Three-dimensional modeling method and device applied to power distribution room and electronic equipment

Abstract

The embodiment of the invention discloses a three-dimensional modeling method and device applied to a power distribution room and electronic equipment. A specific embodiment of the method comprises the steps of generating an image quality improved image set according to a target image set; performing image splicing on the images after image quality improvement in the image set after image quality improvement; generating a model according to the spliced image and a pre-trained initial three-dimensional model, and generating an initial power distribution room three-dimensional model and model description information; for the model element description information, executing the following processing steps: determining whether a model element matched with the model element description information exists in a pre-constructed model element library or not according to an element type and an element feature vector included in the model element description information; in response to existence, determining the model elements matched with the model element description information as candidate model elements; and performing model element updating on the initial three-dimensional model of the power distribution room. According to the embodiment, the modeling period is shortened, and the computing resource consumption is reduced.

Description

Technical Field

[0001] The embodiments of the present disclosure relate to the field of computer technology, and in particular to a three-dimensional modeling method, device, and electronic equipment applied to a power distribution room. Background Art

[0002] As one of the important facilities for power supply, the distribution room can generate a refined monitoring distribution room through 3D modeling, which can effectively build the corresponding relationship between the distribution room and the 3D model, and help the subsequent control and management of the distribution room based on the 3D model. At present, common 3D modeling methods include: 3D modeling through point cloud modeling.

[0003] However, when the above method is adopted, the following technical problems often occur: Point cloud modeling requires a large amount of data processing, which increases the modeling cycle and computing resource consumption; Next, when performing 3D modeling based on images, there is a further technical problem: The image-based modeling method has poor model accuracy for the three-dimensional model.

[0004] The above information disclosed in this Background section is only for enhancement of understanding of the background of the inventive concept and therefore it may contain information that does not form the prior art that is already known to a person of ordinary skill in the art. Summary of the invention

[0005] The content of this disclosure is used to introduce concepts in a brief form, which will be described in detail in the detailed implementation section below. The content of this disclosure is not intended to identify the key features or essential features of the technical solution claimed for protection, nor is it intended to limit the scope of the technical solution claimed for protection.

[0006] Some embodiments of the present disclosure propose a three-dimensional modeling method, device, and electronic device applied to a power distribution room to solve one or more of the technical problems mentioned in the above background technology section.

[0007] In a first aspect, some embodiments of the present disclosure provide a three-dimensional modeling method for a distribution room, the method comprising: acquiring a target image set, wherein the target image set is a pre-collected wide-angle image of the distribution room to be three-dimensionally modeled; generating a set of improved images based on the target image set, wherein the improved images are images obtained by performing local image quality improvement on at least one target image; performing image stitching on each of the improved images in the improved image set to generate a stitched image; generating a model based on the stitched images and a pre-trained initial three-dimensional model, generating an initial distribution room three-dimensional model and model description information, wherein the model description information comprises: a model element description information set, ... The element description information includes: element type, element feature vector and element position information, and the element position information represents the position of the model element corresponding to the model element description information in the initial three-dimensional model of the distribution room; for each model element description information in the above-mentioned model element description information set, the following processing steps are performed: according to the element type and element feature vector included in the above-mentioned model element description information, it is determined whether there is a model element matching the above-mentioned model element description information in the pre-built model element library; in response to the existence, the model element matching the above-mentioned model element description information is determined as a candidate model element; according to the obtained candidate model element set, the model elements of the above-mentioned initial three-dimensional model of the distribution room are updated to generate an updated three-dimensional model of the distribution room.

[0008] In a second aspect, some embodiments of the present disclosure provide a three-dimensional modeling device for a distribution room, the device comprising: an acquisition unit, configured to acquire a target image set, wherein the target image set is a pre-collected wide-angle image of the distribution room to be three-dimensionally modeled; a first generation unit, configured to generate a set of improved images based on the target image set, wherein the improved images are images obtained by performing local image quality improvement on at least one target image; an image stitching unit, configured to stitch each improved image in the improved image set to generate a stitched image; a second generation unit, configured to generate a model based on the stitched image and a pre-trained initial three-dimensional model, to generate an initial distribution room three-dimensional model and model description information, wherein the model description information comprises: model elements A description information set, wherein the model element description information includes: element type, element feature vector and element position information, wherein the element position information represents the position of the model element corresponding to the model element description information in the initial three-dimensional model of the distribution room; an execution unit, configured to perform the following processing steps for each model element description information in the above-mentioned model element description information set: determining whether there is a model element matching the above-mentioned model element description information in a pre-built model element library according to the element type and element feature vector included in the above-mentioned model element description information; in response to the existence, determining the model element matching the above-mentioned model element description information as a candidate model element; a model element updating unit, configured to perform model element update on the above-mentioned initial three-dimensional model of the distribution room according to the obtained candidate model element set, so as to generate an updated three-dimensional model of the distribution room.

[0009] In a third aspect, some embodiments of the present disclosure provide an electronic device comprising: one or more processors; a storage device on which one or more programs are stored, and when the one or more programs are executed by the one or more processors, the one or more processors implement the method described in any implementation manner of the above-mentioned first aspect.

[0010] In a fourth aspect, some embodiments of the present disclosure provide a computer-readable medium having a computer program stored thereon, wherein when the program is executed by a processor, the method described in any implementation manner of the above-mentioned first aspect is implemented.

[0011] The above-mentioned various embodiments of the present disclosure have the following beneficial effects: through the three-dimensional modeling method applied to the distribution room of some embodiments of the present disclosure, the modeling cycle is shortened and the consumption of computing resources is reduced. Specifically, the reason for the long modeling cycle is that the point cloud modeling method has a large amount of data processing. Based on this, the three-dimensional modeling method applied to the distribution room of some embodiments of the present disclosure, first, obtain a target image set, wherein the above-mentioned target image set is a pre-collected wide-angle image of the distribution room to be three-dimensionally modeled. Compared with the point cloud modeling method, the image-based three-dimensional modeling method has the advantage of convenient image acquisition. Secondly, according to the above-mentioned target image set, a set of images with improved image quality is generated, wherein the image with improved image quality is an image after local image quality improvement through at least one target image. By improving the image quality, the model accuracy of the subsequently generated three-dimensional model is guaranteed. Then, each of the images with improved image quality in the above-mentioned image quality improvement set is image stitching to generate a stitched image. Further, according to the above-mentioned spliced ​​image and the pre-trained initial three-dimensional model generation model, an initial distribution room three-dimensional model and model description information are generated, wherein the above-mentioned model description information includes: a model element description information set, the model element description information includes: an element type, an element feature vector and an element position information, and the element position information represents the position of the model element corresponding to the model element description information in the initial distribution room three-dimensional model. In this way, the image is combined to generate an initial distribution room three-dimensional model for the distribution room to be three-dimensionally modeled. In addition, for each model element description information in the above-mentioned model element description information set, the following processing steps are performed: the first step is to determine whether there is a model element matching the above-mentioned model element description information in the pre-built model element library according to the element type and element feature vector included in the above-mentioned model element description information. The second step is to determine the model element matching the above-mentioned model element description information as a candidate model element in response to the existence. Finally, according to the obtained candidate model element set, the model element of the above-mentioned initial distribution room three-dimensional model is updated to generate an updated distribution room three-dimensional model. By matching the model element replacement method, the model accuracy of the updated distribution room three-dimensional model is further improved. This method only requires images to generate a three-dimensional model. Compared with the point cloud modeling method, it shortens the modeling cycle and reduces computing resource consumption. BRIEF DESCRIPTION OF THE DRAWINGS

[0012] The above and other features, advantages and aspects of the embodiments of the present disclosure will become more apparent with reference to the following detailed description in conjunction with the accompanying drawings. Throughout the accompanying drawings, the same or similar reference numerals represent the same or similar elements. It should be understood that the drawings are schematic and that components and elements are not necessarily drawn to scale.

[0013] Figure 1is a flow chart of some embodiments of a three-dimensional modeling method applied to a power distribution room according to the present disclosure; Figure 2 It is a structural schematic diagram of some embodiments of the three-dimensional modeling device applied to the power distribution room according to the present disclosure; Figure 3 It is a schematic diagram of the structure of an electronic device suitable for implementing some embodiments of the present disclosure. DETAILED DESCRIPTION

[0014] Embodiments of the present disclosure will be described in more detail below with reference to the accompanying drawings. Although certain embodiments of the present disclosure are shown in the accompanying drawings, it should be understood that the present disclosure can be implemented in various forms and should not be construed as being limited to the embodiments set forth herein. On the contrary, these embodiments are provided to provide a more thorough and complete understanding of the present disclosure. It should be understood that the drawings and embodiments of the present disclosure are only for exemplary purposes and are not intended to limit the scope of protection of the present disclosure.

[0015] It should also be noted that, for ease of description, only the parts related to the invention are shown in the drawings. In the absence of conflict, the embodiments and features in the embodiments of the present disclosure can be combined with each other.

[0016] It should be noted that the concepts such as "first" and "second" mentioned in the present disclosure are only used to distinguish different devices, modules or units, and are not used to limit the order or interdependence of the functions performed by these devices, modules or units.

[0017] It should be noted that the modifications of "one" and "plurality" mentioned in the present disclosure are illustrative rather than restrictive, and those skilled in the art should understand that unless otherwise clearly indicated in the context, it should be understood as "one or more".

[0018] The names of the messages or information exchanged between multiple devices in the embodiments of the present disclosure are only used for illustrative purposes and are not used to limit the scope of these messages or information.

[0019] The present disclosure will be described in detail below with reference to the accompanying drawings and in conjunction with embodiments.

[0020] refer to Figure 1 , shows a process 100 of some embodiments of the three-dimensional modeling method applied to a power distribution room according to the present disclosure. The three-dimensional modeling method applied to a power distribution room includes the following steps: Step 101: Obtain a target image set.

[0021] In some embodiments, the execution subject (for example, a computing device) of the three-dimensional modeling method applied to the power distribution room can obtain the above-mentioned target image set through a wired connection or a wireless connection. Among them, the target image set is a pre-collected wide-angle image of the power distribution room to be three-dimensionally modeled. Specifically, the target image set is an image set collected by a camera with a wide-angle lens, which contains a panoramic view of the power distribution room to be three-dimensionally modeled. The power distribution room to be three-dimensionally modeled can be a power distribution room whose corresponding three-dimensional model is to be generated by modeling.

[0022] It should be noted that the above-mentioned wireless connection methods may include but are not limited to 3G / 4G / 5G connection, WiFi connection, Bluetooth connection, WiMAX connection, Zigbee connection, UWB (ultra wideband) connection, and other wireless connection methods currently known or to be developed in the future.

[0023] It should be noted that the above-mentioned computing device can be hardware or software. When the computing device is hardware, it can be implemented as a distributed cluster consisting of multiple servers or terminal devices, or it can be implemented as a single server or a single terminal device. When the computing device is embodied as software, it can be installed in the hardware devices listed above. It can be implemented as multiple software or software modules for providing distributed services, for example, or it can be implemented as a single software or software module. No specific limitation is made here. It should be understood that the number of computing devices can be any number according to the implementation needs.

[0024] Step 102: Generate a set of images with improved image quality based on the target image set.

[0025] In some embodiments, the execution subject may generate a set of images with improved image quality based on the target image set. The improved image is an image obtained by partially improving the image quality of at least one target image. In practice, when collecting target images, there are often repeated areas between the collected target images. Therefore, the set of images with improved image quality may be generated based on the target image set. Specifically, the execution subject may generate the improved image by stacking images.

[0026] As an example, the target image set may include: target image A, target image B, and target image C. Among them, target image A and target image B have an overlapping area A. Target image B and target image C have an overlapping area B. Therefore, for target image A and target image B, the above-mentioned execution subject may splice target image A and target image B, and average the pixel values ​​of the pixel points of target image A and target image B in the overlapping area A to obtain image A after image quality improvement. The above-mentioned execution subject may splice target image B and target image C, and average the pixel values ​​of the pixel points of target image B and target image C in the overlapping area B to obtain image B after image quality improvement.

[0027] In some optional implementations of some embodiments, the execution subject generating the image set after image quality improvement according to the target image set may include the following steps: In the first step, for each target image in the above target image set, perform the following image preprocessing steps: The first sub-step is to perform distortion calibration on the target image to generate a distortion-corrected image.

[0028] In practice, since the target image is a wide-angle image, there is a certain degree of distortion. Therefore, the above-mentioned execution subject can calibrate the distortion of the target image through geometric correction to generate a distortion-corrected image.

[0029] The second sub-step is to perform target detection on the above-mentioned distortion-corrected image to generate a target object description information set.

[0030] Among them, the target object description information in the target object description information set includes: a set of object feature points. In practice, the target object, as an important content in the image, is extremely important for the subsequent three-dimensional modeling. For example, the target object may be a transformer, and the accuracy of transformer modeling affects the availability of the updated three-dimensional model of the distribution room generated subsequently. And the image alignment method based on the target object has a faster alignment speed than the full pixel comparison method. In addition, considering that target detection is only one of the sub-steps in image preprocessing, in order to improve the efficiency of target detection, the present disclosure adopts the NanoDet model to perform target detection on the above-mentioned distortion-corrected image to generate a target object description information set.

[0031] In the second step, according to the target object description information set corresponding to the target image, image similarity matching is performed on the target images in the above target image set to generate a target image group set.

[0032] In practice, the above-mentioned execution entity can determine the feature point matching degree of the object feature point set included in the target object description information corresponding to the target image through feature point matching, so as to take the matched target image as the target image group to obtain the target image group set.

[0033] As an example, the target object description information set corresponding to the target image A includes: target object description information A1 and target object description information A2. Among them, the object feature point set included in the target object description information A1 includes: object feature point A 11 and object feature point A 12 The target object description information A2 includes a set of object feature points: 21 and object feature point A 22 The target object description information set corresponding to the target image B includes: target object description information B1 and target object description information B2. The target object description information B1 includes the object feature point set: object feature point B 11 and object feature point B 12 The target object description information B2 includes a set of object feature points: object feature points B 21 and object feature point B 22 Among them, the object feature point A 11 and object feature point A 12 and object feature points B 11 and object feature point B 12 Matching. Object feature point A 21 and object feature point A 22 and object feature points B 21 and object feature point B 22 Therefore, target image A and target image B constitute a target image group.

[0034] In the third step, for each target image group in the above target image group set, the following image quality improvement steps are performed: In the first sub-step, a target image is randomly selected from the target image group as a base image.

[0035] As an example, the target image group may include: a target image A and a target image B. The above execution subject may select the target image A as the base image.

[0036] The second sub-step is to locally enhance the image quality of the base image according to the target images in the target image group except the base image, so as to generate an enhanced image in the enhanced image set.

[0037] In practice, the execution entity may only superimpose the local area where the object feature points are located, which is included in the target image group except the base image, onto the base image, and perform pixel value averaging to generate an image with improved image quality.

[0038] Step 103 , stitching the enhanced images in the enhanced image set to generate a stitched image.

[0039] In some embodiments, the execution subject may stitch the enhanced images in the enhanced image set to generate a stitched image. In practice, the execution subject may stitch the enhanced images in sequence according to the image acquisition order to obtain the stitched image.

[0040] In some optional implementations of some embodiments, the execution subject stitches the enhanced images in the enhanced image set to generate a stitched image, which may include the following steps: In the first step, for each enhanced image in the enhanced image set, feature points are extracted from the horizontal edge region in the enhanced image to generate edge region features.

[0041] Among them, the horizontal edge area is the rectangular area on both sides of the image in the image after image quality improvement. In practice, due to the acquisition order of the target image, the global feature point extraction method has a large amount of data processing, and the accuracy improvement of image stitching is not high. Therefore, the present disclosure only extracts feature points from the horizontal edge area in the image after image quality improvement to generate edge area features. In practice, the above-mentioned execution entity can use the SIFT (Scale-Invariant Feature Transform) algorithm to extract feature points from the horizontal edge area in the above-mentioned image after image quality improvement to generate edge area features.

[0042] The second step is to perform image matching on the enhanced images in the enhanced image set according to the edge region features corresponding to the enhanced images, so as to generate a stitching order index array. The stitching order index array represents the image stitching order of each enhanced image in the enhanced image set. In practice, the execution subject can perform image matching on the enhanced images in the enhanced image set by matching feature points.

[0043] As an example, the enhanced image set may include: enhanced image A, enhanced image B, enhanced image C, and enhanced image D. Among them, enhanced image A corresponds to index A. Enhanced image B corresponds to index B. Enhanced image C corresponds to index C. Enhanced image D corresponds to index D. The initial stitching order index array may be [index A, index B, index C, index D]. First, for enhanced image A, the edge region features corresponding to enhanced image A are sequentially matched with the edge region features corresponding to enhanced image B, the edge region features corresponding to enhanced image C, and the edge region features corresponding to enhanced image D, for example, matched with the edge region features corresponding to enhanced image C, so the initial stitching order index array after the first adjustment may be [index A, index C, index B, index D]. Next, the edge region features corresponding to the enhanced image C are matched with the edge region features corresponding to the enhanced image B and the edge region features corresponding to the enhanced image D in sequence, for example, the edge region features corresponding to the enhanced image C are matched, so the initial splicing order index array after the second adjustment can be [index A, index C, index D, index B]. Next, the edge region features corresponding to the enhanced image D are matched with the edge region features corresponding to the enhanced image B, for example, the edge region features corresponding to the enhanced image D are matched with the edge region features corresponding to the enhanced image B, so [index A, index C, index D, index B] is the splicing order index array.

[0044] The third step is to stitch the enhanced images in the enhanced image set according to the stitching order index array to generate the stitched image.

[0045] As an example, the above-mentioned execution entity can splice the improved image A corresponding to index A to the left side of the improved image C corresponding to index C, splice the improved image C corresponding to index C to the left side of the improved image D corresponding to index D, and splice the improved image D corresponding to index D to the left side of the improved image B corresponding to index B.

[0046] Step 104, generating a model based on the spliced ​​image and the pre-trained initial three-dimensional model, generating an initial distribution room three-dimensional model and model description information.

[0047] In some embodiments, the above-mentioned execution entity can generate a model based on the spliced ​​image and the pre-trained initial three-dimensional model, and generate an initial distribution room three-dimensional model and model description information. Among them, the model description information includes: a set of model element description information. The model element description information includes: element type, element feature vector and element position information. The element position information represents the position of the model element corresponding to the model element description information in the initial distribution room three-dimensional model. The element type represents the element category of the model element. The element feature vector can be a one-dimensional feature vector for the model element.

[0048] Optionally, the initial three-dimensional model generation model includes: an image encoder, an image decoder, a feature refinement model and a threshold adjustment model. The image encoder includes: a first 2D convolution layer, a first residual convolution block, a second residual convolution block, a third residual convolution block, a fourth residual convolution block, a fifth residual convolution block, a sixth residual convolution block, a seventh residual convolution block, a second 2D convolution layer, a third 2D convolution layer and a fourth 2D convolution layer. A maximum pooling layer is provided between the first 2D convolution layer and the first residual convolution block. A maximum pooling layer is provided between the second 2D convolution layer and the third 2D convolution layer. A maximum pooling layer is provided between the third 2D convolution layer and the fourth 2D convolution layer. The number of channels of the first residual convolution block is (64, 64, 256). The number of channels of the second residual convolution block is (64, 64, 256). The number of channels of the third residual convolution block is (64, 64, 256). The number of channels of the fourth residual convolution block is (128, 128, 256). The number of channels of the fifth residual convolution block is (128, 128, 256). The number of channels of the sixth residual convolution block is (128, 128, 256). The number of channels of the seventh residual convolution block is (128, 128, 256). The decoder includes: 5 serially connected three-dimensional deconvolution layers. Specifically, the 5 serially connected three-dimensional deconvolution layers include: a first three-dimensional deconvolution layer, a second three-dimensional deconvolution layer, a third three-dimensional deconvolution layer, a fourth three-dimensional deconvolution layer and a fifth three-dimensional deconvolution layer. Among them, the convolution kernel sizes of the first three-dimensional deconvolution layer, the second three-dimensional deconvolution layer, the third three-dimensional deconvolution layer and the fourth three-dimensional deconvolution layer are all 4 3 The convolution kernel size of the fifth 3D deconvolution layer is 1 3 . The number of channels of the first 3D deconvolution layer is 512. The number of channels of the second 3D deconvolution layer is 128. The number of channels of the third 3D deconvolution layer is 32. The number of channels of the fourth 3D deconvolution layer is 8. The number of channels of the fifth 3D deconvolution layer is 1. The feature refinement model includes: the first 3D convolution layer, the second 3D convolution layer, the third 3D convolution layer, the first fully connected layer, the second fully connected layer, the first attention block, the second attention block and the third attention block. Among them, the convolution kernel size of the first 3D convolution layer, the second 3D convolution layer and the third 3D convolution layer is 4 3The number of channels of the first 3D convolution layer is 32. The number of channels of the second 3D convolution layer is 64. The number of channels of the third 3D convolution layer is 128. The first attention block, the second attention block and the third attention block each include an attention mechanism layer and a 3D deconvolution layer. The number of channels of the 3D deconvolution layer included in the first attention block is 64 and the convolution kernel size is 4. 3 The second attention block includes a 3D deconvolution layer with 32 channels and a convolution kernel size of 4. 3 The third attention block includes a 3D deconvolution layer with 1 channel and 4 convolution kernels. 3 The threshold adjustment model can use YOLO as the backbone network. Specifically, the threshold adjustment model extracts image features from the spliced ​​image, converts them into feature maps of three different feature dimensions, and superimposes them, predicts the category probability of the target object framed by the anchor frame, and uses a threshold adaptive method to adjust the threshold to selectively adjust the threshold during 3D modeling.

[0049] In some optional implementations of some embodiments, the execution subject generates a model based on the stitched image and the pre-trained initial three-dimensional model to generate an initial distribution room three-dimensional model and model description information, which may include the following steps: The first step is to generate image encoding features based on the above image encoder and the above spliced ​​image.

[0050] The second step is to generate image decoded features based on the above image decoder and the above image encoded features.

[0051] The third step is to generate refined image features based on the feature refinement model and the image decoded features.

[0052] The fourth step is to generate threshold adjustment parameters according to the threshold adjustment model and the stitched image.

[0053] The fifth step is to generate the initial three-dimensional model of the distribution room and the model description information according to the threshold adjustment parameters and the refined image features.

[0054] Specifically, the element type can be the category of the target object framed by the threshold adjustment model through the prediction anchor frame. The element feature vector can be a one-dimensional feature vector corresponding to the target object framed by the prediction anchor frame. The element position information can represent the position of the target object after three-dimensional reconstruction in the initial three-dimensional model of the power distribution room. Specifically, the element position information can be determined by projection.

[0055] The above-mentioned contents of "optionally" and "in some optional implementations of some embodiments", as an inventive point of the present disclosure, solve the second technical problem mentioned in the background technology, namely, "the model accuracy of the three-dimensional model obtained by modeling based on the image is poor". Based on this, firstly, the present disclosure adds a feature refinement model to the encoder-decoder structure to better extract the shape, texture and spatial relationship of the three-dimensional object. At the same time, the reconstruction quality and detail restoration ability are improved by introducing the attention mechanism in the feature refinement model. Then, by introducing the threshold adjustment model, the three-dimensional reconstruction can be selectively performed by controlling the threshold during reconstruction. In this way, the model accuracy of the three-dimensional model obtained by modeling is greatly improved.

[0056] Step 105: for each model element description information in the model element description information set, perform the following processing steps: Step 1051 : Determine, based on the element type and element feature vector included in the model element description information, whether there is a model element matching the model element description information in the pre-built model element library.

[0057] In some embodiments, the execution subject may determine whether there is a model element matching the model element description information in a pre-built model element library according to the element type and element feature vector included in the model element description information. The model element library may be a database storing pre-built and updated model elements. The model element may be a three-dimensional model for an electric power device. In practice, the execution subject may determine whether there is a model element matching the model element description information in a pre-built model element library according to the element type and element feature vector included in the model element description information by means of a database query.

[0058] Optionally, the model elements in the model element library correspond to hash identifiers, which are 256-bit hash strings. Specifically, the hash identifiers can be obtained by concatenating the element type and the element feature vector of the model element and performing hash processing.

[0059] In some optional implementations of some embodiments, determining whether there is a model element matching the model element description information in a pre-built model element library according to the element type and the element feature vector included in the model element description information may include the following steps: In the first step, the element types included in the above model element description information are one-hot encoded to generate encoded element types.

[0060] In practice, since the number of element types is fixed, the length of the vector of element types after one-hot encoding is fixed.

[0061] The second step is to concatenate the encoded element type with the element feature vector included in the model element description information to generate a concatenated vector.

[0062] The third step is to perform hashing on the concatenated vector to generate a hashed vector.

[0063] The above hashed vector is a 256-bit hash string.

[0064] In the fourth step, the hashed vector is matched with the hash identifier corresponding to the model element in the model element library to determine whether there is a model element matching the model element description information in the model element library.

[0065] Specifically, the execution subject may determine whether there are model elements with corresponding hash identifiers identical to the hashed vectors in the model element library one by one by traversing, so as to determine whether there are model elements matching the model element description information in the model element library.

[0066] Step 1052: In response to existence, determine the model element matching the model element description information as a candidate model element.

[0067] In some embodiments, in response to existence, the execution entity determines the model element matching the model element description information as a candidate model element.

[0068] Step 106: Update the model elements of the initial three-dimensional model of the power distribution room according to the obtained candidate model element set to generate an updated three-dimensional model of the power distribution room.

[0069] In some embodiments, the execution entity updates the model elements of the initial three-dimensional model of the power distribution room according to the obtained candidate model element set to generate an updated three-dimensional model of the power distribution room.

[0070] In some optional implementations of some embodiments, updating the model elements of the initial three-dimensional model of the power distribution room according to the obtained candidate model element set to generate an updated three-dimensional model of the power distribution room may include the following steps: For each candidate model element in the candidate model element set, the model element in the initial three-dimensional model of the power distribution room corresponding to the candidate model element is replaced by the candidate model element.

[0071] Optionally, the above method further includes: The first step is to associate the real-time operating parameters of the distribution room equipment in the above-mentioned distribution room to be three-dimensionally modeled with the above-mentioned updated distribution room three-dimensional model.

[0072] In practice, in response to the successful modeling of the updated three-dimensional model of the distribution room, the above-mentioned execution entity can monitor the real-time operating parameters of the distribution room equipment by automatic point tracking, and synchronize the real-time operating parameters with the updated three-dimensional model of the distribution room in real time to achieve parameter association.

[0073] In the second step, in response to the successful parameter association, the three-dimensional model of the distribution room after the update is used to display the equipment operation status of the distribution room equipment in the distribution room to be three-dimensionally modeled in real time.

[0074] The above-mentioned various embodiments of the present disclosure have the following beneficial effects: through the three-dimensional modeling method applied to the distribution room of some embodiments of the present disclosure, the modeling cycle is shortened and the consumption of computing resources is reduced. Specifically, the reason for the long modeling cycle is that the point cloud modeling method has a large amount of data processing. Based on this, the three-dimensional modeling method applied to the distribution room of some embodiments of the present disclosure, first, obtain a target image set, wherein the above-mentioned target image set is a pre-collected wide-angle image of the distribution room to be three-dimensionally modeled. Compared with the point cloud modeling method, the image-based three-dimensional modeling method has the advantage of convenient image acquisition. Secondly, according to the above-mentioned target image set, a set of images with improved image quality is generated, wherein the image with improved image quality is an image after local image quality improvement through at least one target image. By improving the image quality, the model accuracy of the subsequently generated three-dimensional model is guaranteed. Then, each of the images with improved image quality in the above-mentioned image quality improvement set is image stitching to generate a stitched image. Further, according to the above-mentioned spliced ​​image and the pre-trained initial three-dimensional model generation model, an initial distribution room three-dimensional model and model description information are generated, wherein the above-mentioned model description information includes: a model element description information set, the model element description information includes: an element type, an element feature vector and an element position information, and the element position information represents the position of the model element corresponding to the model element description information in the initial distribution room three-dimensional model. In this way, the image is combined to generate an initial distribution room three-dimensional model for the distribution room to be three-dimensionally modeled. In addition, for each model element description information in the above-mentioned model element description information set, the following processing steps are performed: the first step is to determine whether there is a model element matching the above-mentioned model element description information in the pre-built model element library according to the element type and element feature vector included in the above-mentioned model element description information. The second step is to determine the model element matching the above-mentioned model element description information as a candidate model element in response to the existence. Finally, according to the obtained candidate model element set, the model element of the above-mentioned initial distribution room three-dimensional model is updated to generate an updated distribution room three-dimensional model. By matching the model element replacement method, the model accuracy of the updated distribution room three-dimensional model is further improved. This method only requires images to generate a three-dimensional model. Compared with the point cloud modeling method, it shortens the modeling cycle and reduces computing resource consumption.

[0075] Further references Figure 2 As an implementation of the methods shown in the above figures, the present disclosure provides some embodiments of a three-dimensional modeling device for a power distribution room. These device embodiments are similar to Figure 1 Corresponding to the method embodiments shown, the three-dimensional modeling device applied to the power distribution room can be specifically applied to various electronic devices.

[0076] like Figure 2 As shown, in some embodiments, a three-dimensional modeling device 200 applied to a power distribution room includes: an acquisition unit 201, a first generation unit 202, an image stitching unit 203, a second generation unit 204, an execution unit 205, and a model element updating unit 206. The acquisition unit 201 is configured to acquire a target image set, wherein the target image set is a pre-collected wide-angle image of the power distribution room to be three-dimensionally modeled; the first generation unit 202 is configured to generate an improved image set according to the target image set, wherein the improved image is an image obtained by performing local image quality enhancement on at least one target image; the image stitching unit 203 is configured to stitch each improved image in the improved image set to generate a stitched image; the second generation unit 204 is configured to generate a model according to the stitched image and the pre-trained initial three-dimensional model, and generate an initial power distribution room three-dimensional model and model description information, wherein the model description information includes: a model element description information set, ... The information includes: element type, element feature vector and element position information, the element position information represents the position of the model element corresponding to the model element description information in the initial three-dimensional model of the distribution room; the execution unit 205 is configured to perform the following processing steps for each model element description information in the above-mentioned model element description information set: according to the element type and element feature vector included in the above-mentioned model element description information, determine whether there is a model element matching the above-mentioned model element description information in the pre-built model element library; in response to the existence, determine the model element matching the above-mentioned model element description information as a candidate model element; the model element updating unit 206 is configured to update the model elements of the above-mentioned initial three-dimensional model of the distribution room according to the obtained candidate model element set to generate an updated three-dimensional model of the distribution room.

[0077] It can be understood that the units described in the three-dimensional modeling device 200 for a power distribution room are similar to those described in the reference Figure 1 Therefore, the operations, features and beneficial effects described above for the method are also applicable to the three-dimensional modeling device 200 applied to the power distribution room and the units contained therein, and will not be repeated here.

[0078] Reference below Figure 3, which shows a structural schematic diagram of an electronic device (eg, a computing device) 300 suitable for implementing some embodiments of the present disclosure. Figure 3 The electronic device shown is only an example and should not bring any limitation to the functions and scope of use of the embodiments of the present disclosure.

[0079] like Figure 3 As shown, the electronic device 300 may include a processing device (e.g., a central processing unit, a graphics processing unit, etc.) 301, which can perform various appropriate actions and processes according to a program stored in a read-only memory 302 or a program loaded from a storage device 308 into a random access memory 303. Various programs and data required for the operation of the electronic device 300 are also stored in the random access memory 303. The processing device 301, the read-only memory 302, and the random access memory 303 are connected to each other via a bus 304. An input / output interface 305 is also connected to the bus 304.

[0080] Typically, the following devices may be connected to the I / O interface 305: an input device 306 including, for example, a touch screen, a touch pad, a keyboard, a mouse, a camera, a microphone, an accelerometer, a gyroscope, etc.; an output device 307 including, for example, a liquid crystal display (LCD), a speaker, a vibrator, etc.; a storage device 308 including, for example, a magnetic tape, a hard disk, etc.; and a communication device 309. The communication device 309 may allow the electronic device 300 to communicate with other devices wirelessly or by wire to exchange data. Figure 3 The electronic device 300 is shown with various devices, but it should be understood that it is not required to implement or possess all the devices shown. More or fewer devices may be implemented or possessed instead. Figure 3 Each block shown in the figure may represent one device, or may represent multiple devices as required.

[0081] In particular, according to some embodiments of the present disclosure, the process described above with reference to the flowchart can be implemented as a computer software program. For example, some embodiments of the present disclosure include a computer program product, which includes a computer program carried on a computer-readable medium, and the computer program contains program code for executing the method shown in the flowchart. In some such embodiments, the computer program can be downloaded and installed from the network through the communication device 309, or installed from the storage device 308, or installed from the read-only memory 302. When the computer program is executed by the processing device 301, the above-mentioned functions defined in the method of some embodiments of the present disclosure are executed.

[0082] It should be noted that the computer-readable medium recorded in some embodiments of the present disclosure may be a computer-readable signal medium or a computer-readable storage medium or any combination of the above two. The computer-readable storage medium may be, for example, but not limited to, an electrical, magnetic, optical, electromagnetic, infrared, or semiconductor system, device or device, or any combination of the above. More specific examples of computer-readable storage media may include, but are not limited to: an electrical connection with one or more wires, a portable computer disk, a hard disk, a random access memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or flash memory), an optical fiber, a portable compact disk read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination of the above. In some embodiments of the present disclosure, a computer-readable storage medium may be any tangible medium containing or storing a program, which may be used by or in combination with an instruction execution system, device or device. In some embodiments of the present disclosure, a computer-readable signal medium may include a data signal propagated in a baseband or as part of a carrier wave, which carries a computer-readable program code. Such propagated data signals may take a variety of forms, including but not limited to electromagnetic signals, optical signals, or any suitable combination of the above. Computer readable signal media may also be any computer readable medium other than computer readable storage media, which may send, propagate or transmit a program for use by or in conjunction with an instruction execution system, apparatus or device. The program code contained on the computer readable medium may be transmitted using any appropriate medium, including but not limited to: wires, optical cables, RF (radio frequency), etc., or any suitable combination of the above.

[0083] In some embodiments, the client and the server may communicate using any currently known or future developed network protocol such as HTTP (Hyper Text Transfer Protocol), and may be interconnected with any form or medium of digital data communication (e.g., a communication network). Examples of communication networks include a local area network ("LAN"), a wide area network ("WAN"), an internet (e.g., the Internet), and a peer-to-peer network (e.g., an ad hoc peer-to-peer network), as well as any currently known or future developed network.

[0084] The above-mentioned computer-readable medium may be included in the above-mentioned electronic device; or it may exist independently without being assembled into the electronic device. The above-mentioned computer-readable medium carries one or more programs. When the above-mentioned one or more programs are executed by the electronic device, the electronic device: obtains a target image set, wherein the above-mentioned target image set is a pre-collected wide-angle image of the distribution room to be three-dimensionally modeled; generates a set of images with improved image quality based on the above-mentioned target image set, wherein the images with improved image quality are images obtained by performing local image quality improvement on at least one target image; stitches the images with improved image quality in the above-mentioned set of images with improved image quality to generate a stitched image; generates a model based on the above-mentioned stitched images and the pre-trained initial three-dimensional model, and generates an initial three-dimensional model of the distribution room and model description information, wherein the above-mentioned model description information includes: model element description information A set of model element description information, including: element type, element feature vector and element position information, wherein the element position information represents the position of the model element corresponding to the model element description information in the initial three-dimensional model of the distribution room; for each model element description information in the above-mentioned model element description information set, the following processing steps are performed: according to the element type and element feature vector included in the above-mentioned model element description information, it is determined whether there is a model element matching the above-mentioned model element description information in the pre-built model element library; in response to the existence, the model element matching the above-mentioned model element description information is determined as a candidate model element; according to the obtained candidate model element set, the model elements of the above-mentioned initial three-dimensional model of the distribution room are updated to generate an updated three-dimensional model of the distribution room.

[0085] Computer program code for performing the operations of some embodiments of the present disclosure may be written in one or more programming languages ​​or a combination thereof, including object-oriented programming languages ​​such as Java, Smalltalk, C++, and conventional procedural programming languages ​​such as "C" or similar programming languages. The program code may be executed entirely on the user's computer, partially on the user's computer, as a separate software package, partially on the user's computer and partially on a remote computer, or entirely on a remote computer or server. In the case of a remote computer, the remote computer may be connected to the user's computer through any type of network, including a local area network (LAN) or a wide area network (WAN), or may be connected to an external computer (e.g., via the Internet using an Internet service provider).

[0086] The flow chart and block diagram in the accompanying drawings illustrate the possible architecture, function and operation of the system, method and computer program product according to various embodiments of the present disclosure. In this regard, each square box in the flow chart or block diagram can represent a module, a program segment or a part of a code, and the module, the program segment or a part of the code contains one or more executable instructions for realizing the specified logical function. It should also be noted that in some implementations as replacements, the functions marked in the square box can also occur in a sequence different from that marked in the accompanying drawings. For example, two square boxes represented in succession can actually be executed substantially in parallel, and they can sometimes be executed in the opposite order, depending on the functions involved. It should also be noted that each square box in the block diagram and / or flow chart, and the combination of the square boxes in the block diagram and / or flow chart can be implemented with a dedicated hardware-based system that performs a specified function or operation, or can be implemented with a combination of dedicated hardware and computer instructions.

[0087] The units described in some embodiments of the present disclosure may be implemented by software or hardware. The units described may also be set in a processor, for example, may be described as: a processor includes an acquisition unit, a first generation unit, an image stitching unit, a second generation unit, an execution unit and a model element update unit. Among them, the names of these units do not constitute a limitation on the unit itself under certain circumstances. For example, the execution unit may also be described as "for each model element description information in the above-mentioned model element description information set, perform the following processing steps: according to the element type and element feature vector included in the above-mentioned model element description information, determine whether there is a model element matching the above-mentioned model element description information in the pre-built model element library; in response to the existence, determine the model element matching the above-mentioned model element description information as a candidate model element unit".

[0088] The functions described above herein may be performed at least in part by one or more hardware logic components. For example, without limitation, exemplary types of hardware logic components that may be used include: field programmable gate arrays (FPGAs), application specific integrated circuits (ASICs), application specific standard products (ASSPs), systems on chips (SOCs), complex programmable logic devices (CPLDs), and the like.

[0089] The above descriptions are only some preferred embodiments of the present disclosure and an explanation of the technical principles used. Those skilled in the art should understand that the scope of the invention involved in the embodiments of the present disclosure is not limited to the technical solutions formed by a specific combination of the above technical features, but should also cover other technical solutions formed by any combination of the above technical features or their equivalent features without departing from the above inventive concept. For example, the above features are replaced with (but not limited to) technical features with similar functions disclosed in the embodiments of the present disclosure.

Claims

1. A three-dimensional modeling method applied to a power distribution room, comprising: Acquire a target image set, wherein the target image set is a pre-collected wide-angle image of the distribution room to be three-dimensionally modeled; Generating a set of images with improved image quality according to the target image set, wherein the images with improved image quality are images obtained by partially improving the image quality of at least one target image; Performing image stitching on each of the enhanced images in the enhanced image set to generate a stitched image; Generate a model based on the spliced ​​image and the pre-trained initial three-dimensional model, generate an initial three-dimensional model of the power distribution room and model description information, wherein the model description information includes: a set of model element description information, the model element description information includes: element type, element feature vector and element position information, and the element position information represents the position of the model element corresponding to the model element description information in the initial three-dimensional model of the power distribution room; For each model element description information in the model element description information set, the following processing steps are performed: Determining, according to the element type and the element feature vector included in the model element description information, whether there is a model element matching the model element description information in a pre-built model element library; In response to existence, determining a model element matching the model element description information as a candidate model element; According to the obtained candidate model element set, the model elements of the initial power distribution room three-dimensional model are updated to generate an updated power distribution room three-dimensional model.

2. The method according to claim 1, wherein: The method further comprises: Associating the real-time operating parameters of the power distribution room equipment in the power distribution room to be three-dimensionally modeled with the updated three-dimensional model of the power distribution room; In response to the successful parameter association, the updated three-dimensional model of the power distribution room is used to display in real time the equipment operating status of the power distribution room equipment in the power distribution room to be three-dimensionally modeled.

3. The method according to claim 2, wherein: Generating a set of images with improved image quality according to the target image set includes: For each target image in the target image set, the following image preprocessing steps are performed: Performing distortion calibration on the target image to generate a distortion-corrected image; Performing target detection on the distortion-corrected image to generate a target object description information set, wherein the target object description information in the target object description information set includes: an object feature point set; According to the target object description information set corresponding to the target image, performing image similarity matching on the target images in the target image set to generate a target image group set; For each target image group in the target image group set, the following image quality improvement steps are performed: Randomly select a target image from the target image group as a base image; According to the target images in the target image group other than the base image, the base image is locally enhanced to generate an enhanced image in the enhanced image set.

4. The method according to claim 3, wherein: The step of stitching the images in the set of images with improved image quality to generate a stitched image includes: For each improved image in the improved image set, extracting feature points from a horizontal edge region in the improved image to generate edge region features; According to edge region features corresponding to the enhanced images, image matching is performed on the enhanced images in the enhanced image set to generate a splicing order index array, wherein the splicing order index array represents an image splicing order of each enhanced image in the enhanced image set; According to the stitching order index array, image stitching is performed on each of the enhanced images in the enhanced image set to generate the stitched image.

5. The method according to claim 4, wherein: The model elements in the model element library correspond to hash identifiers, where the hash identifiers are 256-bit hash strings; and The determining, according to the element type and the element feature vector included in the model element description information, whether there is a model element matching the model element description information in a pre-built model element library includes: One-hot encoding the element type included in the model element description information to generate an encoded element type; splicing the encoded element type with the element feature vector included in the model element description information to generate a spliced ​​vector; Performing hash processing on the concatenated vector to generate a hashed vector, wherein the hashed vector is a 256-bit hash string; The hashed vector is matched with a hash identifier corresponding to a model element in the model element library to determine whether there is a model element in the model element library that matches the model element description information.

6. The method according to claim 5, wherein: The updating of the model elements of the initial three-dimensional model of the power distribution room according to the obtained candidate model element set to generate an updated three-dimensional model of the power distribution room includes: For each candidate model element in the candidate model element set, the model element in the initial three-dimensional model of the power distribution room corresponding to the candidate model element is replaced with the candidate model element.

7. The method according to claim 6, wherein: The initial three-dimensional model generation model includes: an image encoder, an image decoder, a feature refinement model and a threshold adjustment model; and The generating a model according to the spliced ​​image and the pre-trained initial three-dimensional model to generate an initial distribution room three-dimensional model and model description information includes: Generate image encoding features according to the image encoder and the spliced ​​image; Generate a decoded image feature according to the image decoder and the encoded image feature; Generate refined image features according to the feature refinement model and the decoded image features; Generate a threshold adjustment parameter according to the threshold adjustment model and the spliced ​​image; The initial power distribution room three-dimensional model and the model description information are generated according to the threshold adjustment parameters and the refined image features.

8. A three-dimensional modeling device applied to a power distribution room, comprising: An acquisition unit is configured to acquire a target image set, wherein the target image set is a pre-collected wide-angle image of the distribution room to be three-dimensionally modeled; A first generating unit is configured to generate a set of images with improved image quality according to the target image set, wherein the images with improved image quality are images obtained by partially improving the image quality of at least one target image; An image stitching unit is configured to stitch each of the enhanced images in the enhanced image set to generate a stitched image; A second generating unit is configured to generate a model according to the stitched image and the pre-trained initial three-dimensional model, and generate an initial three-dimensional model of the power distribution room and model description information, wherein the model description information includes: a set of model element description information, the model element description information includes: an element type, an element feature vector and an element position information, and the element position information represents a position of a model element corresponding to the model element description information in the initial three-dimensional model of the power distribution room; The execution unit is configured to perform the following processing steps for each model element description information in the model element description information set: determine whether there is a model element matching the model element description information in a pre-built model element library according to the element type and element feature vector included in the model element description information; in response to the existence, determine the model element matching the model element description information as a candidate model element; The model element updating unit is configured to update the model elements of the initial three-dimensional model of the power distribution room according to the obtained candidate model element set, so as to generate an updated three-dimensional model of the power distribution room.

9. An electronic device, comprising: one or more processors; a storage device having one or more programs stored thereon; When the one or more programs are executed by the one or more processors, the one or more processors implement the method according to any one of claims 1 to 7.

10. A computer readable medium having a computer program stored thereon, wherein: When the computer program is executed by a processor, the method according to any one of claims 1 to 7 is implemented.

Images