A method and system for determining the position and posture of a tunnel boring machine body based on three laser point targets
Through the method based on three laser point targets, combined with the total station and the mining camera to collect laser spot characteristics, the time accumulation error and harsh environmental impact of the position measurement of the position of the underground tunneling machine in coal mine are solved, and the position of the body of the tunneling machine is realized The precise measurement and stability support the intelligent development of coal mines underground.
Patent Information
- Application Number
- CN202210098038.1
- Authority / Receiving Office
- CN · China
- Patent Type
- Patents(China)
- Current Assignee / Owner
- Filing Date
- 2022-01-27
- Publication Date
- 2024-11-22
- Estimated Expiration
- 2042-01-27
AI Technical Summary
The position measurement method of underground tunneling machine in coal mines has time accumulation errors and harsh environmental impacts, resulting in unstable measurement results and difficult to achieve intelligent development.
Using the method based on three laser point targets, the mapping relationship between three-dimensional spatial coordinates and two-dimensional images is used to collect laser spot features using a total station and a mining camera, and the region segmentation is performed by combining color component constraints and European-style distance constraints, and the improved The Hough circular transformation algorithm locates the center of the laser spot, establishes a pose solution model for the boring machine fuselage, and determines the position and attitude angle.
It realizes accurate measurement of the body position of the boring machine, provides technical support for the intelligent development of coal mines underground, and improves the stability and accuracy of the measurement results.
Smart Images

Figure CN114429469B_ABST
Abstract
Description
Technical Field
[0001] The present invention relates to the field of coal mine tunneling equipment operation status monitoring, and in particular to a tunneling machine body posture determination method and system based on three laser point targets. Background Art
[0002] The construction process of underground tunneling working faces in coal mines is complex, the level of intelligence is low, and the contradiction of "unbalanced tunneling" restricts production efficiency. The autonomous measurement and dynamic positioning of tunneling equipment has become the primary problem facing the intelligent development of tunneling equipment. The existing methods for measuring the posture of tunneling machines in underground coal mines include: posture measurement system based on inertial navigation, posture measurement system based on UWB, posture measurement system based on total station, and posture measurement system based on machine vision. Among them, the posture measurement system based on inertial navigation does not require any external information, but there is a time accumulation error and it is seriously affected by vibration conditions; the posture measurement system based on total station is affected by the harsh environment during tunneling, and the prism light path is easily blocked, and the stability of the measurement results needs to be solved urgently. Summary of the invention
[0003] The purpose of the present invention is to provide a method and system for determining the position and attitude of a tunnel boring machine body based on three-laser point targets, which can obtain the position and attitude angle of the tunnel boring machine body by utilizing the mapping relationship between the two-dimensional images of the three laser points and the three-dimensional coordinates of the space.
[0004] To achieve the above object, the present invention provides the following solutions:
[0005] A method for determining the position and posture of a tunnel boring machine body based on three laser point targets, comprising:
[0006] A three-laser point target is constructed based on three laser points emitted by three mining laser pointers placed on the top of the tunnel at the excavation working face;
[0007] The three-laser point target is calibrated using a total station to determine the three-dimensional spatial coordinates of the three laser emission points under the three-laser point target coordinates, as well as the relative position conversion relationship between the three-laser point target coordinate system and the tunnel coordinate system of the excavation working face;
[0008] The three-laser target image is collected using a mining camera installed behind the tunnel boring machine.
[0009] The laser spot region is segmented for the three-laser point target image using color component constraints and Euclidean distance constraints.
[0010] The laser spot sub-pixel center positioning algorithm based on improved Hough circle transform is used to locate the region segmented image and determine the center coordinates of the three laser spots.
[0011] The position and attitude angle of the tunnel boring machine body in the tunnel coordinate system are determined according to the tunnel boring machine body posture solution model based on the three-laser spot positioning feature, the center coordinates of the three laser spots of the three-laser point target image, and the three-dimensional spatial coordinates of the three laser points in the three-laser point target coordinate system; the tunnel boring machine body posture solution model based on the three-laser spot positioning feature takes the center coordinates of the three laser spots of the three-laser point target image and the three-dimensional spatial coordinates of the three laser points in the three-laser point target coordinate system as input, and takes the position and attitude angle of the tunnel boring machine body in the tunnel coordinate system as output;
[0012] Optionally, the method of performing laser spot regional segmentation on the three-laser point target image by using color component constraint and Euclidean distance constraint specifically includes:
[0013] Each pixel in the three-laser spot target image is judged according to the color component constraint to determine the initial laser spot pixel cluster segmentation area set;
[0014] The maximum gray value in the initial laser spot pixel cluster segmentation area set is determined as the adaptive gray threshold of the current target image;
[0015] According to the adaptive grayscale threshold, the three-laser point target image is binarized and segmented using the Otsu threshold segmentation algorithm to determine the connected area pixel point set after the binarization segmentation process;
[0016] According to the statistical value of the pixel points in the connected area of the image after the above binary segmentation processing and the statistical value threshold of the pixel points in the connected area, the image obtained by the binary segmentation processing is subjected to secondary segmentation processing;
[0017] The Euclidean distance constraint is used to screen the image after secondary segmentation to determine the area of the laser spot.
[0018] Optionally, the laser spot sub-pixel center positioning algorithm using an improved Hough circle transform is used to position the region segmented image to determine the center coordinates of the three laser spots, specifically including:
[0019] The laser spot area is processed by using Canny edge detection to determine the initial pixel clustering set of the edge of the laser spot contour;
[0020] The Sobel gradient operator is used to extract the pixel cluster set of the initial laser spot contour edge to determine the gradient of the laser spot contour edge;
[0021] Filter the pixel points in the initial pixel point clustering set of the laser spot contour edge by using the symmetric geometric constraint of the gradient of the laser spot contour edge, and determine the pixel point clustering set of the laser spot contour edge after filtering out the interference of the noise points;
[0022] The Hough circle transform is used to process the pixel clustering set of the contour edge of the laser spot after filtering out the interference of noise points, and the sub-pixel center coordinates of the laser spot are determined.
[0023] A tunnel boring machine body position determination system based on three laser point targets, comprising:
[0024] A three-laser point target construction module is used to construct a three-laser point target based on three laser points emitted by three mining laser pointers placed on the top of the tunnel of the excavation working face;
[0025] The calibration module uses a total station to calibrate the three-laser point target, determine the three-dimensional spatial coordinates of the three laser emission points under the three-laser point target coordinates, and the relative posture conversion relationship between the three-laser point target coordinate system and the tunnel coordinate system of the excavation working face;
[0026] Three-laser point target image acquisition module, used to acquire three-laser point target images using a mining camera installed at the rear of the tunnel boring machine;
[0027] The laser spot area segmentation module is used to perform laser spot area segmentation on the three-laser point target image using color component constraints and Euclidean distance constraints;
[0028] The center coordinate determination module is used to locate the region segmented image using the laser spot sub-pixel center positioning algorithm of the improved Hough circle transform to determine the center coordinates of the three laser spots;
[0029] A tunnel boring machine body posture determination module is used to determine the position and posture angle of the tunnel boring machine body in the tunnel coordinate system according to a tunnel boring machine body posture solution model based on three-laser spot positioning features, the center coordinates of the three laser spots of the three-laser point target image, and the three-dimensional spatial coordinates of the three laser points in the three-laser point target coordinate system; the tunnel boring machine body posture solution model based on the three-laser spot positioning features takes the center coordinates of the three laser spots of the three-laser point target image and the three-dimensional spatial coordinates of the three laser points in the three-laser point target coordinate system as input, and takes the position and posture angle of the tunnel boring machine body in the tunnel coordinate system as output;
[0030] Optionally, the laser spot area segmentation module specifically includes:
[0031] An initial laser spot pixel point clustering segmentation region set determination unit is used to determine an initial laser spot pixel point clustering segmentation region set by judging each pixel point in the three-laser point target image according to the color space constraint;
[0032] An adaptive grayscale threshold determination unit, used to determine the maximum grayscale value in the initial laser spot pixel point cluster segmentation area set as the adaptive grayscale threshold of the current target image;
[0033] A binary segmentation processing unit is used to perform binary segmentation processing on the three-laser point target image according to an adaptive grayscale threshold using an Otsu threshold segmentation algorithm;
[0034] A secondary segmentation unit is used to segment the image after the binary segmentation processing according to the statistical values of the pixels in the connected region set in the image after the binary segmentation processing and the statistical threshold of the pixels in the connected region;
[0035] The laser spot area determination unit is used to screen the image after secondary segmentation by using the Euclidean distance constraint to determine the area of the laser spot.
[0036] Optionally, the center coordinate determination module specifically includes:
[0037] A pixel point clustering set determining unit of the initial laser spot contour edge is used to process the laser spot area by using Canny edge detection to determine the pixel point clustering set of the initial laser spot contour edge;
[0038] The gradient extraction unit of the laser spot contour edge is used to extract the pixel point clustering set of the initial laser spot contour edge by using the Sobel gradient operator to determine the gradient of the laser spot contour edge;
[0039] A noise interference filtering unit is used to screen the pixel points in the initial pixel point clustering set of the edge of the laser spot contour by using the symmetric geometric constraint of the gradient of the edge of the laser spot contour, and determine the pixel point clustering set of the edge of the laser spot contour after filtering out the noise interference;
[0040] The center coordinate determination unit is used to process the pixel point clustering set of the contour edge of the laser spot after filtering out the interference of the noise points by using Hough circle transformation, so as to determine the sub-pixel center coordinate of the laser spot.
[0041] According to the specific embodiments provided by the present invention, the present invention discloses the following technical effects:
[0042] The present invention provides a method and system for determining the posture of a tunnel boring machine body based on three laser point targets. The mine camera collects the laser point features formed by the mine laser pointer, obtains the laser spot feature parameters through image processing, and substitutes them into the established tunnel boring machine body posture visual measurement model based on three-point positioning features to obtain the posture parameters of the tunnel boring machine relative to the tunnel. The mine camera is fixed behind the tunnel boring machine body, collects the three laser spot images formed by the mine laser pointer above the tunnel boring tunnel, performs regional segmentation and spot center detection on the obtained spot image, and obtains the center coordinate parameters of the three laser spots; constructs a tunnel boring machine body posture visual measurement model based on the three laser point positioning features, substitutes the extracted laser spot center coordinates into the above model, and obtains the posture parameters of the tunnel boring machine relative to the tunnel. The present invention can use the mapping relationship between the spatial three-dimensional coordinates of the three laser points and the two-dimensional image to obtain the position and attitude angle information of the tunnel boring machine body, and provide necessary technical support for the posture measurement of the tunnel boring machine body in the tunneling working face of the coal mine. BRIEF DESCRIPTION OF THE DRAWINGS
[0043] In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the drawings required for use in the embodiments will be briefly introduced below. Obviously, the drawings described below are only some embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying creative labor.
[0044] Figure 1 A schematic flow chart of a method for determining the position and posture of a tunnel boring machine body based on three laser point targets provided by the present invention;
[0045] Figure 2 A schematic diagram of the overall process of a method for determining the position and posture of a tunnel boring machine body based on three laser point targets provided by the present invention;
[0046] Figure 3 The schematic diagram of the tunnel boring machine body visual measurement system based on three laser point targets;
[0047] Figure 4 Schematic diagram of the posture calculation model of the tunnel boring machine body based on three laser point targets. DETAILED DESCRIPTION
[0048] The following will be combined with the drawings in the embodiments of the present invention to clearly and completely describe the technical solutions in the embodiments of the present invention. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present invention.
[0049] The purpose of the present invention is to provide a method and system for determining the position and attitude of a tunnel boring machine body based on three-laser point targets, which can obtain the position and attitude angle of the tunnel boring machine body by utilizing the mapping relationship between the two-dimensional images of the three laser points and the three-dimensional coordinates of the space.
[0050] In order to make the above-mentioned objects, features and advantages of the present invention more obvious and easy to understand, the present invention is further described in detail below with reference to the accompanying drawings and specific embodiments.
[0051] Figure 1 The present invention provides a method for determining the position and posture of a tunnel boring machine body based on three laser point targets. Figure 2 The overall flow diagram of a method for determining the position and posture of a tunnel boring machine body based on three laser point targets provided by the present invention is as follows: Figure 1 and Figure 2 As shown, the present invention provides a method for determining the posture of a tunnel boring machine body based on three laser point targets, comprising:
[0052] S101, such as Figure 3 As shown, a three-laser point target is constructed based on three laser spots emitted by three mining laser pointers placed on the top of the tunnel of the excavation working face;
[0053] S102, calibrating the three-laser point target using a total station to determine the three-dimensional spatial coordinates of the three laser emission points under the three-laser point target coordinates, and the relative position conversion relationship between the three-laser point target coordinate system and the tunnel coordinate system of the excavation working face;
[0054] S103, using a mining camera installed at the rear of the tunnel boring machine to collect a three-laser point target image;
[0055] S104, performing laser spot region segmentation on the three-laser point target image using color component constraints and Euclidean distance constraints;
[0056] S104 specifically includes:
[0057] Each pixel in the three-laser spot target image is judged according to the color space constraint to determine the initial laser spot pixel cluster segmentation area set;
[0058] The maximum gray value in the initial laser spot pixel cluster segmentation area set is determined as the adaptive gray threshold of the current target image;
[0059] According to the adaptive grayscale threshold, the three-laser point target image is binarized and segmented using the Otsu threshold segmentation algorithm.
[0060] According to the statistical value of the pixel points in the connected area of the image after the above binary segmentation processing and the statistical value threshold of the pixel points in the connected area, the image obtained by the binary segmentation processing is subjected to secondary segmentation processing;
[0061] The Euclidean distance constraint is used to screen the image after secondary segmentation to determine the area of the laser spot.
[0062] As a specific embodiment, the specific steps of the area segmentation of the laser spot are as follows:
[0063] Step (1), assuming that the i-th image point in the three-laser point target image is represented by I(x i ,y i ), define the color space component constraint as 0<H(x i ,y i )<10,40<S(x i ,y i )<250,40<V(x i ,y i )<250, each pixel point in the current three-laser point target image is judged according to the above color space constraints to obtain the initial laser spot pixel point clustering segmentation area set;
[0064] Step (2), obtaining an adaptive grayscale threshold of the current target image by calculating the maximum grayscale value of the cluster segmentation area of the initial laser spot pixel point currently obtained;
[0065] Step (3), combining the adaptive grayscale threshold obtained in step (2), using the Otsu threshold segmentation algorithm to perform binary segmentation processing on the current image, and defining the threshold segmentation to obtain an area S, which contains not only the laser spot but also the stray light spot;
[0066] Step (4), assuming S k Represents the pixel set of the kth connected region in region S, let S′ k is the connected region set S k The intersection of the initial laser spot pixel cluster segmentation area set L obtained in step (1), N k For the set S′ k The statistical value of the pixel in the color space is used to satisfy the pixel statistical value N k >m to split the region S, where m is usually set to 5;
[0067] Step (5), using the Euclidean distance constraint relationship between pixels of the three laser spot centers along the u-axis and the v-axis, further screen the segmented spot areas and determine the three laser spot areas.
[0068] S105, using an improved Hough circle transform laser spot sub-pixel center positioning algorithm to position the region segmented image, and determine the center coordinates of the three laser spots;
[0069] S105 specifically includes:
[0070] The laser spot area is processed by using Canny edge detection to determine the initial pixel clustering set of the edge of the laser spot contour;
[0071] The Sobel gradient operator is used to extract the pixel cluster set of the initial laser spot contour edge to determine the gradient of the laser spot contour edge;
[0072] Filter the pixel points in the initial pixel point clustering set of the laser spot contour edge by using the symmetric geometric constraint of the gradient of the laser spot contour edge, and determine the pixel point clustering set of the laser spot contour edge after filtering out the interference of the noise points;
[0073] The Hough circle transform is used to process the pixel clustering set of the contour edge of the laser spot after filtering out the interference of noise points, and the sub-pixel center coordinates of the laser spot are determined.
[0074] S106, determining the position and attitude angle of the tunnel boring machine body in the tunnel coordinate system according to the tunnel boring machine body posture calculation model based on the three-laser spot positioning feature, the center coordinates of the three laser spots of the three-laser point target image, and the three-dimensional spatial coordinates of the three laser points in the three-laser point target coordinate system; the tunnel boring machine body posture calculation model based on the three-laser spot positioning feature takes the center coordinates of the three laser spots of the three-laser point target image and the three-dimensional spatial coordinates of the three laser points in the three-laser point target coordinate system as input, and takes the position and attitude angle of the tunnel boring machine body in the tunnel coordinate system as output;
[0075] The specific steps to establish the posture calculation model of the tunnel boring machine are as follows:
[0076] Step (1) Create Figure 4 The lane coordinate system O shown n X n Y n Z n , three laser point target coordinate system O b X b Y b Z b and the camera coordinate system O c =(X c ,Y c ,Z c ) ; establish a pixel coordinate system Ouv, the origin of the pixel coordinate system is O, (u, v) represents the number of rows and columns of the pixel point on the image; P 1, P 2 , P 3 is the center of the laser spot of the three laser targets, P 1 P 2 The distance between them is d, P 1 The projection on the image is p 1 (x 1 ,y 1 ,z 1 ), P 2 The projection on the image is p 2 (x 2 ,y 2 ,z 2 ), P 3 The projection on the image is p 3 (x 3 ,y 3 ,z 3 );
[0077] Step (2) Define the auxiliary coordinate system M 1 For (O 1 ,m x1 ,m y1 ,m z1 ), where m x1 =O c p 1 / ||O c p 1 ||,m y1 =m z1 ×m x1 , m z1 =m x1 ×O c p 2 / ||m x1 ×O c p 2 ||, define the auxiliary coordinate system M 2 =(O 2 ,m x2 ,m y2 ,m z2 ), where m x2 =P 1 P 2 / ||P 1 P 2 ||,m z2 =m x2 ×P 1 P 3 / ||m x2 ×P 1 P 3 ||,m y2 =m z2 ×m x2, camera coordinate system and auxiliary coordinate system M 1 The transformation matrix between can be expressed as Three laser point target coordinate system and auxiliary coordinate system M 2 The transformation matrix between can be expressed as
[0078] Step (3) defines the vector O c P 1 With vector O c P 2 Constitute the auxiliary plane π, then the auxiliary coordinate system M 1 (O 1 ,m x1 ,m y1 ,m z1 ) projected onto the auxiliary plane π can be expressed as the projected auxiliary coordinate system M 1 ′=[m′ x1 ,m′ y1 ,m′ z1 ],m′ x1 =[-cosθ,-sinθ,0],m′ y1 =[-cosθ,-sinθ,0],m′ z1 =[-cosθ,-sinθ,0]. Therefore, assuming that the auxiliary coordinate system M 1 With the auxiliary coordinate system M 2 The coordinate transformation matrix between α , auxiliary coordinate system M 1 With the auxiliary coordinate system M 2 The transformation relationship between them can be expressed as the projection auxiliary coordinate system M′ 1 Around the auxiliary coordinate system M 1 The vector axis m x1 Rotation angle α,
[0079]
[0080] in,
[0081]
[0082]
[0083]
[0084] Camera coordinate system O c The projection onto the auxiliary plane π can be expressed as the projection auxiliary coordinate system M′ o =[O′ x1 ,O′ y1 ,O′ z1 ],O′ x1=dcosθ 1 sinθ 1 cotθ 2 +dcos 2 θ 1 , O′ y1 =dsin 2 θ 1 sincotθ 2 +dsinθ 1 cosθ 1 , O′ z1 = 0, projection auxiliary coordinate system M′ o Transform to auxiliary coordinate system M 2 It can be expressed as:
[0085]
[0086] in,
[0087]
[0088]
[0089]
[0090] Step (4) Define the laser point P in the target coordinate system 3 Transform to auxiliary coordinate system M 2 It can be expressed as
[0091]
[0092] Laser point P in target coordinate system 3 Transform to auxiliary coordinate system M 1 It can be expressed as
[0093]
[0094] According to the established auxiliary coordinate system, the laser point P in the target coordinate system 3 You can also convert to the auxiliary coordinate system M 2 Then transform it to the auxiliary coordinate system M 1 , so we can get
[0095]
[0096] Assuming x = cosα, combining formulas (4) and (5), we can obtain the fourth-order polynomial shown in formula (6):
[0097] K 0 x 4 +K 1 x 3 +K2 x 2 +K 3 x+K 4 =0 (6)
[0098] in,
[0099]
[0100]
[0101]
[0102]
[0103]
[0104] Step (6) Assume that the coordinate system of the tunnel boring machine body is the camera coordinate system, and obtain the rotation matrix of the tunnel boring machine body coordinate system and the laser target coordinate system according to the following formula: and translation matrix
[0105]
[0106]
[0107] Step (7) obtains the position and attitude angle of the tunnel boring machine body in the tunnel coordinates based on the rotation matrix and translation matrix between the tunnel boring machine body coordinate system and the laser target coordinate system obtained above, combined with the relative posture transformation relationship between the three-laser point target coordinate system and the tunneling working face coordinate system.
[0108] The present invention provides a tunnel boring machine body position determination system based on three laser point targets, comprising:
[0109] A three-laser point target construction module is used to construct a three-laser point target based on three laser spots emitted by three mining laser pointers placed on the top of the tunnel of the excavation working face;
[0110] The calibration module is used to calibrate the three-laser point target using a total station, determine the three-dimensional spatial coordinates of the three laser emission points under the three-laser point target coordinates, and the relative posture conversion relationship between the three-laser point target coordinate system and the tunnel coordinate system of the excavation working face;
[0111] Three-laser point target image acquisition module, used to acquire three-laser point target images using a mining camera installed at the rear of the tunnel boring machine;
[0112] The laser spot area segmentation module is used to perform laser spot area segmentation on the three-laser point target image using color component constraints and Euclidean distance constraints;
[0113] The center coordinate determination module is used to locate the region segmented image using the laser spot sub-pixel center positioning algorithm of the improved Hough circle transform to determine the center coordinates of the three laser spots;
[0114] A tunnel boring machine body posture determination module is used to determine the position and posture angle of the tunnel boring machine body in the tunnel coordinate system according to a tunnel boring machine body posture solution model based on three-laser spot positioning features, the center coordinates of the three laser spots of the three-laser point target image, and the three-dimensional spatial coordinates of the three laser points in the three-laser point target coordinate system; the tunnel boring machine body posture solution model based on the three-laser spot positioning features takes the center coordinates of the three laser spots of the three-laser point target image and the three-dimensional spatial coordinates of the three laser points in the three-laser point target coordinate system as input, and takes the position and posture angle of the tunnel boring machine body in the tunnel coordinate system as output;
[0115] The laser spot area segmentation module specifically includes:
[0116] An initial laser spot pixel point clustering segmentation region set determination unit is used to determine an initial laser spot pixel point clustering segmentation region set by judging each pixel point in the three-laser point target image according to the color space constraint;
[0117] An adaptive grayscale threshold determination unit, used to determine the maximum grayscale value in the initial laser spot pixel point cluster segmentation area set as the adaptive grayscale threshold of the current target image;
[0118] A binary segmentation processing unit is used to perform binary segmentation processing on the three-laser point target image according to an adaptive grayscale threshold using an Otsu threshold segmentation algorithm;
[0119] A secondary segmentation unit is used to segment the image after the binary segmentation processing according to the statistical values of the pixels in the connected region set in the image after the binary segmentation processing and the statistical threshold of the pixels in the connected region;
[0120] The laser spot area determination unit is used to screen the image after secondary segmentation by using the Euclidean distance constraint to determine the area of the laser spot.
[0121] The center coordinate determination module specifically includes:
[0122] A pixel point clustering set determining unit of the initial laser spot contour edge is used to process the laser spot area by using Canny edge detection to determine the pixel point clustering set of the initial laser spot contour edge;
[0123] The gradient extraction unit of the laser spot contour edge is used to extract the pixel point clustering set of the initial laser spot contour edge by using the Sobel gradient operator to determine the gradient of the laser spot contour edge;
[0124] A noise interference filtering unit is used to screen the pixel points in the initial pixel point clustering set of the edge of the laser spot contour by using the symmetric geometric constraint of the gradient of the edge of the laser spot contour, and determine the pixel point clustering set of the edge of the laser spot contour after filtering out the noise interference;
[0125] The center coordinate determination unit is used to process the pixel point clustering set of the contour edge of the laser spot after filtering out the interference of the noise points by using Hough circle transformation, so as to determine the sub-pixel center coordinate of the laser spot.
[0126] In this specification, each embodiment is described in a progressive manner, and each embodiment focuses on the differences from other embodiments. The same or similar parts between the embodiments can be referred to each other. For the system disclosed in the embodiment, since it corresponds to the method disclosed in the embodiment, the description is relatively simple, and the relevant parts can be referred to the method part.
[0127] The principles and implementation methods of the present invention are described in this article using specific examples. The description of the above embodiments is only used to help understand the method and core idea of the present invention. At the same time, for those skilled in the art, according to the idea of the present invention, there will be changes in the specific implementation methods and application scope. In summary, the content of this specification should not be understood as limiting the present invention.
Claims
1. A method for determining the position and posture of a tunnel boring machine body based on three laser point targets, characterized in that: include: A three-laser point target is constructed based on three laser spots emitted by three mining laser pointers placed on the top of the tunnel at the excavation working face; The three-laser point target is calibrated using a total station to determine the three-dimensional spatial coordinates of the three laser emission points under the three-laser point target coordinates, as well as the relative position conversion relationship between the three-laser point target coordinate system and the tunnel coordinate system of the excavation working face; The three-laser target image is collected using a mining camera installed behind the tunnel boring machine. The laser spot region of the three-laser point target image is segmented using color component constraints and Euclidean distance constraints. The laser spot sub-pixel center positioning algorithm based on improved Hough circle transform is used to locate the region segmented image and determine the center coordinates of the three laser spots. The position and attitude angle of the tunnel boring machine body in the tunnel coordinate system are determined according to the tunnel boring machine body posture solution model based on the three-laser spot positioning features, the center coordinates of the three laser spots of the three-laser point target image and the three-dimensional spatial coordinates of the three laser points in the three-laser point target coordinate system; the tunnel boring machine body posture solution model based on the three-laser spot positioning features takes the center coordinates of the three laser spots of the three-laser point target image and the three-dimensional spatial coordinates of the three laser points in the three-laser point target coordinate system as input, and takes the position and attitude angle of the tunnel boring machine body in the tunnel coordinate system as output.
2. According to the method for determining the position and posture of a tunnel boring machine body based on three laser point targets according to claim 1, it is characterized in that: The method of performing laser spot area segmentation on the three-laser point target image by using the color component constraint and the Euclidean distance constraint specifically includes: Each pixel in the three-laser spot target image is judged according to the color space constraint to determine the initial laser spot pixel cluster segmentation area set; The maximum gray value in the initial laser spot pixel cluster segmentation area set is determined as the adaptive gray threshold of the current target image; According to the adaptive grayscale threshold, the three-laser point target image is binarized and segmented using the Otsu threshold segmentation algorithm. According to the statistical value of the pixel points in the connected area of the image after the above binary segmentation processing and the statistical value threshold of the pixel points in the connected area, the image obtained by the binary segmentation processing is subjected to secondary segmentation processing; The Euclidean distance constraint is used to screen the image after secondary segmentation to determine the area of the laser spot.
3. The method for determining the position and posture of a tunnel boring machine body based on three laser point targets according to claim 1 is characterized in that: The laser spot sub-pixel center positioning algorithm using the improved Hough circle transform is used to position the region segmented image and determine the center coordinates of the three laser spots, specifically including: The laser spot area is processed using Canny edge detection to determine the initial pixel clustering set of the edge of the laser spot contour; The Sobel gradient operator is used to extract the pixel cluster set of the initial laser spot contour edge to determine the gradient of the laser spot contour edge; Utilizing the symmetric geometric constraint of the gradient of the laser spot contour edge, the pixel points in the initial pixel point clustering set of the laser spot contour edge are screened to determine the pixel point clustering set of the laser spot contour edge from which the noise interference is filtered out; The Hough circle transform is used to process the pixel clustering set of the contour edge of the laser spot after filtering out the interference of noise points, and the sub-pixel center coordinates of the laser spot are determined.
4. A tunnel boring machine body posture determination system based on three laser point targets, characterized in that: include: A three-laser point target construction module is used to construct a three-laser point target based on three laser spots emitted by three mining laser pointers placed on the top of the tunnel of the excavation working face; The calibration module uses a total station to calibrate the three-laser point target, determine the three-dimensional spatial coordinates of the three laser emission points under the three-laser point target coordinates, and the relative posture conversion relationship between the three-laser point target coordinate system and the tunnel coordinate system of the excavation working face; Three-laser point target image acquisition module, used to acquire three-laser point target images using a mining camera installed at the rear of the tunnel boring machine; The laser spot area segmentation module is used to perform laser spot area segmentation on the three-laser point target image using color component constraints and Euclidean distance constraints; The center coordinate determination module is used to locate the region segmented image using the laser spot sub-pixel center positioning algorithm of the improved Hough circle transform to determine the center coordinates of the three laser spots; The tunnel boring machine body posture determination module is used to determine the position and posture angle of the tunnel boring machine body in the tunnel coordinate system according to the tunnel boring machine body posture solution model based on the three-laser spot positioning feature, the center coordinates of the three laser spots of the three-laser point target image, and the three-dimensional spatial coordinates of the three laser points in the three-laser point target coordinate system; the tunnel boring machine body posture solution model based on the three-laser spot positioning feature takes the center coordinates of the three laser spots of the three-laser point target image and the three-dimensional spatial coordinates of the three laser points in the three-laser point target coordinate system as input, and takes the position and posture angle of the tunnel boring machine body in the tunnel coordinate system as output.
5. The system for determining the position and posture of a tunnel boring machine body based on three laser point targets according to claim 4 is characterized in that: The laser spot area segmentation module specifically includes: An initial laser spot pixel point clustering segmentation region set determination unit is used to determine an initial laser spot pixel point clustering segmentation region set by judging each pixel point in the three-laser point target image according to the color space constraint; An adaptive grayscale threshold determination unit, used to determine the maximum grayscale value in the initial laser spot pixel cluster segmentation area set as the adaptive grayscale threshold of the current target image; A binary segmentation processing unit is used to perform binary segmentation processing on the three-laser point target image using an Otsu threshold segmentation algorithm according to an adaptive grayscale threshold; A secondary segmentation unit is used to segment the image after the binary segmentation processing according to the statistical values of the pixels in the connected region set in the image after the binary segmentation processing and the statistical threshold of the pixels in the connected region; The laser spot area determination unit is used to screen the image after secondary segmentation by using the Euclidean distance constraint to determine the area of the laser spot.
6. The system for determining the position and posture of a tunnel boring machine body based on three laser point targets according to claim 4 is characterized in that: The center coordinate determination module specifically includes: A pixel point clustering set determining unit of the initial laser spot contour edge is used to process the laser spot area by using Canny edge detection to determine the pixel point clustering set of the initial laser spot contour edge; The gradient extraction unit of the laser spot contour edge is used to extract the pixel point clustering set of the initial laser spot contour edge by using the Sobel gradient operator to determine the gradient of the laser spot contour edge; A noise interference filtering unit is used to screen the pixel points in the initial pixel point clustering set of the edge of the laser spot contour by using the symmetric geometric constraint of the gradient of the edge of the laser spot contour, and determine the pixel point clustering set of the edge of the laser spot contour after filtering out the noise interference; The center coordinate determination unit is used to process the pixel point clustering set of the contour edge of the laser spot after filtering out the interference of the noise points by using Hough circle transformation, so as to determine the sub-pixel center coordinate of the laser spot.
