a blind area of ​​the camera array according to the occlusion orientation relationship includes: Determine whether each sampling point is blocked within the acquisition field of view of each camera in the camera array; If a sampling point is blocked within the acquisition field of view of more than a preset number of cameras, it is determined that the sampling point is in a blind area of ​​the field of view of the camera array.

9. The method according to claim 8, wherein: Determining whether each sampling point is blocked within the acquisition field of view of each camera in the camera array includes: Determine whether each sampling point is within the acquisition field of view of each camera in the camera array; If a sampling point is within the acquisition field of view of a camera and a virtual line between the sampling point and the camera passes through a simulated position of at least one object, then it is determined that the sampling point is blocked in the acquisition field of view of the camera; If a sampling point is not within the acquisition field of view of a camera, it is directly determined that the sampling point is blocked in the acquisition field of view of the camera.

10. The method according to claim 1, wherein: Determining a simulated position of at least one object in an optical positioning field includes: Acquire three-dimensional image data of the optical positioning site, and perform surface mesh representation on the three-dimensional image data; Performing feature recognition on the surface mesh representation to obtain at least one object in the optical positioning field; The identified position of the at least one object is marked as a simulated position.

11. An optical positioning configuration device, comprising: A determination module determines a simulated position of at least one object in an optical positioning site, wherein a camera array for performing optical positioning in the optical positioning site is arranged in the optical positioning site; A matching module spatially matches the simulated pose parameters of the camera array with the optical positioning site, and determines, based on the matching result, an occlusion orientation relationship between a collection field of view of the camera array in the optical positioning site and a simulated position of the at least one object; An adjustment module, which adjusts the simulation posture parameters of the camera array according to the occlusion orientation relationship so that the proportion of the blind area of ​​the camera array's acquisition field of view blocked by the at least one object is less than a preset threshold; A configuration module is used to configure the parameters of the camera array according to the adjusted simulation posture parameters.

12. An electronic device comprising: A processor, a memory, a communication interface and a communication bus, wherein the processor, the memory and the communication interface communicate with each other via the communication bus; The memory is used to store at least one executable instruction, and the executable instruction enables the processor to execute the method according to any one of claims 1-10.

13. A computer storage medium having a computer program stored thereon, wherein when the program is executed by a processor, the method according to any one of claims 1 to 10 is implemented.

14. A computer program product, comprising computer instructions, which implement the method according to any one of claims 1 to 10 when executed by a processor.

Images