Mine underground offline positioning method, device and electronic equipment

Abstract

This application discloses an offline positioning method, device, and electronic device for underground mines, relating to the fields of intelligent mining technology and positioning technology. The method comprises: acquiring an underground image captured by a mobile terminal in an underground mine; extracting image features of the underground image; matching the image features of the underground image with the panoramic features of pre-collected panoramic images of the underground mine to obtain a matching panoramic image; and determining the current position of the mobile terminal on the underground electronic map based on the positions of the matching panoramic images marked on the underground electronic map of the mine. This solution improves the accuracy and efficiency of underground mine positioning.

Description

Technical Field

[0001] The present application relates to the fields of intelligent mining technology and positioning technology, and in particular to an offline positioning method, device and electronic equipment for underground mines. Background Art

[0002] In underground mines, accurate positioning of workers is an important safety measure. However, common underground positioning solutions have some problems and limitations.

[0003] First, traditional underground positioning solutions, such as UWB, Wi-Fi, and Bluetooth, are expensive to build. They require specialized hardware and wearable devices, which not only increases operating costs but also results in variable accuracy. Furthermore, the maintenance and upgrades of these base stations and equipment require significant capital investment.

[0004] Secondly, due to the particularity of the underground environment, GPS signals are often very weak or cannot be received at all, and the errors are also extremely large, which makes the positioning technology that relies on GPS unusable underground.

[0005] Thirdly, blasting operations are often carried out underground in mines, which causes the location of IoT devices to change frequently, making it impossible for positioning technologies that rely on fixed locations to accurately obtain the location information of the devices.

[0006] In addition, the base station signal underground is poor, and the mobile phone network signal is relatively weak. Mobile phones are often offline, making it impossible to meet real-time positioning requirements.

[0007] Therefore, it is necessary to study a new downhole offline positioning method that can overcome the above problems and achieve accurate and efficient downhole positioning. Summary of the Invention

[0008] The embodiments of the present application provide a mine underground offline positioning method, device and electronic equipment to solve the problems of low accuracy and low efficiency of mine underground positioning in the prior art.

[0009] The present invention provides an offline positioning method for underground mines, including:

[0010] Acquire underground images taken by a mobile terminal in a mine;

[0011] extracting image features of the downhole image;

[0012] Matching the image features with panoramic features of each panoramic image of the mine collected in advance to obtain a matching panoramic image;

[0013] Based on the position of the matching panoramic image marked on the underground electronic map of the mine, the current position of the mobile terminal on the underground electronic map is determined.

[0014] Furthermore, extracting the image features of the downhole image includes:

[0015] Identifying whether a preset key area exists in the downhole image;

[0016] When a key area exists, feature description information of the key area is extracted as image features of the downhole image.

[0017] Furthermore, the preset key areas include at least one of the following areas:

[0018] Underground sign area;

[0019] Corner area in the well;

[0020] underground ventilation shaft entrance area;

[0021] The feature description information of the underground signboard area includes: signboard text and signboard pattern features;

[0022] The feature description information of the downhole corner area includes: corner texture, direction and strength of the corner edge;

[0023] The characteristic description information of the underground ventilation shaft entrance includes: the shape and size of the ventilation shaft.

[0024] Furthermore, before matching the image features with the panoramic features of each panoramic image of the mine collected in advance, the method further includes:

[0025] Acquire the underground horizontal layer where the mobile terminal is located, wherein the mine has multiple underground horizontal layers of different heights;

[0026] The image features are matched with panoramic features of each panoramic image of the mine shaft that is collected in advance and belongs to the same horizontal layer of the shaft.

[0027] Furthermore, the determining the current position of the mobile terminal on the underground electronic map of the mine based on the position of the matching panoramic image marked on the underground electronic map includes:

[0028] determining the position of the matching panoramic image marked on the underground electronic map of the mine as the current position of the mobile terminal on the underground electronic map; or

[0029] Acquire depth information of multiple pixel points of the downhole image; based on the depth information of the multiple pixel points, calculate the offset angles of the multiple pixel points relative to the acquisition center point of the matching panoramic image; based on the offset angles and calibration coordinates of the multiple pixel points, calculate the geographic coordinates of the multiple pixel points, the calibration coordinates representing the position of the matching panoramic image marked on the downhole electronic map of the mine; based on the geographic coordinates of the multiple pixel points, calculate the geographic coordinates of the mobile terminal according to the principle of triangulation as the current position of the mobile terminal on the downhole electronic map.

[0030] The present application also provides an offline positioning device for an underground mine, comprising:

[0031] An image acquisition module is used to acquire underground images taken by a mobile terminal in a mine;

[0032] A feature extraction module, configured to extract image features of the downhole image;

[0033] a feature matching module, configured to match the image features with panoramic features of each pre-collected panoramic image of the mine shaft to obtain a matching panoramic image;

[0034] The position determination module is used to determine the current position of the mobile terminal on the underground electronic map of the mine based on the position of the matching panoramic image marked on the underground electronic map.

[0035] Furthermore, the feature extraction module is specifically used to identify whether a preset key area exists in the downhole image;

[0036] When a key area exists, feature description information of the key area is extracted as image features of the downhole image.

[0037] Furthermore, the preset key areas include at least one of the following areas:

[0038] Underground sign area;

[0039] Corner area in the well;

[0040] underground ventilation shaft entrance area;

[0041] The feature description information of the underground signboard area includes: signboard text and signboard pattern features;

[0042] The feature description information of the downhole corner area includes: corner texture, direction and strength of the corner edge;

[0043] The characteristic description information of the underground ventilation shaft entrance includes: the shape and size of the ventilation shaft.

[0044] Furthermore, the image acquisition module is further configured to acquire the underground horizontal layer where the mobile terminal is located, and the mine has multiple underground horizontal layers of different heights;

[0045] The feature matching module is specifically used to match the image features with the panoramic features of each panoramic image of the mine shaft that is collected in advance and belongs to the same horizontal layer of the shaft.

[0046] Furthermore, the position determination module is specifically configured to determine the position of the matching panoramic image marked on the underground electronic map of the mine as the current position of the mobile terminal on the underground electronic map; or

[0047] Acquire depth information of multiple pixel points of the downhole image; based on the depth information of the multiple pixel points, calculate the offset angles of the multiple pixel points relative to the acquisition center point of the matching panoramic image; based on the offset angles and calibration coordinates of the multiple pixel points, calculate the geographic coordinates of the multiple pixel points, the calibration coordinates representing the position of the matching panoramic image marked on the downhole electronic map of the mine; based on the geographic coordinates of the multiple pixel points, calculate the geographic coordinates of the mobile terminal according to the principle of triangulation as the current position of the mobile terminal on the downhole electronic map.

[0048] An embodiment of the present application also provides an electronic device, including a processor and a machine-readable storage medium, wherein the machine-readable storage medium stores machine-executable instructions that can be executed by the processor, and the processor is prompted by the machine-executable instructions to implement any of the above-mentioned offline positioning methods for underground mines.

[0049] An embodiment of the present application further provides a computer-readable storage medium, wherein the computer-readable storage medium stores a computer program, and when the computer program is executed by a processor, any of the above-mentioned offline positioning methods for underground mines is implemented.

[0050] An embodiment of the present application also provides a computer program product comprising instructions, which, when executed on a computer, enables the computer to execute any of the above-mentioned underground mine offline positioning methods.

[0051] The beneficial effects of this application include:

[0052] In the method provided in the embodiment of the present application, various panoramic images of the mine shaft are pre-collected, and the panoramic features of each panoramic image are extracted, and the location of each panoramic image is marked on the underground electronic map of the mine shaft. When positioning is required in the mine shaft, the underground image taken by the mobile terminal in the mine shaft is obtained, and the image features of the underground image are extracted. The image features are matched with the panoramic features of each pre-collected panoramic image to obtain a matching panoramic image, and based on the location of the matching panoramic image marked on the underground electronic map, the current location of the mobile terminal on the underground electronic map is determined. Using this method, there is no need to pre-install hardware equipment in the mine shaft, nor is there any need to perform positioning based on network signals, such as GPS signals or base station signals, thereby making it easier to achieve positioning and improving positioning efficiency. In addition, the underground electronic map can be pre-stored on the mobile terminal, thereby achieving offline positioning in the mine shaft, which is also more accurate.

[0053] Other features and advantages of the present application will be described in the following description, and in part will become apparent from the description, or will be understood by practicing the present application. The purposes and other advantages of the present application can be realized and obtained by the structures particularly pointed out in the written description, claims, and drawings. BRIEF DESCRIPTION OF THE DRAWINGS

[0054] The accompanying drawings are used to provide a further understanding of the present application and constitute a part of the specification. Together with the embodiments of the present application, they are used to explain the present application and do not constitute a limitation of the present application. In the accompanying drawings:

[0055] Figure 1 A flowchart of the offline positioning method for an underground mine provided in an embodiment of the present application;

[0056] Figure 2 A flowchart of an offline positioning method for an underground mine provided by another embodiment of the present application;

[0057] Figure 3 A schematic diagram of the structure of an offline positioning device for an underground mine provided in an embodiment of the present application;

[0058] Figure 4 A schematic diagram of the structure of an electronic device provided in an embodiment of the present application. DETAILED DESCRIPTION

[0059] To provide an implementation solution for improving the accuracy and efficiency of underground mine positioning, the present application provides an offline mine positioning method, device, and electronic device. The preferred embodiments of the present application are described below in conjunction with the accompanying drawings. It should be understood that the preferred embodiments described herein are intended only to illustrate and explain the present application and are not intended to limit the present application. Furthermore, the embodiments and features within the embodiments of the present application may be combined with each other unless there is a conflict.

[0060] The present application embodiment provides a mine underground offline positioning method, such as Figure 1 Shown, including:

[0061] Step 11: Acquire underground images taken by the mobile terminal in the mine;

[0062] Step 12: extracting image features of the downhole image;

[0063] Step 13: Match the image features of the underground image with the panoramic features of each panoramic image of the mine collected in advance to obtain a matching panoramic image;

[0064] Step 14: Based on the position of the matching panoramic image marked on the underground electronic map of the mine, determine the current position of the mobile terminal on the underground electronic map.

[0065] The above-mentioned offline positioning method for underground mines proposed in the embodiment of the present application does not require the pre-installation of hardware equipment underground in the mine, nor does it require positioning based on network signals, such as GPS signals or base station signals, thereby making it easier to achieve positioning and improving positioning efficiency. In addition, the underground electronic map can be pre-stored in the mobile terminal, thereby achieving offline positioning underground in the mine, and the accuracy is also higher.

[0066] The method and device provided in this application are described in detail below with reference to specific embodiments in conjunction with the accompanying drawings.

[0067] The present application embodiment provides a mine underground offline positioning method, such as Figure 2 Shown, including:

[0068] Step 21: Acquire underground images taken by the mobile terminal in the mine.

[0069] In an embodiment of the present application, a user in a mine can use a mobile terminal to shoot the surrounding scenes in the mine when positioning is required. The user can turn on the video mode to continuously capture images of the surrounding scenes, or can take photos, such as taking photos of more iconic scenes.

[0070] The captured images are used as downhole images for subsequent feature matching and offline positioning.

[0071] Step 22: Identify whether there is a preset key area in the acquired downhole image.

[0072] In order to more accurately identify the image features of the downhole image, in the embodiment of the present application, key areas are preset, wherein the preset key areas may include at least one of the following areas:

[0073] Underground sign area;

[0074] Corner area in the well;

[0075] The entrance area of the underground ventilation shaft.

[0076] Among them, the underground signboard has the number of the underground tunnel, the underground corner is the obvious turning area of the tunnel, and the underground ventilation shaft entrance has a unique shape and size. Therefore, the underground signboard area, the underground corner area and the underground ventilation shaft entrance area all have unique and obvious characteristics, so they can be used as key areas.

[0077] Step 23: When a key area exists, extract feature description information of the key area as image features of the downhole image.

[0078] The feature description information of the underground signboard area may include: signboard text and signboard pattern features;

[0079] The feature description information of the underground corner area may include: corner texture, direction and strength of the corner edge;

[0080] The characteristic description information of the underground ventilation shaft entrance may include: the shape and size of the ventilation shaft.

[0081] In the embodiment of the present application, OpenCV can be used as a core tool, and its built-in SIFT algorithm can be used to implement feature extraction of the acquired downhole image.

[0082] In the embodiment of the present application, if the key area is not identified from the acquired downhole image, the overall image feature extraction may be performed on the downhole image to obtain the image features of the downhole image.

[0083] Step 24: Obtain the underground horizontal layer where the mobile terminal is located.

[0084] In actual mine underground scenarios, there are often multiple underground horizontal layers with different heights. In response to this situation, in an embodiment of the present application, the underground horizontal layer where the mobile terminal is currently located can be obtained. The current underground horizontal layer can be determined based on the altitude detected by the mobile terminal, or it can be manually input by the user.

[0085] Step 25: Match the extracted image features of the downhole image with the panoramic features of the pre-collected panoramic images belonging to the same downhole horizontal layer to obtain matching panoramic images.

[0086] In an embodiment of the present application, a panoramic camera is used in advance to perform all-round image capture of various scenes underground in a mine. In particular, panoramic images can be captured for scenes containing key areas. The panoramic image includes a 360-degree field of view and can record information in the four basic directions of east, south, west, and north.

[0087] And for each collected panorama, image features are extracted as the panoramic features of the panorama. Specifically, feature description information of key areas in the panorama can be extracted as the panoramic features of the panorama.

[0088] In an embodiment of the present application, after extracting image features from the panoramic images, the positions of the panoramic images can be marked on the underground electronic map of the mine according to the image features of each panoramic image, thereby establishing a corresponding relationship between the panoramic images and the map coordinates.

[0089] Specifically, the geographical coordinates (longitude, latitude) of the panoramic image can be matched with the corresponding position on the underground electronic map, and the orientation of the panoramic image can be ensured to be consistent with the direction on the underground electronic map, thereby achieving accurate position mapping and direction calibration of the panoramic image on the underground electronic map.

[0090] Furthermore, when there are multiple underground horizontal layers with different heights in the mine, the panoramic image can also be associated with the underground horizontal layer in which it is located.

[0091] In this step, the image features of the downhole image are matched with the panoramic features of each panoramic image, which can also be achieved using the SIFT algorithm built into OpenCV.

[0092] In an embodiment of the present application, after obtaining the matching panoramic image, the position of the matching panoramic image marked on the underground electronic map of the mine can be directly determined as the current position of the mobile terminal on the underground electronic map.

[0093] Furthermore, in order to more accurately determine the location of the mobile terminal, the depth information of the downhole image and the panoramic image may also be used to determine the location of the mobile terminal, which specifically includes the following steps:

[0094] Step 26: Obtain depth information of multiple pixel points of the downhole image.

[0095] In the embodiment of the present application, if a depth camera is used to capture a downhole image, the downhole environment image and the depth information of each pixel point of the downhole image can be captured simultaneously.

[0096] In this step, the depth information of the multiple pixels obtained may be the depth information of the multiple pixels at a specified position of the downhole image, or the depth information of the multiple pixels in a key area of the downhole image.

[0097] Step 27: Based on the depth information of the multiple pixel points, calculate the offset angles of the multiple pixel points relative to the acquisition center point of the matching panoramic image.

[0098] In this step, the following formula can be used to calculate the offset angles of multiple pixel points relative to the acquisition center point of the matching panorama:

[0099] X=d*(x / width);

[0100] Y=d*(y / high);

[0101] Where x and y are the pixel coordinates of the pixel, d is the depth of the pixel, width is the image width, and high is the image height;

[0102] theta_deg = math.atan2(X,Y);

[0103] phi_deg =math.atan(Y / (math.sqrt(X**2+Y**2)));

[0104] Among them, theta_deg represents the horizontal offset angle, and phi_deg represents the vertical offset angle.

[0105] In this step, the calculated offset angles of the multiple pixel points relative to the acquisition center point of the matching panoramic image can represent the directions of the multiple pixel points in the matching panoramic image.

[0106] Step 28 calculates the geographic coordinates of the plurality of pixel points based on the offset angles and the calibration coordinates of the plurality of pixel points, the calibration coordinates representing the positions of the matching panoramic images marked on the underground electronic map of the mine.

[0107] x_pixel=x_c+d*math.sin(phi)*math.cos(theta);

[0108] y_pixel=y_c+d*math.sin(phi)*math.cos(theta);

[0109] z_pixel=z_c+d*math.cos(phi);

[0110] theta=math.radians(theta_deg);

[0111] phi = math.radians(phi_deg);

[0112] Among them, x_pixel, y_pixel and z_pixel are the geographic coordinates of the pixel point, theta_deg is the horizontal offset angle, phi_deg is the vertical offset angle, theta is the radian converted from the horizontal offset angle, and phi is the radian converted from the vertical offset angle.

[0113] Step 29: Based on the geographic coordinates of the multiple pixel points, the geographic coordinates of the mobile terminal are calculated according to the triangulation principle as the current position of the mobile terminal on the underground electronic map.

[0114] In the embodiment of the present application, after the current position of the mobile terminal on the underground electronic map is obtained, the current position of the mobile terminal can be displayed on the underground electronic map.

[0115] In the embodiment of the present application, the underground electronic map may be an underground GIS (Geographic Information System) map. The underground GIS map may be produced in the following manner:

[0116] First, the CAD drawings of the mine's underground tunnels were converted into GIS electronic maps to establish a spatial model of the underground tunnels.

[0117] Among them: the graphics elements in the underground tunnel CAD drawings are generally Cartesian coordinates (X, Y, Z), while GIS Figure 1 Generally based on the WGS84 geographic coordinate system (L, B, H). To create an underground GIS map using underground tunnel drawings, you first need to convert Cartesian coordinates (X, Y, Z) to WGS84 geographic coordinates (L, B, H).

[0118] The Cartesian coordinates (X, Y, Z) of a primitive refer to:

[0119] Reference point (origin): In underground tunnel CAD drawings, the reference point is generally the center of the earth, which serves as the starting point of the entire coordinate system. This facilitates the conversion between geographic coordinates on the earth's surface and Cartesian coordinates by applying appropriate map projection methods.

[0120] X: The straight line extending from the reference point to the east and west is defined as the X axis. The positive direction of the X axis points to the east, and the negative direction points to the west.

[0121] Y: The straight line extending from the reference point to the north and south is defined as the Y axis. The positive direction of the Y axis points to the north, and the negative direction points to the south;

[0122] Z: Indicates the altitude, starting from the reference point. The positive direction of the Z axis points upward, i.e. vertically upward, and the negative direction points downward, i.e. vertically downward.

[0123] The WGS84 geographic coordinate system (L, B, H) in GIS maps refers to:

[0124] L (Longitude): Indicates the position of a graphic element on the Earth's surface in the east-west direction, and is the angle value extending east or west from the prime meridian. The range of longitude is 0° to 180°, with positive values for east longitude and negative values for west longitude.

[0125] B (Latitude): Indicates the position of the element on the Earth's surface in the north-south direction, and is the angle value extending north or south with the equator as the reference. The range of latitude is 0° to 90°, with positive values for north latitude and negative values for south latitude;

[0126] H (Altitude): Indicates the vertical height of the feature relative to mean sea level, in meters. Positive and negative values of altitude indicate the height of the feature relative to mean sea level.

[0127] Cesium is an open source JavaScript library for creating high-performance, cross-platform 3D maps and data visualization applications. It supports a variety of data formats and conversions, including terrain, satellite imagery, 3D models, etc., and can achieve seamless rendering and interaction of global geospatial data in the browser. In the embodiment of this application, the Cesium tool can be used to convert coordinates. There are two types of coordinates in Cesium, namely WGS84 geographic coordinate system and Cartesian spatial coordinate system;

[0128] Use Cesium to convert coordinates; use the cartesianToCartographic method provided in the Cesium tool to convert the WGS84 geographic coordinate system (L, B, H);

[0129] The coordinates of the CAD drawings were converted to the WGS84 geographic coordinate system (L, B, H) and saved. The parsed and converted vector data of the CAD laneways was stored in a spatial database using PostGIS, providing the foundational data for building the electronic map. PostgreSQL is an object-relational database management system (ORDBMS), a powerful, feature-rich, and complex free software database system. PostGIS is an extension of the object-relational database system PostgreSQL. PostGIS supports all spatial data types, including points (POINT), lines (LINESTRING), and polygons (POLYGON), making it compatible with CAD drawing vector data.

[0130] The established underground tunnel GIS electronic map shows the tunnel layout, intersections, connection methods, and related attribute information in detail, including accurate underground road network information. The topological relationship of the road network is established in GIS to ensure the correctness of the tunnel connections. Guide points are added to the road network. These points can be important intersections, turning points, or specific geographical features.

[0131] A GIS network topology typically consists of nodes and edges. Nodes represent intersections or endpoints, while edges represent paths connecting nodes. Guide points are often important nodes in a road network and can serve as reference points or destinations in route analysis.

[0132] At the same time, add underground horizontal layer information: When creating a GIS map of underground tunnels, in addition to tunnel layout and intersection information, it is also necessary to record the horizontal layer information of each tunnel. This can be achieved by adding a field to the attribute table of the GIS map. This solution uses levelID "horizontal layer number".

[0133] Export underground tunnel GIS electronic maps offline. Based on the spatial database PostGIS, export the electronic map of the underground tunnel to GeoJson format. This data includes the tunnel's geometry information, attribute information, and road network information. The generated offline map data can be stored on a mobile phone.

[0134] GeoJSON is an open-source format based on JSON for representing geospatial information. It is a lightweight data exchange format that is easy to read and write, and can be easily processed by various programming languages.

[0135] The GeoJSON data format includes several major geographic data types, such as point (Point), line (LineString), surface (Polygon), multipoint (MultiPoint), and collection (GeometryCollection). It can also contain features (Feature) and feature collections (FeatureCollection), which contain geometric objects and attribute information.

[0136] Among them: Road network information contains line features, so the LineString type in GeoJSON can be used to represent this information;

[0137] The FeatureCollection above contains two Feature objects: one representing a road network of type LineString and the other representing a guide point of type Point. A guide point has a geometry attribute that describes the point's geographic location and a properties attribute that contains non-spatial information related to the point.

[0138] Based on the same inventive concept, according to the mine underground offline positioning method provided by the above embodiment of the present application, correspondingly, another embodiment of the present application also provides a mine underground offline positioning device, the structural diagram of which is shown in FIG. Figure 3 As shown, specifically including:

[0139] The image acquisition module 31 is used to acquire underground images taken by the mobile terminal in the mine;

[0140] A feature extraction module 32 is used to extract image features of the downhole image;

[0141] A feature matching module 33 is used to match the image features with the panoramic features of each panoramic image of the mine collected in advance to obtain a matching panoramic image;

[0142] The location determination module 34 is configured to determine the current location of the mobile terminal on the underground electronic map of the mine based on the location of the matching panoramic image marked on the underground electronic map.

[0143] Furthermore, the feature extraction module 32 is specifically used to identify whether a preset key area exists in the downhole image;

[0144] When a key area exists, feature description information of the key area is extracted as image features of the downhole image.

[0145] Furthermore, the preset key areas include at least one of the following areas:

[0146] Underground sign area;

[0147] Corner area in the well;

[0148] underground ventilation shaft entrance area;

[0149] The feature description information of the underground signboard area includes: signboard text and signboard pattern features;

[0150] The feature description information of the downhole corner area includes: corner texture, direction and strength of the corner edge;

[0151] The characteristic description information of the underground ventilation shaft entrance includes: the shape and size of the ventilation shaft.

[0152] Furthermore, the image acquisition module 31 is further configured to acquire the underground horizontal layer where the mobile terminal is located, and the mine has multiple underground horizontal layers of different heights;

[0153] The feature matching module 33 is specifically configured to match the image features with the panoramic image features of the pre-collected panoramic images of the mine belonging to the same horizontal layer.

[0154] Furthermore, the position determination module 34 is specifically configured to determine the position of the matching panoramic image marked on the underground electronic map of the mine as the current position of the mobile terminal on the underground electronic map; or

[0155] Acquire depth information of multiple pixel points of the downhole image; based on the depth information of the multiple pixel points, calculate the offset angles of the multiple pixel points relative to the acquisition center point of the matching panoramic image; based on the offset angles and calibration coordinates of the multiple pixel points, calculate the geographic coordinates of the multiple pixel points, the calibration coordinates representing the position of the matching panoramic image marked on the downhole electronic map of the mine; based on the geographic coordinates of the multiple pixel points, calculate the geographic coordinates of the mobile terminal according to the principle of triangulation as the current position of the mobile terminal on the downhole electronic map.

[0156] The functions of the above modules can correspond to Figure 1 and Figure 2 The corresponding processing steps in the shown process will not be repeated here.

[0157] The offline positioning device for underground mines provided in the embodiments of the present application can be implemented via a computer program. Those skilled in the art will appreciate that the aforementioned modular division is only one of many possible modular divisions, and that other modular divisions or no modular divisions, as long as the offline positioning device for underground mines has the aforementioned functions, are within the scope of protection of the present application.

[0158] The present application also provides an electronic device, such as Figure 4 As shown, it includes a processor 41 and a machine-readable storage medium 42, wherein the machine-readable storage medium 42 stores machine-executable instructions that can be executed by the processor 41, and the processor 41 is prompted by the machine-executable instructions to implement any of the above-mentioned offline positioning methods for underground mines.

[0159] An embodiment of the present application further provides a computer-readable storage medium, wherein the computer-readable storage medium stores a computer program, and when the computer program is executed by a processor, any of the above-mentioned offline positioning methods for underground mines is implemented.

[0160] An embodiment of the present application also provides a computer program product comprising instructions, which, when executed on a computer, enables the computer to execute any of the above-mentioned underground mine offline positioning methods.

[0161] The machine-readable storage medium in the electronic device may include random access memory (RAM) or non-volatile memory (NVM), such as at least one disk storage device. Alternatively, the memory may be at least one storage device located remotely from the processor.

[0162] The above-mentioned processor can be a general-purpose processor, including a central processing unit (CPU), a network processor (NP), etc.; it can also be a digital signal processor (DSP), an application specific integrated circuit (ASIC), a field programmable gate array (FPGA) or other programmable logic devices, discrete gate or transistor logic devices, and discrete hardware components.

[0163] Each embodiment in this specification is described in a related manner. Similar portions between the various embodiments can be referenced to each other. Each embodiment focuses on the differences between the other embodiments. In particular, the device, electronic device, computer-readable storage medium, and computer program product embodiments are generally similar to the method embodiments, so their descriptions are relatively simple. For related portions, reference can be made to the descriptions of the method embodiments.

[0164] It should be noted that, in this document, relational terms such as first and second, etc., are used only to distinguish one entity or operation from another entity or operation, and do not necessarily require or imply the existence of any such actual relationship or order between these entities or operations. Moreover, the terms "comprises," "comprising," or any other variants thereof are intended to cover non-exclusive inclusion, so that a process, method, article, or device comprising a series of elements includes not only those elements, but also other elements not explicitly listed, or elements inherent to such process, method, article, or device. In the absence of further limitations, an element defined by the phrase "comprising a ..." does not exclude the presence of other identical elements in the process, method, article, or device comprising the element.

[0165] The present application is described with reference to the flowcharts and / or block diagrams of the methods, devices (systems), and computer program products according to the embodiments of the present application. It should be understood that each process and / or block in the flowchart and / or block diagram, as well as the combination of processes and / or blocks in the flowchart and / or block diagram, can be implemented by computer program instructions. These computer program instructions can be provided to a processor of a general-purpose computer, a special-purpose computer, an embedded processor, or other programmable data processing device to produce a machine, so that the instructions executed by the processor of the computer or other programmable data processing device generate instructions for implementing the processes in the flowchart and / or block diagram. Figure 1 a process or multiple processes and / or boxes Figure 1 A device that provides the functions specified in a block or multiple blocks.

[0166] These computer program instructions may also be stored in a computer readable memory that can direct a computer or other programmable data processing device to work in a specific manner, so that the instructions stored in the computer readable memory produce an article of manufacture comprising an instruction device, which implements the process Figure 1 a process or multiple processes and / or boxes Figure 1 The function specified in one or more boxes.

[0167] These computer program instructions can also be loaded onto a computer or other programmable data processing device so that a series of operational steps are executed on the computer or other programmable device to produce a computer-implemented process, thereby providing the instructions executed on the computer or other programmable device for implementing the process. Figure 1 a process or multiple processes and / or boxes Figure 1 A step that specifies a function in one or more boxes.

[0168] Obviously, those skilled in the art may make various changes and modifications to this application without departing from the spirit and scope of this application. Thus, if these modifications and variations of this application fall within the scope of the claims of this application and their equivalents, this application is intended to include these modifications and variations.

Claims

1. A mine offline positioning method, characterized in that: include: Acquire underground images taken by a mobile terminal in a mine; extracting image features of the downhole image; Matching the image features with panoramic features of each panoramic image of the mine collected in advance to obtain a matching panoramic image; Acquiring depth information of a plurality of pixel points of the downhole image; Calculating, based on the depth information of the plurality of pixel points, offset angles of the plurality of pixel points relative to a collection center point of the matching panoramic image; Calculating geographic coordinates of the plurality of pixel points based on the offset angles and calibration coordinates of the plurality of pixel points, the calibration coordinates representing positions of the matching panoramic image marked on an underground electronic map of the mine; Based on the geographic coordinates of the multiple pixel points, the geographic coordinates of the mobile terminal are calculated according to the triangulation principle as the current position of the mobile terminal on the underground electronic map.

2. The method according to claim 1, wherein The extracting the image features of the downhole image includes: Identifying whether a preset key area exists in the downhole image; When a key area exists, feature description information of the key area is extracted as image features of the downhole image.

3. The method according to claim 2, wherein The preset key areas include at least one of the following areas: Underground sign area; Corner area in the well; underground ventilation shaft entrance area; The feature description information of the underground signboard area includes: signboard text and signboard pattern features; The feature description information of the downhole corner area includes: corner texture, direction and strength of the corner edge; The characteristic description information of the underground ventilation shaft entrance includes: the shape and size of the ventilation shaft.

4. The method according to claim 1, wherein Before matching the image features with the panoramic features of each panoramic image of the mine collected in advance, the method further includes: Acquire the underground horizontal layer where the mobile terminal is located, wherein the mine has multiple underground horizontal layers of different heights; The matching of the image features with panoramic features of each panoramic image of the mine collected in advance includes: The image features are matched with panoramic features of each panoramic image of the mine shaft that is collected in advance and belongs to the same horizontal layer of the shaft.

5. An offline positioning device for underground mines, characterized in that: include: An image acquisition module is used to acquire underground images taken by a mobile terminal in a mine; A feature extraction module, configured to extract image features of the downhole image; a feature matching module, configured to match the image features with panoramic features of each pre-collected panoramic image of the mine shaft to obtain a matching panoramic image; a position determination module, configured to obtain depth information of a plurality of pixel points of the downhole image; Calculating, based on the depth information of the plurality of pixel points, offset angles of the plurality of pixel points relative to a collection center point of the matching panoramic image; Calculating geographic coordinates of the plurality of pixel points based on the offset angles and calibration coordinates of the plurality of pixel points, the calibration coordinates representing positions of the matching panoramic image marked on an underground electronic map of the mine; Based on the geographic coordinates of the multiple pixel points, the geographic coordinates of the mobile terminal are calculated according to the triangulation principle as the current position of the mobile terminal on the underground electronic map.

6. The device according to claim 5, characterized in that The feature extraction module is specifically used to identify whether there is a preset key area in the downhole image; When a key area exists, feature description information of the key area is extracted as image features of the downhole image.

7. The device according to claim 6, characterized in that The preset key areas include at least one of the following areas: Underground sign area; Corner area in the well; underground ventilation shaft entrance area; The feature description information of the underground signboard area includes: signboard text and signboard pattern features; The feature description information of the downhole corner area includes: corner texture, direction and strength of the corner edge; The characteristic description information of the underground ventilation shaft entrance includes: the shape and size of the ventilation shaft.

8. An electronic device, characterized in that: The method comprises a processor and a machine-readable storage medium, wherein the machine-readable storage medium stores machine-executable instructions that can be executed by the processor, and the processor is prompted by the machine-executable instructions to implement the method according to any one of claims 1 to 4.

9. A computer-readable storage medium, characterized in that The computer-readable storage medium stores a computer program, and when the computer program is executed by a processor, the method according to any one of claims 1 to 4 is implemented.

Images