Power grid park modeling method and system based on VR data

Abstract

The invention discloses a power grid park modeling method and system based on VR data. The method comprises the steps of obtaining image data sent by a plurality of VR devices in a target park area; generating a plurality of sub-region models corresponding to the target park region according to the device position of each VR device and the image data; correcting the intersection part of the plurality of sub-region models according to a preset intersection correction rule to obtain a plurality of corrected sub-region models; and generating a park three-dimensional model corresponding to the target park area based on a model union set algorithm according to all the corrected sub-area models. It can be seen that the more accurate park three-dimensional model can be generated in combination with the VR equipment data in the park, the park modeling efficiency and precision are improved, and the labor cost is reduced.

Description

Technical Field

[0001] The present invention relates to the field of data processing technology, and in particular to a power grid park modeling method and system based on VR data. Background Art

[0002] With the increasing demand for intelligent management and the widespread improvement of data processing capabilities, more and more parks have begun to introduce panoramic three-dimensional model technology to achieve more intelligent and intuitive twin model management functions. Among them, how to improve the efficiency and accuracy of modeling has become an important technical issue. Most of the existing park modeling technology solutions still only use complex light reflection data modeling technology to achieve this, and do not fully consider the use of image data collected by park personnel through VR equipment in the park to improve the efficiency and accuracy of modeling. The modeling efficiency and accuracy are both lacking, and the labor cost is too high. It can be seen that the existing technology has defects that need to be solved urgently. Summary of the invention

[0003] The technical problem to be solved by the present invention is to provide a power grid park modeling method and system based on VR data, which can generate a more accurate three-dimensional model of the park by combining the VR equipment data in the park, improve the efficiency and accuracy of park modeling, and reduce labor costs.

[0004] In order to solve the above technical problems, the first aspect of the present invention discloses a power grid park modeling method based on VR data, the method comprising: Acquire image data sent by multiple VR devices in the target park area; Generate multiple sub-area models corresponding to the target park area according to the device position of each VR device and the image data; Correcting the intersection parts of the multiple sub-region models according to a preset intersection correction rule to obtain multiple corrected sub-region models; According to all the corrected sub-region models, based on the model union algorithm, a three-dimensional park model corresponding to the target park area is generated.

[0005] As an optional implementation, in the first aspect of the present invention, the VR device is provided with a three-dimensional panoramic image acquisition camera for acquiring the image data in a panoramic image format.

[0006] As an optional implementation, in the first aspect of the present invention, generating a plurality of sub-area models corresponding to the target park area according to the device position of each VR device and the image data includes: Based on the position combination rule, grouping all the VR devices into a plurality of device sets according to the device position of each of the VR devices; Inputting the image data of all the VR devices in each of the device sets into a trained three-dimensional reconstruction neural network to obtain a set three-dimensional model corresponding to the device set; For each sub-area of ​​the target park area, determining all the device sets corresponding to the sub-area according to the area range of the sub-area; The set three-dimensional model corresponding to all the device sets corresponding to the sub-region is determined as the sub-region model corresponding to the sub-region.

[0007] As an optional implementation, in the first aspect of the present invention, the location-based combination rule groups all the VR devices into a plurality of device sets according to the device position of each VR device, including: Calculating the geometric center point of the device positions of all the VR devices; Calculate the distance vector between the geometric center point and the regional center point of the target park area; the direction of the distance vector is from the geometric center point to the regional center point, and the size of the distance vector is the distance between the geometric center point and the regional center point; Clustering and partitioning all the VR devices based on the K-MEANS algorithm to obtain multiple initial device set areas; For each initial device collection area in which the number of devices is lower than a preset number threshold, determining other initial device collection areas adjacent to the initial device collection area to obtain a plurality of adjacent device collection areas; Multiplying the device position of the VR device in each of the adjacent device set areas by the distance vector to obtain a corresponding corrected position; Classify the VR device in the initial device set area after the correction into the initial device set area; The VR devices belonging to the same initial device set area are determined as a device set to obtain a plurality of device sets.

[0008] As an optional embodiment, in the first aspect of the present invention, the three-dimensional reconstruction neural network is a RNN neural network, which is trained by a training data set including multiple training images and corresponding three-dimensional model annotations.

[0009] As an optional implementation manner, in the first aspect of the present invention, determining, according to the area range of the sub-area, the set of all devices corresponding to the sub-area includes: Calculate the average value of the device correction positions of all the VR devices in each device set to obtain the set position corresponding to each device set; wherein the device correction position of each VR device is set to the corrected position when the VR device is multiplied by the distance vector to obtain the corresponding corrected position during classification, otherwise it is set to the device position of the VR device; All the device sets whose set locations are within the area range of the sub-area are determined as all the device sets corresponding to the sub-area.

[0010] As an optional implementation, in the first aspect of the present invention, the intersection of the plurality of sub-region models is corrected according to a preset intersection correction rule to obtain a plurality of corrected sub-region models, including: For the intersection of any two sub-region models, calculating the difference between the partial models of the two sub-region models corresponding to the intersection; Determine whether the difference is greater than a preset difference threshold, and obtain a determination result; When the judgment result is no, the one with the lower average difference between the two partial models is determined as the model content in the two sub-region models corresponding to the intersection; the average difference is the average value of the difference between the partial model and all other sub-region models with intersections; When the judgment result is yes, the number of first types belonging to power grid equipment and the number of second types belonging to infrastructure in all model part types corresponding to the two part models are determined based on a preset three-dimensional part recognition algorithm; the three-dimensional part recognition algorithm is to match and recognize through a preset three-dimensional template of power grid equipment or a three-dimensional template of infrastructure; Correcting the two partial models of the intersection part according to the first type quantity and the second type quantity to obtain a corrected partial model; The corrected partial model is determined as the model content in the two sub-region models corresponding to the intersection part, and the corresponding corrected sub-region model is obtained.

[0011] As an optional implementation, in the first aspect of the present invention, the two partial models of the intersection part are corrected according to the first type quantity and the second type quantity to obtain a corrected partial model, including: When the number of the first types is greater than a first number threshold, the power grid equipment rules corresponding to the target park area are introduced, and the model parts that have differences in the two partial models of the intersection part and do not comply with the power grid equipment rules are deleted; When the number of the second types is greater than a second number threshold, an infrastructure rule corresponding to the target park area is introduced, and the model parts that are different in the two partial models of the intersection part and do not comply with the infrastructure rule are deleted; The remaining model parts of the two partial models of the intersection part with the lower average difference are retained to obtain the corresponding corrected partial model.

[0012] A second aspect of an embodiment of the present invention discloses a power grid park modeling system based on VR data, the system comprising: An acquisition module, used to acquire image data sent by multiple VR devices in the target park area; A first generating module, configured to generate a plurality of sub-region models corresponding to the target park area according to the device position of each VR device and the image data; A correction module, used to correct the intersection of the plurality of sub-region models according to a preset intersection correction rule to obtain a plurality of corrected sub-region models; The second generation module is used to generate a three-dimensional park model corresponding to the target park area based on all the corrected sub-area models and based on a model union algorithm.

[0013] As an optional implementation, in the second aspect of the present invention, the VR device is provided with a three-dimensional panoramic image acquisition camera for acquiring the image data in a panoramic image format.

[0014] As an optional implementation, in the second aspect of the present invention, the specific manner in which the first generating module generates a plurality of sub-area models corresponding to the target park area according to the device position of each VR device and the image data includes: Based on the position combination rule, grouping all the VR devices into a plurality of device sets according to the device position of each of the VR devices; Inputting the image data of all the VR devices in each of the device sets into a trained three-dimensional reconstruction neural network to obtain a set three-dimensional model corresponding to the device set; For each sub-area of ​​the target park area, determining all the device sets corresponding to the sub-area according to the area range of the sub-area; The set three-dimensional model corresponding to all the device sets corresponding to the sub-region is determined as the sub-region model corresponding to the sub-region.

[0015] As an optional implementation, in the second aspect of the present invention, the first generating module groups all the VR devices into a plurality of device sets based on the position combination rule and according to the device position of each VR device, including: Calculating the geometric center point of the device positions of all the VR devices; Calculate the distance vector between the geometric center point and the regional center point of the target park area; the direction of the distance vector is from the geometric center point to the regional center point, and the size of the distance vector is the distance between the geometric center point and the regional center point; Clustering and partitioning all the VR devices based on the K-MEANS algorithm to obtain multiple initial device set areas; For each initial device collection area in which the number of devices is lower than a preset number threshold, determining other initial device collection areas adjacent to the initial device collection area to obtain a plurality of adjacent device collection areas; Multiplying the device position of the VR device in each of the adjacent device set areas by the distance vector to obtain a corresponding corrected position; Classify the VR device in the initial device set area after the correction into the initial device set area; The VR devices belonging to the same initial device set area are determined as a device set to obtain a plurality of device sets.

[0016] As an optional embodiment, in the second aspect of the present invention, the three-dimensional reconstruction neural network is a RNN neural network, which is trained by a training data set including multiple training images and corresponding three-dimensional model annotations.

[0017] As an optional implementation, in the second aspect of the present invention, the first generating module determines the specific manner of all the device sets corresponding to the sub-area according to the area range of the sub-area, including: Calculate the average value of the device correction positions of all the VR devices in each device set to obtain the set position corresponding to each device set; wherein the device correction position of each VR device is set to the corrected position when the VR device is multiplied by the distance vector to obtain the corresponding corrected position during classification, otherwise it is set to the device position of the VR device; All the device sets whose set locations are within the area range of the sub-area are determined as all the device sets corresponding to the sub-area.

[0018] As an optional implementation, in the second aspect of the present invention, the correction module corrects the intersection of the multiple sub-region models according to a preset intersection correction rule to obtain a plurality of corrected sub-region models, including: For the intersection of any two sub-region models, calculating the difference between the partial models of the two sub-region models corresponding to the intersection; Determine whether the difference is greater than a preset difference threshold, and obtain a determination result; When the judgment result is no, the one with the lower average difference between the two partial models is determined as the model content in the two sub-region models corresponding to the intersection; the average difference is the average value of the difference between the partial model and all other sub-region models with intersections; When the judgment result is yes, the number of first types belonging to power grid equipment and the number of second types belonging to infrastructure in all model part types corresponding to the two part models are determined based on a preset three-dimensional part recognition algorithm; the three-dimensional part recognition algorithm is to match and recognize through a preset three-dimensional template of power grid equipment or a three-dimensional template of infrastructure; Correcting the two partial models of the intersection part according to the first type quantity and the second type quantity to obtain a corrected partial model; The corrected partial model is determined as the model content in the two sub-region models corresponding to the intersection part, and the corresponding corrected sub-region model is obtained.

[0019] As an optional implementation, in the second aspect of the present invention, the correction module corrects the two partial models of the intersection part according to the first type number and the second type number, and obtains the corrected partial model in a specific manner, including: When the number of the first types is greater than a first number threshold, the power grid equipment rules corresponding to the target park area are introduced, and the model parts that have differences in the two partial models of the intersection part and do not comply with the power grid equipment rules are deleted; When the number of the second types is greater than a second number threshold, an infrastructure rule corresponding to the target park area is introduced, and the model parts that are different in the two partial models of the intersection part and do not comply with the infrastructure rule are deleted; The remaining model parts of the two partial models of the intersection part with the lower average difference are retained to obtain the corresponding corrected partial model.

[0020] A third aspect of the present invention discloses another power grid park modeling system based on VR data, the system comprising: A memory storing executable program code; a processor coupled to the memory; The processor calls the executable program code stored in the memory to execute part or all of the steps in the power grid park modeling method based on VR data disclosed in the first aspect of the present invention.

[0021] The fourth aspect of the present invention discloses a computer storage medium, which stores computer instructions. When the computer instructions are called, they are used to execute some or all of the steps in the power grid park modeling method based on VR data disclosed in the first aspect of the present invention.

[0022] Compared with the prior art, the embodiments of the present invention have the following beneficial effects: The present invention can generate corresponding multiple sub-area models based on the image data sent by multiple VR devices in the target park area and the device positions of the VR devices, and then perform model correction based on the intersection part of the sub-area models and a preset intersection correction rule, so as to comprehensively generate a park three-dimensional model corresponding to the target park area based on the model union algorithm, thereby being able to generate a more accurate park three-dimensional model by combining the VR device data in the park, thereby improving the efficiency and accuracy of park modeling and reducing labor costs. BRIEF DESCRIPTION OF THE DRAWINGS

[0023] In order to more clearly illustrate the technical solutions in the embodiments of the present invention, the following briefly introduces the drawings required for use in the description of the embodiments. Obviously, the drawings described below are only some embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without creative work.

[0024] Figure 1 It is a flow chart of a method for modeling a power grid park based on VR data disclosed in an embodiment of the present invention.

[0025] Figure 2 It is a structural schematic diagram of a power grid park modeling system based on VR data disclosed in an embodiment of the present invention.

[0026] Figure 3 It is a structural schematic diagram of another power grid park modeling system based on VR data disclosed in an embodiment of the present invention. DETAILED DESCRIPTION

[0027] In order to enable those skilled in the art to better understand the scheme of the present invention, the technical scheme in the embodiments of the present invention will be clearly and completely described below in conjunction with the drawings in the embodiments of the present invention. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present invention.

[0028] The terms "first", "second", etc. in the specification and claims of the present invention and the above-mentioned drawings are used to distinguish different objects, rather than to describe a specific order. In addition, the terms "including" and "having" and any variations thereof are intended to cover non-exclusive inclusions. For example, a process, method, device, product or equipment that includes a series of steps or units is not limited to the listed steps or units, but may optionally include steps or units that are not listed, or may optionally include other steps or units that are inherent to these processes, methods, products or equipment.

[0029] Reference to "embodiments" herein means that a particular feature, structure, or characteristic described in conjunction with the embodiments may be included in at least one embodiment of the present invention. The appearance of the phrase in various places in the specification does not necessarily refer to the same embodiment, nor is it an independent or alternative embodiment that is mutually exclusive with other embodiments. It is explicitly and implicitly understood by those skilled in the art that the embodiments described herein may be combined with other embodiments.

[0030] The present invention discloses a power grid park modeling method and system based on VR data, which can generate corresponding multiple sub-area models based on image data sent by multiple VR devices in the target park area and the device positions of the VR devices, and then perform model correction based on the intersection of the sub-area models and the preset intersection correction rules, so as to comprehensively generate a park three-dimensional model corresponding to the target park area based on the model union algorithm, thereby being able to generate a more accurate park three-dimensional model by combining the VR device data in the park, improving the efficiency and accuracy of park modeling, and reducing labor costs. The following are detailed descriptions.

[0031] Embodiment 1 See also Figure 1 , Figure 1 1 is a flow chart of a method for modeling a power grid park based on VR data disclosed in an embodiment of the present invention. Figure 1 The described power grid park modeling method based on VR data can be applied to a data processing system / data processing device / data processing server (wherein the server includes a local processing server or a cloud processing server). Figure 1 As shown, the power grid park modeling method based on VR data may include the following operations: 101. Obtain image data sent by multiple VR devices in a target park area.

[0032] 102. Generate multiple sub-area models corresponding to the target park area based on the device position and image data of each VR device. 103. Correct the intersection parts of the multiple sub-region models according to a preset intersection correction rule to obtain multiple corrected sub-region models. 104. According to all corrected sub-region models, a three-dimensional park model corresponding to the target park area is generated based on a model union algorithm.

[0033] It can be seen that the above-mentioned embodiments of the invention can generate corresponding multiple sub-area models based on the image data sent by multiple VR devices in the target park area and the device positions of the VR devices, and then perform model correction based on the intersection part of the sub-area models and the preset intersection correction rules, so as to comprehensively generate a park three-dimensional model corresponding to the target park area based on the model union algorithm, thereby being able to generate a more accurate park three-dimensional model by combining the VR device data in the park, thereby improving the efficiency and accuracy of park modeling and reducing labor costs.

[0034] As an optional embodiment, in the above steps, the VR device is provided with a three-dimensional panoramic image acquisition camera for acquiring image data in a panoramic image format.

[0035] It can be seen that through the above optional embodiments, the device type and function of the VR device are clarified, which can more accurately and comprehensively obtain images within the park, and assist in combining the VR device data within the park to generate a more accurate three-dimensional model of the park, thereby improving the efficiency and accuracy of park modeling and reducing labor costs.

[0036] As an optional embodiment, in the above steps, generating multiple sub-area models corresponding to the target park area according to the device position and image data of each VR device includes: Based on the position combination rule, all VR devices are grouped into multiple device sets according to the device position of each VR device; Input the image data of all VR devices in each device set into the trained 3D reconstruction neural network to obtain a set 3D model corresponding to the device set; For each sub-area of ​​the target park area, determine a set of all devices corresponding to the sub-area according to the area range of the sub-area; The collective three-dimensional model corresponding to the set of all devices corresponding to the sub-region is determined as the sub-region model corresponding to the sub-region.

[0037] It can be seen that through the above optional embodiments, after the VR devices are grouped based on the position combination rules, the images of each device set can be three-dimensionally reorganized to obtain the corresponding set three-dimensional model, and then the sub-region model corresponding to each sub-region can be determined based on the positional relationship of the sub-regions, so as to facilitate the subsequent accurate determination of the three-dimensional model of the park, and assist in combining the VR device data in the park to generate a more accurate three-dimensional model of the park, thereby improving the efficiency and accuracy of park modeling and reducing labor costs.

[0038] As an optional embodiment, in the above steps, based on the position combination rule, according to the device position of each VR device, all VR devices are grouped into multiple device sets, including: Calculate the geometric center point of the device positions of all VR devices; Calculate the distance vector between the geometric center point and the regional center point of the target park area; optionally, the direction of the distance vector points from the geometric center point to the regional center point, and the magnitude of the distance vector is the distance between the geometric center point and the regional center point; All VR devices are clustered and partitioned based on the K-MEANS algorithm to obtain multiple initial device collection areas; For each initial device collection area where the number of devices is lower than a preset number threshold, determine other initial device collection areas adjacent to the initial device collection area to obtain a plurality of adjacent device collection areas; Multiply the device position of the VR device in each adjacent device set area by the distance vector to obtain the corresponding corrected position; Classify the VR device whose position after correction is in the initial device set area into the initial device set area; VR devices belonging to the same initial device set area are determined as a device set to obtain multiple device sets.

[0039] It can be seen that through the above optional embodiments, by calculating the deviation vectors of the center of the device and the center of the area, the device positions of the nearby sets can be corrected for the sets with a smaller number of devices after all the devices are clustered, so that the entire grouping is more reasonable, and each area of ​​the park area has uniform VR devices for three-dimensional reconstruction, which is convenient for the subsequent precise determination of the three-dimensional model of the park, and assists in combining the VR device data in the park to generate a more accurate three-dimensional model of the park, thereby improving the efficiency and accuracy of park modeling and reducing labor costs.

[0040] As an optional embodiment, in the above steps, the three-dimensional reconstruction neural network is a RNN neural network, which is trained by a training data set including a plurality of training images and corresponding three-dimensional model annotations.

[0041] It can be seen that through the above optional embodiments, the network details and training details of the three-dimensional reconstruction neural network are clarified, which can more accurately perform three-dimensional reconstruction on the image of each device set to obtain the corresponding set three-dimensional model points, and assist in combining the VR device data in the park to generate a more accurate three-dimensional model of the park, thereby improving the efficiency and accuracy of park modeling and reducing labor costs.

[0042] As an optional embodiment, in the above step, determining the set of all devices corresponding to the sub-area according to the area range of the sub-area includes: Calculate the average value of the device correction positions of all VR devices in each device set to obtain the set position corresponding to each device set; optionally, the device correction position of each VR device is set to the corrected position when the VR device is multiplied by the distance vector during classification to obtain the corresponding corrected position, otherwise it is set to the device position of the VR device; All device sets whose collection positions are within the area range of the sub-area are determined as all device sets corresponding to the sub-area.

[0043] It can be seen that through the above-mentioned optional embodiments, the position of the set can be obtained by averaging the corrected positions of the devices in the set, so as to determine all the device sets corresponding to the sub-area based on range judgment, thereby facilitating the subsequent accurate determination of the three-dimensional model of the park, and assisting in combining the VR device data in the park to generate a more accurate three-dimensional model of the park, thereby improving the efficiency and accuracy of park modeling and reducing labor costs.

[0044] As an optional embodiment, in the above steps, correcting the intersection of the multiple sub-region models according to a preset intersection correction rule to obtain multiple corrected sub-region models includes: For the intersection of any two sub-region models, calculate the difference between the partial models of the two sub-region models corresponding to the intersection; Determine whether the difference is greater than a preset difference threshold and obtain a determination result; When the judgment result is no, the one with the lower average difference between the two partial models is determined as the model content in the two sub-region models corresponding to the intersection part; optionally, the average difference is the average value of the difference between the partial model and all other sub-region models with the intersection part; When the judgment result is yes, the number of first types belonging to power grid equipment and the number of second types belonging to infrastructure in all model part types corresponding to the two part models are determined based on a preset three-dimensional part recognition algorithm; optionally, the three-dimensional part recognition algorithm is to match and recognize through a preset three-dimensional template of power grid equipment or a three-dimensional template of infrastructure; Correcting the two partial models of the intersection part according to the first type quantity and the second type quantity to obtain a corrected partial model; The corrected partial model is determined as the model content in the two sub-region models corresponding to the intersection part, and the corresponding corrected sub-region model is obtained.

[0045] It can be seen that through the above-mentioned optional embodiments, model correction can be achieved through difference calculation, and when the difference is high, a three-dimensional part recognition algorithm is introduced to determine the model part type to further achieve correction, so as to facilitate the subsequent accurate determination of the three-dimensional model of the park, and assist in combining the VR equipment data in the park to generate a more accurate three-dimensional model of the park, thereby improving the efficiency and accuracy of park modeling and reducing labor costs.

[0046] As an optional embodiment, in the above step, according to the first type quantity and the second type quantity, the two partial models of the intersection part are corrected to obtain the corrected partial model, including: When the number of the first type is greater than the first number threshold, the power grid equipment rule corresponding to the target park area is introduced, and the model part that has differences in the two partial models of the intersection part and does not comply with the power grid equipment rule is deleted; When the number of the second types is greater than the second number threshold, the infrastructure rules corresponding to the target park area are introduced, and the model parts that have differences in the two partial models of the intersection part and do not comply with the infrastructure rules are deleted; The remaining model parts of the two partial models of the intersection part with the lower average difference are retained to obtain the corresponding corrected partial model.

[0047] It can be seen that through the above-mentioned optional embodiments, the timing of introducing corresponding correction rules can be determined according to the size of the number of different model parts, so as to achieve more flexible and accurate model correction, facilitate the subsequent accurate determination of the three-dimensional model of the park, and assist in combining the VR equipment data in the park to generate a more accurate three-dimensional model of the park, thereby improving the efficiency and accuracy of park modeling and reducing labor costs.

[0048] Embodiment 2 See also Figure 2 , Figure 2 Schematic diagram of a power grid park modeling system based on VR data disclosed in an embodiment of the present invention. Figure 2 The described power grid park modeling system based on VR data can be applied to a data processing system / data processing device / data processing server (wherein the server includes a local processing server or a cloud processing server). Figure 2 As shown, the power grid park modeling system based on VR data may include: The acquisition module 201 is used to acquire image data sent by multiple VR devices in the target campus area.

[0049] The first generating module 202 is used to generate a plurality of sub-area models corresponding to the target park area according to the device position and image data of each VR device. The correction module 203 is used to correct the intersection of the multiple sub-region models according to a preset intersection correction rule to obtain multiple corrected sub-region models. The second generating module 204 is used to generate a three-dimensional park model corresponding to the target park area based on all corrected sub-area models and based on a model union algorithm.

[0050] It can be seen that the above-mentioned embodiments of the invention can generate corresponding multiple sub-area models based on the image data sent by multiple VR devices in the target park area and the device positions of the VR devices, and then perform model correction based on the intersection part of the sub-area models and the preset intersection correction rules, so as to comprehensively generate a park three-dimensional model corresponding to the target park area based on the model union algorithm, thereby being able to generate a more accurate park three-dimensional model by combining the VR device data in the park, thereby improving the efficiency and accuracy of park modeling and reducing labor costs.

[0051] As an optional embodiment, the VR device is provided with a three-dimensional panoramic image acquisition camera for acquiring image data in a panoramic image format.

[0052] It can be seen that through the above optional embodiments, the device type and function of the VR device are clarified, which can more accurately and comprehensively obtain images within the park, and assist in combining the VR device data within the park to generate a more accurate three-dimensional model of the park, thereby improving the efficiency and accuracy of park modeling and reducing labor costs.

[0053] As an optional embodiment, the specific manner in which the first generating module generates multiple sub-area models corresponding to the target park area according to the device position and image data of each VR device includes: Based on the position combination rule, all VR devices are grouped into multiple device sets according to the device position of each VR device; Input the image data of all VR devices in each device set into the trained 3D reconstruction neural network to obtain a set 3D model corresponding to the device set; For each sub-area of ​​the target park area, determine a set of all devices corresponding to the sub-area according to the area range of the sub-area; The collective three-dimensional model corresponding to the set of all devices corresponding to the sub-region is determined as the sub-region model corresponding to the sub-region.

[0054] It can be seen that through the above optional embodiments, after the VR devices are grouped based on the position combination rules, the images of each device set can be three-dimensionally reorganized to obtain the corresponding set three-dimensional model, and then the sub-region model corresponding to each sub-region can be determined based on the positional relationship of the sub-regions, so as to facilitate the subsequent accurate determination of the three-dimensional model of the park, and assist in combining the VR device data in the park to generate a more accurate three-dimensional model of the park, thereby improving the efficiency and accuracy of park modeling and reducing labor costs.

[0055] As an optional embodiment, the first generating module groups all VR devices into a plurality of device sets based on the position combination rule and the device position of each VR device, including: Calculate the geometric center point of the device positions of all VR devices; Calculate the distance vector between the geometric center point and the regional center point of the target park area; optionally, the direction of the distance vector points from the geometric center point to the regional center point, and the magnitude of the distance vector is the distance between the geometric center point and the regional center point; All VR devices are clustered and partitioned based on the K-MEANS algorithm to obtain multiple initial device collection areas; For each initial device collection area where the number of devices is lower than a preset number threshold, determine other initial device collection areas adjacent to the initial device collection area to obtain a plurality of adjacent device collection areas; Multiply the device position of the VR device in each adjacent device set area by the distance vector to obtain the corresponding corrected position; Classify the VR device whose position after correction is in the initial device set area into the initial device set area; VR devices belonging to the same initial device set area are determined as a device set to obtain multiple device sets.

[0056] It can be seen that through the above optional embodiments, by calculating the deviation vectors of the center of the device and the center of the area, the device positions of the nearby sets can be corrected for the sets with a smaller number of devices after all the devices are clustered, so that the entire grouping is more reasonable, and each area of ​​the park area has uniform VR devices for three-dimensional reconstruction, which is convenient for the subsequent precise determination of the three-dimensional model of the park, and assists in combining the VR device data in the park to generate a more accurate three-dimensional model of the park, thereby improving the efficiency and accuracy of park modeling and reducing labor costs.

[0057] As an optional embodiment, the three-dimensional reconstruction neural network is a RNN neural network, which is trained by a training data set including a plurality of training images and corresponding three-dimensional model annotations.

[0058] It can be seen that through the above optional embodiments, the network details and training details of the three-dimensional reconstruction neural network are clarified, which can more accurately perform three-dimensional reconstruction on the image of each device set to obtain the corresponding set three-dimensional model points, and assist in combining the VR device data in the park to generate a more accurate three-dimensional model of the park, thereby improving the efficiency and accuracy of park modeling and reducing labor costs.

[0059] As an optional embodiment, the first generating module determines the specific manner of all device sets corresponding to the sub-area according to the area range of the sub-area, including: Calculate the average value of the device correction positions of all VR devices in each device set to obtain the set position corresponding to each device set; optionally, the device correction position of each VR device is set to the corrected position when the VR device is multiplied by the distance vector during classification to obtain the corresponding corrected position, otherwise it is set to the device position of the VR device; All device sets whose collection positions are within the area range of the sub-area are determined as all device sets corresponding to the sub-area.

[0060] It can be seen that through the above-mentioned optional embodiments, the position of the set can be obtained by averaging the corrected positions of the devices in the set, so as to determine all the device sets corresponding to the sub-area based on range judgment, thereby facilitating the subsequent accurate determination of the three-dimensional model of the park, and assisting in combining the VR device data in the park to generate a more accurate three-dimensional model of the park, thereby improving the efficiency and accuracy of park modeling and reducing labor costs.

[0061] As an optional embodiment, the correction module corrects the intersection of multiple sub-region models according to a preset intersection correction rule to obtain multiple corrected sub-region models, including: For the intersection of any two sub-region models, calculate the difference between the partial models of the two sub-region models corresponding to the intersection; Determine whether the difference is greater than a preset difference threshold and obtain a determination result; When the judgment result is no, the one with the lower average difference between the two partial models is determined as the model content in the two sub-region models corresponding to the intersection part; optionally, the average difference is the average value of the difference between the partial model and all other sub-region models with the intersection part; When the judgment result is yes, the number of first types belonging to power grid equipment and the number of second types belonging to infrastructure in all model part types corresponding to the two part models are determined based on a preset three-dimensional part recognition algorithm; optionally, the three-dimensional part recognition algorithm is to match and recognize through a preset three-dimensional template of power grid equipment or a three-dimensional template of infrastructure; Correcting the two partial models of the intersection part according to the first type quantity and the second type quantity to obtain a corrected partial model; The corrected partial model is determined as the model content in the two sub-region models corresponding to the intersection part, and the corresponding corrected sub-region model is obtained.

[0062] It can be seen that through the above-mentioned optional embodiments, model correction can be achieved through difference calculation, and when the difference is high, a three-dimensional part recognition algorithm is introduced to determine the model part type to further achieve correction, so as to facilitate the subsequent accurate determination of the three-dimensional model of the park, and assist in combining the VR equipment data in the park to generate a more accurate three-dimensional model of the park, thereby improving the efficiency and accuracy of park modeling and reducing labor costs.

[0063] As an optional embodiment, the correction module corrects the two partial models of the intersection part according to the first type quantity and the second type quantity to obtain the corrected partial model in a specific manner including: When the number of the first type is greater than the first number threshold, the power grid equipment rule corresponding to the target park area is introduced, and the model part that has differences in the two partial models of the intersection part and does not comply with the power grid equipment rule is deleted; When the number of the second types is greater than the second number threshold, the infrastructure rules corresponding to the target park area are introduced, and the model parts that have differences in the two partial models of the intersection part and do not comply with the infrastructure rules are deleted; The remaining model parts of the two partial models of the intersection part with the lower average difference are retained to obtain the corresponding corrected partial model.

[0064] It can be seen that through the above-mentioned optional embodiments, the timing of introducing corresponding correction rules can be determined according to the size of the number of different model parts, so as to achieve more flexible and accurate model correction, facilitate the subsequent accurate determination of the three-dimensional model of the park, and assist in combining the VR equipment data in the park to generate a more accurate three-dimensional model of the park, thereby improving the efficiency and accuracy of park modeling and reducing labor costs.

[0065] Embodiment 3 See also Figure 3 , Figure 3 This is another power grid park modeling system based on VR data disclosed in an embodiment of the present invention. Figure 3 The described power grid park modeling system based on VR data is applied to a data processing system / data processing device / data processing server (wherein the server includes a local processing server or a cloud processing server). Figure 3 As shown, the power grid park modeling system based on VR data may include: A memory 301 storing executable program codes; a processor 302 coupled to the memory 301; The processor 302 calls the executable program code stored in the memory 301 to execute the steps of the power grid park modeling method based on VR data described in the first embodiment.

[0066] Embodiment 4 An embodiment of the present invention discloses a computer-readable storage medium storing a computer program for electronic data exchange, wherein the computer program enables a computer to execute the steps of the method for modeling a power grid park based on VR data described in the first embodiment.

[0067] Embodiment 5 An embodiment of the present invention discloses a computer program product, which includes a non-transitory computer-readable storage medium storing a computer program, and the computer program is operable to enable a computer to execute the steps of the power grid park modeling method based on VR data described in Example 1.

[0068] The above describes specific embodiments of the present specification, and other embodiments are within the scope of the appended claims. In some cases, the actions or steps recorded in the claims can be performed in an order different from that in the embodiments and still achieve the desired results. In addition, the processes depicted in the accompanying drawings do not necessarily have to be performed in the specific order or sequential order shown to achieve the desired results. In some embodiments, multitasking and parallel processing are also possible or may be advantageous.

[0069] The systems, devices, modules or units described in the above embodiments may be implemented by computer chips or entities, or by products with certain functions. A typical implementation device is a computer. Specifically, the computer may be, for example, a personal computer, a laptop computer, a cellular phone, a camera phone, a smart phone, a personal digital assistant, a media player, a navigation device, an email device, a game console, a tablet computer, a wearable device, or a combination of any of these devices.

[0070] For the convenience of description, the above device is described in various units according to their functions. Of course, when implementing this specification, the functions of each unit can be implemented in the same or multiple software and / or hardware.

[0071] Those skilled in the art will appreciate that the embodiments of this specification may be provided as methods, systems, or computer program products. Therefore, the embodiments of this specification may be in the form of complete hardware embodiments, complete software embodiments, or embodiments in combination with software and hardware. Moreover, the embodiments of this specification may be in the form of a computer program product implemented in one or more computer-usable storage media (including but not limited to disk storage, CD-ROM, optical storage, etc.) that contain computer-usable program code.

[0072] This specification is described with reference to the flowcharts and / or block diagrams of the methods, devices (systems), and computer program products according to the embodiments of this specification. It should be understood that each process and / or box in the flowchart and / or block diagram, as well as the combination of the processes and / or boxes in the flowchart and / or block diagram, can be implemented by computer program instructions. These computer program instructions can be provided to a processor of a general-purpose computer, a special-purpose computer, an embedded processor, or other programmable data processing device to produce a machine, so that the instructions executed by the processor of the computer or other programmable data processing device generate instructions for implementing the processes in the flowchart and / or block diagram. Figure 1 A process or multiple processes and / or boxes Figure 1 A device that provides the functions specified in a block or multiple blocks.

[0073] These computer program instructions may also be stored in a computer-readable memory capable of directing a computer or other programmable data processing device to operate in a specific manner, so that the instructions stored in the computer-readable memory produce an article of manufacture comprising an instruction device, which implements the process Figure 1 A process or multiple processes and / or boxes Figure 1 A function specified in one or more boxes.

[0074] These computer program instructions can also be loaded onto a computer or other programmable data processing device so that a series of operating steps are executed on the computer or other programmable device to produce a computer-implemented process, thereby providing instructions for implementing the process. Figure 1 A process or multiple processes and / or boxes Figure 1 The steps for the functions specified in one or more boxes.

[0075] In a typical configuration, a computing device includes one or more processors (CPU), input / output interfaces, network interfaces, and memory.

[0076] The memory may include non-permanent storage in a computer-readable medium, random access memory (RAM) and / or non-volatile memory in the form of read-only memory (ROM) or flash RAM. The memory is an example of a computer-readable medium.

[0077] Computer readable media include permanent and non-permanent, removable and non-removable media that can be implemented by any method or technology to store information. Information can be computer readable instructions, data structures, program modules or other data. Examples of computer storage media include, but are not limited to, phase change memory (PRAM), static random access memory (SRAM), dynamic random access memory (DRAM), other types of random access memory (RAM), read-only memory (ROM), electrically erasable programmable read-only memory (EEPROM), flash memory or other memory technology, compact disk read-only memory (CD-ROM), digital versatile disk (DVD) or other optical storage, magnetic cassettes, magnetic disk storage or other magnetic storage devices or any other non-transmission media that can be used to store information that can be accessed by a computing device. As defined herein, computer readable media does not include temporary computer readable media (transitory media), such as modulated data signals and carrier waves.

[0078] It should also be noted that the terms "include", "comprises" or any other variations thereof are intended to cover non-exclusive inclusion, so that a process, method, commodity or device including a series of elements includes not only those elements, but also other elements not explicitly listed, or also includes elements inherent to such process, method, commodity or device. In the absence of more restrictions, the elements defined by the sentence "comprises a ..." do not exclude the existence of other identical elements in the process, method, commodity or device including the elements.

[0079] This specification may be described in the general context of computer-executable instructions executed by a computer, such as program modules. Generally, program modules include routines, programs, objects, components, data structures, etc. that perform specific tasks or implement specific abstract data types. This specification may also be practiced in distributed computing environments where tasks are performed by remote processing devices connected through a communication network. In a distributed computing environment, program modules may be located in local and remote computer storage media, including storage devices.

[0080] Each embodiment in this specification is described in a progressive manner, and the same or similar parts between the embodiments can be referred to each other, and each embodiment focuses on the differences from other embodiments. In particular, for the system embodiment, since it is basically similar to the method embodiment, the description is relatively simple, and the relevant parts can be referred to the partial description of the method embodiment.

[0081] Finally, it should be noted that the power grid park modeling method and system based on VR data disclosed in the embodiment of the present invention discloses only the preferred embodiment of the present invention, which is only used to illustrate the technical solution of the present invention, rather than to limit it. Although the present invention has been described in detail with reference to the aforementioned embodiments, those skilled in the art should understand that the technical solutions described in the aforementioned embodiments can still be modified, or some of the technical features therein can be replaced by equivalents. However, these modifications or replacements do not deviate the essence of the corresponding technical solutions from the spirit and scope of the technical solutions of the embodiments of the present invention.

Claims

1. A power grid park modeling method based on VR data, characterized in that: The method comprises: Acquire image data sent by multiple VR devices in the target park area; Generate multiple sub-area models corresponding to the target park area according to the device position of each VR device and the image data; Correcting the intersection parts of the multiple sub-region models according to a preset intersection correction rule to obtain multiple corrected sub-region models; According to all the corrected sub-region models, based on the model union algorithm, a three-dimensional park model corresponding to the target park area is generated.

2. The power grid park modeling method based on VR data according to claim 1 is characterized in that: The VR device is provided with a three-dimensional panoramic image acquisition camera for acquiring the image data in a panoramic image format.

3. The power grid park modeling method based on VR data according to claim 2 is characterized in that: The step of generating a plurality of sub-area models corresponding to the target park area according to the device position of each VR device and the image data includes: Based on the position combination rule, grouping all the VR devices into a plurality of device sets according to the device position of each of the VR devices; Inputting the image data of all the VR devices in each of the device sets into a trained three-dimensional reconstruction neural network to obtain a set three-dimensional model corresponding to the device set; For each sub-area of ​​the target park area, determining all the device sets corresponding to the sub-area according to the area range of the sub-area; The set three-dimensional model corresponding to all the device sets corresponding to the sub-region is determined as the sub-region model corresponding to the sub-region.

4. The power grid park modeling method based on VR data according to claim 3 is characterized in that: The location-based combination rule groups all the VR devices into a plurality of device sets according to the device position of each VR device, including: Calculating the geometric center point of the device positions of all the VR devices; Calculate the distance vector between the geometric center point and the regional center point of the target park area; the direction of the distance vector is from the geometric center point to the regional center point, and the size of the distance vector is the distance between the geometric center point and the regional center point; Clustering and partitioning all the VR devices based on the K-MEANS algorithm to obtain multiple initial device set areas; For each initial device collection area in which the number of devices is lower than a preset number threshold, determining other initial device collection areas adjacent to the initial device collection area to obtain a plurality of adjacent device collection areas; Multiplying the device position of the VR device in each of the adjacent device set areas by the distance vector to obtain a corresponding corrected position; Classify the VR device in the initial device set area after the correction into the initial device set area; The VR devices belonging to the same initial device set area are determined as a device set to obtain a plurality of device sets.

5. The power grid park modeling method based on VR data according to claim 3 is characterized in that: The three-dimensional reorganization neural network is a RNN neural network, which is trained by a training data set including a plurality of training images and corresponding three-dimensional model annotations.

6. The method for modeling a power grid park based on VR data according to claim 4 is characterized in that: The step of determining, according to the area range of the sub-area, all the device sets corresponding to the sub-area includes: Calculate the average value of the device correction positions of all the VR devices in each device set to obtain the set position corresponding to each device set; wherein the device correction position of each VR device is set to the corrected position when the VR device is multiplied by the distance vector to obtain the corresponding corrected position during classification, otherwise it is set to the device position of the VR device; All the device sets whose set locations are within the area range of the sub-area are determined as all the device sets corresponding to the sub-area.

7. The method for modeling a power grid park based on VR data according to claim 1, characterized in that: The step of correcting the intersection of the plurality of sub-region models according to a preset intersection correction rule to obtain a plurality of corrected sub-region models includes: For the intersection of any two sub-region models, calculating the difference between the partial models of the two sub-region models corresponding to the intersection; Determine whether the difference is greater than a preset difference threshold, and obtain a determination result; When the judgment result is no, the one with the lower average difference between the two partial models is determined as the model content in the two sub-region models corresponding to the intersection; the average difference is the average value of the difference between the partial model and all other sub-region models with intersections; When the judgment result is yes, the number of first types belonging to power grid equipment and the number of second types belonging to infrastructure in all model part types corresponding to the two part models are determined based on a preset three-dimensional part recognition algorithm; the three-dimensional part recognition algorithm is to match and recognize through a preset three-dimensional template of power grid equipment or a three-dimensional template of infrastructure; Correcting the two partial models of the intersection part according to the first type quantity and the second type quantity to obtain a corrected partial model; The corrected partial model is determined as the model content in the two sub-region models corresponding to the intersection part, and the corresponding corrected sub-region model is obtained.

8. The method for modeling a power grid park based on VR data according to claim 7, characterized in that: The step of correcting the two partial models of the intersection part according to the first type quantity and the second type quantity to obtain a corrected partial model includes: When the number of the first types is greater than a first number threshold, the power grid equipment rules corresponding to the target park area are introduced, and the model parts that have differences in the two partial models of the intersection part and do not comply with the power grid equipment rules are deleted; When the number of the second types is greater than a second number threshold, an infrastructure rule corresponding to the target park area is introduced, and the model parts that are different in the two partial models of the intersection part and do not comply with the infrastructure rule are deleted; The remaining model parts of the two partial models of the intersection part with the lower average difference are retained to obtain the corresponding corrected partial model.

9. A power grid park modeling system based on VR data, characterized in that: The system comprises: An acquisition module, used to acquire image data sent by multiple VR devices in the target park area; A first generating module, configured to generate a plurality of sub-region models corresponding to the target park area according to the device position of each VR device and the image data; A correction module, used to correct the intersection of the plurality of sub-region models according to a preset intersection correction rule to obtain a plurality of corrected sub-region models; The second generation module is used to generate a three-dimensional park model corresponding to the target park area based on all the corrected sub-area models and based on a model union algorithm.

10. A power grid park modeling system based on VR data, characterized in that: The system comprises: A memory storing executable program code; a processor coupled to the memory; The processor calls the executable program code stored in the memory to execute the power grid park modeling method based on VR data as described in any one of claims 1-8.

Images