Line icing thickness monitoring method and device based on machine vision

Abstract

The invention discloses a line icing thickness monitoring method based on machine vision. The method comprises the following steps that 1, an unmanned aerial vehicle carries a camera and a short-wave lamp to take off; 2, the unmanned aerial vehicle flies towards the target power transmission line, and the short-wave lamp has at least two optical signals with different wavelengths; 3, after the reference object has the length and points to the reference object and enters the view of the camera, the camera obtains an icing image; 4, fusing the image Tj of the ice under the optical signals with different wavelengths in the same context to obtain a fused image; and 5, calculating the thickness of the icing according to the ratio of the reference object to the icing. The invention further discloses a line icing thickness monitoring device based on machine vision. The device is simple in structure and reasonable in design, short waves with different wavelengths are adopted to irradiate icing, and the edge characteristics of the icing are increased; images with different wavelengths are fused, so that the utilization rate of image information is improved; the unmanned aerial vehicle carries a reference object, calculation is simple, errors are small, and precision is high.

Description

Technical Field

[0001] The present invention belongs to the technical field of image recognition, and in particular relates to a method and device for monitoring line ice thickness based on machine vision. Background Art

[0002] With the frequent occurrence of severe weather conditions such as ice and snow, haze, and freezing, the ice and snow disasters on transmission lines are irresistible, highly random, and unpredictable. Transmission lines, as important channels for power transmission, are facing major challenges. Icing on transmission lines will cause a variety of serious accidents such as insulator flashover, conductor dancing, line breakage, pole collapse, and power communication interruption, posing a serious threat to the safe and stable operation of the power system and causing huge economic losses. In addition, severe icing on transmission lines is usually accompanied by extremely severe weather conditions such as strong winds and blizzards, which will seriously affect the communication network of the existing icing monitoring system.

[0003] There are two types of ice monitoring at present. One is to measure with a handheld electronic caliper or with an electronic caliper mounted on a drone. Due to the vibration and shaking of the drone during flight, interference from external factors such as airflow and wind, which may cause changes in its flight posture, as well as the measurement errors of the electronic caliper itself, the measurement results may be biased, and even valid measurement data may not be obtained. The other is to identify the length of ice cover through machine vision. Due to the characteristics of the ice cover itself, such as shape, color, and texture, in a complex and changing background environment, machine vision may find it difficult to accurately separate the ice cover from the background, and edge recognition may become blurred, especially in poor lighting conditions, which may lead to the inability to accurately identify the length of the ice cover, and the accuracy of the detection results will be affected.

[0004] Therefore, a monitoring method that can improve the accuracy of ice cover identification is needed. Summary of the invention

[0005] The technical problem to be solved by the present invention is to provide a method and device for monitoring the thickness of line ice cover based on machine vision in view of the deficiencies in the above-mentioned prior art. The method and device have a simple structure and a reasonable design. The method uses shortwaves of different wavelengths to illuminate the ice cover to increase the edge features of the ice cover. The images of different wavelengths are fused to improve the utilization rate of the image information. The drone carries a reference object, which makes the calculation simple, the error small and the accuracy high.

[0006] In order to solve the above technical problems, the technical solution adopted by the present invention is: a line ice thickness monitoring method based on machine vision, characterized in that it includes the following steps:

[0007] Step 1: The drone takes off with the camera and shortwave light;

[0008] Step 2: The drone flies toward the target transmission line, and the camera and the short-wave light start working respectively. The short-wave light has a wavelength range of 390-480nm and at least two different wavelengths of light signals. The at least two different wavelengths of light signals alternately illuminate the ice on the target transmission line at different angles;

[0009] Step 3: The reference object has length and direction. After the reference object enters the camera's field of view, the camera obtains an image of the ice under natural light, denoted as T 1 , the camera obtains images of ice under light signals of different wavelengths, denoted as T j , j is a positive integer not less than 2;

[0010] Step 4: Take image T 1 As a benchmark, the images of ice coverage under different wavelengths of light signals in the same context are fused. j , obtain a fused image;

[0011] Step 5: Calculate the thickness of the ice cover based on the ratio of the reference object to the ice cover.

[0012] The above-mentioned line ice thickness monitoring method based on machine vision is characterized in that the short-wave lamp has at least a purple first light signal and a blue second light signal, the wavelength of the first light signal is 390nm~450nm, and the wavelength of the second light signal is 450nm~480nm.

[0013] The above-mentioned line ice thickness monitoring method based on machine vision is characterized in that the specific method of step 4 is:

[0014] Step 401: Calculate D 1 , D 1 Indicates T 1 The diagonal length of the reference object in the image; calculate D i , D i Indicates T i The diagonal length of the reference object in the image; calculate θ i ,θ i Indicates T i The angle θ between the reference object in the image and the boundary line to which the reference object points i ; 0≤i≤j, i is a positive integer;

[0015] Step 402: D 1 Length based on scaling D i , with θ 1 Angle is the reference rotation θ i , generating T i A reference image of the image;

[0016] Step 403: Calculate fusion weight: based on length Di Calculate the initial weight with wavelength, normalize the initial weight, and get the fusion weight;

[0017] Step 404: Based on the fusion weight and T j The pixel values ​​in the reference image of the image are used to calculate the fused pixels to obtain a fused image.

[0018] The above-mentioned line ice thickness monitoring method based on machine vision is characterized in that: the calculation formula of the initial weight is: in Indicates D 1 To D j The standard deviation of i Indicates T i The wavelength of the light signal when the image is formed, k represents the light signal constant.

[0019] The present invention provides a line ice thickness monitoring device based on machine vision, characterized by: a drone, and a drone field and a remote controller respectively communicating with the drone;

[0020] The bottom of the drone is detachably connected with a mounting plate, one side of the mounting plate is fixedly installed with a main control box, the main control box is provided with a main processor, the main processor and the camera are wiredly connected, the main processor communicates with the drone airport through a wireless image transmission module, the main processor communicates with the slave processor in the remote controller, a switch module is connected between the shortwave light and the main processor, and the switch module is connected to a power module;

[0021] A camera mounting box and a shortwave light mounting bracket are fixedly connected to the other side of the mounting plate. The camera mounting box is rotatably connected to the camera, and the shortwave light mounting bracket is fixedly connected to the shortwave light. The angle between the shortwave light mounting bracket and the mounting plate is adjustable, and also includes a reference object that can enter the camera's field of view.

[0022] The above-mentioned line ice thickness monitoring device based on machine vision is characterized in that: the outer wall of the short-wave lamp is fixedly connected to one end of the fixed rod and one end of the movable rod respectively, the other end of the fixed rod is rotatably sleeved in the through hole of the mounting plate, and the other end of the movable rod can move along the track, and the track is opened on the bottom surface of the mounting plate and the main control box; the rod body of the fixed rod and the rod body of the movable rod are fixedly connected by a connecting rod.

[0023] The above-mentioned line ice thickness monitoring device based on machine vision is characterized in that: the other end of the moving rod is fixedly connected to one end of the first rack through a chain, the first rack is meshed with the first gear, the first gear is sleeved on the output shaft of the first motor, and a first motor drive module is connected between the first motor and the main processor.

[0024] The above-mentioned line ice thickness monitoring device based on machine vision is characterized in that: a second motor is arranged in the camera mounting box, a second motor driving module is installed between the main processor and the second motor, the second motor includes a first power output shaft and a second power output shaft extending out of the camera mounting box, the first power output shaft is sleeved with a first driving gear, the first driving gear is meshed with a first arc-shaped rack, the first arc-shaped rack is arranged in a cavity of a first hanging ear, and the first hanging ear is fixedly connected to the housing of the camera; the second power output shaft is sleeved with a second driving gear, the second driving gear is meshed with a second arc-shaped rack, the second arc-shaped rack is arranged in the cavity of the second hanging ear, and the second hanging ear is fixedly connected to the housing of the camera.

[0025] The above-mentioned line ice thickness monitoring device based on machine vision is characterized in that the reference object is a transparent scale bar set on the camera lens.

[0026] The above-mentioned line ice thickness monitoring device based on machine vision is characterized in that: the reference object is a scale rod with scale lines arranged in front of the camera, the scale rod is connected to one end of the electric lifting rod, and the other end of the electric lifting rod passes through the mounting plate and extends into the main control box.

[0027] Compared with the prior art, the present invention has the following advantages:

[0028] 1. The invention has a simple structure, reasonable design, and is easy to implement and operate.

[0029] 2. The present invention uses short waves of different wavelengths to illuminate the ice, thereby increasing the edge features of the ice, avoiding blurring of the ice edge, and improving the efficiency of ice recognition.

[0030] 2. The present invention uses shortwave irradiation of different wavelengths to cover ice, and fuses images of different wavelengths. By integrating multiple images from different colors and different perspectives, the beneficial information in each channel is extracted to the maximum extent, so that the fused image contains richer information, thereby improving the utilization rate of image information.

[0031] 3. The present invention carries a reference object. Since the length of the reference object is known, the ice thickness can be calculated by using a simple proportional algorithm. The calculation is simple, the error is small, the accuracy is high, and the use effect is good.

[0032] In summary, the present invention has a simple structure and a reasonable design. It uses short waves of different wavelengths to irradiate the ice cover to increase the edge features of the ice cover. It also fuses images of different wavelengths to improve the utilization rate of image information. In addition, the drone carries a reference object, which makes calculation simple, with small errors and high precision.

[0033] The technical solution of the present invention is further described in detail below through the accompanying drawings and embodiments. BRIEF DESCRIPTION OF THE DRAWINGS

[0034] Figure 1 The present invention is a flow chart of the method.

[0035] Figure 2 It is a schematic diagram of the system structure of the present invention.

[0036] Figure 3 Schematic diagram of the structure of the UAV in the first embodiment of the present invention.

[0037] Figure 4 The figure is a schematic diagram of the installation structure of the installation plate, the camera and the shortwave lamp in the first embodiment of the present invention.

[0038] Figure 5 This is a circuit principle block diagram of Embodiment 1 of the present invention.

[0039] Figure 6 The figure is a schematic structural diagram of the shortwave lamp angle adjustment mechanism according to the first embodiment of the present invention.

[0040] Figure 7 The figure is a schematic diagram of the structure of the first hanging ear according to the first embodiment of the present invention.

[0041] Figure 8 A schematic structural diagram of a camera lens according to an embodiment of the present invention.

[0042] Fig. 9 A schematic diagram of the structure of a drone in Embodiment 2 of the present invention.

[0043] Fig.10 The figure is a schematic diagram of the installation structure of the installation plate, the camera, the shortwave lamp and the reference object in the first embodiment of the present invention.

[0044] Fig.11 This is the camera imaging of the first embodiment of the present invention.

[0045] Fig.12 This is the camera imaging of the second embodiment of the present invention.

[0046] Description of reference numerals:

[0047] 1—Camera; 2—Shortwave light; 3—Wireless image transmission module;

[0048] 4—Switch module; 5—Power module; 6—Main processor;

[0049] 7—remote controller; 8—drone airport; 9—ground terminal;

[0050] 10—Mounting plate; 11—Reference object; 111—Electric lifting rod;

[0051] 112—transparent scale bar; 113—camera lens; 12—electric rod;

[0052] 13—first motor driving module; 14—first motor; 141—first gear;

[0053] 142—first rack; 143—connecting rod; 144—track;

[0054] 15—camera mounting box; 151—first mounting ear; 152—first arc-shaped rack;

[0055] 153—cavity; 16—short-wave lamp mounting frame; 161—fixing rod;

[0056] 162—moving rod; 17—second motor; 18—second motor driving module;

[0057] 19—main control box; 20—drone. DETAILED DESCRIPTION

[0058] The method of the present invention is further described in detail below in conjunction with the accompanying drawings and embodiments of the present invention.

[0059] It should be noted that, in the absence of conflict, the embodiments and features in the embodiments of the present application can be combined with each other. The present invention will be described in detail below with reference to the accompanying drawings and in combination with the embodiments.

[0060] It should be noted that the terms used herein are only for describing specific embodiments and are not intended to limit the exemplary embodiments according to the present application. As used herein, unless the context clearly indicates otherwise, the singular form is also intended to include the plural form. In addition, it should be understood that when the terms "comprise" and / or "include" are used in this specification, it indicates the presence of features, steps, operations, devices, components and / or combinations thereof.

[0061] It should be noted that the terms "first", "second", etc. in the specification and claims of the present application and the above-mentioned drawings are used to distinguish similar objects, and are not necessarily used to describe a specific order or sequence. It should be understood that the data used in this way can be interchangeable where appropriate, so that the embodiments of the present application described herein can be implemented in an order other than those illustrated or described herein, for example. In addition, the terms "including" and "having" and any of their variations are intended to cover non-exclusive inclusions, for example, a process, method, system, product or device that includes a series of steps or units is not necessarily limited to those steps or units that are clearly listed, but may include other steps or units that are not clearly listed or inherent to these processes, methods, products or devices.

[0062] For ease of description, spatially relative terms such as "above", "above", "on the upper surface of", "above", etc. may be used here to describe the spatial positional relationship between a device or feature and other devices or features as shown in the figure. It should be understood that spatially relative terms are intended to include different orientations of the device in use or operation in addition to the orientation described in the figure. For example, if the device in the accompanying drawings is inverted, the device described as "above other devices or structures" or "above other devices or structures" will be positioned as "below other devices or structures" or "below other devices or structures". Thus, the exemplary term "above" can include both "above" and "below". The device can also be positioned in other different ways (rotated 90 degrees or in other orientations), and the spatially relative descriptions used here are interpreted accordingly.

[0063] Embodiment 1

[0064] like Figure 1 As shown, a line ice thickness monitoring method based on machine vision of the present invention comprises the following steps:

[0065] Step 1: The drone takes off with camera 1 and shortwave light 2.

[0066] In a possible embodiment, the short-wave lamp 2 has at least a purple first light signal and a blue second light signal, the wavelength of the first light signal is 390nm-450nm, and the wavelength of the second light signal is 450nm-480nm. The wavelength of the first light signal is 410nm; the wavelength of the second light signal is 470nm.

[0067] In another possible embodiment, the short-wave lamp 2 has a first light signal with a wavelength of 410 nm, a second light signal with a wavelength of 440 nm, a third light signal with a wavelength of 460 nm, and a fourth light signal with a wavelength of 480 nm.

[0068] According to the characteristics of Rayleigh scattering, the shorter the wavelength, the stronger the scattering. Therefore, it is difficult for light with a shorter wavelength to penetrate the ice and be scattered. Therefore, blue light is used to illuminate the ice, and the ice looks blue. Therefore, short waves of different wavelengths are used to illuminate the ice to increase the edge features of the ice, avoid blurring the edge of the ice, and improve the efficiency of ice recognition.

[0069] Step 2: The UAV flies toward the target transmission line, and the camera 1 and the shortwave light 2 start working respectively. The shortwave light 2 has a light signal with a wavelength range of 390-480nm and at least two different wavelengths. The at least two different wavelengths of the light signals alternately illuminate the ice on the target transmission line at different angles.

[0070] In actual operation, the flight altitude of the drone 20 will be adjusted according to the height of the line, the severity of the ice coating, and the performance of the drone. In one possible embodiment, the drone flies to a specified altitude and then flies toward the target transmission line. The specified altitude refers to the ground altitude of the transmission line. In one possible embodiment, at the top of a mountain at an altitude of 680m, a small multi-rotor drone is used to cooperate in pre-deicing reconnaissance, that is, ice thickness monitoring. First, the drone 20 rises to 650m above sea level in an open field, and then flies toward the target transmission line.

[0071] Step 3: The reference object has length and orientation. After the reference object enters the field of view of camera 1, camera 1 obtains an image of the ice under natural light, which is recorded as T 1 , camera 1 obtains images of ice under light signals of different wavelengths, denoted as T j , j is a positive integer not less than 2;

[0072] like Fig.11 As shown, in a possible embodiment, the reference object is a transparent scale bar 112 disposed on the camera lens 113. The reference object points to the side where the centimeter scale is higher than the millimeter scale, or an arrow or other mark on the transparent scale bar 112. In a specific implementation, the transparent scale bar 112 is a plastic product, and the transparent scale bar 112 is pasted on the camera lens 113.

[0073] like Fig.12 As shown, in another possible embodiment, the reference object 11 is a scale rod 111 arranged in front of the camera 1, and a scale line is arranged on the scale rod 111. The scale rod 111 is connected to one end of the electric lifting rod 12, and the other end of the electric lifting rod 12 passes through the mounting plate and extends into the main control box 19. The reference object points to the side where the number indicating the scale is located, or an arrow or other mark. In specific implementation, the scale rod 111 is a transparent plastic product, and the scale rod 111 is bonded to the electric lifting rod 12.

[0074] In a possible embodiment, the drone 20 obtains at least 5 photos at the same location, which are 1 photo of ice covered by natural light, 2 photos of ice covered by blue light, and 2 photos of ice covered by purple light. The 2 photos of ice covered by blue light have different angles, and the 2 photos of ice covered by purple light have different angles. It should be noted that in order to achieve different angles, the angle of the camera 1 can be adjusted, and the angle of the short-wave light 2 can also be adjusted.

[0075] When short waves of different wavelengths irradiate the ice, the degree of light in the forward direction and the reverse direction is the same, and the degree of Rayleigh scattering is lowest in the direction perpendicular to the incident light. Therefore, different angles will also affect the coloring effect of the ice.

[0076] It should be noted that the optical signals of different wavelengths are alternated in sequence every 5 seconds.

[0077] Step 4: Fusion of images of ice coverage in the same context under different wavelengths of light signals T i , obtain a fused image; use short waves of different wavelengths to irradiate the ice, and fuse the images of different wavelengths. By integrating multiple images from different colors and different perspectives, the beneficial information in each channel is extracted to the maximum extent, so that the fused image contains richer information, thereby improving the utilization rate of image information.

[0078] Step 5: Calculate the thickness of the ice cover based on the ratio of the reference object 11 and the ice cover.

[0079] In actual use, the thickness of ice d 1 represents the pixel length of ice cover in the thickness direction of the fused image, d 2 Indicates the actual length of the reference object, d 3 Indicates the pixel length of the reference object on the fused image.

[0080] Since the length of the reference object is known and determined, the ice thickness can be calculated using a simple proportional algorithm. The calculation is simple, the error is small, the accuracy is high, and the use effect is good.

[0081] In this embodiment, the specific method of step 4 is:

[0082] Step 401: Calculate D 1 , D 1 Indicates T 1 The diagonal length of the reference object in the image; calculate D i , D i Indicates T i The diagonal length of the reference object in the image; calculate θ i ,θ i Indicates T i The angle θ between the reference object in the image and the boundary line to which the reference object points i ; 0≤i≤j, i is a positive integer. The boundary line pointed by the reference object in the image is fixed, so for each image, the angle θ i In one possible embodiment, D i The length of any given diagonal, or the average length of two diagonals.

[0083] Step 402: D 1 Length based on scaling D i , with θ 1 Angle is the reference rotation θ i , generating T i The reference image of the image.

[0084] In actual use, according to D j With D 1 The ratio of T is used as the scaling factor. j The image is scaled to θ j- θ 1 is the rotation angle T j The image is rotated and the rotated-scaled image is used as T j The reference image of the image.

[0085] Step 403: Calculate fusion weight: based on length D i The initial weight is calculated by the wavelength, and the initial weight is normalized to obtain the fusion weight; the calculation formula of the initial weight is: in Indicates D 1 To D j The standard deviation of .

[0086] Used to adjust the effect of wavelength on weight, λ j Indicates T j The wavelength of the optical signal of the image when it is formed is 390nm to 450nm, and the wavelength of the second optical signal is 450nm to 480nm. k represents the optical signal constant. k = 500. In a possible embodiment, in order to improve the calculation efficiency, the influence of the wavelength on the weight can be removed, and the formula is Calculate weights.

[0087] Step 404: Based on the fusion weight and T j The pixel values ​​in the reference image of the image are used to calculate the fused pixels to obtain a fused image.

[0088] By using the complementary information between different image sources and weighted fusion of pixel values, the information of multiple images is fused together to generate a fused image containing more useful information, thereby improving the signal-to-noise ratio of the fused image to a certain extent, helping to improve the visual effect of the image, making the image clearer and easier to identify. In actual use, the fused image contains richer information and clearer details, so the subsequent ice edge recognition processing based on the fused image will be easier and more accurate.

[0089] Embodiment 2

[0090] like Figures 2 to 8 As shown, a line ice thickness monitoring device based on machine vision of the present invention includes a drone 20, and a drone airport 8 and a remote controller 7 respectively communicating with the drone 20. In actual use, the drone airport 8 is connected to the ground terminal 9 for communication.

[0091] It should be noted that the staff sends control instructions to the drone 20 through the remote control 7, the drone 20 executes the control instructions, carries out camera 1 to collect images of ice cover, and sends the images to the ground terminal 9 through the drone airport 8, and the computer or staff of the ground terminal 9 calculates the thickness of the ice cover.

[0092] The communication between the drone 20 and the remote controller 7 is achieved through radio waves, including a variety of wireless communication technologies, such as radio frequency signals, Bluetooth, Wi-Fi, etc. Among them, the 2.4GHz and 5.8GHz frequency bands are the most commonly used remote control frequencies. The communication between the drone 20 and the drone field 8 adopts a communication protocol to ensure the accurate transmission of data and the accurate execution of instructions. These protocols usually include security measures such as data encapsulation, verification, and encryption to ensure that the drone 20 can accurately receive and execute instructions from the drone field 8. The communication between the drone field 8 and the ground terminal 9 usually involves functions such as data transmission, command issuance, and status monitoring. This communication may be wired or wireless, depending on the application scenario and requirements. In scenarios where long-distance communication or mobile communication is required, wireless communication methods such as 4G / 5G mobile communication networks, Wi-Fi, etc. may be used between the drone 8 and the ground terminal 9.

[0093] The bottom of the drone 20 is detachably connected to a mounting plate 10, and a main control box 19 is fixedly installed on one side of the mounting plate 10. A main processor 6 is arranged in the main control box 19. The main processor 6 and the camera 1 are connected by wire. The main processor 6 communicates with the drone field 8 through the wireless image transmission module 3. The main processor 6 is communicated with the slave processor in the remote control 7. A switch module 4 is connected between the shortwave light 2 and the main processor 6, and the switch module 4 is connected to a power supply module 5.

[0094] The main control box 19 has a hole at the bottom thereof which is in communication with the mounting plate 10 , and the camera mounting box 15 has a hole at the bottom thereof which is in communication with the mounting plate 10 .

[0095] The image captured by the camera 1 is transmitted to the main processor 6 through a wired connection, and the main processor 6 communicates with the drone airport 8 through the wireless image transmission module 3. The wireless image transmission module 3 includes a chip of model INTQ6600. INTQ6600 is a wireless transmission and image encoding and decoding module, which is divided into two parts: the airborne end and the ground end. The airborne end of INTQ6600 is mounted in the main control box 19 of the drone 20, and the ground end of INTQ6600 is set in the drone airport 8, which is used for the transmission and encoding and decoding of image data between the drone 20 and the drone airport 8. In actual use, the communication distance between the drone 20 and the drone airport 8 is less than or equal to 10km. Wireless frequency band: 1430Mhz-1444Mhz.

[0096] A camera mounting box 15 and a shortwave lamp mounting bracket 16 are fixedly connected to the other side of the mounting plate 10. The camera mounting box 15 is rotatably connected to the camera 1, and the shortwave lamp mounting bracket 16 is fixedly connected to the shortwave lamp 2. The angle between the shortwave lamp mounting bracket 16 and the mounting plate 10 is adjustable, and also includes a reference object that can enter the viewing angle of the camera 1.

[0097] In actual use, the short-wave lamp 2 has at least a blue LED lamp bead and a purple LED lamp bead, and the blue LED lamp bead and the purple LED lamp bead work alternately. It should be noted that the blue LED lamp bead and the purple LED lamp bead are both cold-colored LED lamp beads. The short-wave lamp 2 has at least a purple first light signal and a blue second light signal, the wavelength of the first light signal is 390nm to 450nm, and the wavelength of the second light signal is 450nm to 480nm. The wavelength of the first light signal is 410nm; the wavelength of the second light signal is 470nm.

[0098] In actual use, the camera mounting box 15 is rotatably connected to the camera 1, so the shooting angle of the camera 1 can be adjusted. The shortwave lamp mounting frame 16 is fixedly connected to the shortwave lamp 2, but the angle between the shortwave lamp mounting frame 16 and the mounting plate 10 is adjustable, so the shortwave lamp mounting frame 16 can drive the shortwave lamp 2 to adjust the angle.

[0099] In this embodiment, the outer wall of the short-wave lamp 2 is fixedly connected to one end of the fixed rod 161 and one end of the movable rod 162 respectively. The other end of the fixed rod 161 is rotatably sleeved in the through hole of the mounting plate 10, and the other end of the movable rod 162 can move along the track 144. The track 144 is opened on the bottom surface of the mounting plate 10 and the main control box 19; the rod body of the fixed rod 161 and the rod body of the movable rod 162 are fixedly connected by the connecting rod 143.

[0100] In actual use, a rotating bearing is provided in the through hole of the mounting plate 10, and the other end of the fixing rod 161 extends into the rotating bearing and is rotatably connected to the mounting plate 10. The moving rod 162 can move along the track 144, thereby driving the short-wave lamp 2 to change position and angle.

[0101] In this embodiment, the other end of the moving rod 162 is fixedly connected to one end of the first rack 142 through a chain, the first rack 142 is meshed with the first gear 141, the first gear 141 is sleeved on the output shaft of the first motor 14, and the first motor driving module 13 is connected between the first motor 14 and the main processor 6. In actual use, the first motor 14 drives the first gear 141 to rotate, the first gear 141 pushes the first rack 142 to move, the first rack 142 and the moving rod 162 are fixedly connected through a chain, and the first rack 142 is used to push the moving rod 162 to move along the track 144.

[0102] In this embodiment, a second motor 17 is arranged in the camera mounting box 15, and a second motor driving module 18 is installed between the main processor 6 and the second motor 17. The second motor 17 includes a first power output shaft and a second power output shaft extending out of the camera mounting box 15. The first power output shaft is sleeved with a first driving gear, which is engaged with a first arc-shaped rack 152. The first arc-shaped rack is arranged in a cavity 153 of a first hanging ear 151, and the first hanging ear 151 is fixedly connected to the housing of the camera 1; the second power output shaft is sleeved with a second driving gear, which is engaged with a second arc-shaped rack, and the second arc-shaped rack is arranged in the cavity of the second hanging ear, and the second hanging ear is fixedly connected to the housing of the camera 1.

[0103] In actual use, the second motor 17 drives the first driving gear and the second driving gear to rotate, and the first driving gear drives the first arc-shaped rack 152 to move, thereby changing the angle of the first hanging ear 151, and the first hanging ear 151 drives the camera housing to move, thereby changing the position and angle of the camera 1.

[0104] In this embodiment, the reference object 11 is a transparent scale bar 112 disposed on the camera lens 113. In a specific implementation, the transparent scale bar 112 is a plastic product, and the transparent scale bar 112 is pasted on the camera lens 113.

[0105] Embodiment 3

[0106] like Fig. 9 and Fig.10 As shown, different from the second embodiment, in this embodiment, the reference object 11 is a scale rod 111 with scale lines arranged in front of the camera 1, the scale rod 111 is connected to one end of the electric lifting rod 12, and the other end of the electric lifting rod 12 passes through the mounting plate and extends into the main control box 19. In specific implementation, the scale rod 111 is a transparent plastic product, and the scale rod 111 is bonded to the electric lifting rod 12. The electric lifting rod 12 is controlled by the main processor 6 in the main control box 19.

[0107] The above description is only an embodiment of the present invention and does not limit the present invention in any way. Any simple modification, change and equivalent structural change made to the above embodiment based on the technical essence of the present invention still falls within the protection scope of the technical solution of the present invention.

Claims

1. A line ice thickness monitoring method based on machine vision, characterized in that: The following steps are involved: Step 1: The drone takes off with the camera (1) and the shortwave light (2); Step 2: The drone flies toward the target transmission line, and the camera (1) and the shortwave light (2) start working respectively. The shortwave light (2) has a light signal with a wavelength range of 390-480nm and at least two different wavelengths. The at least two different wavelengths of the light signals alternately illuminate the ice on the target transmission line at different angles. Step 3: The reference object has a length and a direction. After the reference object enters the field of view of the camera (1), the camera (1) obtains an image of the ice under natural light, denoted as T1. The camera (1) obtains images of the ice under light signals of different wavelengths, denoted as T j , j is a positive integer not less than 2; Step 4: Taking image T1 as the benchmark, fuse the images T1 of ice coverage under different wavelengths of light signals in the same context j , obtain the fused image; Step 5: Calculate the thickness of the ice cover based on the ratio of the reference object (11) to the ice cover.

2. A line ice thickness monitoring method based on machine vision according to claim 1, characterized in that: The short-wave lamp (2) has at least a purple first light signal and a blue second light signal, the wavelength of the first light signal is 390nm-450nm, and the wavelength of the second light signal is 450nm-480nm.

3. A line ice thickness monitoring method based on machine vision according to claim 1, characterized in that: The specific method of step four is: Step 401: Calculate D1, where D1 represents the diagonal length of the reference object in the T1 image; Calculate D i , D i Indicates T i The diagonal length of the reference object in the image; calculate θ i ,θ i Indicates T i The angle θ between the reference object in the image and the boundary line to which the reference object points i ; 0≤i≤j, i is a positive integer; Step 402: Scale D based on the length of D1 i , rotate θ based on angle θ1 i , generating T i A reference image of the image; Step 403: Calculate fusion weight: based on length D i Calculate the initial weight with wavelength, normalize the initial weight, and get the fusion weight; Step 404: Based on the fusion weight and T j The pixel values ​​in the reference image of the image are used to calculate the fused pixels to obtain a fused image.

4. A line ice thickness monitoring method based on machine vision according to claim 1, characterized in that: The calculation formula for the initial weight is: in Indicates D1 to D j The standard deviation of i Indicates T i The wavelength of the light signal when the image is formed, k represents the light signal constant.

5. A line ice thickness monitoring device based on machine vision, characterized in that: A drone (20), and a drone field (8) and a remote controller (7) respectively communicating with the drone (20); The bottom of the drone (20) is detachably connected to a mounting plate (10), a main control box (19) is fixedly mounted on one side of the mounting plate (10), a main processor (6) is arranged in the main control box (19), the main processor (6) and the camera (1) are connected by wire, the main processor (6) communicates with the drone field (8) through a wireless image transmission module (3), the main processor (6) is connected to a slave processor in a remote controller (7), a switch module (4) is connected between the short-wave light (2) and the main processor (6), and the switch module (4) is connected to a power module (5); The other side of the mounting plate (10) is respectively fixedly connected with a camera mounting box (15) and a shortwave lamp mounting frame (16); the camera mounting box (15) is rotatably connected to the camera (1); the shortwave lamp mounting frame (16) is fixedly connected to the shortwave lamp (2); the angle between the shortwave lamp mounting frame (16) and the mounting plate (10) is adjustable; and a reference object that can enter the viewing angle of the camera (1) is also included.

6. A machine vision-based line ice thickness monitoring device according to claim 5, characterized in that: The outer wall of the short-wave lamp (2) is fixedly connected to one end of a fixed rod (161) and one end of a movable rod (162), respectively; the other end of the fixed rod (161) is rotatably sleeved in a through hole of a mounting plate (10); the other end of the movable rod (162) can move along a track (144); the track (144) is provided on the bottom surface of the mounting plate (10) and the main control box (19); the rod body of the fixed rod (161) and the rod body of the movable rod (162) are fixedly connected via a connecting rod (143).

7. A machine vision-based line ice thickness monitoring device according to claim 6, characterized in that: The other end of the moving rod (162) is fixedly connected to one end of the first rack (142) via a chain, the first rack (142) is meshed with the first gear (141), the first gear (141) is sleeved on the output shaft of the first motor (14), and a first motor driving module (13) is connected between the first motor (14) and the main processor (6).

8. A machine vision-based line ice thickness monitoring device according to claim 5, characterized in that: A second motor (17) is arranged in the camera mounting box (15), a second motor driving module (18) is installed between the main processor (6) and the second motor (17), the second motor (17) comprises a first power output shaft and a second power output shaft extending out of the camera mounting box (15), the first power output shaft is sleeved with a first driving gear, the first driving gear is meshed with a first arc-shaped rack (152), the first arc-shaped rack is arranged in a cavity (153) of a first hanging ear (151), and the first hanging ear (151) is fixedly connected to the housing of the camera (1); a second driving gear is sleeved with the second power output shaft, the second driving gear is meshed with a second arc-shaped rack, the second arc-shaped rack is arranged in the cavity of the second hanging ear, and the second hanging ear is fixedly connected to the housing of the camera (1).

9. A machine vision-based line ice thickness monitoring device according to claim 5, characterized in that: The reference object (11) is a transparent scale bar (112) arranged on the camera lens (113).

10. A line ice thickness monitoring device based on machine vision according to claim 5, characterized in that: The reference object (11) is a scale rod (111) provided with scale lines and arranged in front of the camera (1). The scale rod (111) is connected to one end of the electric lifting rod (12). The other end of the electric lifting rod (12) passes through the mounting plate and extends into the main control box (19).

Images