CN115690689A - Image identification method and device for tunnel face overbreak after blasting by drilling and blasting method - Google Patents
Image identification method and device for tunnel face overbreak after blasting by drilling and blasting method Download PDFInfo
- Publication number
- CN115690689A CN115690689A CN202211411948.7A CN202211411948A CN115690689A CN 115690689 A CN115690689 A CN 115690689A CN 202211411948 A CN202211411948 A CN 202211411948A CN 115690689 A CN115690689 A CN 115690689A
- Authority
- CN
- China
- Prior art keywords
- face
- tunnel
- image
- blasting
- area
- 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
Abstract
The invention belongs to the field of tunnel engineering, and particularly relates to an image identification method and device for tunnel face overbreak after tunnel blasting by a drilling and blasting method. The specific technical scheme is as follows: identifying a face overbreak area and a background area of the face image based on a semantic segmentation algorithm principle in image identification according to an established database of the blasted face image; identifying a target area and a background area of the palm surface target image based on a semantic segmentation algorithm principle in image identification according to the established palm surface target image database; and finally, comparing and analyzing the coordinates of the face overburdened area under the tunnel coordinate system with the tunnel blasting design contour line to obtain the overburdened amount of the face after tunnel blasting. The method reduces the error of the tunnel out-of-break calculation result, reduces the influence on the construction time and the construction cost, and solves the technical problem of low accuracy of the tunnel out-of-break calculation in the traditional method.
Description
Technical Field
The invention belongs to the field of tunnel engineering, and particularly relates to an image identification method and device for tunnel face overbreak after tunnel blasting by a drilling and blasting method.
Background
In the process of excavating the tunnel, the drilling and blasting method is one of the main methods for excavating, but the drilling and blasting method has the disadvantage that once the blasting design is improper, a large amount of overbreak and underexcavation phenomena of the tunnel are inevitably caused. The tunnel is overexcavated and underexcavated into, and overexcavation refers to the actual excavation contour line of tunnel and is greater than the tunnel design excavation contour line, and underexcavated refers to the actual excavation contour line of tunnel and is less than the tunnel design excavation contour line. The tunnel is surpassed and underexcavated, so that the construction progress is influenced, the engineering quality is also influenced, and the construction cost is even increased. Therefore, the convenient, quick and reliable tunnel face overbreak and underbreak evaluation method after tunnel blasting is very important in the tunnel excavation process.
At present, most of tunnel overbreak and underbreak calculation methods still stay at the manual field actual measurement of tunnel overbreak and underbreak layers. This method has the following problems: manual testing is time-consuming and labor-consuming, and a measurement result has large errors due to human factors during each test; each section can not be infinitely measured, and only a plurality of local positions can be measured; the mapping is troublesome after the test, and the whole process is relatively complicated.
Therefore, if a convenient, rapid and accurate tunnel face overbreak image identification method after tunnel blasting can be provided, the method has superior industrial application value.
Disclosure of Invention
In order to solve the technical problems, the invention aims to provide an image identification method and device for tunnel face overbreak after blasting of a drilling and blasting tunnel.
In order to realize the purpose of the invention, the technical scheme adopted by the invention is as follows: identifying a face overbreak area and a background area of the face image based on a semantic segmentation algorithm principle in image identification according to an established database of the blasted face image; identifying a target area and a background area of the palm surface target image based on a semantic segmentation algorithm principle in image identification according to the established palm surface target image database; and finally, comparing and analyzing the coordinates of the face overburdened area under the tunnel coordinate system with the tunnel blasting design contour line to obtain the overburdened amount of the face after tunnel blasting.
Preferably, the following components: the image recognition method for the face overbreak after the tunnel blasting by the drilling and blasting method comprises the following steps,
step 101: acquiring a large number of blasted face image samples, establishing a face image sample database, performing deep learning on the face images, and establishing an ultra-underpolished area identification model of the tunnel blasted face images;
step 102: acquiring a large number of blasted tunnel face target image samples, establishing a tunnel face upper target image sample database, performing deep learning on the tunnel face target images, and establishing a tunnel face upper target area identification model;
step 103: and identifying the overbreak and underbreak amount of the tunnel face after blasting based on the overbreak and underbreak area identification model and the target area identification model.
Preferably, the following components: said step 101 comprises the steps of,
step 1011: by marking the original image of the blasted face, dividing the original image of the blasted face into a face ultra-short excavation area and a background area, and establishing a sample database of the blasted face image;
step 1012: and according to the established post-blasting face image sample database, performing deep learning on the face image sample, and establishing an ultra-underproduction area identification model of the tunnel post-blasting face image.
Preferably: said step 102 comprises the steps of,
step 1021: dividing the blasted face original image into a target area and a background area by marking the blasted face original image, and establishing a target image sample database on the face;
step 1022: and according to the established database of the target image samples on the tunnel face after blasting, performing deep learning on the target image samples on the tunnel face, and establishing a target area identification model on the tunnel face by a drilling and blasting method.
Preferably: said step 103 comprises the steps of,
step 1031: according to the face super-under-cut area identification model and the target area identification model, obtaining a super-under-cut area and a target area on the face image;
step 1032: obtaining the coordinates of the overburdened area and the area where the target is located under a tunnel coordinate system based on the overburdened area and the area where the target is located on the tunnel face image;
step 1033: and comparing and analyzing the coordinates of the overburdened area and the area where the target is located based on the tunnel coordinate system with the tunnel blasting design contour line to obtain the overburdened amount of the tunnel face after blasting.
Correspondingly: the image recognition device for tunnel face overbreak after tunnel blasting by the drilling and blasting method comprises an image acquisition module, a construction module I, a construction module II and an analysis processing module;
the image acquisition module acquires tunnel face images after tunnel blasting and transmits the tunnel face images to the construction module I and the construction module II;
the construction module I constructs an identification model of the overbreak area of the tunnel face image after blasting of the tunnel by a drilling and blasting method according to the constructed sample database of the image of the tunnel face after blasting;
the second construction module is used for constructing a target area recognition model on the tunnel face image of the drilling and blasting method according to the established target image sample database on the tunnel face;
and the analysis processing module analyzes the overbreak and underbreak amount of the tunnel face after blasting based on the identification result of the pair of face images of the construction module and the identification result of the pair of face target images of the construction module.
Preferably: the first construction module comprises a face image data module and a face super-undermining identification module;
the palm surface image data module receives the palm surface images transmitted by the image acquisition module, establishes a palm surface image database and transmits the palm surface images to the palm surface ultra-short excavation region identification module;
the face back break recognition module receives the face image, recognizes a face area and a background area in the face image, performs deep learning on the face image, and establishes a face back break area recognition model.
Preferably: the second construction module comprises a palm surface target image data module and a palm surface target area identification module;
the palm surface target image data module receives the palm surface image transmitted by the image acquisition module, establishes a palm surface target image database and transmits the palm surface target image to the palm surface target area identification module;
the face target area identification module receives the face target image, identifies a target area and a background area in the face target image, performs deep learning on the face target image, and establishes a face target area identification model.
Correspondingly: an electronic device, comprising:
one or more processors;
storage means for storing one or more programs;
when the one or more programs are executed by the one or more processors, the one or more processors implement a method for image recognition of rock face overbreak after a drill-and-blast tunnel blast.
Correspondingly: a computer-readable medium, in which a computer program is stored which, when executed by a processor, implements a method for image recognition of rock face overbreak after a drill-and-blast tunnel blast.
Compared with the prior art, the invention has the following beneficial effects:
identifying a face overbreak area and a background area of the face image based on a semantic segmentation algorithm principle in image identification according to an established database of the blasted face image; identifying a target area and a background area of the palm surface target image based on a semantic segmentation algorithm principle in image identification according to the established palm surface target image database; and finally, comparing and analyzing the coordinates of the face overburdened area under the tunnel coordinate system with the tunnel blasting design contour line to obtain the overburdened amount of the face after tunnel blasting. Along with the continuous tunneling of the tunnel, the revealed face overbreak and overbreak data are continuously updated, and the face overbreak and overbreak amount after each cycle of blasting can be accurately calculated through image recognition, so that the blasting design is optimized, and the construction cost is reduced. The method reduces the error of the tunnel out-of-break calculation result, reduces the influence on the construction time and the construction cost, and solves the technical problem of low accuracy of the tunnel out-of-break calculation in the traditional method.
Drawings
FIG. 1 is a flow chart of a tunnel face overbreak image identification method after tunnel blasting by a drilling and blasting method;
FIG. 2 is a schematic diagram of the marks of the overbreak area of the tunnel face after the tunnel blasting by the drilling and blasting method of the invention (the overbreak area is an area surrounded by dots in the figure);
FIG. 3 is a schematic diagram illustrating the labeling of a target area on an image of a tunnel face by a drilling and blasting method according to the present invention;
FIG. 4 is a schematic view of the identification of the overbreak area of the tunnel face after the tunnel is blasted by the drilling and blasting method of the invention;
FIG. 5 is a schematic view of the recognition of a target area on an image of a tunnel face by a drilling and blasting method according to the present invention;
FIG. 6 is a schematic diagram of comparative analysis of the tunnel face overbreak identification contour line and the tunnel blasting design contour line after tunnel blasting according to the present invention;
fig. 7 is a schematic diagram of the basic structure of the electronic device 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. Unless otherwise specified, the technical means used in the examples are conventional means well known to those skilled in the art.
The invention discloses an image identification method for tunnel face overbreak after blasting of a drilling and blasting tunnel, which has the core idea that: identifying a face overbreak area and a background area of the face image based on a semantic segmentation algorithm principle in image identification according to an established database of the blasted face image; identifying a target area and a background area of a palm surface target image based on a semantic segmentation algorithm principle in image identification according to an established palm surface target image database; and finally, comparing and analyzing the coordinates of the face overburdened area under the tunnel coordinate system with the tunnel blasting design contour line to obtain the overburdened amount of the face after tunnel blasting.
As shown in fig. 1, an image recognition method for tunnel face overbreak after blasting of a drilling and blasting tunnel comprises the following steps:
step 101: acquiring a large number of blasted face image samples, establishing a blasted face image sample database, performing deep learning on the face image samples based on an image semantic segmentation principle, and establishing an ultra-undermining area identification model of the blasted face image after tunnel blasting by a drilling and blasting method.
Specifically, the step 101 includes the following steps:
step 1011: the method comprises the steps of dividing an original image of a blasted face into a face ultra-undermining area and a background area by marking the original image of the blasted face, wherein a marking schematic diagram of the face ultra-undermining after the tunnel blasting by a drilling and blasting method is shown in FIG. 2, and a blasting face image sample database is established based on a large number of blasted face images.
Step 1012: and establishing an ultra-short excavation region identification model of the tunnel face image after blasting by the drilling and blasting method based on the semantic segmentation algorithm principle in image identification according to the established blasting face image sample database. In the deep learning process, the face image is used as an input variable, the face super-under digging area and the background area are used as output variables, and a super-under digging area identification model of the face image is established. The super-undercut area identification model of the face image can identify a face super-undercut area and a background area in the face image.
Specifically, one embodiment of the method for establishing the overbreak and underbreak recognition model of the tunnel face image after the tunnel blasting by the drilling and blasting method is performed, in step 1012, the method includes the following steps:
step 1012.1: constructing a deep learning palm image semantic segmentation network framework;
step 1012.2: optimizing the network parameters of the step 1012.1, and training the network weight parameters of the step 1012.1 by using the tunnel face image database of the step 1012 until the total loss does not decrease any more, so as to obtain the model parameters under the minimum test error. The optimization step 1012.1 may be one or more of changing the model learning rate, changing the backbone feature extraction network, changing the loss function calculation method, and the like.
Step 1012.3: and establishing an ultra-underpinning area identification model of the tunnel face image after tunnel blasting based on the network frame of the step 1012.1 and the final network training parameters of the step 1012.2.
Step 102: aiming at the target image of the blasted tunnel face, a corresponding target image database on the tunnel face is established, deep learning is carried out on the target image sample of the tunnel face based on the semantic segmentation algorithm principle in image recognition, and a target area recognition model on the tunnel face of the tunnel by the drilling and blasting method is established. The target may be a fixed-length, clear-colored rod, a fixed-area, clear-colored flat plate, or a fixed-diameter, clear-colored dots. I.e. the target should be distinguishable from the face area by color, the target being an object present on the face target image itself after blasting. And carrying out equal-proportion conversion between the palm surface target coordinate and a pixel coordinate system through the ratio of the actual length of the target to the target image pixel.
Specifically, the step 102 includes the following steps:
step 1021: the blasting face original image is divided into a target area and a background area by marking the blasting face target original image, the marking schematic diagram of the targets on the drilling and blasting tunnel face image is shown in fig. 3, and a face target image sample database is established based on a large number of face target images.
Step 1022: and establishing a target area identification model on the tunnel face of the tunnel by the drilling and blasting method based on a semantic segmentation algorithm principle in image identification according to the established database of the target image on the tunnel face after blasting. In the deep learning process, a target image of the working face is used as an input variable, a target area and a background area are used as output variables, and a target area recognition model on the working face is established.
Specifically, an embodiment of establishing a model for identifying a target area on a tunnel face of a tunnel by a drilling and blasting method is described, where step 1012 includes the following steps:
step 1022.1: constructing a semantic segmentation network framework of a target image on a deep learning palm surface;
step 1022.2: optimizing the network parameters of the step 1022.1, training the network weight parameters of the step 1022.1 by using the tunnel face target image database of the step 1022 until the total loss does not decrease any more, and obtaining the model parameters under the minimum test error. The optimization step 1022.1 may be one or more of changing the model learning rate, changing the backbone feature extraction network, changing the loss function calculation method, and the like.
Step 1022.3: and establishing a target area recognition model on the tunnel face based on the network frame in the step 1022.1 and the final network training parameters in the step 1022.2.
Step 103: and identifying the overbreak and underbreak amount of the tunnel face after blasting through the pixel length of the target and the position of the target under a tunnel coordinate system based on an overbreak area identification model of the tunnel face image after blasting of the tunnel by the drilling and blasting method and a target area identification model on the tunnel face image by the drilling and blasting method.
Specifically, the step 103 includes the steps of:
step 1031: and aiming at the tunnel face image after the same tunnel is blasted, according to the tunnel face super-under-excavated area identification model and the target area identification model, obtaining a super-under-excavated area and a target area on the tunnel face image.
Step 1032: and obtaining the coordinates of the area under the tunnel coordinate system and the area where the target is located through the pixel length of the target and the position of the target under the tunnel coordinate system based on the area under the tunnel face image and the area where the target is located. Firstly, the problem of positioning is that a tunnel coordinate system always takes a tunnel face as a coordinate system plane, a target (taking a rod as an example) is vertically arranged at an intersection point of a tunnel central axis, the tunnel face and a step plane, the intersection point is taken as an original point, the horizontal direction is the X-axis direction, and the vertical direction is the Y-axis direction; and secondly, a coordinate system conversion problem, namely converting the image coordinate system and the tunnel coordinate system in an equal proportion by taking an original point as a reference according to a conversion proportion between the pixel length and the actual length of the target.
Step 1033: and comparing and analyzing the coordinates of the overburdened area and the area where the target is located based on the tunnel coordinate system with the tunnel blasting design contour line to obtain the overburdened amount of the tunnel face after blasting. And then, calculating the overbreak value under the image coordinate system, and converting the overbreak value under the image coordinate system into the overbreak value under the tunnel coordinate system according to the conversion ratio, namely the actual overbreak amount.
In a specific embodiment, a schematic diagram of identification of the overbreak area of the tunnel face after blasting in the drilling and blasting tunnel is shown in fig. 4; a schematic diagram of target area identification on a tunnel face image of a drilling and blasting tunnel is shown in fig. 5; fig. 6 shows a schematic diagram of comparative analysis of the tunnel face overbreak area identification contour line and the tunnel blasting design contour line after tunnel blasting.
Along with the continuous tunneling of the tunnel, the revealed face overbreak and overbreak data are continuously updated, and the face overbreak and overbreak amount after each cycle of blasting can be accurately calculated through image recognition, so that the blasting design is optimized, and the construction cost is reduced. The method reduces the error of the tunnel out-of-break calculation result, reduces the influence on the construction time and the construction cost, and solves the technical problem of low accuracy of the tunnel out-of-break calculation in the traditional method. In addition, the method creates an intelligent, efficient, few-person and unmanned image recognition new mode for tunnel face overbreak after tunnel blasting by the drilling and blasting method, and has high degree of intelligence which is not possessed by the traditional method.
As an implementation of the method, the present application further provides an image recognition apparatus for tunnel face overbreak after blasting by a drilling and blasting method, where an embodiment of the apparatus corresponds to the method embodiment shown in fig. 1, and the apparatus may be specifically applied to various electronic devices. The application further discloses an image recognition device for tunnel face overbreak after blasting of a drilling and blasting method tunnel, which comprises an image acquisition module, a first construction module, a second construction module and an analysis processing module. When the working, the image acquisition module acquires the face image and outputs the face image to the analysis processing module; the construction module I establishes an ultra-undermining area identification model of a tunnel face image after tunnel blasting by a drilling and blasting method; a second construction module establishes a target area recognition model on the tunnel face of the tunnel; and the analysis processing module acquires the identification model of the overburdened area of the first construction module and the identification model of the target area of the second construction module, processes and analyzes the face image, and identifies the overburdened amount of the tunnel face after blasting.
Further, the image acquisition module acquires a tunnel face image after tunnel blasting and transmits the tunnel face image to the first construction module and the second construction module. Specifically, the image acquisition module transmits the palm surface image to the palm surface image data module and the palm surface target image data module.
Further, the first building module is used for building an identification model of the under-cut region of the tunnel face image after blasting by the drilling and blasting method based on the deep learning and image semantic segmentation principle according to the built sample database of the image of the tunnel face after blasting.
In some alternative embodiments, the first building block is specifically configured to: distinguishing a face overbreak area and a background area by marking an original image, and establishing a blasting face image sample database on the basis of a large number of blasting face images; and constructing an ultra-underproduction area identification model of the tunnel face image after blasting by the drilling and blasting method based on the deep learning and semantic segmentation principle according to the established sample database of the image of the tunnel face after blasting.
Specifically, the first building module comprises a face image data module and a face super-undermining area identification module. The face image data module receives the face images transmitted by the image acquisition module, establishes a face image database, and transmits the face images to the face super-undermining area identification module. The face super-under-digging area recognition module receives the face images, recognizes face areas and background areas in the face images based on an image semantic segmentation principle, conducts deep learning model training on a large number of face images based on a large number of face images, and establishes a face super-under-digging area recognition model.
Furthermore, the second building module is used for building a recognition model of the target area on the tunnel face image of the drilling and blasting method based on deep learning and semantic segmentation principles according to the built database of the target image sample on the tunnel face.
In some optional embodiments, the building block two is specifically configured to: distinguishing a target area and a background area by marking an original image, and establishing a target image sample database on a palm surface on the basis of a large number of target images on the palm surface; and constructing a target area recognition model on the tunnel face image of the drilling and blasting method based on the deep learning and image semantic segmentation principle according to the established target image sample database on the face.
Specifically, the second building module comprises a palm surface target image data module and a palm surface target area identification module. The palm surface target image data module receives the palm surface images transmitted by the image acquisition module, establishes a palm surface target image database and transmits the palm surface target images to the palm surface target area identification module. The face target area recognition module receives the face target image, recognizes a target area and a background area in the face target image based on an image semantic segmentation principle, and performs deep learning on a large number of face target images based on a large number of face target images to establish a face target area recognition model.
Further, the analysis processing module obtains a face overbreak area identification model of the first building module and a face target area identification model of the second building module, and analyzes the overbreak amount of the tunnel face after blasting according to the identification result of the face overbreak area identification module on the face image and the identification result of the face target area identification module on the face target image and the pixel length of the target and the position of the target under a tunnel coordinate system.
In some optional embodiments, the analysis processing module is specifically configured to: according to the face overbreak and undermine recognition model and the target area recognition model, acquiring an overbreak and undermine area and a target area on the image; obtaining the coordinates of the area under the tunnel coordinate system and the area where the target is located through the pixel length of the target and the position of the target under the tunnel coordinate system based on the area under the tunnel and the area where the target is located on the image; and comparing and analyzing the coordinates of the overburdened area and the area where the target is located based on the tunnel coordinate system with the tunnel blasting design contour line to obtain the overburdened amount of the tunnel face after blasting.
Referring to fig. 7, a schematic structural diagram of an electronic device suitable for use in implementing embodiments of the present disclosure is shown. The electronic devices in the embodiments of the present disclosure may include, but are not limited to, mobile terminals such as mobile phones, notebook computers, digital broadcast receivers, PDAs (personal digital assistants), PADs (tablet computers), PMPs (portable multimedia players), in-vehicle terminals (e.g., car navigation terminals), and the like, and fixed terminals such as digital TVs, desktop computers, and the like. The electronic device shown in fig. 7 is only an example, and should not bring any limitation to the functions and the scope of use of the embodiments of the present disclosure.
As shown in fig. 7, the electronic device may include a processing means (e.g., a central processing unit, a graphic processor, etc.) 901, which may perform various appropriate actions and processes according to a program stored in a Read Only Memory (ROM) 902 or a program loaded from a storage means 908 into a Random Access Memory (RAM) 903. In the RAM 903, various programs and data necessary for the operation of the electronic apparatus 900 are also stored. The processing apparatus 901, ROM 902, and RAM 903 are connected to each other via a bus 904. An input/output (I/O) interface 905 is also connected to bus 904.
Generally, the following devices may be connected to the I/O interface 905: input devices 906 including, for example, a touch screen, touch pad, keyboard, mouse, camera, microphone, accelerometer, gyroscope, etc.; an output device 907 including, for example, a Liquid Crystal Display (LCD), a speaker, a vibrator, and the like; storage 908 including, for example, magnetic tape, hard disk, etc.; and a communication device 909. The communication means 909 may allow the electronic device to perform wireless or wired communication with other devices to exchange data. While fig. 7 illustrates an electronic device having various means, it is to be understood that not all illustrated means are required to be implemented or provided. More or fewer devices may alternatively be implemented or provided.
In particular, according to an embodiment of the present disclosure, the processes described above with reference to the flowcharts may be implemented as computer software programs. For example, embodiments of the present disclosure include a computer program product comprising a computer program carried on a non-transitory computer readable medium, the computer program containing program code for performing the method illustrated by the flow chart. In such an embodiment, the computer program may be downloaded and installed from a network through the communication device 909, or installed from the storage device 908, or installed from the ROM 902. The computer program performs the above-described functions defined in the methods of the embodiments of the present disclosure when executed by the processing apparatus 901.
It should be noted that the computer readable medium of the present disclosure can be a computer readable signal medium or a computer readable storage medium or any combination of the two. A computer readable storage medium may be, for example, but not limited to, an electronic, magnetic, optical, electromagnetic, infrared, or semiconductor system, apparatus, or device, or any combination of the foregoing. More specific examples of the computer readable storage medium may include, but are not limited to: an electrical connection having 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 portable compact disc read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination of the foregoing. In the present disclosure, a computer readable storage medium may be any tangible medium that can contain, or store a program for use by or in connection with an instruction execution system, apparatus, or device. In contrast, in the present disclosure, a computer readable signal medium may comprise a propagated data signal with computer readable program code embodied therein, either in baseband or as part of a carrier wave. Such a propagated data signal may take any of a variety of forms, including, but not limited to, electro-magnetic, optical, or any suitable combination thereof. A computer readable signal medium may also be any computer readable medium that is not a computer readable storage medium and that can communicate, propagate, or transport a program for use by or in connection with an instruction execution system, apparatus, or device. Program code embodied on a computer readable medium may be transmitted using any appropriate medium, including but not limited to: electrical wires, optical cables, RF (radio frequency), etc., or any suitable combination of the foregoing.
In some embodiments, the clients, servers may communicate using any currently known or future developed network Protocol, such as HTTP (HyperText Transfer Protocol), and may be interconnected with any form or medium of digital data communication (e.g., a communication network). Examples of communication networks include a local area network ("LAN"), a wide area network ("WAN"), the Internet (e.g., the Internet), and peer-to-peer networks (e.g., ad hoc peer-to-peer networks), as well as any currently known or future developed network.
The computer readable medium may be embodied in the electronic device; or may exist separately without being assembled into the electronic device.
The computer readable medium carries one or more programs which, when executed by the electronic device, cause the electronic device to: according to the established sample database of the blasted tunnel face image, constructing an ultra-short excavation region identification model of the blasted tunnel face image by the drilling and blasting method based on the deep learning and semantic segmentation principles; constructing a target area recognition model on a tunnel face image of a drilling and blasting method based on deep learning and semantic segmentation principles according to the established target image sample database on the face; and identifying the overbreak and underbreak amount of the tunnel face after blasting through the pixel length of the target and the position of the target under a tunnel coordinate system based on the overbreak and underbreak area identification model of the tunnel face image after blasting of the tunnel by the drilling and blasting method and the target area identification model on the tunnel face image by the drilling and blasting method.
Computer program code for carrying out operations for the present disclosure may be written in any combination of one or more programming languages, including but not limited to an object oriented programming language such as Java, smalltalk, C + +, and conventional procedural programming languages, such as the "C" programming language or similar programming languages. The program code may execute entirely on the user's computer, partly on the user's computer, as a stand-alone software package, partly on the user's computer and partly on a remote computer or entirely on the remote computer or server. In the case of a remote computer, the remote computer may be connected to the user's computer through any type of network, including a Local Area Network (LAN) or a Wide Area Network (WAN), or the connection may be made to an external computer (for example, through the Internet using an Internet service provider).
The flowchart and block diagrams in the figures illustrate the architecture, functionality, and operation of possible implementations of systems, methods and computer program products according to various embodiments of the present disclosure. 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 some 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.
The units described in the embodiments of the present disclosure may be implemented by software or hardware. The name of the unit does not form a limitation on the unit per se under certain conditions, for example, the first building module may also be described as a unit for building an identification model of the super-undermined area of the tunnel face image after the tunnel blasting by the drilling and blasting method based on the deep learning and semantic segmentation principles according to the built sample database of the tunnel face image after the blasting.
The functions described herein above may be performed, at least in part, by one or more hardware logic components. For example, without limitation, exemplary types of hardware logic components that may be used include: field Programmable Gate Arrays (FPGAs), application Specific Integrated Circuits (ASICs), application Specific Standard Products (ASSPs), systems on a chip (SOCs), complex Programmable Logic Devices (CPLDs), and the like.
In the context of this disclosure, a machine-readable medium may be a tangible medium that can contain, or store a program for use by or in connection with an instruction execution system, apparatus, or device. The machine-readable medium may be a machine-readable signal medium or a machine-readable storage medium. A machine-readable 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. 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.
The foregoing description is only exemplary of the preferred embodiments of the disclosure and is illustrative of the principles of the technology employed. It will be appreciated by those skilled in the art that the scope of the disclosure herein is not limited to the particular combination of features described above, but also encompasses other embodiments in which any combination of the features described above or their equivalents does not depart from the spirit of the disclosure. For example, the above features and (but not limited to) the features disclosed in this disclosure having similar functions are replaced with each other to form the technical solution.
Further, while operations are depicted in a particular order, this should not be understood as requiring that such operations be performed in the particular order shown or in sequential order. Under certain circumstances, multitasking and parallel processing may be advantageous. Likewise, while several specific implementation details are included in the above discussion, these should not be construed as limitations on the scope of the disclosure. Certain features that are described in the context of separate embodiments can also be implemented in combination in a single embodiment. Conversely, various features that are described in the context of a single embodiment can also be implemented in multiple embodiments separately or in any suitable subcombination.
Although the subject matter has been described in language specific to structural features and/or methodological acts, it is to be understood that the subject matter defined in the appended claims is not necessarily limited to the specific features or acts described above. Rather, the specific features and acts described above are disclosed as example forms of implementing the claims.
The above-described embodiments are merely illustrative of the preferred embodiments of the present invention, and do not limit the scope of the present invention, and various changes, modifications, alterations, and substitutions which may be made by those skilled in the art without departing from the spirit of the present invention shall fall within the protection scope defined by the claims of the present invention.
Claims (10)
1. The image identification method for the face overbreak and undermining after the tunnel blasting by the drilling and blasting method is characterized by comprising the following steps of: identifying a face overbreak area and a background area of the face image based on a semantic segmentation algorithm principle in image identification according to an established database of the blasted face image; identifying a target area and a background area of the palm surface target image based on a semantic segmentation algorithm principle in image identification according to the established palm surface target image database; and finally, comparing and analyzing the coordinates of the face overburdened area under the tunnel coordinate system with the tunnel blasting design contour line to obtain the overburdened amount of the face after tunnel blasting.
2. The image recognition method for face overbreak after blasting of a drill-blast tunnel according to claim 1, characterized in that: comprises the following steps of (a) carrying out,
step 101: acquiring a large number of blasted face image samples, establishing a face image sample database, performing deep learning on the face images, and establishing an ultra-underpolished area identification model of the tunnel blasted face images;
step 102: acquiring a large number of blasted tunnel face target image samples, establishing a tunnel face target image sample database, performing deep learning on the tunnel face target image, and establishing a tunnel face target area identification model;
step 103: and identifying the overbreak and underbreak amount of the tunnel face of the tunnel after blasting based on the recognition model of the overbreak and underbreak area of the tunnel face and the recognition model of the target area of the tunnel face.
3. The image recognition method for face overbreak after blasting in a drilling and blasting tunnel according to claim 2, characterized in that: said step 101 comprises the steps of,
step 1011: by marking the original image of the blasted face, dividing the original image of the blasted face into a face ultra-short excavation area and a background area, and establishing a sample database of the blasted face image;
step 1012: and according to the established post-blasting face image sample database, performing deep learning on the face image sample, and establishing an ultra-short excavation identification model of the tunnel post-blasting face image.
4. The image recognition method for face overbreak after blasting in a drilling and blasting tunnel according to claim 2, characterized in that: said step 102 comprises the steps of,
step 1021: dividing the blasted face original image into a target area and a background area by marking the blasted face original image, and establishing a target image sample database on the face;
step 1022: and according to the established database of the target image samples on the tunnel face after blasting, performing deep learning on the target image samples on the tunnel face, and establishing a target area identification model on the tunnel face by a drilling and blasting method.
5. The image recognition method for face overbreak after blasting in a drilling and blasting tunnel according to claim 2, characterized in that: said step 103 comprises the steps of,
step 1031: according to the face super-under-cut area identification model and the target area identification model, obtaining a super-under-cut area and a target area on the face image;
step 1032: obtaining the coordinates of the overburdened area and the area where the target is located under a tunnel coordinate system based on the overburdened area and the area where the target is located on the tunnel face image;
step 1033: and comparing and analyzing the coordinates of the overburdened area and the area where the target is located based on the tunnel coordinate system with the tunnel blasting design contour line to obtain the overburdened amount of the tunnel face after blasting.
6. Image identification device that face surpassed owed and dug behind drilling and blasting method tunnel blasting, its characterized in that: the system comprises an image acquisition module, a construction module I, a construction module II and an analysis processing module;
the image acquisition module acquires a tunnel face image after tunnel blasting and transmits the tunnel face image to the first construction module and the second construction module;
the construction module I constructs an identification model of the overbreak area of the tunnel face image after blasting of the tunnel by a drilling and blasting method according to the constructed sample database of the image of the tunnel face after blasting;
the second construction module is used for constructing a target area recognition model on the tunnel face image of the drilling and blasting method according to the established target image sample database on the tunnel face;
and the analysis processing module analyzes the overbreak and underbreak amount of the tunnel face after blasting based on the identification result of the pair of face images of the construction module and the identification result of the pair of face target images of the construction module.
7. The image recognition device of the face overbreak after the drill-blast tunnel blasting according to claim 6, wherein: the first construction module comprises a face image data module and a face ultra-short digging area identification module;
the palm surface image data module receives the palm surface images transmitted by the image acquisition module, establishes a palm surface image database and transmits the palm surface images to the palm surface ultra-short excavation region identification module;
the face super-under-excavation identification module receives the face image, identifies a face super-under-excavation area and a background area in the face image, performs deep learning on the face image, and establishes a face super-under-excavation area identification model.
8. The image recognition device of the face overbreak after the drill-blast tunnel blasting according to claim 6, wherein: the second construction module comprises a palm surface target image data module and a palm surface target area identification module;
the palm surface target image data module receives the palm surface image transmitted by the image acquisition module, establishes a palm surface target image database and transmits the palm surface target image to the palm surface target area identification module;
the face target area identification module receives the face target image, identifies a target area and a background area in the face target image, performs deep learning on the face target image, and establishes a face target area identification model.
9. An electronic device, characterized in that: the method comprises the following steps:
one or more processors;
storage means for storing one or more programs;
when executed by the one or more processors, cause the one or more processors to implement the method of any one of claims 1-5.
10. A computer readable medium, said readable medium storing a computer program, characterized in that: the computer program, when executed by a processor, implementing the method as claimed in any one of claims 1-5.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202211411948.7A CN115690689A (en) | 2022-11-11 | 2022-11-11 | Image identification method and device for tunnel face overbreak after blasting by drilling and blasting method |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202211411948.7A CN115690689A (en) | 2022-11-11 | 2022-11-11 | Image identification method and device for tunnel face overbreak after blasting by drilling and blasting method |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN115690689A true CN115690689A (en) | 2023-02-03 |
Family
ID=85051710
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202211411948.7A Pending CN115690689A (en) | 2022-11-11 | 2022-11-11 | Image identification method and device for tunnel face overbreak after blasting by drilling and blasting method |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN115690689A (en) |
-
2022
- 2022-11-11 CN CN202211411948.7A patent/CN115690689A/en active Pending
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN111950555B (en) | Text recognition method and device, readable medium and electronic equipment | |
| CN110826549A (en) | Inspection robot instrument image identification method and system based on computer vision | |
| CN115690688A (en) | Blast hole target detection method and device for blast hole image of tunnel face of drilling and blasting method | |
| JP7273129B2 (en) | Lane detection method, device, electronic device, storage medium and vehicle | |
| US20230091252A1 (en) | Method for processing high-definition map data, electronic device and medium | |
| CN111292420A (en) | Method and device for constructing map | |
| CN115616937A (en) | Automatic driving simulation test method, device, equipment and computer readable medium | |
| US10571446B2 (en) | Data quality control using a correlated sensor group | |
| CN114387410B (en) | Road data fusion map generation method and device and electronic equipment | |
| US20240037349A1 (en) | Model training method and apparatus, machine translation method and apparatus, and device and storage medium | |
| CN113592033B (en) | Oil tank image recognition model training method, oil tank image recognition method and device | |
| CN115359308A (en) | Model training method, apparatus, device, storage medium, and program for identifying difficult cases | |
| CN116934769A (en) | Interactive segmentation model training method, annotation data generation method and equipment | |
| CN114596431A (en) | Information determination method and device and electronic equipment | |
| CN112712795B (en) | Labeling data determining method, labeling data determining device, labeling data determining medium and electronic equipment | |
| CN115690689A (en) | Image identification method and device for tunnel face overbreak after blasting by drilling and blasting method | |
| CN110348369B (en) | Video scene classification method and device, mobile terminal and storage medium | |
| CN111368668A (en) | Three-dimensional hand recognition method and device, electronic equipment and storage medium | |
| CN116248991A (en) | Camera position adjustment method, camera position adjustment device, electronic equipment and computer readable medium | |
| CN110348374B (en) | Vehicle detection method and device, electronic equipment and storage medium | |
| CN114155545A (en) | Form identification method and device, readable medium and electronic equipment | |
| CN112685996B (en) | Text punctuation prediction method and device, readable medium and electronic equipment | |
| CN114565170A (en) | Pollutant tracing method and device, equipment, medium and product | |
| CN111445499B (en) | Method and device for identifying target information | |
| CN114758342A (en) | Text recognition method, device, medium and electronic equipment |
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 |