CN115937652A - Underground pipeline identification method, device, equipment and storage medium - Google Patents
Underground pipeline identification method, device, equipment and storage medium Download PDFInfo
- Publication number
- CN115937652A CN115937652A CN202211687538.5A CN202211687538A CN115937652A CN 115937652 A CN115937652 A CN 115937652A CN 202211687538 A CN202211687538 A CN 202211687538A CN 115937652 A CN115937652 A CN 115937652A
- Authority
- CN
- China
- Prior art keywords
- underground pipeline
- radar image
- target
- pipeline identification
- network
- 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.)
- Pending
Links
Images
Landscapes
- Image Processing (AREA)
Abstract
The invention discloses an underground pipeline identification method, an underground pipeline identification device, underground pipeline identification equipment and a storage medium, wherein the underground pipeline identification method comprises the following steps: acquiring a target radar image to be identified; the target radar image is obtained by scanning the underground medium according to a preset ground penetrating radar scanning mode; determining a target area included in a target radar image through an underground pipeline identification model; the underground pipeline identification model is obtained by training a preset deep learning network according to a plurality of radar images and Fourier transformation results corresponding to the radar images; and determining an underground pipeline identification result corresponding to the target radar image according to the target area through the underground pipeline identification model. According to the technical scheme of the embodiment of the invention, the accuracy of the underground pipeline identification result in the radar image can be improved.
Description
Technical Field
The invention relates to the technical field of computers, in particular to an underground pipeline identification method, an underground pipeline identification device, underground pipeline identification equipment and a storage medium.
Background
Ground Penetrating Radar (GPR) is an important technical means for underground nondestructive testing, and is widely used for studying near-surface geophysical structures and detecting buried targets. As a ground penetrating radar scanning mode, the B-scan is widely applied to various engineering fields. When the underground buried target is researched through the radar image, the underground pipeline identification difficulty is higher due to the fact that underground media are not uniform and various sundries exist.
In the prior art, when an underground pipeline in a radar image is identified, a plurality of radar images are usually directly used as training samples to train a preset deep learning model, and then the underground pipeline in the radar image to be detected is identified through the trained model.
However, the training samples of the models in the prior art generally include a noisy image background, which results in a low accuracy of the underground pipeline identification result.
Disclosure of Invention
The invention provides an underground pipeline identification method, an underground pipeline identification device, underground pipeline identification equipment and a storage medium, which can improve the accuracy of an underground pipeline identification result in a radar image.
According to an aspect of the present invention, there is provided an underground utility identifying method including:
acquiring a target radar image to be identified; the target radar image is obtained by scanning an underground medium according to a preset ground penetrating radar scanning mode;
determining a target area included in the target radar image through an underground pipeline identification model; the underground pipeline identification model is obtained by training a preset deep learning network according to a plurality of radar images and Fourier transformation results corresponding to the radar images;
and determining an underground pipeline identification result corresponding to the target radar image according to the target area through the underground pipeline identification model.
Optionally, before acquiring the target radar image to be identified, the method further includes:
acquiring a training set consisting of a plurality of radar images, and sequentially acquiring one radar image in the training set as a training sample;
training a preset deep learning network by using the training sample and a Fourier transform result corresponding to the training sample;
the deep learning network comprises a backbone network, an anchor frame recommendation network, a full convolution network and a full connection layer of the convolution neural network;
judging whether the processing of all radar images is finished or not;
if so, taking the trained deep learning network as the underground pipeline identification model;
and if not, returning to execute the operation of sequentially acquiring one radar image in the training set as a training sample until the processing of all the radar images is completed.
Optionally, determining a target area included in the target radar image through an underground pipeline identification model includes:
inputting the target radar image into a backbone network of an underground pipeline identification model to obtain a characteristic diagram corresponding to the target radar image;
and inputting the characteristic diagram into an anchor frame recommendation network of an underground pipeline identification model to obtain a target area included in the target radar image.
Optionally, the inputting the feature map into an anchor frame recommendation network of an underground pipeline identification model to obtain a target area included in the target radar image includes:
inputting the characteristic diagram into an anchor frame recommendation network of an underground pipeline identification model;
and processing the characteristic graph through a softmax network layer and a frame regression network layer in the anchor frame recommendation network to obtain a target area included in the target radar image.
Optionally, determining, by the underground pipeline identification model and according to the target area, an underground pipeline identification result corresponding to the target radar image, includes:
inputting the target area into a full convolution network of an underground pipeline identification model to obtain an edge detection result corresponding to the underground pipeline in the target radar image;
inputting the target area and the Fourier transform result corresponding to the target area into a full connection layer of an underground pipeline identification model respectively to obtain a rectangular frame corresponding to the underground pipeline in the target radar image and a type detection result corresponding to the underground pipeline;
and taking the edge detection result, the rectangular frame and the type detection result as the underground pipeline identification result corresponding to the target radar image.
Optionally, the inputting the target area and the fourier transform result corresponding to the target area into a full connection layer of an underground pipeline identification model respectively to obtain a rectangular frame corresponding to the underground pipeline in the target radar image and a type detection result corresponding to the underground pipeline includes:
inputting the target area into a full connection layer of an underground pipeline identification model, and processing the target area through the full connection layer by adopting a frame regression algorithm to obtain a rectangular frame corresponding to the underground pipeline in the target radar image;
and inputting the target area and the corresponding Fourier transform result into a full connection layer of the underground pipeline identification model, and processing the target area and the Fourier transform result by adopting a softmax algorithm through the full connection layer to obtain a type detection result corresponding to the underground pipeline in the target radar image.
According to another aspect of the present invention, there is provided an underground utility identification apparatus, the apparatus including:
the image acquisition module is used for acquiring a target radar image to be identified; the target radar image is obtained by scanning an underground medium according to a preset ground penetrating radar scanning mode;
the target area determining module is used for determining a target area included in the target radar image through an underground pipeline identification model; the underground pipeline identification model is obtained by training a preset deep learning network according to a plurality of radar images and Fourier transformation results corresponding to the radar images;
and the identification result determining module is used for determining the underground pipeline identification result corresponding to the target radar image according to the target area through the underground pipeline identification model.
Optionally, the apparatus further comprises:
the training set acquisition module is used for acquiring a training set consisting of a plurality of radar images, and acquiring one radar image in sequence in the training set as a training sample;
the network training module is used for training a preset deep learning network by using the training sample and a Fourier transform result corresponding to the training sample;
the deep learning network comprises a backbone network, an anchor frame recommendation network, a full convolution network and a full connection layer of the convolution neural network;
the judging module is used for judging whether the processing of all the radar images is finished or not; if so, taking the trained deep learning network as the underground pipeline identification model; and if not, returning to execute the operation of sequentially acquiring one radar image in the training set as a training sample until the processing of all the radar images is completed.
According to another aspect of the present invention, there is provided an electronic apparatus including:
at least one processor; and
a memory communicatively coupled to the at least one processor; wherein the content of the first and second substances,
the memory stores a computer program executable by the at least one processor, the computer program being executable by the at least one processor to enable the at least one processor to perform the underground pipeline identification method according to any one of the embodiments of the present invention.
According to another aspect of the present invention, there is provided a computer-readable storage medium storing computer instructions for causing a processor to implement the underground pipeline identification method according to any one of the embodiments of the present invention when executed.
According to the technical scheme provided by the embodiment of the invention, the target radar image to be identified is obtained, and the target area included in the target radar image is determined through the underground pipeline identification model; the underground pipeline identification model is obtained by training a preset deep learning network according to a plurality of radar images and Fourier transform results corresponding to the radar images, and the accuracy of the underground pipeline identification result in the radar images can be improved by the technical means of determining the underground pipeline identification result corresponding to the target radar image according to the target area through the underground pipeline identification model.
It should be understood that the statements in this section do not necessarily identify key or critical features of the embodiments of the present invention, nor do they necessarily limit the scope of the invention. Other features of the present invention will become apparent from the following description.
Drawings
In order to more clearly illustrate the technical solutions in the embodiments of the present invention, the drawings required to be used in the description of the embodiments are briefly introduced below, and it is obvious that the drawings in the description below are only some embodiments of the present invention, and it is obvious for those skilled in the art that other drawings can be obtained according to the drawings without creative efforts.
FIG. 1 is a flow chart of a method for identifying an underground utility provided in accordance with an embodiment of the present invention;
FIG. 2 is a flow chart of another method of underground utility identification provided in accordance with an embodiment of the present invention;
FIG. 3 is a schematic structural diagram of an underground pipeline identification device provided according to an embodiment of the present invention;
fig. 4 is a schematic structural diagram of an electronic device for implementing the underground pipeline identification method according to the embodiment of the present invention.
Detailed Description
In order to make the technical solutions of the present invention better understood, 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. All other embodiments, which can be derived by a person skilled in the art from the embodiments given herein without making any creative effort, shall fall within the protection scope of the present invention.
It should be noted that the terms "first," "second," and the like in the description and claims of the present invention and in the drawings described above are used for distinguishing between similar elements and not necessarily for describing a particular sequential or chronological order. It is to be understood that the data so used is interchangeable under appropriate circumstances such that the embodiments of the invention described herein are capable of operation in sequences other than those illustrated or described herein. Furthermore, the terms "comprises," "comprising," and "having," and any variations thereof, are intended to cover a non-exclusive inclusion, such that a process, method, system, article, or apparatus that comprises a list of steps or elements is not necessarily limited to those steps or elements expressly listed, but may include other steps or elements not expressly listed or inherent to such process, method, article, or apparatus.
Fig. 1 is a flowchart of an underground pipeline identification method according to an embodiment of the present invention, where the method is applicable to a situation of identifying an underground pipeline in a ground penetrating radar image, and the method can be executed by an underground pipeline identification device, where the underground pipeline identification device can be implemented in hardware and/or software, and the underground pipeline identification device can be configured in an electronic device (for example, a terminal or a server) with a data processing function. As shown in fig. 1, the method includes:
and step 110, acquiring a target radar image to be identified.
In this embodiment, the target radar image may be a radar image waiting for identification of the underground pipeline, and the target radar image is obtained by scanning the underground medium according to a preset ground penetrating radar scanning mode. Specifically, the scanning mode of the ground penetrating radar can be B-scan.
In this embodiment, optionally, before obtaining a target radar image to be identified, a plurality of radar images and fourier transform results of the radar images may be obtained in advance, and the deep learning network is trained by using the radar images and the fourier transform results to obtain the underground pipeline identification model.
In practical application, the underground pipeline usually shows two curves in a radar image, and after the radar image is subjected to Fourier transform, the underground pipeline usually shows two horizontal bright lines and one vertical bright line. Because the transformed radar image has good discrimination and image characteristics which are easy to identify, the Fourier transform result of the radar image can be used as a training sample to train a deep learning network, so that the effectiveness of the underground pipeline identification model and the accuracy of the subsequent underground pipeline identification result are improved.
In a specific embodiment, assuming that the radar image F (x, y) has a length and a width of M, N, respectively, the radar image can be fourier-transformed by the following formula to obtain a transformation result F (u, v):
in this step, optionally, the underground pipeline identification model may extract an image feature corresponding to the target radar image, and determine the target area according to the image feature.
In an implementation manner of this embodiment, before acquiring the target radar image to be recognized, the method further includes:
acquiring a training set consisting of a plurality of radar images, and sequentially acquiring one radar image in the training set as a training sample;
training a preset deep learning network by using the training sample and a Fourier transform result corresponding to the training sample;
the deep learning network comprises a backbone network, an anchor frame recommendation network, a full convolutional network (full convolutional networks) and a full Connected layer (full Connected Layers) of a convolutional neural network.
Judging whether the processing of all radar images is finished or not;
if so, taking the trained deep learning network as the underground pipeline identification model;
if not, returning to execute the operation of sequentially acquiring one radar image in the training set as a training sample until all the radar images are processed.
And step 130, determining an underground pipeline identification result corresponding to the target radar image according to the target area through the underground pipeline identification model.
In this step, optionally, the underground pipeline identification model may extract an image feature corresponding to the target area, and determine an underground pipeline identification result according to the image feature.
According to the technical scheme provided by the embodiment of the invention, a target area included in a target radar image is determined through acquiring the target radar image to be identified and an underground pipeline identification model; the underground pipeline identification model is obtained by training a preset deep learning network according to a plurality of radar images and Fourier transform results corresponding to the radar images, and the accuracy of the underground pipeline identification result in the radar images can be improved by the technical means of determining the underground pipeline identification result corresponding to the target radar image according to the target area through the underground pipeline identification model.
Fig. 2 is a flowchart of an underground pipeline identification method according to a second embodiment of the present invention, which is further detailed in the second embodiment. As shown in fig. 2, the method includes:
And 220, inputting the target radar image into a backbone network of an underground pipeline identification model to obtain a characteristic diagram corresponding to the target radar image.
And step 230, inputting the feature map into an anchor frame recommendation network of an underground pipeline identification model to obtain a target area included in the target radar image.
In this embodiment, the Anchor Box (Anchor Box) recommendation network may process the feature map to obtain an area (i.e., a target area) where the underground pipeline exists in the target radar image.
In an implementation manner of this embodiment, inputting the feature map into an anchor frame recommendation network of an underground pipeline identification model to obtain a target area included in the target radar image includes: inputting the characteristic diagram into an anchor frame recommendation network of an underground pipeline identification model; and processing the characteristic diagram through a softmax network layer and a border Regression (BBox Reg) network layer in the anchor frame recommendation network to obtain a target area included in the target radar image.
In a specific embodiment, the anchor frame recommendation network may include a plurality of convolutional network layers, after feature maps corresponding to target radar images are obtained, the feature maps may be respectively input into different convolutional network layers, the feature maps are processed by using a softmax algorithm through a part of the convolutional network layers, the feature maps are processed by using a BBox Reg algorithm through another part of the convolutional network layers, and finally, a target area is determined according to processing results of all the convolutional network layers.
The size of the convolutional network layer may be 3*3, and the specific value may be preset according to an actual situation, which is not limited in this embodiment.
And 240, inputting the target area into a full convolution network of an underground pipeline identification model to obtain an edge detection result corresponding to the underground pipeline in the target radar image.
And 250, respectively inputting the target area and the Fourier transform result corresponding to the target area into a full connection layer of an underground pipeline identification model to obtain a rectangular frame corresponding to the underground pipeline in the target radar image and a type detection result corresponding to the underground pipeline.
In this step, the target area may be input to a part of the full link layer, and the target area is processed through the full link layer to obtain a rectangular frame. And simultaneously inputting the target area and the corresponding Fourier transform result into the other part of the full connection layer, and then processing the target area and the Fourier transform result through the full connection layer to obtain a type detection result.
In this embodiment, the underground pipeline identification model may include a multitask classification network, where the multitask classification network includes a full convolution network and a full connection layer. In performing steps 240 and 250, a multitasking classification network may be employed to simultaneously determine edge detection results, rectangular boxes, and type detection results.
In an implementation manner of this embodiment, inputting the target area and the fourier transform result corresponding to the target area into a full connection layer of an underground pipeline identification model, respectively, to obtain a rectangular frame corresponding to an underground pipeline in the target radar image and a type detection result corresponding to the underground pipeline, includes: inputting the target area into a full connection layer of an underground pipeline identification model, and processing the target area through the full connection layer by adopting a frame regression algorithm to obtain a rectangular frame corresponding to the underground pipeline in the target radar image; and inputting the target area and the corresponding Fourier transform result into a full connection layer of the underground pipeline identification model, and processing the target area and the Fourier transform result by adopting a softmax algorithm through the full connection layer to obtain a type detection result corresponding to the underground pipeline in the target radar image.
The method has the advantages that the BBox Reg algorithm and the softmax algorithm are adopted to process the target area and the Fourier transform result, and the accuracy of the underground pipeline identification result in the target radar image can be improved.
And step 260, taking the edge detection result, the rectangular frame and the type detection result as an underground pipeline identification result corresponding to the target radar image.
In this embodiment, in order to verify the effectiveness of the underground pipeline identification model, a large number of reinforced radar images under the real bridge concrete may be collected, and the underground pipeline in the reinforced radar images may be identified by the underground pipeline identification model. Through experiments, the underground pipeline identification model can ensure that the accuracy of the underground pipeline identification result reaches 99.3%, and compared with the method of directly using a residual error network (ResNet), the accuracy can be improved by 2%.
According to the technical scheme provided by the embodiment of the invention, the target radar image to be identified is obtained, the target radar image is input into a backbone network of an underground pipeline identification model to obtain a characteristic diagram corresponding to the target radar image, the characteristic diagram is input into an anchor frame recommendation network of the underground pipeline identification model to obtain a target area included in the target radar image, the target area is input into a full convolution network of the underground pipeline identification model to obtain an edge detection result corresponding to the underground pipeline in the target radar image, the target area and a corresponding Fourier transformation result are respectively input into a full connection layer of the underground pipeline identification model to obtain a rectangular frame corresponding to the underground pipeline in the target radar image and a type detection result corresponding to the underground pipeline, and the edge detection result, the rectangular frame and the type detection result are used as technical means of the underground pipeline identification result corresponding to the target radar image, so that the accuracy of the underground pipeline identification result in the radar image can be improved.
Fig. 3 is a schematic structural view of an underground pipeline identifying device according to a third embodiment of the present invention, and as shown in fig. 3, the underground pipeline identifying device includes: an image acquisition module 310, a target area determination module 320, and a recognition result determination module 330.
The image acquisition module 310 is configured to acquire a target radar image to be identified; the target radar image is obtained by scanning an underground medium according to a preset ground penetrating radar scanning mode;
a target area determination module 320, configured to determine a target area included in the target radar image through an underground pipeline identification model; the underground pipeline identification model is obtained by training a preset deep learning network according to a plurality of radar images and Fourier transformation results corresponding to the radar images;
and the identification result determining module 330 is configured to determine, according to the target area, an underground pipeline identification result corresponding to the target radar image through the underground pipeline identification model.
According to the technical scheme provided by the embodiment of the invention, a target area included in a target radar image is determined through acquiring the target radar image to be identified and an underground pipeline identification model; the underground pipeline identification model is obtained by training a preset deep learning network according to a plurality of radar images and Fourier transformation results corresponding to the radar images, and the accuracy of the underground pipeline identification result in the radar images can be improved by the technical means of determining the underground pipeline identification result corresponding to the target radar image according to the target area through the underground pipeline identification model.
On the basis of the above embodiment, the apparatus further includes:
the training set acquisition module is used for acquiring a training set consisting of a plurality of radar images, and acquiring one radar image in sequence in the training set as a training sample;
the network training module is used for training a preset deep learning network by using the training sample and a Fourier transform result corresponding to the training sample;
the deep learning network comprises a backbone network, an anchor frame recommendation network, a full convolution network and a full connection layer of the convolution neural network;
the judging module is used for judging whether the processing of all the radar images is finished or not; if so, taking the trained deep learning network as the underground pipeline identification model; and if not, returning to execute the operation of sequentially acquiring one radar image in the training set as a training sample until the processing of all the radar images is completed.
The target area determination module 320 includes:
the characteristic diagram determining unit is used for inputting the target radar image into a backbone network of an underground pipeline identification model to obtain a characteristic diagram corresponding to the target radar image;
the anchor frame recommendation network processing unit is used for inputting the characteristic diagram into an anchor frame recommendation network of an underground pipeline identification model to obtain a target area included in the target radar image;
the characteristic diagram input unit is used for inputting the characteristic diagram into an anchor frame recommendation network of the underground pipeline identification model;
and the characteristic map processing unit is used for processing the characteristic map through a softmax network layer and a frame regression network layer in the anchor frame recommendation network to obtain a target area included in the target radar image.
The recognition result determining module 330 includes:
the edge detection unit is used for inputting the target area into a full convolution network of an underground pipeline identification model to obtain an edge detection result corresponding to the underground pipeline in the target radar image;
the target area processing unit is used for respectively inputting the target area and the Fourier transform result corresponding to the target area into a full connection layer of an underground pipeline identification model to obtain a rectangular frame corresponding to the underground pipeline in the target radar image and a type detection result corresponding to the underground pipeline;
the underground pipeline identification result determining unit is used for taking the edge detection result, the rectangular frame and the type detection result as an underground pipeline identification result corresponding to the target radar image;
the rectangular frame determining unit is used for inputting the target area into a full connection layer of an underground pipeline identification model, and processing the target area through the full connection layer by adopting a frame regression algorithm to obtain a rectangular frame corresponding to the underground pipeline in the target radar image;
and the type detection unit is used for inputting the target area and the corresponding Fourier transform result into a full connection layer of the underground pipeline identification model, and processing the target area and the Fourier transform result by adopting a softmax algorithm through the full connection layer to obtain the type detection result corresponding to the underground pipeline in the target radar image.
The device can execute the methods provided by all the embodiments of the invention, and has corresponding functional modules and beneficial effects for executing the methods. For technical details which are not described in detail in the embodiments of the present invention, reference may be made to the methods provided in all the embodiments of the present invention described above.
FIG. 4 shows a schematic block diagram of an electronic device 10 that may be used to implement an embodiment of the invention. Electronic devices are intended to represent various forms of digital computers, such as laptops, desktops, workstations, personal digital assistants, servers, blade servers, mainframes, and other appropriate computers. The electronic device may also represent various forms of mobile devices, such as personal digital assistants, cellular phones, smart phones, wearable devices (e.g., helmets, glasses, watches, etc.), and other similar computing devices. The components shown herein, their connections and relationships, and their functions, are meant to be exemplary only, and are not meant to limit implementations of the inventions described and/or claimed herein.
As shown in fig. 4, the electronic device 10 includes at least one processor 11, and a memory communicatively connected to the at least one processor 11, such as a Read Only Memory (ROM) 12, a Random Access Memory (RAM) 13, and the like, wherein the memory stores a computer program executable by the at least one processor, and the processor 11 can perform various suitable actions and processes according to the computer program stored in the Read Only Memory (ROM) 12 or the computer program loaded from a storage unit 18 into the Random Access Memory (RAM) 13. In the RAM 13, various programs and data necessary for the operation of the electronic apparatus 10 can also be stored. The processor 11, the ROM 12, and the RAM 13 are connected to each other via a bus 14. An input/output (I/O) interface 15 is also connected to bus 14.
A number of components in the electronic device 10 are connected to the I/O interface 15, including: an input unit 16 such as a keyboard, a mouse, or the like; an output unit 17 such as various types of displays, speakers, and the like; a storage unit 18 such as a magnetic disk, an optical disk, or the like; and a communication unit 19 such as a network card, modem, wireless communication transceiver, etc. The communication unit 19 allows the electronic device 10 to exchange information/data with other devices via a computer network such as the internet and/or various telecommunication networks.
In some embodiments, the underground utility identification method may be implemented as a computer program that is tangibly embodied in a computer-readable storage medium, such as the storage unit 18. In some embodiments, part or all of the computer program may be loaded and/or installed onto the electronic device 10 via the ROM 12 and/or the communication unit 19. When loaded into RAM 13 and executed by processor 11, the computer program may perform one or more of the steps of the underground pipeline identification method described above. Alternatively, in other embodiments, the processor 11 may be configured to perform the underground pipeline identification method by any other suitable means (e.g., by way of firmware).
Various implementations of the systems and techniques described here above may be implemented in digital electronic circuitry, integrated circuitry, field Programmable Gate Arrays (FPGAs), application Specific Integrated Circuits (ASICs), application Specific Standard Products (ASSPs), system on a chip (SOCs), load programmable logic devices (CPLDs), computer hardware, firmware, software, and/or combinations thereof. These various embodiments may include: implemented in one or more computer programs that are executable and/or interpretable on a programmable system including at least one programmable processor, which may be special or general purpose, receiving data and instructions from, and transmitting data and instructions to, a storage system, at least one input device, and at least one output device.
A computer program for implementing the methods of the present invention may be written in any combination of one or more programming languages. These computer programs may be provided to a processor of a general purpose computer, special purpose computer, or other programmable data processing apparatus, such that the computer programs, when executed by the processor, cause the functions/acts specified in the flowchart and/or block diagram block or blocks to be performed. A computer program can execute entirely on a machine, partly on the machine, as a stand-alone software package, partly on the machine and partly on a remote machine or entirely on the remote machine or server.
In the context of the present invention, a computer-readable storage medium may be a tangible medium that can contain, or store a computer program for use by or in connection with an instruction execution system, apparatus, or device. A computer readable storage medium may include, but is not limited to, an electronic, magnetic, optical, electromagnetic, infrared, or semiconductor system, apparatus, or device, or any suitable combination of the foregoing. Alternatively, the computer readable storage medium may be a machine readable signal medium. More specific examples of a machine-readable storage medium would include an electrical connection based on one or more wires, a portable computer diskette, 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 compact disc read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination of the foregoing.
To provide for interaction with a user, the systems and techniques described here can be implemented on an electronic device having: a display device (e.g., a CRT (cathode ray tube) or LCD (liquid crystal display) monitor) for displaying information to a user; and a keyboard and a pointing device (e.g., a mouse or a trackball) by which a user can provide input to the electronic device. Other kinds of devices may also be used to provide for interaction with a user; for example, feedback provided to the user can be any form of sensory feedback (e.g., visual feedback, auditory feedback, or tactile feedback); and input from the user may be received in any form, including acoustic, speech, or tactile input.
The systems and techniques described here can be implemented in a computing system that includes a back-end component (e.g., as a data server), or that includes a middleware component (e.g., an application server), or that includes a front-end component (e.g., a user computer having a graphical user interface or a web browser through which a user can interact with an implementation of the systems and techniques described here), or any combination of such back-end, middleware, or front-end components. The components of the system can be interconnected by any form or medium of digital data communication (e.g., a communication network). Examples of communication networks include: local Area Networks (LANs), wide Area Networks (WANs), blockchain networks, and the internet.
The computing system may include clients and servers. A client and server are generally remote from each other and typically interact through a communication network. The relationship of client and server arises by virtue of computer programs running on the respective computers and having a client-server relationship to each other. The server can be a cloud server, also called a cloud computing server or a cloud host, and is a host product in a cloud computing service system, so that the defects of high management difficulty and weak service expansibility in the traditional physical host and VPS service are overcome.
It should be understood that various forms of the flows shown above, reordering, adding or deleting steps, may be used. For example, the steps described in the present invention may be executed in parallel, sequentially, or in different orders, and are not limited herein as long as the desired results of the technical solution of the present invention can be achieved.
The above-described embodiments should not be construed as limiting the scope of the invention. It should be understood by those skilled in the art that various modifications, combinations, sub-combinations and substitutions may be made in accordance with design requirements and other factors. Any modification, equivalent replacement, and improvement made within the spirit and principle of the present invention should be included in the protection scope of the present invention.
Claims (10)
1. An underground pipeline identification method, characterized in that the method comprises:
acquiring a target radar image to be identified; the target radar image is obtained by scanning an underground medium according to a preset ground penetrating radar scanning mode;
determining a target area included in the target radar image through an underground pipeline identification model; the underground pipeline identification model is obtained by training a preset deep learning network according to a plurality of radar images and Fourier transform results corresponding to the radar images;
and determining an underground pipeline identification result corresponding to the target radar image according to the target area through the underground pipeline identification model.
2. The method of claim 1, further comprising, prior to acquiring the target radar image to be identified:
acquiring a training set consisting of a plurality of radar images, and sequentially acquiring one radar image in the training set as a training sample;
training a preset deep learning network by using the training sample and a Fourier transform result corresponding to the training sample;
the deep learning network comprises a backbone network, an anchor frame recommending network, a full convolution network and a full connection layer of the convolution neural network;
judging whether the processing of all radar images is finished or not;
if so, taking the trained deep learning network as the underground pipeline identification model;
if not, returning to execute the operation of sequentially acquiring one radar image in the training set as a training sample until all the radar images are processed.
3. The method of claim 2, wherein determining a target area included in the target radar image through an underground pipeline identification model comprises:
inputting the target radar image into a backbone network of an underground pipeline identification model to obtain a characteristic diagram corresponding to the target radar image;
and inputting the characteristic diagram into an anchor frame recommendation network of an underground pipeline identification model to obtain a target area included in the target radar image.
4. The method according to claim 3, wherein inputting the feature map into an anchor frame recommendation network of an underground pipeline identification model to obtain a target area included in the target radar image comprises:
inputting the characteristic diagram into an anchor frame recommendation network of an underground pipeline identification model;
and processing the characteristic graph through a softmax network layer and a frame regression network layer in the anchor frame recommendation network to obtain a target area included in the target radar image.
5. The method of claim 2, wherein determining, by the underground pipeline identification model and according to the target area, an underground pipeline identification result corresponding to a target radar image comprises:
inputting the target area into a full convolution network of an underground pipeline identification model to obtain an edge detection result corresponding to the underground pipeline in the target radar image;
inputting the target area and the Fourier transform result corresponding to the target area into a full connection layer of an underground pipeline identification model respectively to obtain a rectangular frame corresponding to the underground pipeline in the target radar image and a type detection result corresponding to the underground pipeline;
and taking the edge detection result, the rectangular frame and the type detection result as the underground pipeline identification result corresponding to the target radar image.
6. The method according to claim 5, wherein the step of inputting the target area and the Fourier transform result corresponding to the target area into a full connection layer of an underground pipeline identification model respectively to obtain a rectangular frame corresponding to an underground pipeline in the target radar image and a type detection result corresponding to the underground pipeline comprises the steps of:
inputting the target area into a full connection layer of an underground pipeline identification model, and processing the target area through the full connection layer by adopting a frame regression algorithm to obtain a rectangular frame corresponding to the underground pipeline in the target radar image;
and inputting the target area and the corresponding Fourier transform result into a full connection layer of the underground pipeline identification model, and processing the target area and the Fourier transform result by adopting a softmax algorithm through the full connection layer to obtain a type detection result corresponding to the underground pipeline in the target radar image.
7. An underground utility identification apparatus, the apparatus comprising:
the image acquisition module is used for acquiring a target radar image to be identified; the target radar image is obtained by scanning an underground medium according to a preset ground penetrating radar scanning mode;
the target area determining module is used for determining a target area included in the target radar image through an underground pipeline identification model; the underground pipeline identification model is obtained by training a preset deep learning network according to a plurality of radar images and Fourier transformation results corresponding to the radar images;
and the identification result determining module is used for determining the underground pipeline identification result corresponding to the target radar image according to the target area through the underground pipeline identification model.
8. The apparatus of claim 7, further comprising:
the training set acquisition module is used for acquiring a training set consisting of a plurality of radar images, and acquiring one radar image in sequence in the training set as a training sample;
the network training module is used for training a preset deep learning network by using the training sample and a Fourier transform result corresponding to the training sample;
the deep learning network comprises a backbone network, an anchor frame recommendation network, a full convolution network and a full connection layer of the convolution neural network;
the judging module is used for judging whether the processing of all the radar images is finished or not; if so, taking the trained deep learning network as the underground pipeline identification model; if not, returning to execute the operation of sequentially acquiring one radar image in the training set as a training sample until all the radar images are processed.
9. An electronic device, characterized in that the electronic device comprises:
at least one processor; and
a memory communicatively coupled to the at least one processor; wherein the content of the first and second substances,
the memory stores a computer program executable by the at least one processor to enable the at least one processor to perform the underground pipeline identification method of any one of claims 1-6.
10. A computer-readable storage medium having stored thereon computer instructions for causing a processor to execute the underground pipeline identification method according to any one of claims 1 to 6.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202211687538.5A CN115937652A (en) | 2022-12-27 | 2022-12-27 | Underground pipeline identification method, device, equipment and storage medium |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202211687538.5A CN115937652A (en) | 2022-12-27 | 2022-12-27 | Underground pipeline identification method, device, equipment and storage medium |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN115937652A true CN115937652A (en) | 2023-04-07 |
Family
ID=86700687
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202211687538.5A Pending CN115937652A (en) | 2022-12-27 | 2022-12-27 | Underground pipeline identification method, device, equipment and storage medium |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN115937652A (en) |
-
2022
- 2022-12-27 CN CN202211687538.5A patent/CN115937652A/en active Pending
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN114419035B (en) | Product identification method, model training device and electronic equipment | |
| CN113705628B (en) | Determination method and device of pre-training model, electronic equipment and storage medium | |
| CN112949767A (en) | Sample image increment, image detection model training and image detection method | |
| CN115861462B (en) | Training method and device for image generation model, electronic equipment and storage medium | |
| CN113360711B (en) | Model training and executing method, device, equipment and medium for video understanding task | |
| CN115294332B (en) | Image processing method, device, equipment and storage medium | |
| CN113780098A (en) | Character recognition method, character recognition device, electronic equipment and storage medium | |
| CN112419268A (en) | Method, device, equipment and medium for detecting image defects of power transmission line | |
| CN115937652A (en) | Underground pipeline identification method, device, equipment and storage medium | |
| CN115359322A (en) | Target detection model training method, device, equipment and storage medium | |
| CN115147395A (en) | Lipoprotein subtype component dividing method, device, equipment and storage medium | |
| CN113032071A (en) | Page element positioning method, page testing method, device, equipment and medium | |
| CN113807391A (en) | Task model training method and device, electronic equipment and storage medium | |
| CN113344064A (en) | Event processing method and device | |
| CN117746069B (en) | Graph searching model training method and graph searching method | |
| CN117198272B (en) | Voice processing method and device, electronic equipment and storage medium | |
| CN117115568B (en) | Data screening method, device, equipment and storage medium | |
| CN113642495B (en) | Training method, apparatus, and program product for evaluating model for time series nomination | |
| CN113267815B (en) | Method and device for filtering repeated broken edge data | |
| CN117271289A (en) | Webpage monitoring method, device, equipment and storage medium | |
| CN117636048A (en) | Abnormality detection method, device, equipment and storage medium for trade background contract | |
| CN117764975A (en) | Image detection method, device, equipment and medium | |
| CN115329933A (en) | Model interpretation method and device, electronic equipment and storage medium | |
| CN117576077A (en) | Defect detection method, device, equipment and storage medium | |
| CN117911871A (en) | Identification method, device, equipment and medium for target power transmission facility |
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 |