CN109214457B - Power line classification method and device - Google Patents
Power line classification method and device Download PDFInfo
- Publication number
- CN109214457B CN109214457B CN201811043754.XA CN201811043754A CN109214457B CN 109214457 B CN109214457 B CN 109214457B CN 201811043754 A CN201811043754 A CN 201811043754A CN 109214457 B CN109214457 B CN 109214457B
- Authority
- CN
- China
- Prior art keywords
- power line
- data
- dimensional
- sub
- image
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Active
Links
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/24—Classification techniques
- G06F18/241—Classification techniques relating to the classification model, e.g. parametric or non-parametric approaches
- G06F18/2413—Classification techniques relating to the classification model, e.g. parametric or non-parametric approaches based on distances to training or reference patterns
Abstract
The invention provides a method and a device for classifying power lines, wherein the method for classifying the power lines comprises the following steps: acquiring power line data comprising power line data and tower data; processing the electric power line data to obtain an electric power line diagram, and generating a three-dimensional grid image which corresponds to the electric power line data and comprises a plurality of sub-grid images according to the electric power line diagram; acquiring a category attribute comparison table comprising category attribute labels corresponding to the sub-grid images; analyzing the three-dimensional raster image by taking a preset three-dimensional convolution neural network and a category attribute comparison table as a basis to obtain a category attribute data set corresponding to the three-dimensional raster image; and combining the power line data and the category attribute data set to obtain category data corresponding to the power line data. The method and the device for classifying the power lines can improve the classification precision of the power lines, improve the classification efficiency of the power lines and realize mass data processing.
Description
Technical Field
The invention relates to the field of power inspection, in particular to a method and a device for classifying power lines.
Background
In the process of power inspection, detection of dangerous points and simulation analysis of various working conditions are usually performed on the basis of power lines and towers included in a power line, so that acquisition and classification of information related to the power lines and the towers are particularly important. In practice, the existing power line and tower classification method generally adopts an artificial classification method, however, although the precision of the artificial classification method is high, the efficiency of the method is low, and mass data processing cannot be realized.
Disclosure of Invention
In view of the above problems, the present invention provides a method and an apparatus for classifying power lines, which can improve the classification accuracy of power lines, improve the classification efficiency of power lines, and implement massive data processing.
In order to achieve the purpose, the invention adopts the following technical scheme:
in a first aspect, the present invention provides a method for classifying power lines, including:
acquiring power line data comprising power line data and tower data;
processing the electric power line data to obtain an electric power line diagram, and generating a three-dimensional grid image which corresponds to the electric power line data and comprises a plurality of sub-grid images according to the electric power line diagram;
acquiring a category attribute comparison table comprising category attribute labels corresponding to the sub-grid images;
analyzing the three-dimensional raster image by taking a preset three-dimensional convolution neural network and the category attribute comparison table as a basis to obtain a category attribute data set corresponding to the three-dimensional raster image;
and combining the power line data and the category attribute data set to obtain category data corresponding to the power line data.
As an optional implementation, after the step of combining the power line data and the category attribute data set to obtain the classification data corresponding to the power line data, the method further comprises:
and optimizing the classified data by a preset search algorithm to obtain the classified optimized data.
As an optional implementation, the step of acquiring power line data including power line data and tower data includes:
controlling a laser radar to transmit a detection signal to a power line comprising a power line and a tower;
receiving echo signals reflected by the power line;
performing signal processing on the detection signal and the echo signal to obtain laser radar point cloud data comprising power line data and tower data;
and determining the laser radar point cloud data as power line data.
As an optional implementation, the step of processing the power line data to obtain a three-dimensional grid image including a plurality of sub-grid images includes:
processing the power line data to obtain a power line diagram;
the power circuit diagram is sliced according to a preset reference surface to obtain a sliced image;
dividing the slice image according to a preset dividing mode to obtain a plurality of sub-grid images, and acquiring a plurality of gray values which are in one-to-one correspondence with the plurality of sub-grid images;
and combining the slice image and the plurality of gray values to obtain a three-dimensional grid image.
As an optional implementation manner, the step of obtaining a category attribute comparison table including a category attribute tag corresponding to each sub-grid image includes:
sampling the plurality of sub-raster images included in the three-dimensional raster image to obtain sample data;
embedding the class attribute labels into the sample data according to a preset label embedding standard to obtain a class attribute comparison table comprising the class attribute labels corresponding to the sub-grid images.
In a second aspect, the present invention provides a power line classification device, including an acquisition module, a processing module, an analysis module, and a combination module, wherein,
the acquisition module is used for acquiring power line data comprising power line data and tower data;
the processing module is used for processing the electric power line data to obtain an electric power line diagram and generating a three-dimensional grid image which corresponds to the electric power line data and comprises a plurality of sub-grid images according to the electric power line diagram;
the acquisition module is further used for acquiring a category attribute comparison table comprising category attribute labels corresponding to the sub-grid images;
the analysis module is used for analyzing the three-dimensional raster image according to a preset three-dimensional convolution neural network and the category attribute comparison table to obtain a category attribute data set corresponding to the three-dimensional raster image;
the combination module is used for combining the electric power line data and the category attribute data set to obtain category data corresponding to the electric power line data.
As an optional implementation manner, the processing module is further configured to perform optimization processing on the classified data by using a preset search algorithm to obtain the classified optimized data.
As an optional implementation manner, the obtaining module includes a sampling unit and an embedding unit, wherein,
the sampling unit is used for sampling the plurality of sub-grid images included in the three-dimensional grid image to obtain sample data;
and the embedding unit is used for embedding the class attribute label into the sample data according to a preset label embedding standard to obtain a class attribute comparison table comprising the class attribute label corresponding to the sub-grid image.
In a third aspect, the present invention provides a computer device comprising a memory for storing a computer program and a processor for executing the computer program to cause the computer device to perform a method of classifying a power line according to the first aspect of the present invention.
In a fourth aspect, the invention provides a computer-readable storage medium storing a computer program for use in the computer apparatus of the third aspect of the invention.
According to the method and the device for classifying the power lines, provided by the invention, the power line data comprising the power line data and the tower data can be preferentially obtained and processed to obtain the three-dimensional raster image; meanwhile, a category attribute comparison table is obtained, so that the classification device can analyze the three-dimensional raster image according to the category attribute comparison table and the artificial intelligent neural network to obtain a corresponding category attribute data set; and finally, combining the power line data and the category attribute data set to obtain total category data corresponding to the power line data. Therefore, by implementing the embodiment, the power line data can be processed to obtain the corresponding three-dimensional raster image and the category attribute comparison table is obtained, so that the method can analyze and classify the three-dimensional raster image through the artificial intelligent neural network, and the classified data of the power line data can be obtained. Therefore, the method can improve the classification precision and the classification efficiency of the power line by analyzing through the artificial intelligence neural network, and realize massive data processing through automatic acquisition and processing of data.
In order to make the aforementioned and other objects, features and advantages of the present invention comprehensible, preferred embodiments accompanied with figures are described in detail below.
Drawings
To more clearly illustrate the technical solutions of the embodiments of the present invention, the drawings that are required to be used in the embodiments will be briefly described below, and it should be understood that the following drawings only illustrate some embodiments of the present invention, and therefore should not be considered as limiting the scope of the present invention.
Fig. 1 is a schematic flow chart of a method for classifying power lines according to a first embodiment of the present invention;
fig. 2 is a schematic flow chart of a method for classifying power lines according to a second embodiment of the present invention;
fig. 3 is a schematic structural diagram of a sorting apparatus for power lines according to a third embodiment of the present invention.
Detailed Description
The technical solutions in the embodiments of the present invention will be clearly and completely described below with reference to the drawings in the embodiments of the present invention, and it is obvious that the described embodiments are only a part of the embodiments of the present invention, and not all of the embodiments. The components of embodiments of the present invention generally described and illustrated in the figures herein may be arranged and designed in a wide variety of different configurations. Thus, the following detailed description of the embodiments of the present invention, presented in the figures, is not intended to limit the scope of the invention, as claimed, but is merely representative of selected embodiments of the invention. All other embodiments, which can be derived by a person skilled in the art from the embodiments of the present invention without making any creative effort, shall fall within the protection scope of the present invention.
Aiming at the problems in the prior art, the invention provides a power line classification method which can preferentially acquire power line data comprising power line data and tower data and process the power line data to obtain a three-dimensional grid image; meanwhile, a category attribute comparison table is obtained, so that the classification device can analyze the three-dimensional raster image according to the category attribute comparison table and the artificial intelligent neural network to obtain a corresponding category attribute data set; and finally, combining the power line data and the category attribute data set to obtain total category data corresponding to the power line data. Therefore, by implementing the embodiment, the power line data can be processed to obtain the corresponding three-dimensional raster image and the category attribute comparison table is obtained, so that the method can analyze and classify the three-dimensional raster image through the artificial intelligent neural network, and the classified data of the power line data can be obtained. Therefore, the method can improve the classification precision and the classification efficiency of the power line by analyzing through the artificial intelligence neural network, and realize massive data processing through automatic acquisition and processing of data. The following is described by way of example.
The above technical method can also be implemented by using related software or hardware, and further description is not repeated in this embodiment. The following describes a method and an apparatus for classifying the power lines by way of example.
Example 1
Please refer to fig. 1, which is a schematic flow chart illustrating a method for classifying power lines according to an embodiment of the present invention, the method for classifying power lines includes the following steps:
s101, obtaining power line data including power line data and tower data.
In this embodiment, the power line data may include all data information related to power transmission, such as distribution data and specification data of power transmission lines in the power line. Here, the power transmission line refers to a line for transmitting electric energy among a power plant, a substation, and a power consumer, and is an important component of a power supply system, which is responsible for the tasks of transmitting and distributing electric energy.
In this embodiment, the power transmission line is a conductor loop that connects the substation and the electric energy users or electric equipment, and transmits and distributes the electric energy from the power source end (substation and distribution substation) to the load end (electric energy users or electric equipment). The power transmission line can be divided into a high voltage line and a low voltage line according to the voltage, wherein the high voltage line refers to a power transmission line with a voltage of 1kV or more, and the low voltage line refers to a power transmission line with a voltage of 1kV or less. Meanwhile, some power transmission lines of 1kV to 10kV (or 35kV) are called medium-voltage lines, power transmission lines of 35kV or more to 110kV (or 220kV) are called high-voltage lines, and power transmission lines of 220kV or more (or 330kV) are called extra-high-voltage lines.
In this embodiment, the power transmission line should have the basic effects of safe and reliable power supply, convenient operation, flexible operation and the like.
In this embodiment, the power transmission line may be divided into an overhead line, a cable line, an indoor line, and the like according to the structural form, and the structural form of the power transmission line is not limited in this embodiment.
In this embodiment, the tower is a support for supporting the power transmission line in the overhead power transmission line, wherein the tower is mostly made of steel or reinforced concrete and is a main support structure of the overhead power transmission line.
In this embodiment, the tower data includes all data information related to the tower, such as the structure of the tower, the category of the tower, and the purpose of the tower.
As an alternative embodiment, the power line data may also include data about other structures or components of the power transmission, including power line data and tower data.
By implementing the implementation mode, the data of the power line can be further improved, so that the method can obtain more data (or characteristics), and further the classification precision of the power line is improved.
And S102, processing the power line data to obtain a power line diagram, and generating a three-dimensional grid image which corresponds to the power line data and comprises a plurality of sub-grid images according to the power line diagram.
In this embodiment, the power line data may be point cloud data acquired by a laser radar technology.
In this embodiment, the power line data may be bitmap data having a plurality of pixels, and each pixel has a unique gray value, where the bitmap may be considered as a raster image, and only the raster image is two-dimensional, and the gray value exists as a three-dimensional supplement.
By implementing the implementation mode, the acquired data can be converted into the corresponding image, and the subsequent processing can be continued on the image, so that the data display is more visual, and the subsequent processing is facilitated.
As an optional implementation, the step of processing the power line data to obtain a power line map, and generating a three-dimensional grid image including a plurality of sub-grid images corresponding to the power line data according to the power line map may include:
processing the power line data to obtain a power line diagram, obtaining pixel gray values in the power line data, uniformly dividing the power line diagram, and combining the divided power line diagram and the pixel gray values to obtain a three-dimensional grid image comprising a plurality of sub-grid images; the sub-grid images are divided by the step of uniformly dividing the power circuit diagram, and the division is not to cut the power circuit diagram but only to divide the area of the power circuit diagram.
By implementing such an embodiment, the three-dimensional raster image acquisition mode may be embodied such that the three-dimensional raster image is obtained by implementing the above steps in addition to being directly generated by a machine.
In this embodiment, the plurality of sub-raster images are divided from the three-dimensional raster image, and it can be understood that the plurality of sub-raster images are a part of the three-dimensional raster image.
In this embodiment, the three-dimensional raster image is a three-dimensional raster image having two planar dimensions and a third grayscale value, and during data processing, the three-dimensional raster image may be correspondingly processed by a third-order matrix.
S103, obtaining a category attribute comparison table comprising category attribute labels corresponding to the sub-grid images.
In this embodiment, the category attribute comparison table includes a plurality of sub-raster images and category attribute tags corresponding to the plurality of sub-raster images one to one. The category attribute tag may be manually labeled or stored by a machine, which is not limited in this embodiment.
In this embodiment, the category attribute comparison table is used for obtaining the category attribute corresponding to the sub-grid image through matching.
In this embodiment, the category attribute comparison table has the advantages of a large number of features (labels), detailed contents of the features (labels), and the like because the category attribute comparison table is processed independently (manually labeled or machine-independently labeled), and thus the classification accuracy of subsequent steps is improved.
For example, the sub-grid image is a tower, and the category attribute of the sub-grid image is to describe what tower the sub-grid image is, what role it has, and the like.
And S104, analyzing the three-dimensional raster image by taking a preset three-dimensional convolution neural network and the category attribute comparison table as a basis to obtain a category attribute data set corresponding to the three-dimensional raster image.
In this embodiment, the three-dimensional convolutional neural network may include an input layer, a hard-line layer, a first convolutional layer, a down-sampling layer, a second convolutional layer, a down-sampling layer, and a third convolutional layer.
In this embodiment, the classification device of the power line acquires all the features (such as categories, attributes, and the like) in the category attribute comparison table, and inputs all the features into the input layer of the three-dimensional convolutional neural network, so that the three-dimensional convolutional neural network performs black box processing on all the features, thereby obtaining a large amount of data sets for comparing what features a sub-raster image in the three-dimensional raster image has.
In this embodiment, analyzing the three-dimensional raster image refers to analyzing the three-dimensional raster image according to a result obtained by artificial intelligence (three-dimensional convolutional neural network). The result obtained by artificial intelligence (three-dimensional convolutional neural network) is a comparison table of a large number of sub-grid images and the category attributes.
And S105, combining the power line data and the category attribute data set to obtain category data corresponding to the power line data.
In this embodiment, combining the power line data and the category attribute data set enables each part of the power line data to be superimposed with a corresponding category attribute, so that the power line data is classified, and corresponding classified data is obtained.
In the method for classifying power lines described in fig. 1, the method for classifying power lines may preferentially obtain power line data including power line data and tower data, and process the power line data to obtain a three-dimensional grid image; meanwhile, a category attribute comparison table is obtained, so that the classification device can analyze the three-dimensional raster image according to the category attribute comparison table and the artificial intelligent neural network to obtain a corresponding category attribute data set; and finally, combining the power line data and the category attribute data set to obtain total category data corresponding to the power line data. It can be seen that, by implementing the method for classifying power lines described in fig. 1, the power line data can be processed to obtain a corresponding three-dimensional raster image and obtain the category attribute comparison table, so that the method can analyze and classify the three-dimensional raster image through an artificial intelligence neural network, thereby obtaining classification data of the power line data. Therefore, the method can improve the classification precision and the classification efficiency of the power line by analyzing through the artificial intelligence neural network, and realize massive data processing through automatic acquisition and processing of data.
Example 2
Referring to fig. 2, fig. 2 is a schematic flow chart illustrating a method for classifying power lines according to the present embodiment. As shown in fig. 2, the method for classifying power lines includes the following steps:
s201, controlling the laser radar to transmit detection signals to the power line comprising the power line and the tower.
In this embodiment, the lidar is an active remote sensing device that uses a laser as a light emitting source and adopts a photoelectric detection technical means. In particular, the laser radar is an advanced detection mode combining a laser technology and a modern photoelectric detection technology, and the detection mode comprises a transmitting system, a receiving system, information processing and the like. Wherein, the transmitting system is composed of various lasers, such as a carbon dioxide laser, a neodymium-doped yttrium aluminum garnet laser, a semiconductor laser, a wavelength tunable solid laser, an optical beam expanding unit and the like; the receiving system adopts a telescope and various forms of photodetectors, such as photomultiplier tubes, semiconductor photodiodes, avalanche photodiodes, infrared and visible light multi-element detection devices, and the like. Meanwhile, the laser radar adopts two working modes of pulse or continuous wave, and the detection method can be divided into meter scattering, Rayleigh scattering, Raman scattering, Brillouin scattering, fluorescence and the like according to different detection principles.
S202, receiving an echo signal reflected by the power line.
In this embodiment, the echo signal may be obtained after the detection signal is changed, where the two signals are the same signal and are only changed by external interference.
And S203, performing signal processing on the detection signal and the echo signal to obtain laser radar point cloud data comprising power line data and tower data.
As an optional implementation, the signal processing of the probe signal and the echo signal may include:
and acquiring the difference characteristics between the detection signal and the echo signal, and matching the difference characteristics to obtain corresponding data so as to finish processing.
By implementing the embodiment, the processing mode can be embodied, and the uncertainty caused by the black box operation is avoided, so that the processing precision and the processing accuracy are improved.
And S204, determining the laser radar point cloud data as power line data.
And S205, processing the power line data to obtain a power line diagram.
And S206, slicing the power circuit diagram by taking the preset reference surface as a basis to obtain a slice image.
In this embodiment, based on the preset reference plane, slicing the power line data may be understood as slicing the sample data along a horizontal direction and a vertical direction, where the horizontal direction and the vertical direction are preset.
In this embodiment, the reference plane may be a horizontal plane.
In the present embodiment, the slice image may be a bitmap (pixel map).
S207, dividing the slice image according to a preset dividing mode to obtain a plurality of sub-grid images, and acquiring a plurality of gray values corresponding to the plurality of sub-grid images one by one.
In this embodiment, the gray value is a specific attribute of each pixel point in the sub-grid image.
And S208, combining the slice image and the plurality of gray values to obtain a three-dimensional grid image.
Implementing this embodiment, a third dimension may be superimposed in the two-dimensional image, resulting in three-dimensional data (a three-dimensional raster image).
S209, sampling a plurality of sub-grid images included in the three-dimensional grid image to obtain sample data.
S210, embedding the class attribute labels into the sample data according to a preset label embedding standard to obtain a class attribute comparison table comprising the class attribute labels corresponding to the sub-grid images.
As can be known from the implementation of steps S209 to S210, the category attribute comparison table is obtained through the sampling image of the three-dimensional raster image, and as a result, the category attribute table and the three-dimensional raster image are locally corresponding to each other, and both have identity, so that the data comparison and processing efficiency can be improved, and the classification accuracy can also be improved.
And S211, analyzing the three-dimensional raster image by taking a preset three-dimensional convolution neural network and a category attribute comparison table as a basis to obtain a category attribute data set corresponding to the three-dimensional raster image.
S212, combining the power line data and the category attribute data set to obtain category data corresponding to the power line data.
And S213, optimizing the classified data by using a preset search algorithm to obtain the classified optimized data.
In this embodiment, the preset search algorithm may be one or more of an enumeration algorithm, a depth-first search, a breadth-first search, an a-x algorithm, a backtracking algorithm, a monte carlo tree search, a hash function, a local search algorithm, a neighborhood search algorithm, a variable neighborhood search algorithm, and the like.
As an optional implementation, the preset search algorithm is a neighborhood search algorithm.
In the embodiment, the classified data is optimized by using the search algorithm, so that the search scale can be reduced, pruning can be performed according to the constraint conditions of the problems, and the advantages of intermediate solutions in the search process and repeated calculation can be avoided.
For example, the method can select a part of samples from laser radar point cloud data to be processed, and mark power lines and pole tower categories in the samples; slicing the sample data along the horizontal direction and the vertical direction respectively to generate a grid image, acquiring the gray value of each grid, and recording the category attribute of each grid; slicing the data to be processed along the horizontal and vertical directions to generate a grid image and acquire the gray value of a grid; analyzing data to be processed through a 3D-CNN algorithm, and endowing each grid with a category attribute; finding out a corresponding point cloud according to the horizontal vertical coordinate of the grid, and giving the category attribute corresponding to the grid to the corresponding point cloud; and performing neighborhood search on the point clouds classified into the power line and the tower category, and optimizing a classification result.
By implementing the implementation mode, the classification of the power line and the tower can be carried out through a deep learning algorithm, and along with the richness of samples, the classification precision is improved.
In the method for classifying power lines described in fig. 2, the method for classifying power lines may preferentially obtain power line data including power line data and tower data, and process the power line data to obtain a three-dimensional grid image; meanwhile, a category attribute comparison table is obtained, so that the classification device can analyze the three-dimensional raster image according to the category attribute comparison table and the artificial intelligent neural network to obtain a corresponding category attribute data set; and finally, combining the power line data and the category attribute data set to obtain total category data corresponding to the power line data. It can be seen that, by implementing the method for classifying power lines described in fig. 2, the power line data can be processed to obtain a corresponding three-dimensional raster image and obtain the category attribute comparison table, so that the method can analyze and classify the three-dimensional raster image through an artificial intelligence neural network, thereby obtaining classification data of the power line data. Therefore, the method can improve the classification precision and the classification efficiency of the power line by analyzing through the artificial intelligence neural network, and realize massive data processing through automatic acquisition and processing of data.
Example 3
Fig. 3 is a schematic structural diagram of a classification device for power lines according to this embodiment.
As shown in fig. 3, the classification apparatus for electric power lines includes an acquisition module 310, a processing module 320, an analysis module 330, and a combination module 340, wherein,
the obtaining module 310 is configured to obtain power line data including power line data and tower data;
the processing module 320 is configured to process the power line data to obtain a power line diagram, and generate a three-dimensional grid image including a plurality of sub-grid images corresponding to the power line data according to the power line diagram;
the obtaining module 310 is further configured to obtain a category attribute comparison table including a category attribute tag corresponding to the sub-grid image;
the analysis module 330 is configured to analyze the three-dimensional raster image based on a preset three-dimensional convolutional neural network and a category attribute comparison table to obtain a category attribute data set corresponding to the three-dimensional raster image;
the combining module 340 is configured to combine the power line data and the category attribute data set to obtain category data corresponding to the power line data.
As an optional implementation manner, the processing module 320 is further configured to perform optimization processing on the classified data by using a preset search algorithm to obtain the classified optimized data.
As an alternative implementation, the obtaining module 310 includes a sampling unit 311 and an embedding unit 312, wherein,
the sampling unit 311 is configured to sample a plurality of sub-grid images included in the three-dimensional grid image to obtain sample data;
the embedding unit 312 embeds the category attribute tag in the sample data according to a preset tag embedding standard to obtain a category attribute comparison table including the category attribute tag corresponding to the sub-grid image.
It can be seen that, by using the power line classification device described in fig. 3, the power line data can be processed to obtain the corresponding three-dimensional raster image and obtain the category attribute comparison table, so that the method can analyze and classify the three-dimensional raster image through the artificial intelligence neural network, thereby obtaining the classification data of the power line data. Therefore, the method can improve the classification precision and the classification efficiency of the power line by analyzing through the artificial intelligent neural network, and realize massive data processing through automatic acquisition and processing of data
In addition, the invention also provides another computer device which can comprise a smart phone, a tablet computer, a vehicle-mounted computer, an intelligent wearable device and the like. The computer device comprises a memory and a processor, wherein the memory can be used for storing a computer program, and the processor can be used for executing the computer program so as to enable the computer device to execute the method or the functions of each unit in the device.
The memory may include a storage program area and a storage data area, wherein the storage program area may store an operating system, an application program required for at least one function (such as a sound playing function, an image playing function, etc.), and the like; the storage data area may store data (such as audio data, a phonebook, etc.) created according to the use of the computer device, and the like. Further, the memory may include high speed random access memory, and may also include non-volatile memory, such as at least one magnetic disk storage device, flash memory device, or other volatile solid state storage device.
The embodiment also provides a computer storage medium for storing a computer program used in the computer device.
In the embodiments provided in the present application, it should be understood that the disclosed apparatus and method can be implemented in other ways. The apparatus embodiments described above are merely illustrative and, for example, the flowchart and block diagrams in the figures illustrate the architecture, functionality, and operation of possible implementations of apparatus, methods and computer program products according to various embodiments of the present invention. In this regard, each block in the flowchart or block diagrams may represent a module, segment, or portion of code, which comprises one or more executable instructions for implementing the specified logical function(s). It should also be noted that, in alternative implementations, the functions noted in the block may occur out of the order noted in the figures. For example, two blocks shown in succession may, in fact, be executed substantially concurrently, or the blocks may sometimes be executed in the reverse order, depending upon the functionality involved. It will also be noted that each block of the block diagrams and/or flowchart illustration, and combinations of blocks in the block diagrams and/or flowchart illustration, can be implemented by special purpose hardware-based systems which perform the specified functions or acts, or combinations of special purpose hardware and computer instructions.
In addition, each functional module or unit in each embodiment of the present invention may be integrated together to form an independent part, or each module may exist separately, or two or more modules may be integrated to form an independent part.
The described functions, if implemented in the form of software functional modules and sold or used as a stand-alone product, may be stored in a computer readable storage medium. Based on such understanding, the technical solution of the present invention or a part of the technical solution that contributes to the prior art in essence can be embodied in the form of a software product, which is stored in a storage medium and includes instructions for causing a computer device (which may be a smart phone, a personal computer, a server, or a network device, etc.) to execute all or part of the steps of the method described in the embodiments of the present invention. And the aforementioned storage medium includes: a U-disk, a removable hard disk, a Read-Only Memory (ROM), a Random Access Memory (RAM), a magnetic disk or an optical disk, and other various media capable of storing program codes.
The above description is only for the specific embodiment of the present invention, but the scope of the present invention is not limited thereto, and any person skilled in the art can easily conceive of the changes or substitutions within the technical scope of the present invention, and all the changes or substitutions should be covered within the scope of the present invention. Therefore, the protection scope of the present invention shall be subject to the protection scope of the claims.
Claims (8)
1. A method of classifying an electrical power line, comprising:
acquiring power line data comprising power line data and tower data; the power line data is bitmap data with a plurality of pixel points, and each pixel point has a unique gray value; wherein the bitmap data is a raster image, the raster image being two-dimensional, the grayscale values being for three-dimensional supplementation;
processing the electric power line data to obtain an electric power line diagram, and generating a three-dimensional grid image which corresponds to the electric power line data and comprises a plurality of sub-grid images according to the electric power line diagram;
acquiring a category attribute comparison table comprising category attribute labels corresponding to the sub-grid images;
analyzing the three-dimensional raster image by taking a preset three-dimensional convolution neural network and the category attribute comparison table as a basis to obtain a category attribute data set corresponding to the three-dimensional raster image;
combining the power line data and the category attribute data set to obtain category data corresponding to the power line data;
the step of processing the power line data to obtain a three-dimensional grid image including a plurality of sub-grid images includes:
processing the power line data to obtain a power line diagram;
the power circuit diagram is sliced according to a preset reference surface to obtain a sliced image;
dividing the slice image according to a preset dividing mode to obtain a plurality of sub-grid images, and acquiring a plurality of gray values which are in one-to-one correspondence with the plurality of sub-grid images;
and combining the slice image and the plurality of gray values to obtain a three-dimensional grid image.
2. The method of classifying an electrical power line according to claim 1, wherein after the step of combining the electrical power line data and the category attribute data set to obtain classification data corresponding to the electrical power line data, the method further comprises:
and optimizing the classified data by a preset search algorithm to obtain the classified optimized data.
3. The method for classifying power lines according to claim 1, wherein the step of obtaining a category attribute comparison table including category attribute labels corresponding to the sub-grid images includes:
sampling the plurality of sub-raster images included in the three-dimensional raster image to obtain sample data;
embedding the class attribute labels into the sample data according to a preset label embedding standard to obtain a class attribute comparison table comprising the class attribute labels corresponding to the sub-grid images.
4. A classification device for electric power lines is characterized by comprising an acquisition module, a processing module, an analysis module and a combination module, wherein,
the acquisition module is used for acquiring power line data comprising power line data and tower data; the power line data is bitmap data with a plurality of pixel points, and each pixel point has a unique gray value; wherein the bitmap data is a raster image, the raster image being two-dimensional, the grayscale values being for three-dimensional supplementation;
the processing module is used for processing the electric power line data to obtain an electric power line diagram and generating a three-dimensional grid image which corresponds to the electric power line data and comprises a plurality of sub-grid images according to the electric power line diagram;
the acquisition module is further used for acquiring a category attribute comparison table comprising category attribute labels corresponding to the sub-grid images;
the analysis module is used for analyzing the three-dimensional raster image according to a preset three-dimensional convolution neural network and the category attribute comparison table to obtain a category attribute data set corresponding to the three-dimensional raster image;
the combination module is used for combining the electric power line data and the category attribute data set to obtain category data corresponding to the electric power line data;
the processing module is specifically configured to process the power line data to obtain a power line diagram; the power circuit diagram is sliced according to a preset reference surface to obtain a sliced image; dividing the slice image according to a preset dividing mode to obtain a plurality of sub-grid images, and acquiring a plurality of gray values which are in one-to-one correspondence with the plurality of sub-grid images; and combining the slice image and the plurality of gray values to obtain a three-dimensional grid image.
5. The apparatus for sorting electric power lines according to claim 4,
the processing module is further used for optimizing the classified data by a preset search algorithm to obtain the classified optimized data.
6. The apparatus according to claim 5, wherein the acquisition module comprises a sampling unit and an embedding unit, wherein,
the sampling unit is used for sampling the plurality of sub-grid images included in the three-dimensional grid image to obtain sample data;
and the embedding unit is used for embedding the class attribute label into the sample data according to a preset label embedding standard to obtain a class attribute comparison table comprising the class attribute label corresponding to the sub-grid image.
7. A computer device, characterized in that it comprises a memory for storing a computer program and a processor for executing the computer program to make the computer device execute a method of classification of an electric power line according to any one of claims 1 to 3.
8. A computer-readable storage medium, characterized in that it stores a computer program for use in the computer device of claim 7.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201811043754.XA CN109214457B (en) | 2018-09-07 | 2018-09-07 | Power line classification method and device |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201811043754.XA CN109214457B (en) | 2018-09-07 | 2018-09-07 | Power line classification method and device |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN109214457A CN109214457A (en) | 2019-01-15 |
| CN109214457B true CN109214457B (en) | 2021-08-24 |
Family
ID=64986656
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201811043754.XA Active CN109214457B (en) | 2018-09-07 | 2018-09-07 | Power line classification method and device |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN109214457B (en) |
Families Citing this family (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN110120091B (en) * | 2019-04-28 | 2023-06-16 | 深圳供电局有限公司 | Method and device for manufacturing electric power inspection image sample and computer equipment |
| CN112364878A (en) * | 2020-09-25 | 2021-02-12 | 江苏师范大学 | Power line classification method based on deep learning under complex background |
| CN113238578B (en) * | 2021-05-11 | 2022-12-16 | 上海电力大学 | Routing planning method and system for power tower unmanned aerial vehicle inspection route |
Citations (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN104866840A (en) * | 2015-06-04 | 2015-08-26 | 广东中城规划设计有限公司 | Method for recognizing overhead power transmission line from airborne laser point cloud data |
| CN106408011A (en) * | 2016-09-09 | 2017-02-15 | 厦门大学 | Laser scanning three-dimensional point cloud tree automatic classifying method based on deep learning |
| GB2545602A (en) * | 2016-09-21 | 2017-06-21 | Univ Oxford Innovation Ltd | A neural network and method of using a neural network to detect objects in an environment |
-
2018
- 2018-09-07 CN CN201811043754.XA patent/CN109214457B/en active Active
Patent Citations (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN104866840A (en) * | 2015-06-04 | 2015-08-26 | 广东中城规划设计有限公司 | Method for recognizing overhead power transmission line from airborne laser point cloud data |
| CN106408011A (en) * | 2016-09-09 | 2017-02-15 | 厦门大学 | Laser scanning three-dimensional point cloud tree automatic classifying method based on deep learning |
| GB2545602A (en) * | 2016-09-21 | 2017-06-21 | Univ Oxford Innovation Ltd | A neural network and method of using a neural network to detect objects in an environment |
Non-Patent Citations (1)
| Title |
|---|
| Point Cloud Labeling using 3D Convolutional Neural Network;Jing Huang，Suya You;《2016 23rd International Conference on Pattern Recognition》;20161208;第2670-2675页 * |
Also Published As
| Publication number | Publication date |
|---|---|
| CN109214457A (en) | 2019-01-15 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN109214457B (en) | Power line classification method and device | |
| US10585948B2 (en) | Method and device for constructing spatial index of massive point cloud data | |
| CN108919232B (en) | Method and device for detecting dangerous points of power transmission line | |
| CN110533055B (en) | Point cloud data processing method and device | |
| CN108764012B (en) | Urban road rod-shaped object recognition algorithm based on multi-frame combined vehicle-mounted laser radar data | |
| CN110632608B (en) | Target detection method and device based on laser point cloud | |
| Carr et al. | Individual tree segmentation from a leaf-off photogrammetric point cloud | |
| Kim et al. | 3D classification of power-line scene from airborne laser scanning data using random forests | |
| AU2018326401A1 (en) | Method and system for use in performing localisation | |
| CN104951489A (en) | Meteorological data analyzing and processing method applied to power system | |
| CN109580004A (en) | A kind of temperature checking method and device | |
| CN107832849B (en) | Knowledge base-based power line corridor three-dimensional information extraction method and device | |
| US20100182316A1 (en) | Geospatial modeling system for 3d clutter data and related methods | |
| CN104318611A (en) | Three-dimensional tree re-establishing method based on laser scanning point cloud | |
| CN112798540A (en) | Water body pollution source early warning system based on high-resolution remote sensing | |
| CN115439753A (en) | Steep river bank identification method and system based on DEM | |
| CN116739558A (en) | Tree obstacle hidden danger early warning method based on laser point cloud modeling | |
| Gura et al. | Classification and automatisation of laser reflection points processing in the detection of vegetation | |
| CN115546664A (en) | Cascaded network-based insulator self-explosion detection method and system | |
| CN112614207B (en) | Contour line drawing method, device and equipment | |
| CN115731560B (en) | Deep learning-based slot line identification method and device, storage medium and terminal | |
| WO2023247827A1 (en) | Method and system for processing point-cloud data | |
| CN113379884B (en) | Map rendering method, map rendering device, electronic device, storage medium and vehicle | |
| CN115356706A (en) | Power transmission line progress confirmation method based on BIM information and laser point cloud data | |
| CN111415355A (en) | Image processing-based method, system and device for measuring safety distance of power transmission line |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant | ||
| CP03 | Change of name, title or address |
Address after: 100000 room 2301-2308, third floor, building 2, incubator of Dongbeiwang Zhongguancun Software Park, Haidian District, Beijing Patentee after: Beijing Digital Green Earth Technology Co.,Ltd. Address before: 100000 incubator 2a2308, Zhongguancun Software Park, Haidian District, Beijing Patentee before: BEIJING GREENVALLEY TECHNOLOGY Co.,Ltd. |
|
| CP03 | Change of name, title or address |