Drilling and blasting tunnel face hole image hole target detection method and device

Abstract

The present application belongs to the field of tunnel engineering, and particularly relates to a blast hole target detection method and device for a drill-and-blast tunnel face blast hole image. The specific technical solution is as follows: according to a post-drilling tunnel face image database, a tunnel post-drilling tunnel face region recognition model and a tunnel face blast hole target detection model are constructed; first, the tunnel post-drilling tunnel face region recognition model is used to recognize the tunnel face region, and then the recognition result is applied to the tunnel face blast hole target detection model, so as to intelligently recognize the blast hole in the tunnel face region. This method reduces the influence of objects outside the tunnel face region on blast hole recognition, improves the accuracy of the tunnel face blast hole recognition result, and greatly reduces the workload of workers compared with the method of manually counting the tunnel face blast holes.

Description

Technical Field

[0001] This invention belongs to the field of tunnel engineering, specifically relating to a method and apparatus for detecting blast hole targets in images of blast holes at the tunnel face using the drill-and-blast method. Background Technology

[0002] During tunnel excavation, the drill-and-blast method is primarily used for railway, highway, and subway tunnels due to its simplicity, flexibility, low cost, and wide applicability. The drill-and-blast process includes drilling, charging explosives, and blasting to excavate the rock. During drilling, hundreds of blast holes are typically drilled. Accurate acquisition and recording of blast hole parameters are crucial for subsequent analysis of the excavation effect after blasting and for optimizing blasting parameters.

[0003] Currently, there is no method for detecting borehole targets based on images of boreholes at the tunnel face. Image recognition research related to tunnels mainly focuses on detecting defects such as cracks and water leakage in tunnel lining concrete, and on the rapid identification of targets such as vehicles and personnel within the tunnel; research on methods for detecting borehole targets based on images of boreholes at the tunnel face has not yet been conducted.

[0004] Therefore, the detection and analysis of blast hole images at the tunnel face in the drill-and-blast method is very important in the tunnel excavation process. If a convenient, fast, and accurate method for detecting and analyzing blast hole images at the tunnel face in the drill-and-blast method can be provided, it will have excellent industrial application value. Summary of the Invention

[0005] To address the aforementioned technical problems, the purpose of this invention is to provide a method and apparatus for detecting borehole targets in borehole images from the tunnel face using the drill-and-blast method.

[0006] To achieve the above-mentioned objectives, the technical solution adopted by this invention is: a method for detecting blast hole targets in images of blast holes at the tunnel face using the drill-and-blast method. Based on a database of images of the tunnel face after drilling, a region recognition model for the tunnel face after drilling and a blast hole target detection model for the tunnel face are constructed. First, the region recognition model for the tunnel face after drilling is used to identify the tunnel face region, and then the identification results are applied to the blast hole target detection model for the tunnel face, thereby intelligently identifying blast holes within the tunnel face region.

[0007] Preferred: Includes the following steps,

[0008] Step 101: Acquire a large number of images of the tunnel face after drilling, establish a database of images of the tunnel face after drilling, and construct a region recognition model of the tunnel face after drilling based on the semantic segmentation algorithm principle in image recognition.

[0009] Step 102: Based on the image database of the borehole face after drilling, and based on the target detection algorithm principle in image recognition, construct a target detection model for blast holes at the tunnel face;

[0010] Step 103: First, use the tunnel face area recognition model after drilling to identify the tunnel face area, and then apply the recognition results to the tunnel face blast hole target detection model to intelligently identify blast holes in the tunnel face area.

[0011] Preferably, step 101 includes:

[0012] Step 1011: Obtain a large number of drilling face images, use Labelme software to label the face area and background area in the images, obtain JSON label files for the face area and background area, and establish the original training dataset of face images.

[0013] Step 1012: Based on the semantic segmentation algorithm principle in image recognition, train the model on the original training dataset of tunnel face images to construct a tunnel face region recognition model after drilling, which is used to identify the tunnel face region and background region in the tunnel face image after drilling.

[0014] Preferably, step 102 includes:

[0015] Step 1021: Obtain a large number of borehole face images. First, crop the borehole face images into images of a fixed size. Then, use Labelimg software to label the borehole targets on the face images to obtain the borehole target XML tag file and establish the original training dataset of borehole images on the face.

[0016] Step 1022: Based on the target detection algorithm principle in image recognition, train the model on the original training dataset of tunnel face blast hole images to construct a tunnel face blast hole target detection model, which is used to detect blast hole targets on the tunnel face images after drilling.

[0017] Correspondingly: a target detection device for borehole images of tunnel face using the drill-and-blast method, including an image acquisition module, a construction module one, a construction module two, and an analysis and processing module;

[0018] The image acquisition module acquires images of the tunnel face after drilling and transmits these images to Construction Module 1 and Construction Module 2.

[0019] The first construction module constructs a face region recognition model for the face images after drilling in the drill-blast method tunnel based on the established sample database of drilling face images.

[0020] The second construction module constructs a target detection model for blast holes on the drilling face images after drilling in the drill-blast method, based on the established database of drilling face image samples.

[0021] The analysis and processing module first uses the tunnel face area recognition model after drilling to identify the tunnel face area, and then applies the identification results to the tunnel face blast hole target detection model, thereby intelligently identifying blast holes in the tunnel face area.

[0022] Preferably, the first construction module includes a face borehole image data module and a face region recognition module;

[0023] The face borehole image data module acquires a large number of face borehole images, establishes a raw database of face borehole images, and transmits the face borehole images to the face region recognition module.

[0024] The tunnel face region recognition module performs deep learning training on the established post-drilling tunnel face dataset to establish a tunnel face region recognition model.

[0025] Preferably, the second construction module includes a face borehole image data module and a face borehole recognition module;

[0026] The face borehole image data module acquires a large number of face borehole images, establishes a raw database of face borehole images, and transmits the face borehole images to the face borehole recognition module.

[0027] The tunnel face blast hole recognition module performs deep learning training on the cropped and labeled tunnel face blast hole image dataset to establish an intelligent recognition model for tunnel face blast hole images.

[0028] Correspondingly: an electronic device, comprising:

[0029] One or more processors;

[0030] Storage device for storing one or more programs;

[0031] When the one or more programs are executed by the one or more processors, the one or more processors implement a method for detecting borehole targets in images of boreholes at the tunnel face using the drill-and-blast method.

[0032] Correspondingly: a computer-readable medium storing a computer program that, when executed by a processor, implements a method for detecting borehole targets in borehole images of a tunnel face using the drill-and-blast method.

[0033] Compared with the prior art, the present invention has the following beneficial effects:

[0034] Based on the established database of borehole face images, and using the semantic segmentation algorithm principle in image recognition, a region recognition model for the borehole face in tunnels is constructed. Similarly, based on the same database, a target detection model for blast holes in tunnel faces is constructed using the target detection algorithm principle in image recognition. First, the region recognition model identifies the tunnel face region; then, the identified results are applied to the blast hole target detection model, thereby intelligently identifying blast holes within the face region. This method reduces the influence of objects outside the tunnel face region on blast hole identification, improves the accuracy of blast hole identification results, and solves the technical problem of low accuracy in blast hole identification using traditional image recognition methods. Furthermore, this method pioneers a new "intelligent, efficient, minimally manned, and unmanned" blast hole target detection mode for borehole images in drill-and-blast tunnels, possessing a high degree of intelligence not found in traditional methods. Attached Figure Description

[0035] Figure 1 This is a flowchart of the borehole target detection method for the borehole image of the tunnel face in the drilling and blasting method of the present invention;

[0036] Figure 2 This is a schematic diagram showing the tunnel face area after drilling according to the present invention (the area enclosed by the dots and lines in the diagram is the tunnel face area);

[0037] Figure 3 This is a schematic diagram of the image recognition results of the area where the tunnel face is located after drilling according to the present invention;

[0038] Figure 4 This is a schematic diagram of the cropping result of the blast hole image at the tunnel face according to the present invention;

[0039] Figure 5 This is a schematic diagram of the annotation of blast holes after cropping the image of the blast hole at the tunnel face according to the present invention;

[0040] Figure 6 This is a schematic diagram of using the tunnel face area identification results for borehole detection;

[0041] Figure 7 This is a schematic diagram of the present invention merging the result image of borehole detection with the original image;

[0042] Figure 8 This is a schematic diagram of the basic structure of the electronic device of the present invention. Detailed Implementation

[0043] The technical solutions of the embodiments of the present invention will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some embodiments of the present invention, and not all embodiments. Unless otherwise specified, the technical means used in the embodiments are conventional means well known to those skilled in the art.

[0044] This application discloses a method for detecting blast hole targets in images of blast holes at the tunnel face using the drill-and-blast method. The core idea is as follows: Based on an established database of images of the tunnel face after drilling, a region recognition model for the tunnel face after drilling is constructed using the semantic segmentation algorithm principle in image recognition. Based on the established database of images of the tunnel face after drilling, a target detection model for blast holes at the tunnel face is constructed using the target detection algorithm principle in image recognition. First, the tunnel face region recognition model is used to identify the tunnel face region, and then the identified results are applied to the blast hole target detection model at the tunnel face, thereby intelligently identifying blast holes within the tunnel face region.

[0045] Please see Figure 1 The method for detecting borehole targets in images of boreholes at the tunnel face using the drill-and-blast method includes the following steps:

[0046] Step 101: Obtain a large number of images of the tunnel face after drilling, establish a database of images of the tunnel face after drilling, and perform deep learning on the database of images of the tunnel face after drilling based on the principle of semantic segmentation algorithm in image recognition to construct a region recognition model of the tunnel face after drilling.

[0047] Specifically, step 101 includes the following steps:

[0048] Step 1011: Obtain a large number of post-drilling face images, and use Labelme software to label the face and background regions in the images, obtaining JSON label files for the face and background regions, thereby establishing the original training dataset for the face images. See the schematic diagram of the labeling of the post-drilling face region of the tunnel. Figure 2 .

[0049] Step 1012: Based on the semantic segmentation algorithm principle in image recognition, a deep learning model is trained on the established original training dataset of tunnel face images to construct a tunnel face region recognition model after drilling, used to identify the tunnel face region and background region in the tunnel face image after drilling. A schematic diagram of the image recognition results for the region where the tunnel face is located after drilling is shown below. Figure 3 .

[0050] Specifically, in one implementation of establishing a tunnel face region identification model after drilling, step 1012 includes the following steps:

[0051] Step 1012.1: Construct a deep learning network framework for semantic segmentation of the drilling face image after drilling;

[0052] Step 1012.2: Optimize the network parameters of Step 1012.1. Train the network weight parameters of Step 1012.1 using the drilling face image training dataset from Step 1011 until the total loss no longer decreases, obtaining the model parameters with the minimum test error. Optimizing Step 1012.1 can involve changing one or more of the following: changing the model learning rate, changing the backbone feature extraction network, or changing the loss function calculation method.

[0053] Step 1012.3: Based on the network framework of Step 1012.1 and the final network training parameters of Step 1012.2, establish a tunnel face region recognition model after drilling.

[0054] Step 102: Based on the established image database of the borehole face after drilling, and based on the target detection algorithm principle in image recognition, perform deep learning on the image database of the borehole face after drilling to construct a target detection model for the blast holes at the tunnel face.

[0055] Specifically, step 102 includes the following steps:

[0056] Step 1021: Obtain a large number of post-drilling face images. First, crop the post-drilling face images into images of a fixed size. Then, use Labelimg software to label the blast hole targets on the face in the fixed-size images, obtaining their XML tag files, and thus establishing the original training dataset of tunnel face blast hole images. A schematic diagram of the tunnel face blast hole image cropping result is shown below. Figure 4 As shown in the diagram, this is a cropped and annotated image of the blast hole at the tunnel face. Figure 5 As shown.

[0057] Step 1022: Based on the target detection algorithm principle in image recognition, a deep learning model is trained on the established image dataset to construct a target detection model for blast holes at the tunnel face, which is used to detect blast hole targets on the tunnel face image after drilling.

[0058] Specifically, in one implementation of establishing an intelligent recognition model for the image region of a tunnel face using the drill-and-blast method, step 1022 includes the following steps:

[0059] Step 1022.1: Build the network framework for a deep learning-based target detection model for blast holes at the tunnel face;

[0060] Step 1022.2: Optimize the network parameters from Step 1022.1. Train the network weight parameters from Step 1022.1 using the final training dataset of tunnel face images from Step 1021 until the total loss no longer decreases, obtaining the model parameters with the minimum test error. Optimizing Step 1022.1 can involve changing the model learning rate, changing the network pre-training weights, changing the loss function calculation method, or adding an attention mechanism, among other things.

[0061] Step 1022.3: Based on the network framework in Step 1022.1 and the final network training parameters in Step 1022.2, establish a target detection model for blast holes at the tunnel face.

[0062] Step 103: First, use the tunnel face area recognition model to identify the tunnel face area image, and then use the tunnel face blast hole target detection model to intelligently identify the blast holes in the tunnel face area in the recognition result.

[0063] Specifically, the area where the tunnel face is processed in step 101 is segmented, and the segmentation result is input into the tunnel face image blast hole intelligent recognition model. Then, the blast hole detection result image is fused with the original image to finally obtain the blast hole detection image of the tunnel face area in the detection image. A schematic diagram of blast hole detection using the tunnel face area recognition result is shown below. Figure 6 As shown in the diagram, the result image of the borehole detection is then merged with the original image. Figure 7 As shown.

[0064] As the tunnel continues to be excavated, the location and number of blast holes will change continuously as the blasting parameters are adjusted. This method can be used to detect the blast holes on the tunnel face in each cycle, thereby optimizing the blasting parameters and improving the blasting effect.

[0065] This method for detecting blast hole targets in drill-and-blast tunnel face images is based on an established database of post-drilling face images. It constructs a region recognition model for the tunnel face based on semantic segmentation algorithms in image recognition. Then, it constructs a target detection model for blast holes within the same database. The method first identifies the face region using the post-drilling face image recognition model, and then applies this identification result to the blast hole target detection model, thereby intelligently identifying blast holes within the face region. This method reduces the influence of objects outside the tunnel face region on blast hole identification, improves the accuracy of blast hole identification results, and solves the technical problem of low accuracy in traditional image recognition methods for tunnel face blast hole identification. Furthermore, this method pioneers a new "intelligent, efficient, and less-manned" mode for blast hole target detection in drill-and-blast tunnel face images, possessing a high degree of intelligence not found in traditional methods.

[0066] Furthermore, as an implementation of the method described above, this invention discloses a borehole target detection device for borehole images of tunnel face using the drill-and-blast method. The embodiment of this device is similar to... Figure 1 Corresponding to the method embodiments shown, this device can be specifically applied to various electronic devices.

[0067] This application also discloses a borehole target detection device for borehole images of the tunnel face using the drill-and-blast method, comprising: an image acquisition module, a construction module one, a construction module two, and an analysis and processing module. During operation, the image acquisition module acquires images of the tunnel face after drilling and transmits these images to construction modules one and two for construction. Construction module one receives the images of the tunnel face after drilling and constructs a region recognition model of the tunnel face after drilling, thereby identifying the tunnel face region in the image. Construction module two receives the images of the tunnel face after drilling and constructs a borehole target detection model of the tunnel face after drilling, thereby detecting the borehole targets in the image. The analysis and processing module first inputs the image to be detected into the region recognition model of the tunnel face after drilling, and then inputs the recognition result into the borehole target detection model of the tunnel face after drilling, finally obtaining a detected image of the borehole targets within the tunnel face region of the image.

[0068] Furthermore, the image acquisition module is used to acquire images of the drilling face after drilling and transmit the images of the drilling face to construction module one and construction module two.

[0069] Furthermore, the first construction module includes a face borehole image data module and a face region recognition module; the face borehole image data module acquires a large number of face borehole images, establishes a raw face borehole image database, and transmits the face borehole images to the face region recognition module; the face region recognition module performs deep learning training on the established post-drilling face dataset to establish a tunnel face region recognition model.

[0070] Furthermore, the second construction module includes a tunnel face blast hole image data module and a tunnel face blast hole recognition module. The tunnel face blast hole image data module acquires a large number of tunnel face blast hole images, establishes a raw database of tunnel face blast hole images, and transmits the tunnel face blast hole images to the tunnel face blast hole recognition module. The tunnel face blast hole recognition module performs deep learning training on the cropped and labeled tunnel face blast hole image dataset to establish an intelligent recognition model for tunnel face blast hole images.

[0071] Furthermore, the analysis and processing module first uses the tunnel face area recognition model after drilling to identify the face area, and then applies the identified face area image results to the tunnel face blast hole target detection model, thereby intelligently identifying blast holes in the face area.

[0072] In some optional implementations, the image acquisition module is specifically used to: acquire a large number of borehole face images, use Labelme software to label the face area and background area in the images, obtain their JSON tag files, and then establish the original training dataset of face images; acquire a large number of borehole face images, first crop the images into images of a fixed size, then use Labelme software to label the blast hole targets on the face of the images, obtain their XML tag files, and then establish the original training dataset of face blast hole images.

[0073] In some optional implementations, the construction module one is specifically used to: construct a face region recognition model for the face images of the borehole after drilling based on the established sample database of borehole face images.

[0074] In some optional implementations, the second construction module is specifically used to: construct a target detection model for blast holes on the drilling face images of the drilled tunnel using the drill-blast method, based on the established database of drilling face image samples.

[0075] In some optional implementations, the analysis and processing module is specifically used to: first identify the tunnel face region using the tunnel face region recognition model after drilling, and then apply the identified tunnel face region image results to the tunnel face blast hole target detection model, thereby intelligently identifying blast holes in the tunnel face region.

[0076] The following is for reference. Figure 8 The diagram illustrates a structural schematic of an electronic device suitable for implementing embodiments of the present disclosure. The electronic devices in the embodiments of the present disclosure may include, but are not limited to, mobile terminals such as mobile phones, laptops, digital broadcast receivers, PDAs (personal digital assistants), PADs (tablet computers), PMPs (portable multimedia players), in-vehicle terminals (e.g., in-vehicle navigation terminals), and fixed terminals such as digital TVs and desktop computers. Figure 8 The electronic device shown is merely an example and should not be construed as limiting the functionality and scope of the embodiments disclosed herein.

[0077] like Figure 8 As shown, the electronic device may include a processing unit (e.g., a central processing unit, a graphics processing unit, etc.) 901, which can 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 device 908 into a random access memory (RAM) 903. The RAM 903 also stores various programs and data required for the operation of the electronic device 900. The processing unit 901, ROM 902, and RAM 903 are interconnected via a bus 904. An input / output (I / O) interface 905 is also connected to the bus 904.

[0078] Typically, the following devices can be connected to I / O interface 905: input devices 906 including, for example, touchscreens, touchpads, keyboards, mice, cameras, microphones, accelerometers, gyroscopes, etc.; output devices 907 including, for example, liquid crystal displays (LCDs), speakers, vibrators, etc.; storage devices 908 including, for example, magnetic tapes, hard disks, etc.; and communication devices 909. Communication device 909 allows electronic devices to communicate wirelessly or wiredly with other devices to exchange data. Although Figure 8 Electronic devices with various devices are shown, but it should be understood that it is not required to implement or have all of the devices shown. More or fewer devices may be implemented or have alternatively.

[0079] In particular, according to embodiments of this disclosure, the processes described above with reference to the flowcharts can be implemented as computer software programs. For example, embodiments of this 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 methods shown in the flowcharts. In such embodiments, the computer program can be downloaded and installed from a network via communication device 909, or installed from storage device 908, or installed from ROM 6902. When the computer program is executed by processing device 901, it performs the functions defined in the methods of embodiments of this disclosure.

[0080] It should be noted that the computer-readable medium of this disclosure may be a computer-readable signal medium or a computer-readable storage medium, or any combination thereof. A computer-readable storage medium may be, for example,—but not limited to—an electrical, magnetic, optical, electromagnetic, infrared, or semiconductor system, apparatus, or device, or any combination thereof. More specific examples of a computer-readable storage medium may include, but are not limited to: an electrical connection having one or more wires, a portable computer disk, a hard disk, random access memory (RAM), read-only memory (ROM), erasable programmable read-only memory (EPROM or flash memory), optical fiber, portable compact disk read-only memory (CD-ROM), optical storage device, magnetic storage device, or any suitable combination thereof. In this disclosure, a computer-readable storage medium may be any tangible medium containing or storing a program that can be used by or in conjunction with an instruction execution system, apparatus, or device. In this disclosure, a computer-readable signal medium may include a data signal propagated in baseband or as part of a carrier wave, carrying computer-readable program code. Such propagated data signals may take various forms, including but not limited to electromagnetic signals, optical signals, or any suitable combination thereof. A computer-readable signal medium can be any computer-readable medium other than a computer-readable storage medium, which can send, propagate, or transmit a program for use by or in connection with an instruction execution system, apparatus, or device. The program code contained on the computer-readable medium can be transmitted using any suitable medium, including but not limited to: wires, optical fibers, RF (radio frequency), etc., or any suitable combination thereof.

[0081] In some implementations, clients and servers can communicate using any currently known or future-developed network protocol such as HTTP (Hypertext Transfer Protocol) and can interconnect with digital data communication (e.g., communication networks) of any form or medium. Examples of communication networks include local area networks (“LANs”), wide area networks (“WANs”), the Internet (e.g., the Internet of Things), and peer-to-peer networks (e.g., ad hoc peer-to-peer networks), as well as any currently known or future-developed networks.

[0082] The aforementioned computer-readable medium may be included in the aforementioned electronic device; or it may exist independently and not assembled into the electronic device.

[0083] The aforementioned computer-readable medium carries one or more programs, which, when executed by the electronic device, cause the electronic device to: construct a tunnel borehole face region recognition model based on the established borehole face image database and the semantic segmentation algorithm principle in image recognition; construct a tunnel face blast hole target detection model based on the established borehole face image database and the target detection algorithm principle in image recognition; firstly, segment the face region using the tunnel borehole face region recognition model, and then apply the segmentation result to the tunnel face blast hole target detection model, thereby intelligently identifying blast holes within the face region.

[0084] Computer program code for performing the operations of this disclosure can be written in one or more programming languages ​​or a combination thereof, including but not limited to object-oriented programming languages ​​such as Java, Smalltalk, and C++, as well as conventional procedural programming languages ​​such as the "C" language or similar programming languages. The program code can be executed entirely on the user's computer, partially on the user's computer, as a standalone software package, partially on the user's computer and partially on a remote computer, or entirely on a remote computer or server. In cases involving remote computers, the remote computer can be connected to the user's computer via any type of network—including a local area network (LAN) or a wide area network (WAN)—or can be connected to an external computer (e.g., via the Internet using an Internet service provider).

[0085] The flowcharts and block diagrams in the accompanying drawings illustrate the architecture, functionality, and operation of possible implementations of systems, methods, and computer program products according to various embodiments of this disclosure. In this regard, each block in a flowchart or block diagram may represent a module, segment, or portion of code containing one or more executable instructions for implementing a specified logical function. It should also be noted that in some alternative implementations, the functions indicated in the blocks may occur in a different order than those indicated in the drawings. For example, two consecutively indicated blocks may actually be executed substantially in parallel, and they may sometimes be executed in reverse order, depending on the functions involved. It should also be noted that each block in the block diagrams and / or flowcharts, and combinations of blocks in the block diagrams and / or flowcharts, can be implemented using a dedicated hardware-based system that performs the specified function or operation, or using a combination of dedicated hardware and computer instructions.

[0086] The units described in the embodiments of this disclosure can be implemented in software or hardware. The names of the units are not necessarily limiting in certain circumstances; for example, module one can also be described as "a unit that constructs a model based on the acquisition results of tunnel face images after drilling and divides the face region of the images to be detected."

[0087] The functions described above in this document can be performed, at least in part, by one or more hardware logic components. For example, exemplary types of hardware logic components that can be used, without limitation, include: Field Programmable Gate Arrays (FPGAs), Application-Specific Integrated Circuits (ASICs), Application Standard Products (ASSPs), System-on-Chip (SoCs), Complex Programmable Logic Devices (CPLDs), and so on.

[0088] In the context of this disclosure, a machine-readable medium can be a tangible medium that may contain or store a program for use by or in conjunction with an instruction execution system, apparatus, or device. A machine-readable medium can be a machine-readable signal medium or a machine-readable storage medium. A machine-readable medium can be, but is not limited to, electronic, magnetic, optical, electromagnetic, infrared, or semiconductor systems, apparatus, or devices, or any suitable combination of the foregoing. More specific examples of machine-readable storage media include electrical connections based on one or more wires, portable computer disks, hard disks, random access memory (RAM), read-only memory (ROM), erasable programmable read-only memory (EPROM or flash memory), optical fiber, portable compact disk read-only memory (CD-ROM), optical storage devices, magnetic storage devices, or any suitable combination of the foregoing.

[0089] The above description is merely a preferred embodiment of this disclosure and an explanation of the technical principles employed. Those skilled in the art should understand that the scope of this disclosure is not limited to technical solutions formed by specific combinations of the above-described technical features, but should also cover other technical solutions formed by arbitrary combinations of the above-described technical features or their equivalents without departing from the above-described concept. For example, technical solutions formed by substituting the above features with (but not limited to) technical features disclosed in this disclosure that have similar functions.

[0090] Furthermore, while the operations are described in a specific order, this should not be construed as requiring these operations to be performed in the specific order shown or in a sequential order. In certain environments, multitasking and parallel processing may be advantageous. Similarly, while several specific implementation details are included in the above discussion, these should not be construed as limiting the scope of this disclosure. Certain features described in the context of individual embodiments may also be implemented in combination in a single embodiment. Conversely, various features described in the context of a single embodiment may also be implemented individually or in any suitable sub-combination in multiple embodiments.

[0091] Although the subject matter has been described using language specific to structural features and / or methodological logic, it should be understood that the subject matter defined in the appended claims is not necessarily limited to the specific features or actions described above. Rather, the specific features and actions described above are merely illustrative examples of implementing the claims.

[0092] The embodiments described above are merely preferred embodiments of the present invention and are not intended to limit the scope of the present invention. Any modifications, alterations, substitutions, or variations made by those skilled in the art to the technical solutions of the present invention without departing from the spirit of the present invention shall fall within the protection scope defined by the claims of the present invention.

Claims

1. A method for blasthole target detection of a drill and blast tunnel face blasthole image, characterized in that: According to the tunnel drilling face image database, a tunnel drilling face region recognition model and a tunnel drilling face blast hole target detection model are constructed; first, the tunnel drilling face region recognition model is used to recognize the drilling face region, and then the recognized result is applied to the tunnel drilling face blast hole target detection model, so as to intelligently recognize the blast hole in the drilling face region; comprising the following steps, Step 101: a large number of drilling face images after drilling are obtained, a drilling face image database after drilling is established, and a tunnel drilling face region recognition model is constructed based on the principle of semantic segmentation algorithm in image recognition; the step 101 comprises, Step 1011: a large number of drilling face images after drilling are obtained, the drilling face region and the background region in the image are labeled by using Labelme software, the json label file of the drilling face region and the background region is obtained, and a drilling face image original training data set is established; Step 1012: based on the principle of semantic segmentation algorithm in image recognition, the drilling face image original training data set is trained, a tunnel drilling face region recognition model is constructed, and the drilling face region and the background region of the drilling face image after drilling are recognized; Step 102: according to the tunnel drilling face image database, a tunnel drilling face blast hole target detection model is constructed based on the principle of target detection algorithm in image recognition; the step 102 comprises, Step 1021: a large number of drilling face images after drilling are obtained, the drilling face image after drilling is first cut into a picture with a fixed size, and then the blast hole target on the drilling face image is labeled by using Labelimg software, the xml label file of the blast hole target is obtained, and a drilling face blast hole image original training data set is established; Step 1022: based on the principle of target detection algorithm in image recognition, the drilling face blast hole image original training data set is trained, a tunnel drilling face blast hole target detection model is constructed, and the blast hole target on the drilling face image after drilling is detected; Step 103: first, the tunnel drilling face region recognition model is used to recognize the drilling face region, and then the recognized result is applied to the tunnel drilling face blast hole target detection model, so as to intelligently recognize the blast hole in the drilling face region.

2. The device for detecting the blast hole target of the blast hole image of the tunnel face in the drill and blast method according to claim 1, characterized in that: The image acquisition module, the construction module one, the construction module two and the analysis processing module are included; The image acquisition module acquires the drilling face image after drilling, and transmits the drilling face image after drilling to the construction module one and the construction module two; The construction module one constructs a drilling face region recognition model of the drilling face image after drilling of the drill and blast tunnel according to the established drilling face image sample database after drilling; The construction module two constructs a blast hole target detection model on the drilling face image after drilling of the drill and blast tunnel according to the established drilling face image sample database after drilling; The analysis processing module first uses the tunnel drilling face region recognition model to recognize the drilling face region, and then applies the recognized result to the tunnel drilling face blast hole target detection model, so as to intelligently recognize the blast hole in the drilling face region.

3. The device for blast hole target detection of drill-and-blast tunnel face blast hole images according to claim 2, characterized in that: The construction module one comprises a drilling face blast hole image data module and a drilling face region recognition module; The face hole image data module acquires a large number of face hole images, establishes a face hole image original database, and transmits the face hole images to the face area recognition module; The face area recognition module performs deep learning training on the established drilled face data set, and establishes a tunnel face area recognition model.

4. The device for blast hole target detection of drill-and-blast tunnel face blast hole images according to claim 2, characterized in that: The construction module two comprises a face hole image data module and a face hole recognition module; The face hole image data module acquires a large number of face hole images, establishes a face hole image original database, and transmits the face hole images to the face hole recognition module; The face hole recognition module performs deep learning training on the face hole image data set after being cut and labeled, and establishes a tunnel face hole image intelligent recognition model.

5. An electronic device, comprising: Comprise: One or more processors; Storage devices 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 the method of claim 1.

6. A computer readable medium storing a computer program, characterized in that: The computer program is executed by the processor to implement the method of claim 1.

Images