Light environment model construction method and device, equipment and storage medium

Abstract

The invention provides a light environment model construction method and device, equipment and a storage medium, and relates to the technical field of optics, and the specific implementation scheme is as follows: obtaining scene feature information corresponding to a target light environment scene; according to the scene feature information, obtaining an overall optical representation graph of the target light environment scene, wherein the pixel value of each pixel point in the overall optical representation graph represents the optical index of the corresponding scene position; partitioning the overall light distribution image, and determining feature points of each partition; and for each partition, obtaining an optical index association relationship between the feature points and association points in the partition, and obtaining a scene light environment model. Through the implementation of the scheme of the invention, the optical indexes of all scene positions in the light environment scene are comprehensively represented, and then the optical index association relationship between the feature points and all the association points in the partitions is established for each scene region, so that the information amount of the scene light environment model is enriched, the generalization ability of the model is effectively improved, and the user experience is improved. And the practicability of the model is expanded.

Description

Technical Field

[0001] The present application relates to the field of optical technology, and in particular to a method, device, equipment and storage medium for constructing a light environment model. Background Art

[0002] With the continuous development of science and technology, more and more electronic devices are present in living spaces and urban spaces. At present, people generally have the need to model the light environment under luminous scenes. In related technologies, usually only optical information of some positions in the light environment is obtained by point detection using optical equipment, and then the scene light environment model is simulated based on the detected limited optical information. However, the scene light environment model only contains the optical information corresponding to the limited position points, and does not contain other characterization information. That is, the amount of information provided in the scene light environment model is relatively small and basic, which is difficult to meet the needs of actual applications.

[0003] It is important to note that the techniques described in this section are not necessarily those that have been previously conceived or employed. Unless otherwise indicated, it should not be assumed that any technique described in this section is prior art simply because it is included in this section. Similarly, unless otherwise indicated, the issues mentioned in this section should not be considered to have been recognized as prior art. Summary of the Invention

[0004] The embodiments of the present application provide a method, apparatus, device, and storage medium for constructing a light environment model, which aim to solve at least one of the problems in the related art to a certain extent.

[0005] A first aspect of an embodiment of the present application provides a method for constructing a light environment model, comprising:

[0006] Acquire scene feature information corresponding to the target light environment scene; wherein the scene feature information includes light source information in the scene, scene geometric features, and material properties of objects in the scene;

[0007] Acquire an overall optical representation of the target light environment scene according to the scene feature information; wherein the pixel value of each pixel point in the overall optical representation represents the optical index of the corresponding scene position;

[0008] Partitioning the overall light distribution image, and determining feature points of each partition;

[0009] For each of the partitions, an optical index correlation relationship between the feature points and the associated points in the partition is obtained to obtain a scene light environment model.

[0010] In an optional embodiment, for each image partition, the optical index correlation relationship between the feature point and the associated points within the partition is obtained to obtain a scene light environment model, including: for each of the partitions, obtaining the optical index correlation relationship between the feature point and the associated points within the partition, and combining the position correlation relationship between the feature point and the associated points within the partition to obtain the scene light environment model.

[0011] In an optional embodiment, after obtaining the optical index correlation relationship between the feature points and the associated points within the partition for each image partition and obtaining the scene light environment model, it also includes: obtaining a first optical index corresponding to the feature point in the light environment scene to be predicted; based on the scene light environment model and the first optical index, obtaining a second optical index of the associated points within the partition corresponding to the feature point; and generating an overall optical representation map corresponding to the light environment scene to be predicted based on the first optical index of all feature points and the second optical index of all associated points within the partition.

[0012] In an optional embodiment, after generating the overall optical representation map corresponding to the light environment scene to be predicted, it includes: obtaining corresponding predicted optical indicators on the overall optical representation map according to the position information corresponding to the position to be predicted in the light environment scene to be predicted; and outputting corresponding indication information based on the predicted optical indicators.

[0013] In an optional embodiment, the obtaining of the overall optical characterization diagram of the target light environment scene according to the scene characteristic information includes: determining the type of optical indicator to be characterized; wherein the optical indicator type includes any one of the following: spectrum, light intensity, illuminance, light chromaticity, light health index, light pollution index, luminous energy consumption, and luminous carbon emission index; for the target light environment scene, obtaining the overall optical characterization diagram that conforms to the type of optical indicator to be characterized according to the scene characteristic information.

[0014] In an optional implementation manner, determining the feature points of each partition includes: determining the feature points of each partition based on pixel values ​​of all pixels in each partition and / or partition geometric features.

[0015] In an optional embodiment, each of the feature points has a corresponding partition feature representation strength, and the feature points of each partition are determined based on the pixel values ​​and / or partition geometric features of all pixel points in each partition, including: preliminarily determining the feature points of each partition based on the pixel values ​​and / or partition geometric features of all pixel points in each partition; obtaining the total partition feature representation strength of all the feature points preliminarily determined; if the total partition feature representation strength is greater than or equal to a preset strength threshold, the preliminarily determined feature points are used as the final required feature points; if the total partition feature representation strength is less than the strength threshold, additional feature points are determined again for each partition until the total partition feature representation strength is greater than or equal to the strength threshold, and then the preliminarily determined feature points and the additional feature points are used as the final required feature points.

[0016] In an optional embodiment, obtaining the optical index association relationship between the feature point and the associated points within the partition includes: obtaining the optical indexes of multiple feature points corresponding to the associated points within the partition; and establishing a corresponding optical index association relationship by combining the optical indexes of the associated points within the partition and the optical indexes of multiple feature points.

[0017] In an optional implementation, the light environment model construction method further includes: acquiring light source control information corresponding to the target light environment scene; and establishing a mapping relationship between the scene light environment model and the corresponding light source control information.

[0018] A second aspect of the embodiments of the present application provides a light environment model construction device, including:

[0019] A first acquisition module is used to acquire scene feature information corresponding to the target light environment scene; wherein the scene feature information includes light source information in the scene, scene geometric features, and material properties of objects in the scene;

[0020] A second acquisition module is configured to acquire an overall optical representation of the target light environment scene based on the scene feature information; wherein the pixel value of each pixel point in the overall optical representation represents an optical index of the corresponding scene position;

[0021] a determination module, configured to partition the overall light distribution image and determine characteristic points of each partition;

[0022] The modeling module is used to obtain the optical index correlation relationship between the feature points and the associated points in the partition for each partition, so as to obtain a scene light environment model.

[0023] A third aspect of an embodiment of the present application provides an electronic device, comprising: a memory and a processor, wherein the processor is used to execute a computer program stored in the memory. When the processor executes the computer program, it implements each step of the light environment model construction method provided in the first aspect of the embodiment of the present application.

[0024] The fourth aspect of the embodiment of the present application provides a computer-readable storage medium on which a computer program is stored. When the computer program is executed by a processor, the steps of the light environment model construction method provided in the first aspect of the embodiment of the present application are implemented.

[0025] As can be seen from the above, according to the light environment model construction method, device, equipment and storage medium provided by the present application, the scene feature information corresponding to the target light environment scene is obtained; based on the scene feature information, the overall optical representation map of the target light environment scene is obtained, and the pixel value of each pixel point in the overall optical representation map represents the optical index of the corresponding scene position; the overall light distribution image is partitioned, and the feature points of each partition are determined; for each partition, the optical index correlation relationship between the feature point and the associated points in the partition is obtained to obtain the scene light environment model. Through the implementation of the present application, the optical indexes of all scene positions in the light environment scene are comprehensively characterized, and then the optical index correlation relationship between the feature point and all associated points in the partition is established for each scene area, which enriches the information content of the scene light environment model, effectively improves the generalization ability of the model, and thus expands the practicality of the model.

[0026] It should be understood that the content described in this section is not intended to identify the key or important features of this application, nor is it intended to limit the scope of this application. Other features of this application will become easily understood through the following description. BRIEF DESCRIPTION OF THE DRAWINGS

[0027] The accompanying drawings illustrate exemplary embodiments and constitute a part of the specification. Together with the description of the specification, they serve to explain exemplary implementations of the embodiments. The drawings are shown for illustrative purposes only and do not limit the scope of the claims. Throughout the drawings, the same reference numerals designate similar, but not necessarily identical, elements.

[0028] Figure 1 A schematic diagram of the basic flow of a method for constructing a light environment model according to an embodiment of the present application;

[0029] Figure 2 A schematic diagram of constructing characteristic points of an indoor light environment provided in one embodiment of the present application;

[0030] Figure 3 A schematic diagram of a detailed process of constructing a light environment model according to an embodiment of the present application;

[0031] Figure 4 A schematic diagram of the functional modules of a light environment model building device provided in one embodiment of the present application;

[0032] Figure 5 A schematic diagram of the structure of an electronic device provided in one embodiment of the present application. DETAILED DESCRIPTION

[0033] In order to make the purpose, features, and advantages of the invention of this application more obvious and easy to understand, the technical solutions in the embodiments of this application will be clearly and completely described below in conjunction with the drawings in the embodiments of this application. Obviously, the described embodiments are only part of the embodiments of this application, not all embodiments. Based on the embodiments in this application, all other embodiments obtained by those skilled in the art without making creative efforts shall fall within the scope of protection of this application.

[0034] In the description of the embodiments of the present application, the terms "first" and "second" are used for descriptive purposes only and are not to be understood as indicating or implying relative importance or implicitly indicating the number of the indicated technical features. Thus, the features defined as "first" and "second" may explicitly or implicitly include one or more of the features. In the description of the embodiments of the present application, the meaning of "plurality" is two or more, unless otherwise clearly and specifically defined. In addition, the term "comprising" indicates the presence of the described features, wholes, steps, operations, elements and / or components, but does not exclude the presence or addition of one or more other features, wholes, steps, operations, elements, components and / or their collections.

[0035] In order to solve the problem that the amount of information provided in the scene light environment model constructed by the related technology is relatively small and difficult to meet the actual application needs, an embodiment of the present application provides a light environment model construction method, such as Figure 1 This is a basic flow chart of the light environment model construction method provided in this embodiment. The light environment model construction method includes the following steps:

[0036] Step 101: Acquire scene feature information corresponding to a target light environment scene.

[0037] The scene feature information in this embodiment includes, but is not limited to, light source information, geometric features of all objects in the scene, and material properties of objects in the scene. It is worth noting that in this embodiment, the light environment scene includes at least one light source. If there are multiple light sources, light source information must be obtained for each of the multiple light sources.

[0038] Step 102: Obtain an overall optical representation of the target light environment scene according to the scene feature information.

[0039] The pixel values ​​of each pixel in the overall optical representation of this embodiment represent the optical index of the corresponding scene location. Depending on the actual application requirements, the optical index type includes any of the following: spectrum, light intensity, light illuminance, light chromaticity, light health index, light pollution index, luminous energy consumption, and luminous carbon emission index. It is worth noting that the overall optical representation can be obtained through simulation, experimentation, actual measurement, etc., and preferably can be obtained based on simulation software or a neural network model.

[0040] In an optional implementation manner of this embodiment, the above-mentioned obtaining of an overall optical representation diagram of the target light environment scene based on scene feature information includes: determining the type of optical indicator to be characterized; and for the target light environment scene, obtaining an overall optical representation diagram that conforms to the type of optical indicator to be characterized based on the scene feature information.

[0041] Step 103: partition the entire light distribution image and determine the feature points of each partition.

[0042] In actual application scenarios, the scene contains different spatial objects. Taking the indoor light environment as an example, it includes desktops, walls, floors, etc. Different scene positions have different positions relative to the light source and different material properties, so their optical properties are different. Therefore, this embodiment can partition the overall light distribution image based on scene feature information. In addition, each partition includes multiple pixel points corresponding to different actual scene positions, and this embodiment selects one or more points with the most typical and strong correlation from each partition as feature points, so as to enrich the effective light information of the scene light environment model based on the feature points. Figure 2 The figure shows a schematic diagram of constructing feature points of an indoor light environment provided by this embodiment. Given the three-dimensional structure, material properties and lighting information of the indoor space, the indoor space can be partitioned and feature points can be set for each partition. Figure 2 The dot-shaped diagram in the middle represents the characteristic points of different indoor space partitions. It should be noted that the distribution of characteristic points is only a schematic illustration and does not limit the setting of characteristic points in actual application scenarios.

[0043] In an optional implementation manner of this embodiment, the above-mentioned determining the feature points of each partition includes: determining the feature points of each partition according to the pixel values ​​of all pixels in each partition and / or the geometric features of the partition.

[0044] In practical applications, there are many ways to determine feature points within a partition. This embodiment exemplifies implementation methods based on pixel values ​​and geometric features. For the implementation method based on pixel values, it can be implemented by analyzing the average value, maximum / minimum value and correlation between the pixel values ​​of different pixels in the partition, while the determination method based on geometric features can be implemented by analyzing the edges, corners, symmetry axes, etc. of the partition.

[0045] In an optional implementation manner of this embodiment, each feature point has a corresponding partition feature characterization strength. Accordingly, the above-mentioned determination of the feature points of each partition based on the pixel values ​​and / or partition geometric features of all pixel points in each partition includes: preliminarily determining the feature points of each partition based on the pixel values ​​and / or partition geometric features of all pixel points in each partition; obtaining the total partition feature characterization strength of all preliminarily determined feature points; if the total partition feature characterization strength is greater than or equal to a preset strength threshold, then using the preliminarily determined feature points as the final required feature points; if the total partition feature characterization strength is less than the strength threshold, then determining additional feature points again for each partition until the total partition feature characterization strength is greater than or equal to the strength threshold, and then using the preliminarily determined feature points and the additional feature points as the final required feature points.

[0046] In actual applications, the morphology of each partition is relatively diverse. For partitions with simple morphology, fewer feature points can effectively utilize the feature point attributes to characterize the entire partition, while for partitions with complex morphology, more feature points are required to achieve the accuracy of partition characterization. In this embodiment, one or a few feature points that are most relevant to the partition are preliminarily determined, and the total partition feature characterization intensity of the preliminarily obtained feature points is obtained. If the intensity reaches a preset intensity threshold, it means that the preliminarily determined feature points can effectively characterize the corresponding partition and the feature point acquisition is completed. Otherwise, the feature points with the second highest correlation are obtained from the corresponding partition again. The total partition feature characterization intensity is increased by increasing the number of feature points until the total partition feature characterization intensity of all the obtained feature points reaches the intensity threshold. This effectively avoids the situation where the limited feature points obtained in complex scenes cannot accurately characterize the corresponding partition, thereby improving the accuracy of the subsequently constructed scene light environment model.

[0047] Step 104 : For each partition, obtain the optical index correlation relationship between the feature points and the associated points in the partition to obtain a scene light environment model.

[0048] Based on the overall optical characterization diagram obtained above in this embodiment, the optical indicators of the feature points and the associated points can be obtained by region, and then the optical indicator correlation relationship between the two can be obtained, so that the scene light environment model corresponding to the target light environment scene can be constructed. It is worth mentioning that the scene light environment model finally constructed in this embodiment is an expression of the correlation between the optical indicators of the feature points and the associated points in the scene. This correlation expression effectively improves the generalization ability of the model and is suitable for subsequent expansion applications. It should also be noted that in an optional implementation manner of this embodiment, for each partition, the optical indicator correlation relationship between the feature points and the associated points in the partition is obtained, and the scene light environment model is obtained in combination with the position correlation relationship between the feature points and the associated points in the partition. This position correlation relationship can be a position function.

[0049] In an optional implementation manner of this embodiment, the above-mentioned acquisition of the optical index association relationship between the feature points and the associated points within the partition includes: acquiring the optical indexes of multiple feature points corresponding to the associated points within the partition; and establishing a corresponding optical index association relationship by combining the optical indexes of the associated points within the partition and the optical indexes of the multiple feature points.

[0050] It should be noted that the association points in this embodiment refer to all points in the partition except the feature points. Depending on the actual application scenarios and needs, one or more feature points can be determined in the partition. If there are multiple feature points in the partition, different feature points can be used to construct optical indicator association relationships with different association points in the partition, or multiple feature points can be combined with each association point to construct optical indicator association relationships. Since the scene light environment model constructed in this embodiment fully considers the optical information of all scene positions, the amount of information in the scene light environment model is improved, and it can meet a wider range of application needs in actual applications.

[0051] In an optional implementation manner of the present embodiment, after obtaining the optical index correlation relationship between the feature points and the associated points within the partition for each image partition and obtaining the scene light environment model, the method further includes: obtaining a first optical index corresponding to the feature point in the light environment scene to be predicted; based on the scene light environment model and the first optical index, obtaining a second optical index of the associated points within the partition corresponding to the feature point; and generating an overall optical representation map corresponding to the light environment scene to be predicted based on the first optical index of all feature points and the second optical index of all associated points within the partition.

[0052] In actual applications, users usually have the need to obtain optical information in a luminous scene. However, in related technologies, it is usually necessary to use optical detection equipment to detect the optical information of limited position points in the luminous scene each time. On the one hand, since manual detection is required each time, the convenience and efficiency are poor; on the other hand, since only the optical information of limited position points can be obtained, the amount of optical information is small and it is impossible to provide sufficient guidance information to the user. Based on the scene light environment model constructed above in this embodiment, if the need for optical information detection is required in the actual light environment scene, only the optical indicators of the feature points can be measured. Then, the optical indicators of the associated points can be obtained by using the correlation relationship between the feature points provided by the above scene light environment model and the optical indicators of the associated points in the partition. Then, the overall optical representation map of the actual light environment scene can be obtained. This method greatly reduces manual operation, improves the convenience and efficiency of light environment perception, and comprehensively represents all positions in the actual light environment scene, which can provide users with sufficient and comprehensive optical information.

[0053] In an optional implementation manner of this embodiment, after the above-mentioned generation of the overall optical representation map corresponding to the light environment scene to be predicted, it includes: obtaining corresponding predicted optical indicators on the overall optical representation map according to the position information corresponding to the position to be predicted in the light environment scene to be predicted; and outputting corresponding indication information based on the predicted optical indicators.

[0054] The light environment model construction method of this embodiment can be applied to different scenarios, for example, it can be applied to the field of low-altitude traffic, that is, the light environment scene to be predicted can be a low-altitude traffic scene. After the optical information prediction is performed on the low-altitude traffic scene to obtain the overall optical representation diagram, the corresponding predicted optical indicators can be obtained for a specific location such as a low-altitude airway, and then the corresponding indication information can be output, such as whether the light environment required for safety identification is met, the type of object at a specific location, etc., to provide guidance for low-altitude traffic management. For another example, taking the road light environment as an example, road lighting lamps are usually arranged according to certain principles, and the installation distance, height, and light distribution are usually consistent in the same road section. This embodiment sets the feature points that best represent the road lighting characteristics, such as directly below the street lamp, between two lamps, and the central axis of the road. After the overall optical representation diagram is obtained based on the measured optical indicators of the feature points and the reconstruction of the above-mentioned scene light environment model, the corresponding predicted optical indicators can be obtained for the specific location, and then the corresponding indication information can be input to provide guidance on the working conditions of the lamps, dimming levels, etc.

[0055] In an optional implementation manner of this embodiment, the light environment model construction method further includes: acquiring light source control information corresponding to the target light environment scene; and establishing a mapping relationship between the scene light environment model and the corresponding light source control information.

[0056] The light source control information of this embodiment includes but is not limited to the light source distribution status, the light source control channel ratio, and the light source point control information. This embodiment can use the light source control information as a variable to execute the aforementioned process of steps 101 to 104, so as to obtain the scene light environment model under different light source luminous behaviors in the same scene. Then, in actual application scenarios, the corresponding scene light environment model can be called based on the light source control information.

[0057] In order to better illustrate the embodiment of the present application, an embodiment of the present application also provides a detailed light environment model construction method, such as Figure 3 FIG. 1 is a schematic diagram of a detailed process of a light environment model construction method provided in an embodiment of the present application, which specifically includes the following processes:

[0058] Step 301: Acquire scene feature information corresponding to the target light environment scene;

[0059] Step 302: Simulate an overall optical representation of the target light environment scene based on the scene feature information;

[0060] Step 303: partition the entire light distribution image, obtain pixel values ​​of all pixels in each partition, and determine feature points of each partition by combining all pixel values;

[0061] Step 304: For each partition, obtain the optical index correlation relationship between the feature point and the associated points in the partition, and combine the position function of the feature point and the associated points in the partition to obtain the scene light environment model;

[0062] Step 305: Obtain a first optical index corresponding to a feature point in the light environment scene to be predicted;

[0063] Step 306: Based on the scene light environment model and the first optical index, obtain a second optical index of the associated point in the partition corresponding to the feature point;

[0064] Step 307: Generate an overall optical representation corresponding to the light environment scene to be predicted based on the first optical indexes of all feature points and the second optical indexes of all associated points in the partitions;

[0065] Step 308: Obtain corresponding predicted optical indicators on the overall optical representation diagram according to the position information corresponding to the position to be predicted in the light environment scene to be predicted;

[0066] Step 309: Output corresponding indication information based on the predicted optical index.

[0067] It should be understood that the size of the serial numbers of the steps in this embodiment does not mean the order in which the steps are executed. The order in which the steps are executed should be determined by their functions and internal logic, and should not constitute a sole limitation on the implementation process of the embodiments of this application.

[0068] Figure 4 An embodiment of the present application provides a light environment model construction device, which can be used to implement the light environment model construction method in the aforementioned embodiment, mainly including:

[0069] The first acquisition module 401 is used to obtain scene feature information corresponding to the target light environment scene; wherein the scene feature information includes light source information in the scene, scene geometric features, and material properties of objects in the scene;

[0070] The second acquisition module 402 is configured to acquire an overall optical representation of the target light environment scene based on the scene feature information; wherein the pixel value of each pixel in the overall optical representation represents the optical index of the corresponding scene position;

[0071] A determination module 403 is used to partition the overall light distribution image and determine feature points of each partition;

[0072] The modeling module 404 is used to obtain, for each partition, the optical index correlation relationship between the feature points and the associated points in the partition, and obtain a scene light environment model.

[0073] In an optional implementation of this embodiment, the light environment model construction device also includes: a generation module, which is used to: obtain a first optical indicator corresponding to a feature point in the light environment scene to be predicted; based on the scene light environment model and the first optical indicator, obtain a second optical indicator of an associated point within a partition corresponding to the feature point; and generate an overall optical representation map corresponding to the light environment scene to be predicted based on the first optical indicators of all feature points and the second optical indicators of all associated points within the partition.

[0074] In an optional implementation of this embodiment, the light environment model construction device also includes: an output module, which is used to: obtain corresponding predicted optical indicators on the overall optical representation diagram according to position information corresponding to the position to be predicted in the light environment scene to be predicted; and output corresponding indication information based on the predicted optical indicators.

[0075] In an optional implementation of this embodiment, the light environment model construction device further includes: an establishment module for: obtaining light source control information corresponding to the target light environment scene; and establishing a mapping relationship between the scene light environment model and the corresponding light source control information.

[0076] It should be noted that the light environment model construction methods in the aforementioned method embodiments can all be implemented based on the light environment model construction device provided in this embodiment. Ordinary technical personnel in the relevant field can clearly understand that for the convenience and conciseness of description, the specific working process of the light environment model construction device described in this embodiment can be implemented by referring to the corresponding working process in the aforementioned method embodiments, and will not be repeated here.

[0077] Based on the technical solution of the embodiment of the present application described above, scene feature information corresponding to the target light environment scene is obtained; based on the scene feature information, an overall optical representation of the target light environment scene is obtained, wherein the pixel value of each pixel in the overall optical representation represents the optical index of the corresponding scene position; the overall light distribution image is partitioned, and the feature points of each partition are determined; for each partition, the optical index correlation relationship between the feature point and the associated points within the partition is obtained to obtain a scene light environment model. Through the implementation of the solution of the present application, the optical indexes of all scene positions in the light environment scene are comprehensively characterized, and then, for each scene area, an optical index correlation relationship between the feature point and all associated points within the partition is established, thereby enriching the information content of the scene light environment model, effectively improving the generalization ability of the model, and thus expanding the practicality of the model.

[0078] Figure 5An electronic device is provided in one embodiment of the present application. This electronic device can be used to implement the light environment model construction method in the aforementioned embodiment, and mainly includes: a memory 501 and a processor 502. The memory 501 stores a computer program 503 that can be executed on the processor 502. The memory 501 and the processor 502 are in communication with each other. When the processor 502 executes the computer program 503, the light environment model construction method in the aforementioned embodiment is implemented. The number of processors 502 can be one or more.

[0079] The memory 501 can be a high-speed random access memory (RAM) memory or a non-volatile memory such as a disk memory. The memory 501 is used to store executable program codes. The processor 502 is coupled to the memory 501 .

[0080] Furthermore, the embodiment of the present application also provides a computer-readable storage medium, which can be provided in the electronic device in the above embodiments. The computer-readable storage medium can be the above Figure 5 Memory in the illustrated embodiment.

[0081] The computer-readable storage medium stores a computer program that, when executed by a processor, implements the light environment model construction method described in the aforementioned embodiment. Furthermore, the computer-readable storage medium may be a USB flash drive, a mobile hard drive, a read-only memory (ROM), RAM, a magnetic disk, or an optical disk, among other media capable of storing program code.

[0082] In the several embodiments provided in this application, it should be understood that the disclosed devices and methods can be implemented in other ways. For example, the device embodiments described above are merely illustrative. For example, the division of modules is only a logical function division. In actual implementation, there may be other division methods, such as multiple modules or components can be combined or integrated into another system, or some features can be ignored or not executed. Another point is that the mutual coupling or direct coupling or communication connection shown or discussed can be through some interfaces, indirect coupling or communication connection of devices or modules, which can be electrical, mechanical or other forms.

[0083] Modules described as separate components may or may not be physically separate, and components shown as modules may or may not be physical modules, that is, they may be located in one place or distributed across multiple network modules. Some or all of these modules may be selected to achieve the purpose of this embodiment based on actual needs.

[0084] In addition, the functional modules in the various embodiments of the present application may be integrated into a processing module, or each module may exist physically separately, or two or more modules may be integrated into a single module. The above-mentioned integrated modules may be implemented in the form of hardware or software functional modules.

[0085] If the integrated module is implemented in the form of a software functional module and sold or used as an independent product, it can be stored in a computer-readable storage medium. Based on this understanding, the technical solution of the present application, or the part that contributes to the prior art, or all or part of the technical solution can be embodied in the form of a software product, which is stored in a readable storage medium and includes several instructions for enabling a computer device (which can be a personal computer, server, or network device, etc.) to execute all or part of the steps of the various embodiments of the present application. The aforementioned readable storage medium includes various media that can store program codes, such as a USB flash drive, a mobile hard disk, a ROM, a RAM, a magnetic disk, or an optical disk.

[0086] It should be noted that for the aforementioned method embodiments, for ease of description, they are all expressed as a series of action combinations, but those skilled in the art should be aware that this application is not limited by the order of the actions described, because according to this application, certain steps can be performed in other orders or simultaneously. Secondly, those skilled in the art should also be aware that the embodiments described in this specification are all preferred embodiments, and the actions and modules involved are not necessarily required by this application.

[0087] In the above embodiments, the description of each embodiment has its own focus. For parts that are not described in detail in a certain embodiment, reference can be made to the relevant descriptions of other embodiments.

[0088] The above is a description of the light environment model construction method, device, equipment and storage medium provided in this application. For technicians in this field, based on the ideas of the embodiments of this application, there may be changes in the specific implementation methods and application scope. In summary, the content of this specification should not be understood as a limitation on this application.

Claims

1. A method for constructing a light environment model, characterized in that: include: Acquire scene feature information corresponding to the target light environment scene; wherein the scene feature information includes light source information in the scene, scene geometric features, and material properties of objects in the scene; Acquire an overall optical representation of the target light environment scene according to the scene feature information; wherein the pixel value of each pixel point in the overall optical representation represents the optical index of the corresponding scene position; Partitioning the overall light distribution image, and determining feature points of each partition; For each of the partitions, an optical index correlation relationship between the feature points and the associated points in the partition is obtained to obtain a scene light environment model.

2. The method for constructing a light environment model according to claim 1, wherein: The step of obtaining, for each image partition, an optical index correlation relationship between the feature points and associated points within the partition to obtain a scene light environment model includes: For each of the partitions, an optical index correlation relationship between the feature points and associated points within the partition is obtained, and a scene light environment model is obtained by combining the position correlation relationship between the feature points and associated points within the partition.

3. The method for constructing a light environment model according to claim 1, wherein: After obtaining the optical index correlation relationship between the feature points and the associated points in each image partition and obtaining the scene light environment model, the method further includes: Acquire a first optical index corresponding to the feature point in the light environment scene to be predicted; Based on the scene light environment model and the first optical index, obtaining a second optical index of an associated point in the partition corresponding to the feature point; An overall optical representation graph corresponding to the light environment scene to be predicted is generated according to the first optical indicators of all feature points and the second optical indicators of all associated points in the partitions.

4. The method for constructing a light environment model according to claim 3, wherein: After generating the overall optical representation corresponding to the light environment scene to be predicted, the method includes: Acquiring corresponding predicted optical indicators on the overall optical representation diagram according to position information corresponding to the position to be predicted in the light environment scene to be predicted; Corresponding indication information is output based on the predicted optical index.

5. The method for constructing a light environment model according to claim 1, wherein: The step of obtaining an overall optical representation of the target light environment scene according to the scene feature information includes: Determine the type of optical indicator to be characterized; wherein the optical indicator type includes any one of the following: spectrum, light intensity, brightness, illuminance, light chromaticity, light health index, light pollution index, luminous energy consumption, and luminous carbon emission index; For the target light environment scene, an overall optical characterization diagram that meets the type of optical indicator to be characterized is obtained according to the scene feature information.

6. The method for constructing a light environment model according to claim 1, wherein: Determining the characteristic points of each partition includes: The feature points of each partition are determined based on the pixel values ​​of all pixels in each partition and / or the partition geometric features.

7. The method for constructing a light environment model according to claim 6, wherein: Each of the feature points has a corresponding partition feature representation strength, and determining the feature points of each partition based on the pixel values ​​of all pixels in each partition and / or the partition geometric features includes: Preliminarily determine the feature points of each partition based on the pixel values ​​of all pixels in each partition and / or the partition geometric features; Obtaining the total partition feature representation strength of all the feature points initially determined; If the total partition feature representation strength is greater than or equal to the preset strength threshold, the initially determined feature points are used as the final required feature points; If the total partition feature characterization strength is less than the strength threshold, additional feature points are determined again for each partition until the total partition feature characterization strength is greater than or equal to the strength threshold, and then the preliminarily determined feature points and the additional feature points are used as the final required feature points.

8. The method for constructing a light environment model according to claim 1, wherein: The obtaining of the optical index correlation relationship between the feature point and the associated points in the partition includes: Obtaining optical indicators of a plurality of feature points associated with the associated points within the partition; The optical indexes of the associated points in the partition and the optical indexes of the plurality of feature points are combined to establish a corresponding optical index association relationship.

9. The method for constructing a light environment model according to any one of claims 1 to 8, wherein: Also includes: Acquire light source control information corresponding to the target light environment scene; A mapping relationship between the scene light environment model and the corresponding light source control information is established.

10. A light environment model construction device, characterized in that: include: A first acquisition module is used to acquire scene feature information corresponding to the target light environment scene; wherein the scene feature information includes light source information in the scene, scene geometric features, and material properties of objects in the scene; A second acquisition module is configured to acquire an overall optical representation of the target light environment scene based on the scene feature information; wherein the pixel value of each pixel point in the overall optical representation represents an optical index of the corresponding scene position; a determination module, configured to partition the overall light distribution image and determine characteristic points of each partition; The modeling module is used to obtain the optical index correlation relationship between the feature points and the associated points in the partition for each partition, so as to obtain a scene light environment model.

11. An electronic device, characterized in that: Comprising a memory and a processor, wherein: The processor is configured to execute a computer program stored in the memory; When the processor executes the computer program, the steps in the light environment model construction method according to any one of claims 1 to 9 are implemented.

12. A computer-readable storage medium having a computer program stored thereon, characterized in that: When the computer program is executed by a processor, the steps in the light environment model construction method according to any one of claims 1 to 9 are implemented.

Images