System and method for measuring stroke of long oil cylinder of fully mechanized coal mining face based on binocular vision sensor

Abstract

The invention discloses a system and a method for measuring the stroke of a long oil cylinder of a fully mechanized coal mining face based on a binocular vision sensor. The system comprises the binocular vision sensor, a holder and an oil cylinder piston rod calibration disc, wherein the holder has double rotational degrees of freedom in the horizontal direction and the vertical direction and is used for bearing the binocular vision sensor and adjusting the angle change of the binocular vision sensor in the horizontal direction and the vertical direction; the oil cylinder piston rod calibration disc is printed on the surface of a piston rod of the long oil cylinder based on a laser surface treatment process and is used for calibrating the binocular vision sensor; the binocular vision sensor is arranged right above the long oil cylinder and used for measuring the stroke of the long oil cylinder at a vertically downward angle after calibration is completed. According to the system, the binocular vision sensor with the holder structure is reasonably calibrated, the stroke data of the long oil cylinder can be accurately measured, and the accuracy and convenience of stroke measurement of the long oil cylinder are improved.

Description

Technical Field

[0001] The present application relates to the technical field of underground mine data collection, and in particular to a system and method for measuring the long oil cylinder stroke of a fully mechanized mining face based on a binocular vision sensor. Background Art

[0002] Currently, many devices in fully mechanized mining face operations are driven by hydraulic cylinders, such as the hydraulic support pullers, the scraper conveyor pushers, the advanced hydraulic support movers, and the movement of the transfer machine and crusher. To achieve precise control of these devices, it is necessary to measure the stroke of the corresponding hydraulic cylinders (referred to as cylinders in this application).

[0003] In the related art, the displacement change of the piston rod of the oil cylinder is generally sensed by arranging a magnetic ring sensor on the inner diameter of the oil cylinder, thereby realizing the measurement of the displacement of the oil cylinder. However, the measurement method in the above-mentioned related art is only applicable to the measurement of the oil cylinder with a shorter stroke in the comprehensive mining working surface. In actual applications, there are also oil cylinders with a longer stroke in the comprehensive mining working surface (which may be referred to as long oil cylinders in this application). For example, the oil cylinder used for the self-movement of the transfer machine is the longest in the working surface, which can reach about 2.1m, and is also called the Madiel mechanism. However, due to the size limitation of the measurement of the magnetic ring sensor, the magnetic ring sensor is not applicable to the measurement of the long oil cylinder stroke of the Madiel mechanism. Therefore, under normal circumstances, the Madiel mechanism underground is not equipped with a sensor, which makes it impossible to measure the stroke of the long oil cylinder.

[0004] Therefore, how to accurately measure the stroke of the long oil cylinder in the fully mechanized mining working face has become an urgent problem that needs to be solved. Summary of the Invention

[0005] The purpose of this application is to solve one of the above technical problems at least to a certain extent.

[0006] To this end, the first objective of this application is to propose a system for measuring the stroke of long oil cylinders in fully mechanized mining working faces based on a binocular vision sensor. By properly calibrating a binocular vision sensor with a pan-tilt structure, this system can accurately measure the stroke data of long oil cylinders, improving the accuracy and convenience of long oil cylinder stroke measurement and resolving the difficulty of long oil cylinder stroke detection in fully mechanized mining working faces.

[0007] The second purpose of this application is to propose a method for measuring the long cylinder stroke of a fully mechanized mining working face based on a binocular vision sensor.

[0008] The third purpose of this application is to propose a device for measuring the long cylinder stroke of a fully mechanized mining working face based on a binocular vision sensor.

[0009] The fourth object of this application is to provide a computer-readable storage medium.

[0010] To achieve the above-mentioned purpose, the first aspect of the present application proposes a measurement system for the long oil cylinder stroke of a fully mechanized mining face based on a binocular vision sensor, the system comprising: a binocular vision sensor, a pan-tilt platform and a cylinder piston rod calibration plate; wherein,

[0011] The platform has two rotational degrees of freedom in the horizontal and vertical directions, and is used to carry the binocular vision sensor and adjust the angle change of the binocular vision sensor in the horizontal and vertical directions;

[0012] The oil cylinder piston rod calibration plate is printed on the surface of the piston rod of the long oil cylinder to be measured based on a laser surface treatment process, and the oil cylinder piston rod calibration plate is used to calibrate the binocular vision sensor;

[0013] The binocular vision sensor is arranged directly above the long oil cylinder. The binocular vision sensor is used to measure the stroke of the long oil cylinder at a vertical downward angle after calibration.

[0014] Optionally, in some embodiments, the pan-tilt head is specifically used to: when measuring the stroke of the long oil cylinder, adjust the binocular vision sensor to face the long oil cylinder vertically downward; when not measuring the stroke of the long oil cylinder, adjust the binocular vision sensor to a horizontal direction.

[0015] Optionally, in some embodiments, the binocular vision sensor is also used to collect video monitoring data of the fully mechanized mining working face in the horizontal direction.

[0016] To achieve the above-mentioned object, the second aspect of the present invention proposes a method for measuring the long oil cylinder stroke of a fully-mechanized mining working face based on a binocular vision sensor, which is applied to the long oil cylinder stroke measurement system of a fully-mechanized mining working face based on a binocular vision sensor of the first aspect. The method comprises:

[0017] When it is necessary to measure the stroke of the long oil cylinder to be measured, the binocular vision sensor is adjusted to face the long oil cylinder vertically downward through the dual-rotational degree of freedom pan-tilt platform, wherein the binocular vision sensor is the original sensor in the fully mechanized mining working face;

[0018] Calibrate the binocular vision sensor by printing a cylinder piston rod calibration disk on the surface of the piston rod of the long cylinder in advance based on a laser surface treatment process;

[0019] The stroke data of the long oil cylinder is measured by the calibrated binocular vision sensor.

[0020] Optionally, in some embodiments, before calibrating the binocular vision sensor, the method further includes: during the extension and retraction of the piston rod, cleaning the cylinder piston rod calibration disk through the sealing structure of the long cylinder.

[0021] Optionally, in some embodiments, measuring the stroke data of the long cylinder by the calibrated binocular vision sensor includes: preprocessing the image data collected by the binocular vision sensor; performing feature processing and depth calculation on the preprocessed image to obtain the displacement information of the long cylinder; and generating overall three-dimensional scene information of the long cylinder movement process by combining the displacement information and the angle adjustment data output by the pan-tilt head.

[0022] Optionally, in some embodiments, after the calibrated binocular vision sensor measures the stroke data of the long cylinder, it also includes: adjusting the binocular vision sensor to a horizontal direction through the pan-tilt head; and collecting video monitoring data of the comprehensive mining working face in the horizontal direction through the binocular vision sensor.

[0023] To achieve the above-mentioned object, the third aspect of the present invention proposes a device for measuring the long oil cylinder stroke of a fully mechanized mining working face based on a binocular vision sensor, the device comprising:

[0024] An adjustment module is used to adjust the binocular vision sensor to face the long oil cylinder vertically downward through a dual-rotational-degree-of-freedom pan-tilt platform when the stroke of the long oil cylinder to be measured needs to be measured, wherein the binocular vision sensor is an existing sensor in the fully mechanized mining working face;

[0025] a calibration module, configured to calibrate the binocular vision sensor by using a cylinder piston rod calibration disk pre-printed on the surface of the piston rod of the long cylinder based on a laser surface treatment process;

[0026] The measuring module is used to measure the stroke data of the long oil cylinder through the calibrated binocular vision sensor.

[0027] To achieve the above-mentioned purpose, the fourth aspect of the present invention proposes a computer-readable storage medium on which a computer program is stored. When the computer program is executed by a processor, it implements the method for measuring the long cylinder stroke of the comprehensive mining working face based on the binocular vision sensor as described in any one of the embodiments of the second aspect above.

[0028] The technical solutions provided by the embodiments of this application bring at least the following beneficial effects:

[0029] This application adjusts the existing binocular vision sensor in the fully mechanized mining face, adding a pan-tilt system with dual horizontal and vertical degrees of freedom to adjust the sensor's monitoring angle. The dual-rotational-freedom pan-tilt binocular vision sensor is then positioned directly above the long oil cylinder. Laser surface treatment is also employed to print a calibration disc onto the surface of the cylinder piston rod for calibrating the binocular vision sensor. Since laser surface treatment removes minimal material from the piston rod surface, the long oil cylinder's tightness is ensured. The calibrated binocular vision sensor can thus accurately measure the stroke changes of the long oil cylinder, enabling data collection. By adjusting the angle changes of the pan-tilt binocular vision sensor, this application can monitor the operating status of the working face equipment, ensuring the safety of operators, and detect the stroke changes of the long oil cylinder. Using a properly calibrated binocular vision sensor, high-precision stroke monitoring at the millimeter or even micrometer level is achieved. Consequently, this application improves the accuracy and convenience of long oil cylinder stroke measurement, increases the utilization rate of monitoring equipment, and reduces the cost of long oil cylinder stroke measurement. This facilitates precise control of the transfer machine's self-movement and enhances the data perception capabilities of the entire coal mine working face.

[0030] Additional aspects and advantages of the present application will be given in part in the description below, and in part will become apparent from the description below, or will be learned through practice of the present application. BRIEF DESCRIPTION OF THE DRAWINGS

[0031] The above and / or additional aspects and advantages of the present application will become apparent and easily understood from the following description of the embodiments in conjunction with the accompanying drawings, in which:

[0032] Figure 1 This is a schematic diagram of the structure of a measurement system for the long oil cylinder stroke of a fully mechanized mining face based on a binocular vision sensor proposed in an embodiment of the present application;

[0033] Figure 2 A schematic diagram of a calibration plate located on a long oil cylinder piston rod proposed in an embodiment of the present application;

[0034] Figure 3 This is a flow chart of a method for measuring the long oil cylinder stroke of a fully mechanized mining face based on a binocular vision sensor, as proposed in an embodiment of the present application;

[0035] Figure 4 This is a structural schematic diagram of a device for measuring the long oil cylinder stroke of a fully mechanized mining working face based on a binocular vision sensor proposed in an embodiment of the present application. DETAILED DESCRIPTION

[0036] The following describes in detail embodiments of the present application, examples of which are shown in the accompanying drawings, wherein the same or similar reference numerals throughout represent the same or similar elements or elements having the same or similar functions. The embodiments described below with reference to the accompanying drawings are exemplary and are intended to be used to explain the present application, and should not be construed as limiting the present application.

[0037] The following describes, with reference to the accompanying drawings, a system and method for measuring the long oil cylinder stroke of a fully mechanized mining face based on a binocular vision sensor in an embodiment of the present application.

[0038] Figure 1 This is a structural diagram of a measurement system for the long oil cylinder stroke of a fully mechanized mining face based on a binocular vision sensor proposed in an embodiment of the present application, as shown in FIG. Figure 1 As shown, the system includes: a binocular vision sensor 1, a pan / tilt head 2 and a cylinder piston rod calibration plate 3.

[0039] The binocular vision sensor 1 is an existing sensor device within the fully mechanized mining face. Equipment such as transfer machines using long oil cylinders are typically located in areas such as the transport lanes within the fully mechanized mining face. These areas typically require cameras to monitor the working status of the equipment and the activities of operators. Therefore, this application utilizes a binocular vision sensor, a common sensor in coal mine working faces, to improve the economic efficiency of long oil cylinder stroke measurement.

[0040] The platform 2 has two rotational degrees of freedom in the horizontal and vertical directions. The platform 2 is used to carry the binocular vision sensor 1 and adjust the angle change of the binocular vision sensor 1 in the horizontal and vertical directions.

[0041] Specifically, the present application improves the existing binocular vision sensor by adding a pan-tilt structure with dual rotational degrees of freedom in the horizontal and vertical directions, thereby obtaining a pan-tilt binocular vision sensor. The pan-tilt structure can rotate, pitch, and perform other movements within a certain angle range. It can expand the field of view of the binocular vision sensor 1, enabling it to cover a wider area and realize the measurement of objects in different directions and positions.

[0042] The pan / tilt head 2 of the present application has dual rotational degrees of freedom in the horizontal and vertical directions, that is, it can adjust the angle of the binocular vision sensor 1 along the X-axis and Y-axis. As a possible implementation method, the pan / tilt head 2 can adopt a structure such as an integrated high-speed dome camera, with horizontal and pitch angle rotation functions and high preset position repeatability, so as to accurately control the measurement angle of the binocular vision sensor 1.

[0043] The oil cylinder piston rod calibration plate 3 is printed on the piston rod surface of the long oil cylinder to be measured based on the laser surface treatment process. The oil cylinder piston rod calibration plate 3 is used to calibrate the binocular vision sensor.

[0044] Specifically, such as Figure 2 As shown, this application uses a laser surface treatment process to print the oil cylinder piston rod calibration plate 3 onto the surface of the long oil cylinder piston rod for calibration of the binocular vision sensor 1. The laser surface treatment process removes very little material from the piston rod surface, avoiding affecting its sealing, and can ensure the accuracy and quality of the calibration plate, thereby ensuring the accuracy of the calibration results. As an example, Figure 2 As shown, the cylinder piston rod calibration plate 3 is composed of a pattern with strict geometric characteristics, which can be Figure 2 The checkerboard shown.

[0045] The binocular vision sensor 1 is arranged just above the long oil cylinder. The binocular vision sensor 1 is used to measure the stroke of the long oil cylinder at a vertical downward angle after calibration.

[0046] Specifically, the calibrated binocular vision sensor 1 can accurately measure the stroke change of the long oil cylinder. By performing calculation and analysis on the image data collected by the binocular vision sensor 1, stroke data such as the displacement change of the long oil cylinder can be obtained.

[0047] Among them, reference Figure 1 As reflected in the positional arrangement of the various devices, this application adjusts the installation position of the binocular vision sensor 1 and sets it just above the long oil cylinder in order to collect the displacement image data of the long oil cylinder.

[0048] In one embodiment of the present application, the pan-tilt head 2 is specifically used to: when measuring the stroke of the long oil cylinder, adjust the binocular vision sensor to face the long oil cylinder vertically downward; when not measuring the stroke of the long oil cylinder, adjust the binocular vision sensor to a horizontal direction.

[0049] Specifically, when measuring the stroke of the long oil cylinder, the pan-tilt head 2 adjusts the angle of the binocular vision sensor 1 to face the cylinder vertically downward, allowing the binocular vision sensor 1 to comprehensively collect data on the cylinder's stroke from a vertically downward angle. When measuring the cylinder's stroke is not necessary, the pan-tilt head 2 adjusts the binocular vision sensor 1 to face horizontally. Furthermore, in this embodiment, the binocular vision sensor is also used to collect horizontal video surveillance data of the fully mechanized mining face.

[0050] The horizontal video monitoring data of the fully-mechanized mining face includes monitoring data of various equipment and personnel in the fully-mechanized mining face tunnel. Therefore, this application can measure the stroke of the long oil cylinder and realize the video monitoring function of the fully-mechanized mining face when the long oil cylinder is not in operation, thereby improving the utilization rate of the binocular vision sensor 1.

[0051] In summary, the binocular vision sensor-based system for measuring the stroke of long oil cylinders in a fully mechanized mining face, according to an embodiment of the present application, modifies the existing binocular vision sensor in the fully mechanized mining face by adding a pan-tilt system with dual horizontal and vertical degrees of freedom to adjust the sensor's monitoring angle. The dual-rotational pan-tilt binocular vision sensor is then positioned directly above the long oil cylinder. Laser surface treatment is also employed to print a calibration disc onto the surface of the cylinder piston rod for calibrating the binocular vision sensor. Laser surface treatment minimizes material removal from the piston rod surface, ensuring the long oil cylinder's tightness. The calibrated binocular vision sensor can thus accurately measure the stroke change of the long oil cylinder, enabling data collection. By adjusting the angle of the pan-tilt binocular vision sensor, this system not only monitors the operating status of the working face equipment, ensuring operator safety, but also detects the stroke change of the long oil cylinder. Using a properly calibrated binocular vision sensor, high-precision stroke monitoring at the millimeter or even micrometer level is possible. This system thus improves the accuracy and convenience of long oil cylinder stroke measurement, increases the utilization rate of monitoring equipment, and reduces the cost of long oil cylinder stroke measurement. It is conducive to the precise control of the transfer machine's self-movement and enhances the data perception capability of the entire working face of the coal mine.

[0052] In order to more clearly illustrate the specific implementation process of measuring the long oil cylinder stroke of the fully mechanized mining working face in this application, the following is a detailed description of a method for measuring the long oil cylinder stroke of the fully mechanized mining working face based on a binocular vision sensor proposed in an embodiment of this application. This method is applied to the measurement system for the long oil cylinder stroke of the fully mechanized mining working face based on a binocular vision sensor in the above embodiment, that is, the measurement method of this embodiment is realized by performing relevant control on the system in the above embodiment. The various devices in the measurement system involved in this method can be referred to the above embodiment, and will not be repeated here. The execution subject of the measurement method of this application can be the relevant control equipment in the above system.

[0053] Figure 3 This is a flow chart of a method for measuring the long oil cylinder stroke of a fully mechanized mining working face based on a binocular vision sensor proposed in an embodiment of the present application, as shown in FIG. Figure 3 As shown, the method includes the following steps:

[0054] Step S101: When the stroke of the long oil cylinder to be measured needs to be measured, the binocular vision sensor is adjusted to face the long oil cylinder vertically downward through a dual-rotational-degree-of-freedom pan-tilt platform.

[0055] The binocular vision sensor is the original sensor in the fully mechanized mining face. This application adjusts the original camera in the fully mechanized mining face and places it directly above the self-propelled cylinder of the loader. At the same time, it is replaced with a pan-tilt binocular vision sensor with two degrees of freedom in the X and Y axes.

[0056] Specifically, when it is necessary to measure the stroke of the long cylinder to be measured, for example, after receiving the long cylinder movement instruction, or detecting that the long cylinder starts to move, the binocular vision sensor is adjusted to face the long cylinder vertically downward through the dual-rotational degree of freedom pan-tilt head.

[0057] Step S102: Calibrate the binocular vision sensor using a cylinder piston rod calibration disk pre-printed on the surface of the piston rod of the long cylinder based on a laser surface treatment process.

[0058] Specifically, a laser surface treatment method is used to print a cylinder piston rod calibration disk onto the surface of the cylinder piston rod for calibration of the binocular vision sensor.

[0059] As a possible implementation method, calibrating the binocular vision sensor using the cylinder piston rod calibration disk includes the following steps:

[0060] Step S11: Acquire images. Images of the cylinder piston rod calibration disk are captured at various angles and positions. This step typically uses control software to automatically control a binocular vision sensor to capture images. Ensure that the cylinder piston rod calibration disk is clearly visible in the image and covers a sufficient field of view.

[0061] Step S12: Feature point detection. Image processing algorithms are used to identify feature points on the cylinder piston rod calibration plate from the image. For example, feature matching algorithms that can be used include SIFT, SURF, and ORB. As an example, the SIFT algorithm can detect unique and easily matched feature points and calculate their descriptors in the image, thereby achieving feature point matching.

[0062] Step S13: Calculate parameters. Calculate camera parameters based on the detected feature point positions. These parameters include intrinsic parameters (e.g., focal length, principal point position, distortion coefficients, etc.) and extrinsic parameters (e.g., rotation matrix and translation vector). These parameters are typically calculated using geometric or optimization methods.

[0063] Step S14: Verify accuracy. Verify the accuracy of the calibration parameters by measuring objects at known distances. Calibration accuracy can be verified by reconstructing the 3D positions of corner points. If the calibration results are inaccurate, readjust the calibration process, check the placement of the calibration disk, the quality of image acquisition, and the accuracy of parameter calculations.

[0064] Step S15: Optimize and adjust. In practical applications, further optimization and adjustment of the calibration results may be required. For example, parameters such as parallax range and lighting conditions can be adjusted based on specific application scenarios and requirements in different areas of the fully mechanized mining face to improve measurement performance and stability.

[0065] Therefore, the calibration of the binocular vision sensor can be completed through the above steps, and accurate data can be provided in subsequent stroke measurement.

[0066] In an embodiment of the present application, before calibrating the binocular vision sensor, the oil cylinder piston rod calibration disc is cleaned by the sealing structure of the long oil cylinder during the extension and retraction of the piston rod.

[0067] Specifically, due to the oil cylinder sealing structure, the oil cylinder piston rod has self-cleaning properties during extension and retraction, that is, the piston rod can be automatically cleaned by the oil cylinder sealing structure, so that the oil cylinder piston rod always maintains a clear surface. The oil cylinder piston rod calibration disc on the surface of the piston rod can be cleaned, and the oil cylinder piston rod calibration disc is cleaned by the sealing structure of the long oil cylinder during the retraction of the piston rod in the last stroke measurement. Therefore, a clear oil cylinder piston rod calibration disc can be obtained before calibration in the current measurement process, ensuring the accuracy of the calibration result.

[0068] As an example, the sealing structure of the long oil cylinder includes piston rod sealing elements such as lip seal rings, O-shaped seal rings, and double-acting seal rings, and various sealing grooves can also be used.

[0069] It should be noted that the laser surface treatment process used in the present application removes a small amount of material from the surface of the piston rod and does not affect its sealing performance, thereby ensuring the automatic cleaning effect of the oil cylinder piston rod calibration disc and improving the accuracy of the calibration result.

[0070] Step S103: measuring the stroke data of the long oil cylinder by the calibrated binocular vision sensor.

[0071] Specifically, the stroke change of the long oil cylinder can be accurately measured by the calibrated binocular vision sensor, and the detection accuracy can reach millimeter level or even micron level.

[0072] In an embodiment of the present application, the stroke data of the long oil cylinder is measured by the calibrated binocular vision sensor, including the following steps:

[0073] Step S21: pre-processing the image data collected by the binocular vision sensor;

[0074] Specifically, when the binocular vision sensor collects images, two cameras simultaneously capture the long oil cylinder to obtain two images with parallax. Then, the collected images are pre-processed by denoising and enhancing to improve the image quality and facilitate subsequent feature extraction and matching.

[0075] Step S22: performing feature processing and depth calculation on the pre-processed images to obtain displacement information of the long oil cylinder.

[0076] Specifically, feature extraction and matching are performed first to extract feature points from the two images, such as corners and edges, and then the matching points between them are determined through relevant algorithms to calculate the disparity.

[0077] Then, depth calculation is performed. According to the parallax, the focal length of the camera and the baseline length between the two cameras, the depth information of the long cylinder is calculated using the principle of triangulation. Based on the depth information, the displacement change data in the currently collected image can be obtained, and then the long cylinder stroke can be obtained.

[0078] Step S23 , combining the displacement information and the angle adjustment data output by the pan / tilt head to generate the overall three-dimensional scene information of the long cylinder movement process.

[0079] Specifically, this step also involves fusing the pan / tilt head's angle control data with the image data. During the stroke measurement process, the binocular vision sensor continuously captures images. During this process, the pan / tilt head dynamically adjusts the camera's orientation as needed to acquire image data from different angles. This data is then fused together to provide more comprehensive 3D scene information. Specifically, by determining the acquisition angle corresponding to the displacement change data in each image and fusing the image data from these different angles, comprehensive 3D scene information can be obtained for the entire long cylinder structure, from the start to the end of its displacement.

[0080] Therefore, this embodiment can improve the comprehensiveness of the measured travel information.

[0081] Based on the above embodiment, after measuring the stroke data of the long cylinder through the calibrated binocular vision sensor, it also includes: adjusting the binocular vision sensor to a horizontal direction through a pan-tilt platform; and collecting video monitoring data of the comprehensive mining working face in the horizontal direction through the binocular vision sensor.

[0082] Specifically, when measuring the stroke of the long hydraulic cylinder is not necessary, the pan / tilt system adjusts the binocular vision sensor's angle to the horizontal. Furthermore, the binocular vision sensor can also collect horizontal video surveillance data of the fully mechanized mining face, including monitoring data on various equipment and personnel within the fully mechanized mining face tunnels.

[0083] Therefore, the present application can not only measure the stroke of the long oil cylinder, but also realize the video monitoring function of the comprehensive mining working face when the long oil cylinder is not moving.

[0084] In summary, the binocular vision sensor-based method for measuring the stroke of long oil cylinders in a fully mechanized mining face implemented in this application, by adjusting the angle of the pan-tilt binocular vision sensor, can both monitor the working status of the working face equipment and ensure the safety of workers, and detect changes in the stroke of the long oil cylinder. Using a properly calibrated binocular vision sensor, high-precision stroke monitoring at the millimeter or even micron level can be achieved. This method improves the accuracy and convenience of long oil cylinder stroke measurement, increases the utilization rate of monitoring equipment, and reduces the cost of long oil cylinder stroke measurement.

[0085] To implement the above-mentioned embodiment, this application also proposes a device for measuring the long oil cylinder stroke of a fully-mechanized mining face using a binocular vision sensor. This device corresponds to the method for measuring the long oil cylinder stroke of a fully-mechanized mining face using a binocular vision sensor described in the second embodiment. As a possible implementation, this device can be the control device in the measurement system of the first embodiment, thereby controlling various devices in the measurement system. Figure 4 This is a schematic diagram of the structure of a device for measuring the long oil cylinder stroke of a fully mechanized mining face based on a binocular vision sensor proposed in an embodiment of the present application. Figure 4 As shown, the device includes: an adjustment module 100 , a calibration module 200 and a measurement module 300 .

[0086] Among them, the adjustment module 100 is used to adjust the binocular vision sensor to face vertically downward directly towards the long oil cylinder through a dual-rotational degree-of-freedom pan-tilt head when it is necessary to measure the stroke of the long oil cylinder to be measured, wherein the binocular vision sensor is the original sensor in the comprehensive mining working face.

[0087] The calibration module 200 is used to calibrate the binocular vision sensor by using a cylinder piston rod calibration disk pre-printed on the surface of the piston rod of the long cylinder based on a laser surface treatment process.

[0088] The measurement module 300 is used to measure the stroke data of the long oil cylinder through a calibrated binocular vision sensor.

[0089] In one embodiment of the present application, the device also includes a monitoring module, which is specifically used to: adjust the binocular vision sensor to a horizontal direction through a pan-tilt platform; and collect video monitoring data of the comprehensive mining working face in the horizontal direction through the binocular vision sensor.

[0090] It should be noted that the above explanation of the embodiment of the method for measuring the long cylinder stroke of the comprehensive mining working face based on the binocular vision sensor is also applicable to the device of this embodiment. The specific process of each module in the device to realize its function can be referred to the description in the above-mentioned related embodiments and will not be repeated here.

[0091] To sum up, the device for measuring the long oil cylinder stroke of the comprehensive mining working face based on the binocular vision sensor in the embodiment of the present application can realize high-precision long oil cylinder stroke monitoring by using the binocular vision sensor after reasonable calibration, thereby improving the accuracy and convenience of long oil cylinder stroke measurement, improving the utilization rate of the monitoring equipment, and reducing the cost of long oil cylinder stroke measurement.

[0092] In order to implement the above-mentioned embodiments, the present application also proposes a computer-readable storage medium on which a computer program is stored. When the computer program is executed by a processor, it implements the method for measuring the long cylinder stroke of the comprehensive mining working face based on a binocular vision sensor as described in any one of the aforementioned second aspect embodiments of the present application.

[0093] It should be noted that it should be understood that various parts of the present application can be implemented using hardware, software, firmware, or a combination thereof. In the above embodiments, multiple steps or methods can be implemented using software or firmware stored in a memory and executed by a suitable instruction execution system. For example, if implemented using hardware, as in another embodiment, any one of the following technologies known in the art or a combination thereof can be used to implement: a discrete logic circuit having a logic gate circuit for implementing a logic function on a data signal, an application-specific integrated circuit having a suitable combination of logic gate circuits, a programmable gate array (PGA), a field programmable gate array (FPGA), etc.

[0094] In addition, in the description of this application, the terms "center", "up", "down", "left", "right", "vertical", "horizontal", "inside", "outside", etc., indicating the orientation or position relationship, are based on the orientation or position relationship shown in the accompanying drawings. They are only for the convenience of describing this application and simplifying the description, and do not indicate or imply that the device or element referred to must have a specific orientation, be constructed and operated in a specific orientation. Therefore, they should not be understood as limiting the present invention.

[0095] Furthermore, the terms "first" and "second" are used for descriptive purposes only and should not be construed as indicating or implying relative importance or implicitly specifying the number of the technical features being referred to. Thus, a feature defined as "first" or "second" may explicitly or implicitly include at least one such feature. In the description of the present invention, "plurality" means at least two, such as two, three, etc., unless otherwise specifically defined.

[0096] In the present invention, unless otherwise specified or limited, the terms "installed," "connected," "connect," "fixed," etc. should be understood in a broad sense. For example, they can refer to fixed connection, detachable connection, or integration; mechanical connection, electrical connection; direct connection, or indirect connection through an intermediate medium; internal communication between two components, or interaction between two components, unless otherwise specified. Those skilled in the art will understand the specific meanings of the above terms in the present invention based on specific circumstances.

[0097] In the description of this specification, the description with reference to the terms "one embodiment", "some embodiments", "example", "specific example", or "some examples" means that the specific features, structures, materials or characteristics described in conjunction with the embodiment or example are included in at least one embodiment or example of the present application. In this specification, the schematic representations of the above terms do not necessarily refer to the same embodiment or example. Moreover, the specific features, structures, materials or characteristics described can be combined in any one or more embodiments or examples in a suitable manner. In addition, those skilled in the art can combine and combine different embodiments or examples described in this specification and features of different embodiments or examples without contradiction.

[0098] Although the embodiments of the present application have been shown and described above, it can be understood that the above embodiments are exemplary and cannot be understood as limitations on the present application. Ordinary technicians in this field can change, modify, replace and modify the above embodiments within the scope of the present invention.

Claims

1. A measurement system for the long oil cylinder stroke of a fully mechanized mining face based on a binocular vision sensor, characterized in that: include: Binocular vision sensor, pan / tilt and cylinder piston rod calibration plate; Among them, The platform has two rotational degrees of freedom in the horizontal and vertical directions, and is used to carry the binocular vision sensor and adjust the angle change of the binocular vision sensor in the horizontal and vertical directions; The oil cylinder piston rod calibration plate is printed on the surface of the piston rod of the long oil cylinder to be measured based on a laser surface treatment process, and the oil cylinder piston rod calibration plate is used to calibrate the binocular vision sensor; The binocular vision sensor is arranged directly above the long oil cylinder. The binocular vision sensor is used to measure the stroke of the long oil cylinder at a vertical downward angle after calibration.

2. The system according to claim 1, wherein: The pan / tilt platform is specifically used for: When measuring the stroke of the long oil cylinder, the binocular vision sensor is adjusted to face the long oil cylinder vertically downward; Without measuring the stroke of the long oil cylinder, the binocular vision sensor is adjusted to a horizontal direction.

3. The system according to claim 2, characterized in that The binocular vision sensor is also used for: Collect video monitoring data of the fully mechanized mining working face in the horizontal direction.

4. A method for measuring the long oil cylinder stroke of a fully mechanized mining face based on a binocular vision sensor, characterized in that: The method for measuring the long oil cylinder stroke of a fully mechanized mining face based on a binocular vision sensor according to any one of claims 1 to 3 comprises the following steps: When it is necessary to measure the stroke of the long oil cylinder to be measured, the binocular vision sensor is adjusted to face the long oil cylinder vertically downward through the dual-rotational degree of freedom pan-tilt platform, wherein the binocular vision sensor is the original sensor in the fully mechanized mining working face; Calibrate the binocular vision sensor by printing a cylinder piston rod calibration disk on the surface of the piston rod of the long cylinder in advance based on a laser surface treatment process; The stroke data of the long oil cylinder is measured by the calibrated binocular vision sensor.

5. The method according to claim 4, characterized in that Before calibrating the binocular vision sensor, the method further includes: During the extension and retraction of the piston rod, the oil cylinder piston rod calibration disk is cleaned through the sealing structure of the long oil cylinder.

6. The method according to claim 4, characterized in that The stroke data of the long oil cylinder measured by the calibrated binocular vision sensor includes: Preprocessing the image data collected by the binocular vision sensor; Performing feature processing and depth calculation on the pre-processed image to obtain displacement information of the long oil cylinder; The overall three-dimensional scene information of the long cylinder movement process is generated by combining the displacement information and the angle adjustment data output by the pan-tilt head.

7. The method according to claim 4, characterized in that After the calibrated binocular vision sensor measures the stroke data of the long oil cylinder, the method further includes: Adjusting the binocular vision sensor to a horizontal direction through the pan-tilt platform; The binocular vision sensor is used to collect video monitoring data of the fully mechanized mining working face in the horizontal direction.

8. A device for measuring the long oil cylinder stroke of a fully mechanized mining face based on a binocular vision sensor, characterized in that: Includes the following modules: An adjustment module is used to adjust the binocular vision sensor to face the long oil cylinder vertically downward through a dual-rotational-degree-of-freedom pan-tilt platform when the stroke of the long oil cylinder to be measured needs to be measured, wherein the binocular vision sensor is an existing sensor in the fully mechanized mining working face; a calibration module, configured to calibrate the binocular vision sensor by using a cylinder piston rod calibration disk pre-printed on the surface of the piston rod of the long cylinder based on a laser surface treatment process; The measuring module is used to measure the stroke data of the long oil cylinder through the calibrated binocular vision sensor.

9. The device according to claim 8, characterized in that Also includes: The monitoring module is specifically used to: Adjusting the binocular vision sensor to a horizontal direction through the pan-tilt platform; The binocular vision sensor is used to collect video monitoring data of the fully mechanized mining working face in the horizontal direction.

10. A computer-readable storage medium having a computer program stored thereon, characterized in that: When the computer program is executed by the processor, the method for measuring the long cylinder stroke of the fully mechanized mining working face based on the binocular vision sensor as described in any one of claims 4 to 7 is implemented.

Images