A plumb line-based component perpendicularity visual monitoring system and method

Abstract

The application relates to a visual monitoring system for the perpendicularity of a component based on a plumb line, which comprises a side plate installed on one side of the component, a pointer strip serving as a plumb line mark and hung on the side plate, the pointer strip being provided with two pointers, namely an upper pointer and a lower pointer, two scales fixed on the side plate and parallel to the horizontal plane, the scales being an upper scale and a lower scale, the end of the upper pointer pointing to the scale of the upper scale, and the end of the lower pointer pointing to the scale of the lower scale, and a camera configured to collect a current image containing the two pointers and the corresponding scales, and an industrial computer configured to recognize the readings of the two pointers on the corresponding scales at the current time according to the current image and calculate the perpendicularity of the component. The pointer strip is hung on the side plate as a plumb line mark, the pointers are used for representing the direction of the plumb line above the two scales, and the scales provide a reference for the horizontal position of the ends of the pointers, so that the structure is simple, installation is convenient, and the visual monitoring system is suitable for different scenes.

Description

Technical Field

[0001] The present invention relates to the technical field of bridge monitoring, and in particular to a component verticality visual monitoring system and method based on a vertical line. Background Art

[0002] Component perpendicularity is the maximum allowable deviation between a component's surface, axis, or edge and a reference line (usually a plumb line or the normal to a horizontal plane). Component perpendicularity is often used to measure how closely a component adheres to a perfect vertical line. In engineering, perpendicularity is a crucial geometric tolerance, ensuring that components meet design requirements during installation or fabrication.

[0003] The verticality of slender components such as bridge piers and towers plays a critical role during both bridge construction and operation. During construction, due to the inherent geometric characteristics of these components, their verticality during installation and alignment controls the accuracy of the component's end positioning. For example, a 0.01° verticality deviation in a 30m-long component can result in an end misalignment of approximately 5mm. This misalignment can further complicate or lead to large errors in the installation of subsequent connectors, impacting the quality of bridge construction. During operation, verticality monitoring of slender components such as piers and towers provides a comprehensive understanding of the overall shape of the bridge's substructure, facilitating timely warnings of bridge collapses caused by natural disasters such as ship collisions or mudslides, minimizing the adverse impact of these disasters on traffic accidents on the bridge.

[0004] In related technologies, methods for measuring the verticality of bridge components include multi-sensor fusion methods and suspended plumb bob methods. For example, the multi-sensor fusion method controls the verticality of components in a more robust manner by integrating the coordinate, elevation, and geodetic inclination information obtained by a total station, a level, and an inclinometer. However, the installation of each device is complex and is only suitable for measuring and controlling a few key components. For example, the suspended plumb bob method involves hanging a plumb bob on the component, placing a scale below, and measuring the verticality by the difference in scale readings. This method, combined with a long plumb bob, can improve measurement accuracy to a certain extent, but it is accompanied by poor environmental adaptability and is more sensitive to environmental vibrations and wind fields. Summary of the Invention

[0005] The present application provides a component verticality visual monitoring system and method based on a heavy plumb line. The first purpose is to solve the technical problem of complex equipment installation in related technologies, and the second purpose is to solve the technical problem of poor environmental adaptability in related technologies.

[0006] In a first aspect, an embodiment of the present application further provides a component verticality visual monitoring system based on a vertical line, comprising:

[0007] Side plate, installed on one side of the component;

[0008] A pointer bar, the pointer bar being hung on the side panel as a vertical line mark, the pointer bar having two pointers, namely an up pointer and a down pointer;

[0009] Two scales, fixed to the side plates and both parallel to the horizontal plane, the scales being an upper scale and a lower scale, the end of the upper pointer pointing to the scale of the upper scale, and the end of the lower pointer pointing to the scale of the lower scale;

[0010] A camera is configured to: capture a current image including the two pointers and the corresponding ruler;

[0011] The industrial computer is configured to: identify the readings of the two pointers on the corresponding scales at the current moment according to the current image, and calculate the verticality of the component.

[0012] In combination with the first aspect, in one embodiment, the component verticality visual monitoring system further includes a housing, the housing includes the side panels, and the housing accommodates the camera and the industrial computer.

[0013] In combination with the first aspect, in one embodiment, the component verticality visual monitoring system further includes a fill light disposed in the housing, and the housing is a closed housing.

[0014] In combination with the first aspect, in one embodiment, there is one camera, and its field of view covers the two pointers and the ruler; or there are two cameras, and their fields of view respectively cover the upper pointer and upper ruler, and the lower pointer and lower ruler.

[0015] In combination with the first aspect, in one embodiment, both ends of the ruler are fixed to the side panels via spacers, so that the ruler is located in front of the pointer bar.

[0016] In combination with the first aspect, in one embodiment, the component verticality visual monitoring system further includes a plurality of control point targets provided on both sides of the scale;

[0017] The industrial computer is further configured to correct jitter deviation of the reading based on the plane constraint according to the control point target.

[0018] In a second aspect, an embodiment of the present application provides a component verticality visual monitoring method based on a vertical line, using any of the component verticality visual monitoring systems described above, the method comprising the following steps:

[0019] Acquire the current image including two pointers and corresponding rulers;

[0020] Identify the readings of the two pointers on the corresponding scales at the current moment according to the current image;

[0021] The verticality of the component is calculated based on the readings.

[0022] In conjunction with the second aspect, in one embodiment, calculating the verticality of the component according to the reading includes:

[0023] The calculation formula is: ;

[0024] The initial state is the state before the side panels are fixed to the components. is the verticality of the component, is the initial verticality; For the current moment The reading of the upper pointer on the upper scale, is the initial reading of the upper pointer on the upper scale; For the current moment The reading of the lower pointer on the lower scale, is the initial reading of the lower pointer on the lower scale; is the distance between the upper and lower scales.

[0025] In conjunction with the second aspect, in one embodiment, identifying the readings of the two pointers on the corresponding scales at the current moment according to the current image includes:

[0026] Establishing a reference coordinate system with the plane of the side plate as a reference plane, using an image area including the pointer end, the reading corresponding to the scale and the adjacent long scale as a pointer template image, and performing template matching between the pointer template image and the current image to obtain a current pointer image and integer pixel coordinates of the pointer;

[0027] Perform line detection on the current pointer image to identify the two oblique lines at the end of the pointer and calculate the coordinates of the intersection point of the two oblique lines ;

[0028] Perform optical character detection on the current pointer image to identify the intersection point The readings of the two nearest long scales are the nearest left scale and the nearest right tick , the corresponding scale vertex coordinates are and ;

[0029] Calculate the reading of the pointer on the corresponding scale at the current moment:

[0030] The calculation formula is: ;

[0031] in, Mark the distance between adjacent long scale marks on the ruler.

[0032] In conjunction with the second aspect, in one embodiment, the component verticality visual monitoring method based on the heavy vertical line further includes: correcting the jitter deviation of the reading based on the plane constraint;

[0033] The jitter deviation of the correction reading based on the plane constraint includes:

[0034] Arrange on both sides of the scale n Control point targets ( n ≥4), the coordinate system takes a control point target as the origin, and the coordinates of the control point target are pre-calibrated ;

[0035] Identify the current time according to the current pointer image The center pixel coordinates of each control point target ;

[0036] Constructing overdetermined equations , solve h ;

[0037] in, ;

[0038] ;

[0039] Correction 、 and The pixel coordinates of

[0040] The correction formula is: .

[0041] The beneficial effects of the technical solutions provided in the embodiments of the present application include:

[0042] The present application provides a component verticality visual monitoring system based on a gravity plumb line. A pointer bar is hung on a side panel. The hanging finger can freely point in the direction of gravity around the hanging point, thereby serving as a gravity plumb line mark. The pointer on the pointer bar is used to represent the direction of the gravity plumb line above two scales. The scale provides a reference for the horizontal position of the pointer end, which makes it easier for machine vision to read the pointer direction to determine the reading reference. The image acquisition and image recognition processes are completed through a camera and an industrial computer. The visual monitoring system has a simple structure and is easy to install and is suitable for different scenarios. BRIEF DESCRIPTION OF THE DRAWINGS

[0043] In order to more clearly illustrate the technical solutions in the embodiments of the present application, the following briefly introduces the drawings required for use in the description of the embodiments. Obviously, the drawings described below are only some embodiments of the present application. For ordinary technicians in this field, other drawings can be obtained based on these drawings without any creative work.

[0044] Figure 1 Schematic diagram of the arrangement of a component verticality visual monitoring system based on a perpendicular line in one embodiment of the present invention.

[0045] Figure 2 Schematic diagram of the front view of the pointer bar in one embodiment of the present invention.

[0046] Figure 3 Schematic diagram of the structure of a control point target in one embodiment of the present invention.

[0047] Figure 4 The figure is a flow chart of a method for visually monitoring component verticality based on a perpendicular line in one embodiment of the present invention.

[0048] Figure 5 Schematic diagram of pointer reading in one embodiment of the present invention.

[0049] In the figure: 1. Outer shell; 11. Side panel; 2. Pointer bar; 3. Pointer; 31. Upper pointer; 32. Lower pointer; 4. Ruler; 41. Upper ruler; 42. Lower ruler; 43. Pad; 5. Camera; 6. Industrial computer; 7. Fill light; 8. Control point target. DETAILED DESCRIPTION

[0050] In order to enable those skilled in the art to better understand the present invention, the following will clearly and completely describe the technical solutions in the embodiments of the present invention in conjunction with the accompanying drawings. 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 this application.

[0051] An embodiment of the present application provides a component verticality visual monitoring system based on a heavy plumb line, the first purpose of which is to solve the technical problem of complex equipment installation in related technologies.

[0052] like Figure 1 and Figure 2 As shown, Figure 1 Schematic diagram of the arrangement of a component verticality visual monitoring system based on a perpendicular line in one embodiment of the present invention. Figure 2 Schematic diagram of the front view of the pointer bar in one embodiment of the present invention.

[0053] This embodiment provides a component verticality visual monitoring system based on a vertical line, which includes:

[0054] Side plate 11, installed on one side of the component;

[0055] Pointer bar 2, the pointer bar 2 is hung on the side plate 11 as a heavy vertical line mark, and the pointer bar 2 has two pointers 3, namely an upper pointer 31 and a lower pointer 32;

[0056] Two scales 4 are fixed to the side plate 11 and are parallel to the horizontal plane. The scales 4 are an upper scale 41 and a lower scale 42. The end of the upper pointer 31 points to the scale of the upper scale 41, and the end of the lower pointer 32 points to the scale of the lower scale 42.

[0057] The camera 5 is configured to: capture a current image including the two pointers 3 and the corresponding ruler 4;

[0058] The industrial computer 6 is configured to: identify the readings of the two pointers 3 on the corresponding scales 4 at the current moment according to the current image, and calculate the verticality of the component.

[0059] This embodiment provides a component verticality visual monitoring system based on a gravity plumb line. A pointer bar is hung on a side panel. The hanging finger can freely point in the direction of gravity around the hanging point, thereby serving as a gravity plumb line mark. The pointer on the pointer bar is used to represent the direction of the gravity plumb line above the two rulers. The ruler provides a reference for the horizontal position of the pointer end, which makes it easier for machine vision to read the pointer direction to determine the reading reference. The image acquisition and image recognition processes are completed by a camera and an industrial computer. The visual monitoring system has a simple structure and is easy to install. It is suitable for different scenarios.

[0060] In one embodiment, the component verticality visual monitoring system further includes a housing 1 , the housing 1 includes a side panel 11 , and the housing 1 accommodates a camera 5 and an industrial computer 6 .

[0061] Through the above solution, all structures are integrated into one shell, which reduces the overall size, makes it more convenient to carry and use, and reduces the impact on the environment.

[0062] If the housing 1 is a cubic structure, it provides installation positions for various structures, and the side panel surface of the pointer bar 2 is installed as a reference plane. When installing the system, the side panel 11 of the housing 1 and one side of the component are fixedly connected by bolts, and the bottom plate of the housing 1 is as parallel to the ground as possible.

[0063] In one embodiment, the housing 1 is a closed housing.

[0064] Through the above solution, the interference of ambient light outside the shell on machine vision readings is isolated, thereby improving measurement accuracy.

[0065] The pointer bar 2 is a reflective pointer bar, and the pointer 3 is a pasted reflective pointer mark. The reflection enhances the local contrast and facilitates the identification of the pointer end. Of course, in other embodiments, the pointer bar 2 and the pointer 3 may also be non-reflective.

[0066] The pointer bar 2 is specifically a long thin plate with a hole on the top, which is suspended on the side plate 11 through a cylindrical shaft. It can freely point in the direction of gravity around the cylindrical shaft, thereby serving as a mark of the vertical line.

[0067] Scales 4 provide a reference for the horizontal position of the end of pointer 3. One scale 4 is installed parallel to the upper and lower sides of side panel 11. Scales 4 are kept as parallel to the bottom plate of housing 1 as possible. When the system is fully vertical, scales 4 should be parallel to the ground plane. Each scale 4 contains long and short scale lines, with specific numbers below the long scale. Short scale lines can be either unnumbered or numbered. At the height of scale 4 installation, upper pointer 31 is located above upper scale 41, and lower pointer 32 is located above lower scale 42. The end of pointer 3 points to the scale on scale 4.

[0068] In one embodiment, both ends of the scale 4 are fixed to the side panels 11 via spacers 43 , so that the scale 4 is located in front of the pointer bar 2 .

[0069] With the above solution, the two ends of the ruler are raised by using the pads, so that the ruler is kept in front of the pointer bar, and the pointer bar is prevented from blocking the ruler.

[0070] The camera 5 is used to observe structures such as the scale 4 and the pointer 3 arranged in the reference plane, and provide raw data for image recognition and coordinate calculation.

[0071] In one embodiment, there is one camera 5 whose field of view covers the two pointers 3 and the ruler 4; or there are two cameras 5 whose fields of view respectively cover the upper pointer 31 and the upper ruler 41, and the lower pointer 32 and the lower ruler 42.

[0072] Through the above solution, a single-camera observation solution or a dual-camera observation solution can be provided according to actual needs, which is more flexible.

[0073] The industrial computer 6 includes a camera acquisition hardware interface, a computing board, a communication board and other structures to realize functions such as image data acquisition, image processing, sag calculation and data transmission.

[0074] In one embodiment, the component verticality visual monitoring system further includes a fill light 7 disposed in the housing 1 .

[0075] Through the above solution, the fill light is used to enhance the illumination of the observation area of ​​the reference plane, so that the illumination of the observation area is uniform, the imaging contrast of the pointer is improved, and the light source is stable and will not produce additional random deviation effects on the imaging.

[0076] In one embodiment, the component verticality visual monitoring system further includes a plurality of control point targets 8 provided on both sides of the scale 4; the industrial computer 6 is further configured to correct the jitter deviation of the reading based on the plane constraint according to the control point targets 8.

[0077] The control point target 8 is located within the field of view of the camera 5 and is used to provide a reference plane coordinate system and a basic reference for suppressing the camera shake effect.

[0078] like Figure 3 As shown, Figure 3 Schematic diagram of the structure of a control point target in one embodiment of the present invention.

[0079] The control point target 8 may be a white circular pattern on a black background. Of course, the control point target 8 may also be other patterns.

[0080] like Figure 4 As shown, Figure 4 The figure is a flow chart of a method for visually monitoring component verticality based on a perpendicular line in one embodiment of the present invention.

[0081] This embodiment also provides a component verticality visual monitoring method based on a vertical line, which uses the component verticality visual monitoring system described above and includes the following steps:

[0082] Step S1, collecting a current image including two pointers 3 and a corresponding scale 4;

[0083] Step S2: Identify the readings of the two pointers 3 on the corresponding scales 4 at the current moment according to the current image;

[0084] Step S3: Calculate the verticality of the component based on the readings.

[0085] like Figure 5 As shown, Figure 5 Schematic diagram of pointer reading in one embodiment of the present invention.

[0086] In one embodiment, step S2, identifying the readings of the two pointers 3 on the corresponding scales 4 at the current moment according to the current image, includes:

[0087] Step S21: establish a reference coordinate system with the plane where the side panel 11 is located as the reference plane, and use the image area including the end of the pointer 3, the reading on the corresponding ruler 4 and its adjacent long scale as the pointer template image. Perform template matching between the pointer template image and the current image to obtain the current pointer image and the integer pixel coordinates of the pointer.

[0088] Specifically, template matching is a computer vision method that detects image portions that match a predetermined template for object localization. In its most basic form, the algorithm compares each source image region to the template, one pixel at a time, a process known as cross-correlation. The result of this process is another image whose pixel values ​​correspond to how similar the template image would be to the source image if inserted at that pixel location. The process involves loading a source image and converting it from RGB to grayscale; loading a template image, storing the width and height of the template, and then initializing a discovery variable to track the region and proportion of the image with the best match. Using the template matching function, the template is detected in the input source image, a threshold is set for the desired output, a rectangle is drawn in the template matching object, and the source image with the marked template region is displayed.

[0089] Step S22: Perform straight line detection on the current pointer image to identify two oblique lines at the end of the pointer. and , calculate the coordinates of the intersection point of the two oblique lines .

[0090] Specifically, after template matching is completed, the oblique line pixel area is roughly clear and can be identified using general line detection technology, and then the intersection point is calculated according to the plane line intersection formula.

[0091] Step S23: Perform optical character detection on the current pointer image to identify the intersection point. The readings of the two nearest long scales are the nearest left scale and the nearest right tick , the corresponding scale vertex coordinates are and .

[0092] Step S25: Calculate the current pointer reading on the corresponding scale:

[0093] The calculation formula is: ;

[0094] in, Mark the distance between adjacent long scale marks on the ruler.

[0095] Through the above scheme, when machine vision is used to read images, digital interpolation technology is used to output sub-pixel level readings. Compared with manual readings that are limited by image resolution and can only obtain pixel level readings, the method provided in this embodiment has higher accuracy in measuring the verticality of components.

[0096] In one embodiment, step S2, identifying the readings of the two pointers 3 on the corresponding scales 4 at the current moment according to the current image, further comprises: step S24, correcting the jitter deviation of the readings based on the plane constraint;

[0097] Step S24, correcting the jitter deviation of the reading based on the plane constraint, includes:

[0098] Step S241: Arrange on both sides of the ruler 4 n Control point targets 8 ( n ≥4), the coordinate system takes a control point target 8 as the origin, and the coordinates of the control point target 8 are pre-calibrated .

[0099] Specifically, the origin of the reference plane coordinate system is set to the center of the control point target 8 in the upper left corner of the field of view, and the horizontal right is x The positive direction of the axis is vertically upward. y Axis positive direction, perpendicular to the target outward z Positive axis direction.

[0100] Step S242: Identify the current time based on the current pointer image The center pixel coordinates of each control point target 8 .

[0101] Based on the collected current pointer image, the control point target 8 is identified using an ellipse recognition algorithm. The ellipse recognition algorithm has high accuracy and can adapt to the center deviation caused by observing the circle from different perspectives.

[0102] Step S243: Constructing an overdetermined equation , solve h ;

[0103] in, ;

[0104] ;

[0105] Step S244: Correction 、 and Pixel coordinates:

[0106] The correction formula is: .

[0107] Through the above scheme, based on the plane constraint correction coordinate, the camera jitter, drift and distortion effects can be corrected, thereby improving environmental adaptability, avoiding interference with visual measurement due to environmental factors, reducing the perspective deviation caused by slight camera jitter and the subsequent scale recognition and reading deviation, and greatly suppressing the deviation.

[0108] In one embodiment, step S3, calculating the verticality of the component according to the current readings of the two pointers on the corresponding scales, includes:

[0109] The calculation formula is: ;

[0110] The initial state is the state before the side panels are fixed to the components. is the verticality of the component, is the initial verticality, measured by the inclinometer when the system is at rest in its initial state; For the current moment The reading of the upper pointer on the upper scale, is the initial reading of the upper pointer on the upper scale; For the current moment The reading of the lower pointer on the lower scale, is the initial reading of the lower pointer on the lower scale; is the distance between the upper and lower scales.

[0111] Through the above scheme, based on the readings of the upper and lower pointers on the two rulers, the system verticality is calculated by the difference between the current reading and the initial reading, and the verticality of the system itself is transferred to the component installation position to obtain the component verticality.

[0112] In the description of this application, it should be noted that the terms "upper" and "lower" and the like indicate orientations or positional relationships based on the orientations or positional relationships shown in the accompanying drawings, and 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, and therefore cannot be understood as a limitation on this application. Unless otherwise clearly specified and limited, the terms "installed", "connected", and "connected" should be understood in a broad sense, for example, it can be a fixed connection, a detachable connection, or an integral connection; it can be a mechanical connection or an electrical connection; it can be a direct connection, or an indirect connection through an intermediate medium, or it can be internal communication between two elements. For those of ordinary skill in the art, the specific meanings of the above terms in this application can be understood according to the specific circumstances.

[0113] It should be noted that, in this application, relational terms such as "first" and "second" are used only to distinguish one entity or operation from another entity or operation, and do not necessarily require or imply any actual relationship or order between these entities or operations. Moreover, the terms "include", "comprise" 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 also includes elements inherent to such process, method, article or device. In the absence of further restrictions, an element defined by the sentence "comprising a ..." does not exclude the presence of other identical elements in the process, method, article or device comprising the element.

[0114] In the description of the embodiments of the present application, unless otherwise specified, “ / ” means or, for example, A / B can mean A or B; “and / or” in the text is merely a description of the association relationship of associated objects, indicating that three relationships may exist, for example, A and / or B can mean: A exists alone, A and B exist at the same time, and B exists alone. In addition, in the description of the embodiments of the present application, “multiple” refers to two or more than two.

[0115] The above are merely specific embodiments of the present application to enable those skilled in the art to understand or implement the present application. Various modifications to these embodiments will be apparent to those skilled in the art, and the general principles defined herein may be implemented in other embodiments without departing from the spirit or scope of the present application. Therefore, the present application will not be limited to the embodiments shown herein, but rather is intended to conform to the widest scope consistent with the principles and novel features of the present application.

Claims

1. A component verticality visual monitoring system based on a vertical line, characterized in that: It includes: A side plate (11) is mounted on one side of the component; A pointer bar (2), the pointer bar (2) being hung on the side panel (11) as a vertical line mark, the pointer bar (2) having two pointers (3), namely an upper pointer (31) and a lower pointer (32); Two scales (4) are fixed to the side plate (11) and are parallel to the horizontal plane, the scales (4) are an upper scale (41) and a lower scale (42), the end of the upper pointer (31) points to the scale of the upper scale (41), and the end of the lower pointer (32) points to the scale of the lower scale (42); A camera (5) is configured to: capture a current image including the two pointers (3) and the corresponding ruler (4); The industrial control computer (6) is configured to: identify the readings of the two pointers (3) on the corresponding scale (4) at the current moment according to the current image, and calculate the verticality of the component; The component verticality visual monitoring system further includes a plurality of control point targets (8) disposed on both sides of the scale (4); the industrial control computer (6) is further configured to: correct the jitter deviation of the reading based on the plane constraint according to the control point targets (8); The industrial control computer (6) recognizes the readings of the two pointers (3) on the corresponding scale (4) at the current moment according to the current image, and calculates the verticality of the component, including: The calculation formula is: ; The initial state is the state before the side panels are fixed to the components. is the verticality of the component, is the initial verticality; For the current moment The reading of the upper pointer on the upper scale, is the initial reading of the upper pointer on the upper scale; For the current moment The reading of the lower pointer on the lower scale, is the initial reading of the lower pointer on the lower scale; is the distance between the upper and lower scales.

2. The component verticality visual monitoring system based on the vertical line according to claim 1 is characterized in that: The component verticality visual monitoring system further comprises a housing (1), wherein the housing (1) comprises the side panels (11), and the housing (1) accommodates the camera (5) and the industrial computer (6).

3. The component verticality visual monitoring system based on the vertical line according to claim 2 is characterized in that: The component verticality visual monitoring system further comprises a fill light (7) arranged in the housing (1), and the housing (1) is a closed housing.

4. The component verticality visual monitoring system based on the vertical line according to claim 1 is characterized in that: There is one camera (5), and its field of view covers the two pointers (3) and the ruler (4); or there are two cameras (5), and their fields of view respectively cover the upper pointer (31) and the upper ruler (41), and the lower pointer (32) and the lower ruler (42).

5. The component verticality visual monitoring system based on the heavy plumb line according to claim 1 is characterized in that: Both ends of the scale (4) are fixed to the side panels (11) via pads (43), so that the scale (4) is located in front of the pointer bar (2).

6. A method for visually monitoring component verticality based on a vertical line, characterized in that: The component verticality visual monitoring system according to any one of claims 1 to 5 is applied, and the method comprises the following steps: Acquire the current image including two pointers and corresponding rulers; Identify the readings of the two pointers on the corresponding scales at the current moment according to the current image; The verticality of the component is calculated based on the readings.

7. The component verticality visual monitoring method based on the vertical line according to claim 6 is characterized in that: The step of identifying the readings of the two pointers on the corresponding scale at the current moment according to the current image includes: Establishing a reference coordinate system with the plane of the side plate as a reference plane, using an image area including the pointer end, the reading corresponding to the scale and the adjacent long scale as a pointer template image, and performing template matching between the pointer template image and the current image to obtain a current pointer image and integer pixel coordinates of the pointer; Perform line detection on the current pointer image to identify the two oblique lines at the end of the pointer and calculate the coordinates of the intersection point of the two oblique lines ; Perform optical character detection on the current pointer image to identify the intersection point The readings of the two nearest long scales are the nearest left scale and the nearest right tick , the corresponding scale vertex coordinates are and ; Calculate the reading of the pointer on the corresponding scale at the current moment: The calculation formula is: ; in, Mark the distance between adjacent long scale marks on the ruler.

8. The component verticality visual monitoring method based on the vertical line according to claim 7 is characterized in that: The identifying, based on the current image, the readings of the two pointers on the corresponding scale at the current moment further comprises: correcting jitter deviation of the readings based on plane constraints; The jitter deviation of the correction reading based on the plane constraint includes: Arrange on both sides of the scale n control point targets, n ≥4, the reference coordinate system takes a control point target as the origin, and the coordinates of the control point target are pre-calibrated ; Identify the current time according to the current pointer image The center pixel coordinates of each control point target ; Constructing overdetermined equations , solve h ; in, ; ； Correction 、 and The pixel coordinates of The correction formula is: .

Images